mirror of
https://github.com/prometheus-community/windows_exporter.git
synced 2026-02-08 22:16:38 +00:00
Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
d9404c6cc2 |
@@ -1,6 +0,0 @@
|
||||
root = true
|
||||
|
||||
[*.wxs]
|
||||
|
||||
indent_style = space
|
||||
indent_size = 2
|
||||
3
.gitattributes
vendored
3
.gitattributes
vendored
@@ -1,3 +0,0 @@
|
||||
*.go text eol=lf
|
||||
*.sh text eol=lf
|
||||
Makefile text eol=lf
|
||||
1
.github/CODEOWNERS
vendored
1
.github/CODEOWNERS
vendored
@@ -1 +0,0 @@
|
||||
* @prometheus-community/windows_exporter-reviewers
|
||||
71
.github/ISSUE_TEMPLATE/bug_report.yaml
vendored
71
.github/ISSUE_TEMPLATE/bug_report.yaml
vendored
@@ -1,71 +0,0 @@
|
||||
name: 🐞 Bug
|
||||
description: Something is not working as indended.
|
||||
labels: [ 🐞 bug ]
|
||||
body:
|
||||
- type: markdown
|
||||
attributes:
|
||||
value: Thanks for taking the time to fill out this bug report!
|
||||
|
||||
- type: textarea
|
||||
attributes:
|
||||
label: Current Behavior
|
||||
description: A concise description of what you're experiencing.
|
||||
placeholder: |
|
||||
When I do <X>, <Y> happens and I see the error message attached below:
|
||||
```...```
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
attributes:
|
||||
label: Expected Behavior
|
||||
description: A concise description of what you expected to happen.
|
||||
placeholder: When I do <X>, <Z> should happen instead.
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
attributes:
|
||||
label: Steps To Reproduce
|
||||
description: Steps to reproduce the behavior.
|
||||
placeholder: |
|
||||
1. In this environment...
|
||||
2. With this config...
|
||||
3. Run '...'
|
||||
4. See error...
|
||||
render: Markdown
|
||||
validations:
|
||||
required: false
|
||||
|
||||
- type: textarea
|
||||
attributes:
|
||||
label: Environment
|
||||
description: |
|
||||
examples:
|
||||
- **windows_exporter Version**: 0.26
|
||||
- **Windows Server Version**: 2019
|
||||
value: |
|
||||
- windows_exporter Version:
|
||||
- Windows Server Version:
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
attributes:
|
||||
label: windows_exporter logs
|
||||
description: |
|
||||
Log of windows_exporter.
|
||||
⚠️ Without proving logs, we unable to assist here. ⚠️
|
||||
render: shell
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
attributes:
|
||||
label: Anything else?
|
||||
description: |
|
||||
Links? References? Anything that will give us more context about the issue you are encountering!
|
||||
|
||||
Tip: You can attach images or log files by clicking this area to highlight it and then dragging files in.
|
||||
validations:
|
||||
required: false
|
||||
1
.github/ISSUE_TEMPLATE/config.yml
vendored
1
.github/ISSUE_TEMPLATE/config.yml
vendored
@@ -1 +0,0 @@
|
||||
blank_issues_enabled: false
|
||||
41
.github/ISSUE_TEMPLATE/enhancement.yaml
vendored
41
.github/ISSUE_TEMPLATE/enhancement.yaml
vendored
@@ -1,41 +0,0 @@
|
||||
name: ✨ Enhancement / Feature / Task
|
||||
description: Some feature is missing or incomplete.
|
||||
labels: [ ✨ enhancement ]
|
||||
body:
|
||||
- type: textarea
|
||||
attributes:
|
||||
label: Problem Statement
|
||||
description: Without specifying a solution, describe what the project is missing today.
|
||||
placeholder: |
|
||||
The rotating project logo has a fixed size and color.
|
||||
There is no way to make it larger and more shiny.
|
||||
validations:
|
||||
required: false
|
||||
- type: textarea
|
||||
attributes:
|
||||
label: Proposed Solution
|
||||
description: Describe the proposed solution to the problem above.
|
||||
placeholder: |
|
||||
- Implement 2 new flags CLI: ```--logo-color=FFD700``` and ```--logo-size=100```
|
||||
- Let these flags control the size of the rotating project logo.
|
||||
validations:
|
||||
required: false
|
||||
- type: textarea
|
||||
attributes:
|
||||
label: Additional information
|
||||
placeholder: |
|
||||
We considered adjusting the logo size to the phase of the moon, but there was no
|
||||
reliable data source in air-gapped environments.
|
||||
validations:
|
||||
required: false
|
||||
- type: textarea
|
||||
attributes:
|
||||
label: Acceptance Criteria
|
||||
placeholder: |
|
||||
- [ ] As a user, I can control the size of the rotating logo using a CLI flag.
|
||||
- [ ] As a user, I can control the color of the rotating logo using a CLI flag.
|
||||
- [ ] Defaults are reasonably set.
|
||||
- [ ] New settings are appropriately documented.
|
||||
- [ ] No breaking change for current users of the rotating logo feature.
|
||||
validations:
|
||||
required: false
|
||||
27
.github/ISSUE_TEMPLATE/question.yaml
vendored
27
.github/ISSUE_TEMPLATE/question.yaml
vendored
@@ -1,27 +0,0 @@
|
||||
name: ❓ Question
|
||||
description: Something is not clear.
|
||||
labels: [ ❓ question ]
|
||||
body:
|
||||
- type: textarea
|
||||
attributes:
|
||||
label: Problem Statement
|
||||
description: Without specifying a solution, describe what the project is missing today.
|
||||
placeholder: |
|
||||
The rotating project logo has a fixed size and color.
|
||||
There is no way to make it larger and more shiny.
|
||||
validations:
|
||||
required: false
|
||||
|
||||
- type: textarea
|
||||
attributes:
|
||||
label: Environment
|
||||
description: |
|
||||
examples:
|
||||
- **windows_exporter Version**: 0.26
|
||||
- **Windows Server Version**: 2019
|
||||
value: |
|
||||
- windows_exporter Version:
|
||||
- Windows Server Version:
|
||||
validations:
|
||||
required: true
|
||||
|
||||
15
.github/dependabot.yml
vendored
15
.github/dependabot.yml
vendored
@@ -1,15 +0,0 @@
|
||||
version: 2
|
||||
updates:
|
||||
- package-ecosystem: "github-actions"
|
||||
directory: "/"
|
||||
schedule:
|
||||
interval: "weekly"
|
||||
labels:
|
||||
- "🛠️ dependencies"
|
||||
|
||||
- package-ecosystem: "gomod"
|
||||
directory: "/"
|
||||
schedule:
|
||||
interval: "weekly"
|
||||
labels:
|
||||
- "🛠️ dependencies"
|
||||
23
.github/release.yml
vendored
23
.github/release.yml
vendored
@@ -1,23 +0,0 @@
|
||||
changelog:
|
||||
exclude:
|
||||
labels:
|
||||
- chore
|
||||
categories:
|
||||
- title: 💥 Breaking Changes
|
||||
labels:
|
||||
- 💥 breaking-change
|
||||
- title: ✨ Exciting New Features
|
||||
labels:
|
||||
- ✨ enhancement
|
||||
- title: 🐞 Bug Fixes
|
||||
labels:
|
||||
- 🐞 bug
|
||||
- title: 🛠️ Dependencies
|
||||
labels:
|
||||
- 🛠️ dependencies
|
||||
- title: 📖 Documentation
|
||||
labels:
|
||||
- 📖 docs
|
||||
- title: Other Changes
|
||||
labels:
|
||||
- "*"
|
||||
57
.github/workflows/container_description.yml
vendored
57
.github/workflows/container_description.yml
vendored
@@ -1,57 +0,0 @@
|
||||
---
|
||||
name: Push README to Docker Hub
|
||||
on:
|
||||
push:
|
||||
paths:
|
||||
- "README.md"
|
||||
- "README-containers.md"
|
||||
- ".github/workflows/container_description.yml"
|
||||
branches: [ main, master ]
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
PushDockerHubReadme:
|
||||
runs-on: ubuntu-latest
|
||||
name: Push README to Docker Hub
|
||||
if: github.repository_owner == 'prometheus' || github.repository_owner == 'prometheus-community' # Don't run this workflow on forks.
|
||||
steps:
|
||||
- name: git checkout
|
||||
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
|
||||
- name: Set docker hub repo name
|
||||
run: echo "DOCKER_REPO_NAME=$(make docker-repo-name)" >> $GITHUB_ENV
|
||||
- name: Push README to Dockerhub
|
||||
uses: christian-korneck/update-container-description-action@d36005551adeaba9698d8d67a296bd16fa91f8e8 # v1
|
||||
env:
|
||||
DOCKER_USER: ${{ secrets.DOCKER_HUB_LOGIN }}
|
||||
DOCKER_PASS: ${{ secrets.DOCKER_HUB_PASSWORD }}
|
||||
with:
|
||||
destination_container_repo: ${{ env.DOCKER_REPO_NAME }}
|
||||
provider: dockerhub
|
||||
short_description: ${{ env.DOCKER_REPO_NAME }}
|
||||
# Empty string results in README-containers.md being pushed if it
|
||||
# exists. Otherwise, README.md is pushed.
|
||||
readme_file: ''
|
||||
|
||||
PushQuayIoReadme:
|
||||
runs-on: ubuntu-latest
|
||||
name: Push README to quay.io
|
||||
if: github.repository_owner == 'prometheus' || github.repository_owner == 'prometheus-community' # Don't run this workflow on forks.
|
||||
steps:
|
||||
- name: git checkout
|
||||
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
|
||||
- name: Set quay.io org name
|
||||
run: echo "DOCKER_REPO=$(echo quay.io/${GITHUB_REPOSITORY_OWNER} | tr -d '-')" >> $GITHUB_ENV
|
||||
- name: Set quay.io repo name
|
||||
run: echo "DOCKER_REPO_NAME=$(make docker-repo-name)" >> $GITHUB_ENV
|
||||
- name: Push README to quay.io
|
||||
uses: christian-korneck/update-container-description-action@d36005551adeaba9698d8d67a296bd16fa91f8e8 # v1
|
||||
env:
|
||||
DOCKER_APIKEY: ${{ secrets.QUAY_IO_API_TOKEN }}
|
||||
with:
|
||||
destination_container_repo: ${{ env.DOCKER_REPO_NAME }}
|
||||
provider: quay
|
||||
# Empty string results in README-containers.md being pushed if it
|
||||
# exists. Otherwise, README.md is pushed.
|
||||
readme_file: ''
|
||||
104
.github/workflows/lint.yml
vendored
104
.github/workflows/lint.yml
vendored
@@ -1,104 +0,0 @@
|
||||
name: Linting
|
||||
|
||||
# Trigger on pull requests and pushes to master branch where Go-related files
|
||||
# have been changed.
|
||||
on:
|
||||
push:
|
||||
paths:
|
||||
- "go.mod"
|
||||
- "go.sum"
|
||||
- "**.go"
|
||||
- ".github/workflows/lint.yml"
|
||||
- "tools/e2e-output.txt"
|
||||
branches:
|
||||
- master
|
||||
pull_request:
|
||||
paths:
|
||||
- "go.mod"
|
||||
- "go.sum"
|
||||
- "**.go"
|
||||
- ".github/workflows/lint.yml"
|
||||
- "tools/e2e-output.txt"
|
||||
branches:
|
||||
- master
|
||||
|
||||
env:
|
||||
PROMU_VER: '0.14.0'
|
||||
PROMTOOL_VER: '2.43.0'
|
||||
|
||||
jobs:
|
||||
test:
|
||||
runs-on: windows-2019
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-go@v5
|
||||
with:
|
||||
go-version-file: 'go.mod'
|
||||
|
||||
- name: Test
|
||||
run: make test
|
||||
|
||||
- name: Install e2e deps
|
||||
run: |
|
||||
Invoke-WebRequest -Uri https://github.com/prometheus/promu/releases/download/v$($Env:PROMU_VER)/promu-$($Env:PROMU_VER).windows-amd64.zip -OutFile promu-$($Env:PROMU_VER).windows-amd64.zip
|
||||
Expand-Archive -Path promu-$($Env:PROMU_VER).windows-amd64.zip -DestinationPath .
|
||||
Copy-Item -Path promu-$($Env:PROMU_VER).windows-amd64\promu.exe -Destination "$(go env GOPATH)\bin"
|
||||
|
||||
# GOPATH\bin dir must be appended to PATH else the `promu` command won't be found
|
||||
echo "$(go env GOPATH)\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||
|
||||
- name: e2e Test
|
||||
run: make e2e-test
|
||||
|
||||
promtool:
|
||||
runs-on: windows-2019
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-go@v5
|
||||
with:
|
||||
go-version-file: 'go.mod'
|
||||
|
||||
- name: Install promtool
|
||||
run: |
|
||||
Invoke-WebRequest -Uri https://github.com/prometheus/prometheus/releases/download/v$($Env:PROMTOOL_VER)/prometheus-$($Env:PROMTOOL_VER).windows-amd64.zip -OutFile prometheus-$($Env:PROMTOOL_VER).windows-amd64.zip
|
||||
Expand-Archive -Path prometheus-$($Env:PROMTOOL_VER).windows-amd64.zip -DestinationPath .
|
||||
Copy-Item -Path prometheus-$($Env:PROMTOOL_VER).windows-amd64\promtool.exe -Destination "$(go env GOPATH)\bin"
|
||||
|
||||
Invoke-WebRequest -Uri https://github.com/prometheus/promu/releases/download/v$($Env:PROMU_VER)/promu-$($Env:PROMU_VER).windows-amd64.zip -OutFile promu-$($Env:PROMU_VER).windows-amd64.zip
|
||||
Expand-Archive -Path promu-$($Env:PROMU_VER).windows-amd64.zip -DestinationPath .
|
||||
Copy-Item -Path promu-$($Env:PROMU_VER).windows-amd64\promu.exe -Destination "$(go env GOPATH)\bin"
|
||||
|
||||
# GOPATH\bin dir must be appended to PATH else the `promu` command won't be found
|
||||
echo "$(go env GOPATH)\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||
|
||||
- name: Promtool
|
||||
run: make promtool
|
||||
|
||||
- name: Upload windows_exporter.exe
|
||||
uses: actions/upload-artifact@v4
|
||||
if: always()
|
||||
with:
|
||||
name: windows_exporter.amd64.exe
|
||||
path: 'windows_exporter.exe'
|
||||
retention-days: 7
|
||||
if-no-files-found: error
|
||||
|
||||
lint:
|
||||
runs-on: windows-2022
|
||||
steps:
|
||||
# `gofmt` linter run by golangci-lint fails on CRLF line endings (the default for Windows)
|
||||
- name: Set git to use LF
|
||||
run: |
|
||||
git config --global core.autocrlf false
|
||||
git config --global core.eol lf
|
||||
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-go@v5
|
||||
with:
|
||||
go-version-file: 'go.mod'
|
||||
|
||||
- name: golangci-lint
|
||||
uses: golangci/golangci-lint-action@v6
|
||||
with:
|
||||
version: v1.59
|
||||
args: "--timeout=5m"
|
||||
48
.github/workflows/pr-check.yaml
vendored
48
.github/workflows/pr-check.yaml
vendored
@@ -1,48 +0,0 @@
|
||||
name: Validate Pull Request
|
||||
on:
|
||||
pull_request:
|
||||
types:
|
||||
- opened
|
||||
- reopened
|
||||
- synchronize
|
||||
- labeled
|
||||
- unlabeled
|
||||
|
||||
jobs:
|
||||
required-labels-missing:
|
||||
name: required labels missing
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: check
|
||||
if: >-
|
||||
!contains(github.event.pull_request.labels.*.name, '💥 breaking-change')
|
||||
&& !contains(github.event.pull_request.labels.*.name, '✨ enhancement')
|
||||
&& !contains(github.event.pull_request.labels.*.name, '🐞 bug')
|
||||
&& !contains(github.event.pull_request.labels.*.name, '📖 docs')
|
||||
&& !contains(github.event.pull_request.labels.*.name, 'chore')
|
||||
&& !contains(github.event.pull_request.labels.*.name, '🛠️ dependencies')
|
||||
run: >-
|
||||
echo One of the following labels is missing on this PR:
|
||||
breaking-change
|
||||
enhancement
|
||||
bug
|
||||
docs
|
||||
chore
|
||||
&& exit 1
|
||||
title:
|
||||
name: check title prefix
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: check
|
||||
run: |
|
||||
PR_TITLE_PREFIX=$(echo "$PR_TITLE" | cut -d':' -f1)
|
||||
if [[ -d "pkg/collector/$PR_TITLE_PREFIX" ]] || [[ -d "$PR_TITLE_PREFIX" ]] || [[ "$PR_TITLE_PREFIX" == "chore" ]] || [[ "$PR_TITLE_PREFIX" == "chore(deps)" ]] || [[ "$PR_TITLE_PREFIX" == "*" ]] || [[ "$PR_TITLE_PREFIX" == "Synchronize common files from prometheus/prometheus" ]]; then
|
||||
exit 0
|
||||
fi
|
||||
|
||||
echo "PR title must start with an name of an collector package"
|
||||
echo "Example: 'logical_disk: description'"
|
||||
exit 1
|
||||
env:
|
||||
PR_TITLE: ${{ github.event.pull_request.title }}
|
||||
165
.github/workflows/release.yml
vendored
165
.github/workflows/release.yml
vendored
@@ -1,165 +0,0 @@
|
||||
name: Releases
|
||||
|
||||
# Trigger on releases.
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- master
|
||||
pull_request:
|
||||
release:
|
||||
types:
|
||||
- published
|
||||
- edited
|
||||
|
||||
permissions:
|
||||
contents: write
|
||||
packages: write
|
||||
|
||||
env:
|
||||
PROMU_VER: '0.14.0'
|
||||
|
||||
jobs:
|
||||
build:
|
||||
runs-on: windows-2022
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
# fetch-depth required for gitversion in `Build` step
|
||||
fetch-depth: 0
|
||||
|
||||
- uses: actions/setup-go@v5
|
||||
with:
|
||||
go-version-file: 'go.mod'
|
||||
|
||||
# https://github.com/pl4nty/Windows-Containers/blob/Main/helpful_tools/Install-BuildKit-GitHubActions/workflow.yaml
|
||||
- name: Setup containerd
|
||||
run: |
|
||||
$version = "1.7.20"
|
||||
curl.exe -L https://github.com/containerd/containerd/releases/download/v$version/containerd-$version-windows-amd64.tar.gz -o containerd.tar.gz
|
||||
tar.exe xvf containerd.tar.gz
|
||||
.\bin\containerd.exe --register-service
|
||||
Start-Service containerd
|
||||
- name: Setup BuildKit
|
||||
run: |
|
||||
$version = "v0.15.0"
|
||||
curl.exe -L https://github.com/moby/buildkit/releases/download/$version/buildkit-$version.windows-amd64.tar.gz -o buildkit.tar.gz
|
||||
tar.exe xvf buildkit.tar.gz
|
||||
|
||||
.\bin\buildkitd.exe --register-service
|
||||
Start-Service buildkitd
|
||||
- name: Setup Docker Buildx
|
||||
run: |
|
||||
$version = "v0.16.1"
|
||||
curl.exe -L https://github.com/docker/buildx/releases/download/$version/buildx-$version.windows-amd64.exe -o $env:ProgramData\Docker\cli-plugins\docker-buildx.exe
|
||||
- uses: docker/setup-buildx-action@v3
|
||||
with:
|
||||
driver: remote
|
||||
endpoint: npipe:////./pipe/buildkitd
|
||||
|
||||
- name: Install WiX
|
||||
run: dotnet tool install --global wix
|
||||
|
||||
- name: Install WiX extensions
|
||||
run: |
|
||||
wix extension add -g WixToolset.Util.wixext
|
||||
wix extension add -g WixToolset.Firewall.wixext
|
||||
|
||||
- name: Install Build deps
|
||||
run: |
|
||||
Invoke-WebRequest -Uri https://github.com/prometheus/promu/releases/download/v$($Env:PROMU_VER)/promu-$($Env:PROMU_VER).windows-amd64.zip -OutFile promu-$($Env:PROMU_VER).windows-amd64.zip
|
||||
Expand-Archive -Path promu-$($Env:PROMU_VER).windows-amd64.zip -DestinationPath .
|
||||
Copy-Item -Path promu-$($Env:PROMU_VER).windows-amd64\promu.exe -Destination "$(go env GOPATH)\bin"
|
||||
|
||||
# GOPATH\bin dir must be added to PATH else the `promu` commands won't be found
|
||||
echo "$(go env GOPATH)\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||
|
||||
- name: Build
|
||||
run: |
|
||||
$ErrorActionPreference = "Stop"
|
||||
|
||||
$Version = git describe --tags --always
|
||||
$Version = $Version -replace 'v', ''
|
||||
# '+' symbols are invalid characters in image tags
|
||||
$Version = $Version -replace '\+', '_'
|
||||
$Version | Set-Content VERSION -PassThru
|
||||
|
||||
make build-all
|
||||
|
||||
# GH requires all files to have different names, so add version/arch to differentiate
|
||||
foreach($Arch in "amd64", "arm64") {
|
||||
Move-Item output\$Arch\windows_exporter.exe output\windows_exporter-$Version-$Arch.exe
|
||||
}
|
||||
|
||||
Get-ChildItem -Path output
|
||||
|
||||
- name: Upload Artifacts
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: windows_exporter_binaries
|
||||
path: output\windows_exporter-*.exe
|
||||
|
||||
- name: Build Release Artifacts
|
||||
run: |
|
||||
$ErrorActionPreference = "Stop"
|
||||
$Version = Get-Content VERSION
|
||||
|
||||
foreach($Arch in "amd64", "arm64") {
|
||||
Write-Host "Building windows_exporter $Version msi for $Arch"
|
||||
.\installer\build.ps1 -PathToExecutable .\output\windows_exporter-$Version-$Arch.exe -Version $Version -Arch "$Arch"
|
||||
}
|
||||
|
||||
Move-Item installer\*.msi output\
|
||||
Get-ChildItem -Path output\
|
||||
|
||||
promu checksum output\
|
||||
|
||||
- name: Build Docker Artifacts
|
||||
run: make build-all
|
||||
env:
|
||||
VERSION: >-
|
||||
${{
|
||||
startsWith(github.ref, 'refs/tags/') && 'latest' ||
|
||||
(
|
||||
github.event_name == 'pull_request' && format('pr-{0}', github.event.number) || github.ref_name
|
||||
)
|
||||
}}
|
||||
|
||||
- name: Login to Docker Hub
|
||||
if: ${{ github.event_name != 'pull_request' }}
|
||||
uses: docker/login-action@v3
|
||||
with:
|
||||
username: ${{ secrets.DOCKER_HUB_LOGIN }}
|
||||
password: ${{ secrets.DOCKER_HUB_PASSWORD }}
|
||||
|
||||
#- name: Login to quay.io
|
||||
# if: ${{ github.event_name != 'pull_request' }}
|
||||
# uses: docker/login-action@v3
|
||||
# with:
|
||||
# registry: quay.io
|
||||
# username: 'robot'
|
||||
# password: ${{ secrets.QUAY_IO_API_TOKEN }}
|
||||
|
||||
- name: Login to GitHub container registry
|
||||
if: ${{ github.event_name != 'pull_request' }}
|
||||
uses: docker/login-action@v3
|
||||
with:
|
||||
registry: ghcr.io
|
||||
username: ${{ github.repository_owner }}
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Push Latest image
|
||||
if: ${{ github.event_name != 'pull_request' }}
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
VERSION: ${{ startsWith(github.ref, 'refs/tags/') && 'latest' || github.ref_name }}
|
||||
run: |
|
||||
make push-all
|
||||
|
||||
- name: Release
|
||||
if: startsWith(github.ref, 'refs/tags/')
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
run: |
|
||||
$TagName = $env:GITHUB_REF -replace 'refs/tags/', ''
|
||||
Get-ChildItem -Path output\* -Include @('windows_exporter*.msi', 'windows_exporter*.exe', 'sha256sums.txt') | Foreach-Object {gh release upload $TagName $_}
|
||||
make push-all
|
||||
26
.github/workflows/spelling.yml
vendored
26
.github/workflows/spelling.yml
vendored
@@ -1,26 +0,0 @@
|
||||
name: Spell checking
|
||||
|
||||
# Trigger on pull requests, and pushes to master branch.
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- master
|
||||
pull_request:
|
||||
branches:
|
||||
- master
|
||||
|
||||
env:
|
||||
PROMU_VER: 'v0.14.0'
|
||||
|
||||
jobs:
|
||||
codespell:
|
||||
name: Check for spelling errors
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: codespell-project/actions-codespell@master
|
||||
with:
|
||||
check_filenames: true
|
||||
# When using this Action in other repos, the --skip option below can be removed
|
||||
skip: ./.git,go.mod,go.sum
|
||||
ignore_words_list: calle
|
||||
21
.github/workflows/stale.yml
vendored
21
.github/workflows/stale.yml
vendored
@@ -1,21 +0,0 @@
|
||||
name: 'Close stale issues and PRs'
|
||||
on:
|
||||
schedule:
|
||||
- cron: '30 1 * * *'
|
||||
|
||||
permissions:
|
||||
issues: write
|
||||
pull-requests: write
|
||||
|
||||
jobs:
|
||||
stale:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/stale@v9
|
||||
with:
|
||||
stale-issue-message: 'This issue has been marked as stale because it has been open for 90 days with no activity. This thread will be automatically closed in 30 days if no further activity occurs.'
|
||||
exempt-issue-labels: 'lifecycle/frozen'
|
||||
days-before-stale: 90
|
||||
days-before-close: 30
|
||||
enable-statistics: false
|
||||
operations-per-run: 500
|
||||
6
.gitignore
vendored
6
.gitignore
vendored
@@ -4,8 +4,4 @@ VERSION
|
||||
*.un~
|
||||
output/
|
||||
.vscode
|
||||
.idea
|
||||
*.syso
|
||||
installer/*.msi
|
||||
installer/*.wixpdb
|
||||
local/
|
||||
.idea
|
||||
@@ -1,63 +1,23 @@
|
||||
linters:
|
||||
enable-all: true
|
||||
disable:
|
||||
- containedctx
|
||||
- contextcheck
|
||||
- cyclop
|
||||
- depguard
|
||||
- dogsled
|
||||
- dupl
|
||||
- err113
|
||||
- exhaustive
|
||||
- exhaustruct
|
||||
- fatcontext
|
||||
- funlen
|
||||
- gochecknoglobals
|
||||
- gocognit
|
||||
- goconst
|
||||
- gocyclo
|
||||
- godox
|
||||
- inamedparam
|
||||
- ireturn
|
||||
- lll
|
||||
- mnd
|
||||
- nlreturn
|
||||
- noctx
|
||||
- testpackage
|
||||
- varnamelen
|
||||
- wrapcheck
|
||||
- wsl
|
||||
- execinquery
|
||||
- gomnd
|
||||
- stylecheck
|
||||
- maintidx
|
||||
|
||||
linters-settings:
|
||||
gci:
|
||||
sections:
|
||||
- prefix(github.com/prometheus-community/windows_exporter/pkg/initiate)
|
||||
- standard # Standard section: captures all standard packages.
|
||||
- default # Default section: contains all imports that could not be matched to another section type.
|
||||
custom-order: true
|
||||
tagliatelle:
|
||||
case:
|
||||
use-field-name: true
|
||||
rules:
|
||||
# Any struct tag type can be used.
|
||||
# Support string case: `camel`, `pascal`, `kebab`, `snake`, `upperSnake`, `goCamel`, `goPascal`, `goKebab`, `goSnake`, `upper`, `lower`, `header`
|
||||
json: camel
|
||||
yaml: snake
|
||||
disable-all: true
|
||||
enable:
|
||||
- deadcode
|
||||
- errcheck
|
||||
- golint
|
||||
- govet
|
||||
- gofmt
|
||||
- ineffassign
|
||||
- interfacer
|
||||
- structcheck
|
||||
- unconvert
|
||||
- varcheck
|
||||
|
||||
issues:
|
||||
exclude:
|
||||
- don't use underscores in Go names
|
||||
- don't use an underscore in package name
|
||||
- exported type .+ should have comment or be unexported
|
||||
exclude-rules:
|
||||
- # Golint has many capitalisation complaints on WMI class names
|
||||
text: "`?\\w+`? should be `?\\w+`?"
|
||||
linters:
|
||||
- revive
|
||||
- text: "don't use ALL_CAPS in Go names; use CamelCase"
|
||||
linters:
|
||||
- revive
|
||||
- golint
|
||||
|
||||
@@ -1,10 +1,8 @@
|
||||
go:
|
||||
version: 1.20
|
||||
repository:
|
||||
path: github.com/prometheus-community/windows_exporter
|
||||
path: github.com/martinlindhe/wmi_exporter
|
||||
build:
|
||||
binaries:
|
||||
- name: windows_exporter
|
||||
- name: wmi_exporter
|
||||
ldflags: |
|
||||
-X github.com/prometheus/common/version.Version={{.Version}}
|
||||
-X github.com/prometheus/common/version.Revision={{.Revision}}
|
||||
@@ -16,4 +14,5 @@ tarball:
|
||||
- LICENSE
|
||||
crossbuild:
|
||||
platforms:
|
||||
- windows
|
||||
- windows/amd64
|
||||
- windows/386
|
||||
|
||||
4
AUTHORS.md
Normal file
4
AUTHORS.md
Normal file
@@ -0,0 +1,4 @@
|
||||
Contributors in alphabetical order
|
||||
|
||||
* [Martin Lindhe](https://github.com/martinlindhe)
|
||||
* [Calle Pettersson](https://github.com/carlpett)
|
||||
@@ -1,3 +0,0 @@
|
||||
# Prometheus Community Code of Conduct
|
||||
|
||||
Prometheus follows the [CNCF Code of Conduct](https://github.com/cncf/foundation/blob/main/code-of-conduct.md).
|
||||
@@ -1,9 +0,0 @@
|
||||
# Note this image doesn't really matter for hostprocess but it is good to build per OS version
|
||||
# the files in the image are copied to $env:CONTAINER_SANDBOX_MOUNT_POINT on the host
|
||||
# but the file system is the Host NOT the container
|
||||
ARG BASE="mcr.microsoft.com/windows/nanoserver:ltsc2022"
|
||||
FROM $BASE
|
||||
|
||||
ENV PATH="C:\Windows\system32;C:\Windows;"
|
||||
COPY output/amd64/windows_exporter.exe /windows_exporter.exe
|
||||
ENTRYPOINT ["windows_exporter.exe"]
|
||||
@@ -1,22 +0,0 @@
|
||||
# Build this Docker Image on any platform with
|
||||
# docker buildx build -t a --platform=windows/amd64 .
|
||||
|
||||
ARG BASE=mcr.microsoft.com/oss/kubernetes/windows-host-process-containers-base-image:v1.0.0
|
||||
|
||||
FROM --platform=$BUILDPLATFORM golang:1.21 as builder
|
||||
ARG TARGETARCH
|
||||
ARG TARGETOS
|
||||
|
||||
# Get dependencies
|
||||
WORKDIR /w
|
||||
COPY go.mod go.sum ./
|
||||
RUN go mod download
|
||||
RUN go install github.com/prometheus/promu@latest
|
||||
|
||||
# Build windows_exporter
|
||||
COPY . ./
|
||||
RUN GOOS=$TARGETOS GOARCH=$TARGETARCH make windows_exporter.exe
|
||||
|
||||
FROM $BASE
|
||||
COPY --from=builder /w/windows_exporter.exe /windows_exporter.exe
|
||||
ENTRYPOINT ["windows_exporter.exe"]
|
||||
@@ -1,10 +0,0 @@
|
||||
Maintainers in alphabetical order
|
||||
|
||||
* [Ben Reedy](https://github.com/breed808) - breed808@breed808.com
|
||||
* [Calle Pettersson](https://github.com/carlpett) - calle@cape.nu
|
||||
* [Jan-Otto Kröpke](https://github.com/jkroepke) - github@jkroepke.de
|
||||
|
||||
Alumni
|
||||
|
||||
* [Brian Brazil](https://github.com/brian-brazil)
|
||||
* [Martin Lindhe](https://github.com/martinlindhe)
|
||||
85
Makefile
85
Makefile
@@ -1,96 +1,19 @@
|
||||
GOOS ?= windows
|
||||
VERSION ?= $(shell cat VERSION)
|
||||
DOCKER ?= docker
|
||||
export GOOS=windows
|
||||
|
||||
# DOCKER_REPO is the official image repository name at docker.io, quay.io.
|
||||
DOCKER_REPO ?= prometheuscommunity
|
||||
DOCKER_IMAGE_NAME ?= windows-exporter
|
||||
|
||||
# ALL_DOCKER_REPOS is the list of repositories to push the image to. ghcr.io requires that org name be the same as the image repo name.
|
||||
ALL_DOCKER_REPOS ?= docker.io/$(DOCKER_REPO) ghcr.io/prometheus-community # quay.io/$(DOCKER_REPO)
|
||||
|
||||
# Image Variables for host process Container
|
||||
# Windows image build is heavily influenced by https://github.com/kubernetes/kubernetes/blob/master/cluster/images/etcd/Makefile
|
||||
OS ?= ltsc2019
|
||||
ALL_OS ?= ltsc2019 ltsc2022
|
||||
BASE_IMAGE ?= mcr.microsoft.com/windows/nanoserver
|
||||
|
||||
.PHONY: build
|
||||
build: generate windows_exporter.exe
|
||||
|
||||
windows_exporter.exe: pkg/**/*.go
|
||||
build:
|
||||
promu build -v
|
||||
|
||||
.PHONY: generate
|
||||
generate:
|
||||
go generate ./...
|
||||
|
||||
test:
|
||||
go test -v ./...
|
||||
|
||||
bench:
|
||||
go test -v -bench='benchmarkcollector' ./pkg/collector/{cpu,logical_disk,physical_disk,logon,memory,net,printer,process,service,system,tcp,time}
|
||||
|
||||
lint:
|
||||
golangci-lint -c .golangci.yaml run
|
||||
|
||||
.PHONY: e2e-test
|
||||
e2e-test: windows_exporter.exe
|
||||
pwsh -NonInteractive -ExecutionPolicy Bypass -File .\tools\end-to-end-test.ps1
|
||||
|
||||
.PHONY: promtool
|
||||
promtool: windows_exporter.exe
|
||||
pwsh -NonInteractive -ExecutionPolicy Bypass -File .\tools\promtool.ps1
|
||||
|
||||
fmt:
|
||||
gofmt -l -w -s .
|
||||
|
||||
crossbuild: generate
|
||||
crossbuild:
|
||||
# The prometheus/golang-builder image for promu crossbuild doesn't exist
|
||||
# on Windows, so for now, we'll just build twice
|
||||
GOARCH=amd64 promu build --prefix=output/amd64
|
||||
GOARCH=arm64 promu build --prefix=output/arm64
|
||||
|
||||
.PHONY: package
|
||||
package: crossbuild
|
||||
powershell -NonInteractive -ExecutionPolicy Bypass -File .\installer\build.ps1 -PathToExecutable .\output\amd64\windows_exporter.exe -Version $(shell git describe --tags --abbrev=0)
|
||||
|
||||
build-image: crossbuild
|
||||
$(DOCKER) build --build-arg=BASE=$(BASE_IMAGE):$(OS) -f Dockerfile -t local/$(DOCKER_IMAGE_NAME):$(VERSION)-$(OS) .
|
||||
|
||||
build-hostprocess:
|
||||
$(DOCKER) buildx build --build-arg=BASE=mcr.microsoft.com/oss/kubernetes/windows-host-process-containers-base-image:v1.0.0 -f Dockerfile -t local/$(DOCKER_IMAGE_NAME):$(VERSION)-hostprocess .
|
||||
|
||||
sub-build-%:
|
||||
$(MAKE) OS=$* build-image
|
||||
|
||||
build-all: $(addprefix sub-build-,$(ALL_OS)) build-hostprocess
|
||||
|
||||
push:
|
||||
set -x; \
|
||||
for docker_repo in ${DOCKER_REPO}; do \
|
||||
for osversion in ${ALL_OS}; do \
|
||||
$(DOCKER) tag local/$(DOCKER_IMAGE_NAME):$(VERSION)-$${osversion} $${docker_repo}/$(DOCKER_IMAGE_NAME):$(VERSION)-$${osversion}; \
|
||||
$(DOCKER) push $${docker_repo}/$(DOCKER_IMAGE_NAME):$(VERSION)-$${osversion}; \
|
||||
$(DOCKER) manifest create --amend $${docker_repo}/$(DOCKER_IMAGE_NAME):$(VERSION) $${docker_repo}/$(DOCKER_IMAGE_NAME):$(VERSION)-$${osversion}; \
|
||||
full_version=`$(DOCKER) manifest inspect $(BASE_IMAGE):$${osversion} | grep "os.version" | head -n 1 | awk -F\" '{print $$4}'` || true; \
|
||||
$(DOCKER) manifest annotate --os windows --arch amd64 --os-version $${full_version} $${docker_repo}/$(DOCKER_IMAGE_NAME):$(VERSION) $${docker_repo}/$(DOCKER_IMAGE_NAME):$(VERSION)-$${osversion}; \
|
||||
done; \
|
||||
$(DOCKER) manifest push --purge $${docker_repo}/$(DOCKER_IMAGE_NAME):$(VERSION); \
|
||||
done
|
||||
|
||||
# We can't load the image into the local docker store, so we have to build and push it in one go
|
||||
push-hostprocess:
|
||||
set -x; \
|
||||
for docker_repo in ${DOCKER_REPO}; do \
|
||||
$(DOCKER) buildx build --push --build-arg=BASE=mcr.microsoft.com/oss/kubernetes/windows-host-process-containers-base-image:v1.0.0 -f Dockerfile -t $${docker_repo}/$(DOCKER_IMAGE_NAME):$(VERSION)-hostprocess .; \
|
||||
done
|
||||
|
||||
.PHONY: push-all
|
||||
push-all: build-all
|
||||
$(MAKE) DOCKER_REPO="$(ALL_DOCKER_REPOS)" push # push-hostprocess - disabled until it works on Windows
|
||||
|
||||
# Mandatory target for container description sync action
|
||||
.PHONY: docker-repo-name
|
||||
docker-repo-name:
|
||||
@echo "$(DOCKER_REPO)/$(DOCKER_IMAGE_NAME)"
|
||||
GOARCH=386 promu build --prefix=output/386
|
||||
|
||||
193
README.md
193
README.md
@@ -1,38 +1,25 @@
|
||||
# windows_exporter
|
||||
# WMI exporter
|
||||
|
||||
|
||||
[](https://ci.appveyor.com/project/martinlindhe/wmi-exporter)
|
||||
|
||||
Prometheus exporter for Windows machines, using the WMI (Windows Management Instrumentation).
|
||||
|
||||
A Prometheus exporter for Windows machines.
|
||||
|
||||
## Collectors
|
||||
|
||||
Name | Description | Enabled by default
|
||||
---------|-------------|--------------------
|
||||
[ad](docs/collector.ad.md) | Active Directory Domain Services |
|
||||
[adcs](docs/collector.adcs.md) | Active Directory Certificate Services |
|
||||
[adfs](docs/collector.adfs.md) | Active Directory Federation Services |
|
||||
[cache](docs/collector.cache.md) | Cache metrics |
|
||||
[cpu](docs/collector.cpu.md) | CPU usage | ✓
|
||||
[cpu_info](docs/collector.cpu_info.md) | CPU Information |
|
||||
[cs](docs/collector.cs.md) | "Computer System" metrics (system properties, num cpus/total memory) | ✓
|
||||
[container](docs/collector.container.md) | Container metrics |
|
||||
[diskdrive](docs/collector.diskdrive.md) | Diskdrive metrics |
|
||||
[dfsr](docs/collector.dfsr.md) | DFSR metrics |
|
||||
[dhcp](docs/collector.dhcp.md) | DHCP Server |
|
||||
[dns](docs/collector.dns.md) | DNS Server |
|
||||
[exchange](docs/collector.exchange.md) | Exchange metrics |
|
||||
[fsrmquota](docs/collector.fsrmquota.md) | Microsoft File Server Resource Manager (FSRM) Quotas collector |
|
||||
[hyperv](docs/collector.hyperv.md) | Hyper-V hosts |
|
||||
[iis](docs/collector.iis.md) | IIS sites and applications |
|
||||
[license](docs/collector.license.md) | Windows license status |
|
||||
[logical_disk](docs/collector.logical_disk.md) | Logical disks, disk I/O | ✓
|
||||
[logon](docs/collector.logon.md) | User logon sessions |
|
||||
[memory](docs/collector.memory.md) | Memory usage metrics |
|
||||
[mscluster_cluster](docs/collector.mscluster_cluster.md) | MSCluster cluster metrics |
|
||||
[mscluster_network](docs/collector.mscluster_network.md) | MSCluster network metrics |
|
||||
[mscluster_node](docs/collector.mscluster_node.md) | MSCluster Node metrics |
|
||||
[mscluster_resource](docs/collector.mscluster_resource.md) | MSCluster Resource metrics |
|
||||
[mscluster_resourcegroup](docs/collector.mscluster_resourcegroup.md) | MSCluster ResourceGroup metrics |
|
||||
[msmq](docs/collector.msmq.md) | MSMQ queues |
|
||||
[mssql](docs/collector.mssql.md) | [SQL Server Performance Objects](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/use-sql-server-objects#SQLServerPOs) metrics |
|
||||
[netframework_clrexceptions](docs/collector.netframework_clrexceptions.md) | .NET Framework CLR Exceptions |
|
||||
@@ -45,76 +32,31 @@ Name | Description | Enabled by default
|
||||
[netframework_clrsecurity](docs/collector.netframework_clrsecurity.md) | .NET Framework Security Check metrics |
|
||||
[net](docs/collector.net.md) | Network interface I/O | ✓
|
||||
[os](docs/collector.os.md) | OS metrics (memory, processes, users) | ✓
|
||||
[physical_disk](docs/collector.physical_disk.md) | physical disk metrics | ✓
|
||||
[printer](docs/collector.printer.md) | Printer metrics |
|
||||
[process](docs/collector.process.md) | Per-process metrics |
|
||||
[remote_fx](docs/collector.remote_fx.md) | RemoteFX protocol (RDP) metrics |
|
||||
[scheduled_task](docs/collector.scheduled_task.md) | Scheduled Tasks metrics |
|
||||
[service](docs/collector.service.md) | Service state metrics | ✓
|
||||
[smb](docs/collector.smb.md) | SMB Server |
|
||||
[smbclient](docs/collector.smbclient.md) | SMB Client |
|
||||
[smtp](docs/collector.smtp.md) | IIS SMTP Server |
|
||||
[system](docs/collector.system.md) | System calls | ✓
|
||||
[tcp](docs/collector.tcp.md) | TCP connections |
|
||||
[teradici_pcoip](docs/collector.teradici_pcoip.md) | [Teradici PCoIP](https://www.teradici.com/web-help/pcoip_wmi_specs/) session metrics |
|
||||
[time](docs/collector.time.md) | Windows Time Service |
|
||||
[thermalzone](docs/collector.thermalzone.md) | Thermal information
|
||||
[terminal_services](docs/collector.terminal_services.md) | Terminal services (RDS)
|
||||
[textfile](docs/collector.textfile.md) | Read prometheus metrics from a text file |
|
||||
[vmware_blast](docs/collector.vmware_blast.md) | VMware Blast session metrics |
|
||||
[textfile](docs/collector.textfile.md) | Read prometheus metrics from a text file | ✓
|
||||
[vmware](docs/collector.vmware.md) | Performance counters installed by the Vmware Guest agent |
|
||||
|
||||
See the linked documentation on each collector for more information on reported metrics, configuration settings and usage examples.
|
||||
|
||||
### Filtering enabled collectors
|
||||
|
||||
The `windows_exporter` will expose all metrics from enabled collectors by default. This is the recommended way to collect metrics to avoid errors when comparing metrics of different families.
|
||||
|
||||
For advanced use the `windows_exporter` can be passed an optional list of collectors to filter metrics. The `collect[]` parameter may be used multiple times. In Prometheus configuration you can use this syntax under the [scrape config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#<scrape_config>).
|
||||
|
||||
```
|
||||
params:
|
||||
collect[]:
|
||||
- foo
|
||||
- bar
|
||||
```
|
||||
|
||||
This can be useful for having different Prometheus servers collect specific metrics from nodes.
|
||||
|
||||
## Flags
|
||||
|
||||
windows_exporter accepts flags to configure certain behaviours. The ones configuring the global behaviour of the exporter are listed below, while collector-specific ones are documented in the respective collector documentation above.
|
||||
|
||||
| Flag | Description | Default value |
|
||||
|--------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------|---------------|
|
||||
| `--web.listen-address` | host:port for exporter. | `:9182` |
|
||||
| `--telemetry.path` | URL path for surfacing collected metrics. | `/metrics` |
|
||||
| `--telemetry.max-requests` | Maximum number of concurrent requests. 0 to disable. | `5` |
|
||||
| `--collectors.enabled` | Comma-separated list of collectors to use. Use `[defaults]` as a placeholder which gets expanded containing all the collectors enabled by default." | `[defaults]` |
|
||||
| `--collectors.print` | If true, print available collectors and exit. | |
|
||||
| `--scrape.timeout-margin` | Seconds to subtract from the timeout allowed by the client. Tune to allow for overhead or high loads. | `0.5` |
|
||||
| `--web.config.file` | A [web config][web_config] for setting up TLS and Auth | None |
|
||||
| `--config.file` | [Using a config file](#using-a-configuration-file) from path or URL | None |
|
||||
| `--config.file.insecure-skip-verify` | Skip TLS when loading config file from URL | false |
|
||||
|
||||
## Installation
|
||||
The latest release can be downloaded from the [releases page](https://github.com/prometheus-community/windows_exporter/releases).
|
||||
The latest release can be downloaded from the [releases page](https://github.com/martinlindhe/wmi_exporter/releases).
|
||||
|
||||
Each release provides a .msi installer. The installer will setup the windows_exporter as a Windows service, as well as create an exception in the Windows Firewall.
|
||||
Each release provides a .msi installer. The installer will setup the WMI Exporter as a Windows service, as well as create an exception in the Windows Firewall.
|
||||
|
||||
If the installer is run without any parameters, the exporter will run with default settings for enabled collectors, ports, etc. The following parameters are available:
|
||||
|
||||
| Name | Description |
|
||||
|----------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------|
|
||||
| `ENABLED_COLLECTORS` | As the `--collectors.enabled` flag, provide a comma-separated list of enabled collectors |
|
||||
| `LISTEN_ADDR` | The IP address to bind to. Defaults to an empty string. (any local address) |
|
||||
| `LISTEN_PORT` | The port to bind to. Defaults to `9182`. |
|
||||
| `METRICS_PATH` | The path at which to serve metrics. Defaults to `/metrics` |
|
||||
| `TEXTFILE_DIRS` | As the `--collector.textfile.directories` flag, provide a directory to read text files with metrics from |
|
||||
| `REMOTE_ADDR` | Allows setting comma separated remote IP addresses for the Windows Firewall exception (allow list). Defaults to an empty string (any remote address). |
|
||||
| `EXTRA_FLAGS` | Allows passing full CLI flags. Defaults to an empty string. |
|
||||
| `ADD_FIREWALL_EXCEPTION` | Setup an firewall exception for windows_exporter. Defaults to `yes`. |
|
||||
| `ENABLE_V1_PERFORMANCE_COUNTERS` | Enables V1 performance counter on modern systems. Defaults to `yes`. |
|
||||
Name | Description
|
||||
-----|------------
|
||||
`ENABLED_COLLECTORS` | As the `--collectors.enabled` flag, provide a comma-separated list of enabled collectors
|
||||
`LISTEN_ADDR` | The IP address to bind to. Defaults to 0.0.0.0
|
||||
`LISTEN_PORT` | The port to bind to. Defaults to 9182.
|
||||
`METRICS_PATH` | The path at which to serve metrics. Defaults to `/metrics`
|
||||
`TEXTFILE_DIR` | As the `--collector.textfile.directory` flag, provide a directory to read text files with metrics from
|
||||
`EXTRA_FLAGS` | Allows passing full CLI flags. Defaults to an empty string.
|
||||
|
||||
Parameters are sent to the installer via `msiexec`. Example invocations:
|
||||
|
||||
@@ -127,64 +69,23 @@ Example service collector with a custom query.
|
||||
msiexec /i <path-to-msi-file> ENABLED_COLLECTORS=os,service --% EXTRA_FLAGS="--collector.service.services-where ""Name LIKE 'sql%'"""
|
||||
```
|
||||
|
||||
On some older versions of Windows,
|
||||
you may need to surround parameter values with double quotes to get the installation command parsing properly:
|
||||
On some older versions of Windows you may need to surround parameter values with double quotes to get the install command parsing properly:
|
||||
```powershell
|
||||
msiexec /i C:\Users\Administrator\Downloads\windows_exporter.msi ENABLED_COLLECTORS="ad,iis,logon,memory,process,tcp,textfile,thermalzone" TEXTFILE_DIRS="C:\custom_metrics\"
|
||||
msiexec /i C:\Users\Administrator\Downloads\wmi_exporter.msi ENABLED_COLLECTORS="ad,iis,logon,memory,process,tcp,thermalzone" TEXTFILE_DIR="C:\custom_metrics\"
|
||||
```
|
||||
|
||||
To install the exporter with creating a firewall exception, use the following command:
|
||||
## Roadmap
|
||||
|
||||
```powershell
|
||||
msiexec /i <path-to-msi-file> ADD_FIREWALL_EXCEPTION=yes
|
||||
```
|
||||
See [open issues](https://github.com/martinlindhe/wmi_exporter/issues)
|
||||
|
||||
To repair an installation, e.g force re-creating Windows service:
|
||||
|
||||
```powershell
|
||||
msiexec /fa <path-to-msi-file>
|
||||
```
|
||||
|
||||
|
||||
Powershell versions 7.3 and above require [PSNativeCommandArgumentPassing](https://learn.microsoft.com/en-us/powershell/scripting/learn/experimental-features?view=powershell-7.3) to be set to `Legacy` when using `--% EXTRA_FLAGS`:
|
||||
|
||||
```powershell
|
||||
$PSNativeCommandArgumentPassing = 'Legacy'
|
||||
msiexec /i <path-to-msi-file> ENABLED_COLLECTORS=os,service --% EXTRA_FLAGS="--collector.service.services-where ""Name LIKE 'sql%'"""
|
||||
```
|
||||
|
||||
## Docker Implementation
|
||||
|
||||
The windows_exporter can be run as a Docker container. The Docker image is available on
|
||||
|
||||
* [Docker Hub](https://hub.docker.com/r/prometheuscommunity/windows-exporter): `docker.io/prometheuscommunity/windows-exporter`
|
||||
* [GitHub Container Registry](https://github.com/prometheus-community/windows_exporter/pkgs/container/windows-exporter): `ghcr.io/prometheus-community/windows-exporter`
|
||||
<!-- * [quay.io Registry](https://quay.io/repository/prometheuscommunity/windows-exporter): `quay.io/prometheuscommunity/windows-exporter` -->
|
||||
|
||||
### Tags
|
||||
|
||||
The Docker image is tagged with the version of the exporter. The `latest` tag is also available and points to the latest release.
|
||||
|
||||
Additionally, a flavor `hostprocess` with `-hostprocess` as suffix is based on the https://github.com/microsoft/windows-host-process-containers-base-image
|
||||
which is designed to run as a Windows host process container. The size of that images is smaller than the default one.
|
||||
|
||||
## Kubernetes Implementation
|
||||
|
||||
See detailed steps to install on Windows Kubernetes [here](./kubernetes/kubernetes.md).
|
||||
|
||||
## Supported versions
|
||||
|
||||
`windows_exporter` supports Windows Server versions 2016 and later, and desktop Windows version 10 and 11 (21H2 or later).
|
||||
|
||||
Windows Server 2012 and 2012R2 are supported as best-effort only, but not guaranteed to work.
|
||||
|
||||
## Usage
|
||||
|
||||
go get -u github.com/prometheus/promu
|
||||
go get -u github.com/prometheus-community/windows_exporter
|
||||
cd $env:GOPATH/src/github.com/prometheus-community/windows_exporter
|
||||
promu build -v
|
||||
.\windows_exporter.exe
|
||||
go get -u github.com/martinlindhe/wmi_exporter
|
||||
cd $env:GOPATH/src/github.com/martinlindhe/wmi_exporter
|
||||
promu build -v .
|
||||
.\wmi_exporter.exe
|
||||
|
||||
The prometheus metrics will be exposed on [localhost:9182](http://localhost:9182)
|
||||
|
||||
@@ -192,57 +93,17 @@ The prometheus metrics will be exposed on [localhost:9182](http://localhost:9182
|
||||
|
||||
### Enable only service collector and specify a custom query
|
||||
|
||||
.\windows_exporter.exe --collectors.enabled "service" --collector.service.services-where "Name='windows_exporter'"
|
||||
.\wmi_exporter.exe --collectors.enabled "service" --collector.service.services-where "Name='wmi_exporter'"
|
||||
|
||||
### Enable only process collector and specify a custom query
|
||||
|
||||
.\windows_exporter.exe --collectors.enabled "process" --collector.process.include="firefox.+"
|
||||
.\wmi_exporter.exe --collectors.enabled "process" --collector.process.processes-where "Name LIKE 'firefox%'"
|
||||
|
||||
When there are multiple processes with the same name, WMI represents those after the first instance as `process-name#index`. So to get them all, rather than just the first one, the [regular expression](https://en.wikipedia.org/wiki/Regular_expression) must use `.+`. See [process](docs/collector.process.md) for more information.
|
||||
When there are multiple processes with the same name, WMI represents those after the first instance as `process-name#index`. So to get them all, rather than just the first one, the query needs to be a wildcard search using a `%` character.
|
||||
|
||||
### Using [defaults] with `--collectors.enabled` argument
|
||||
Please note that in Windows batch scripts (and when using the `cmd` command prompt), the `%` character is reserved, so it has to be escaped with another `%`. For example, the wildcard syntax for searching for all firefox processes is `firefox%%`.
|
||||
|
||||
Using `[defaults]` with `--collectors.enabled` argument which gets expanded with all default collectors.
|
||||
|
||||
.\windows_exporter.exe --collectors.enabled "[defaults],process,container"
|
||||
|
||||
This enables the additional process and container collectors on top of the defaults.
|
||||
|
||||
### Using a configuration file
|
||||
|
||||
YAML configuration files can be specified with the `--config.file` flag. e.g. `.\windows_exporter.exe --config.file=config.yml`. If you are using the absolute path, make sure to quote the path, e.g. `.\windows_exporter.exe --config.file="C:\Program Files\windows_exporter\config.yml"`
|
||||
|
||||
It is also possible to load the configuration from a URL. e.g. `.\windows_exporter.exe --config.file="https://example.com/config.yml"`
|
||||
|
||||
If you need to skip TLS verification, you can use the `--config.file.insecure-skip-verify` flag. e.g. `.\windows_exporter.exe --config.file="https://example.com/config.yml" --config.file.insecure-skip-verify`
|
||||
|
||||
```yaml
|
||||
collectors:
|
||||
enabled: cpu,cs,net,service
|
||||
collector:
|
||||
service:
|
||||
services-where: "Name='windows_exporter'"
|
||||
log:
|
||||
level: warn
|
||||
```
|
||||
|
||||
An example configuration file can be found [here](docs/example_config.yml).
|
||||
|
||||
#### Configuration file notes
|
||||
|
||||
Configuration file values can be mixed with CLI flags. E.G.
|
||||
|
||||
`.\windows_exporter.exe --collectors.enabled=cpu,logon`
|
||||
|
||||
```yaml
|
||||
log:
|
||||
level: debug
|
||||
```
|
||||
|
||||
CLI flags enjoy a higher priority over values specified in the configuration file.
|
||||
|
||||
## License
|
||||
|
||||
Under [MIT](LICENSE)
|
||||
|
||||
[web_config]: https://github.com/prometheus/exporter-toolkit/blob/master/docs/web-configuration.md
|
||||
|
||||
@@ -1,6 +0,0 @@
|
||||
# Reporting a security issue
|
||||
|
||||
The Prometheus security policy, including how to report vulnerabilities, can be
|
||||
found here:
|
||||
|
||||
<https://prometheus.io/docs/operating/security/>
|
||||
78
appveyor.yml
Normal file
78
appveyor.yml
Normal file
@@ -0,0 +1,78 @@
|
||||
version: "{build}"
|
||||
|
||||
os: Visual Studio 2017
|
||||
build: off
|
||||
stack: go 1.13
|
||||
|
||||
environment:
|
||||
GOPATH: c:\gopath
|
||||
GO111MODULE: on
|
||||
|
||||
clone_folder: c:\gopath\src\github.com\martinlindhe\wmi_exporter
|
||||
|
||||
install:
|
||||
- mkdir %GOPATH%\bin
|
||||
- set PATH=%GOPATH%\bin;%PATH%
|
||||
- set PATH=%PATH%;C:\mingw-w64\x86_64-7.2.0-posix-seh-rt_v5-rev1\mingw64\bin
|
||||
- choco install gitversion.portable make -y
|
||||
- ps: |
|
||||
appveyor DownloadFile https://github.com/golangci/golangci-lint/releases/download/v1.21.0/golangci-lint-1.21.0-windows-amd64.zip
|
||||
Expand-Archive golangci-lint-1.21.0-windows-amd64.zip
|
||||
Move-Item golangci-lint-1.21.0-windows-amd64\golangci-lint-1.21.0-windows-amd64\golangci-lint.exe $env:GOPATH\bin\golangci-lint.exe
|
||||
- ps: |
|
||||
$env:GO111MODULE="off"
|
||||
go get -u github.com/prometheus/promu
|
||||
$env:GO111MODULE="on"
|
||||
|
||||
test_script:
|
||||
- make test
|
||||
|
||||
after_test:
|
||||
- make lint
|
||||
|
||||
build_script:
|
||||
- ps: |
|
||||
# go mod download (or, if we don't call it, go build) will write every dependent package name to
|
||||
# stderr, which will be interpreted as an error and abort the build if ErrorActionPreference is Stop,
|
||||
# so we need to run it before setting the preference.
|
||||
go mod download
|
||||
$ErrorActionPreference = "Stop"
|
||||
gitversion /output json /showvariable FullSemVer | Set-Content VERSION -PassThru
|
||||
$Version = Get-Content VERSION
|
||||
make crossbuild
|
||||
# GH requires all files to have different names, so add version/arch to differentiate
|
||||
foreach($Arch in "amd64","386") {
|
||||
Rename-Item output\$Arch\wmi_exporter.exe -NewName wmi_exporter-$Version-$Arch.exe
|
||||
}
|
||||
|
||||
after_build:
|
||||
- ps: |
|
||||
# Build installer packages only on tagged releases
|
||||
if($env:APPVEYOR_REPO_TAG -ne "True") {
|
||||
return
|
||||
}
|
||||
$ErrorActionPreference = "Stop"
|
||||
$BuildVersion = Get-Content VERSION
|
||||
# The MSI version is not semver compliant, so just take the numerical parts
|
||||
$MSIVersion = $env:APPVEYOR_REPO_TAG_NAME -replace '^v?([0-9\.]+).*$','$1'
|
||||
foreach($Arch in "amd64","386") {
|
||||
Write-Verbose "Building wmi_exporter $MSIVersion msi for $Arch"
|
||||
.\installer\build.ps1 -PathToExecutable .\output\$Arch\wmi_exporter-$BuildVersion-$Arch.exe -Version $MSIVersion -Arch "$Arch"
|
||||
Move-Item installer\Output\wmi_exporter-$MSIVersion-$Arch.msi output\$Arch\
|
||||
}
|
||||
- promu checksum output\
|
||||
|
||||
artifacts:
|
||||
- name: Artifacts
|
||||
path: output\**\*
|
||||
|
||||
deploy:
|
||||
- provider: GitHub
|
||||
description: WMI Exporter version $(appveyor_build_version)
|
||||
artifact: Artifacts
|
||||
auth_token:
|
||||
secure: 'CrXWeTf7qONUOEki5olFfGEUPMLDeHj61koDXV3OVEaLgtACmnVHsKUub9POflda'
|
||||
draft: false
|
||||
prerelease: false
|
||||
on:
|
||||
appveyor_repo_tag: true
|
||||
File diff suppressed because it is too large
Load Diff
188
collector/adfs.go
Normal file
188
collector/adfs.go
Normal file
@@ -0,0 +1,188 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("adfs", newADFSCollector)
|
||||
}
|
||||
|
||||
type adfsCollector struct {
|
||||
adLoginConnectionFailures *prometheus.Desc
|
||||
certificateAuthentications *prometheus.Desc
|
||||
deviceAuthentications *prometheus.Desc
|
||||
extranetAccountLockouts *prometheus.Desc
|
||||
federatedAuthentications *prometheus.Desc
|
||||
passportAuthentications *prometheus.Desc
|
||||
passiveRequests *prometheus.Desc
|
||||
passwordChangeFailed *prometheus.Desc
|
||||
passwordChangeSucceeded *prometheus.Desc
|
||||
tokenRequests *prometheus.Desc
|
||||
windowsIntegratedAuthentications *prometheus.Desc
|
||||
}
|
||||
|
||||
// newADFSCollector constructs a new adfsCollector
|
||||
func newADFSCollector() (Collector, error) {
|
||||
const subsystem = "adfs"
|
||||
|
||||
return &adfsCollector{
|
||||
adLoginConnectionFailures: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "ad_login_connection_failures"),
|
||||
"Total number of connection failures to an Active Directory domain controller",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
certificateAuthentications: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "certificate_authentications"),
|
||||
"Total number of User Certificate authentications",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
deviceAuthentications: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "device_authentications"),
|
||||
"Total number of Device authentications",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
extranetAccountLockouts: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "extranet_account_lockouts"),
|
||||
"Total number of Extranet Account Lockouts",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
federatedAuthentications: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "federated_authentications"),
|
||||
"Total number of authentications from a federated source",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
passportAuthentications: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "passport_authentications"),
|
||||
"Total number of Microsoft Passport SSO authentications",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
passiveRequests: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "passive_requests"),
|
||||
"Total number of passive (browser-based) requests",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
passwordChangeFailed: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "password_change_failed"),
|
||||
"Total number of failed password changes",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
passwordChangeSucceeded: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "password_change_succeeded"),
|
||||
"Total number of successful password changes",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
tokenRequests: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "token_requests"),
|
||||
"Total number of token requests",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
windowsIntegratedAuthentications: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "windows_integrated_authentications"),
|
||||
"Total number of Windows integrated authentications (Kerberos/NTLM)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
type perflibADFS struct {
|
||||
AdLoginConnectionFailures float64 `perflib:"AD login Connection Failures"`
|
||||
CertificateAuthentications float64 `perflib:"Certificate Authentications"`
|
||||
DeviceAuthentications float64 `perflib:"Device Authentications"`
|
||||
ExtranetAccountLockouts float64 `perflib:"Extranet Account Lockouts"`
|
||||
FederatedAuthentications float64 `perflib:"Federated Authentications"`
|
||||
PassportAuthentications float64 `perflib:"Microsoft Passport Authentications"`
|
||||
PassiveRequests float64 `perflib:"Passive Requests"`
|
||||
PasswordChangeFailed float64 `perflib:"Password Change Failed Requests"`
|
||||
PasswordChangeSucceeded float64 `perflib:"Password Change Successful Requests"`
|
||||
TokenRequests float64 `perflib:"Token Requests"`
|
||||
WindowsIntegratedAuthentications float64 `perflib:"Windows Integrated Authentications"`
|
||||
}
|
||||
|
||||
func (c *adfsCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
var adfsData []perflibADFS
|
||||
err := unmarshalObject(ctx.perfObjects["AD FS"], &adfsData)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.adLoginConnectionFailures,
|
||||
prometheus.CounterValue,
|
||||
adfsData[0].AdLoginConnectionFailures,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.certificateAuthentications,
|
||||
prometheus.CounterValue,
|
||||
adfsData[0].CertificateAuthentications,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.deviceAuthentications,
|
||||
prometheus.CounterValue,
|
||||
adfsData[0].DeviceAuthentications,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.extranetAccountLockouts,
|
||||
prometheus.CounterValue,
|
||||
adfsData[0].ExtranetAccountLockouts,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.federatedAuthentications,
|
||||
prometheus.CounterValue,
|
||||
adfsData[0].FederatedAuthentications,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.passportAuthentications,
|
||||
prometheus.CounterValue,
|
||||
adfsData[0].PassportAuthentications,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.passiveRequests,
|
||||
prometheus.CounterValue,
|
||||
adfsData[0].PassiveRequests,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.passwordChangeFailed,
|
||||
prometheus.CounterValue,
|
||||
adfsData[0].PasswordChangeFailed,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.passwordChangeSucceeded,
|
||||
prometheus.CounterValue,
|
||||
adfsData[0].PasswordChangeSucceeded,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.tokenRequests,
|
||||
prometheus.CounterValue,
|
||||
adfsData[0].TokenRequests,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.windowsIntegratedAuthentications,
|
||||
prometheus.CounterValue,
|
||||
adfsData[0].WindowsIntegratedAuthentications,
|
||||
)
|
||||
return nil
|
||||
}
|
||||
106
collector/collector.go
Normal file
106
collector/collector.go
Normal file
@@ -0,0 +1,106 @@
|
||||
package collector
|
||||
|
||||
import (
|
||||
"strconv"
|
||||
"strings"
|
||||
|
||||
"github.com/leoluk/perflib_exporter/perflib"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
"golang.org/x/sys/windows/registry"
|
||||
)
|
||||
|
||||
// ...
|
||||
const (
|
||||
// TODO: Make package-local
|
||||
Namespace = "wmi"
|
||||
|
||||
// Conversion factors
|
||||
ticksToSecondsScaleFactor = 1 / 1e7
|
||||
windowsEpoch = 116444736000000000
|
||||
)
|
||||
|
||||
// getWindowsVersion reads the version number of the OS from the Registry
|
||||
// See https://docs.microsoft.com/en-us/windows/desktop/sysinfo/operating-system-version
|
||||
func getWindowsVersion() float64 {
|
||||
k, err := registry.OpenKey(registry.LOCAL_MACHINE, `SOFTWARE\Microsoft\Windows NT\CurrentVersion`, registry.QUERY_VALUE)
|
||||
if err != nil {
|
||||
log.Warn("Couldn't open registry", err)
|
||||
return 0
|
||||
}
|
||||
defer func() {
|
||||
err = k.Close()
|
||||
if err != nil {
|
||||
log.Warnf("Failed to close registry key: %v", err)
|
||||
}
|
||||
}()
|
||||
|
||||
currentv, _, err := k.GetStringValue("CurrentVersion")
|
||||
if err != nil {
|
||||
log.Warn("Couldn't open registry to determine current Windows version:", err)
|
||||
return 0
|
||||
}
|
||||
|
||||
currentv_flt, err := strconv.ParseFloat(currentv, 64)
|
||||
|
||||
log.Debugf("Detected Windows version %f\n", currentv_flt)
|
||||
|
||||
return currentv_flt
|
||||
}
|
||||
|
||||
type collectorBuilder func() (Collector, error)
|
||||
|
||||
var (
|
||||
builders = make(map[string]collectorBuilder)
|
||||
perfCounterDependencies = make(map[string]string)
|
||||
)
|
||||
|
||||
func registerCollector(name string, builder collectorBuilder, perfCounterNames ...string) {
|
||||
builders[name] = builder
|
||||
perfIndicies := make([]string, 0, len(perfCounterNames))
|
||||
for _, cn := range perfCounterNames {
|
||||
perfIndicies = append(perfIndicies, MapCounterToIndex(cn))
|
||||
}
|
||||
perfCounterDependencies[name] = strings.Join(perfIndicies, " ")
|
||||
}
|
||||
|
||||
func Available() []string {
|
||||
cs := make([]string, 0, len(builders))
|
||||
for c := range builders {
|
||||
cs = append(cs, c)
|
||||
}
|
||||
return cs
|
||||
}
|
||||
func Build(collector string) (Collector, error) {
|
||||
return builders[collector]()
|
||||
}
|
||||
func getPerfQuery(collectors []string) string {
|
||||
parts := make([]string, 0, len(collectors))
|
||||
for _, c := range collectors {
|
||||
if p := perfCounterDependencies[c]; p != "" {
|
||||
parts = append(parts, p)
|
||||
}
|
||||
}
|
||||
return strings.Join(parts, " ")
|
||||
}
|
||||
|
||||
// Collector is the interface a collector has to implement.
|
||||
type Collector interface {
|
||||
// Get new metrics and expose them via prometheus registry.
|
||||
Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) (err error)
|
||||
}
|
||||
|
||||
type ScrapeContext struct {
|
||||
perfObjects map[string]*perflib.PerfObject
|
||||
}
|
||||
|
||||
// PrepareScrapeContext creates a ScrapeContext to be used during a single scrape
|
||||
func PrepareScrapeContext(collectors []string) (*ScrapeContext, error) {
|
||||
q := getPerfQuery(collectors) // TODO: Memoize
|
||||
objs, err := getPerflibSnapshot(q)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
return &ScrapeContext{objs}, nil
|
||||
}
|
||||
282
collector/container.go
Normal file
282
collector/container.go
Normal file
@@ -0,0 +1,282 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"github.com/Microsoft/hcsshim"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("container", NewContainerMetricsCollector)
|
||||
}
|
||||
|
||||
// A ContainerMetricsCollector is a Prometheus collector for containers metrics
|
||||
type ContainerMetricsCollector struct {
|
||||
// Presence
|
||||
ContainerAvailable *prometheus.Desc
|
||||
|
||||
// Number of containers
|
||||
ContainersCount *prometheus.Desc
|
||||
// memory
|
||||
UsageCommitBytes *prometheus.Desc
|
||||
UsageCommitPeakBytes *prometheus.Desc
|
||||
UsagePrivateWorkingSetBytes *prometheus.Desc
|
||||
|
||||
// CPU
|
||||
RuntimeTotal *prometheus.Desc
|
||||
RuntimeUser *prometheus.Desc
|
||||
RuntimeKernel *prometheus.Desc
|
||||
|
||||
// Network
|
||||
BytesReceived *prometheus.Desc
|
||||
BytesSent *prometheus.Desc
|
||||
PacketsReceived *prometheus.Desc
|
||||
PacketsSent *prometheus.Desc
|
||||
DroppedPacketsIncoming *prometheus.Desc
|
||||
DroppedPacketsOutgoing *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewContainerMetricsCollector constructs a new ContainerMetricsCollector
|
||||
func NewContainerMetricsCollector() (Collector, error) {
|
||||
const subsystem = "container"
|
||||
return &ContainerMetricsCollector{
|
||||
ContainerAvailable: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "available"),
|
||||
"Available",
|
||||
[]string{"container_id"},
|
||||
nil,
|
||||
),
|
||||
ContainersCount: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "count"),
|
||||
"Number of containers",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
UsageCommitBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "memory_usage_commit_bytes"),
|
||||
"Memory Usage Commit Bytes",
|
||||
[]string{"container_id"},
|
||||
nil,
|
||||
),
|
||||
UsageCommitPeakBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "memory_usage_commit_peak_bytes"),
|
||||
"Memory Usage Commit Peak Bytes",
|
||||
[]string{"container_id"},
|
||||
nil,
|
||||
),
|
||||
UsagePrivateWorkingSetBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "memory_usage_private_working_set_bytes"),
|
||||
"Memory Usage Private Working Set Bytes",
|
||||
[]string{"container_id"},
|
||||
nil,
|
||||
),
|
||||
RuntimeTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "cpu_usage_seconds_total"),
|
||||
"Total Run time in Seconds",
|
||||
[]string{"container_id"},
|
||||
nil,
|
||||
),
|
||||
RuntimeUser: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "cpu_usage_seconds_usermode"),
|
||||
"Run Time in User mode in Seconds",
|
||||
[]string{"container_id"},
|
||||
nil,
|
||||
),
|
||||
RuntimeKernel: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "cpu_usage_seconds_kernelmode"),
|
||||
"Run time in Kernel mode in Seconds",
|
||||
[]string{"container_id"},
|
||||
nil,
|
||||
),
|
||||
BytesReceived: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "network_receive_bytes_total"),
|
||||
"Bytes Received on Interface",
|
||||
[]string{"container_id", "interface"},
|
||||
nil,
|
||||
),
|
||||
BytesSent: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "network_transmit_bytes_total"),
|
||||
"Bytes Sent on Interface",
|
||||
[]string{"container_id", "interface"},
|
||||
nil,
|
||||
),
|
||||
PacketsReceived: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "network_receive_packets_total"),
|
||||
"Packets Received on Interface",
|
||||
[]string{"container_id", "interface"},
|
||||
nil,
|
||||
),
|
||||
PacketsSent: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "network_transmit_packets_total"),
|
||||
"Packets Sent on Interface",
|
||||
[]string{"container_id", "interface"},
|
||||
nil,
|
||||
),
|
||||
DroppedPacketsIncoming: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "network_receive_packets_dropped_total"),
|
||||
"Dropped Incoming Packets on Interface",
|
||||
[]string{"container_id", "interface"},
|
||||
nil,
|
||||
),
|
||||
DroppedPacketsOutgoing: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "network_transmit_packets_dropped_total"),
|
||||
"Dropped Outgoing Packets on Interface",
|
||||
[]string{"container_id", "interface"},
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *ContainerMetricsCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting ContainerMetricsCollector metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// containerClose closes the container resource
|
||||
func containerClose(c hcsshim.Container) {
|
||||
err := c.Close()
|
||||
if err != nil {
|
||||
log.Error(err)
|
||||
}
|
||||
}
|
||||
|
||||
func (c *ContainerMetricsCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
|
||||
// Types Container is passed to get the containers compute systems only
|
||||
containers, err := hcsshim.GetContainers(hcsshim.ComputeSystemQuery{Types: []string{"Container"}})
|
||||
if err != nil {
|
||||
log.Error("Err in Getting containers:", err)
|
||||
return nil, err
|
||||
}
|
||||
|
||||
count := len(containers)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ContainersCount,
|
||||
prometheus.GaugeValue,
|
||||
float64(count),
|
||||
)
|
||||
if count == 0 {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
for _, containerDetails := range containers {
|
||||
containerId := containerDetails.ID
|
||||
|
||||
container, err := hcsshim.OpenContainer(containerId)
|
||||
if container != nil {
|
||||
defer containerClose(container)
|
||||
}
|
||||
if err != nil {
|
||||
log.Error("err in opening container: ", containerId, err)
|
||||
continue
|
||||
}
|
||||
|
||||
cstats, err := container.Statistics()
|
||||
if err != nil {
|
||||
log.Error("err in fetching container Statistics: ", containerId, err)
|
||||
continue
|
||||
}
|
||||
// HCS V1 is for docker runtime. Add the docker:// prefix on container_id
|
||||
containerId = "docker://" + containerId
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ContainerAvailable,
|
||||
prometheus.CounterValue,
|
||||
1,
|
||||
containerId,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.UsageCommitBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(cstats.Memory.UsageCommitBytes),
|
||||
containerId,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.UsageCommitPeakBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(cstats.Memory.UsageCommitPeakBytes),
|
||||
containerId,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.UsagePrivateWorkingSetBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(cstats.Memory.UsagePrivateWorkingSetBytes),
|
||||
containerId,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.RuntimeTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(cstats.Processor.TotalRuntime100ns)*ticksToSecondsScaleFactor,
|
||||
containerId,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.RuntimeUser,
|
||||
prometheus.CounterValue,
|
||||
float64(cstats.Processor.RuntimeUser100ns)*ticksToSecondsScaleFactor,
|
||||
containerId,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.RuntimeKernel,
|
||||
prometheus.CounterValue,
|
||||
float64(cstats.Processor.RuntimeKernel100ns)*ticksToSecondsScaleFactor,
|
||||
containerId,
|
||||
)
|
||||
|
||||
if len(cstats.Network) == 0 {
|
||||
log.Info("No Network Stats for container: ", containerId)
|
||||
continue
|
||||
}
|
||||
|
||||
networkStats := cstats.Network
|
||||
|
||||
for _, networkInterface := range networkStats {
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.BytesReceived,
|
||||
prometheus.CounterValue,
|
||||
float64(networkInterface.BytesReceived),
|
||||
containerId, networkInterface.EndpointId,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.BytesSent,
|
||||
prometheus.CounterValue,
|
||||
float64(networkInterface.BytesSent),
|
||||
containerId, networkInterface.EndpointId,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PacketsReceived,
|
||||
prometheus.CounterValue,
|
||||
float64(networkInterface.PacketsReceived),
|
||||
containerId, networkInterface.EndpointId,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PacketsSent,
|
||||
prometheus.CounterValue,
|
||||
float64(networkInterface.PacketsSent),
|
||||
containerId, networkInterface.EndpointId,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.DroppedPacketsIncoming,
|
||||
prometheus.CounterValue,
|
||||
float64(networkInterface.DroppedPacketsIncoming),
|
||||
containerId, networkInterface.EndpointId,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.DroppedPacketsOutgoing,
|
||||
prometheus.CounterValue,
|
||||
float64(networkInterface.DroppedPacketsOutgoing),
|
||||
containerId, networkInterface.EndpointId,
|
||||
)
|
||||
break
|
||||
}
|
||||
}
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
375
collector/cpu.go
Normal file
375
collector/cpu.go
Normal file
@@ -0,0 +1,375 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"strings"
|
||||
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
)
|
||||
|
||||
func init() {
|
||||
var deps string
|
||||
// See below for 6.05 magic value
|
||||
if getWindowsVersion() > 6.05 {
|
||||
deps = "Processor Information"
|
||||
} else {
|
||||
deps = "Processor"
|
||||
}
|
||||
registerCollector("cpu", newCPUCollector, deps)
|
||||
}
|
||||
|
||||
type cpuCollectorBasic struct {
|
||||
CStateSecondsTotal *prometheus.Desc
|
||||
TimeTotal *prometheus.Desc
|
||||
InterruptsTotal *prometheus.Desc
|
||||
DPCsTotal *prometheus.Desc
|
||||
}
|
||||
type cpuCollectorFull struct {
|
||||
CStateSecondsTotal *prometheus.Desc
|
||||
TimeTotal *prometheus.Desc
|
||||
InterruptsTotal *prometheus.Desc
|
||||
DPCsTotal *prometheus.Desc
|
||||
ClockInterruptsTotal *prometheus.Desc
|
||||
IdleBreakEventsTotal *prometheus.Desc
|
||||
ParkingStatus *prometheus.Desc
|
||||
ProcessorFrequencyMHz *prometheus.Desc
|
||||
ProcessorMaxFrequencyMHz *prometheus.Desc
|
||||
ProcessorPerformance *prometheus.Desc
|
||||
}
|
||||
|
||||
// newCPUCollector constructs a new cpuCollector, appropriate for the running OS
|
||||
func newCPUCollector() (Collector, error) {
|
||||
const subsystem = "cpu"
|
||||
|
||||
version := getWindowsVersion()
|
||||
// For Windows 2008 (version 6.0) or earlier we only have the "Processor"
|
||||
// class. As of Windows 2008 R2 (version 6.1) the more detailed
|
||||
// "Processor Information" set is available (although some of the counters
|
||||
// are added in later versions, so we aren't guaranteed to get all of
|
||||
// them).
|
||||
// Value 6.05 was selected to split between Windows versions.
|
||||
if version < 6.05 {
|
||||
return &cpuCollectorBasic{
|
||||
CStateSecondsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "cstate_seconds_total"),
|
||||
"Time spent in low-power idle state",
|
||||
[]string{"core", "state"},
|
||||
nil,
|
||||
),
|
||||
TimeTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "time_total"),
|
||||
"Time that processor spent in different modes (idle, user, system, ...)",
|
||||
[]string{"core", "mode"},
|
||||
nil,
|
||||
),
|
||||
InterruptsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "interrupts_total"),
|
||||
"Total number of received and serviced hardware interrupts",
|
||||
[]string{"core"},
|
||||
nil,
|
||||
),
|
||||
DPCsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "dpcs_total"),
|
||||
"Total number of received and serviced deferred procedure calls (DPCs)",
|
||||
[]string{"core"},
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
return &cpuCollectorFull{
|
||||
CStateSecondsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "cstate_seconds_total"),
|
||||
"Time spent in low-power idle state",
|
||||
[]string{"core", "state"},
|
||||
nil,
|
||||
),
|
||||
TimeTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "time_total"),
|
||||
"Time that processor spent in different modes (idle, user, system, ...)",
|
||||
[]string{"core", "mode"},
|
||||
nil,
|
||||
),
|
||||
InterruptsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "interrupts_total"),
|
||||
"Total number of received and serviced hardware interrupts",
|
||||
[]string{"core"},
|
||||
nil,
|
||||
),
|
||||
DPCsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "dpcs_total"),
|
||||
"Total number of received and serviced deferred procedure calls (DPCs)",
|
||||
[]string{"core"},
|
||||
nil,
|
||||
),
|
||||
ClockInterruptsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "clock_interrupts_total"),
|
||||
"Total number of received and serviced clock tick interrupts",
|
||||
[]string{"core"},
|
||||
nil,
|
||||
),
|
||||
IdleBreakEventsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "idle_break_events_total"),
|
||||
"Total number of time processor was woken from idle",
|
||||
[]string{"core"},
|
||||
nil,
|
||||
),
|
||||
ParkingStatus: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "parking_status"),
|
||||
"Parking Status represents whether a processor is parked or not",
|
||||
[]string{"core"},
|
||||
nil,
|
||||
),
|
||||
ProcessorFrequencyMHz: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "core_frequency_mhz"),
|
||||
"Core frequency in megahertz",
|
||||
[]string{"core"},
|
||||
nil,
|
||||
),
|
||||
ProcessorPerformance: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "processor_performance"),
|
||||
"Processor Performance is the average performance of the processor while it is executing instructions, as a percentage of the nominal performance of the processor. On some processors, Processor Performance may exceed 100%",
|
||||
[]string{"core"},
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
type perflibProcessor struct {
|
||||
Name string
|
||||
C1Transitions float64 `perflib:"C1 Transitions/sec"`
|
||||
C2Transitions float64 `perflib:"C2 Transitions/sec"`
|
||||
C3Transitions float64 `perflib:"C3 Transitions/sec"`
|
||||
DPCRate float64 `perflib:"DPC Rate"`
|
||||
DPCsQueued float64 `perflib:"DPCs Queued/sec"`
|
||||
Interrupts float64 `perflib:"Interrupts/sec"`
|
||||
PercentC2Time float64 `perflib:"% C1 Time"`
|
||||
PercentC3Time float64 `perflib:"% C2 Time"`
|
||||
PercentC1Time float64 `perflib:"% C3 Time"`
|
||||
PercentDPCTime float64 `perflib:"% DPC Time"`
|
||||
PercentIdleTime float64 `perflib:"% Idle Time"`
|
||||
PercentInterruptTime float64 `perflib:"% Interrupt Time"`
|
||||
PercentPrivilegedTime float64 `perflib:"% Privileged Time"`
|
||||
PercentProcessorTime float64 `perflib:"% Processor Time"`
|
||||
PercentUserTime float64 `perflib:"% User Time"`
|
||||
}
|
||||
|
||||
func (c *cpuCollectorBasic) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
data := make([]perflibProcessor, 0)
|
||||
err := unmarshalObject(ctx.perfObjects["Processor"], &data)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
for _, cpu := range data {
|
||||
if strings.Contains(strings.ToLower(cpu.Name), "_total") {
|
||||
continue
|
||||
}
|
||||
core := cpu.Name
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CStateSecondsTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.PercentC1Time,
|
||||
core, "c1",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CStateSecondsTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.PercentC2Time,
|
||||
core, "c2",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CStateSecondsTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.PercentC3Time,
|
||||
core, "c3",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TimeTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.PercentIdleTime,
|
||||
core, "idle",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TimeTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.PercentInterruptTime,
|
||||
core, "interrupt",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TimeTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.PercentDPCTime,
|
||||
core, "dpc",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TimeTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.PercentPrivilegedTime,
|
||||
core, "privileged",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TimeTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.PercentUserTime,
|
||||
core, "user",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.InterruptsTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.Interrupts,
|
||||
core,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.DPCsTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.DPCsQueued,
|
||||
core,
|
||||
)
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
type perflibProcessorInformation struct {
|
||||
Name string
|
||||
C1TimeSeconds float64 `perflib:"% C1 Time"`
|
||||
C2TimeSeconds float64 `perflib:"% C2 Time"`
|
||||
C3TimeSeconds float64 `perflib:"% C3 Time"`
|
||||
C1TransitionsTotal float64 `perflib:"C1 Transitions/sec"`
|
||||
C2TransitionsTotal float64 `perflib:"C2 Transitions/sec"`
|
||||
C3TransitionsTotal float64 `perflib:"C3 Transitions/sec"`
|
||||
ClockInterruptsTotal float64 `perflib:"Clock Interrupts/sec"`
|
||||
DPCsQueuedTotal float64 `perflib:"DPCs Queued/sec"`
|
||||
DPCTimeSeconds float64 `perflib:"% DPC Time"`
|
||||
IdleBreakEventsTotal float64 `perflib:"Idle Break Events/sec"`
|
||||
IdleTimeSeconds float64 `perflib:"% Idle Time"`
|
||||
InterruptsTotal float64 `perflib:"Interrupts/sec"`
|
||||
InterruptTimeSeconds float64 `perflib:"% Interrupt Time"`
|
||||
ParkingStatus float64 `perflib:"Parking Status"`
|
||||
PerformanceLimitPercent float64 `perflib:"% Performance Limit"`
|
||||
PriorityTimeSeconds float64 `perflib:"% Priority Time"`
|
||||
PrivilegedTimeSeconds float64 `perflib:"% Privileged Time"`
|
||||
PrivilegedUtilitySeconds float64 `perflib:"% Privileged Utility"`
|
||||
ProcessorFrequencyMHz float64 `perflib:"Processor Frequency"`
|
||||
ProcessorPerformance float64 `perflib:"% Processor Performance"`
|
||||
ProcessorTimeSeconds float64 `perflib:"% Processor Time"`
|
||||
ProcessorUtilityRate float64 `perflib:"% Processor Utility"`
|
||||
UserTimeSeconds float64 `perflib:"% User Time"`
|
||||
}
|
||||
|
||||
func (c *cpuCollectorFull) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
data := make([]perflibProcessorInformation, 0)
|
||||
err := unmarshalObject(ctx.perfObjects["Processor Information"], &data)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
for _, cpu := range data {
|
||||
if strings.Contains(strings.ToLower(cpu.Name), "_total") {
|
||||
continue
|
||||
}
|
||||
core := cpu.Name
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CStateSecondsTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.C1TimeSeconds,
|
||||
core, "c1",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CStateSecondsTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.C2TimeSeconds,
|
||||
core, "c2",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CStateSecondsTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.C3TimeSeconds,
|
||||
core, "c3",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TimeTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.IdleTimeSeconds,
|
||||
core, "idle",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TimeTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.InterruptTimeSeconds,
|
||||
core, "interrupt",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TimeTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.DPCTimeSeconds,
|
||||
core, "dpc",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TimeTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.PrivilegedTimeSeconds,
|
||||
core, "privileged",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TimeTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.UserTimeSeconds,
|
||||
core, "user",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.InterruptsTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.InterruptsTotal,
|
||||
core,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.DPCsTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.DPCsQueuedTotal,
|
||||
core,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ClockInterruptsTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.ClockInterruptsTotal,
|
||||
core,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.IdleBreakEventsTotal,
|
||||
prometheus.CounterValue,
|
||||
cpu.IdleBreakEventsTotal,
|
||||
core,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ParkingStatus,
|
||||
prometheus.GaugeValue,
|
||||
cpu.ParkingStatus,
|
||||
core,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ProcessorFrequencyMHz,
|
||||
prometheus.GaugeValue,
|
||||
cpu.ProcessorFrequencyMHz,
|
||||
core,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ProcessorPerformance,
|
||||
prometheus.GaugeValue,
|
||||
cpu.ProcessorPerformance,
|
||||
core,
|
||||
)
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
112
collector/cs.go
Normal file
112
collector/cs.go
Normal file
@@ -0,0 +1,112 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"errors"
|
||||
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("cs", NewCSCollector)
|
||||
}
|
||||
|
||||
// A CSCollector is a Prometheus collector for WMI metrics
|
||||
type CSCollector struct {
|
||||
PhysicalMemoryBytes *prometheus.Desc
|
||||
LogicalProcessors *prometheus.Desc
|
||||
Hostname *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewCSCollector ...
|
||||
func NewCSCollector() (Collector, error) {
|
||||
const subsystem = "cs"
|
||||
|
||||
return &CSCollector{
|
||||
LogicalProcessors: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "logical_processors"),
|
||||
"ComputerSystem.NumberOfLogicalProcessors",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
PhysicalMemoryBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "physical_memory_bytes"),
|
||||
"ComputerSystem.TotalPhysicalMemory",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
Hostname: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "hostname"),
|
||||
"Labeled system hostname information as provided by ComputerSystem.DNSHostName and ComputerSystem.Domain",
|
||||
[]string{
|
||||
"hostname",
|
||||
"domain",
|
||||
"fqdn"},
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *CSCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting cs metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Win32_ComputerSystem docs:
|
||||
// - https://msdn.microsoft.com/en-us/library/aa394102
|
||||
type Win32_ComputerSystem struct {
|
||||
NumberOfLogicalProcessors uint32
|
||||
TotalPhysicalMemory uint64
|
||||
DNSHostname string
|
||||
Domain string
|
||||
Workgroup *string
|
||||
}
|
||||
|
||||
func (c *CSCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_ComputerSystem
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if len(dst) == 0 {
|
||||
return nil, errors.New("WMI query returned empty result set")
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.LogicalProcessors,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].NumberOfLogicalProcessors),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PhysicalMemoryBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].TotalPhysicalMemory),
|
||||
)
|
||||
|
||||
var fqdn string
|
||||
if dst[0].Workgroup == nil || dst[0].Domain != *dst[0].Workgroup {
|
||||
fqdn = dst[0].DNSHostname + "." + dst[0].Domain
|
||||
} else {
|
||||
fqdn = dst[0].DNSHostname
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Hostname,
|
||||
prometheus.GaugeValue,
|
||||
1.0,
|
||||
dst[0].DNSHostname,
|
||||
dst[0].Domain,
|
||||
fqdn,
|
||||
)
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
498
collector/dns.go
Normal file
498
collector/dns.go
Normal file
@@ -0,0 +1,498 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"errors"
|
||||
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("dns", NewDNSCollector)
|
||||
}
|
||||
|
||||
// A DNSCollector is a Prometheus collector for WMI Win32_PerfRawData_DNS_DNS metrics
|
||||
type DNSCollector struct {
|
||||
ZoneTransferRequestsReceived *prometheus.Desc
|
||||
ZoneTransferRequestsSent *prometheus.Desc
|
||||
ZoneTransferResponsesReceived *prometheus.Desc
|
||||
ZoneTransferSuccessReceived *prometheus.Desc
|
||||
ZoneTransferSuccessSent *prometheus.Desc
|
||||
ZoneTransferFailures *prometheus.Desc
|
||||
MemoryUsedBytes *prometheus.Desc
|
||||
DynamicUpdatesQueued *prometheus.Desc
|
||||
DynamicUpdatesReceived *prometheus.Desc
|
||||
DynamicUpdatesFailures *prometheus.Desc
|
||||
NotifyReceived *prometheus.Desc
|
||||
NotifySent *prometheus.Desc
|
||||
SecureUpdateFailures *prometheus.Desc
|
||||
SecureUpdateReceived *prometheus.Desc
|
||||
Queries *prometheus.Desc
|
||||
Responses *prometheus.Desc
|
||||
RecursiveQueries *prometheus.Desc
|
||||
RecursiveQueryFailures *prometheus.Desc
|
||||
RecursiveQuerySendTimeouts *prometheus.Desc
|
||||
WinsQueries *prometheus.Desc
|
||||
WinsResponses *prometheus.Desc
|
||||
UnmatchedResponsesReceived *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewDNSCollector ...
|
||||
func NewDNSCollector() (Collector, error) {
|
||||
const subsystem = "dns"
|
||||
return &DNSCollector{
|
||||
ZoneTransferRequestsReceived: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "zone_transfer_requests_received_total"),
|
||||
"Number of zone transfer requests (AXFR/IXFR) received by the master DNS server",
|
||||
[]string{"qtype"},
|
||||
nil,
|
||||
),
|
||||
ZoneTransferRequestsSent: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "zone_transfer_requests_sent_total"),
|
||||
"Number of zone transfer requests (AXFR/IXFR) sent by the secondary DNS server",
|
||||
[]string{"qtype"},
|
||||
nil,
|
||||
),
|
||||
ZoneTransferResponsesReceived: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "zone_transfer_response_received_total"),
|
||||
"Number of zone transfer responses (AXFR/IXFR) received by the secondary DNS server",
|
||||
[]string{"qtype"},
|
||||
nil,
|
||||
),
|
||||
ZoneTransferSuccessReceived: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "zone_transfer_success_received_total"),
|
||||
"Number of successful zone transfers (AXFR/IXFR) received by the secondary DNS server",
|
||||
[]string{"qtype", "protocol"},
|
||||
nil,
|
||||
),
|
||||
ZoneTransferSuccessSent: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "zone_transfer_success_sent_total"),
|
||||
"Number of successful zone transfers (AXFR/IXFR) of the master DNS server",
|
||||
[]string{"qtype"},
|
||||
nil,
|
||||
),
|
||||
ZoneTransferFailures: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "zone_transfer_failures_total"),
|
||||
"Number of failed zone transfers of the master DNS server",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
MemoryUsedBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "memory_used_bytes_total"),
|
||||
"Total memory used by DNS server",
|
||||
[]string{"area"},
|
||||
nil,
|
||||
),
|
||||
DynamicUpdatesQueued: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "dynamic_updates_queued"),
|
||||
"Number of dynamic updates queued by the DNS server",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
DynamicUpdatesReceived: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "dynamic_updates_received_total"),
|
||||
"Number of secure update requests received by the DNS server",
|
||||
[]string{"operation"},
|
||||
nil,
|
||||
),
|
||||
DynamicUpdatesFailures: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "dynamic_updates_failures_total"),
|
||||
"Number of dynamic updates which timed out or were rejected by the DNS server",
|
||||
[]string{"reason"},
|
||||
nil,
|
||||
),
|
||||
NotifyReceived: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "notify_received_total"),
|
||||
"Number of notifies received by the secondary DNS server",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
NotifySent: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "notify_sent_total"),
|
||||
"Number of notifies sent by the master DNS server",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SecureUpdateFailures: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "secure_update_failures_total"),
|
||||
"Number of secure updates that failed on the DNS server",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SecureUpdateReceived: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "secure_update_received_total"),
|
||||
"Number of secure update requests received by the DNS server",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
Queries: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "queries_total"),
|
||||
"Number of queries received by DNS server",
|
||||
[]string{"protocol"},
|
||||
nil,
|
||||
),
|
||||
Responses: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "responses_total"),
|
||||
"Number of reponses sent by DNS server",
|
||||
[]string{"protocol"},
|
||||
nil,
|
||||
),
|
||||
RecursiveQueries: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "recursive_queries_total"),
|
||||
"Number of recursive queries received by DNS server",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
RecursiveQueryFailures: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "recursive_query_failures_total"),
|
||||
"Number of recursive query failures",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
RecursiveQuerySendTimeouts: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "recursive_query_send_timeouts_total"),
|
||||
"Number of recursive query sending timeouts",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
WinsQueries: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "wins_queries_total"),
|
||||
"Number of WINS lookup requests received by the server",
|
||||
[]string{"direction"},
|
||||
nil,
|
||||
),
|
||||
WinsResponses: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "wins_responses_total"),
|
||||
"Number of WINS lookup responses sent by the server",
|
||||
[]string{"direction"},
|
||||
nil,
|
||||
),
|
||||
UnmatchedResponsesReceived: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "unmatched_responses_total"),
|
||||
"Number of response packets received by the DNS server that do not match any outstanding remote query",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *DNSCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting dns metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Win32_PerfRawData_DNS_DNS docs:
|
||||
// - https://msdn.microsoft.com/en-us/library/ms803992.aspx?f=255&MSPPError=-2147217396
|
||||
// - https://technet.microsoft.com/en-us/library/cc977686.aspx
|
||||
type Win32_PerfRawData_DNS_DNS struct {
|
||||
AXFRRequestReceived uint32
|
||||
AXFRRequestSent uint32
|
||||
AXFRResponseReceived uint32
|
||||
AXFRSuccessReceived uint32
|
||||
AXFRSuccessSent uint32
|
||||
CachingMemory uint32
|
||||
DatabaseNodeMemory uint32
|
||||
DynamicUpdateNoOperation uint32
|
||||
DynamicUpdateQueued uint32
|
||||
DynamicUpdateRejected uint32
|
||||
DynamicUpdateTimeOuts uint32
|
||||
DynamicUpdateWrittentoDatabase uint32
|
||||
IXFRRequestReceived uint32
|
||||
IXFRRequestSent uint32
|
||||
IXFRResponseReceived uint32
|
||||
IXFRSuccessSent uint32
|
||||
IXFRTCPSuccessReceived uint32
|
||||
IXFRUDPSuccessReceived uint32
|
||||
NbstatMemory uint32
|
||||
NotifyReceived uint32
|
||||
NotifySent uint32
|
||||
RecordFlowMemory uint32
|
||||
RecursiveQueries uint32
|
||||
RecursiveQueryFailure uint32
|
||||
RecursiveSendTimeOuts uint32
|
||||
SecureUpdateFailure uint32
|
||||
SecureUpdateReceived uint32
|
||||
TCPMessageMemory uint32
|
||||
TCPQueryReceived uint32
|
||||
TCPResponseSent uint32
|
||||
UDPMessageMemory uint32
|
||||
UDPQueryReceived uint32
|
||||
UDPResponseSent uint32
|
||||
UnmatchedResponsesReceived uint32
|
||||
WINSLookupReceived uint32
|
||||
WINSResponseSent uint32
|
||||
WINSReverseLookupReceived uint32
|
||||
WINSReverseResponseSent uint32
|
||||
ZoneTransferFailure uint32
|
||||
ZoneTransferSOARequestSent uint32
|
||||
}
|
||||
|
||||
func (c *DNSCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_DNS_DNS
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if len(dst) == 0 {
|
||||
return nil, errors.New("WMI query returned empty result set")
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ZoneTransferRequestsReceived,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].AXFRRequestReceived),
|
||||
"full",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ZoneTransferRequestsReceived,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].IXFRRequestReceived),
|
||||
"incremental",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ZoneTransferRequestsSent,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].AXFRRequestSent),
|
||||
"full",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ZoneTransferRequestsSent,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].IXFRRequestSent),
|
||||
"incremental",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ZoneTransferRequestsSent,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].ZoneTransferSOARequestSent),
|
||||
"soa",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ZoneTransferResponsesReceived,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].AXFRResponseReceived),
|
||||
"full",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ZoneTransferResponsesReceived,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].IXFRResponseReceived),
|
||||
"incremental",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ZoneTransferSuccessReceived,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].AXFRSuccessReceived),
|
||||
"full",
|
||||
"tcp",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ZoneTransferSuccessReceived,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].IXFRTCPSuccessReceived),
|
||||
"incremental",
|
||||
"tcp",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ZoneTransferSuccessReceived,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].IXFRTCPSuccessReceived),
|
||||
"incremental",
|
||||
"udp",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ZoneTransferSuccessSent,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].AXFRSuccessSent),
|
||||
"full",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ZoneTransferSuccessSent,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].IXFRSuccessSent),
|
||||
"incremental",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ZoneTransferFailures,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].ZoneTransferFailure),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemoryUsedBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].CachingMemory),
|
||||
"caching",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemoryUsedBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].DatabaseNodeMemory),
|
||||
"database_node",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemoryUsedBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].NbstatMemory),
|
||||
"nbstat",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemoryUsedBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].RecordFlowMemory),
|
||||
"record_flow",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemoryUsedBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].TCPMessageMemory),
|
||||
"tcp_message",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemoryUsedBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].UDPMessageMemory),
|
||||
"udp_message",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.DynamicUpdatesReceived,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].DynamicUpdateNoOperation),
|
||||
"noop",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.DynamicUpdatesReceived,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].DynamicUpdateWrittentoDatabase),
|
||||
"written",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.DynamicUpdatesQueued,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].DynamicUpdateQueued),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.DynamicUpdatesFailures,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].DynamicUpdateRejected),
|
||||
"rejected",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.DynamicUpdatesFailures,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].DynamicUpdateTimeOuts),
|
||||
"timeout",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NotifyReceived,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].NotifyReceived),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NotifySent,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].NotifySent),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.RecursiveQueries,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].RecursiveQueries),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.RecursiveQueryFailures,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].RecursiveQueryFailure),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.RecursiveQuerySendTimeouts,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].RecursiveSendTimeOuts),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Queries,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].TCPQueryReceived),
|
||||
"tcp",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Queries,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].UDPQueryReceived),
|
||||
"udp",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Responses,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].TCPResponseSent),
|
||||
"tcp",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Responses,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].UDPResponseSent),
|
||||
"udp",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.UnmatchedResponsesReceived,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].UnmatchedResponsesReceived),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.WinsQueries,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].WINSLookupReceived),
|
||||
"forward",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.WinsQueries,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].WINSReverseLookupReceived),
|
||||
"reverse",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.WinsResponses,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].WINSResponseSent),
|
||||
"forward",
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.WinsResponses,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].WINSReverseResponseSent),
|
||||
"reverse",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SecureUpdateFailures,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].SecureUpdateFailure),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SecureUpdateReceived,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].SecureUpdateReceived),
|
||||
)
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
1423
collector/hyperv.go
Normal file
1423
collector/hyperv.go
Normal file
File diff suppressed because it is too large
Load Diff
1957
collector/iis.go
Normal file
1957
collector/iis.go
Normal file
File diff suppressed because it is too large
Load Diff
302
collector/logical_disk.go
Normal file
302
collector/logical_disk.go
Normal file
@@ -0,0 +1,302 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"regexp"
|
||||
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
"gopkg.in/alecthomas/kingpin.v2"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("logical_disk", NewLogicalDiskCollector, "LogicalDisk")
|
||||
}
|
||||
|
||||
var (
|
||||
volumeWhitelist = kingpin.Flag(
|
||||
"collector.logical_disk.volume-whitelist",
|
||||
"Regexp of volumes to whitelist. Volume name must both match whitelist and not match blacklist to be included.",
|
||||
).Default(".+").String()
|
||||
volumeBlacklist = kingpin.Flag(
|
||||
"collector.logical_disk.volume-blacklist",
|
||||
"Regexp of volumes to blacklist. Volume name must both match whitelist and not match blacklist to be included.",
|
||||
).Default("").String()
|
||||
)
|
||||
|
||||
// A LogicalDiskCollector is a Prometheus collector for perflib logicalDisk metrics
|
||||
type LogicalDiskCollector struct {
|
||||
RequestsQueued *prometheus.Desc
|
||||
ReadBytesTotal *prometheus.Desc
|
||||
ReadsTotal *prometheus.Desc
|
||||
WriteBytesTotal *prometheus.Desc
|
||||
WritesTotal *prometheus.Desc
|
||||
ReadTime *prometheus.Desc
|
||||
WriteTime *prometheus.Desc
|
||||
TotalSpace *prometheus.Desc
|
||||
FreeSpace *prometheus.Desc
|
||||
IdleTime *prometheus.Desc
|
||||
SplitIOs *prometheus.Desc
|
||||
ReadLatency *prometheus.Desc
|
||||
WriteLatency *prometheus.Desc
|
||||
ReadWriteLatency *prometheus.Desc
|
||||
|
||||
volumeWhitelistPattern *regexp.Regexp
|
||||
volumeBlacklistPattern *regexp.Regexp
|
||||
}
|
||||
|
||||
// NewLogicalDiskCollector ...
|
||||
func NewLogicalDiskCollector() (Collector, error) {
|
||||
const subsystem = "logical_disk"
|
||||
|
||||
return &LogicalDiskCollector{
|
||||
RequestsQueued: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "requests_queued"),
|
||||
"The number of requests queued to the disk (LogicalDisk.CurrentDiskQueueLength)",
|
||||
[]string{"volume"},
|
||||
nil,
|
||||
),
|
||||
|
||||
ReadBytesTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "read_bytes_total"),
|
||||
"The number of bytes transferred from the disk during read operations (LogicalDisk.DiskReadBytesPerSec)",
|
||||
[]string{"volume"},
|
||||
nil,
|
||||
),
|
||||
|
||||
ReadsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "reads_total"),
|
||||
"The number of read operations on the disk (LogicalDisk.DiskReadsPerSec)",
|
||||
[]string{"volume"},
|
||||
nil,
|
||||
),
|
||||
|
||||
WriteBytesTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "write_bytes_total"),
|
||||
"The number of bytes transferred to the disk during write operations (LogicalDisk.DiskWriteBytesPerSec)",
|
||||
[]string{"volume"},
|
||||
nil,
|
||||
),
|
||||
|
||||
WritesTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "writes_total"),
|
||||
"The number of write operations on the disk (LogicalDisk.DiskWritesPerSec)",
|
||||
[]string{"volume"},
|
||||
nil,
|
||||
),
|
||||
|
||||
ReadTime: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "read_seconds_total"),
|
||||
"Seconds that the disk was busy servicing read requests (LogicalDisk.PercentDiskReadTime)",
|
||||
[]string{"volume"},
|
||||
nil,
|
||||
),
|
||||
|
||||
WriteTime: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "write_seconds_total"),
|
||||
"Seconds that the disk was busy servicing write requests (LogicalDisk.PercentDiskWriteTime)",
|
||||
[]string{"volume"},
|
||||
nil,
|
||||
),
|
||||
|
||||
FreeSpace: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "free_bytes"),
|
||||
"Free space in bytes (LogicalDisk.PercentFreeSpace)",
|
||||
[]string{"volume"},
|
||||
nil,
|
||||
),
|
||||
|
||||
TotalSpace: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "size_bytes"),
|
||||
"Total space in bytes (LogicalDisk.PercentFreeSpace_Base)",
|
||||
[]string{"volume"},
|
||||
nil,
|
||||
),
|
||||
|
||||
IdleTime: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "idle_seconds_total"),
|
||||
"Seconds that the disk was idle (LogicalDisk.PercentIdleTime)",
|
||||
[]string{"volume"},
|
||||
nil,
|
||||
),
|
||||
|
||||
SplitIOs: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "split_ios_total"),
|
||||
"The number of I/Os to the disk were split into multiple I/Os (LogicalDisk.SplitIOPerSec)",
|
||||
[]string{"volume"},
|
||||
nil,
|
||||
),
|
||||
|
||||
ReadLatency: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "read_latency_seconds_total"),
|
||||
"Shows the average time, in seconds, of a read operation from the disk (LogicalDisk.AvgDiskSecPerRead)",
|
||||
[]string{"volume"},
|
||||
nil,
|
||||
),
|
||||
|
||||
WriteLatency: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "write_latency_seconds_total"),
|
||||
"Shows the average time, in seconds, of a write operation to the disk (LogicalDisk.AvgDiskSecPerWrite)",
|
||||
[]string{"volume"},
|
||||
nil,
|
||||
),
|
||||
|
||||
ReadWriteLatency: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "read_write_latency_seconds_total"),
|
||||
"Shows the time, in seconds, of the average disk transfer (LogicalDisk.AvgDiskSecPerTransfer)",
|
||||
[]string{"volume"},
|
||||
nil,
|
||||
),
|
||||
|
||||
volumeWhitelistPattern: regexp.MustCompile(fmt.Sprintf("^(?:%s)$", *volumeWhitelist)),
|
||||
volumeBlacklistPattern: regexp.MustCompile(fmt.Sprintf("^(?:%s)$", *volumeBlacklist)),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *LogicalDiskCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ctx, ch); err != nil {
|
||||
log.Error("failed collecting logical_disk metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Win32_PerfRawData_PerfDisk_LogicalDisk docs:
|
||||
// - https://msdn.microsoft.com/en-us/windows/hardware/aa394307(v=vs.71) - Win32_PerfRawData_PerfDisk_LogicalDisk class
|
||||
// - https://msdn.microsoft.com/en-us/library/ms803973.aspx - LogicalDisk object reference
|
||||
type logicalDisk struct {
|
||||
Name string
|
||||
CurrentDiskQueueLength float64 `perflib:"Current Disk Queue Length"`
|
||||
DiskReadBytesPerSec float64 `perflib:"Disk Read Bytes/sec"`
|
||||
DiskReadsPerSec float64 `perflib:"Disk Reads/sec"`
|
||||
DiskWriteBytesPerSec float64 `perflib:"Disk Write Bytes/sec"`
|
||||
DiskWritesPerSec float64 `perflib:"Disk Writes/sec"`
|
||||
PercentDiskReadTime float64 `perflib:"% Disk Read Time"`
|
||||
PercentDiskWriteTime float64 `perflib:"% Disk Write Time"`
|
||||
PercentFreeSpace float64 `perflib:"% Free Space_Base"`
|
||||
PercentFreeSpace_Base float64 `perflib:"Free Megabytes"`
|
||||
PercentIdleTime float64 `perflib:"% Idle Time"`
|
||||
SplitIOPerSec float64 `perflib:"Split IO/Sec"`
|
||||
AvgDiskSecPerRead float64 `perflib:"Avg. Disk sec/Read"`
|
||||
AvgDiskSecPerWrite float64 `perflib:"Avg. Disk sec/Write"`
|
||||
AvgDiskSecPerTransfer float64 `perflib:"Avg. Disk sec/Transfer"`
|
||||
}
|
||||
|
||||
func (c *LogicalDiskCollector) collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []logicalDisk
|
||||
if err := unmarshalObject(ctx.perfObjects["LogicalDisk"], &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
for _, volume := range dst {
|
||||
if volume.Name == "_Total" ||
|
||||
c.volumeBlacklistPattern.MatchString(volume.Name) ||
|
||||
!c.volumeWhitelistPattern.MatchString(volume.Name) {
|
||||
continue
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.RequestsQueued,
|
||||
prometheus.GaugeValue,
|
||||
volume.CurrentDiskQueueLength,
|
||||
volume.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ReadBytesTotal,
|
||||
prometheus.CounterValue,
|
||||
volume.DiskReadBytesPerSec,
|
||||
volume.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ReadsTotal,
|
||||
prometheus.CounterValue,
|
||||
volume.DiskReadsPerSec,
|
||||
volume.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.WriteBytesTotal,
|
||||
prometheus.CounterValue,
|
||||
volume.DiskWriteBytesPerSec,
|
||||
volume.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.WritesTotal,
|
||||
prometheus.CounterValue,
|
||||
volume.DiskWritesPerSec,
|
||||
volume.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ReadTime,
|
||||
prometheus.CounterValue,
|
||||
volume.PercentDiskReadTime,
|
||||
volume.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.WriteTime,
|
||||
prometheus.CounterValue,
|
||||
volume.PercentDiskWriteTime,
|
||||
volume.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.FreeSpace,
|
||||
prometheus.GaugeValue,
|
||||
volume.PercentFreeSpace_Base*1024*1024,
|
||||
volume.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TotalSpace,
|
||||
prometheus.GaugeValue,
|
||||
volume.PercentFreeSpace*1024*1024,
|
||||
volume.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.IdleTime,
|
||||
prometheus.CounterValue,
|
||||
volume.PercentIdleTime,
|
||||
volume.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SplitIOs,
|
||||
prometheus.CounterValue,
|
||||
volume.SplitIOPerSec,
|
||||
volume.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ReadLatency,
|
||||
prometheus.CounterValue,
|
||||
volume.AvgDiskSecPerRead*ticksToSecondsScaleFactor,
|
||||
volume.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.WriteLatency,
|
||||
prometheus.CounterValue,
|
||||
volume.AvgDiskSecPerWrite*ticksToSecondsScaleFactor,
|
||||
volume.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ReadWriteLatency,
|
||||
prometheus.CounterValue,
|
||||
volume.AvgDiskSecPerTransfer*ticksToSecondsScaleFactor,
|
||||
volume.Name,
|
||||
)
|
||||
}
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
@@ -1,81 +1,43 @@
|
||||
//go:build windows
|
||||
// +build windows
|
||||
|
||||
package logon
|
||||
package collector
|
||||
|
||||
import (
|
||||
"errors"
|
||||
|
||||
"github.com/alecthomas/kingpin/v2"
|
||||
"github.com/go-kit/log"
|
||||
"github.com/go-kit/log/level"
|
||||
"github.com/prometheus-community/windows_exporter/pkg/types"
|
||||
"github.com/prometheus-community/windows_exporter/pkg/wmi"
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
const Name = "logon"
|
||||
|
||||
type Config struct{}
|
||||
|
||||
var ConfigDefaults = Config{}
|
||||
|
||||
// A Collector is a Prometheus Collector for WMI metrics.
|
||||
type Collector struct {
|
||||
config Config
|
||||
logger log.Logger
|
||||
|
||||
logonType *prometheus.Desc
|
||||
func init() {
|
||||
registerCollector("logon", NewLogonCollector)
|
||||
}
|
||||
|
||||
func New(logger log.Logger, config *Config) *Collector {
|
||||
if config == nil {
|
||||
config = &ConfigDefaults
|
||||
}
|
||||
|
||||
c := &Collector{
|
||||
config: *config,
|
||||
}
|
||||
|
||||
c.SetLogger(logger)
|
||||
|
||||
return c
|
||||
// A LogonCollector is a Prometheus collector for WMI metrics
|
||||
type LogonCollector struct {
|
||||
LogonType *prometheus.Desc
|
||||
}
|
||||
|
||||
func NewWithFlags(_ *kingpin.Application) *Collector {
|
||||
return &Collector{}
|
||||
}
|
||||
// NewLogonCollector ...
|
||||
func NewLogonCollector() (Collector, error) {
|
||||
const subsystem = "logon"
|
||||
|
||||
func (c *Collector) GetName() string {
|
||||
return Name
|
||||
}
|
||||
|
||||
func (c *Collector) SetLogger(logger log.Logger) {
|
||||
c.logger = log.With(logger, "collector", Name)
|
||||
}
|
||||
|
||||
func (c *Collector) GetPerfCounter() ([]string, error) {
|
||||
return []string{}, nil
|
||||
}
|
||||
|
||||
func (c *Collector) Close() error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (c *Collector) Build() error {
|
||||
c.logonType = prometheus.NewDesc(
|
||||
prometheus.BuildFQName(types.Namespace, Name, "logon_type"),
|
||||
"Number of active logon sessions (LogonSession.LogonType)",
|
||||
[]string{"status"},
|
||||
nil,
|
||||
)
|
||||
return nil
|
||||
return &LogonCollector{
|
||||
LogonType: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "logon_type"),
|
||||
"Number of active logon sessions (LogonSession.LogonType)",
|
||||
[]string{"status"},
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *Collector) Collect(_ *types.ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if err := c.collect(ch); err != nil {
|
||||
_ = level.Error(c.logger).Log("msg", "failed collecting user metrics", "err", err)
|
||||
func (c *LogonCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting user metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
@@ -87,14 +49,14 @@ type Win32_LogonSession struct {
|
||||
LogonType uint32
|
||||
}
|
||||
|
||||
func (c *Collector) collect(ch chan<- prometheus.Metric) error {
|
||||
func (c *LogonCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_LogonSession
|
||||
q := wmi.QueryAll(&dst, c.logger)
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return err
|
||||
return nil, err
|
||||
}
|
||||
if len(dst) == 0 {
|
||||
return errors.New("WMI query returned empty result set")
|
||||
return nil, errors.New("WMI query returned empty result set")
|
||||
}
|
||||
|
||||
// Init counters
|
||||
@@ -144,94 +106,94 @@ func (c *Collector) collect(ch chan<- prometheus.Metric) error {
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.logonType,
|
||||
c.LogonType,
|
||||
prometheus.GaugeValue,
|
||||
float64(system),
|
||||
"system",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.logonType,
|
||||
c.LogonType,
|
||||
prometheus.GaugeValue,
|
||||
float64(interactive),
|
||||
"interactive",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.logonType,
|
||||
c.LogonType,
|
||||
prometheus.GaugeValue,
|
||||
float64(network),
|
||||
"network",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.logonType,
|
||||
c.LogonType,
|
||||
prometheus.GaugeValue,
|
||||
float64(batch),
|
||||
"batch",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.logonType,
|
||||
c.LogonType,
|
||||
prometheus.GaugeValue,
|
||||
float64(service),
|
||||
"service",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.logonType,
|
||||
c.LogonType,
|
||||
prometheus.GaugeValue,
|
||||
float64(proxy),
|
||||
"proxy",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.logonType,
|
||||
c.LogonType,
|
||||
prometheus.GaugeValue,
|
||||
float64(unlock),
|
||||
"unlock",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.logonType,
|
||||
c.LogonType,
|
||||
prometheus.GaugeValue,
|
||||
float64(networkcleartext),
|
||||
"network_clear_text",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.logonType,
|
||||
c.LogonType,
|
||||
prometheus.GaugeValue,
|
||||
float64(newcredentials),
|
||||
"new_credentials",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.logonType,
|
||||
c.LogonType,
|
||||
prometheus.GaugeValue,
|
||||
float64(remoteinteractive),
|
||||
"remote_interactive",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.logonType,
|
||||
c.LogonType,
|
||||
prometheus.GaugeValue,
|
||||
float64(cachedinteractive),
|
||||
"cached_interactive",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.logonType,
|
||||
c.LogonType,
|
||||
prometheus.GaugeValue,
|
||||
float64(remoteinteractive),
|
||||
"cached_remote_interactive",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.logonType,
|
||||
c.LogonType,
|
||||
prometheus.GaugeValue,
|
||||
float64(cachedunlock),
|
||||
"cached_unlock",
|
||||
)
|
||||
return nil
|
||||
return nil, nil
|
||||
}
|
||||
502
collector/memory.go
Normal file
502
collector/memory.go
Normal file
@@ -0,0 +1,502 @@
|
||||
// returns data points from Win32_PerfRawData_PerfOS_Memory
|
||||
// <add link to documentation here> - Win32_PerfRawData_PerfOS_Memory class
|
||||
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("memory", NewMemoryCollector, "Memory")
|
||||
}
|
||||
|
||||
// A MemoryCollector is a Prometheus collector for perflib Memory metrics
|
||||
type MemoryCollector struct {
|
||||
AvailableBytes *prometheus.Desc
|
||||
CacheBytes *prometheus.Desc
|
||||
CacheBytesPeak *prometheus.Desc
|
||||
CacheFaultsTotal *prometheus.Desc
|
||||
CommitLimit *prometheus.Desc
|
||||
CommittedBytes *prometheus.Desc
|
||||
DemandZeroFaultsTotal *prometheus.Desc
|
||||
FreeAndZeroPageListBytes *prometheus.Desc
|
||||
FreeSystemPageTableEntries *prometheus.Desc
|
||||
ModifiedPageListBytes *prometheus.Desc
|
||||
PageFaultsTotal *prometheus.Desc
|
||||
SwapPageReadsTotal *prometheus.Desc
|
||||
SwapPagesReadTotal *prometheus.Desc
|
||||
SwapPagesWrittenTotal *prometheus.Desc
|
||||
SwapPageOperationsTotal *prometheus.Desc
|
||||
SwapPageWritesTotal *prometheus.Desc
|
||||
PoolNonpagedAllocsTotal *prometheus.Desc
|
||||
PoolNonpagedBytes *prometheus.Desc
|
||||
PoolPagedAllocsTotal *prometheus.Desc
|
||||
PoolPagedBytes *prometheus.Desc
|
||||
PoolPagedResidentBytes *prometheus.Desc
|
||||
StandbyCacheCoreBytes *prometheus.Desc
|
||||
StandbyCacheNormalPriorityBytes *prometheus.Desc
|
||||
StandbyCacheReserveBytes *prometheus.Desc
|
||||
SystemCacheResidentBytes *prometheus.Desc
|
||||
SystemCodeResidentBytes *prometheus.Desc
|
||||
SystemCodeTotalBytes *prometheus.Desc
|
||||
SystemDriverResidentBytes *prometheus.Desc
|
||||
SystemDriverTotalBytes *prometheus.Desc
|
||||
TransitionFaultsTotal *prometheus.Desc
|
||||
TransitionPagesRepurposedTotal *prometheus.Desc
|
||||
WriteCopiesTotal *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewMemoryCollector ...
|
||||
func NewMemoryCollector() (Collector, error) {
|
||||
const subsystem = "memory"
|
||||
|
||||
return &MemoryCollector{
|
||||
AvailableBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "available_bytes"),
|
||||
"The amount of physical memory immediately available for allocation to a process or for system use. It is equal to the sum of memory assigned to"+
|
||||
" the standby (cached), free and zero page lists (AvailableBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
CacheBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "cache_bytes"),
|
||||
"(CacheBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
CacheBytesPeak: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "cache_bytes_peak"),
|
||||
"(CacheBytesPeak)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
CacheFaultsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "cache_faults_total"),
|
||||
"(CacheFaultsPersec)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
CommitLimit: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "commit_limit"),
|
||||
"(CommitLimit)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
CommittedBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "committed_bytes"),
|
||||
"(CommittedBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
DemandZeroFaultsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "demand_zero_faults_total"),
|
||||
"The number of zeroed pages required to satisfy faults. Zeroed pages, pages emptied of previously stored data and filled with zeros, are a security"+
|
||||
" feature of Windows that prevent processes from seeing data stored by earlier processes that used the memory space (DemandZeroFaults)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
FreeAndZeroPageListBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "free_and_zero_page_list_bytes"),
|
||||
"(FreeAndZeroPageListBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
FreeSystemPageTableEntries: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "free_system_page_table_entries"),
|
||||
"(FreeSystemPageTableEntries)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
ModifiedPageListBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "modified_page_list_bytes"),
|
||||
"(ModifiedPageListBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
PageFaultsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "page_faults_total"),
|
||||
"(PageFaultsPersec)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SwapPageReadsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "swap_page_reads_total"),
|
||||
"Number of disk page reads (a single read operation reading several pages is still only counted once) (PageReadsPersec)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SwapPagesReadTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "swap_pages_read_total"),
|
||||
"Number of pages read across all page reads (ie counting all pages read even if they are read in a single operation) (PagesInputPersec)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SwapPagesWrittenTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "swap_pages_written_total"),
|
||||
"Number of pages written across all page writes (ie counting all pages written even if they are written in a single operation) (PagesOutputPersec)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SwapPageOperationsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "swap_page_operations_total"),
|
||||
"Total number of swap page read and writes (PagesPersec)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SwapPageWritesTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "swap_page_writes_total"),
|
||||
"Number of disk page writes (a single write operation writing several pages is still only counted once) (PageWritesPersec)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
PoolNonpagedAllocsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "pool_nonpaged_allocs_total"),
|
||||
"The number of calls to allocate space in the nonpaged pool. The nonpaged pool is an area of system memory area for objects that cannot be written"+
|
||||
" to disk, and must remain in physical memory as long as they are allocated (PoolNonpagedAllocs)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
PoolNonpagedBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "pool_nonpaged_bytes_total"),
|
||||
"(PoolNonpagedBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
PoolPagedAllocsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "pool_paged_allocs_total"),
|
||||
"(PoolPagedAllocs)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
PoolPagedBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "pool_paged_bytes"),
|
||||
"(PoolPagedBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
PoolPagedResidentBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "pool_paged_resident_bytes"),
|
||||
"(PoolPagedResidentBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
StandbyCacheCoreBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "standby_cache_core_bytes"),
|
||||
"(StandbyCacheCoreBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
StandbyCacheNormalPriorityBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "standby_cache_normal_priority_bytes"),
|
||||
"(StandbyCacheNormalPriorityBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
StandbyCacheReserveBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "standby_cache_reserve_bytes"),
|
||||
"(StandbyCacheReserveBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SystemCacheResidentBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "system_cache_resident_bytes"),
|
||||
"(SystemCacheResidentBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SystemCodeResidentBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "system_code_resident_bytes"),
|
||||
"(SystemCodeResidentBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SystemCodeTotalBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "system_code_total_bytes"),
|
||||
"(SystemCodeTotalBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SystemDriverResidentBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "system_driver_resident_bytes"),
|
||||
"(SystemDriverResidentBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SystemDriverTotalBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "system_driver_total_bytes"),
|
||||
"(SystemDriverTotalBytes)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
TransitionFaultsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "transition_faults_total"),
|
||||
"(TransitionFaultsPersec)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
TransitionPagesRepurposedTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "transition_pages_repurposed_total"),
|
||||
"(TransitionPagesRePurposedPersec)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
WriteCopiesTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "write_copies_total"),
|
||||
"The number of page faults caused by attempting to write that were satisfied by copying the page from elsewhere in physical memory (WriteCopiesPersec)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *MemoryCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ctx, ch); err != nil {
|
||||
log.Error("failed collecting memory metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
type memory struct {
|
||||
AvailableBytes float64 `perflib:"Available Bytes"`
|
||||
AvailableKBytes float64 `perflib:"Available KBytes"`
|
||||
AvailableMBytes float64 `perflib:"Available MBytes"`
|
||||
CacheBytes float64 `perflib:"Cache Bytes"`
|
||||
CacheBytesPeak float64 `perflib:"Cache Bytes Peak"`
|
||||
CacheFaultsPersec float64 `perflib:"Cache Faults/sec"`
|
||||
CommitLimit float64 `perflib:"Commit Limit"`
|
||||
CommittedBytes float64 `perflib:"Committed Bytes"`
|
||||
DemandZeroFaultsPersec float64 `perflib:"Demand Zero Faults/sec"`
|
||||
FreeAndZeroPageListBytes float64 `perflib:"Free & Zero Page List Bytes"`
|
||||
FreeSystemPageTableEntries float64 `perflib:"Free System Page Table Entries"`
|
||||
ModifiedPageListBytes float64 `perflib:"Modified Page List Bytes"`
|
||||
PageFaultsPersec float64 `perflib:"Page Faults/sec"`
|
||||
PageReadsPersec float64 `perflib:"Page Reads/sec"`
|
||||
PagesInputPersec float64 `perflib:"Pages Input/sec"`
|
||||
PagesOutputPersec float64 `perflib:"Pages Output/sec"`
|
||||
PagesPersec float64 `perflib:"Pages/sec"`
|
||||
PageWritesPersec float64 `perflib:"Page Writes/sec"`
|
||||
PoolNonpagedAllocs float64 `perflib:"Pool Nonpaged Allocs"`
|
||||
PoolNonpagedBytes float64 `perflib:"Pool Nonpaged Bytes"`
|
||||
PoolPagedAllocs float64 `perflib:"Pool Paged Allocs"`
|
||||
PoolPagedBytes float64 `perflib:"Pool Paged Bytes"`
|
||||
PoolPagedResidentBytes float64 `perflib:"Pool Paged Resident Bytes"`
|
||||
StandbyCacheCoreBytes float64 `perflib:"Standby Cache Core Bytes"`
|
||||
StandbyCacheNormalPriorityBytes float64 `perflib:"Standby Cache Normal Priority Bytes"`
|
||||
StandbyCacheReserveBytes float64 `perflib:"Standby Cache Reserve Bytes"`
|
||||
SystemCacheResidentBytes float64 `perflib:"System Cache Resident Bytes"`
|
||||
SystemCodeResidentBytes float64 `perflib:"System Code Resident Bytes"`
|
||||
SystemCodeTotalBytes float64 `perflib:"System Code Total Bytes"`
|
||||
SystemDriverResidentBytes float64 `perflib:"System Driver Resident Bytes"`
|
||||
SystemDriverTotalBytes float64 `perflib:"System Driver Total Bytes"`
|
||||
TransitionFaultsPersec float64 `perflib:"Transition Faults/sec"`
|
||||
TransitionPagesRePurposedPersec float64 `perflib:"Transition Pages RePurposed/sec"`
|
||||
WriteCopiesPersec float64 `perflib:"Write Copies/sec"`
|
||||
}
|
||||
|
||||
func (c *MemoryCollector) collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []memory
|
||||
if err := unmarshalObject(ctx.perfObjects["Memory"], &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.AvailableBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].AvailableBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CacheBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].CacheBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CacheBytesPeak,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].CacheBytesPeak,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CacheFaultsTotal,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].CacheFaultsPersec,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CommitLimit,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].CommitLimit,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CommittedBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].CommittedBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.DemandZeroFaultsTotal,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].DemandZeroFaultsPersec,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.FreeAndZeroPageListBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].FreeAndZeroPageListBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.FreeSystemPageTableEntries,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].FreeSystemPageTableEntries,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ModifiedPageListBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].ModifiedPageListBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PageFaultsTotal,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].PageFaultsPersec,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SwapPageReadsTotal,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].PageReadsPersec,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SwapPagesReadTotal,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].PagesInputPersec,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SwapPagesWrittenTotal,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].PagesOutputPersec,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SwapPageOperationsTotal,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].PagesPersec,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SwapPageWritesTotal,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].PageWritesPersec,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PoolNonpagedAllocsTotal,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].PoolNonpagedAllocs,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PoolNonpagedBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].PoolNonpagedBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PoolPagedAllocsTotal,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].PoolPagedAllocs,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PoolPagedBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].PoolPagedBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PoolPagedResidentBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].PoolPagedResidentBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.StandbyCacheCoreBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].StandbyCacheCoreBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.StandbyCacheNormalPriorityBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].StandbyCacheNormalPriorityBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.StandbyCacheReserveBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].StandbyCacheReserveBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SystemCacheResidentBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].SystemCacheResidentBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SystemCodeResidentBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].SystemCodeResidentBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SystemCodeTotalBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].SystemCodeTotalBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SystemDriverResidentBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].SystemDriverResidentBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SystemDriverTotalBytes,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].SystemDriverTotalBytes,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TransitionFaultsTotal,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].TransitionFaultsPersec,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TransitionPagesRepurposedTotal,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].TransitionPagesRePurposedPersec,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.WriteCopiesTotal,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].WriteCopiesPersec,
|
||||
)
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
127
collector/msmq.go
Normal file
127
collector/msmq.go
Normal file
@@ -0,0 +1,127 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"strings"
|
||||
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
"gopkg.in/alecthomas/kingpin.v2"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("msmq", NewMSMQCollector)
|
||||
}
|
||||
|
||||
var (
|
||||
msmqWhereClause = kingpin.Flag("collector.msmq.msmq-where", "WQL 'where' clause to use in WMI metrics query. Limits the response to the msmqs you specify and reduces the size of the response.").String()
|
||||
)
|
||||
|
||||
// A Win32_PerfRawData_MSMQ_MSMQQueueCollector is a Prometheus collector for WMI Win32_PerfRawData_MSMQ_MSMQQueue metrics
|
||||
type Win32_PerfRawData_MSMQ_MSMQQueueCollector struct {
|
||||
BytesinJournalQueue *prometheus.Desc
|
||||
BytesinQueue *prometheus.Desc
|
||||
MessagesinJournalQueue *prometheus.Desc
|
||||
MessagesinQueue *prometheus.Desc
|
||||
|
||||
queryWhereClause string
|
||||
}
|
||||
|
||||
// NewWin32_PerfRawData_MSMQ_MSMQQueueCollector ...
|
||||
func NewMSMQCollector() (Collector, error) {
|
||||
const subsystem = "msmq"
|
||||
|
||||
if *msmqWhereClause == "" {
|
||||
log.Warn("No where-clause specified for msmq collector. This will generate a very large number of metrics!")
|
||||
}
|
||||
|
||||
return &Win32_PerfRawData_MSMQ_MSMQQueueCollector{
|
||||
BytesinJournalQueue: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "bytes_in_journal_queue"),
|
||||
"Size of queue journal in bytes",
|
||||
[]string{"name"},
|
||||
nil,
|
||||
),
|
||||
BytesinQueue: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "bytes_in_queue"),
|
||||
"Size of queue in bytes",
|
||||
[]string{"name"},
|
||||
nil,
|
||||
),
|
||||
MessagesinJournalQueue: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "messages_in_journal_queue"),
|
||||
"Count messages in queue journal",
|
||||
[]string{"name"},
|
||||
nil,
|
||||
),
|
||||
MessagesinQueue: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "messages_in_queue"),
|
||||
"Count messages in queue",
|
||||
[]string{"name"},
|
||||
nil,
|
||||
),
|
||||
queryWhereClause: *msmqWhereClause,
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *Win32_PerfRawData_MSMQ_MSMQQueueCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting msmq metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
type Win32_PerfRawData_MSMQ_MSMQQueue struct {
|
||||
Name string
|
||||
|
||||
BytesinJournalQueue uint64
|
||||
BytesinQueue uint64
|
||||
MessagesinJournalQueue uint64
|
||||
MessagesinQueue uint64
|
||||
}
|
||||
|
||||
func (c *Win32_PerfRawData_MSMQ_MSMQQueueCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_MSMQ_MSMQQueue
|
||||
q := queryAllWhere(&dst, c.queryWhereClause)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
for _, msmq := range dst {
|
||||
|
||||
if msmq.Name == "Computer Queues" {
|
||||
continue
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.BytesinJournalQueue,
|
||||
prometheus.GaugeValue,
|
||||
float64(msmq.BytesinJournalQueue),
|
||||
strings.ToLower(msmq.Name),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.BytesinQueue,
|
||||
prometheus.GaugeValue,
|
||||
float64(msmq.BytesinQueue),
|
||||
strings.ToLower(msmq.Name),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MessagesinJournalQueue,
|
||||
prometheus.GaugeValue,
|
||||
float64(msmq.MessagesinJournalQueue),
|
||||
strings.ToLower(msmq.Name),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MessagesinQueue,
|
||||
prometheus.GaugeValue,
|
||||
float64(msmq.MessagesinQueue),
|
||||
strings.ToLower(msmq.Name),
|
||||
)
|
||||
}
|
||||
return nil, nil
|
||||
}
|
||||
3887
collector/mssql.go
Normal file
3887
collector/mssql.go
Normal file
File diff suppressed because it is too large
Load Diff
259
collector/net.go
Normal file
259
collector/net.go
Normal file
@@ -0,0 +1,259 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"regexp"
|
||||
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
"gopkg.in/alecthomas/kingpin.v2"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("net", NewNetworkCollector, "Network Interface")
|
||||
}
|
||||
|
||||
var (
|
||||
nicWhitelist = kingpin.Flag(
|
||||
"collector.net.nic-whitelist",
|
||||
"Regexp of NIC:s to whitelist. NIC name must both match whitelist and not match blacklist to be included.",
|
||||
).Default(".+").String()
|
||||
nicBlacklist = kingpin.Flag(
|
||||
"collector.net.nic-blacklist",
|
||||
"Regexp of NIC:s to blacklist. NIC name must both match whitelist and not match blacklist to be included.",
|
||||
).Default("").String()
|
||||
nicNameToUnderscore = regexp.MustCompile("[^a-zA-Z0-9]")
|
||||
)
|
||||
|
||||
// A NetworkCollector is a Prometheus collector for Perflib Network Interface metrics
|
||||
type NetworkCollector struct {
|
||||
BytesReceivedTotal *prometheus.Desc
|
||||
BytesSentTotal *prometheus.Desc
|
||||
BytesTotal *prometheus.Desc
|
||||
PacketsOutboundDiscarded *prometheus.Desc
|
||||
PacketsOutboundErrors *prometheus.Desc
|
||||
PacketsTotal *prometheus.Desc
|
||||
PacketsReceivedDiscarded *prometheus.Desc
|
||||
PacketsReceivedErrors *prometheus.Desc
|
||||
PacketsReceivedTotal *prometheus.Desc
|
||||
PacketsReceivedUnknown *prometheus.Desc
|
||||
PacketsSentTotal *prometheus.Desc
|
||||
CurrentBandwidth *prometheus.Desc
|
||||
|
||||
nicWhitelistPattern *regexp.Regexp
|
||||
nicBlacklistPattern *regexp.Regexp
|
||||
}
|
||||
|
||||
// NewNetworkCollector ...
|
||||
func NewNetworkCollector() (Collector, error) {
|
||||
const subsystem = "net"
|
||||
|
||||
return &NetworkCollector{
|
||||
BytesReceivedTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "bytes_received_total"),
|
||||
"(Network.BytesReceivedPerSec)",
|
||||
[]string{"nic"},
|
||||
nil,
|
||||
),
|
||||
BytesSentTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "bytes_sent_total"),
|
||||
"(Network.BytesSentPerSec)",
|
||||
[]string{"nic"},
|
||||
nil,
|
||||
),
|
||||
BytesTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "bytes_total"),
|
||||
"(Network.BytesTotalPerSec)",
|
||||
[]string{"nic"},
|
||||
nil,
|
||||
),
|
||||
PacketsOutboundDiscarded: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "packets_outbound_discarded"),
|
||||
"(Network.PacketsOutboundDiscarded)",
|
||||
[]string{"nic"},
|
||||
nil,
|
||||
),
|
||||
PacketsOutboundErrors: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "packets_outbound_errors"),
|
||||
"(Network.PacketsOutboundErrors)",
|
||||
[]string{"nic"},
|
||||
nil,
|
||||
),
|
||||
PacketsReceivedDiscarded: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "packets_received_discarded"),
|
||||
"(Network.PacketsReceivedDiscarded)",
|
||||
[]string{"nic"},
|
||||
nil,
|
||||
),
|
||||
PacketsReceivedErrors: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "packets_received_errors"),
|
||||
"(Network.PacketsReceivedErrors)",
|
||||
[]string{"nic"},
|
||||
nil,
|
||||
),
|
||||
PacketsReceivedTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "packets_received_total"),
|
||||
"(Network.PacketsReceivedPerSec)",
|
||||
[]string{"nic"},
|
||||
nil,
|
||||
),
|
||||
PacketsReceivedUnknown: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "packets_received_unknown"),
|
||||
"(Network.PacketsReceivedUnknown)",
|
||||
[]string{"nic"},
|
||||
nil,
|
||||
),
|
||||
PacketsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "packets_total"),
|
||||
"(Network.PacketsPerSec)",
|
||||
[]string{"nic"},
|
||||
nil,
|
||||
),
|
||||
PacketsSentTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "packets_sent_total"),
|
||||
"(Network.PacketsSentPerSec)",
|
||||
[]string{"nic"},
|
||||
nil,
|
||||
),
|
||||
CurrentBandwidth: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "current_bandwidth"),
|
||||
"(Network.CurrentBandwidth)",
|
||||
[]string{"nic"},
|
||||
nil,
|
||||
),
|
||||
|
||||
nicWhitelistPattern: regexp.MustCompile(fmt.Sprintf("^(?:%s)$", *nicWhitelist)),
|
||||
nicBlacklistPattern: regexp.MustCompile(fmt.Sprintf("^(?:%s)$", *nicBlacklist)),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *NetworkCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ctx, ch); err != nil {
|
||||
log.Error("failed collecting net metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// mangleNetworkName mangles Network Adapter name (non-alphanumeric to _)
|
||||
// that is used in networkInterface.
|
||||
func mangleNetworkName(name string) string {
|
||||
return nicNameToUnderscore.ReplaceAllString(name, "_")
|
||||
}
|
||||
|
||||
// Win32_PerfRawData_Tcpip_NetworkInterface docs:
|
||||
// - https://technet.microsoft.com/en-us/security/aa394340(v=vs.80)
|
||||
type networkInterface struct {
|
||||
BytesReceivedPerSec float64 `perflib:"Bytes Received/sec"`
|
||||
BytesSentPerSec float64 `perflib:"Bytes Sent/sec"`
|
||||
BytesTotalPerSec float64 `perflib:"Bytes Total/sec"`
|
||||
Name string
|
||||
PacketsOutboundDiscarded float64 `perflib:"Packets Outbound Discarded"`
|
||||
PacketsOutboundErrors float64 `perflib:"Packets Outbound Errors"`
|
||||
PacketsPerSec float64 `perflib:"Packets/sec"`
|
||||
PacketsReceivedDiscarded float64 `perflib:"Packets Received Discarded"`
|
||||
PacketsReceivedErrors float64 `perflib:"Packets Received Errors"`
|
||||
PacketsReceivedPerSec float64 `perflib:"Packets Received/sec"`
|
||||
PacketsReceivedUnknown float64 `perflib:"Packets Received Unknown"`
|
||||
PacketsSentPerSec float64 `perflib:"Packets Sent/sec"`
|
||||
CurrentBandwidth float64 `perflib:"Current Bandwidth"`
|
||||
}
|
||||
|
||||
func (c *NetworkCollector) collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []networkInterface
|
||||
|
||||
if err := unmarshalObject(ctx.perfObjects["Network Interface"], &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
for _, nic := range dst {
|
||||
if c.nicBlacklistPattern.MatchString(nic.Name) ||
|
||||
!c.nicWhitelistPattern.MatchString(nic.Name) {
|
||||
continue
|
||||
}
|
||||
|
||||
name := mangleNetworkName(nic.Name)
|
||||
if name == "" {
|
||||
continue
|
||||
}
|
||||
|
||||
// Counters
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.BytesReceivedTotal,
|
||||
prometheus.CounterValue,
|
||||
nic.BytesReceivedPerSec,
|
||||
name,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.BytesSentTotal,
|
||||
prometheus.CounterValue,
|
||||
nic.BytesSentPerSec,
|
||||
name,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.BytesTotal,
|
||||
prometheus.CounterValue,
|
||||
nic.BytesTotalPerSec,
|
||||
name,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PacketsOutboundDiscarded,
|
||||
prometheus.CounterValue,
|
||||
nic.PacketsOutboundDiscarded,
|
||||
name,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PacketsOutboundErrors,
|
||||
prometheus.CounterValue,
|
||||
nic.PacketsOutboundErrors,
|
||||
name,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PacketsTotal,
|
||||
prometheus.CounterValue,
|
||||
nic.PacketsPerSec,
|
||||
name,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PacketsReceivedDiscarded,
|
||||
prometheus.CounterValue,
|
||||
nic.PacketsReceivedDiscarded,
|
||||
name,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PacketsReceivedErrors,
|
||||
prometheus.CounterValue,
|
||||
nic.PacketsReceivedErrors,
|
||||
name,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PacketsReceivedTotal,
|
||||
prometheus.CounterValue,
|
||||
nic.PacketsReceivedPerSec,
|
||||
name,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PacketsReceivedUnknown,
|
||||
prometheus.CounterValue,
|
||||
nic.PacketsReceivedUnknown,
|
||||
name,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PacketsSentTotal,
|
||||
prometheus.CounterValue,
|
||||
nic.PacketsSentPerSec,
|
||||
name,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CurrentBandwidth,
|
||||
prometheus.GaugeValue,
|
||||
nic.CurrentBandwidth,
|
||||
name,
|
||||
)
|
||||
}
|
||||
return nil, nil
|
||||
}
|
||||
@@ -1,14 +1,10 @@
|
||||
//go:build windows
|
||||
// +build windows
|
||||
|
||||
package net
|
||||
package collector
|
||||
|
||||
import (
|
||||
"testing"
|
||||
)
|
||||
import "testing"
|
||||
|
||||
func TestNetworkToInstanceName(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
data := map[string]string{
|
||||
"Intel[R] Dual Band Wireless-AC 8260": "Intel_R__Dual_Band_Wireless_AC_8260",
|
||||
}
|
||||
117
collector/netframework_clrexceptions.go
Normal file
117
collector/netframework_clrexceptions.go
Normal file
@@ -0,0 +1,117 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("netframework_clrexceptions", NewNETFramework_NETCLRExceptionsCollector)
|
||||
}
|
||||
|
||||
// A NETFramework_NETCLRExceptionsCollector is a Prometheus collector for WMI Win32_PerfRawData_NETFramework_NETCLRExceptions metrics
|
||||
type NETFramework_NETCLRExceptionsCollector struct {
|
||||
NumberofExcepsThrown *prometheus.Desc
|
||||
NumberofFilters *prometheus.Desc
|
||||
NumberofFinallys *prometheus.Desc
|
||||
ThrowToCatchDepth *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewNETFramework_NETCLRExceptionsCollector ...
|
||||
func NewNETFramework_NETCLRExceptionsCollector() (Collector, error) {
|
||||
const subsystem = "netframework_clrexceptions"
|
||||
return &NETFramework_NETCLRExceptionsCollector{
|
||||
NumberofExcepsThrown: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "exceptions_thrown_total"),
|
||||
"Displays the total number of exceptions thrown since the application started. This includes both .NET exceptions and unmanaged exceptions that are converted into .NET exceptions.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
NumberofFilters: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "exceptions_filters_total"),
|
||||
"Displays the total number of .NET exception filters executed. An exception filter evaluates regardless of whether an exception is handled.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
NumberofFinallys: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "exceptions_finallys_total"),
|
||||
"Displays the total number of finally blocks executed. Only the finally blocks executed for an exception are counted; finally blocks on normal code paths are not counted by this counter.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
ThrowToCatchDepth: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "throw_to_catch_depth_total"),
|
||||
"Displays the total number of stack frames traversed, from the frame that threw the exception to the frame that handled the exception.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *NETFramework_NETCLRExceptionsCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting win32_perfrawdata_netframework_netclrexceptions metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
type Win32_PerfRawData_NETFramework_NETCLRExceptions struct {
|
||||
Name string
|
||||
|
||||
NumberofExcepsThrown uint32
|
||||
NumberofExcepsThrownPersec uint32
|
||||
NumberofFiltersPersec uint32
|
||||
NumberofFinallysPersec uint32
|
||||
ThrowToCatchDepthPersec uint32
|
||||
}
|
||||
|
||||
func (c *NETFramework_NETCLRExceptionsCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_NETFramework_NETCLRExceptions
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
for _, process := range dst {
|
||||
|
||||
if process.Name == "_Global_" {
|
||||
continue
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberofExcepsThrown,
|
||||
prometheus.CounterValue,
|
||||
float64(process.NumberofExcepsThrown),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberofFilters,
|
||||
prometheus.CounterValue,
|
||||
float64(process.NumberofFiltersPersec),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberofFinallys,
|
||||
prometheus.CounterValue,
|
||||
float64(process.NumberofFinallysPersec),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ThrowToCatchDepth,
|
||||
prometheus.CounterValue,
|
||||
float64(process.ThrowToCatchDepthPersec),
|
||||
process.Name,
|
||||
)
|
||||
}
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
103
collector/netframework_clrinterop.go
Normal file
103
collector/netframework_clrinterop.go
Normal file
@@ -0,0 +1,103 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("netframework_clrinterop", NewNETFramework_NETCLRInteropCollector)
|
||||
}
|
||||
|
||||
// A NETFramework_NETCLRInteropCollector is a Prometheus collector for WMI Win32_PerfRawData_NETFramework_NETCLRInterop metrics
|
||||
type NETFramework_NETCLRInteropCollector struct {
|
||||
NumberofCCWs *prometheus.Desc
|
||||
Numberofmarshalling *prometheus.Desc
|
||||
NumberofStubs *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewNETFramework_NETCLRInteropCollector ...
|
||||
func NewNETFramework_NETCLRInteropCollector() (Collector, error) {
|
||||
const subsystem = "netframework_clrinterop"
|
||||
return &NETFramework_NETCLRInteropCollector{
|
||||
NumberofCCWs: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "com_callable_wrappers_total"),
|
||||
"Displays the current number of COM callable wrappers (CCWs). A CCW is a proxy for a managed object being referenced from an unmanaged COM client.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
Numberofmarshalling: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "interop_marshalling_total"),
|
||||
"Displays the total number of times arguments and return values have been marshaled from managed to unmanaged code, and vice versa, since the application started.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
NumberofStubs: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "interop_stubs_created_total"),
|
||||
"Displays the current number of stubs created by the common language runtime. Stubs are responsible for marshaling arguments and return values from managed to unmanaged code, and vice versa, during a COM interop call or a platform invoke call.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *NETFramework_NETCLRInteropCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting win32_perfrawdata_netframework_netclrinterop metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
type Win32_PerfRawData_NETFramework_NETCLRInterop struct {
|
||||
Name string
|
||||
|
||||
NumberofCCWs uint32
|
||||
Numberofmarshalling uint32
|
||||
NumberofStubs uint32
|
||||
NumberofTLBexportsPersec uint32
|
||||
NumberofTLBimportsPersec uint32
|
||||
}
|
||||
|
||||
func (c *NETFramework_NETCLRInteropCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_NETFramework_NETCLRInterop
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
for _, process := range dst {
|
||||
|
||||
if process.Name == "_Global_" {
|
||||
continue
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberofCCWs,
|
||||
prometheus.CounterValue,
|
||||
float64(process.NumberofCCWs),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Numberofmarshalling,
|
||||
prometheus.CounterValue,
|
||||
float64(process.Numberofmarshalling),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberofStubs,
|
||||
prometheus.CounterValue,
|
||||
float64(process.NumberofStubs),
|
||||
process.Name,
|
||||
)
|
||||
}
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
119
collector/netframework_clrjit.go
Normal file
119
collector/netframework_clrjit.go
Normal file
@@ -0,0 +1,119 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("netframework_clrjit", NewNETFramework_NETCLRJitCollector)
|
||||
}
|
||||
|
||||
// A NETFramework_NETCLRJitCollector is a Prometheus collector for WMI Win32_PerfRawData_NETFramework_NETCLRJit metrics
|
||||
type NETFramework_NETCLRJitCollector struct {
|
||||
NumberofMethodsJitted *prometheus.Desc
|
||||
TimeinJit *prometheus.Desc
|
||||
StandardJitFailures *prometheus.Desc
|
||||
TotalNumberofILBytesJitted *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewNETFramework_NETCLRJitCollector ...
|
||||
func NewNETFramework_NETCLRJitCollector() (Collector, error) {
|
||||
const subsystem = "netframework_clrjit"
|
||||
return &NETFramework_NETCLRJitCollector{
|
||||
NumberofMethodsJitted: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "jit_methods_total"),
|
||||
"Displays the total number of methods JIT-compiled since the application started. This counter does not include pre-JIT-compiled methods.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
TimeinJit: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "jit_time_percent"),
|
||||
"Displays the percentage of time spent in JIT compilation. This counter is updated at the end of every JIT compilation phase. A JIT compilation phase occurs when a method and its dependencies are compiled.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
StandardJitFailures: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "jit_standard_failures_total"),
|
||||
"Displays the peak number of methods the JIT compiler has failed to compile since the application started. This failure can occur if the MSIL cannot be verified or if there is an internal error in the JIT compiler.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
TotalNumberofILBytesJitted: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "jit_il_bytes_total"),
|
||||
"Displays the total number of Microsoft intermediate language (MSIL) bytes compiled by the just-in-time (JIT) compiler since the application started",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *NETFramework_NETCLRJitCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting win32_perfrawdata_netframework_netclrjit metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
type Win32_PerfRawData_NETFramework_NETCLRJit struct {
|
||||
Name string
|
||||
|
||||
Frequency_PerfTime uint32
|
||||
ILBytesJittedPersec uint32
|
||||
NumberofILBytesJitted uint32
|
||||
NumberofMethodsJitted uint32
|
||||
PercentTimeinJit uint32
|
||||
StandardJitFailures uint32
|
||||
TotalNumberofILBytesJitted uint32
|
||||
}
|
||||
|
||||
func (c *NETFramework_NETCLRJitCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_NETFramework_NETCLRJit
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
for _, process := range dst {
|
||||
|
||||
if process.Name == "_Global_" {
|
||||
continue
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberofMethodsJitted,
|
||||
prometheus.CounterValue,
|
||||
float64(process.NumberofMethodsJitted),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TimeinJit,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.PercentTimeinJit)/float64(process.Frequency_PerfTime),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.StandardJitFailures,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.StandardJitFailures),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TotalNumberofILBytesJitted,
|
||||
prometheus.CounterValue,
|
||||
float64(process.TotalNumberofILBytesJitted),
|
||||
process.Name,
|
||||
)
|
||||
}
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
198
collector/netframework_clrloading.go
Normal file
198
collector/netframework_clrloading.go
Normal file
@@ -0,0 +1,198 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("netframework_clrloading", NewNETFramework_NETCLRLoadingCollector)
|
||||
}
|
||||
|
||||
// A NETFramework_NETCLRLoadingCollector is a Prometheus collector for WMI Win32_PerfRawData_NETFramework_NETCLRLoading metrics
|
||||
type NETFramework_NETCLRLoadingCollector struct {
|
||||
BytesinLoaderHeap *prometheus.Desc
|
||||
Currentappdomains *prometheus.Desc
|
||||
CurrentAssemblies *prometheus.Desc
|
||||
CurrentClassesLoaded *prometheus.Desc
|
||||
TotalAppdomains *prometheus.Desc
|
||||
Totalappdomainsunloaded *prometheus.Desc
|
||||
TotalAssemblies *prometheus.Desc
|
||||
TotalClassesLoaded *prometheus.Desc
|
||||
TotalNumberofLoadFailures *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewNETFramework_NETCLRLoadingCollector ...
|
||||
func NewNETFramework_NETCLRLoadingCollector() (Collector, error) {
|
||||
const subsystem = "netframework_clrloading"
|
||||
return &NETFramework_NETCLRLoadingCollector{
|
||||
BytesinLoaderHeap: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "loader_heap_size_bytes"),
|
||||
"Displays the current size, in bytes, of the memory committed by the class loader across all application domains. Committed memory is the physical space reserved in the disk paging file.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
Currentappdomains: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "appdomains_loaded_current"),
|
||||
"Displays the current number of application domains loaded in this application.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
CurrentAssemblies: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "assemblies_loaded_current"),
|
||||
"Displays the current number of assemblies loaded across all application domains in the currently running application. If the assembly is loaded as domain-neutral from multiple application domains, this counter is incremented only once.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
CurrentClassesLoaded: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "classes_loaded_current"),
|
||||
"Displays the current number of classes loaded in all assemblies.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
TotalAppdomains: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "appdomains_loaded_total"),
|
||||
"Displays the peak number of application domains loaded since the application started.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
Totalappdomainsunloaded: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "appdomains_unloaded_total"),
|
||||
"Displays the total number of application domains unloaded since the application started. If an application domain is loaded and unloaded multiple times, this counter increments each time the application domain is unloaded.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
TotalAssemblies: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "assemblies_loaded_total"),
|
||||
"Displays the total number of assemblies loaded since the application started. If the assembly is loaded as domain-neutral from multiple application domains, this counter is incremented only once.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
TotalClassesLoaded: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "classes_loaded_total"),
|
||||
"Displays the cumulative number of classes loaded in all assemblies since the application started.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
TotalNumberofLoadFailures: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "class_load_failures_total"),
|
||||
"Displays the peak number of classes that have failed to load since the application started.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *NETFramework_NETCLRLoadingCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting win32_perfrawdata_netframework_netclrloading metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
type Win32_PerfRawData_NETFramework_NETCLRLoading struct {
|
||||
Name string
|
||||
|
||||
AssemblySearchLength uint32
|
||||
BytesinLoaderHeap uint64
|
||||
Currentappdomains uint32
|
||||
CurrentAssemblies uint32
|
||||
CurrentClassesLoaded uint32
|
||||
PercentTimeLoading uint64
|
||||
Rateofappdomains uint32
|
||||
Rateofappdomainsunloaded uint32
|
||||
RateofAssemblies uint32
|
||||
RateofClassesLoaded uint32
|
||||
RateofLoadFailures uint32
|
||||
TotalAppdomains uint32
|
||||
Totalappdomainsunloaded uint32
|
||||
TotalAssemblies uint32
|
||||
TotalClassesLoaded uint32
|
||||
TotalNumberofLoadFailures uint32
|
||||
}
|
||||
|
||||
func (c *NETFramework_NETCLRLoadingCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_NETFramework_NETCLRLoading
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
for _, process := range dst {
|
||||
|
||||
if process.Name == "_Global_" {
|
||||
continue
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.BytesinLoaderHeap,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.BytesinLoaderHeap),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Currentappdomains,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.Currentappdomains),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CurrentAssemblies,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.CurrentAssemblies),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CurrentClassesLoaded,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.CurrentClassesLoaded),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TotalAppdomains,
|
||||
prometheus.CounterValue,
|
||||
float64(process.TotalAppdomains),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Totalappdomainsunloaded,
|
||||
prometheus.CounterValue,
|
||||
float64(process.Totalappdomainsunloaded),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TotalAssemblies,
|
||||
prometheus.CounterValue,
|
||||
float64(process.TotalAssemblies),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TotalClassesLoaded,
|
||||
prometheus.CounterValue,
|
||||
float64(process.TotalClassesLoaded),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TotalNumberofLoadFailures,
|
||||
prometheus.CounterValue,
|
||||
float64(process.TotalNumberofLoadFailures),
|
||||
process.Name,
|
||||
)
|
||||
}
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
164
collector/netframework_clrlocksandthreads.go
Normal file
164
collector/netframework_clrlocksandthreads.go
Normal file
@@ -0,0 +1,164 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("netframework_clrlocksandthreads", NewNETFramework_NETCLRLocksAndThreadsCollector)
|
||||
}
|
||||
|
||||
// A NETFramework_NETCLRLocksAndThreadsCollector is a Prometheus collector for WMI Win32_PerfRawData_NETFramework_NETCLRLocksAndThreads metrics
|
||||
type NETFramework_NETCLRLocksAndThreadsCollector struct {
|
||||
CurrentQueueLength *prometheus.Desc
|
||||
NumberofcurrentlogicalThreads *prometheus.Desc
|
||||
NumberofcurrentphysicalThreads *prometheus.Desc
|
||||
Numberofcurrentrecognizedthreads *prometheus.Desc
|
||||
Numberoftotalrecognizedthreads *prometheus.Desc
|
||||
QueueLengthPeak *prometheus.Desc
|
||||
TotalNumberofContentions *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewNETFramework_NETCLRLocksAndThreadsCollector ...
|
||||
func NewNETFramework_NETCLRLocksAndThreadsCollector() (Collector, error) {
|
||||
const subsystem = "netframework_clrlocksandthreads"
|
||||
return &NETFramework_NETCLRLocksAndThreadsCollector{
|
||||
CurrentQueueLength: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "current_queue_length"),
|
||||
"Displays the total number of threads that are currently waiting to acquire a managed lock in the application.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
NumberofcurrentlogicalThreads: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "current_logical_threads"),
|
||||
"Displays the number of current managed thread objects in the application. This counter maintains the count of both running and stopped threads. ",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
NumberofcurrentphysicalThreads: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "physical_threads_current"),
|
||||
"Displays the number of native operating system threads created and owned by the common language runtime to act as underlying threads for managed thread objects. This counter's value does not include the threads used by the runtime in its internal operations; it is a subset of the threads in the operating system process.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
Numberofcurrentrecognizedthreads: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "recognized_threads_current"),
|
||||
"Displays the number of threads that are currently recognized by the runtime. These threads are associated with a corresponding managed thread object. The runtime does not create these threads, but they have run inside the runtime at least once.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
Numberoftotalrecognizedthreads: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "recognized_threads_total"),
|
||||
"Displays the total number of threads that have been recognized by the runtime since the application started. These threads are associated with a corresponding managed thread object. The runtime does not create these threads, but they have run inside the runtime at least once.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
QueueLengthPeak: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "queue_length_total"),
|
||||
"Displays the total number of threads that waited to acquire a managed lock since the application started.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
TotalNumberofContentions: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "contentions_total"),
|
||||
"Displays the total number of times that threads in the runtime have attempted to acquire a managed lock unsuccessfully.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *NETFramework_NETCLRLocksAndThreadsCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting win32_perfrawdata_netframework_netclrlocksandthreads metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
type Win32_PerfRawData_NETFramework_NETCLRLocksAndThreads struct {
|
||||
Name string
|
||||
|
||||
ContentionRatePersec uint32
|
||||
CurrentQueueLength uint32
|
||||
NumberofcurrentlogicalThreads uint32
|
||||
NumberofcurrentphysicalThreads uint32
|
||||
Numberofcurrentrecognizedthreads uint32
|
||||
Numberoftotalrecognizedthreads uint32
|
||||
QueueLengthPeak uint32
|
||||
QueueLengthPersec uint32
|
||||
RateOfRecognizedThreadsPersec uint32
|
||||
TotalNumberofContentions uint32
|
||||
}
|
||||
|
||||
func (c *NETFramework_NETCLRLocksAndThreadsCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_NETFramework_NETCLRLocksAndThreads
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
for _, process := range dst {
|
||||
|
||||
if process.Name == "_Global_" {
|
||||
continue
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CurrentQueueLength,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.CurrentQueueLength),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberofcurrentlogicalThreads,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.NumberofcurrentlogicalThreads),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberofcurrentphysicalThreads,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.NumberofcurrentphysicalThreads),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Numberofcurrentrecognizedthreads,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.Numberofcurrentrecognizedthreads),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Numberoftotalrecognizedthreads,
|
||||
prometheus.CounterValue,
|
||||
float64(process.Numberoftotalrecognizedthreads),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.QueueLengthPeak,
|
||||
prometheus.CounterValue,
|
||||
float64(process.QueueLengthPeak),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TotalNumberofContentions,
|
||||
prometheus.CounterValue,
|
||||
float64(process.TotalNumberofContentions),
|
||||
process.Name,
|
||||
)
|
||||
}
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
302
collector/netframework_clrmemory.go
Normal file
302
collector/netframework_clrmemory.go
Normal file
@@ -0,0 +1,302 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("netframework_clrmemory", NewNETFramework_NETCLRMemoryCollector)
|
||||
}
|
||||
|
||||
// A NETFramework_NETCLRMemoryCollector is a Prometheus collector for WMI Win32_PerfRawData_NETFramework_NETCLRMemory metrics
|
||||
type NETFramework_NETCLRMemoryCollector struct {
|
||||
AllocatedBytes *prometheus.Desc
|
||||
FinalizationSurvivors *prometheus.Desc
|
||||
HeapSize *prometheus.Desc
|
||||
PromotedBytes *prometheus.Desc
|
||||
NumberGCHandles *prometheus.Desc
|
||||
NumberCollections *prometheus.Desc
|
||||
NumberInducedGC *prometheus.Desc
|
||||
NumberofPinnedObjects *prometheus.Desc
|
||||
NumberofSinkBlocksinuse *prometheus.Desc
|
||||
NumberTotalCommittedBytes *prometheus.Desc
|
||||
NumberTotalreservedBytes *prometheus.Desc
|
||||
TimeinGC *prometheus.Desc
|
||||
PromotedFinalizationMemoryfromGen0 *prometheus.Desc
|
||||
PromotedMemoryfromGen0 *prometheus.Desc
|
||||
PromotedMemoryfromGen1 *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewNETFramework_NETCLRMemoryCollector ...
|
||||
func NewNETFramework_NETCLRMemoryCollector() (Collector, error) {
|
||||
const subsystem = "netframework_clrmemory"
|
||||
return &NETFramework_NETCLRMemoryCollector{
|
||||
AllocatedBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "allocated_bytes_total"),
|
||||
"Displays the total number of bytes allocated on the garbage collection heap.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
FinalizationSurvivors: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "finalization_survivors"),
|
||||
"Displays the number of garbage-collected objects that survive a collection because they are waiting to be finalized.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
HeapSize: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "heap_size_bytes"),
|
||||
"Displays the maximum bytes that can be allocated; it does not indicate the current number of bytes allocated.",
|
||||
[]string{"process", "area"},
|
||||
nil,
|
||||
),
|
||||
PromotedBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "promoted_bytes"),
|
||||
"Displays the bytes that were promoted from the generation to the next one during the last GC. Memory is promoted when it survives a garbage collection.",
|
||||
[]string{"process", "area"},
|
||||
nil,
|
||||
),
|
||||
NumberGCHandles: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "number_gc_handles"),
|
||||
"Displays the current number of garbage collection handles in use. Garbage collection handles are handles to resources external to the common language runtime and the managed environment.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
NumberCollections: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "collections_total"),
|
||||
"Displays the number of times the generation objects are garbage collected since the application started.",
|
||||
[]string{"process", "area"},
|
||||
nil,
|
||||
),
|
||||
NumberInducedGC: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "induced_gc_total"),
|
||||
"Displays the peak number of times garbage collection was performed because of an explicit call to GC.Collect.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
NumberofPinnedObjects: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "number_pinned_objects"),
|
||||
"Displays the number of pinned objects encountered in the last garbage collection.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
NumberofSinkBlocksinuse: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "number_sink_blocksinuse"),
|
||||
"Displays the current number of synchronization blocks in use. Synchronization blocks are per-object data structures allocated for storing synchronization information. They hold weak references to managed objects and must be scanned by the garbage collector.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
NumberTotalCommittedBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "committed_bytes"),
|
||||
"Displays the amount of virtual memory, in bytes, currently committed by the garbage collector. Committed memory is the physical memory for which space has been reserved in the disk paging file.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
NumberTotalreservedBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "reserved_bytes"),
|
||||
"Displays the amount of virtual memory, in bytes, currently reserved by the garbage collector. Reserved memory is the virtual memory space reserved for the application when no disk or main memory pages have been used.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
TimeinGC: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "gc_time_percent"),
|
||||
"Displays the percentage of time that was spent performing a garbage collection in the last sample.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *NETFramework_NETCLRMemoryCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting win32_perfrawdata_netframework_netclrmemory metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
type Win32_PerfRawData_NETFramework_NETCLRMemory struct {
|
||||
Name string
|
||||
|
||||
AllocatedBytesPersec uint64
|
||||
FinalizationSurvivors uint64
|
||||
Frequency_PerfTime uint64
|
||||
Gen0heapsize uint64
|
||||
Gen0PromotedBytesPerSec uint64
|
||||
Gen1heapsize uint64
|
||||
Gen1PromotedBytesPerSec uint64
|
||||
Gen2heapsize uint64
|
||||
LargeObjectHeapsize uint64
|
||||
NumberBytesinallHeaps uint64
|
||||
NumberGCHandles uint64
|
||||
NumberGen0Collections uint64
|
||||
NumberGen1Collections uint64
|
||||
NumberGen2Collections uint64
|
||||
NumberInducedGC uint64
|
||||
NumberofPinnedObjects uint64
|
||||
NumberofSinkBlocksinuse uint64
|
||||
NumberTotalcommittedBytes uint64
|
||||
NumberTotalreservedBytes uint64
|
||||
PercentTimeinGC uint32
|
||||
ProcessID uint64
|
||||
PromotedFinalizationMemoryfromGen0 uint64
|
||||
PromotedMemoryfromGen0 uint64
|
||||
PromotedMemoryfromGen1 uint64
|
||||
}
|
||||
|
||||
func (c *NETFramework_NETCLRMemoryCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_NETFramework_NETCLRMemory
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
for _, process := range dst {
|
||||
|
||||
if process.Name == "_Global_" {
|
||||
continue
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.AllocatedBytes,
|
||||
prometheus.CounterValue,
|
||||
float64(process.AllocatedBytesPersec),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.FinalizationSurvivors,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.FinalizationSurvivors),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.HeapSize,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.Gen0heapsize),
|
||||
process.Name,
|
||||
"Gen0",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PromotedBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.Gen0PromotedBytesPerSec),
|
||||
process.Name,
|
||||
"Gen0",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.HeapSize,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.Gen1heapsize),
|
||||
process.Name,
|
||||
"Gen1",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PromotedBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.Gen1PromotedBytesPerSec),
|
||||
process.Name,
|
||||
"Gen1",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.HeapSize,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.Gen2heapsize),
|
||||
process.Name,
|
||||
"Gen2",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.HeapSize,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.LargeObjectHeapsize),
|
||||
process.Name,
|
||||
"LOH",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberGCHandles,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.NumberGCHandles),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberCollections,
|
||||
prometheus.CounterValue,
|
||||
float64(process.NumberGen0Collections),
|
||||
process.Name,
|
||||
"Gen0",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberCollections,
|
||||
prometheus.CounterValue,
|
||||
float64(process.NumberGen1Collections),
|
||||
process.Name,
|
||||
"Gen1",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberCollections,
|
||||
prometheus.CounterValue,
|
||||
float64(process.NumberGen2Collections),
|
||||
process.Name,
|
||||
"Gen2",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberInducedGC,
|
||||
prometheus.CounterValue,
|
||||
float64(process.NumberInducedGC),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberofPinnedObjects,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.NumberofPinnedObjects),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberofSinkBlocksinuse,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.NumberofSinkBlocksinuse),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberTotalCommittedBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.NumberTotalcommittedBytes),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberTotalreservedBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.NumberTotalreservedBytes),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TimeinGC,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.PercentTimeinGC)/float64(process.Frequency_PerfTime),
|
||||
process.Name,
|
||||
)
|
||||
}
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
147
collector/netframework_clrremoting.go
Normal file
147
collector/netframework_clrremoting.go
Normal file
@@ -0,0 +1,147 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("netframework_clrremoting", NewNETFramework_NETCLRRemotingCollector)
|
||||
}
|
||||
|
||||
// A NETFramework_NETCLRRemotingCollector is a Prometheus collector for WMI Win32_PerfRawData_NETFramework_NETCLRRemoting metrics
|
||||
type NETFramework_NETCLRRemotingCollector struct {
|
||||
Channels *prometheus.Desc
|
||||
ContextBoundClassesLoaded *prometheus.Desc
|
||||
ContextBoundObjects *prometheus.Desc
|
||||
ContextProxies *prometheus.Desc
|
||||
Contexts *prometheus.Desc
|
||||
TotalRemoteCalls *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewNETFramework_NETCLRRemotingCollector ...
|
||||
func NewNETFramework_NETCLRRemotingCollector() (Collector, error) {
|
||||
const subsystem = "netframework_clrremoting"
|
||||
return &NETFramework_NETCLRRemotingCollector{
|
||||
Channels: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "channels_total"),
|
||||
"Displays the total number of remoting channels registered across all application domains since application started.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
ContextBoundClassesLoaded: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "context_bound_classes_loaded"),
|
||||
"Displays the current number of context-bound classes that are loaded.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
ContextBoundObjects: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "context_bound_objects_total"),
|
||||
"Displays the total number of context-bound objects allocated.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
ContextProxies: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "context_proxies_total"),
|
||||
"Displays the total number of remoting proxy objects in this process since it started.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
Contexts: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "contexts"),
|
||||
"Displays the current number of remoting contexts in the application.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
TotalRemoteCalls: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "remote_calls_total"),
|
||||
"Displays the total number of remote procedure calls invoked since the application started.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *NETFramework_NETCLRRemotingCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting win32_perfrawdata_netframework_netclrremoting metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
type Win32_PerfRawData_NETFramework_NETCLRRemoting struct {
|
||||
Name string
|
||||
|
||||
Channels uint32
|
||||
ContextBoundClassesLoaded uint32
|
||||
ContextBoundObjectsAllocPersec uint32
|
||||
ContextProxies uint32
|
||||
Contexts uint32
|
||||
RemoteCallsPersec uint32
|
||||
TotalRemoteCalls uint32
|
||||
}
|
||||
|
||||
func (c *NETFramework_NETCLRRemotingCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_NETFramework_NETCLRRemoting
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
for _, process := range dst {
|
||||
|
||||
if process.Name == "_Global_" {
|
||||
continue
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Channels,
|
||||
prometheus.CounterValue,
|
||||
float64(process.Channels),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ContextBoundClassesLoaded,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.ContextBoundClassesLoaded),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ContextBoundObjects,
|
||||
prometheus.CounterValue,
|
||||
float64(process.ContextBoundObjectsAllocPersec),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ContextProxies,
|
||||
prometheus.CounterValue,
|
||||
float64(process.ContextProxies),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Contexts,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.Contexts),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TotalRemoteCalls,
|
||||
prometheus.CounterValue,
|
||||
float64(process.TotalRemoteCalls),
|
||||
process.Name,
|
||||
)
|
||||
}
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
118
collector/netframework_clrsecurity.go
Normal file
118
collector/netframework_clrsecurity.go
Normal file
@@ -0,0 +1,118 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("netframework_clrsecurity", NewNETFramework_NETCLRSecurityCollector)
|
||||
}
|
||||
|
||||
// A NETFramework_NETCLRSecurityCollector is a Prometheus collector for WMI Win32_PerfRawData_NETFramework_NETCLRSecurity metrics
|
||||
type NETFramework_NETCLRSecurityCollector struct {
|
||||
NumberLinkTimeChecks *prometheus.Desc
|
||||
TimeinRTchecks *prometheus.Desc
|
||||
StackWalkDepth *prometheus.Desc
|
||||
TotalRuntimeChecks *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewNETFramework_NETCLRSecurityCollector ...
|
||||
func NewNETFramework_NETCLRSecurityCollector() (Collector, error) {
|
||||
const subsystem = "netframework_clrsecurity"
|
||||
return &NETFramework_NETCLRSecurityCollector{
|
||||
NumberLinkTimeChecks: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "link_time_checks_total"),
|
||||
"Displays the total number of link-time code access security checks since the application started.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
TimeinRTchecks: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "rt_checks_time_percent"),
|
||||
"Displays the percentage of time spent performing runtime code access security checks in the last sample.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
StackWalkDepth: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "stack_walk_depth"),
|
||||
"Displays the depth of the stack during that last runtime code access security check.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
TotalRuntimeChecks: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "runtime_checks_total"),
|
||||
"Displays the total number of runtime code access security checks performed since the application started.",
|
||||
[]string{"process"},
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *NETFramework_NETCLRSecurityCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting win32_perfrawdata_netframework_netclrsecurity metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
type Win32_PerfRawData_NETFramework_NETCLRSecurity struct {
|
||||
Name string
|
||||
|
||||
Frequency_PerfTime uint32
|
||||
NumberLinkTimeChecks uint32
|
||||
PercentTimeinRTchecks uint32
|
||||
PercentTimeSigAuthenticating uint64
|
||||
StackWalkDepth uint32
|
||||
TotalRuntimeChecks uint32
|
||||
}
|
||||
|
||||
func (c *NETFramework_NETCLRSecurityCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_NETFramework_NETCLRSecurity
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
for _, process := range dst {
|
||||
|
||||
if process.Name == "_Global_" {
|
||||
continue
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.NumberLinkTimeChecks,
|
||||
prometheus.CounterValue,
|
||||
float64(process.NumberLinkTimeChecks),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TimeinRTchecks,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.PercentTimeinRTchecks)/float64(process.Frequency_PerfTime),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.StackWalkDepth,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.StackWalkDepth),
|
||||
process.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.TotalRuntimeChecks,
|
||||
prometheus.CounterValue,
|
||||
float64(process.TotalRuntimeChecks),
|
||||
process.Name,
|
||||
)
|
||||
}
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
246
collector/os.go
Normal file
246
collector/os.go
Normal file
@@ -0,0 +1,246 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"time"
|
||||
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("os", NewOSCollector)
|
||||
}
|
||||
|
||||
// A OSCollector is a Prometheus collector for WMI metrics
|
||||
type OSCollector struct {
|
||||
OSInformation *prometheus.Desc
|
||||
PhysicalMemoryFreeBytes *prometheus.Desc
|
||||
PagingFreeBytes *prometheus.Desc
|
||||
VirtualMemoryFreeBytes *prometheus.Desc
|
||||
ProcessesLimit *prometheus.Desc
|
||||
ProcessMemoryLimitBytes *prometheus.Desc
|
||||
Processes *prometheus.Desc
|
||||
Users *prometheus.Desc
|
||||
PagingLimitBytes *prometheus.Desc
|
||||
VirtualMemoryBytes *prometheus.Desc
|
||||
VisibleMemoryBytes *prometheus.Desc
|
||||
Time *prometheus.Desc
|
||||
Timezone *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewOSCollector ...
|
||||
func NewOSCollector() (Collector, error) {
|
||||
const subsystem = "os"
|
||||
|
||||
return &OSCollector{
|
||||
OSInformation: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "info"),
|
||||
"OperatingSystem.Caption, OperatingSystem.Version",
|
||||
[]string{"product", "version"},
|
||||
nil,
|
||||
),
|
||||
PagingLimitBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "paging_limit_bytes"),
|
||||
"OperatingSystem.SizeStoredInPagingFiles",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
PagingFreeBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "paging_free_bytes"),
|
||||
"OperatingSystem.FreeSpaceInPagingFiles",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
PhysicalMemoryFreeBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "physical_memory_free_bytes"),
|
||||
"OperatingSystem.FreePhysicalMemory",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
Time: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "time"),
|
||||
"OperatingSystem.LocalDateTime",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
Timezone: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "timezone"),
|
||||
"OperatingSystem.LocalDateTime",
|
||||
[]string{"timezone"},
|
||||
nil,
|
||||
),
|
||||
Processes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "processes"),
|
||||
"OperatingSystem.NumberOfProcesses",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
ProcessesLimit: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "processes_limit"),
|
||||
"OperatingSystem.MaxNumberOfProcesses",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
ProcessMemoryLimitBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "process_memory_limix_bytes"),
|
||||
"OperatingSystem.MaxProcessMemorySize",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
Users: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "users"),
|
||||
"OperatingSystem.NumberOfUsers",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
VirtualMemoryBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "virtual_memory_bytes"),
|
||||
"OperatingSystem.TotalVirtualMemorySize",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
VisibleMemoryBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "visible_memory_bytes"),
|
||||
"OperatingSystem.TotalVisibleMemorySize",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
VirtualMemoryFreeBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "virtual_memory_free_bytes"),
|
||||
"OperatingSystem.FreeVirtualMemory",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *OSCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting os metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Win32_OperatingSystem docs:
|
||||
// - https://msdn.microsoft.com/en-us/library/aa394239 - Win32_OperatingSystem class
|
||||
type Win32_OperatingSystem struct {
|
||||
Caption string
|
||||
FreePhysicalMemory uint64
|
||||
FreeSpaceInPagingFiles uint64
|
||||
FreeVirtualMemory uint64
|
||||
LocalDateTime time.Time
|
||||
MaxNumberOfProcesses uint32
|
||||
MaxProcessMemorySize uint64
|
||||
NumberOfProcesses uint32
|
||||
NumberOfUsers uint32
|
||||
SizeStoredInPagingFiles uint64
|
||||
TotalVirtualMemorySize uint64
|
||||
TotalVisibleMemorySize uint64
|
||||
Version string
|
||||
}
|
||||
|
||||
func (c *OSCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_OperatingSystem
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
if len(dst) == 0 {
|
||||
return nil, errors.New("WMI query returned empty result set")
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.OSInformation,
|
||||
prometheus.GaugeValue,
|
||||
1.0,
|
||||
dst[0].Caption,
|
||||
dst[0].Version,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PhysicalMemoryFreeBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].FreePhysicalMemory*1024), // KiB -> bytes
|
||||
)
|
||||
|
||||
time := dst[0].LocalDateTime
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Time,
|
||||
prometheus.GaugeValue,
|
||||
float64(time.Unix()),
|
||||
)
|
||||
|
||||
timezoneName, _ := time.Zone()
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Timezone,
|
||||
prometheus.GaugeValue,
|
||||
1.0,
|
||||
timezoneName,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PagingFreeBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].FreeSpaceInPagingFiles*1024), // KiB -> bytes
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.VirtualMemoryFreeBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].FreeVirtualMemory*1024), // KiB -> bytes
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ProcessesLimit,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].MaxNumberOfProcesses),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ProcessMemoryLimitBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].MaxProcessMemorySize*1024), // KiB -> bytes
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Processes,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].NumberOfProcesses),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Users,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].NumberOfUsers),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PagingLimitBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].SizeStoredInPagingFiles*1024), // KiB -> bytes
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.VirtualMemoryBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].TotalVirtualMemorySize*1024), // KiB -> bytes
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.VisibleMemoryBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].TotalVisibleMemorySize*1024), // KiB -> bytes
|
||||
)
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
@@ -1,24 +1,37 @@
|
||||
package perflib
|
||||
package collector
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"reflect"
|
||||
"strings"
|
||||
"strconv"
|
||||
|
||||
"github.com/go-kit/log"
|
||||
"github.com/go-kit/log/level"
|
||||
perflibCollector "github.com/leoluk/perflib_exporter/collector"
|
||||
"github.com/leoluk/perflib_exporter/perflib"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
// Conversion factors.
|
||||
const (
|
||||
TicksToSecondScaleFactor = 1 / 1e7
|
||||
WindowsEpoch = 116444736000000000
|
||||
)
|
||||
var nametable = perflib.QueryNameTable("Counter 009") // Reads the names in English TODO: validate that the English names are always present
|
||||
|
||||
func UnmarshalObject(obj *PerfObject, vs interface{}, logger log.Logger) error {
|
||||
func MapCounterToIndex(name string) string {
|
||||
return strconv.Itoa(int(nametable.LookupIndex(name)))
|
||||
}
|
||||
|
||||
func getPerflibSnapshot(objNames string) (map[string]*perflib.PerfObject, error) {
|
||||
objects, err := perflib.QueryPerformanceData(objNames)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
indexed := make(map[string]*perflib.PerfObject)
|
||||
for _, obj := range objects {
|
||||
indexed[obj.Name] = obj
|
||||
}
|
||||
return indexed, nil
|
||||
}
|
||||
|
||||
func unmarshalObject(obj *perflib.PerfObject, vs interface{}) error {
|
||||
if obj == nil {
|
||||
return errors.New("counter not found")
|
||||
return fmt.Errorf("counter not found")
|
||||
}
|
||||
rv := reflect.ValueOf(vs)
|
||||
if rv.Kind() != reflect.Ptr || rv.IsNil() {
|
||||
@@ -39,7 +52,7 @@ func UnmarshalObject(obj *PerfObject, vs interface{}, logger log.Logger) error {
|
||||
target := ev.Index(idx)
|
||||
rt := target.Type()
|
||||
|
||||
counters := make(map[string]*PerfCounter, len(instance.Counters))
|
||||
counters := make(map[string]*perflib.PerfCounter, len(instance.Counters))
|
||||
for _, ctr := range instance.Counters {
|
||||
if ctr.Def.IsBaseValue && !ctr.Def.IsNanosecondCounter {
|
||||
counters[ctr.Def.Name+"_Base"] = ctr
|
||||
@@ -48,26 +61,16 @@ func UnmarshalObject(obj *PerfObject, vs interface{}, logger log.Logger) error {
|
||||
}
|
||||
}
|
||||
|
||||
for i := range target.NumField() {
|
||||
for i := 0; i < target.NumField(); i++ {
|
||||
f := rt.Field(i)
|
||||
tag := f.Tag.Get("perflib")
|
||||
if tag == "" {
|
||||
continue
|
||||
}
|
||||
secondValue := false
|
||||
|
||||
st := strings.Split(tag, ",")
|
||||
tag = st[0]
|
||||
|
||||
for _, t := range st {
|
||||
if t == "secondvalue" {
|
||||
secondValue = true
|
||||
}
|
||||
}
|
||||
|
||||
ctr, found := counters[tag]
|
||||
if !found {
|
||||
_ = level.Debug(logger).Log("msg", fmt.Sprintf("missing counter %q, have %v", tag, counterMapKeys(counters)))
|
||||
log.Debugf("missing counter %q, have %v", tag, counterMapKeys(counters))
|
||||
continue
|
||||
}
|
||||
if !target.Field(i).CanSet() {
|
||||
@@ -77,19 +80,11 @@ func UnmarshalObject(obj *PerfObject, vs interface{}, logger log.Logger) error {
|
||||
return fmt.Errorf("tagged field %v has wrong type %v, must be float64", f.Name, fieldType)
|
||||
}
|
||||
|
||||
if secondValue {
|
||||
if !ctr.Def.HasSecondValue {
|
||||
return fmt.Errorf("tagged field %v expected a SecondValue, which was not present", f.Name)
|
||||
}
|
||||
target.Field(i).SetFloat(float64(ctr.SecondValue))
|
||||
continue
|
||||
}
|
||||
|
||||
switch ctr.Def.CounterType {
|
||||
case PERF_ELAPSED_TIME:
|
||||
target.Field(i).SetFloat(float64(ctr.Value-WindowsEpoch) / float64(obj.Frequency))
|
||||
case PERF_100NSEC_TIMER, PERF_PRECISION_100NS_TIMER:
|
||||
target.Field(i).SetFloat(float64(ctr.Value) * TicksToSecondScaleFactor)
|
||||
case perflibCollector.PERF_ELAPSED_TIME:
|
||||
target.Field(i).SetFloat(float64(ctr.Value-windowsEpoch) / float64(obj.Frequency))
|
||||
case perflibCollector.PERF_100NSEC_TIMER, perflibCollector.PERF_PRECISION_100NS_TIMER:
|
||||
target.Field(i).SetFloat(float64(ctr.Value) * ticksToSecondsScaleFactor)
|
||||
default:
|
||||
target.Field(i).SetFloat(float64(ctr.Value))
|
||||
}
|
||||
@@ -103,7 +98,7 @@ func UnmarshalObject(obj *PerfObject, vs interface{}, logger log.Logger) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func counterMapKeys(m map[string]*PerfCounter) []string {
|
||||
func counterMapKeys(m map[string]*perflib.PerfCounter) []string {
|
||||
keys := make([]string, 0, len(m))
|
||||
for k := range m {
|
||||
keys = append(keys, k)
|
||||
@@ -1,24 +1,22 @@
|
||||
package perflib
|
||||
package collector
|
||||
|
||||
import (
|
||||
"reflect"
|
||||
"testing"
|
||||
|
||||
"github.com/go-kit/log"
|
||||
perflibCollector "github.com/leoluk/perflib_exporter/collector"
|
||||
"github.com/leoluk/perflib_exporter/perflib"
|
||||
)
|
||||
|
||||
type simple struct {
|
||||
ValA float64 `perflib:"Something"`
|
||||
ValB float64 `perflib:"Something Else"`
|
||||
ValC float64 `perflib:"Something Else,secondvalue"`
|
||||
}
|
||||
|
||||
func TestUnmarshalPerflib(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
cases := []struct {
|
||||
name string
|
||||
obj *PerfObject
|
||||
obj *perflib.PerfObject
|
||||
|
||||
expectedOutput []simple
|
||||
expectError bool
|
||||
@@ -31,14 +29,14 @@ func TestUnmarshalPerflib(t *testing.T) {
|
||||
},
|
||||
{
|
||||
name: "Simple",
|
||||
obj: &PerfObject{
|
||||
Instances: []*PerfInstance{
|
||||
obj: &perflib.PerfObject{
|
||||
Instances: []*perflib.PerfInstance{
|
||||
{
|
||||
Counters: []*PerfCounter{
|
||||
Counters: []*perflib.PerfCounter{
|
||||
{
|
||||
Def: &PerfCounterDef{
|
||||
Def: &perflib.PerfCounterDef{
|
||||
Name: "Something",
|
||||
CounterType: PERF_COUNTER_COUNTER,
|
||||
CounterType: perflibCollector.PERF_COUNTER_COUNTER,
|
||||
},
|
||||
Value: 123,
|
||||
},
|
||||
@@ -51,54 +49,52 @@ func TestUnmarshalPerflib(t *testing.T) {
|
||||
},
|
||||
{
|
||||
name: "Multiple properties",
|
||||
obj: &PerfObject{
|
||||
Instances: []*PerfInstance{
|
||||
obj: &perflib.PerfObject{
|
||||
Instances: []*perflib.PerfInstance{
|
||||
{
|
||||
Counters: []*PerfCounter{
|
||||
Counters: []*perflib.PerfCounter{
|
||||
{
|
||||
Def: &PerfCounterDef{
|
||||
Def: &perflib.PerfCounterDef{
|
||||
Name: "Something",
|
||||
CounterType: PERF_COUNTER_COUNTER,
|
||||
CounterType: perflibCollector.PERF_COUNTER_COUNTER,
|
||||
},
|
||||
Value: 123,
|
||||
},
|
||||
{
|
||||
Def: &PerfCounterDef{
|
||||
Name: "Something Else",
|
||||
CounterType: PERF_COUNTER_COUNTER,
|
||||
HasSecondValue: true,
|
||||
Def: &perflib.PerfCounterDef{
|
||||
Name: "Something Else",
|
||||
CounterType: perflibCollector.PERF_COUNTER_COUNTER,
|
||||
},
|
||||
Value: 256,
|
||||
SecondValue: 222,
|
||||
Value: 256,
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
expectedOutput: []simple{{ValA: 123, ValB: 256, ValC: 222}},
|
||||
expectedOutput: []simple{{ValA: 123, ValB: 256}},
|
||||
expectError: false,
|
||||
},
|
||||
{
|
||||
name: "Multiple instances",
|
||||
obj: &PerfObject{
|
||||
Instances: []*PerfInstance{
|
||||
obj: &perflib.PerfObject{
|
||||
Instances: []*perflib.PerfInstance{
|
||||
{
|
||||
Counters: []*PerfCounter{
|
||||
Counters: []*perflib.PerfCounter{
|
||||
{
|
||||
Def: &PerfCounterDef{
|
||||
Def: &perflib.PerfCounterDef{
|
||||
Name: "Something",
|
||||
CounterType: PERF_COUNTER_COUNTER,
|
||||
CounterType: perflibCollector.PERF_COUNTER_COUNTER,
|
||||
},
|
||||
Value: 321,
|
||||
},
|
||||
},
|
||||
},
|
||||
{
|
||||
Counters: []*PerfCounter{
|
||||
Counters: []*perflib.PerfCounter{
|
||||
{
|
||||
Def: &PerfCounterDef{
|
||||
Def: &perflib.PerfCounterDef{
|
||||
Name: "Something",
|
||||
CounterType: PERF_COUNTER_COUNTER,
|
||||
CounterType: perflibCollector.PERF_COUNTER_COUNTER,
|
||||
},
|
||||
Value: 231,
|
||||
},
|
||||
@@ -112,10 +108,8 @@ func TestUnmarshalPerflib(t *testing.T) {
|
||||
}
|
||||
for _, c := range cases {
|
||||
t.Run(c.name, func(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
output := make([]simple, 0)
|
||||
err := UnmarshalObject(c.obj, &output, log.NewNopLogger())
|
||||
err := unmarshalObject(c.obj, &output)
|
||||
if err != nil && !c.expectError {
|
||||
t.Errorf("Did not expect error, got %q", err)
|
||||
}
|
||||
401
collector/process.go
Normal file
401
collector/process.go
Normal file
@@ -0,0 +1,401 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"strconv"
|
||||
"strings"
|
||||
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
"gopkg.in/alecthomas/kingpin.v2"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("process", NewProcessCollector)
|
||||
}
|
||||
|
||||
var (
|
||||
processWhereClause = kingpin.Flag(
|
||||
"collector.process.processes-where",
|
||||
"WQL 'where' clause to use in WMI metrics query. Limits the response to the processes you specify and reduces the size of the response.",
|
||||
).Default("").String()
|
||||
)
|
||||
|
||||
// A ProcessCollector is a Prometheus collector for WMI Win32_PerfRawData_PerfProc_Process metrics
|
||||
type ProcessCollector struct {
|
||||
StartTime *prometheus.Desc
|
||||
CPUTimeTotal *prometheus.Desc
|
||||
HandleCount *prometheus.Desc
|
||||
IOBytesTotal *prometheus.Desc
|
||||
IOOperationsTotal *prometheus.Desc
|
||||
PageFaultsTotal *prometheus.Desc
|
||||
PageFileBytes *prometheus.Desc
|
||||
PoolBytes *prometheus.Desc
|
||||
PriorityBase *prometheus.Desc
|
||||
PrivateBytes *prometheus.Desc
|
||||
ThreadCount *prometheus.Desc
|
||||
VirtualBytes *prometheus.Desc
|
||||
WorkingSet *prometheus.Desc
|
||||
|
||||
queryWhereClause string
|
||||
}
|
||||
|
||||
// NewProcessCollector ...
|
||||
func NewProcessCollector() (Collector, error) {
|
||||
const subsystem = "process"
|
||||
|
||||
if *processWhereClause == "" {
|
||||
log.Warn("No where-clause specified for process collector. This will generate a very large number of metrics!")
|
||||
}
|
||||
|
||||
return &ProcessCollector{
|
||||
StartTime: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "start_time"),
|
||||
"Time of process start.",
|
||||
[]string{"process", "process_id", "creating_process_id"},
|
||||
nil,
|
||||
),
|
||||
CPUTimeTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "cpu_time_total"),
|
||||
"Returns elapsed time that all of the threads of this process used the processor to execute instructions by mode (privileged, user). An instruction is the basic unit of execution in a computer, a thread is the object that executes instructions, and a process is the object created when a program is run. Code executed to handle some hardware interrupts and trap conditions is included in this count.",
|
||||
[]string{"process", "process_id", "creating_process_id", "mode"},
|
||||
nil,
|
||||
),
|
||||
HandleCount: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "handle_count"),
|
||||
"Total number of handles the process has open. This number is the sum of the handles currently open by each thread in the process.",
|
||||
[]string{"process", "process_id", "creating_process_id"},
|
||||
nil,
|
||||
),
|
||||
IOBytesTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "io_bytes_total"),
|
||||
"Bytes issued to I/O operations in different modes (read, write, other). This property counts all I/O activity generated by the process to include file, network, and device I/Os. Read and write mode includes data operations; other mode includes those that do not involve data, such as control operations. ",
|
||||
[]string{"process", "process_id", "creating_process_id", "mode"},
|
||||
nil,
|
||||
),
|
||||
IOOperationsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "io_operations_total"),
|
||||
"I/O operations issued in different modes (read, write, other). This property counts all I/O activity generated by the process to include file, network, and device I/Os. Read and write mode includes data operations; other mode includes those that do not involve data, such as control operations. ",
|
||||
[]string{"process", "process_id", "creating_process_id", "mode"},
|
||||
nil,
|
||||
),
|
||||
PageFaultsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "page_faults_total"),
|
||||
"Page faults by the threads executing in this process. A page fault occurs when a thread refers to a virtual memory page that is not in its working set in main memory. This can cause the page not to be fetched from disk if it is on the standby list and hence already in main memory, or if it is in use by another process with which the page is shared.",
|
||||
[]string{"process", "process_id", "creating_process_id"},
|
||||
nil,
|
||||
),
|
||||
PageFileBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "page_file_bytes"),
|
||||
"Current number of bytes this process has used in the paging file(s). Paging files are used to store pages of memory used by the process that are not contained in other files. Paging files are shared by all processes, and lack of space in paging files can prevent other processes from allocating memory.",
|
||||
[]string{"process", "process_id", "creating_process_id"},
|
||||
nil,
|
||||
),
|
||||
PoolBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "pool_bytes"),
|
||||
"Pool Bytes is the last observed number of bytes in the paged or nonpaged pool. The nonpaged pool is an area of system memory (physical memory used by the operating system) for objects that cannot be written to disk, but must remain in physical memory as long as they are allocated. The paged pool is an area of system memory (physical memory used by the operating system) for objects that can be written to disk when they are not being used. Nonpaged pool bytes is calculated differently than paged pool bytes, so it might not equal the total of paged pool bytes.",
|
||||
[]string{"process", "process_id", "creating_process_id", "pool"},
|
||||
nil,
|
||||
),
|
||||
PriorityBase: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "priority_base"),
|
||||
"Current base priority of this process. Threads within a process can raise and lower their own base priority relative to the process base priority of the process.",
|
||||
[]string{"process", "process_id", "creating_process_id"},
|
||||
nil,
|
||||
),
|
||||
PrivateBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "private_bytes"),
|
||||
"Current number of bytes this process has allocated that cannot be shared with other processes.",
|
||||
[]string{"process", "process_id", "creating_process_id"},
|
||||
nil,
|
||||
),
|
||||
ThreadCount: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "thread_count"),
|
||||
"Number of threads currently active in this process. An instruction is the basic unit of execution in a processor, and a thread is the object that executes instructions. Every running process has at least one thread.",
|
||||
[]string{"process", "process_id", "creating_process_id"},
|
||||
nil,
|
||||
),
|
||||
VirtualBytes: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "virtual_bytes"),
|
||||
"Current size, in bytes, of the virtual address space that the process is using. Use of virtual address space does not necessarily imply corresponding use of either disk or main memory pages. Virtual space is finite and, by using too much, the process can limit its ability to load libraries.",
|
||||
[]string{"process", "process_id", "creating_process_id"},
|
||||
nil,
|
||||
),
|
||||
WorkingSet: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "working_set"),
|
||||
"Maximum number of bytes in the working set of this process at any point in time. The working set is the set of memory pages touched recently by the threads in the process. If free memory in the computer is above a threshold, pages are left in the working set of a process even if they are not in use. When free memory falls below a threshold, pages are trimmed from working sets. If they are needed, they are then soft-faulted back into the working set before they leave main memory.",
|
||||
[]string{"process", "process_id", "creating_process_id"},
|
||||
nil,
|
||||
),
|
||||
queryWhereClause: *processWhereClause,
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *ProcessCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting process metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Win32_PerfRawData_PerfProc_Process docs:
|
||||
// - https://msdn.microsoft.com/en-us/library/aa394323(v=vs.85).aspx
|
||||
type Win32_PerfRawData_PerfProc_Process struct {
|
||||
Name string
|
||||
CreatingProcessID uint32
|
||||
ElapsedTime uint64
|
||||
Frequency_Object uint64
|
||||
HandleCount uint32
|
||||
IDProcess uint32
|
||||
IODataBytesPersec uint64
|
||||
IODataOperationsPersec uint64
|
||||
IOOtherBytesPersec uint64
|
||||
IOOtherOperationsPersec uint64
|
||||
IOReadBytesPersec uint64
|
||||
IOReadOperationsPersec uint64
|
||||
IOWriteBytesPersec uint64
|
||||
IOWriteOperationsPersec uint64
|
||||
PageFaultsPersec uint32
|
||||
PageFileBytes uint64
|
||||
PageFileBytesPeak uint64
|
||||
PercentPrivilegedTime uint64
|
||||
PercentProcessorTime uint64
|
||||
PercentUserTime uint64
|
||||
PoolNonpagedBytes uint32
|
||||
PoolPagedBytes uint32
|
||||
PriorityBase uint32
|
||||
PrivateBytes uint64
|
||||
ThreadCount uint32
|
||||
Timestamp_Object uint64
|
||||
VirtualBytes uint64
|
||||
VirtualBytesPeak uint64
|
||||
WorkingSet uint64
|
||||
WorkingSetPeak uint64
|
||||
WorkingSetPrivate uint64
|
||||
}
|
||||
|
||||
type WorkerProcess struct {
|
||||
AppPoolName string
|
||||
ProcessId uint32
|
||||
}
|
||||
|
||||
func (c *ProcessCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_PerfProc_Process
|
||||
q := queryAllWhere(&dst, c.queryWhereClause)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
var dst_wp []WorkerProcess
|
||||
q_wp := queryAll(&dst_wp)
|
||||
if err := wmi.QueryNamespace(q_wp, &dst_wp, "root\\WebAdministration"); err != nil {
|
||||
log.Debugf("Could not query WebAdministration namespace for IIS worker processes: %v. Skipping", err)
|
||||
}
|
||||
|
||||
for _, process := range dst {
|
||||
|
||||
if process.Name == "_Total" {
|
||||
continue
|
||||
}
|
||||
// Duplicate processes are suffixed # and an index number. Remove those.
|
||||
processName := strings.Split(process.Name, "#")[0]
|
||||
pid := strconv.FormatUint(uint64(process.IDProcess), 10)
|
||||
cpid := strconv.FormatUint(uint64(process.CreatingProcessID), 10)
|
||||
|
||||
for _, wp := range dst_wp {
|
||||
if wp.ProcessId == process.IDProcess {
|
||||
processName = strings.Join([]string{processName, wp.AppPoolName}, "_")
|
||||
break
|
||||
}
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.StartTime,
|
||||
prometheus.GaugeValue,
|
||||
// convert from Windows timestamp (1 jan 1601) to unix timestamp (1 jan 1970)
|
||||
float64(process.ElapsedTime-116444736000000000)/float64(process.Frequency_Object),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.HandleCount,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.HandleCount),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CPUTimeTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(process.PercentPrivilegedTime)*ticksToSecondsScaleFactor,
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
"privileged",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CPUTimeTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(process.PercentUserTime)*ticksToSecondsScaleFactor,
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
"user",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.IOBytesTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(process.IOOtherBytesPersec),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
"other",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.IOOperationsTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(process.IOOtherOperationsPersec),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
"other",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.IOBytesTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(process.IOReadBytesPersec),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
"read",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.IOOperationsTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(process.IOReadOperationsPersec),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
"read",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.IOBytesTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(process.IOWriteBytesPersec),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
"write",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.IOOperationsTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(process.IOWriteOperationsPersec),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
"write",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PageFaultsTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(process.PageFaultsPersec),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PageFileBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.PageFileBytes),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PoolBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.PoolNonpagedBytes),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
"nonpaged",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PoolBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.PoolPagedBytes),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
"paged",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PriorityBase,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.PriorityBase),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PrivateBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.PrivateBytes),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ThreadCount,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.ThreadCount),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.VirtualBytes,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.VirtualBytes),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.WorkingSet,
|
||||
prometheus.GaugeValue,
|
||||
float64(process.WorkingSet),
|
||||
processName,
|
||||
pid,
|
||||
cpid,
|
||||
)
|
||||
}
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
169
collector/service.go
Normal file
169
collector/service.go
Normal file
@@ -0,0 +1,169 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"strings"
|
||||
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
"gopkg.in/alecthomas/kingpin.v2"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("service", NewserviceCollector)
|
||||
}
|
||||
|
||||
var (
|
||||
serviceWhereClause = kingpin.Flag(
|
||||
"collector.service.services-where",
|
||||
"WQL 'where' clause to use in WMI metrics query. Limits the response to the services you specify and reduces the size of the response.",
|
||||
).Default("").String()
|
||||
)
|
||||
|
||||
// A serviceCollector is a Prometheus collector for WMI Win32_Service metrics
|
||||
type serviceCollector struct {
|
||||
State *prometheus.Desc
|
||||
StartMode *prometheus.Desc
|
||||
Status *prometheus.Desc
|
||||
|
||||
queryWhereClause string
|
||||
}
|
||||
|
||||
// NewserviceCollector ...
|
||||
func NewserviceCollector() (Collector, error) {
|
||||
const subsystem = "service"
|
||||
|
||||
if *serviceWhereClause == "" {
|
||||
log.Warn("No where-clause specified for service collector. This will generate a very large number of metrics!")
|
||||
}
|
||||
|
||||
return &serviceCollector{
|
||||
State: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "state"),
|
||||
"The state of the service (State)",
|
||||
[]string{"name", "state"},
|
||||
nil,
|
||||
),
|
||||
StartMode: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "start_mode"),
|
||||
"The start mode of the service (StartMode)",
|
||||
[]string{"name", "start_mode"},
|
||||
nil,
|
||||
),
|
||||
Status: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "status"),
|
||||
"The status of the service (Status)",
|
||||
[]string{"name", "status"},
|
||||
nil,
|
||||
),
|
||||
queryWhereClause: *serviceWhereClause,
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *serviceCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting service metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Win32_Service docs:
|
||||
// - https://msdn.microsoft.com/en-us/library/aa394418(v=vs.85).aspx
|
||||
type Win32_Service struct {
|
||||
Name string
|
||||
State string
|
||||
Status string
|
||||
StartMode string
|
||||
}
|
||||
|
||||
var (
|
||||
allStates = []string{
|
||||
"stopped",
|
||||
"start pending",
|
||||
"stop pending",
|
||||
"running",
|
||||
"continue pending",
|
||||
"pause pending",
|
||||
"paused",
|
||||
"unknown",
|
||||
}
|
||||
allStartModes = []string{
|
||||
"boot",
|
||||
"system",
|
||||
"auto",
|
||||
"manual",
|
||||
"disabled",
|
||||
}
|
||||
allStatuses = []string{
|
||||
"ok",
|
||||
"error",
|
||||
"degraded",
|
||||
"unknown",
|
||||
"pred fail",
|
||||
"starting",
|
||||
"stopping",
|
||||
"service",
|
||||
"stressed",
|
||||
"nonrecover",
|
||||
"no contact",
|
||||
"lost comm",
|
||||
}
|
||||
)
|
||||
|
||||
func (c *serviceCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_Service
|
||||
q := queryAllWhere(&dst, c.queryWhereClause)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
for _, service := range dst {
|
||||
for _, state := range allStates {
|
||||
isCurrentState := 0.0
|
||||
if state == strings.ToLower(service.State) {
|
||||
isCurrentState = 1.0
|
||||
}
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.State,
|
||||
prometheus.GaugeValue,
|
||||
isCurrentState,
|
||||
strings.ToLower(service.Name),
|
||||
state,
|
||||
)
|
||||
}
|
||||
|
||||
for _, startMode := range allStartModes {
|
||||
isCurrentStartMode := 0.0
|
||||
if startMode == strings.ToLower(service.StartMode) {
|
||||
isCurrentStartMode = 1.0
|
||||
}
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.StartMode,
|
||||
prometheus.GaugeValue,
|
||||
isCurrentStartMode,
|
||||
strings.ToLower(service.Name),
|
||||
startMode,
|
||||
)
|
||||
}
|
||||
|
||||
for _, status := range allStatuses {
|
||||
isCurrentStatus := 0.0
|
||||
if status == strings.ToLower(service.Status) {
|
||||
isCurrentStatus = 1.0
|
||||
}
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Status,
|
||||
prometheus.GaugeValue,
|
||||
isCurrentStatus,
|
||||
strings.ToLower(service.Name),
|
||||
status,
|
||||
)
|
||||
}
|
||||
}
|
||||
return nil, nil
|
||||
}
|
||||
126
collector/system.go
Normal file
126
collector/system.go
Normal file
@@ -0,0 +1,126 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("system", NewSystemCollector, "System")
|
||||
}
|
||||
|
||||
// A SystemCollector is a Prometheus collector for WMI metrics
|
||||
type SystemCollector struct {
|
||||
ContextSwitchesTotal *prometheus.Desc
|
||||
ExceptionDispatchesTotal *prometheus.Desc
|
||||
ProcessorQueueLength *prometheus.Desc
|
||||
SystemCallsTotal *prometheus.Desc
|
||||
SystemUpTime *prometheus.Desc
|
||||
Threads *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewSystemCollector ...
|
||||
func NewSystemCollector() (Collector, error) {
|
||||
const subsystem = "system"
|
||||
|
||||
return &SystemCollector{
|
||||
ContextSwitchesTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "context_switches_total"),
|
||||
"Total number of context switches (WMI source: PerfOS_System.ContextSwitchesPersec)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
ExceptionDispatchesTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "exception_dispatches_total"),
|
||||
"Total number of exceptions dispatched (WMI source: PerfOS_System.ExceptionDispatchesPersec)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
ProcessorQueueLength: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "processor_queue_length"),
|
||||
"Length of processor queue (WMI source: PerfOS_System.ProcessorQueueLength)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SystemCallsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "system_calls_total"),
|
||||
"Total number of system calls (WMI source: PerfOS_System.SystemCallsPersec)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SystemUpTime: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "system_up_time"),
|
||||
"System boot time (WMI source: PerfOS_System.SystemUpTime)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
Threads: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "threads"),
|
||||
"Current number of threads (WMI source: PerfOS_System.Threads)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *SystemCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ctx, ch); err != nil {
|
||||
log.Error("failed collecting system metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Win32_PerfRawData_PerfOS_System docs:
|
||||
// - https://web.archive.org/web/20050830140516/http://msdn.microsoft.com/library/en-us/wmisdk/wmi/win32_perfrawdata_perfos_system.asp
|
||||
type system struct {
|
||||
ContextSwitchesPersec float64 `perflib:"Context Switches/sec"`
|
||||
ExceptionDispatchesPersec float64 `perflib:"Exception Dispatches/sec"`
|
||||
ProcessorQueueLength float64 `perflib:"Processor Queue Length"`
|
||||
SystemCallsPersec float64 `perflib:"System Calls/sec"`
|
||||
SystemUpTime float64 `perflib:"System Up Time"`
|
||||
Threads float64 `perflib:"Threads"`
|
||||
}
|
||||
|
||||
func (c *SystemCollector) collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []system
|
||||
if err := unmarshalObject(ctx.perfObjects["System"], &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ContextSwitchesTotal,
|
||||
prometheus.CounterValue,
|
||||
dst[0].ContextSwitchesPersec,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ExceptionDispatchesTotal,
|
||||
prometheus.CounterValue,
|
||||
dst[0].ExceptionDispatchesPersec,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ProcessorQueueLength,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].ProcessorQueueLength,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SystemCallsTotal,
|
||||
prometheus.CounterValue,
|
||||
dst[0].SystemCallsPersec,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SystemUpTime,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].SystemUpTime,
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Threads,
|
||||
prometheus.GaugeValue,
|
||||
dst[0].Threads,
|
||||
)
|
||||
return nil, nil
|
||||
}
|
||||
174
collector/tcp.go
Normal file
174
collector/tcp.go
Normal file
@@ -0,0 +1,174 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("tcp", NewTCPCollector)
|
||||
}
|
||||
|
||||
// A TCPCollector is a Prometheus collector for WMI Win32_PerfRawData_Tcpip_TCPv4 metrics
|
||||
type TCPCollector struct {
|
||||
ConnectionFailures *prometheus.Desc
|
||||
ConnectionsActive *prometheus.Desc
|
||||
ConnectionsEstablished *prometheus.Desc
|
||||
ConnectionsPassive *prometheus.Desc
|
||||
ConnectionsReset *prometheus.Desc
|
||||
SegmentsTotal *prometheus.Desc
|
||||
SegmentsReceivedTotal *prometheus.Desc
|
||||
SegmentsRetransmittedTotal *prometheus.Desc
|
||||
SegmentsSentTotal *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewTCPCollector ...
|
||||
func NewTCPCollector() (Collector, error) {
|
||||
const subsystem = "tcp"
|
||||
|
||||
return &TCPCollector{
|
||||
ConnectionFailures: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "connection_failures"),
|
||||
"(TCP.ConnectionFailures)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
ConnectionsActive: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "connections_active"),
|
||||
"(TCP.ConnectionsActive)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
ConnectionsEstablished: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "connections_established"),
|
||||
"(TCP.ConnectionsEstablished)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
ConnectionsPassive: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "connections_passive"),
|
||||
"(TCP.ConnectionsPassive)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
ConnectionsReset: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "connections_reset"),
|
||||
"(TCP.ConnectionsReset)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SegmentsTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "segments_total"),
|
||||
"(TCP.SegmentsTotal)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SegmentsReceivedTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "segments_received_total"),
|
||||
"(TCP.SegmentsReceivedTotal)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SegmentsRetransmittedTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "segments_retransmitted_total"),
|
||||
"(TCP.SegmentsRetransmittedTotal)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
SegmentsSentTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "segments_sent_total"),
|
||||
"(TCP.SegmentsSentTotal)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *TCPCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting tcp metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Win32_PerfRawData_Tcpip_TCPv4 docs
|
||||
// - https://msdn.microsoft.com/en-us/library/aa394341(v=vs.85).aspx
|
||||
type Win32_PerfRawData_Tcpip_TCPv4 struct {
|
||||
ConnectionFailures uint64
|
||||
ConnectionsActive uint64
|
||||
ConnectionsEstablished uint64
|
||||
ConnectionsPassive uint64
|
||||
ConnectionsReset uint64
|
||||
SegmentsPersec uint64
|
||||
SegmentsReceivedPersec uint64
|
||||
SegmentsRetransmittedPersec uint64
|
||||
SegmentsSentPersec uint64
|
||||
}
|
||||
|
||||
func (c *TCPCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_Tcpip_TCPv4
|
||||
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if len(dst) == 0 {
|
||||
return nil, errors.New("WMI query returned empty result set")
|
||||
}
|
||||
|
||||
// Counters
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ConnectionFailures,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].ConnectionFailures),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ConnectionsActive,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].ConnectionsActive),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ConnectionsEstablished,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].ConnectionsEstablished),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ConnectionsPassive,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].ConnectionsPassive),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ConnectionsReset,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].ConnectionsReset),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SegmentsTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].SegmentsPersec),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SegmentsReceivedTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].SegmentsReceivedPersec),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SegmentsRetransmittedTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].SegmentsRetransmittedPersec),
|
||||
)
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.SegmentsSentTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].SegmentsSentPersec),
|
||||
)
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
84
collector/terminal_services.go
Normal file
84
collector/terminal_services.go
Normal file
@@ -0,0 +1,84 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"errors"
|
||||
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("terminal_services", NewTerminalServicesCollector)
|
||||
}
|
||||
|
||||
// A TerminalServicesCollector is a Prometheus collector for WMI
|
||||
// Win32_PerfRawData_LocalSessionManager_TerminalServices & Win32_PerfRawData_TermService_TerminalServicesSession metrics
|
||||
type TerminalServicesCollector struct {
|
||||
Local_session_count *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewTerminalServicesCollector ...
|
||||
func NewTerminalServicesCollector() (Collector, error) {
|
||||
const subsystem = "terminal_services"
|
||||
return &TerminalServicesCollector{
|
||||
Local_session_count: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "local_session_count"),
|
||||
"Number of Terminal Services sessions",
|
||||
[]string{"session"},
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *TerminalServicesCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collectTSSessionCount(ch); err != nil {
|
||||
log.Error("failed collecting terminal services session count metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
type Win32_PerfRawData_LocalSessionManager_TerminalServices struct {
|
||||
ActiveSessions uint32
|
||||
InactiveSessions uint32
|
||||
TotalSessions uint32
|
||||
}
|
||||
|
||||
func (c *TerminalServicesCollector) collectTSSessionCount(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_LocalSessionManager_TerminalServices
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if len(dst) == 0 {
|
||||
return nil, errors.New("WMI query returned empty result set")
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Local_session_count,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].ActiveSessions),
|
||||
"active",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Local_session_count,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].InactiveSessions),
|
||||
"inactive",
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Local_session_count,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].TotalSessions),
|
||||
"total",
|
||||
)
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
299
collector/textfile.go
Normal file
299
collector/textfile.go
Normal file
@@ -0,0 +1,299 @@
|
||||
// Copyright 2015 The Prometheus Authors
|
||||
// Licensed under the Apache License, Version 2.0 (the "License");
|
||||
// you may not use this file except in compliance with the License.
|
||||
// You may obtain a copy of the License at
|
||||
//
|
||||
// http://www.apache.org/licenses/LICENSE-2.0
|
||||
//
|
||||
// Unless required by applicable law or agreed to in writing, software
|
||||
// distributed under the License is distributed on an "AS IS" BASIS,
|
||||
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
// See the License for the specific language governing permissions and
|
||||
// limitations under the License.
|
||||
|
||||
// +build !notextfile
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"io"
|
||||
"io/ioutil"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"sort"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/dimchansky/utfbom"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
dto "github.com/prometheus/client_model/go"
|
||||
"github.com/prometheus/common/expfmt"
|
||||
"github.com/prometheus/common/log"
|
||||
kingpin "gopkg.in/alecthomas/kingpin.v2"
|
||||
)
|
||||
|
||||
var (
|
||||
textFileDirectory = kingpin.Flag(
|
||||
"collector.textfile.directory",
|
||||
"Directory to read text files with metrics from.",
|
||||
).Default("C:\\Program Files\\wmi_exporter\\textfile_inputs").String()
|
||||
|
||||
mtimeDesc = prometheus.NewDesc(
|
||||
"wmi_textfile_mtime_seconds",
|
||||
"Unixtime mtime of textfiles successfully read.",
|
||||
[]string{"file"},
|
||||
nil,
|
||||
)
|
||||
)
|
||||
|
||||
type textFileCollector struct {
|
||||
path string
|
||||
// Only set for testing to get predictable output.
|
||||
mtime *float64
|
||||
}
|
||||
|
||||
func init() {
|
||||
registerCollector("textfile", NewTextFileCollector)
|
||||
}
|
||||
|
||||
// NewTextFileCollector returns a new Collector exposing metrics read from files
|
||||
// in the given textfile directory.
|
||||
func NewTextFileCollector() (Collector, error) {
|
||||
return &textFileCollector{
|
||||
path: *textFileDirectory,
|
||||
}, nil
|
||||
}
|
||||
|
||||
func convertMetricFamily(metricFamily *dto.MetricFamily, ch chan<- prometheus.Metric) {
|
||||
var valType prometheus.ValueType
|
||||
var val float64
|
||||
|
||||
allLabelNames := map[string]struct{}{}
|
||||
for _, metric := range metricFamily.Metric {
|
||||
labels := metric.GetLabel()
|
||||
for _, label := range labels {
|
||||
if _, ok := allLabelNames[label.GetName()]; !ok {
|
||||
allLabelNames[label.GetName()] = struct{}{}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
for _, metric := range metricFamily.Metric {
|
||||
if metric.TimestampMs != nil {
|
||||
log.Warnf("Ignoring unsupported custom timestamp on textfile collector metric %v", metric)
|
||||
}
|
||||
|
||||
labels := metric.GetLabel()
|
||||
var names []string
|
||||
var values []string
|
||||
for _, label := range labels {
|
||||
names = append(names, label.GetName())
|
||||
values = append(values, label.GetValue())
|
||||
}
|
||||
|
||||
for k := range allLabelNames {
|
||||
present := false
|
||||
for _, name := range names {
|
||||
if k == name {
|
||||
present = true
|
||||
break
|
||||
}
|
||||
}
|
||||
if present == false {
|
||||
names = append(names, k)
|
||||
values = append(values, "")
|
||||
}
|
||||
}
|
||||
|
||||
metricType := metricFamily.GetType()
|
||||
switch metricType {
|
||||
case dto.MetricType_COUNTER:
|
||||
valType = prometheus.CounterValue
|
||||
val = metric.Counter.GetValue()
|
||||
|
||||
case dto.MetricType_GAUGE:
|
||||
valType = prometheus.GaugeValue
|
||||
val = metric.Gauge.GetValue()
|
||||
|
||||
case dto.MetricType_UNTYPED:
|
||||
valType = prometheus.UntypedValue
|
||||
val = metric.Untyped.GetValue()
|
||||
|
||||
case dto.MetricType_SUMMARY:
|
||||
quantiles := map[float64]float64{}
|
||||
for _, q := range metric.Summary.Quantile {
|
||||
quantiles[q.GetQuantile()] = q.GetValue()
|
||||
}
|
||||
ch <- prometheus.MustNewConstSummary(
|
||||
prometheus.NewDesc(
|
||||
*metricFamily.Name,
|
||||
metricFamily.GetHelp(),
|
||||
names, nil,
|
||||
),
|
||||
metric.Summary.GetSampleCount(),
|
||||
metric.Summary.GetSampleSum(),
|
||||
quantiles, values...,
|
||||
)
|
||||
case dto.MetricType_HISTOGRAM:
|
||||
buckets := map[float64]uint64{}
|
||||
for _, b := range metric.Histogram.Bucket {
|
||||
buckets[b.GetUpperBound()] = b.GetCumulativeCount()
|
||||
}
|
||||
ch <- prometheus.MustNewConstHistogram(
|
||||
prometheus.NewDesc(
|
||||
*metricFamily.Name,
|
||||
metricFamily.GetHelp(),
|
||||
names, nil,
|
||||
),
|
||||
metric.Histogram.GetSampleCount(),
|
||||
metric.Histogram.GetSampleSum(),
|
||||
buckets, values...,
|
||||
)
|
||||
default:
|
||||
log.Errorf("unknown metric type for file")
|
||||
continue
|
||||
}
|
||||
if metricType == dto.MetricType_GAUGE || metricType == dto.MetricType_COUNTER || metricType == dto.MetricType_UNTYPED {
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
prometheus.NewDesc(
|
||||
*metricFamily.Name,
|
||||
metricFamily.GetHelp(),
|
||||
names, nil,
|
||||
),
|
||||
valType, val, values...,
|
||||
)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func (c *textFileCollector) exportMTimes(mtimes map[string]time.Time, ch chan<- prometheus.Metric) {
|
||||
// Export the mtimes of the successful files.
|
||||
if len(mtimes) > 0 {
|
||||
// Sorting is needed for predictable output comparison in tests.
|
||||
filenames := make([]string, 0, len(mtimes))
|
||||
for filename := range mtimes {
|
||||
filenames = append(filenames, filename)
|
||||
}
|
||||
sort.Strings(filenames)
|
||||
|
||||
for _, filename := range filenames {
|
||||
mtime := float64(mtimes[filename].UnixNano() / 1e9)
|
||||
if c.mtime != nil {
|
||||
mtime = *c.mtime
|
||||
}
|
||||
ch <- prometheus.MustNewConstMetric(mtimeDesc, prometheus.GaugeValue, mtime, filename)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
type carriageReturnFilteringReader struct {
|
||||
r io.Reader
|
||||
}
|
||||
|
||||
// Read returns data from the underlying io.Reader, but with \r filtered out
|
||||
func (cr carriageReturnFilteringReader) Read(p []byte) (int, error) {
|
||||
buf := make([]byte, len(p))
|
||||
n, err := cr.r.Read(buf)
|
||||
|
||||
if err != nil && err != io.EOF {
|
||||
return n, err
|
||||
}
|
||||
|
||||
pi := 0
|
||||
for i := 0; i < n; i++ {
|
||||
if buf[i] != '\r' {
|
||||
p[pi] = buf[i]
|
||||
pi++
|
||||
}
|
||||
}
|
||||
|
||||
return pi, err
|
||||
}
|
||||
|
||||
// Update implements the Collector interface.
|
||||
func (c *textFileCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
error := 0.0
|
||||
mtimes := map[string]time.Time{}
|
||||
|
||||
// Iterate over files and accumulate their metrics.
|
||||
files, err := ioutil.ReadDir(c.path)
|
||||
if err != nil && c.path != "" {
|
||||
log.Errorf("Error reading textfile collector directory %q: %s", c.path, err)
|
||||
error = 1.0
|
||||
}
|
||||
|
||||
fileLoop:
|
||||
for _, f := range files {
|
||||
if !strings.HasSuffix(f.Name(), ".prom") {
|
||||
continue
|
||||
}
|
||||
path := filepath.Join(c.path, f.Name())
|
||||
log.Debugf("Processing file %q", path)
|
||||
file, err := os.Open(path)
|
||||
if err != nil {
|
||||
log.Errorf("Error opening %q: %v", path, err)
|
||||
error = 1.0
|
||||
continue
|
||||
}
|
||||
var parser expfmt.TextParser
|
||||
r, encoding := utfbom.Skip(carriageReturnFilteringReader{r: file})
|
||||
if err = checkBOM(encoding); err != nil {
|
||||
log.Errorf("Invalid file encoding detected in %s: %s - file must be UTF8", path, err.Error())
|
||||
error = 1.0
|
||||
continue
|
||||
}
|
||||
parsedFamilies, err := parser.TextToMetricFamilies(r)
|
||||
closeErr := file.Close()
|
||||
if closeErr != nil {
|
||||
log.Warnf("Error closing file: %v", err)
|
||||
}
|
||||
if err != nil {
|
||||
log.Errorf("Error parsing %q: %v", path, err)
|
||||
error = 1.0
|
||||
continue
|
||||
}
|
||||
for _, mf := range parsedFamilies {
|
||||
for _, m := range mf.Metric {
|
||||
if m.TimestampMs != nil {
|
||||
log.Errorf("Textfile %q contains unsupported client-side timestamps, skipping entire file", path)
|
||||
error = 1.0
|
||||
continue fileLoop
|
||||
}
|
||||
}
|
||||
if mf.Help == nil {
|
||||
help := fmt.Sprintf("Metric read from %s", path)
|
||||
mf.Help = &help
|
||||
}
|
||||
}
|
||||
|
||||
// Only set this once it has been parsed and validated, so that
|
||||
// a failure does not appear fresh.
|
||||
mtimes[f.Name()] = f.ModTime()
|
||||
|
||||
for _, mf := range parsedFamilies {
|
||||
convertMetricFamily(mf, ch)
|
||||
}
|
||||
}
|
||||
|
||||
c.exportMTimes(mtimes, ch)
|
||||
|
||||
// Export if there were errors.
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
prometheus.NewDesc(
|
||||
"wmi_textfile_scrape_error",
|
||||
"1 if there was an error opening or reading a file, 0 otherwise",
|
||||
nil, nil,
|
||||
),
|
||||
prometheus.GaugeValue, error,
|
||||
)
|
||||
return nil
|
||||
}
|
||||
|
||||
func checkBOM(encoding utfbom.Encoding) error {
|
||||
if encoding == utfbom.Unknown || encoding == utfbom.UTF8 {
|
||||
return nil
|
||||
}
|
||||
|
||||
return fmt.Errorf(encoding.String())
|
||||
}
|
||||
47
collector/textfile_test.go
Normal file
47
collector/textfile_test.go
Normal file
@@ -0,0 +1,47 @@
|
||||
package collector
|
||||
|
||||
import (
|
||||
"github.com/dimchansky/utfbom"
|
||||
"io/ioutil"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestCRFilter(t *testing.T) {
|
||||
sr := strings.NewReader("line 1\r\nline 2")
|
||||
cr := carriageReturnFilteringReader{r: sr}
|
||||
b, err := ioutil.ReadAll(cr)
|
||||
if err != nil {
|
||||
t.Error(err)
|
||||
}
|
||||
|
||||
if string(b) != "line 1\nline 2" {
|
||||
t.Errorf("Unexpected output %q", b)
|
||||
}
|
||||
}
|
||||
|
||||
func TestCheckBOM(t *testing.T) {
|
||||
testdata := []struct {
|
||||
encoding utfbom.Encoding
|
||||
err string
|
||||
}{
|
||||
{utfbom.Unknown, ""},
|
||||
{utfbom.UTF8, ""},
|
||||
{utfbom.UTF16BigEndian, "UTF16BigEndian"},
|
||||
{utfbom.UTF16LittleEndian, "UTF16LittleEndian"},
|
||||
{utfbom.UTF32BigEndian, "UTF32BigEndian"},
|
||||
{utfbom.UTF32LittleEndian, "UTF32LittleEndian"},
|
||||
}
|
||||
for _, d := range testdata {
|
||||
err := checkBOM(d.encoding)
|
||||
if d.err == "" && err != nil {
|
||||
t.Error(err)
|
||||
}
|
||||
if d.err != "" && err == nil {
|
||||
t.Errorf("Missing expected error %s", d.err)
|
||||
}
|
||||
if err != nil && !strings.Contains(err.Error(), d.err) {
|
||||
t.Error(err)
|
||||
}
|
||||
}
|
||||
}
|
||||
103
collector/thermalzone.go
Normal file
103
collector/thermalzone.go
Normal file
@@ -0,0 +1,103 @@
|
||||
package collector
|
||||
|
||||
import (
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("thermalzone", NewThermalZoneCollector)
|
||||
}
|
||||
|
||||
// A thermalZoneCollector is a Prometheus collector for WMI Win32_PerfRawData_Counters_ThermalZoneInformation metrics
|
||||
type thermalZoneCollector struct {
|
||||
PercentPassiveLimit *prometheus.Desc
|
||||
Temperature *prometheus.Desc
|
||||
ThrottleReasons *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewThermalZoneCollector ...
|
||||
func NewThermalZoneCollector() (Collector, error) {
|
||||
const subsystem = "thermalzone"
|
||||
return &thermalZoneCollector{
|
||||
Temperature: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "temperature_celsius"),
|
||||
"(Temperature)",
|
||||
[]string{
|
||||
"name",
|
||||
},
|
||||
nil,
|
||||
),
|
||||
PercentPassiveLimit: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "percent_passive_limit"),
|
||||
"(PercentPassiveLimit)",
|
||||
[]string{
|
||||
"name",
|
||||
},
|
||||
nil,
|
||||
),
|
||||
ThrottleReasons: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "throttle_reasons"),
|
||||
"(ThrottleReasons)",
|
||||
[]string{
|
||||
"name",
|
||||
},
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *thermalZoneCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collect(ch); err != nil {
|
||||
log.Error("failed collecting thermalzone metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Win32_PerfRawData_Counters_ThermalZoneInformation docs:
|
||||
// https://wutils.com/wmi/root/cimv2/win32_perfrawdata_counters_thermalzoneinformation/
|
||||
type Win32_PerfRawData_Counters_ThermalZoneInformation struct {
|
||||
Name string
|
||||
|
||||
HighPrecisionTemperature uint32
|
||||
PercentPassiveLimit uint32
|
||||
ThrottleReasons uint32
|
||||
}
|
||||
|
||||
func (c *thermalZoneCollector) collect(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_Counters_ThermalZoneInformation
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
for _, info := range dst {
|
||||
//Divide by 10 and subtract 273.15 to convert decikelvin to celsius
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.Temperature,
|
||||
prometheus.GaugeValue,
|
||||
(float64(info.HighPrecisionTemperature)/10.0)-273.15,
|
||||
info.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.PercentPassiveLimit,
|
||||
prometheus.GaugeValue,
|
||||
float64(info.PercentPassiveLimit),
|
||||
info.Name,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.ThrottleReasons,
|
||||
prometheus.GaugeValue,
|
||||
float64(info.ThrottleReasons),
|
||||
info.Name,
|
||||
)
|
||||
}
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
344
collector/vmware.go
Normal file
344
collector/vmware.go
Normal file
@@ -0,0 +1,344 @@
|
||||
// +build windows
|
||||
|
||||
package collector
|
||||
|
||||
import (
|
||||
"errors"
|
||||
|
||||
"github.com/StackExchange/wmi"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func init() {
|
||||
registerCollector("vmware", NewVmwareCollector)
|
||||
}
|
||||
|
||||
// A VmwareCollector is a Prometheus collector for WMI Win32_PerfRawData_vmGuestLib_VMem/Win32_PerfRawData_vmGuestLib_VCPU metrics
|
||||
type VmwareCollector struct {
|
||||
MemActive *prometheus.Desc
|
||||
MemBallooned *prometheus.Desc
|
||||
MemLimit *prometheus.Desc
|
||||
MemMapped *prometheus.Desc
|
||||
MemOverhead *prometheus.Desc
|
||||
MemReservation *prometheus.Desc
|
||||
MemShared *prometheus.Desc
|
||||
MemSharedSaved *prometheus.Desc
|
||||
MemShares *prometheus.Desc
|
||||
MemSwapped *prometheus.Desc
|
||||
MemTargetSize *prometheus.Desc
|
||||
MemUsed *prometheus.Desc
|
||||
|
||||
CpuLimitMHz *prometheus.Desc
|
||||
CpuReservationMHz *prometheus.Desc
|
||||
CpuShares *prometheus.Desc
|
||||
CpuStolenTotal *prometheus.Desc
|
||||
CpuTimeTotal *prometheus.Desc
|
||||
EffectiveVMSpeedMHz *prometheus.Desc
|
||||
HostProcessorSpeedMHz *prometheus.Desc
|
||||
}
|
||||
|
||||
// NewVmwareCollector constructs a new VmwareCollector
|
||||
func NewVmwareCollector() (Collector, error) {
|
||||
const subsystem = "vmware"
|
||||
return &VmwareCollector{
|
||||
MemActive: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "mem_active_bytes"),
|
||||
"(MemActiveMB)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
MemBallooned: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "mem_ballooned_bytes"),
|
||||
"(MemBalloonedMB)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
MemLimit: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "mem_limit_bytes"),
|
||||
"(MemLimitMB)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
MemMapped: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "mem_mapped_bytes"),
|
||||
"(MemMappedMB)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
MemOverhead: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "mem_overhead_bytes"),
|
||||
"(MemOverheadMB)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
MemReservation: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "mem_reservation_bytes"),
|
||||
"(MemReservationMB)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
MemShared: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "mem_shared_bytes"),
|
||||
"(MemSharedMB)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
MemSharedSaved: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "mem_shared_saved_bytes"),
|
||||
"(MemSharedSavedMB)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
MemShares: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "mem_shares"),
|
||||
"(MemShares)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
MemSwapped: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "mem_swapped_bytes"),
|
||||
"(MemSwappedMB)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
MemTargetSize: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "mem_target_size_bytes"),
|
||||
"(MemTargetSizeMB)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
MemUsed: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "mem_used_bytes"),
|
||||
"(MemUsedMB)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
|
||||
CpuLimitMHz: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "cpu_limit_mhz"),
|
||||
"(CpuLimitMHz)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
CpuReservationMHz: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "cpu_reservation_mhz"),
|
||||
"(CpuReservationMHz)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
CpuShares: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "cpu_shares"),
|
||||
"(CpuShares)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
CpuStolenTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "cpu_stolen_seconds_total"),
|
||||
"(CpuStolenMs)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
CpuTimeTotal: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "cpu_time_seconds_total"),
|
||||
"(CpuTimePercents)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
EffectiveVMSpeedMHz: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "effective_vm_speed_mhz"),
|
||||
"(EffectiveVMSpeedMHz)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
HostProcessorSpeedMHz: prometheus.NewDesc(
|
||||
prometheus.BuildFQName(Namespace, subsystem, "host_processor_speed_mhz"),
|
||||
"(HostProcessorSpeedMHz)",
|
||||
nil,
|
||||
nil,
|
||||
),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Collect sends the metric values for each metric
|
||||
// to the provided prometheus Metric channel.
|
||||
func (c *VmwareCollector) Collect(ctx *ScrapeContext, ch chan<- prometheus.Metric) error {
|
||||
if desc, err := c.collectMem(ch); err != nil {
|
||||
log.Error("failed collecting vmware memory metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
if desc, err := c.collectCpu(ch); err != nil {
|
||||
log.Error("failed collecting vmware cpu metrics:", desc, err)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
type Win32_PerfRawData_vmGuestLib_VMem struct {
|
||||
MemActiveMB uint64
|
||||
MemBalloonedMB uint64
|
||||
MemLimitMB uint64
|
||||
MemMappedMB uint64
|
||||
MemOverheadMB uint64
|
||||
MemReservationMB uint64
|
||||
MemSharedMB uint64
|
||||
MemSharedSavedMB uint64
|
||||
MemShares uint64
|
||||
MemSwappedMB uint64
|
||||
MemTargetSizeMB uint64
|
||||
MemUsedMB uint64
|
||||
}
|
||||
|
||||
type Win32_PerfRawData_vmGuestLib_VCPU struct {
|
||||
CpuLimitMHz uint64
|
||||
CpuReservationMHz uint64
|
||||
CpuShares uint64
|
||||
CpuStolenMs uint64
|
||||
CpuTimePercents uint64
|
||||
EffectiveVMSpeedMHz uint64
|
||||
HostProcessorSpeedMHz uint64
|
||||
}
|
||||
|
||||
func (c *VmwareCollector) collectMem(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_vmGuestLib_VMem
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if len(dst) == 0 {
|
||||
return nil, errors.New("WMI query returned empty result set")
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemActive,
|
||||
prometheus.GaugeValue,
|
||||
mbToBytes(dst[0].MemActiveMB),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemBallooned,
|
||||
prometheus.GaugeValue,
|
||||
mbToBytes(dst[0].MemBalloonedMB),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemLimit,
|
||||
prometheus.GaugeValue,
|
||||
mbToBytes(dst[0].MemLimitMB),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemMapped,
|
||||
prometheus.GaugeValue,
|
||||
mbToBytes(dst[0].MemMappedMB),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemOverhead,
|
||||
prometheus.GaugeValue,
|
||||
mbToBytes(dst[0].MemOverheadMB),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemReservation,
|
||||
prometheus.GaugeValue,
|
||||
mbToBytes(dst[0].MemReservationMB),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemShared,
|
||||
prometheus.GaugeValue,
|
||||
mbToBytes(dst[0].MemSharedMB),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemSharedSaved,
|
||||
prometheus.GaugeValue,
|
||||
mbToBytes(dst[0].MemSharedSavedMB),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemShares,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].MemShares),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemSwapped,
|
||||
prometheus.GaugeValue,
|
||||
mbToBytes(dst[0].MemSwappedMB),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemTargetSize,
|
||||
prometheus.GaugeValue,
|
||||
mbToBytes(dst[0].MemTargetSizeMB),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.MemUsed,
|
||||
prometheus.GaugeValue,
|
||||
mbToBytes(dst[0].MemUsedMB),
|
||||
)
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
func mbToBytes(mb uint64) float64 {
|
||||
return float64(mb * 1024 * 1024)
|
||||
}
|
||||
|
||||
func (c *VmwareCollector) collectCpu(ch chan<- prometheus.Metric) (*prometheus.Desc, error) {
|
||||
var dst []Win32_PerfRawData_vmGuestLib_VCPU
|
||||
q := queryAll(&dst)
|
||||
if err := wmi.Query(q, &dst); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if len(dst) == 0 {
|
||||
return nil, errors.New("WMI query returned empty result set")
|
||||
}
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CpuLimitMHz,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].CpuLimitMHz),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CpuReservationMHz,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].CpuReservationMHz),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CpuShares,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].CpuShares),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CpuStolenTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].CpuStolenMs)*ticksToSecondsScaleFactor,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.CpuTimeTotal,
|
||||
prometheus.CounterValue,
|
||||
float64(dst[0].CpuTimePercents)*ticksToSecondsScaleFactor,
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.EffectiveVMSpeedMHz,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].EffectiveVMSpeedMHz),
|
||||
)
|
||||
|
||||
ch <- prometheus.MustNewConstMetric(
|
||||
c.HostProcessorSpeedMHz,
|
||||
prometheus.GaugeValue,
|
||||
float64(dst[0].HostProcessorSpeedMHz),
|
||||
)
|
||||
|
||||
return nil, nil
|
||||
}
|
||||
63
collector/wmi.go
Normal file
63
collector/wmi.go
Normal file
@@ -0,0 +1,63 @@
|
||||
package collector
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"reflect"
|
||||
|
||||
"github.com/prometheus/common/log"
|
||||
)
|
||||
|
||||
func className(src interface{}) string {
|
||||
s := reflect.Indirect(reflect.ValueOf(src))
|
||||
t := s.Type()
|
||||
if s.Kind() == reflect.Slice {
|
||||
t = t.Elem()
|
||||
}
|
||||
return t.Name()
|
||||
}
|
||||
|
||||
func queryAll(src interface{}) string {
|
||||
var b bytes.Buffer
|
||||
b.WriteString("SELECT * FROM ")
|
||||
b.WriteString(className(src))
|
||||
|
||||
log.Debugf("Generated WMI query %s", b.String())
|
||||
return b.String()
|
||||
}
|
||||
|
||||
func queryAllForClass(src interface{}, class string) string {
|
||||
var b bytes.Buffer
|
||||
b.WriteString("SELECT * FROM ")
|
||||
b.WriteString(class)
|
||||
|
||||
log.Debugf("Generated WMI query %s", b.String())
|
||||
return b.String()
|
||||
}
|
||||
|
||||
func queryAllWhere(src interface{}, where string) string {
|
||||
var b bytes.Buffer
|
||||
b.WriteString("SELECT * FROM ")
|
||||
b.WriteString(className(src))
|
||||
|
||||
if where != "" {
|
||||
b.WriteString(" WHERE ")
|
||||
b.WriteString(where)
|
||||
}
|
||||
|
||||
log.Debugf("Generated WMI query %s", b.String())
|
||||
return b.String()
|
||||
}
|
||||
|
||||
func queryAllForClassWhere(src interface{}, class string, where string) string {
|
||||
var b bytes.Buffer
|
||||
b.WriteString("SELECT * FROM ")
|
||||
b.WriteString(class)
|
||||
|
||||
if where != "" {
|
||||
b.WriteString(" WHERE ")
|
||||
b.WriteString(where)
|
||||
}
|
||||
|
||||
log.Debugf("Generated WMI query %s", b.String())
|
||||
return b.String()
|
||||
}
|
||||
@@ -1,9 +1,7 @@
|
||||
package wmi
|
||||
package collector
|
||||
|
||||
import (
|
||||
"testing"
|
||||
|
||||
"github.com/go-kit/log"
|
||||
)
|
||||
|
||||
type fakeWmiClass struct {
|
||||
@@ -12,25 +10,23 @@ type fakeWmiClass struct {
|
||||
}
|
||||
|
||||
var (
|
||||
mapQueryAll = func(src interface{}, _ string, _ string) string {
|
||||
return QueryAll(src, log.NewNopLogger())
|
||||
mapQueryAll = func(src interface{}, class string, where string) string {
|
||||
return queryAll(src)
|
||||
}
|
||||
mapQueryAllWhere = func(src interface{}, _ string, where string) string {
|
||||
return QueryAllWhere(src, where, log.NewNopLogger())
|
||||
mapQueryAllWhere = func(src interface{}, class string, where string) string {
|
||||
return queryAllWhere(src, where)
|
||||
}
|
||||
mapQueryAllForClass = func(src interface{}, class string, _ string) string {
|
||||
return QueryAllForClass(src, class, log.NewNopLogger())
|
||||
mapQueryAllForClass = func(src interface{}, class string, where string) string {
|
||||
return queryAllForClass(src, class)
|
||||
}
|
||||
mapQueryAllForClassWhere = func(src interface{}, class string, where string) string {
|
||||
return QueryAllForClassWhere(src, class, where, log.NewNopLogger())
|
||||
return queryAllForClassWhere(src, class, where)
|
||||
}
|
||||
)
|
||||
|
||||
type queryFunc func(src interface{}, class string, where string) string
|
||||
|
||||
func TestCreateQuery(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
cases := []struct {
|
||||
desc string
|
||||
dst interface{}
|
||||
@@ -111,8 +107,6 @@ func TestCreateQuery(t *testing.T) {
|
||||
}
|
||||
for _, c := range cases {
|
||||
t.Run(c.desc, func(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
if q := c.queryFunc(c.dst, c.class, c.where); q != c.expected {
|
||||
t.Errorf("Case %q failed: Expected %q, got %q", c.desc, c.expected, q)
|
||||
}
|
||||
@@ -1,7 +0,0 @@
|
||||
collectors:
|
||||
enabled: cpu,cpu_info,cs,exchange,iis,logical_disk,logon,memory,net,os,process,remote_fx,service,system,tcp,time,terminal_services,textfile
|
||||
collector:
|
||||
service:
|
||||
services-where: "Name='windows_exporter'"
|
||||
log:
|
||||
level: warn
|
||||
@@ -1,140 +0,0 @@
|
||||
{{ template "head" . }}
|
||||
|
||||
{{ template "prom_content_head" . }}
|
||||
<h1>Node Overview - {{ reReplaceAll "(.*?://)([^:/]+?)(:\\d+)?/.*" "$2" .Params.instance }}</h1>
|
||||
|
||||
<h3>CPU Usage</h3>
|
||||
<div id="cpuGraph"></div>
|
||||
<script>
|
||||
new PromConsole.Graph({
|
||||
node: document.querySelector("#cpuGraph"),
|
||||
expr: "sum by (mode)(irate(windows_cpu_time_total{job='node',instance='{{ .Params.instance }}',mode!='idle'}[5m]))",
|
||||
renderer: 'area',
|
||||
max: {{ with printf "count(count by (cpu)(windows_cpu_time_total{job='node',instance='%s'}))" .Params.instance | query }}{{ . | first | value }}{{ else}}undefined{{end}},
|
||||
yAxisFormatter: PromConsole.NumberFormatter.humanizeNoSmallPrefix,
|
||||
yHoverFormatter: PromConsole.NumberFormatter.humanizeNoSmallPrefix,
|
||||
yTitle: 'Cores'
|
||||
})
|
||||
</script>
|
||||
|
||||
<h3>Network Utilization</h3>
|
||||
<div id="networkioGraph"></div>
|
||||
<script>
|
||||
new PromConsole.Graph({
|
||||
node: document.querySelector("#networkioGraph"),
|
||||
expr: [
|
||||
"irate(windows_net_bytes_sent_total{job='node',instance='{{ .Params.instance }}',nic!~'^isatap_ec2_internal'}[5m])",
|
||||
"irate(windows_net_bytes_received_total{job='node',instance='{{ .Params.instance }}',nic!~'^isatap_ec2_internal'}[5m])",
|
||||
],
|
||||
min: 0,
|
||||
name: [ 'sent', 'received' ],
|
||||
yAxisFormatter: PromConsole.NumberFormatter.humanizeNoSmallPrefix,
|
||||
yHoverFormatter: PromConsole.NumberFormatter.humanizeNoSmallPrefix,
|
||||
yUnits: "B",
|
||||
yTitle: 'Network IO'
|
||||
})
|
||||
</script>
|
||||
|
||||
<h3>Disk I/O Utilization</h3>
|
||||
<div id="diskioGraph"></div>
|
||||
<script>
|
||||
new PromConsole.Graph({
|
||||
node: document.querySelector("#diskioGraph"),
|
||||
expr: [
|
||||
"100 - irate(windows_logical_disk_idle_seconds_total{job='node',instance='{{ .Params.instance }}',volume!~'^HarddiskVolume.*$'}[5m]) * 100",
|
||||
],
|
||||
min: 0,
|
||||
name: '[[ volume ]]',
|
||||
yAxisFormatter: PromConsole.NumberFormatter.humanizeNoSmallPrefix,
|
||||
yHoverFormatter: PromConsole.NumberFormatter.humanizeNoSmallPrefix,
|
||||
yUnits: "%",
|
||||
yTitle: 'Disk I/O Utilization'
|
||||
})
|
||||
</script>
|
||||
|
||||
<h3>Memory</h3>
|
||||
<div id="memoryGraph"></div>
|
||||
<script>
|
||||
new PromConsole.Graph({
|
||||
node: document.querySelector("#memoryGraph"),
|
||||
renderer: 'area',
|
||||
expr: [
|
||||
"windows_cs_physical_memory_bytes{job='node',instance='{{ .Params.instance }}'}",
|
||||
"windows_os_physical_memory_free_bytes{job='node',instance='{{ .Params.instance }}'}",
|
||||
"windows_cs_physical_memory__bytes{job='node',instance='{{ .Params.instance }}'} - windows_os_physical_memory_free_bytes{job='node',instance='{{.Params.instance}}'}",
|
||||
"windows_os_virtual_memory_bytes{job='node',instance='{{ .Params.instance }}'}",
|
||||
],
|
||||
name: ["Physical", "Free", "Used", "Virtual"],
|
||||
min: 0,
|
||||
yUnits: "B",
|
||||
yAxisFormatter: PromConsole.NumberFormatter.humanize1024,
|
||||
yHoverFormatter: PromConsole.NumberFormatter.humanize1024,
|
||||
yTitle: 'Memory'
|
||||
})
|
||||
</script>
|
||||
|
||||
{{ template "prom_right_table_head" }}
|
||||
<tr><th colspan="2">Overview</th></tr>
|
||||
<tr>
|
||||
<td>User CPU</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "sum(irate(windows_cpu_time_total{job='node',instance='%s',mode='user'}[5m])) * 100 / count(count by (cpu)(windows_cpu_time_total{job='node',instance='%s'}))" .Params.instance .Params.instance) "%" "printf.1f") }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Privileged CPU</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "sum(irate(windows_cpu_time_total{job='node',instance='%s',mode='privileged'}[5m])) * 100 / count(count by (cpu)(windows_cpu_time_total{job='node',instance='%s'}))" .Params.instance .Params.instance) "%" "printf.1f") }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Memory Total</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "windows_cs_physical_memory_bytes{job='node',instance='%s'}" .Params.instance) "B" "humanize1024") }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Memory Free</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "windows_os_physical_memory_free_bytes{job='node',instance='%s'}" .Params.instance) "B" "humanize1024") }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th colspan="2">Network</th>
|
||||
</tr>
|
||||
{{ range printf "windows_net_bytes_received_total{job='node',instance='%s',nic!='isatap_ec2_internal'}" .Params.instance | query | sortByLabel "nic" }}
|
||||
<tr>
|
||||
<td>{{ .Labels.nic }} Received</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "irate(windows_net_bytes_received_total{job='node',instance='%s',nic='%s'}[5m])" .Labels.instance .Labels.nic) "B/s" "humanize") }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>{{ .Labels.nic }} Transmitted</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "irate(windows_net_bytes_sent_total{job='node',instance='%s',nic='%s'}[5m])" .Labels.instance .Labels.nic) "B/s" "humanize") }}</td>
|
||||
</tr>
|
||||
{{ end }}
|
||||
</tr>
|
||||
<tr>
|
||||
<th colspan="2">Disks</th>
|
||||
</tr>
|
||||
{{ range printf "windows_logical_disk_size_bytes{job='node',instance='%s',volume!~'^HarddiskVolume.*$'}" .Params.instance | query | sortByLabel "volume" }}
|
||||
<tr>
|
||||
<td>{{ .Labels.volume }} Utilization</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "100 - irate(windows_logical_disk_idle_seconds_total{job='node',instance='%s',volume='%s'}[5m]) * 100" .Labels.instance .Labels.volume) "%" "printf.1f") }}</td>
|
||||
</tr>
|
||||
{{ end }}
|
||||
{{ range printf "windows_logical_disk_size_bytes{job='node',instance='%s',volume!~'^HarddiskVolume.*$'}" .Params.instance | query | sortByLabel "volume" }}
|
||||
<tr>
|
||||
<td>{{ .Labels.volume }} Throughput</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "irate(windows_logical_disk_read_bytes_total{job='node',instance='%s',volume='%s'}[5m]) + irate(windows_logical_disk_write_bytes_total{job='node',instance='%s',volume='%s'}[5m])" .Labels.instance .Labels.volume .Labels.instance .Labels.volume) "B/s" "humanize") }}</td>
|
||||
</tr>
|
||||
{{ end }}
|
||||
<tr>
|
||||
<th colspan="2">Filesystem Fullness</th>
|
||||
</tr>
|
||||
{{ define "roughlyNearZero" }}
|
||||
{{ if gt .1 . }}~0{{ else }}{{ printf "%.1f" . }}{{ end }}
|
||||
{{ end }}
|
||||
{{ range printf "windows_logical_disk_size_bytes{job='node',instance='%s',volume!~'^HarddiskVolume.*$'}" .Params.instance | query | sortByLabel "volume" }}
|
||||
<tr>
|
||||
<td>{{ .Labels.volume }}</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "100 - windows_logical_disk_free_bytes{job='node',instance='%s',volume='%s'} / windows_logical_disk_size_bytes{job='node'} * 100" .Labels.instance .Labels.volume) "%" "roughlyNearZero") }}</td>
|
||||
</tr>
|
||||
{{ end }}
|
||||
</tr>
|
||||
{{ template "prom_right_table_tail" }}
|
||||
|
||||
{{ template "prom_content_tail" . }}
|
||||
|
||||
{{ template "tail" }}
|
||||
140
contrib/console_templates/wmi-overview.html
Normal file
140
contrib/console_templates/wmi-overview.html
Normal file
@@ -0,0 +1,140 @@
|
||||
{{ template "head" . }}
|
||||
|
||||
{{ template "prom_content_head" . }}
|
||||
<h1>Node Overview - {{ reReplaceAll "(.*?://)([^:/]+?)(:\\d+)?/.*" "$2" .Params.instance }}</h1>
|
||||
|
||||
<h3>CPU Usage</h3>
|
||||
<div id="cpuGraph"></div>
|
||||
<script>
|
||||
new PromConsole.Graph({
|
||||
node: document.querySelector("#cpuGraph"),
|
||||
expr: "sum by (mode)(irate(wmi_cpu_time_total{job='node',instance='{{ .Params.instance }}',mode!='idle'}[5m]))",
|
||||
renderer: 'area',
|
||||
max: {{ with printf "count(count by (cpu)(wmi_cpu_time_total{job='node',instance='%s'}))" .Params.instance | query }}{{ . | first | value }}{{ else}}undefined{{end}},
|
||||
yAxisFormatter: PromConsole.NumberFormatter.humanizeNoSmallPrefix,
|
||||
yHoverFormatter: PromConsole.NumberFormatter.humanizeNoSmallPrefix,
|
||||
yTitle: 'Cores'
|
||||
})
|
||||
</script>
|
||||
|
||||
<h3>Network Utilization</h3>
|
||||
<div id="networkioGraph"></div>
|
||||
<script>
|
||||
new PromConsole.Graph({
|
||||
node: document.querySelector("#networkioGraph"),
|
||||
expr: [
|
||||
"irate(wmi_net_bytes_sent_total{job='node',instance='{{ .Params.instance }}',nic!~'^isatap_ec2_internal'}[5m])",
|
||||
"irate(wmi_net_bytes_received_total{job='node',instance='{{ .Params.instance }}',nic!~'^isatap_ec2_internal'}[5m])",
|
||||
],
|
||||
min: 0,
|
||||
name: [ 'sent', 'received' ],
|
||||
yAxisFormatter: PromConsole.NumberFormatter.humanizeNoSmallPrefix,
|
||||
yHoverFormatter: PromConsole.NumberFormatter.humanizeNoSmallPrefix,
|
||||
yUnits: "B",
|
||||
yTitle: 'Network IO'
|
||||
})
|
||||
</script>
|
||||
|
||||
<h3>Disk I/O Utilization</h3>
|
||||
<div id="diskioGraph"></div>
|
||||
<script>
|
||||
new PromConsole.Graph({
|
||||
node: document.querySelector("#diskioGraph"),
|
||||
expr: [
|
||||
"100 - irate(wmi_logical_disk_idle_seconds_total{job='node',instance='{{ .Params.instance }}',volume!~'^HarddiskVolume.*$'}[5m]) * 100",
|
||||
],
|
||||
min: 0,
|
||||
name: '[[ volume ]]',
|
||||
yAxisFormatter: PromConsole.NumberFormatter.humanizeNoSmallPrefix,
|
||||
yHoverFormatter: PromConsole.NumberFormatter.humanizeNoSmallPrefix,
|
||||
yUnits: "%",
|
||||
yTitle: 'Disk I/O Utilization'
|
||||
})
|
||||
</script>
|
||||
|
||||
<h3>Memory</h3>
|
||||
<div id="memoryGraph"></div>
|
||||
<script>
|
||||
new PromConsole.Graph({
|
||||
node: document.querySelector("#memoryGraph"),
|
||||
renderer: 'area',
|
||||
expr: [
|
||||
"wmi_cs_physical_memory_bytes{job='node',instance='{{ .Params.instance }}'}",
|
||||
"wmi_os_physical_memory_free_bytes{job='node',instance='{{ .Params.instance }}'}",
|
||||
"wmi_cs_physical_memory__bytes{job='node',instance='{{ .Params.instance }}'} - wmi_os_physical_memory_free_bytes{job='node',instance='{{.Params.instance}}'}",
|
||||
"wmi_os_virtual_memory_bytes{job='node',instance='{{ .Params.instance }}'}",
|
||||
],
|
||||
name: ["Physical", "Free", "Used", "Virtual"],
|
||||
min: 0,
|
||||
yUnits: "B",
|
||||
yAxisFormatter: PromConsole.NumberFormatter.humanize1024,
|
||||
yHoverFormatter: PromConsole.NumberFormatter.humanize1024,
|
||||
yTitle: 'Memory'
|
||||
})
|
||||
</script>
|
||||
|
||||
{{ template "prom_right_table_head" }}
|
||||
<tr><th colspan="2">Overview</th></tr>
|
||||
<tr>
|
||||
<td>User CPU</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "sum(irate(wmi_cpu_time_total{job='node',instance='%s',mode='user'}[5m])) * 100 / count(count by (cpu)(wmi_cpu_time_total{job='node',instance='%s'}))" .Params.instance .Params.instance) "%" "printf.1f") }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Privileged CPU</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "sum(irate(wmi_cpu_time_total{job='node',instance='%s',mode='privileged'}[5m])) * 100 / count(count by (cpu)(wmi_cpu_time_total{job='node',instance='%s'}))" .Params.instance .Params.instance) "%" "printf.1f") }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Memory Total</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "wmi_cs_physical_memory_bytes{job='node',instance='%s'}" .Params.instance) "B" "humanize1024") }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Memory Free</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "wmi_os_physical_memory_free_bytes{job='node',instance='%s'}" .Params.instance) "B" "humanize1024") }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th colspan="2">Network</th>
|
||||
</tr>
|
||||
{{ range printf "wmi_net_bytes_received_total{job='node',instance='%s',nic!='isatap_ec2_internal'}" .Params.instance | query | sortByLabel "nic" }}
|
||||
<tr>
|
||||
<td>{{ .Labels.nic }} Received</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "irate(wmi_net_bytes_received_total{job='node',instance='%s',nic='%s'}[5m])" .Labels.instance .Labels.nic) "B/s" "humanize") }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>{{ .Labels.nic }} Transmitted</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "irate(wmi_net_bytes_sent_total{job='node',instance='%s',nic='%s'}[5m])" .Labels.instance .Labels.nic) "B/s" "humanize") }}</td>
|
||||
</tr>
|
||||
{{ end }}
|
||||
</tr>
|
||||
<tr>
|
||||
<th colspan="2">Disks</th>
|
||||
</tr>
|
||||
{{ range printf "wmi_logical_disk_size_bytes{job='node',instance='%s',volume!~'^HarddiskVolume.*$'}" .Params.instance | query | sortByLabel "volume" }}
|
||||
<tr>
|
||||
<td>{{ .Labels.volume }} Utilization</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "100 - irate(wmi_logical_disk_idle_seconds_total{job='node',instance='%s',volume='%s'}[5m]) * 100" .Labels.instance .Labels.volume) "%" "printf.1f") }}</td>
|
||||
</tr>
|
||||
{{ end }}
|
||||
{{ range printf "wmi_logical_disk_size_bytes{job='node',instance='%s',volume!~'^HarddiskVolume.*$'}" .Params.instance | query | sortByLabel "volume" }}
|
||||
<tr>
|
||||
<td>{{ .Labels.volume }} Throughput</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "irate(wmi_logical_disk_read_bytes_total{job='node',instance='%s',volume='%s'}[5m]) + irate(wmi_logical_disk_write_bytes_total{job='node',instance='%s',volume='%s'}[5m])" .Labels.instance .Labels.volume .Labels.instance .Labels.volume) "B/s" "humanize") }}</td>
|
||||
</tr>
|
||||
{{ end }}
|
||||
<tr>
|
||||
<th colspan="2">Filesystem Fullness</th>
|
||||
</tr>
|
||||
{{ define "roughlyNearZero" }}
|
||||
{{ if gt .1 . }}~0{{ else }}{{ printf "%.1f" . }}{{ end }}
|
||||
{{ end }}
|
||||
{{ range printf "wmi_logical_disk_size_bytes{job='node',instance='%s',volume!~'^HarddiskVolume.*$'}" .Params.instance | query | sortByLabel "volume" }}
|
||||
<tr>
|
||||
<td>{{ .Labels.volume }}</td>
|
||||
<td>{{ template "prom_query_drilldown" (args (printf "100 - wmi_logical_disk_free_bytes{job='node',instance='%s',volume='%s'} / wmi_logical_disk_size_bytes{job='node'} * 100" .Labels.instance .Labels.volume) "%" "roughlyNearZero") }}</td>
|
||||
</tr>
|
||||
{{ end }}
|
||||
</tr>
|
||||
{{ template "prom_right_table_tail" }}
|
||||
|
||||
{{ template "prom_content_tail" . }}
|
||||
|
||||
{{ template "tail" }}
|
||||
@@ -1,34 +1,19 @@
|
||||
# Documentation
|
||||
This directory contains documentation of the collectors in the windows_exporter, with information such as what metrics are exported, any flags for additional configuration, and some example usage in alerts and queries.
|
||||
This directory contains documentation of the collectors in the WMI exporter, with information such as what metrics are exported, any flags for additional configuration, and some example usage in alerts and queries.
|
||||
|
||||
# Collectors
|
||||
- [`ad`](collector.ad.md)
|
||||
- [`adcs`](collector.adcs.md)
|
||||
- [`adfs`](collector.adfs.md)
|
||||
- [`cache`](collector.cache.md)
|
||||
- [`container`](collector.container.md)
|
||||
- [`cpu`](collector.cpu.md)
|
||||
- [`cpu_info`](collector.cpu_info.md)
|
||||
- [`cs`](collector.cs.md)
|
||||
- [`dfsr`](collector.dfsr.md)
|
||||
- [`dhcp`](collector.dhcp.md)
|
||||
- [`diskdrive`](collector.diskdrive.md)
|
||||
- [`dns`](collector.dns.md)
|
||||
- [`exchange`](collector.exchange.md)
|
||||
- [`fsrmquota`](collector.fsrmquota.md)
|
||||
- [`hyperv`](collector.hyperv.md)
|
||||
- [`iis`](collector.iis.md)
|
||||
- [`logical_disk`](collector.logical_disk.md)
|
||||
- [`logon`](collector.logon.md)
|
||||
- [`memory`](collector.memory.md)
|
||||
- [`mscluster_cluster`](collector.mscluster_cluster.md)
|
||||
- [`mscluster_network`](collector.mscluster_network.md)
|
||||
- [`mscluster_node`](collector.mscluster_node.md)
|
||||
- [`mscluster_resource`](collector.mscluster_resource.md)
|
||||
- [`mscluster_resourcegroup`](collector.mscluster_resourcegroup.md)
|
||||
- [`msmq`](collector.msmq.md)
|
||||
- [`mssql`](collector.mssql.md)
|
||||
- [`net`](collector.net.md)
|
||||
- [`netframework_clrexceptions`](collector.netframework_clrexceptions.md)
|
||||
- [`netframework_clrinterop`](collector.netframework_clrinterop.md)
|
||||
- [`netframework_clrjit`](collector.netframework_clrjit.md)
|
||||
@@ -37,21 +22,11 @@ This directory contains documentation of the collectors in the windows_exporter,
|
||||
- [`netframework_clrmemory`](collector.netframework_clrmemory.md)
|
||||
- [`netframework_clrremoting`](collector.netframework_clrremoting.md)
|
||||
- [`netframework_clrsecurity`](collector.netframework_clrsecurity.md)
|
||||
- [`nps`](collector.nps.md)
|
||||
- [`net`](collector.net.md)
|
||||
- [`os`](collector.os.md)
|
||||
- [`physical_disk`](collector.physical_disk.md)
|
||||
- [`process`](collector.process.md)
|
||||
- [`remote_fx`](collector.remote_fx.md)
|
||||
- [`scheduled_task`](collector.scheduled_task.md)
|
||||
- [`service`](collector.service.md)
|
||||
- [`smb`](collector.smb.md)
|
||||
- [`smtp`](collector.smtp.md)
|
||||
- [`system`](collector.system.md)
|
||||
- [`tcp`](collector.tcp.md)
|
||||
- [`teradici_pcoip`](collector.teradici_pcoip.md)
|
||||
- [`terminal_services`](collector.terminal_services.md)
|
||||
- [`textfile`](collector.textfile.md)
|
||||
- [`thermalzone`](collector.thermalzone.md)
|
||||
- [`time`](collector.time.md)
|
||||
- [`vmware`](collector.vmware.md)
|
||||
- [`vmware_blast`](collector.vmware_blast.md)
|
||||
|
||||
@@ -1,47 +1,47 @@
|
||||
# %name% collector
|
||||
|
||||
The %name% collector exposes metrics about ...
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `%name%`
|
||||
Classes | [`...`](https://msdn.microsoft.com/en-us/library/...)
|
||||
Enabled by default? | Yes/No
|
||||
|
||||
## Flags
|
||||
|
||||
### `--collector....`
|
||||
|
||||
Add description...
|
||||
|
||||
Example: `--collector....`
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_...` | ... | counter/gauge/histogram/summary | ...
|
||||
|
||||
### Example metric
|
||||
|
||||
...:
|
||||
|
||||
`windows_...{...} 1`
|
||||
|
||||
## Useful queries
|
||||
### Add queries...
|
||||
|
||||
`...`
|
||||
|
||||
## Alerting examples
|
||||
### Add alerts...
|
||||
|
||||
```yaml
|
||||
- alert: ""
|
||||
expr: ""
|
||||
for: ""
|
||||
labels:
|
||||
urgency: ""
|
||||
annotations:
|
||||
summary: ""
|
||||
```
|
||||
# %name% collector
|
||||
|
||||
The %name% collector exposes metrics about ...
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `%name%`
|
||||
Classes | [`...`](https://msdn.microsoft.com/en-us/library/...)
|
||||
Enabled by default? | Yes/No
|
||||
|
||||
## Flags
|
||||
|
||||
### `--collector....`
|
||||
|
||||
Add description...
|
||||
|
||||
Example: `--collector....`
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`wmi_...` | ... | counter/gauge/histogram/summary | ...
|
||||
|
||||
### Example metric
|
||||
|
||||
...:
|
||||
|
||||
`wmi_...{...} 1`
|
||||
|
||||
## Useful queries
|
||||
### Add queries...
|
||||
|
||||
`...`
|
||||
|
||||
## Alerting examples
|
||||
### Add alerts...
|
||||
|
||||
```yaml
|
||||
- alert: ""
|
||||
expr: ""
|
||||
for: ""
|
||||
labels:
|
||||
urgency: ""
|
||||
annotations:
|
||||
summary: ""
|
||||
```
|
||||
|
||||
@@ -1,89 +1,88 @@
|
||||
# ad collector
|
||||
|
||||
The ad collector exposes metrics about a Active Directory Domain Services domain controller
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `ad`
|
||||
Classes | [`Win32_PerfRawData_DirectoryServices_DirectoryServices`](https://msdn.microsoft.com/en-us/library/ms803980.aspx)
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_ad_address_book_operations_total` | _Not yet documented_ | counter | `operation`
|
||||
`windows_ad_address_book_client_sessions` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_approximate_highest_distinguished_name_tag` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_atq_estimated_delay_seconds` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_atq_outstanding_requests` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_atq_average_request_latency` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_atq_current_threads` | _Not yet documented_ | gauge | `service`
|
||||
`windows_ad_searches_total` | _Not yet documented_ | counter | `scope`
|
||||
`windows_ad_database_operations_total` | _Not yet documented_ | counter | `operation`
|
||||
`windows_ad_binds_total` | _Not yet documented_ | counter | `bind_method`
|
||||
`windows_ad_replication_highest_usn` | _Not yet documented_ | counter | `state`
|
||||
`windows_ad_replication_data_intrasite_bytes_total` | _Not yet documented_ | counter | `direction`
|
||||
`windows_ad_replication_data_intersite_bytes_total` | _Not yet documented_ | counter | `direction`
|
||||
`windows_ad_replication_inbound_sync_objects_remaining` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_replication_inbound_link_value_updates_remaining` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_replication_inbound_objects_updated_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_replication_inbound_objects_filtered_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_replication_inbound_properties_updated_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_replication_inbound_properties_filtered_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_replication_pending_operations` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_replication_pending_synchronizations` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_replication_sync_requests_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_replication_sync_requests_success_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_replication_sync_requests_schema_mismatch_failure_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_name_translations_total` | _Not yet documented_ | counter | `target_name`
|
||||
`windows_ad_change_monitors_registered` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_change_monitor_updates_pending` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_name_cache_hits_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_name_cache_lookups_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_directory_operations_total` | _Not yet documented_ | counter | `operation`, `origin`
|
||||
`windows_ad_directory_search_suboperations_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_security_descriptor_propagation_events_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_security_descriptor_propagation_events_queued` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_security_descriptor_propagation_access_wait_total_seconds` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_security_descriptor_propagation_items_queued_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_directory_service_threads` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_ldap_closed_connections_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_ldap_opened_connections_total` | _Not yet documented_ | counter | `type`
|
||||
`windows_ad_ldap_active_threads` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_ldap_last_bind_time_seconds` | _Not yet documented_ | gauge | None
|
||||
`windows_ad_ldap_searches_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_ldap_udp_operations_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_ldap_writes_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_ldap_client_sessions` | This is the number of sessions opened by LDAP clients at the time the data is taken. This is helpful in determining LDAP client activity and if the DC is able to handle the load. Of course, spikes during normal periods of authentication — such as first thing in the morning — are not necessarily a problem, but long sustained periods of high values indicate an overworked DC | gauge | None
|
||||
`windows_ad_link_values_cleaned_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_phantom_objects_cleaned_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_phantom_objects_visited_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_sam_group_membership_evaluations_total` | _Not yet documented_ | counter | `group_type`
|
||||
`windows_ad_sam_group_membership_global_catalog_evaluations_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_sam_group_membership_evaluations_nontransitive_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_sam_group_membership_evaluations_transitive_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_sam_group_evaluation_latency` | _Not yet documented_ | gauge | `evaluation_type`
|
||||
`windows_ad_sam_computer_creation_requests_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_sam_computer_creation_successful_requests_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_sam_user_creation_requests_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_sam_user_creation_successful_requests_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_sam_query_display_requests_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_sam_enumerations_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_sam_membership_changes_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_sam_password_changes_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_tombstoned_objects_collected_total` | _Not yet documented_ | counter | None
|
||||
`windows_ad_tombstoned_objects_visited_total` | _Not yet documented_ | counter | None
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
# ad collector
|
||||
|
||||
The ad collector exposes metrics about a Active Directory Domain Services domain controller
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `ad`
|
||||
Classes | [`Win32_PerfRawData_DirectoryServices_DirectoryServices`](https://msdn.microsoft.com/en-us/library/ms803980.aspx)
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`wmi_ad_address_book_operations_total` | _Not yet documented_ | counter | `operation`
|
||||
`wmi_ad_address_book_client_sessions` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_approximate_highest_distinguished_name_tag` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_atq_estimated_delay_seconds` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_atq_outstanding_requests` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_atq_average_request_latency` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_atq_current_threads` | _Not yet documented_ | gauge | `service`
|
||||
`wmi_ad_searches_total` | _Not yet documented_ | counter | `scope`
|
||||
`wmi_ad_database_operations_total` | _Not yet documented_ | counter | `operation`
|
||||
`wmi_ad_binds_total` | _Not yet documented_ | counter | `bind_method`
|
||||
`wmi_ad_replication_highest_usn` | _Not yet documented_ | counter | `state`
|
||||
`wmi_ad_replication_data_intrasite_bytes_total` | _Not yet documented_ | counter | `direction`
|
||||
`wmi_ad_replication_data_intersite_bytes_total` | _Not yet documented_ | counter | `direction`
|
||||
`wmi_ad_replication_inbound_sync_objects_remaining` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_replication_inbound_link_value_updates_remaining` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_replication_inbound_objects_updated_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_replication_inbound_objects_filtered_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_replication_inbound_properties_updated_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_replication_inbound_properties_filtered_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_replication_pending_operations` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_replication_pending_synchronizations` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_replication_sync_requests_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_replication_sync_requests_success_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_replication_sync_requests_schema_mismatch_failure_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_name_translations_total` | _Not yet documented_ | counter | `target_name`
|
||||
`wmi_ad_change_monitors_registered` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_change_monitor_updates_pending` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_name_cache_hits_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_name_cache_lookups_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_directory_operations_total` | _Not yet documented_ | counter | `operation`, `origin`
|
||||
`wmi_ad_directory_search_suboperations_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_security_descriptor_propagation_events_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_security_descriptor_propagation_events_queued` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_security_descriptor_propagation_access_wait_total_seconds` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_security_descriptor_propagation_items_queued_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_directory_service_threads` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_ldap_closed_connections_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_ldap_opened_connections_total` | _Not yet documented_ | counter | `type`
|
||||
`wmi_ad_ldap_active_threads` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_ldap_last_bind_time_seconds` | _Not yet documented_ | gauge | None
|
||||
`wmi_ad_ldap_searches_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_ldap_udp_operations_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_ldap_writes_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_link_values_cleaned_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_phantom_objects_cleaned_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_phantom_objects_visited_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_sam_group_membership_evaluations_total` | _Not yet documented_ | counter | `group_type`
|
||||
`wmi_ad_sam_group_membership_global_catalog_evaluations_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_sam_group_membership_evaluations_nontransitive_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_sam_group_membership_evaluations_transitive_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_sam_group_evaluation_latency` | _Not yet documented_ | gauge | `evaluation_type`
|
||||
`wmi_ad_sam_computer_creation_requests_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_sam_computer_creation_successful_requests_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_sam_user_creation_requests_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_sam_user_creation_successful_requests_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_sam_query_display_requests_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_sam_enumerations_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_sam_membership_changes_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_sam_password_changes_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_tombstoned_objects_collected_total` | _Not yet documented_ | counter | None
|
||||
`wmi_ad_tombstoned_objects_visited_total` | _Not yet documented_ | counter | None
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
|
||||
@@ -1,55 +0,0 @@
|
||||
# adcs collector
|
||||
|
||||
The adcs collector exposes metrics about Active Directory Certificate Services, Note that this collector has only been tested against Windows Server 2019.
|
||||
Other Windows Server versions may work but are not tested.
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `adcs`
|
||||
Data source | Perflib
|
||||
Counters | `Certification Authority`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
|requests_total|Total certificate requests processed|counter|`cert_template`|
|
||||
|request_processing_time_seconds|Last time elapsed for certificate requests|gauge|`cert_template`|
|
||||
|retrievals_total|Last time elapsed for certificate requests|counter|`cert_template`|
|
||||
|retrievals_processing_time_seconds|Last time elapsed for certificate retrieval request|gauge|`cert_template`|
|
||||
|failed_requests_total|Total failed certificate requests processed|counter|`cert_template`|
|
||||
|issued_requests_total|Total issued certificate requests processed|counter|`cert_template`|
|
||||
|pending_requests_total|Total pending certificate requests processed|counter|`cert_template`|
|
||||
|request_cryptographic_signing_time_seconds|Last time elapsed for signing operation request|gauge|`cert_template`|
|
||||
|request_policy_module_processing_time_seconds|Last time elapsed for policy module processing request|gauge|`cert_template`|
|
||||
|challenge_responses_total|Total certificate challenge responses processed|counter|`cert_template`|
|
||||
|challenge_response_processing_time_seconds|Last time elapsed for challenge response|gauge|`cert_template`|
|
||||
|signed_certificate_timestamp_lists_total|Total Signed Certificate Timestamp Lists processed|counter|`cert_template`|
|
||||
|signed_certificate_timestamp_list_processing_time_seconds|Last time elapsed for Signed Certificate Timestamp List|gauge|`cert_template`|
|
||||
|
||||
### Example metric
|
||||
```
|
||||
windows_adcs_issued_requests_total{cert_template="Administrator"} 0
|
||||
windows_adcs_issued_requests_total{cert_template="DirectoryEmailReplication"} 0
|
||||
windows_adcs_issued_requests_total{cert_template="DomainController"} 1
|
||||
windows_adcs_issued_requests_total{cert_template="DomainControllerAuthentication"} 0
|
||||
windows_adcs_issued_requests_total{cert_template="EFS"} 0
|
||||
windows_adcs_issued_requests_total{cert_template="EFSRecovery"} 0
|
||||
windows_adcs_issued_requests_total{cert_template="KerberosAuthentication"} 0
|
||||
windows_adcs_issued_requests_total{cert_template="Machine"} 0
|
||||
windows_adcs_issued_requests_total{cert_template="SubCA"} 0
|
||||
windows_adcs_issued_requests_total{cert_template="User"} 0
|
||||
windows_adcs_issued_requests_total{cert_template="WebServer"} 0
|
||||
windows_adcs_issued_requests_total{cert_template="_Total"} 1
|
||||
```
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
@@ -1,89 +1,51 @@
|
||||
# adfs collector
|
||||
|
||||
The ADFS collector exposes metrics about Active Directory Federation Services. Note that this collector has only been tested against ADFS 4.0/ [Farm Behavior (FLB) 3](https://docs.microsoft.com/en-us/windows-server/identity/ad-fs/deployment/upgrading-to-ad-fs-in-windows-server#ad-fs-farm-behavior-levels-fbl) (Server 2016).
|
||||
Other ADFS versions may work but are not tested.
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `adfs`
|
||||
Data source | Perflib
|
||||
Counters | `AD FS`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_adfs_ad_login_connection_failures_total` | Total number of connection failures between the ADFS server and the Active Directory domain controller(s) | counter | None
|
||||
`windows_adfs_certificate_authentications_total` | Total number of [User Certificate](https://docs.microsoft.com/en-us/windows-server/identity/ad-fs/operations/configure-user-certificate-authentication) authentications. I.E. smart cards or mobile devices with provisioned client certificates | counter | None
|
||||
`windows_adfs_device_authentications_total` | Total number of [device authentications](https://docs.microsoft.com/en-us/windows-server/identity/ad-fs/operations/device-authentication-controls-in-ad-fs) (SignedToken, clientTLS, PkeyAuth). Device authentication is only available on ADFS 2016 or later | counter | None
|
||||
`windows_adfs_extranet_account_lockouts_total` | Total number of [extranet lockouts](https://docs.microsoft.com/en-us/windows-server/identity/ad-fs/operations/configure-ad-fs-extranet-smart-lockout-protection). Requires the Extranet Lockout feature to be enabled | counter | None
|
||||
`windows_adfs_federated_authentications_total` | Total number of authentications from federated sources. E.G. Office365 | counter | None
|
||||
`windows_adfs_passport_authentications_total` | Total number of authentications from [Microsoft Passport](https://en.wikipedia.org/wiki/Microsoft_account) (now named Microsoft Account) | counter | None
|
||||
`windows_adfs_password_change_failed_total` | Total number of failed password changes. The Password Change Portal must be enabled in the AD FS Management tool in order to allow user password changes | counter | None
|
||||
`windows_adfs_password_change_succeeded_total` | Total number of succeeded password changes. The Password Change Portal must be enabled in the AD FS Management tool in order to allow user password changes | counter | None
|
||||
`windows_adfs_token_requests_total` | Total number of requested access tokens | counter | None
|
||||
`windows_adfs_windows_integrated_authentications_total` | Total number of Windows integrated authentications using Kerberos or NTLM | counter | None
|
||||
`windows_adfs_passive_requests_total` | Total number of passive (browser-based) requests | counter | None
|
||||
`windows_adfs_oauth_authorization_requests_total` | Total number of incoming requests to the OAuth Authorization endpoint | counter | None
|
||||
`windows_adfs_oauth_client_authentication_success_total` | Total number of successful OAuth client Authentications | counter | None
|
||||
`windows_adfs_oauth_client_authentication_failure_total` | Total number of failed OAuth client Authentications | counter | None
|
||||
`windows_adfs_oauth_client_credentials_failure_total` | Total number of failed OAuth Client Credentials Requests | counter | None
|
||||
`windows_adfs_oauth_client_credentials_success_total` | Total number of successful RP tokens issued for OAuth Client Credentials Requests | counter | None
|
||||
`windows_adfs_oauth_client_privkey_jwt_authentication_failure_total` | Total number of failed OAuth Client Private Key Jwt Authentications | counter | None
|
||||
`windows_adfs_oauth_client_privkey_jwt_authentications_success_total` | Total number of successful OAuth Client Private Key Jwt Authentications | counter | None
|
||||
`windows_adfs_oauth_client_secret_basic_authentications_failure_total` | Total number of failed OAuth Client Secret Basic Authentications | counter | None
|
||||
`windows_adfs_oauth_client_secret_basic_authentications_success_total` | Total number of successful OAuth Client Secret Basic Authentications | counter | None
|
||||
`windows_adfs_oauth_client_secret_post_authentications_failure_total` | Total number of failed OAuth Client Secret Post Authentications | counter | None
|
||||
`windows_adfs_oauth_client_secret_post_authentications_success_total` | Total number of successful OAuth Client Secret Post Authentications | counter | None
|
||||
`windows_adfs_oauth_client_windows_authentications_failure_total` | Total number of failed OAuth Client Windows Integrated Authentications | counter | None
|
||||
`windows_adfs_oauth_client_windows_authentications_success_total` | Total number of successful OAuth Client Windows Integrated Authentications | counter | None
|
||||
`windows_adfs_oauth_logon_certificate_requests_failure_total` | Total number of failed OAuth Logon Certificate Requests | counter | None
|
||||
`windows_adfs_oauth_logon_certificate_token_requests_success_total` | Total number of successful RP tokens issued for OAuth Logon Certificate Requests | counter | None
|
||||
`windows_adfs_oauth_password_grant_requests_failure_total` | Total number of failed OAuth Password Grant Requests | counter | None
|
||||
`windows_adfs_oauth_password_grant_requests_success_total` | Total number of successful OAuth Password Grant Requests | counter | None
|
||||
`windows_adfs_oauth_token_requests_success_total` | Total number of successful RP tokens issued over OAuth protocol | counter | None
|
||||
`windows_adfs_samlp_token_requests_success_total` | Total number of successful RP tokens issued over SAML-P protocol | counter | None
|
||||
`windows_adfs_sso_authentications_failure_total` | Total number of failed SSO authentications | counter | None
|
||||
`windows_adfs_sso_authentications_success_total` | Total number of successful SSO authentications | counter | None
|
||||
`windows_adfs_wsfed_token_requests_success_total` | Total number of successful RP tokens issued over WS-Fed protocol | counter | None
|
||||
`windows_adfs_wstrust_token_requests_success_total` | Total number of successful RP tokens issued over WS-Trust protocol | counter | None
|
||||
`windows_adfs_userpassword_authentications_failure_total` | Total number of failed AD U/P authentications | counter | None
|
||||
`windows_adfs_userpassword_authentications_success_total` | Total number of successful AD U/P authentications | counter | None
|
||||
`windows_adfs_external_authentications_failure_total` | Total number of failed authentications from external MFA providers | counter | None
|
||||
`windows_adfs_external_authentications_success_total` | Total number of successful authentications from external MFA providers | counter | None
|
||||
`windows_adfs_db_artifact_failure_total` | Total number of failures connecting to the artifact database | counter | None
|
||||
`windows_adfs_db_artifact_query_time_seconds_total` | Accumulator of time taken for an artifact database query | counter | None
|
||||
`windows_adfs_db_config_failure_total` | Total number of failures connecting to the configuration database | counter | None
|
||||
`windows_adfs_db_config_query_time_seconds_total` | Accumulator of time taken for a configuration database query | counter | None
|
||||
`windows_adfs_federation_metadata_requests_total` | Total number of Federation Metadata requests | counter | None
|
||||
|
||||
### Example metric
|
||||
Show rate of device authentications in AD FS:
|
||||
```
|
||||
rate(windows_adfs_device_authentications)[2m]
|
||||
```
|
||||
|
||||
## Useful queries
|
||||
|
||||
|Query|Description|
|
||||
|---|----|
|
||||
|`rate(windows_adfs_oauth_password_grant_requests_failure_total[5m])`| Rate of OAuth requests failing due to bad client/resource values|
|
||||
|`rate(windows_adfs_userpassword_authentications_failures_total[5m])`| Rate of `/adfs/oauth2/token/` requests failing due to bad username/password values (possible credential spraying)|
|
||||
|
||||
## Alerting examples
|
||||
**prometheus.rules**
|
||||
```yaml
|
||||
- alert: "HighExtranetLockouts"
|
||||
expr: "rate(windows_adfs_extranet_account_lockouts)[2m] > 100"
|
||||
for: "10m"
|
||||
labels:
|
||||
severity: "high"
|
||||
annotations:
|
||||
summary: "High number of AD FS extranet lockouts"
|
||||
description: "High number of AD FS extranet lockouts may indicate a password spray attack.\n Server: {{ $labels.instance }}\n Number of lockouts: {{ $value }}"
|
||||
```
|
||||
# adfs collector
|
||||
|
||||
The adfs collector exposes metrics about Active Directory Federation Services. Note that this collector has only been tested against ADFS 4.0 (2016).
|
||||
Other ADFS versions may work but are not tested.
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `adfs`
|
||||
Data source | Perflib
|
||||
Counters | `AD FS`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`wmi_adfs_ad_login_connection_failures` | Total number of connection failures between the ADFS server and the Active Directory domain controller(s) | counter | None
|
||||
`wmi_adfs_certificate_authentications` | Total number of [User Certificate](https://docs.microsoft.com/en-us/windows-server/identity/ad-fs/operations/configure-user-certificate-authentication) authentications. I.E. smart cards or mobile devices with provisioned client certificates | counter | None
|
||||
`wmi_adfs_device_authentications` | Total number of [device authentications](https://docs.microsoft.com/en-us/windows-server/identity/ad-fs/operations/device-authentication-controls-in-ad-fs) (SignedToken, clientTLS, PkeyAuth). Device authentication is only available on ADFS 2016 or later | counter | None
|
||||
`wmi_adfs_extranet_account_lockouts` | Total number of [extranet lockouts](https://docs.microsoft.com/en-us/windows-server/identity/ad-fs/operations/configure-ad-fs-extranet-smart-lockout-protection). Requires the Extranet Lockout feature to be enabled | counter | None
|
||||
`wmi_adfs_federated_authentications` | Total number of authentications from federated sources. E.G. Office365 | counter | None
|
||||
`wmi_adfs_passport_authentications` | Total number of authentications from [Microsoft Passport](https://en.wikipedia.org/wiki/Microsoft_account) (now named Microsoft Account) | counter | None
|
||||
`wmi_adfs_password_change_failed` | Total number of failed password changes. The Password Change Portal must be enabled in the AD FS Management tool in order to allow user password changes | counter | None
|
||||
`wmi_adfs_password_change_succeeded` | Total number of succeeded password changes. The Password Change Portal must be enabled in the AD FS Management tool in order to allow user password changes | counter | None
|
||||
`wmi_adfs_token_requests` | Total number of requested access tokens | counter | None
|
||||
`wmi_adfs_windows_integrated_authentications` | Total number of Windows integrated authentications using Kerberos or NTLM | counter | None
|
||||
|
||||
### Example metric
|
||||
Show rate of device authentications in AD FS:
|
||||
```
|
||||
rate(wmi_adfs_device_authentications)[2m]
|
||||
```
|
||||
|
||||
## Useful queries
|
||||
|
||||
## Alerting examples
|
||||
**prometheus.rules**
|
||||
```yaml
|
||||
- alert: "HighExtranetLockouts"
|
||||
expr: "rate(wmi_adfs_extranet_account_lockouts)[2m] > 100"
|
||||
for: "10m"
|
||||
labels:
|
||||
severity: "high"
|
||||
annotations:
|
||||
summary: "High number of AD FS extranet lockouts"
|
||||
description: "High number of AD FS extranet lockouts may indicate a password spray attack.\n Server: {{ $labels.instance }}\n Number of lockouts: {{ $value }}"
|
||||
```
|
||||
|
||||
@@ -1,60 +0,0 @@
|
||||
# cache collector
|
||||
|
||||
The cache collector exposes metrics about file system cache
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `cache`
|
||||
Data Source | Perflib
|
||||
Classes | [`Win32_PerfFormattedData_PerfOS_Cache`](https://docs.microsoft.com/en-us/previous-versions/aa394267(v=vs.85))
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_cache_async_copy_reads_total` | Number of times that a filesystem, such as NTFS, maps a page of a file into the file system cache to read a page. | counter | None
|
||||
`windows_cache_async_data_maps_total` | Number of times that a filesystem, such as NTFS, maps a page of a file into the file system cache to read the page, and wishes to wait for the page to be retrieved if it is not in main memory. | counter | None
|
||||
`windows_cache_async_fast_reads_total` | Number of reads from the file system cache that bypass the installed file system and retrieve the data directly from the cache. | counter | None
|
||||
`windows_cache_async_mdl_reads_total` | Number of reads from the file system cache that use a Memory Descriptor List (MDL) to access the pages. | counter | None
|
||||
`windows_cache_async_pin_reads_total` | Number of reads from the file system cache preparatory to writing the data back to disk. Pages read in this fashion are pinned in memory at the completion of the read. | counter | None
|
||||
`windows_cache_copy_read_hits_total` | Number of copy read requests that hit the cache, that is, they did not require a disk read in order to provide access to the page in the cache. | counter | None
|
||||
`windows_cache_copy_reads_total` | Number of reads from pages of the file system cache that involve a memory copy of the data from the cache to the application's buffer. | counter | None
|
||||
`windows_cache_data_flushes_total` | Number of times the file system cache has flushed its contents to disk as the result of a request to flush or to satisfy a write-through file write request. | counter | None
|
||||
`windows_cache_data_flush_pages_total` | Number of pages the file system cache has flushed to disk as a result of a request to flush or to satisfy a write-through file write request. | counter | None
|
||||
`windows_cache_data_map_hits_total` | Number of data maps in the file system cache that could be resolved without having to retrieve a page from the disk, because the page was already in physical memory. | counter | None
|
||||
`windows_cache_data_map_pins_total` | Number of data maps in the file system cache that resulted in pinning a page in main memory, an action usually preparatory to writing to the file on disk. | counter | None
|
||||
`windows_cache_data_maps_total` | Number of times that a file system such as NTFS, maps a page of a file into the file system cache to read the page. | counter | None
|
||||
`windows_cache_dirty_pages` | Number of dirty pages on the system cache. | gauge | None
|
||||
`windows_cache_dirty_page_threshold` | Threshold for number of dirty pages on system cache. | gauge | None
|
||||
`windows_cache_fast_read_not_possibles_total` | Number of attempts by an Application Program Interface (API) function call to bypass the file system to get to data in the file system cache that could not be honored without invoking the file system. | counter | None
|
||||
`windows_cache_fast_read_resource_misses_total` | Number of cache misses necessitated by the lack of available resources to satisfy the request. | counter | None
|
||||
`windows_cache_fast_reads_total` | Number of reads from the file system cache that bypass the installed file system and retrieve the data directly from the cache. | counter | None
|
||||
`windows_cache_lazy_write_flushes_total` | Number of Lazy Write flushes the Lazy Writer thread has written to disk. Lazy Writing is the process of updating the disk after the page has been changed in memory, so that the application that changed the file does not have to wait for the disk write to be complete before proceeding. | counter | None
|
||||
`windows_cache_lazy_write_pages_total` | Number of Lazy Write pages the Lazy Writer thread has written to disk. Lazy Writing is the process of updating the disk after the page has been changed in memory, so that the application that changed the file does not have to wait for the disk write to be complete before proceeding. | counter | None
|
||||
`windows_cache_mdl_read_hits_total` | Number of Memory Descriptor List (MDL) Read requests to the file system cache that hit the cache, i.e., did not require disk accesses in order to provide memory access to the page(s) in the cache. | counter | None
|
||||
`windows_cache_mdl_reads_total` | Number of reads from the file system cache that use a Memory Descriptor List (MDL) to access the data. | counter | None
|
||||
`windows_cache_pin_read_hits_total` | Number of pin read requests that hit the file system cache, i.e., did not require a disk read in order to provide access to the page in the file system cache. While pinned, a page's physical address in the file system cache will not be altered. | counter | None
|
||||
`windows_cache_pin_reads_total` | Number of reads into the file system cache preparatory to writing the data back to disk. Pages read in this fashion are pinned in memory at the completion of the read. While pinned, a page's physical address in the file system cache will not be altered. | counter | None
|
||||
`windows_cache_read_aheads_total` | Number of reads from the file system cache in which the Cache detects sequential access to a file. The read aheads permit the data to be transferred in larger blocks than those being requested by the application, reducing the overhead per access. | counter | None
|
||||
`windows_cache_sync_copy_reads_total` | Number of reads from pages of the file system cache that involve a memory copy of the data from the cache to the application's buffer. The file system will not regain control until the copy operation is complete, even if the disk must be accessed to retrieve the page. | counter | None
|
||||
`windows_cache_sync_data_maps_total` | Number of times that a file system such as NTFS maps a page of a file into the file system cache to read the page. | counter | None
|
||||
`windows_cache_sync_fast_reads_total` | Number of reads from the file system cache that bypass the installed file system and retrieve the data directly from the cache. If the data is not in the cache, the request (application program call) will wait until the data has been retrieved from disk. | counter | None
|
||||
`windows_cache_sync_mdl_reads_total` | Number of reads from the file system cache that use a Memory Descriptor List (MDL) to access the pages. If the accessed page(s) are not in main memory, the caller will wait for the pages to fault in from the disk. | counter | None
|
||||
`windows_cache_sync_pin_reads_total` | Number of reads into the file system cache preparatory to writing the data back to disk. The file system will not regain control until the page is pinned in the file system cache, in particular if the disk must be accessed to retrieve the page. | counter | None
|
||||
|
||||
### Example metric
|
||||
Percentage of copy reads that hit the cache
|
||||
```
|
||||
windows_cache_copy_read_hits_total / windows_cache_copy_reads_total * 100
|
||||
```
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
@@ -1,51 +1,42 @@
|
||||
# container collector
|
||||
|
||||
The container collector exposes metrics about containers running on a Hyper-V system
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `container`
|
||||
Data source | [hcsshim](https://github.com/Microsoft/hcsshim)
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_container_available` | Available | counter | `container_id`
|
||||
`windows_container_count` | Number of containers | gauge | `container_id`
|
||||
`windows_container_cpu_usage_seconds_kernelmode` | Run time in Kernel mode in Seconds | counter | `container_id`
|
||||
`windows_container_cpu_usage_seconds_usermode` | Run Time in User mode in Seconds | counter | `container_id`
|
||||
`windows_container_cpu_usage_seconds_total` | Total Run time in Seconds | counter | `container_id`
|
||||
`windows_container_memory_usage_commit_bytes` | Memory Usage Commit Bytes | gauge | `container_id`
|
||||
`windows_container_memory_usage_commit_peak_bytes` | Memory Usage Commit Peak Bytes | gauge | `container_id`
|
||||
`windows_container_memory_usage_private_working_set_bytes` | Memory Usage Private Working Set Bytes | gauge | `container_id`
|
||||
`windows_container_network_receive_bytes_total` | Bytes Received on Interface | counter | `container_id`, `interface`
|
||||
`windows_container_network_receive_packets_total` | Packets Received on Interface | counter | `container_id`, `interface`
|
||||
`windows_container_network_receive_packets_dropped_total` | Dropped Incoming Packets on Interface | counter | `container_id`, `interface`
|
||||
`windows_container_network_transmit_bytes_total` | Bytes Sent on Interface | counter | `container_id`, `interface`
|
||||
`windows_container_network_transmit_packets_total` | Packets Sent on Interface | counter | `container_id`, `interface`
|
||||
`windows_container_network_transmit_packets_dropped_total` | Dropped Outgoing Packets on Interface | counter | `container_id`, `interface`
|
||||
`windows_container_storage_read_count_normalized_total` | Read Count Normalized | counter | `container_id`
|
||||
`windows_container_storage_read_size_bytes_total` | Read Size Bytes | counter | `container_id`
|
||||
`windows_container_storage_write_count_normalized_total` | Write Count Normalized | counter | `container_id`
|
||||
`windows_container_storage_write_size_bytes_total` | Write Size Bytes | counter | `container_id`
|
||||
|
||||
### Example metric
|
||||
_windows_container_network_receive_bytes_total{container_id="docker://1bd30e8b8ac28cbd76a9b697b4d7bb9d760267b0733d1bc55c60024e98d1e43e",interface="822179E7-002C-4280-ABBA-28BCFE401826"} 9.3305343e+07_
|
||||
|
||||
This metric means that total _9.3305343e+07_ bytes received on interface _822179E7-002C-4280-ABBA-28BCFE401826_ for container _docker://1bd30e8b8ac28cbd76a9b697b4d7bb9d760267b0733d1bc55c60024e98d1e43e_
|
||||
|
||||
## Useful queries
|
||||
Attach labels namespace/pod/container fow windows container metrics.
|
||||
```
|
||||
# kube_pod_container_info(a metric of kube-state-metrics) has labels namespace/pod/container/container_id for a container, while windows container metrics only have container_id.
|
||||
# Attaching labels namespace/pod/container for windows container metrics, is useful to query for windows pods.
|
||||
windows_container_network_receive_bytes_total * on(container_id) group_left(namespace, pod, container) kube_pod_container_info{container_id!=""}
|
||||
```
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
# container collector
|
||||
|
||||
The container collector exposes metrics about containers running on system
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `container`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`wmi_container_available` | Available | counter | `container_id`
|
||||
`wmi_container_count` | Number of containers | gauge | `container_id`
|
||||
`wmi_container_cpu_usage_seconds_kernelmode` | Run time in Kernel mode in Seconds | counter | `container_id`
|
||||
`wmi_container_cpu_usage_seconds_usermode` | Run Time in User mode in Seconds | counter | `container_id`
|
||||
`wmi_container_cpu_usage_seconds_total` | Total Run time in Seconds | counter | `container_id`
|
||||
`wmi_container_memory_usage_commit_bytes` | Memory Usage Commit Bytes | gauge | `container_id`
|
||||
`wmi_container_memory_usage_commit_peak_bytes` | Memory Usage Commit Peak Bytes | gauge | `container_id`
|
||||
`wmi_container_memory_usage_private_working_set_bytes` | Memory Usage Private Working Set Bytes | gauge | `container_id`
|
||||
`wmi_container_network_receive_bytes_total` | Bytes Received on Interface | counter | `container_id`, `interface`
|
||||
`wmi_container_network_receive_packets_total` | Packets Received on Interface | counter | `container_id`, `interface`
|
||||
`wmi_container_network_receive_packets_dropped_total` | Dropped Incoming Packets on Interface | counter | `container_id`, `interface`
|
||||
`wmi_container_network_transmit_bytes_total` | Bytes Sent on Interface | counter | `container_id`, `interface`
|
||||
`wmi_container_network_transmit_packets_total` | Packets Sent on Interface | counter | `container_id`, `interface`
|
||||
`wmi_container_network_transmit_packets_dropped_total` | Dropped Outgoing Packets on Interface | counter | `container_id`, `interface`
|
||||
|
||||
### Example metric
|
||||
_wmi_container_network_receive_bytes_total{container_id="docker://1bd30e8b8ac28cbd76a9b697b4d7bb9d760267b0733d1bc55c60024e98d1e43e",interface="822179E7-002C-4280-ABBA-28BCFE401826"} 9.3305343e+07_
|
||||
|
||||
This metric means that total _9.3305343e+07_ bytes received on interface _822179E7-002C-4280-ABBA-28BCFE401826_ for container _docker://1bd30e8b8ac28cbd76a9b697b4d7bb9d760267b0733d1bc55c60024e98d1e43e_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
|
||||
@@ -18,74 +18,43 @@ These metrics are available on all versions of Windows:
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_cpu_cstate_seconds_total` | Time spent in low-power idle states | counter | `core`, `state`
|
||||
`windows_cpu_time_total` | Time that processor spent in different modes (dpc, idle, interrupt, privileged, user) | counter | `core`, `mode`
|
||||
`windows_cpu_interrupts_total` | Total number of received and serviced hardware interrupts | counter | `core`
|
||||
`windows_cpu_dpcs_total` | Total number of received and serviced deferred procedure calls (DPCs) | counter | `core`
|
||||
`wmi_cpu_cstate_seconds_total` | Time spent in low-power idle states | counter | `core`, `state`
|
||||
`wmi_cpu_time_total` | Time that processor spent in different modes (idle, user, system, ...) | counter | `core`, `mode`
|
||||
`wmi_cpu_interrupts_total` | Total number of received and serviced hardware interrupts | counter | `core`
|
||||
`wmi_cpu_dpcs_total` | Total number of received and serviced deferred procedure calls (DPCs) | counter | `core`
|
||||
|
||||
These metrics are only exposed on Windows Server 2008R2 and later:
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_cpu_clock_interrupts_total` | Total number of received and serviced clock tick interrupts | counter | `core`
|
||||
`windows_cpu_idle_break_events_total` | Total number of time processor was woken from idle | counter | `core`
|
||||
`windows_cpu_parking_status` | Parking Status represents whether a processor is parked or not | gauge | `core`
|
||||
`windows_cpu_core_frequency_mhz` | Core frequency in megahertz | gauge | `core`
|
||||
`windows_cpu_processor_performance_total` | Processor Performance is the number of CPU cycles executing instructions by each core; it is believed to be similar to the value that the APERF MSR would show, were it exposed | counter | `core`
|
||||
`windows_cpu_processor_mperf_total` | Processor MPerf Total is proportioanl to the number of TSC ticks each core has accumulated while executing instructions. Due to the manner in which it is presented, it should be scaled by 1e2 to properly line up with Processor Performance Total. As above, it is believed to be closely related to the MPERF MSR. | counter | `core`
|
||||
`windows_cpu_processor_rtc_total` | RTC total is assumed to represent the 64Hz tick rate in Windows. It is not by itself useful, but can be used with `windows_cpu_processor_utility_total` to more accurately measure CPU utilisation than with `windows_cpu_time_total` | counter | `core`
|
||||
`windows_cpu_processor_utility_total` | Processor Utility Total is a newer, more accurate measure of CPU utilization, in particular handling modern CPUs with variant CPU frequencies. The rate of this counter divided by the rate of `windows_cpu_processor_rtc_total` should provide an accurate view of CPU utilisation on modern systems, as observed in Task Manager. | counter | `core`
|
||||
`windows_cpu_processor_privileged_utility_total` | Processor Privileged Utility Total, when used in a similar fashion to `windows_cpu_processor_utility_total` will show the portion of CPU utilization which is happening in privileged mode. | counter | `core`
|
||||
`wmi_cpu_clock_interrupts_total` | Total number of received and serviced clock tick interrupts | `core`
|
||||
`wmi_cpu_idle_break_events_total` | Total number of time processor was woken from idle | `core`
|
||||
`wmi_cpu_parking_status` | Parking Status represents whether a processor is parked or not | `gauge`
|
||||
`wmi_cpu_core_frequency_mhz` | Core frequency in megahertz | `gauge`
|
||||
`wmi_cpu_processor_performance` | Processor Performance is the average performance of the processor while it is executing instructions, as a percentage of the nominal performance of the processor. On some processors, Processor Performance may exceed 100% | `gauge`
|
||||
|
||||
### Example metric
|
||||
Show frequency of host CPU cores
|
||||
```
|
||||
windows_cpu_core_frequency_mhz{instance="localhost"}
|
||||
wmi_cpu_core_frequency_mhz{instance="localhost"}
|
||||
```
|
||||
|
||||
## Useful queries
|
||||
Show cpu usage by mode.
|
||||
```
|
||||
sum by (mode) (irate(windows_cpu_time_total{instance="localhost"}[5m]))
|
||||
sum by (mode) (irate(wmi_cpu_time_total{instance="localhost"}[5m]))
|
||||
```
|
||||
Show per-cpu utilisation using the processor utility metrics
|
||||
```
|
||||
rate(windows_cpu_processor_utility_total{instance="localhost"}[5m]) / rate(windows_cpu_processor_rtc_total{instance="localhost"}[5m])
|
||||
```
|
||||
Show actual average CPU frequency in Hz
|
||||
```
|
||||
avg by(instance) (
|
||||
1e4 * windows_cpu_core_frequency_mhz{}
|
||||
* rate(windows_cpu_processor_performance_total{}[5m])
|
||||
/ rate(windows_cpu_processor_mperf_total{}[5m])
|
||||
)
|
||||
```
|
||||
|
||||
|
||||
## Alerting examples
|
||||
**prometheus.rules**
|
||||
```yaml
|
||||
# Alert on hosts with more than 80% CPU usage over a 10 minute period
|
||||
- alert: CpuUsage
|
||||
expr: 100 - (avg by (instance) (irate(windows_cpu_time_total{mode="idle"}[2m])) * 100) > 80
|
||||
expr: 100 - (avg by (instance) (irate(wmi_cpu_time_total{mode="idle"}[2m])) * 100) > 80
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "CPU Usage (instance {{ $labels.instance }})"
|
||||
description: "CPU Usage is more than 80%\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
# Alert on hosts which are not boosting their CPU frequencies
|
||||
- alert: NoCpuTurbo
|
||||
expr: |
|
||||
avg by(instance) (
|
||||
1e4 * windows_cpu_core_frequency_mhz{}
|
||||
* rate(windows_cpu_processor_performance_total{}[5m])
|
||||
/ rate(windows_cpu_processor_mperf_total{}[5m])
|
||||
)
|
||||
/
|
||||
(1e6 * avg by (instance) (windows_cpu_core_frequency_mhz))
|
||||
< 1.1
|
||||
for: 1h
|
||||
annotations:
|
||||
summary: "CPU Frequency on {{ $labels.instance }} is less than 110% of base frequency, suggesting it is not able to boost.
|
||||
```
|
||||
|
||||
@@ -1,32 +0,0 @@
|
||||
# cpu_info collector
|
||||
|
||||
The cpu_info collector exposes metrics detailing a per-socket breakdown of the Processors in the system
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `cpu_info`
|
||||
Data source | wmi
|
||||
Classes | [`Win32_Processor`](https://docs.microsoft.com/en-us/windows/win32/cimwin32prov/win32-processor)
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_cpu_info` | Labelled CPU information | gauge | `architecture`, `device_id`, `description`, `family`, `l2_cache_size` `l3_cache_size`, `name`
|
||||
|
||||
### Example metric
|
||||
```
|
||||
windows_cpu_info{architecture="9",description="AMD64 Family 23 Model 49 Stepping 0",device_id="CPU0",family="107",l2_cache_size="32768",l3_cache_size="262144",name="AMD EPYC 7702P 64-Core Processor"} 1
|
||||
```
|
||||
The value of the metric is irrelevant, but the labels expose some useful information on the CPU installed in each socket.
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
@@ -1,30 +1,30 @@
|
||||
# cs collector
|
||||
|
||||
The cs collector exposes metrics detailing the hardware of the computer system
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `cs`
|
||||
Classes | [`Win32_ComputerSystem`](https://msdn.microsoft.com/en-us/library/aa394102)
|
||||
Enabled by default? | Yes
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_cs_logical_processors` | Number of installed logical processors | gauge | None
|
||||
`windows_cs_physical_memory_bytes` | Total installed physical memory | gauge | None
|
||||
`windows_cs_hostname` | Labelled system hostname information | gauge | `hostname`, `domain`, `fqdn`
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
# cs collector
|
||||
|
||||
The cs collector exposes metrics detailing the hardware of the computer system
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `cs`
|
||||
Classes | [`Win32_ComputerSystem`](https://msdn.microsoft.com/en-us/library/aa394102)
|
||||
Enabled by default? | Yes
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`wmi_cs_logical_processors` | Number of installed logical processors | gauge | None
|
||||
`wmi_cs_physical_memory_bytes` | Total installed physical memory | gauge | None
|
||||
`wmi_cs_hostname` | Labeled system hostname information | gauge | `hostname`, `domain`, `fqdn`
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
|
||||
@@ -1,75 +0,0 @@
|
||||
# dfsr collector
|
||||
|
||||
The dfsr collector exposes metrics for [DFSR](https://docs.microsoft.com/en-us/windows-server/storage/dfs-replication/dfsr-overview).
|
||||
|
||||
**Collector is currently in an experimental state and testing of metrics has not been undertaken.** Feedback on this collector is welcome.
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `dfsr`
|
||||
Data source | Perflib
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
### `--collectors.dfsr.sources-enabled`
|
||||
|
||||
Comma-separated list of DFSR Perflib sources to use. Supported values are `connection`, `folder` and `volume`.
|
||||
All sources are enabled by default
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_dfsr_collector_duration_seconds` | The time taken for each sub-collector to return | gauge | collector
|
||||
`windows_dfsr_collector_success` | 1 if sub-collector succeeded, 0 otherwise | gauge | collector
|
||||
`windows_dfsr_connection_bandwidth_savings_using_dfs_replication_bytes_total` | Total bandwidth (in bytes) saved by the DFS Replication service for this connection, using a combination of remote differential compression (RDC) and other compression technologies that minimize network bandwidth use. | counter | name
|
||||
`windows_dfsr_connection_bytes_received_total` | Total bytes received for connection | counter | name
|
||||
`windows_dfsr_connection_compressed_size_of_files_received_bytes_total` | Total compressed size of files received on the connection, in bytes | counter | name
|
||||
`windows_dfsr_connection_received_files_total` | Total number of files received for connection | counter | name
|
||||
`windows_dfsr_connection_rdc_received_bytes_total` | Total bytes received on the connection while replicating files using Remote Differential Compression. This is the actual bytes received over the network without the networking protocol overhead | counter | name
|
||||
`windows_dfsr_connection_rdc_compressed_size_of_received_files_bytes_total` | Total compressed size of files received with Remote Differential Compression. This is the number of bytes that would have been received had RDC not been used. This is not the actual number of bytes received over the network. | counter | name
|
||||
`windows_dfsr_connection_rdc_received_files_total` | Total number of files received using remote differential compression | counter | name
|
||||
`windows_dfsr_connection_rdc_size_of_files_received_total` | Total uncompressed size of files received with remote differential compression, in bytes. This is the number of bytes that would have been received had neither compression nor RDC been used. This is not the actual number of bytes received over the network. | counter | name
|
||||
`windows_dfsr_connection_size_of_files_received_total` | Total uncompressed size of files received on the connection, in bytes. This is the number of bytes that would have been received had DFS Replication compression not been used. | counter | name
|
||||
`windows_dfsr_folder_bandwidth_savings_using_dfs_replication_bytes_total` | Total bandwidth (in bytes) saved by the DFS Replication service for this folder, using a combination of remote differential compression (RDC) and other compression technologies that minimize network bandwidth use. | counter | name
|
||||
`windows_dfsr_folder_compressed_size_of_received_files_bytes_total` | Total compressed size of files received for this folder, in bytes | counter | name
|
||||
`windows_dfsr_folder_conflict_cleaned_up_bytes_total` | Total size of conflict loser files and folders deleted from the Conflict and Deleted folder, in bytes. | counter | name
|
||||
`windows_dfsr_folder_conflict_generated_bytes_total` | Total size of conflict loser files and folders moved to the Conflict and Deleted folder, in bytes. | counter | name
|
||||
`windows_dfsr_folder_conflict_cleaned_up_files_total` | Number of conflict loser files deleted from the Conflict and Deleted folder. | counter | name
|
||||
`windows_dfsr_folder_conflict_generated_files_total` | Number of files and folders moved to the Conflict and Deleted folder | counter | name
|
||||
`windows_dfsr_folder_conflict_folder_cleanups_total` | Number of deletions of conflict loser files and folders in the Conflict and Deleted | counter | name
|
||||
`windows_dfsr_folder_conflict_space_in_use` | Total size of the conflict loser files and folders currently in the Conflict and Deleted folder | gauge | name
|
||||
`windows_dfsr_folder_deleted_space_in_use` | Total size (in bytes) of the deleted files and folders currently in the Conflict and Deleted folder. | gauge | name
|
||||
`windows_dfsr_folder_deleted_bytes_cleaned_up_total` | Total size (in bytes) of replicating deleted files and folders that were cleaned up from the Conflict and Deleted folder. | gauge | name
|
||||
`windows_dfsr_folder_deleted_bytes_generated_total` | Total size (in bytes) of replicated deleted files and folders that were moved to the Conflict and Deleted folder after they were deleted from a replicated folder on a sending member. | counter | name
|
||||
`windows_dfsr_folder_deleted_files_cleaned_up_total` | Number of files and folders that were cleaned up from the Conflict and Deleted folder. | counter | name
|
||||
`windows_dfsr_folder_deleted_files_generated_total` | Number of deleted files and folders that were moved to the Conflict and Deleted folder. | counter | name
|
||||
`windows_dfsr_folder_file_installs_retried_total` | Total number of file installs that are being retried due to sharing violations or other errors encountered when installing the files. The DFS Replication service replicates staged files into a staging folder, uncompresses them in the Installing folder, and renames them to the target location. The second and third steps of this process are known as installing the file. | counter | name
|
||||
`windows_dfsr_folder_file_installs_succeeded_total` | Total number of files that were successfully received from sending members and installed locally on this server. The DFS Replication service replicates staged files into a staging folder, uncompresses them in the Installing folder, and renames them to the target location. The second and third steps of this process are known as installing the file. | counter | name
|
||||
`windows_dfsr_folder_files_received_total` | Total number of files received. | counter | name
|
||||
`windows_dfsr_folder_rdc_bytes_received_total` | Total number of bytes received in replicating files using Remote Differential Compression. This is the actual bytes received over the network without the networking protocol overhead. | counter | name
|
||||
`windows_dfsr_folder_rdc_compressed_size_of_files_received_total` | Total compressed size (in bytes) of the files received with Remote Differential Compression. This is the number of bytes that would have been received had RDC not been used. This is not the actual bytes received over the network. | counter | name
|
||||
`windows_dfsr_folder_rdc_number_of_files_received_total` | Total number of files received with Remote Differential Compression. | counter | name
|
||||
`windows_dfsr_folder_rdc_size_of_files_received_total` | Total uncompressed size (in bytes) of the files received with Remote Differential Compression. This is the number of bytes that would have been received had neither compression nor RDC been used. This is not the actual bytes received over the network. | counter | name
|
||||
`windows_dfsr_folder_size_of_files_received_total` | Total uncompressed size (in bytes) of the files received. | counter | name
|
||||
`windows_dfsr_folder_staging_space_in_use` | Total size of files and folders currently in the staging folder. This metric will fluctuate as staging space is reclaimed. | gauge | name
|
||||
`windows_dfsr_folder_staging_bytes_cleaned_up_total` | Total size (in bytes) of the files and folders that have been cleaned up from the staging folder. | counter | name
|
||||
`windows_dfsr_folder_staging_bytes_generated_total` | Total size (in bytes) of replicated files and folders in the staging folder created by the DFS Replication service since last restart. | counter | name
|
||||
`windows_dfsr_folder_staging_files_cleaned_up_total` | Total number of files and folders that have been cleaned up from the staging folder. | counter | name
|
||||
`windows_dfsr_folder_staging_files_generated_total` | Total number of times replicated files and folders have been staged by the DFS Replication service. | counter | name
|
||||
`windows_dfsr_folder_updates_dropped_total` | Total number of redundant file replication update records that have been ignored by the DFS Replication service because they did not change the replicated file or folder. | counter | name
|
||||
`windows_dfsr_volume_database_commits_total` | Total number of DFSR Volume database commits. | counter | name
|
||||
`windows_dfsr_volume_database_lookups_total` | Total number of DFSR Volume database lookups. | counter | name
|
||||
`windows_dfsr_volume_usn_journal_unread_percentage` | Percentage of DFSR Volume USN journal records that are unread. | gauge | name
|
||||
`windows_dfsr_volume_usn_journal_accepted_records_total` | Total number of USN journal records accepted. | counter | name
|
||||
`windows_dfsr_volume_usn_journal_read_records_total` | Total number of DFSR Volume USN journal records read. | counter | name
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
@@ -1,53 +0,0 @@
|
||||
# dhcp collector
|
||||
|
||||
The dhcp collector exposes DHCP Server metrics
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `dhcp`
|
||||
Data source | Perflib
|
||||
Classes | `DHCP Server`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`packets_received_total` | Total number of packets received by the DHCP server | counter | None
|
||||
`duplicates_dropped_total` | Total number of duplicate packets received by the DHCP server | counter | None
|
||||
`packets_expired_total` | Total number of packets expired in the DHCP server message queue | counter | None
|
||||
`active_queue_length` | Number of packets in the processing queue of the DHCP server | gauge | None
|
||||
`conflict_check_queue_length` | Number of packets in the DHCP server queue waiting on conflict detection (ping) | gauge | None
|
||||
`discovers_total` | Total DHCP Discovers received by the DHCP server | counter | None
|
||||
`offers_total` | Total DHCP Offers sent by the DHCP server | counter | None
|
||||
`requests_total` | Total DHCP Requests received by the DHCP server | counter | None
|
||||
`informs_total` | Total DHCP Informs received by the DHCP server | counter | None
|
||||
`acks_total` | Total DHCP Acks sent by the DHCP server | counter | None
|
||||
`nacks_total` | Total DHCP Nacks sent by the DHCP server | counter | None
|
||||
`declines_total` | Total DHCP Declines received by the DHCP server | counter | None
|
||||
`releases_total` | Total DHCP Releases received by the DHCP server | counter | None
|
||||
`offer_queue_length` | Number of packets in the offer queue of the DHCP server | gauge | None
|
||||
`denied_due_to_match_total` | Total number of DHCP requests denied, based on matches from the Deny List | gauge | None
|
||||
`denied_due_to_nonmatch_total` | Total number of DHCP requests denied, based on non-matches from the Allow List | gauge | None
|
||||
`failover_bndupd_sent_total` | Number of DHCP failover Binding Update messages sent | counter | None
|
||||
`failover_bndupd_received_total` | Number of DHCP failover Binding Update messages received | counter | None
|
||||
`failover_bndack_sent_total` | Number of DHCP failover Binding Ack messages sent | counter | None
|
||||
`failover_bndack_received_total` | Number of DHCP failover Binding Ack messages received | counter | None
|
||||
`failover_bndupd_pending_in_outbound_queue` | Number of pending outbound DHCP failover Binding Update messages | counter | None
|
||||
`failover_transitions_communicationinterrupted_state_total` | Total number of transitions into COMMUNICATION INTERRUPTED state | counter | None
|
||||
`failover_transitions_partnerdown_state_total` | Total number of transitions into PARTNER DOWN state | counter | None
|
||||
`failover_transitions_recover_total` | Total number of transitions into RECOVER state | counter | None
|
||||
`failover_bndupd_dropped_total` | Total number of DHCP faileover Binding Updates dropped | counter | None
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
@@ -1,40 +0,0 @@
|
||||
# diskdrive collector
|
||||
|
||||
The diskdrive collector exposes metrics about physical disks
|
||||
|
||||
| | |
|
||||
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| Metric name prefix | `diskdrive` |
|
||||
| Classes | [`Win32_DiskDrive`](https://learn.microsoft.com/en-us/windows/win32/cimwin32prov/win32-diskdrive) |
|
||||
| Enabled by default? | No |
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
| Name | Description | Type | Labels |
|
||||
| ------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- | ------ |
|
||||
| `diskdrive_info` | General identifiable information about the disk drive | gauge | name,caption,device_id,model |
|
||||
| `diskdrive_availability` | The disk drive's current availability | gauge | name,availability |
|
||||
| `diskdrive_partitions` | Number of partitions on the drive | gauge | name |
|
||||
| `diskdrive_size` | Size of the disk drive. It is calculated by multiplying the total number of cylinders, tracks in each cylinder, sectors in each track, and bytes in each sector. | gauge | name |
|
||||
| `diskdrive_status` | Operational status of the drive | gauge | name,status |
|
||||
|
||||
## Alerting examples
|
||||
**prometheus.rules**
|
||||
```yaml
|
||||
groups:
|
||||
- name: Windows Disk Alerts
|
||||
rules:
|
||||
|
||||
- alert: Drive_Status
|
||||
expr: windows_disk_drive_status{status="OK"} != 1
|
||||
for: 10m
|
||||
labels:
|
||||
severity: high
|
||||
annotations:
|
||||
summary: "Instance: {{ $labels.instance }} has drive status: {{ $labels.status }} on disk {{ $labels.name }}"
|
||||
description: "Drive Status Unhealthy"
|
||||
```
|
||||
@@ -1,49 +1,49 @@
|
||||
# dns collector
|
||||
|
||||
The dns collector exposes metrics about the DNS server
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `dns`
|
||||
Classes | [`Win32_PerfRawData_DNS_DNS`](https://technet.microsoft.com/en-us/library/cc977686.aspx)
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_dns_zone_transfer_requests_received_total` | _Not yet documented_ | counter | `qtype`
|
||||
`windows_dns_zone_transfer_requests_sent_total` | _Not yet documented_ | counter | `qtype`
|
||||
`windows_dns_zone_transfer_response_received_total` | _Not yet documented_ | counter | `qtype`
|
||||
`windows_dns_zone_transfer_success_received_total` | _Not yet documented_ | counter | `qtype`, `protocol`
|
||||
`windows_dns_zone_transfer_success_sent_total` | _Not yet documented_ | counter | `qtype`
|
||||
`windows_dns_zone_transfer_failures_total` | _Not yet documented_ | counter | None
|
||||
`windows_dns_memory_used_bytes_total` | _Not yet documented_ | gauge | `area`
|
||||
`windows_dns_dynamic_updates_queued` | _Not yet documented_ | gauge | None
|
||||
`windows_dns_dynamic_updates_received_total` | _Not yet documented_ | counter | `operation`
|
||||
`windows_dns_dynamic_updates_failures_total` | _Not yet documented_ | counter | `reason`
|
||||
`windows_dns_notify_received_total` | _Not yet documented_ | counter | None
|
||||
`windows_dns_notify_sent_total` | _Not yet documented_ | counter | None
|
||||
`windows_dns_secure_update_failures_total` | _Not yet documented_ | counter | None
|
||||
`windows_dns_secure_update_received_total` | _Not yet documented_ | counter | None
|
||||
`windows_dns_queries_total` | _Not yet documented_ | counter | `protocol`
|
||||
`windows_dns_responses_total` | _Not yet documented_ | counter | `protocol`
|
||||
`windows_dns_recursive_queries_total` | _Not yet documented_ | counter | None
|
||||
`windows_dns_recursive_query_failures_total` | _Not yet documented_ | counter | None
|
||||
`windows_dns_recursive_query_send_timeouts_total` | _Not yet documented_ | counter | None
|
||||
`windows_dns_wins_queries_total` | _Not yet documented_ | counter | `direction`
|
||||
`windows_dns_wins_responses_total` | _Not yet documented_ | counter | `direction`
|
||||
`windows_dns_unmatched_responses_total` | _Not yet documented_ | counter | None
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
# dns collector
|
||||
|
||||
The dns collector exposes metrics about the DNS server
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `dns`
|
||||
Classes | [`Win32_PerfRawData_DNS_DNS`](https://technet.microsoft.com/en-us/library/cc977686.aspx)
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`wmi_dns_zone_transfer_requests_received_total` | _Not yet documented_ | counter | `qtype`
|
||||
`wmi_dns_zone_transfer_requests_sent_total` | _Not yet documented_ | counter | `qtype`
|
||||
`wmi_dns_zone_transfer_response_received_total` | _Not yet documented_ | counter | `qtype`
|
||||
`wmi_dns_zone_transfer_success_received_total` | _Not yet documented_ | counter | `qtype`, `protocol`
|
||||
`wmi_dns_zone_transfer_success_sent_total` | _Not yet documented_ | counter | `qtype`
|
||||
`wmi_dns_zone_transfer_failures_total` | _Not yet documented_ | counter | None
|
||||
`wmi_dns_memory_used_bytes_total` | _Not yet documented_ | gauge | `area`
|
||||
`wmi_dns_dynamic_updates_queued` | _Not yet documented_ | gauge | None
|
||||
`wmi_dns_dynamic_updates_received_total` | _Not yet documented_ | counter | `operation`
|
||||
`wmi_dns_dynamic_updates_failures_total` | _Not yet documented_ | counter | `reason`
|
||||
`wmi_dns_notify_received_total` | _Not yet documented_ | counter | None
|
||||
`wmi_dns_notify_sent_total` | _Not yet documented_ | counter | None
|
||||
`wmi_dns_secure_update_failures_total` | _Not yet documented_ | counter | None
|
||||
`wmi_dns_secure_update_received_total` | _Not yet documented_ | counter | None
|
||||
`wmi_dns_queries_total` | _Not yet documented_ | counter | `protocol`
|
||||
`wmi_dns_responses_total` | _Not yet documented_ | counter | `protocol`
|
||||
`wmi_dns_recursive_queries_total` | _Not yet documented_ | counter | None
|
||||
`wmi_dns_recursive_query_failures_total` | _Not yet documented_ | counter | None
|
||||
`wmi_dns_recursive_query_send_timeouts_total` | _Not yet documented_ | counter | None
|
||||
`wmi_dns_wins_queries_total` | _Not yet documented_ | counter | `direction`
|
||||
`wmi_dns_wins_responses_total` | _Not yet documented_ | counter | `direction`
|
||||
`wmi_dns_unmatched_responses_total` | _Not yet documented_ | counter | None
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
|
||||
@@ -1,70 +0,0 @@
|
||||
# exchange collector
|
||||
|
||||
The exchange collector collects metrics from MS Exchange hosts through perflib
|
||||
=======
|
||||
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `exchange`
|
||||
Classes | [Win32_PerfRawData_MSExchangeADAccess_MSExchangeADAccessProcesses](https://docs.microsoft.com/en-us/exchange/)<br/> [Win32_PerfRawData_MSExchangeTransportQueues_MSExchangeTransportQueues](https://docs.microsoft.com/en-us/exchange/)<br/> [Win32_PerfRawData_ESE_MSExchangeDatabaseInstances](https://docs.microsoft.com/en-us/exchange/)<br/> [Win32_PerfRawData_MSExchangeHttpProxy_MSExchangeHttpProxy](https://docs.microsoft.com/en-us/exchange/)<br/> [Win32_PerfRawData_MSExchangeActiveSync_MSExchangeActiveSync](https://docs.microsoft.com/en-us/exchange/)<br/> [Win32_PerfRawData_MSExchangeAvailabilityService_MSExchangeAvailabilityService](https://docs.microsoft.com/en-us/exchange/)<br/> [Win32_PerfRawData_MSExchangeOWA_MSExchangeOWA](https://docs.microsoft.com/en-us/exchange/)<br/> [Win32_PerfRawData_MSExchangeAutodiscover_MSExchangeAutodiscover](https://docs.microsoft.com/en-us/exchange/)<br/> [Win32_PerfRawData_MSExchangeWorkloadManagementWorkloads_MSExchangeWorkloadManagementWorkloads](https://docs.microsoft.com/en-us/exchange/)<br/> [Win32_PerfRawData_MSExchangeRpcClientAccess_MSExchangeRpcClientAccess](https://docs.microsoft.com/en-us/exchange/)<br/>
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
### `--collectors.exchange.list`
|
||||
Lists the Perflib Objects that are queried for data along with the perlfib object id
|
||||
|
||||
### `--collectors.exchange.enabled`
|
||||
Comma-separated list of collectors to use, for example: `--collectors.exchange.enabled=AvailabilityService,OutlookWebAccess`. Matching is case-sensitive. Depending on the exchange installation not all performance counters are available. Use `--collectors.exchange.list` to obtain a list of supported collectors.
|
||||
|
||||
## Metrics
|
||||
Name | Description
|
||||
--------------|---------------
|
||||
`windows_exchange_rpc_avg_latency_sec` | The latency (sec), averaged for the past 1024 packets
|
||||
`windows_exchange_rpc_requests` | Number of client requests currently being processed by the RPC Client Access service
|
||||
`windows_exchange_rpc_active_user_count` | Number of unique users that have shown some kind of activity in the last 2 minutes
|
||||
`windows_exchange_rpc_connection_count` | Total number of client connections maintained
|
||||
`windows_exchange_rpc_operations_total` | The rate at which RPC operations occur
|
||||
`windows_exchange_rpc_user_count` | Number of users
|
||||
`windows_exchange_ldap_read_time_sec` | Time (sec) to send an LDAP read request and receive a response
|
||||
`windows_exchange_ldap_search_time_sec` | Time (sec) to send an LDAP search request and receive a response
|
||||
`windows_exchange_ldap_write_time_sec` | Time (sec) to send an LDAP Add/Modify/Delete request and receive a response
|
||||
`windows_exchange_ldap_timeout_errors_total` | Total number of LDAP timeout errors
|
||||
`windows_exchange_ldap_long_running_ops_per_sec` | Long Running LDAP operations per second
|
||||
`windows_exchange_transport_queues_external_active_remote_delivery` | External Active Remote Delivery Queue length
|
||||
`windows_exchange_transport_queues_internal_active_remote_delivery` | Internal Active Remote Delivery Queue length
|
||||
`windows_exchange_transport_queues_active_mailbox_delivery` | Active Mailbox Delivery Queue length
|
||||
`windows_exchange_transport_queues_retry_mailbox_delivery` | Retry Mailbox Delivery Queue length
|
||||
`windows_exchange_transport_queues_unreachable` | Unreachable Queue length
|
||||
`windows_exchange_transport_queues_external_largest_delivery` | External Largest Delivery Queue length
|
||||
`windows_exchange_transport_queues_internal_largest_delivery` | Internal Largest Delivery Queue length
|
||||
`windows_exchange_transport_queues_poison` | Poison Queue length
|
||||
`windows_exchange_http_proxy_mailbox_server_locator_avg_latency_sec` | Average latency (sec) of MailboxServerLocator web service calls
|
||||
`windows_exchange_http_proxy_avg_auth_latency` | Average time spent authenticating CAS requests over the last 200 samples
|
||||
`windows_exchange_http_proxy_outstanding_proxy_requests` | Number of concurrent outstanding proxy requests
|
||||
`windows_exchange_http_proxy_requests_total` | Number of proxy requests processed each second
|
||||
`windows_exchange_avail_service_requests_per_sec` | Number of requests serviced per second
|
||||
`windows_exchange_owa_current_unique_users` | Number of unique users currently logged on to Outlook Web App
|
||||
`windows_exchange_owa_requests_total` | Number of requests handled by Outlook Web App per second
|
||||
`windows_exchange_autodiscover_requests_total` | Number of autodiscover service requests processed each second
|
||||
`windows_exchange_workload_active_tasks` | Number of active tasks currently running in the background for workload management
|
||||
`windows_exchange_workload_completed_tasks` | Number of workload management tasks that have been completed
|
||||
`windows_exchange_workload_queued_tasks` | Number of workload management tasks that are currently queued up waiting to be processed
|
||||
`windows_exchange_workload_yielded_tasks` | The total number of tasks that have been yielded by a workload
|
||||
`windows_exchange_workload_is_active` | Active indicates whether the workload is in an active (1) or paused (0) state
|
||||
`windows_exchange_activesync_requests_total` | Num HTTP requests received from the client via ASP.NET per sec. Shows Current user load
|
||||
`windows_exchange_http_proxy_avg_cas_proccessing_latency_sec` | Average latency (sec) of CAS processing time over the last 200 reqs
|
||||
`windows_exchange_http_proxy_mailbox_proxy_failure_rate` | % of failures between this CAS and MBX servers over the last 200 sample
|
||||
`windows_exchange_activesync_ping_cmds_pending` | Number of ping commands currently pending in the queue
|
||||
`windows_exchange_activesync_sync_cmds_total` | Number of sync commands processed per second. Clients use this command to synchronize items within a folder
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
|
||||
@@ -1,51 +0,0 @@
|
||||
# Microsoft File Server Resource Manager (FSRM) Quotas collector
|
||||
|
||||
The fsrmquota collector exposes metrics about File Server Resource Manager Quotas. Note that this collector has only been tested against Windows server 2012R2.
|
||||
Other FSRM versions may work but are not tested.
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `fsrmquota`
|
||||
Data source | wmi
|
||||
Counters | `FSRMQUOTA`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_fsrmquota_count` | Number of Quotas | counter |None
|
||||
`windows_fsrmquota_description` | A string up to 1KB in size. Optional. The default value is an empty string. (Description) | counter |`path`, `template`,`description`
|
||||
`windows_fsrmquota_disabled` | If 1, the quota is disabled. The default value is 0. (Disabled) | counter |`path`, `template`
|
||||
`windows_fsrmquota_matchestemplate` | If 1, the property values of this quota match those values of the template from which it was derived. (MatchesTemplate) | counter |`path`, `template`
|
||||
`windows_fsrmquota_peak_usage_bytes ` | The highest amount of disk space usage charged to this quota. (PeakUsage) | counter |`path`, `template`
|
||||
`windows_fsrmquota_size_bytes` | The size of the quota. If the Template property is not provided then the Size property must be provided (Size) | counter |`path`, `template`
|
||||
`windows_fsrmquota_softlimit` | If 1, the quota is a soft limit. If 0, the quota is a hard limit. The default value is 0. Optional (SoftLimit) | counter |`path`, `template`
|
||||
`windows_fsrmquota_template` | A valid quota template name. Up to 1KB in size. Optional (Template) | counter |`path`, `template`
|
||||
`windows_fsrmquota_usage_bytes` | The current amount of disk space usage charged to this quota. (Usage) | counter |`path`, `template`
|
||||
|
||||
|
||||
### Example metric
|
||||
Show rate of Quotas usage:
|
||||
```
|
||||
rate(windows_fsrmquota_usage_bytes)[1d]
|
||||
```
|
||||
|
||||
## Useful queries
|
||||
|
||||
## Alerting examples
|
||||
**prometheus.rules**
|
||||
```yaml
|
||||
- alert: "HighQuotasUsage"
|
||||
expr: "windows_fsrmquota_usage_bytes{instance="SERVER1.COM:9182"} / windows_fsrmquota_size{instance="SERVER1.COM:9182"} >0.85"
|
||||
for: "10m"
|
||||
labels:
|
||||
severity: "high"
|
||||
annotations:
|
||||
summary: "High Quotas Usage"
|
||||
description: "High use of File Resource.\n Quotas: {{ $labels.path }}\n Current use : {{ $value }}"
|
||||
```
|
||||
@@ -1,132 +1,102 @@
|
||||
# hyperv collector
|
||||
|
||||
The hyperv collector exposes metrics about the Hyper-V hypervisor
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `hyperv`
|
||||
Classes | `Win32_PerfRawData_VmmsVirtualMachineStats_HyperVVirtualMachineHealthSummary`<br/>`Win32_PerfRawData_VidPerfProvider_HyperVVMVidPartition`<br/>`Win32_PerfRawData_HvStats_HyperVHypervisorRootPartition`<br/>`Win32_PerfRawData_HvStats_HyperVHypervisor`<br/>`Win32_PerfRawData_HvStats_HyperVHypervisorLogicalProcessor`<br/>`Win32_PerfRawData_HvStats_HyperVHypervisorRootVirtualProcessor`<br/>`Win32_PerfRawData_HvStats_HyperVHypervisorVirtualProcessor`<br/>`Win32_PerfRawData_NvspSwitchStats_HyperVVirtualSwitch`<br/>`Win32_PerfRawData_EthernetPerfProvider_HyperVLegacyNetworkAdapter`<br/>`Win32_PerfRawData_Counters_HyperVVirtualStorageDevice`<br/>`Win32_PerfRawData_NvspNicStats_HyperVVirtualNetworkAdapter`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_hyperv_health_critical` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_health_ok` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_vid_physical_pages_allocated` | _Not yet documented_ | counter | `vm`
|
||||
`windows_hyperv_vid_preferred_numa_node_index` | _Not yet documented_ | counter | `vm`
|
||||
`windows_hyperv_vid_remote_physical_pages` | _Not yet documented_ | counter | `vm`
|
||||
`windows_hyperv_root_partition_address_spaces` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_attached_devices` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_deposited_pages` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_device_dma_errors` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_device_interrupt_errors` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_device_interrupt_mappings` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_device_interrupt_throttle_events` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_preferred_numa_node_index` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_gpa_space_modifications` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_io_tlb_flush_cost` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_io_tlb_flush` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_recommended_virtual_tlb_size` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_physical_pages_allocated` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_1G_device_pages` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_1G_gpa_pages` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_2M_device_pages` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_2M_gpa_pages` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_4K_device_pages` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_4K_gpa_pages` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_virtual_tlb_flush_entires` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_root_partition_virtual_tlb_pages` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_hypervisor_virtual_processors` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_hypervisor_logical_processors` | _Not yet documented_ | counter | None
|
||||
`windows_hyperv_host_lp_guest_run_time_percent` | _Not yet documented_ | counter | `core`
|
||||
`windows_hyperv_host_lp_hypervisor_run_time_percent` | _Not yet documented_ | counter | `core`
|
||||
`windows_hyperv_host_lp_total_run_time_percent` | _Not yet documented_ | counter | `core`
|
||||
`windows_hyperv_host_cpu_guest_run_time` | _Not yet documented_ | counter | `core`
|
||||
`windows_hyperv_host_cpu_hypervisor_run_time` | _Not yet documented_ | counter | `core`
|
||||
`windows_hyperv_host_cpu_remote_run_time` | _Not yet documented_ | counter | `core`
|
||||
`windows_hyperv_host_cpu_total_run_time` | _Not yet documented_ | counter | `core`
|
||||
`windows_hyperv_host_cpu_wait_time_per_dispatch_total` | _Not yet documented_ | counter | `core`
|
||||
`windows_hyperv_vm_cpu_guest_run_time` | _Not yet documented_ | counter | `vm`, `core`
|
||||
`windows_hyperv_vm_cpu_hypervisor_run_time` | _Not yet documented_ | counter | `vm`, `core`
|
||||
`windows_hyperv_vm_cpu_remote_run_time` | _Not yet documented_ | counter | `vm`, `core`
|
||||
`windows_hyperv_vm_cpu_wait_time_per_dispatch_total` | _Not yet documented_ | counter | `vm`, `core`
|
||||
`windows_hyperv_vm_memory_added_total` | _Not yet documented_ | counter | `vm`
|
||||
`windows_hyperv_vm_memory_pressure_average` | _Not yet documented_ | gauge | `vm`
|
||||
`windows_hyperv_vm_memory_pressure_current` | _Not yet documented_ | counter | `vm`
|
||||
`windows_hyperv_vm_memory_physical_guest_visible` | _Not yet documented_ | gauge | `vm`
|
||||
`windows_hyperv_vm_memory_pressure_maximum` | _Not yet documented_ | gauge | `vm`
|
||||
`windows_hyperv_vm_memory_add_operations_total` | _Not yet documented_ | counter | `vm`
|
||||
`windows_hyperv_vm_memory_remove_operations_total` | _Not yet documented_ | counter | `vm`
|
||||
`windows_hyperv_vm_memory_pressure_minumim` | _Not yet documented_ | gauge | `vm`
|
||||
`windows_hyperv_vm_memory_physical` | _Not yet documented_ | gauge | `vm`
|
||||
`windows_hyperv_vm_memory_removed_total` | _Not yet documented_ | counter | `vm`
|
||||
`windows_hyperv_vm_cpu_total_run_time` | _Not yet documented_ | counter | `vm`, `core`
|
||||
`windows_hyperv_vswitch_broadcast_packets_received_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_broadcast_packets_sent_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_bytes_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_bytes_received_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_bytes_sent_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_directed_packets_received_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_directed_packets_send_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_dropped_packets_incoming_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_dropped_packets_outcoming_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_extensions_dropped_packets_incoming_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_extensions_dropped_packets_outcoming_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_learned_mac_addresses_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_multicast_packets_received_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_multicast_packets_sent_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_number_of_send_channel_moves_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_number_of_vmq_moves_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_packets_flooded_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_packets_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_packets_received_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_packets_sent_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_vswitch_purged_mac_addresses_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`windows_hyperv_ethernet_bytes_dropped` | _Not yet documented_ | counter | `adapter`
|
||||
`windows_hyperv_ethernet_bytes_received` | _Not yet documented_ | counter | `adapter`
|
||||
`windows_hyperv_ethernet_bytes_sent` | _Not yet documented_ | counter | `adapter`
|
||||
`windows_hyperv_ethernet_frames_dropped` | _Not yet documented_ | counter | `adapter`
|
||||
`windows_hyperv_ethernet_frames_received` | _Not yet documented_ | counter | `adapter`
|
||||
`windows_hyperv_ethernet_frames_sent` | _Not yet documented_ | counter | `adapter`
|
||||
`windows_hyperv_vm_device_error_count` | _Not yet documented_ | counter | `vm_device`
|
||||
`windows_hyperv_vm_device_queue_length` | _Not yet documented_ | counter | `vm_device`
|
||||
`windows_hyperv_vm_device_bytes_read` | _Not yet documented_ | counter | `vm_device`
|
||||
`windows_hyperv_vm_device_operations_read` | _Not yet documented_ | counter | `vm_device`
|
||||
`windows_hyperv_vm_device_bytes_written` | _Not yet documented_ | counter | `vm_device`
|
||||
`windows_hyperv_vm_device_operations_written` | _Not yet documented_ | counter | `vm_device`
|
||||
`windows_hyperv_vm_interface_bytes_received` | _Not yet documented_ | counter | `vm_interface`
|
||||
`windows_hyperv_vm_interface_bytes_sent` | _Not yet documented_ | counter | `vm_interface`
|
||||
`windows_hyperv_vm_interface_packets_incoming_dropped` | _Not yet documented_ | counter | `vm_interface`
|
||||
`windows_hyperv_vm_interface_packets_outgoing_dropped` | _Not yet documented_ | counter | `vm_interface`
|
||||
`windows_hyperv_vm_interface_packets_received` | _Not yet documented_ | counter | `vm_interface`
|
||||
`windows_hyperv_vm_interface_packets_sent` | _Not yet documented_ | counter | `vm_interface`
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
Percent of physical CPU resources used per VM (on instance "localhost")
|
||||
```
|
||||
(sum (rate(windows_hyperv_vm_cpu_hypervisor_run_time{instance="localhost"}[1m]))) / ignoring(vm) group_left max (windows_cs_logical_processors{instance="localhost"}) / 100000
|
||||
```
|
||||
Percent of physical CPU resources used by all VMs (on all monitored hosts)
|
||||
```
|
||||
(sum by (instance)(rate(windows_hyperv_vm_cpu_total_run_time{}[1m]))) / max by (instance)(windows_cs_logical_processors{}) / 100000
|
||||
```
|
||||
Percent of physical CPU resources by the hosts themselves (on all monitored hosts)
|
||||
```
|
||||
(sum by (instance)(rate(windows_hyperv_host_cpu_total_run_time{}[1m]))) / sum by (instance)(windows_cs_logical_processors{}) / 100000
|
||||
```
|
||||
Percent of physical CPU resources by the hypervisor (on all monitored hosts)
|
||||
```
|
||||
(sum by (instance)(rate(windows_hyperv_host_lp_total_run_time_percent{}[1m]))) / sum by (instance)(windows_hyperv_hypervisor_logical_processors{}) / 100000
|
||||
```
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
# hyperv collector
|
||||
|
||||
The hyperv collector exposes metrics about the Hyper-V hypervisor
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `hyperv`
|
||||
Classes | `Win32_PerfRawData_VmmsVirtualMachineStats_HyperVVirtualMachineHealthSummary`<br/>`Win32_PerfRawData_VidPerfProvider_HyperVVMVidPartition`<br/>`Win32_PerfRawData_HvStats_HyperVHypervisorRootPartition`<br/>`Win32_PerfRawData_HvStats_HyperVHypervisor`<br/>`Win32_PerfRawData_HvStats_HyperVHypervisorRootVirtualProcessor`<br/>`Win32_PerfRawData_HvStats_HyperVHypervisorVirtualProcessor`<br/>`Win32_PerfRawData_NvspSwitchStats_HyperVVirtualSwitch`<br/>`Win32_PerfRawData_EthernetPerfProvider_HyperVLegacyNetworkAdapter`<br/>`Win32_PerfRawData_Counters_HyperVVirtualStorageDevice`<br/>`Win32_PerfRawData_NvspNicStats_HyperVVirtualNetworkAdapter`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`wmi_hyperv_health_critical` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_health_ok` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_vid_physical_pages_allocated` | _Not yet documented_ | counter | `vm`
|
||||
`wmi_hyperv_vid_preferred_numa_node_index` | _Not yet documented_ | counter | `vm`
|
||||
`wmi_hyperv_vid_remote_physical_pages` | _Not yet documented_ | counter | `vm`
|
||||
`wmi_hyperv_root_partition_address_spaces` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_attached_devices` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_deposited_pages` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_device_dma_errors` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_device_interrupt_errors` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_device_interrupt_mappings` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_device_interrupt_throttle_events` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_preferred_numa_node_index` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_gpa_space_modifications` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_io_tlb_flush_cost` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_io_tlb_flush` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_recommended_virtual_tlb_size` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_physical_pages_allocated` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_1G_device_pages` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_1G_gpa_pages` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_2M_device_pages` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_2M_gpa_pages` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_4K_device_pages` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_4K_gpa_pages` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_virtual_tlb_flush_entires` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_root_partition_virtual_tlb_pages` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_hypervisor_virtual_processors` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_hypervisor_logical_processors` | _Not yet documented_ | counter | None
|
||||
`wmi_hyperv_host_cpu_guest_run_time` | _Not yet documented_ | counter | `core`
|
||||
`wmi_hyperv_host_cpu_hypervisor_run_time` | _Not yet documented_ | counter | `core`
|
||||
`wmi_hyperv_host_cpu_remote_run_time` | _Not yet documented_ | counter | `core`
|
||||
`wmi_hyperv_host_cpu_total_run_time` | _Not yet documented_ | counter | `core`
|
||||
`wmi_hyperv_vm_cpu_guest_run_time` | _Not yet documented_ | counter | `vm`, `core`
|
||||
`wmi_hyperv_vm_cpu_hypervisor_run_time` | _Not yet documented_ | counter | `vm`, `core`
|
||||
`wmi_hyperv_vm_cpu_remote_run_time` | _Not yet documented_ | counter | `vm`, `core`
|
||||
`wmi_hyperv_vm_cpu_total_run_time` | _Not yet documented_ | counter | `vm`, `core`
|
||||
`wmi_hyperv_vswitch_broadcast_packets_received_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_broadcast_packets_sent_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_bytes_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_bytes_received_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_bytes_sent_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_directed_packets_received_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_directed_packets_send_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_dropped_packets_incoming_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_dropped_packets_outcoming_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_extensions_dropped_packets_incoming_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_extensions_dropped_packets_outcoming_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_learned_mac_addresses_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_multicast_packets_received_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_multicast_packets_sent_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_number_of_send_channel_moves_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_number_of_vmq_moves_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_packets_flooded_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_packets_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_packets_received_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_packets_sent_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_vswitch_purged_mac_addresses_total` | _Not yet documented_ | counter | `vswitch`
|
||||
`wmi_hyperv_ethernet_bytes_dropped` | _Not yet documented_ | counter | `adapter`
|
||||
`wmi_hyperv_ethernet_bytes_received` | _Not yet documented_ | counter | `adapter`
|
||||
`wmi_hyperv_ethernet_bytes_sent` | _Not yet documented_ | counter | `adapter`
|
||||
`wmi_hyperv_ethernet_frames_dropped` | _Not yet documented_ | counter | `adapter`
|
||||
`wmi_hyperv_ethernet_frames_received` | _Not yet documented_ | counter | `adapter`
|
||||
`wmi_hyperv_ethernet_frames_sent` | _Not yet documented_ | counter | `adapter`
|
||||
`wmi_hyperv_vm_device_error_count` | _Not yet documented_ | counter | `vm_device`
|
||||
`wmi_hyperv_vm_device_queue_length` | _Not yet documented_ | counter | `vm_device`
|
||||
`wmi_hyperv_vm_device_bytes_read` | _Not yet documented_ | counter | `vm_device`
|
||||
`wmi_hyperv_vm_device_operations_read` | _Not yet documented_ | counter | `vm_device`
|
||||
`wmi_hyperv_vm_device_bytes_written` | _Not yet documented_ | counter | `vm_device`
|
||||
`wmi_hyperv_vm_device_operations_written` | _Not yet documented_ | counter | `vm_device`
|
||||
`wmi_hyperv_vm_interface_bytes_received` | _Not yet documented_ | counter | `vm_interface`
|
||||
`wmi_hyperv_vm_interface_bytes_sent` | _Not yet documented_ | counter | `vm_interface`
|
||||
`wmi_hyperv_vm_interface_packets_incoming_dropped` | _Not yet documented_ | counter | `vm_interface`
|
||||
`wmi_hyperv_vm_interface_packets_outgoing_dropped` | _Not yet documented_ | counter | `vm_interface`
|
||||
`wmi_hyperv_vm_interface_packets_received` | _Not yet documented_ | counter | `vm_interface`
|
||||
`wmi_hyperv_vm_interface_packets_sent` | _Not yet documented_ | counter | `vm_interface`
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
|
||||
@@ -1,141 +1,140 @@
|
||||
# iis collector
|
||||
|
||||
The iis collector exposes metrics about the IIS server
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `iis`
|
||||
Data source | Perflib
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
### `--collector.iis.site-include`
|
||||
|
||||
If given, a site needs to match the include regexp in order for the corresponding metrics to be reported.
|
||||
|
||||
### `--collector.iis.site-exclude`
|
||||
|
||||
If given, a site needs to *not* match the exclude regexp in order for the corresponding metrics to be reported.
|
||||
|
||||
### `--collector.iis.app-include`
|
||||
|
||||
If given, an application needs to match the include regexp in order for the corresponding metrics to be reported.
|
||||
|
||||
### `--collector.iis.app-exclude`
|
||||
|
||||
If given, an application needs to *not* match the exclude regexp in order for the corresponding metrics to be reported.
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_iis_current_anonymous_users` | The number of users who currently have an anonymous request pending with the web service | gauge | `site`
|
||||
`windows_iis_current_blocked_async_io_requests` | _Not yet documented_ | gauge | `site`
|
||||
`windows_iis_current_cgi_requests` | The number of CGI requests that are being processed simultaneously by the web service | gauge | `site`
|
||||
`windows_iis_current_connections` | The number of active connections to the web service | gauge | `site`
|
||||
`windows_iis_current_isapi_extension_requests` | The number of [ISAPI extension](https://docs.microsoft.com/en-us/previous-versions/iis/6.0-sdk/ms525172(v=vs.90)) requests that are being processed simultaneously by the web service | gauge | `site`
|
||||
`windows_iis_current_non_anonymous_users` | The number of users who currently have a nonanonymous request pending with the web service | gauge | `site`
|
||||
`windows_iis_service_uptime` | The uptime for the web service or a Web site (seconds) | gauge | `site`
|
||||
`windows_iis_received_bytes_total` | The total bytes of data that have been received by the web service since the service started | counter | `site`
|
||||
`windows_iis_sent_bytes_total` | The number of data bytes that have been sent by the web service since the service started | counter | `site`
|
||||
`windows_iis_anonymous_users_total` | The number of users who have established an anonymous request since the web service started | counter | `site`
|
||||
`windows_iis_blocked_async_io_requests_total` | The total number of blocked asynchronous I/O requests since the start of the IIS service | counter | `site`
|
||||
`windows_iis_cgi_requests_total` | The number of all CGI requests that have been made since the web service started | counter | `site`
|
||||
`windows_iis_connection_attempts_all_instances_total` | The number of connections to the web service that have been attempted since the service started | counter | `site`
|
||||
`windows_iis_requests_total` | The number of requests that have been made since the web service was started | counter | `site`, `method`
|
||||
`windows_iis_files_received_total` | The total number of files that have been received by the FTP service since the service started | counter | `site`
|
||||
`windows_iis_files_sent_total` | The total number of files that have been sent by the FTP service since the service started | counter | `site`
|
||||
`windows_iis_ipapi_extension_requests_total` | The number of ISAPI extension requests that have been made since the web service started | counter | `site`
|
||||
`windows_iis_locked_errors_total` | The number of requests that have been made since the service started that could not be satisfied by the server because the requested document was locked. Usually reported as HTTP error 423 | counter | `site`
|
||||
`windows_iis_logon_attempts_total` | The number of attempts to log on to the web service that have occurred since the service started | counter | `site`
|
||||
`windows_iis_non_anonymous_users_total` | The number of users who have made nonanonymous requests to the web service since the service started | counter | `site`
|
||||
`windows_iis_not_found_errors_total` | The number of requests that have been made since the service started that were not satisfied by the server because the requested document was not found. Usually reported as HTTP error 404 | counter | `site`
|
||||
`windows_iis_rejected_async_io_requests_total` |The total number of rejected asynchronous I/O requests since the start of the IIS service. | counter | `site`
|
||||
`windows_iis_current_application_pool_state` | The current status of the application pool (1 - Uninitialized, 2 - Initialized, 3 - Running, 4 - Disabling, 5 - Disabled, 6 - Shutdown Pending, 7 - Delete Pending) | gauge | `app`, `state`
|
||||
`windows_iis_current_application_pool_start_time` | The unix timestamp for the application pool start time | gauge | `app`
|
||||
`windows_iis_current_worker_processes` | The current number of worker processes that are running in the application pool | gauge | `app`
|
||||
`windows_iis_maximum_worker_processes` | The maximum number of worker processes that have been created for the application pool since Windows Process Activation Service (WAS) started | gauge | `app`
|
||||
`windows_iis_recent_worker_process_failures` | The number of times that worker processes for the application pool failed during the rapid-fail protection interval | gauge | `app`
|
||||
`windows_iis_time_since_last_worker_process_failure` | The length of time, in seconds, since the last worker process failure occurred for the application pool | gauge | `app`
|
||||
`windows_iis_total_application_pool_recycles` | The number of times that the application pool has been recycled since Windows Process Activation Service (WAS) started | counter | `app`
|
||||
`windows_iis_total_application_pool_start_time` | The unix timestamp for the application pool of when the Windows Process Activation Service (WAS) started | counter | `app`
|
||||
`windows_iis_total_worker_processes_created` | The number of worker processes created for the application pool since Windows Process Activation Service (WAS) started | counter | `app`
|
||||
`windows_iis_total_worker_process_failures` | The number of times that worker processes have crashed since the application pool was started | counter | `app`
|
||||
`windows_iis_total_worker_process_ping_failures` | The number of times that Windows Process Activation Service (WAS) did not receive a response to ping messages sent to a worker process | counter | `app`
|
||||
`windows_iis_total_worker_process_shutdown_failures` | The number of times that Windows Process Activation Service (WAS) failed to shut down a worker process | counter | `app`
|
||||
`windows_iis_total_worker_process_startup_failures` | The number of times that Windows Process Activation Service (WAS) failed to start a worker process | counter | `app`
|
||||
`windows_iis_worker_cache_active_flushed_entries` | Number of file handles cached that will be closed when all current transfers complete | gauge | `app`, `pid`
|
||||
`windows_iis_worker_file_cache_memory_bytes` | Current number of bytes used by file cache | gauge | `app`, `pid`
|
||||
`windows_iis_worker_file_cache_max_memory_bytes` | Maximum number of bytes used by file cache | counter | `app`, `pid`
|
||||
`windows_iis_worker_file_cache_flushes_total` | Total number of file cache flushes (since service startup) | counter | `app`, `pid`
|
||||
`windows_iis_worker_file_cache_queries_total` | Total file cache queries (hits + misses) | counter | `app`, `pid`
|
||||
`windows_iis_worker_file_cache_hits_total` | Total number of successful lookups in the user-mode file cache | counter | `app`, `pid`
|
||||
`windows_iis_worker_file_cache_items` | Current number of files whose contents are present in user-mode cache | gauge | `app`, `pid`
|
||||
`windows_iis_worker_file_cache_items_total` | Total number of files whose contents were ever added to the user-mode cache (since service startup) | counter | `app`, `pid`
|
||||
`windows_iis_worker_file_cache_items_flushed_total` | Total number of file handles that have been removed from the user-mode cache (since service startup) | counter | `app`, `pid`
|
||||
`windows_iis_worker_uri_cache_flushes_total` | Total number of URI cache flushes (since service startup) | counter | `app`, `pid`
|
||||
`windows_iis_worker_uri_cache_queries_total` | Total number of uri cache queries (hits + misses) | counter | `app`, `pid`
|
||||
`windows_iis_worker_uri_cache_hits_total` | Total number of successful lookups in the user-mode URI cache (since service startup) | counter | `app`, `pid`
|
||||
`windows_iis_worker_uri_cache_items` | Number of URI information blocks currently in the user-mode cache | gauge | `app`, `pid`
|
||||
`windows_iis_worker_uri_cache_items_total` | Total number of URI information blocks added to the user-mode cache (since service startup) | counter | `app`, `pid`
|
||||
`windows_iis_worker_uri_cache_items_flushed_total` | The number of URI information blocks that have been removed from the user-mode cache (since service startup) | counter | `app`, `pid`
|
||||
`windows_iis_worker_metadata_cache_items` | Number of metadata information blocks currently present in user-mode cache | gauge | `app`, `pid`
|
||||
`windows_iis_worker_metadata_cache_flushes_total` | Total number of user-mode metadata cache flushes (since service startup) | counter | `app`, `pid`
|
||||
`windows_iis_worker_metadata_cache_queries_total` | Total metadata cache queries (hits + misses) | counter | `app`, `pid`
|
||||
`windows_iis_worker_metadata_cache_hits_total` | Total number of successful lookups in the user-mode metadata cache (since service startup) | counter | `app`, `pid`
|
||||
`windows_iis_worker_metadata_cache_items_cached_total` | Total number of metadata information blocks added to the user-mode cache (since service startup) | counter | `app`, `pid`
|
||||
`windows_iis_worker_metadata_cache_items_flushed_total` | Total number of metadata information blocks removed from the user-mode cache (since service startup) | counter | `app`, `pid`
|
||||
`windows_iis_worker_output_cache_active_flushed_items` |The total number of active and flushed items in the output cache of the IIS worker process. Active items are those that are currently being used to serve client requests, while flushed items are those that have been removed from the cache but are still waiting to be flushed to disk. | counter | `app`, `pid`
|
||||
`windows_iis_worker_output_cache_items` | Number of items current present in output cache | counter | `app`, `pid`
|
||||
`windows_iis_worker_output_cache_memory_bytes` | Current number of bytes used by output cache | counter | `app`, `pid`
|
||||
`windows_iis_worker_output_queries_total` | Total number of output cache queries (hits + misses) | counter | `app`, `pid`
|
||||
`windows_iis_worker_output_cache_hits_total` | Total number of successful lookups in output cache (since service startup) | counter | `app`, `pid`
|
||||
`windows_iis_worker_output_cache_items_flushed_total` | Total number of items flushed from output cache (since service startup) | counter | `app`, `pid`
|
||||
`windows_iis_worker_output_cache_flushes_total` | Total number of flushes of output cache (since service startup) | counter | `app`, `pid`
|
||||
`windows_iis_worker_threads` | Number of threads actively processing requests in the worker process | gauge | `app`, `pid`, `state`
|
||||
`windows_iis_worker_max_threads` | Maximum number of threads to which the thread pool can grow as needed | counter | `app`, `pid`
|
||||
`windows_iis_worker_requests_total` | Total number of HTTP requests served by the worker process | counter | `app`, `pid`
|
||||
`windows_iis_worker_current_requests` | Current number of requests being processed by the worker process | counter | `app`, `pid`
|
||||
`windows_iis_worker_request_errors_total` | Total number of requests that returned an error | counter | `app`, `pid`, `status_code`
|
||||
`windows_iis_worker_current_websocket_requests` | the current number of WebSocket connections being processed by the IIS worker process. | counter | `app`, `pid`
|
||||
`windows_iis_worker_websocket_connection_attempts_total` | the total number of attempted WebSocket connections since the start of the IIS worker process | counter | `app`, `pid`
|
||||
`windows_iis_worker_websocket_connection_accepted_total` | the total number of WebSocket connections that have been successfully established since the start of the IIS worker process | counter | `app`, `pid`
|
||||
`windows_iis_worker_websocket_connection_rejected_total` | the total number of WebSocket connections that have been rejected by the server since the start of the IIS worker process. Connections can be rejected for various reasons, such as capacity limitations, authentication failures, or configuration issues | counter | `app`, `pid`
|
||||
`windows_iis_server_cache_active_flushed_entries` | Number of file handles cached that will be closed when all current transfers complete | counter | None
|
||||
`windows_iis_server_file_cache_memory_bytes` | Current number of bytes used by file cache | gauge | None
|
||||
`windows_iis_server_file_cache_max_memory_bytes` | Maximum number of bytes used by file cache | counter | None
|
||||
`windows_iis_server_file_cache_flushes_total` | Total number of file cache flushes (since service startup) | counter | None
|
||||
`windows_iis_server_file_cache_queries_total` | Total number of file cache queries (hits + misses) | counter | None
|
||||
`windows_iis_server_file_cache_hits_total` | Total number of successful lookups in the file cache | counter | None
|
||||
`windows_iis_server_file_cache_items` | Current number of files whose contents are present in cache | gauge | None
|
||||
`windows_iis_server_file_cache_items_total` | Total number of files whose contents were ever added to the cache (since service startup) | counter | None
|
||||
`windows_iis_server_file_cache_items_flushed_total` | Total number of file handles that have been removed from the cache (since service startup) | counter | None
|
||||
`windows_iis_server_uri_cache_flushes_total` | Total number of URI cache flushes (since service startup) | counter | `mode`
|
||||
`windows_iis_server_uri_cache_queries_total` | Total number of uri cache queries (hits + misses) | counter | `mode`
|
||||
`windows_iis_server_uri_cache_hits_total` | Total number of successful lookups in the URI cache (since service startup) | counter | `mode`
|
||||
`windows_iis_server_uri_cache_items` | Number of URI information blocks currently in the cache | gauge | `mode`
|
||||
`windows_iis_server_uri_cache_items_total` | Total number of URI information blocks added to the cache (since service startup) | counter | `mode`
|
||||
`windows_iis_server_uri_cache_items_flushed_total` | The number of URI information blocks that have been removed from the cache (since service startup) | counter | `mode`
|
||||
`windows_iis_server_metadata_cache_items` | Number of metadata information blocks currently present in cache | gauge | None
|
||||
`windows_iis_server_metadata_cache_flushes_total` | Total number of metadata cache flushes (since service startup) | counter | None
|
||||
`windows_iis_server_metadata_cache_queries_total` | Total metadata cache queries (hits + misses) | counter | None
|
||||
`windows_iis_server_metadata_cache_hits_total` | Total number of successful lookups in the metadata cache (since service startup) | counter | None
|
||||
`windows_iis_server_metadata_cache_items_cached_total` | Total number of metadata information blocks added to the cache (since service startup) | counter | None
|
||||
`windows_iis_server_metadata_cache_items_flushed_total` | Total number of metadata information blocks removed from the cache (since service startup) | counter | None
|
||||
`windows_iis_server_output_cache_active_flushed_items` | The total number of active and flushed items in the output cache of the IIS server | counter | None
|
||||
`windows_iis_server_output_cache_items` | Number of items current present in output cache | counter | None
|
||||
`windows_iis_server_output_cache_memory_bytes` | Current number of bytes used by output cache | counter | None
|
||||
`windows_iis_server_output_cache_queries_total` | Total output cache queries (hits + misses) | counter | None
|
||||
`windows_iis_server_output_cache_hits_total` | Total number of successful lookups in output cache (since service startup) | counter | None
|
||||
`windows_iis_server_output_cache_items_flushed_total` | Total number of items flushed from output cache (since service startup) | counter | None
|
||||
`windows_iis_server_output_cache_flushes_total` | Total number of flushes of output cache (since service startup) | counter | None
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
# iis collector
|
||||
|
||||
The iis collector exposes metrics about the IIS server
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `iis`
|
||||
Classes | `Win32_PerfRawData_W3SVC_WebService`<br/>`Win32_PerfRawData_APPPOOLCountersProvider_APPPOOLWAS`<br/>`Win32_PerfRawData_W3SVCW3WPCounterProvider_W3SVCW3WP`<br/>`Win32_PerfRawData_W3SVC_WebServiceCache`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
### `--collector.iis.site-whitelist`
|
||||
|
||||
If given, a site needs to match the whitelist regexp in order for the corresponding metrics to be reported.
|
||||
|
||||
### `--collector.iis.site-blacklist`
|
||||
|
||||
If given, a site needs to *not* match the blacklist regexp in order for the corresponding metrics to be reported.
|
||||
|
||||
### `--collector.iis.app-whitelist`
|
||||
|
||||
If given, an application needs to match the whitelist regexp in order for the corresponding metrics to be reported.
|
||||
|
||||
### `--collector.iis.app-blacklist`
|
||||
|
||||
If given, an application needs to *not* match the blacklist regexp in order for the corresponding metrics to be reported.
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`wmi_iis_current_anonymous_users` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_current_blocked_async_io_requests` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_current_cgi_requests` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_current_connections` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_current_isapi_extension_requests` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_current_non_anonymous_users` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_received_bytes_total` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_sent_bytes_total` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_anonymous_users_total` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_blocked_async_io_requests_total` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_cgi_requests_total` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_connection_attempts_all_instances_total` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_requests_total` | _Not yet documented_ | counter | `site`, `method`
|
||||
`wmi_iis_files_received_total` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_files_sent_total` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_ipapi_extension_requests_total` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_locked_errors_total` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_logon_attempts_total` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_non_anonymous_users_total` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_not_found_errors_total` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_rejected_async_io_requests_total` | _Not yet documented_ | counter | `site`
|
||||
`wmi_iis_current_application_pool_state` | _Not yet documented_ | counter | `app`, `state`
|
||||
`wmi_iis_current_application_pool_start_time` | _Not yet documented_ | counter | `app`
|
||||
`wmi_iis_current_worker_processes` | _Not yet documented_ | counter | `app`
|
||||
`wmi_iis_maximum_worker_processes` | _Not yet documented_ | counter | `app`
|
||||
`wmi_iis_recent_worker_process_failures` | _Not yet documented_ | counter | `app`
|
||||
`wmi_iis_time_since_last_worker_process_failure` | _Not yet documented_ | counter | `app`
|
||||
`wmi_iis_total_application_pool_recycles` | _Not yet documented_ | counter | `app`
|
||||
`wmi_iis_total_application_pool_start_time` | _Not yet documented_ | counter | `app`
|
||||
`wmi_iis_total_worker_processes_created` | _Not yet documented_ | counter | `app`
|
||||
`wmi_iis_total_worker_process_failures` | _Not yet documented_ | counter | `app`
|
||||
`wmi_iis_total_worker_process_ping_failures` | _Not yet documented_ | counter | `app`
|
||||
`wmi_iis_total_worker_process_shutdown_failures` | _Not yet documented_ | counter | `app`
|
||||
`wmi_iis_total_worker_process_startup_failures` | _Not yet documented_ | counter | `app`
|
||||
`wmi_iis_worker_cache_active_flushed_entries` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_file_cache_memory_bytes` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_file_cache_max_memory_bytes` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_file_cache_flushes_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_file_cache_queries_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_file_cache_hits_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_file_cache_items` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_file_cache_items_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_file_cache_items_flushed_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_uri_cache_flushes_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_uri_cache_queries_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_uri_cache_hits_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_uri_cache_items` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_uri_cache_items_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_uri_cache_items_flushed_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_metadata_cache_items` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_metadata_cache_flushes_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_metadata_cache_queries_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_metadata_cache_hits_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_metadata_cache_items_cached_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_metadata_cache_items_flushed_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_output_cache_active_flushed_items` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_output_cache_items` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_output_cache_memory_bytes` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_output_queries_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_output_cache_hits_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_output_cache_items_flushed_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_output_cache_flushes_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_threads` | _Not yet documented_ | counter | `app`, `pid`, `state`
|
||||
`wmi_iis_worker_max_threads` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_requests_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_current_requests` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_request_errors_total` | _Not yet documented_ | counter | `app`, `pid`, `status_code`
|
||||
`wmi_iis_worker_current_websocket_requests` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_websocket_connection_attempts_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_websocket_connection_accepted_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_worker_websocket_connection_rejected_total` | _Not yet documented_ | counter | `app`, `pid`
|
||||
`wmi_iis_server_cache_active_flushed_entries` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_file_cache_memory_bytes` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_file_cache_max_memory_bytes` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_file_cache_flushes_total` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_file_cache_queries_total` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_file_cache_hits_total` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_file_cache_items` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_file_cache_items_total` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_file_cache_items_flushed_total` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_uri_cache_flushes_total` | _Not yet documented_ | counter | `mode`
|
||||
`wmi_iis_server_uri_cache_queries_total` | _Not yet documented_ | counter | `mode`
|
||||
`wmi_iis_server_uri_cache_hits_total` | _Not yet documented_ | counter | `mode`
|
||||
`wmi_iis_server_uri_cache_items` | _Not yet documented_ | counter | `mode`
|
||||
`wmi_iis_server_uri_cache_items_total` | _Not yet documented_ | counter | `mode`
|
||||
`wmi_iis_server_uri_cache_items_flushed_total` | _Not yet documented_ | counter | `mode`
|
||||
`wmi_iis_server_metadata_cache_items` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_metadata_cache_flushes_total` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_metadata_cache_queries_total` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_metadata_cache_hits_total` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_metadata_cache_items_cached_total` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_metadata_cache_items_flushed_total` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_output_cache_active_flushed_items` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_output_cache_items` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_output_cache_memory_bytes` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_output_cache_queries_total` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_output_cache_hits_total` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_output_cache_items_flushed_total` | _Not yet documented_ | counter | None
|
||||
`wmi_iis_server_output_cache_flushes_total` | _Not yet documented_ | counter | None
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
|
||||
@@ -1,53 +0,0 @@
|
||||
# license collector
|
||||
|
||||
The license collector exposes metrics about the Windows license status.
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `license`
|
||||
Data source | Win32
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
| Name | Description | Type | Labels |
|
||||
|--------------------------|----------------|-------|---------|
|
||||
| `windows_license_status` | license status | gauge | `state` |
|
||||
|
||||
### Example metric
|
||||
|
||||
```
|
||||
# HELP windows_license_status Status of windows license
|
||||
# TYPE windows_license_status gauge
|
||||
windows_license_status{state="genuine"} 1
|
||||
windows_license_status{state="invalid_license"} 0
|
||||
windows_license_status{state="last"} 0
|
||||
windows_license_status{state="offline"} 0
|
||||
windows_license_status{state="tampered"} 0
|
||||
```
|
||||
|
||||
|
||||
## Useful queries
|
||||
|
||||
Show if the license is genuine
|
||||
|
||||
```
|
||||
windows_license_status{state="genuine"}
|
||||
```
|
||||
|
||||
## Alerting examples
|
||||
**prometheus.rules**
|
||||
```yaml
|
||||
- alert: "WindowsLicense"
|
||||
expr: 'windows_license_status{state="genuine"} == 0'
|
||||
for: "10m"
|
||||
labels:
|
||||
severity: "high"
|
||||
annotations:
|
||||
summary: "Windows system license is not genuine"
|
||||
description: "The Windows system license is not genuine. Please check the license status."
|
||||
```
|
||||
@@ -11,62 +11,40 @@ Enabled by default? | Yes
|
||||
|
||||
## Flags
|
||||
|
||||
### `--collector.logical_disk.volume-include`
|
||||
### `--collector.logical_disk.volume-whitelist`
|
||||
|
||||
If given, a disk needs to match the include regexp in order for the corresponding disk metrics to be reported
|
||||
If given, a disk needs to match the whitelist regexp in order for the corresponding disk metrics to be reported
|
||||
|
||||
### `--collector.logical_disk.volume-exclude`
|
||||
### `--collector.logical_disk.volume-blacklist`
|
||||
|
||||
If given, a disk needs to *not* match the exclude regexp in order for the corresponding disk metrics to be reported
|
||||
If given, a disk needs to *not* match the blacklist regexp in order for the corresponding disk metrics to be reported
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_logical_disk_info` | A metric with a constant '1' value labeled with logical disk information | gauge | `disk`,`filesystem`,`serial_number`,`volume`,`volume_name`,`type`
|
||||
`windows_logical_disk_requests_queued` | Number of requests outstanding on the disk at the time the performance data is collected | gauge | `volume`
|
||||
`windows_logical_disk_avg_read_requests_queued` | Average number of read requests that were queued for the selected disk during the sample interval | gauge | `volume`
|
||||
`windows_logical_disk_avg_write_requests_queued` | Average number of write requests that were queued for the selected disk during the sample interval | gauge | `volume`
|
||||
`windows_logical_disk_read_bytes_total` | Rate at which bytes are transferred from the disk during read operations | counter | `volume`
|
||||
`windows_logical_disk_reads_total` | Rate of read operations on the disk | counter | `volume`
|
||||
`windows_logical_disk_write_bytes_total` | Rate at which bytes are transferred to the disk during write operations | counter | `volume`
|
||||
`windows_logical_disk_writes_total` | Rate of write operations on the disk | counter | `volume`
|
||||
`windows_logical_disk_read_seconds_total` | Seconds the disk was busy servicing read requests | counter | `volume`
|
||||
`windows_logical_disk_write_seconds_total` | Seconds the disk was busy servicing write requests | counter | `volume`
|
||||
`windows_logical_disk_free_bytes` | Unused space of the disk in bytes (not real time, updates every 10-15 min) | gauge | `volume`
|
||||
`windows_logical_disk_size_bytes` | Total size of the disk in bytes (not real time, updates every 10-15 min) | gauge | `volume`
|
||||
`windows_logical_disk_idle_seconds_total` | Seconds the disk was idle (not servicing read/write requests) | counter | `volume`
|
||||
`windows_logical_disk_split_ios_total` | Number of I/Os to the disk split into multiple I/Os | counter | `volume`
|
||||
`windows_logical_disk_readonly` | Whether the logical disk is read-only | gauge | `volume`
|
||||
|
||||
### Warning about size metrics
|
||||
The `free_bytes` and `size_bytes` metrics are not updated in real time and might have a delay of 10-15min.
|
||||
This is the same behavior as the windows performance counters.
|
||||
`requests_queued` | Number of requests outstanding on the disk at the time the performance data is collected | gauge | `volume`
|
||||
`read_bytes_total` | Rate at which bytes are transferred from the disk during read operations | counter | `volume`
|
||||
`reads_total` | Rate of read operations on the disk | counter | `volume`
|
||||
`write_bytes_total` | Rate at which bytes are transferred to the disk during write operations | counter | `volume`
|
||||
`writes_total` | Rate of write operations on the disk | counter | `volume`
|
||||
`read_seconds_total` | Seconds the disk was busy servicing read requests | counter | `volume`
|
||||
`write_seconds_total` | Seconds the disk was busy servicing write requests | counter | `volume`
|
||||
`free_bytes` | Unused space of the disk in bytes | gauge | `volume`
|
||||
`size_bytes` | Total size of the disk in bytes | gauge | `volume`
|
||||
`idle_seconds_total` | Seconds the disk was idle (not servicing read/write requests) | counter | `volume`
|
||||
`split_ios_total` | Number of I/Os to the disk split into multiple I/Os | counter | `volume`
|
||||
|
||||
### Example metric
|
||||
Query the rate of write operations to a disk
|
||||
```
|
||||
rate(windows_logical_disk_read_bytes_total{instance="localhost", volume=~"C:"}[2m])
|
||||
```
|
||||
|
||||
Logical Volume information
|
||||
```
|
||||
windows_logical_disk_info{disk_id="0",filesystem="",serial_number="",type="",volume="HarddiskVolume2",volume_name=""} 1
|
||||
windows_logical_disk_info{disk_id="0",filesystem="",serial_number="",type="",volume="HarddiskVolume3",volume_name=""} 1
|
||||
windows_logical_disk_info{disk_id="0",filesystem="NTFS",serial_number="668EEC37",type="fixed",volume="C:",volume_name="Windows"} 1
|
||||
windows_logical_disk_info{disk_id="1",filesystem="NTFS",serial_number="50AE953B",type="fixed",volume="D:",volume_name="Temporary Storage"} 1
|
||||
windows_logical_disk_info{disk_id="1",filesystem="ReFS",serial_number="C69B59AD",type="fixed",volume="G:",volume_name="Volume"} 1
|
||||
rate(wmi_logical_disk_read_bytes_total{instance="localhost", volume=~"C:"}[2m])
|
||||
```
|
||||
|
||||
## Useful queries
|
||||
Calculate rate of total IOPS for disk
|
||||
```
|
||||
rate(windows_logical_disk_reads_total{instance="localhost", volume="C:"}[2m]) + rate(windows_logical_disk_writes_total{instance="localhost", volume="C:"}[2m])
|
||||
```
|
||||
|
||||
Show volume usage (%)
|
||||
```
|
||||
100.0 - 100 * (windows_logical_disk_free_bytes{instance="localhost", volume="C:"} / windows_logical_disk_size_bytes{instance="localhost", volume="C:"})
|
||||
rate(wmi_logical_disk_reads_total{instance="localhost", volume="C:"}[2m]) + rate(wmi_logical_disk_writes_total{instance="localhost", volume="C:"}[2m])
|
||||
```
|
||||
|
||||
## Alerting examples
|
||||
@@ -78,7 +56,7 @@ groups:
|
||||
|
||||
# Sends an alert when disk space usage is above 95%
|
||||
- alert: DiskSpaceUsage
|
||||
expr: 100.0 - 100 * (windows_logical_disk_free_bytes / windows_logical_disk_size_bytes) > 95
|
||||
expr: 100.0 - 100 * (wmi_logical_disk_free_bytes / wmi_logical_disk_size_bytes) > 95
|
||||
for: 10m
|
||||
labels:
|
||||
severity: high
|
||||
@@ -88,7 +66,7 @@ groups:
|
||||
|
||||
# Alerts on disks with over 85% space usage predicted to fill within the next four days
|
||||
- alert: DiskFilling
|
||||
expr: 100 * (windows_logical_disk_free_bytes / windows_logical_disk_size_bytes) < 15 and predict_linear(windows_logical_disk_free_bytes[6h], 4 * 24 * 3600) < 0
|
||||
expr: 100 * (wmi_logical_disk_free_bytes / wmi_logical_disk_size_bytes) < 15 and predict_linear(wmi_logical_disk_free_bytes[6h], 4 * 24 * 3600) < 0
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
|
||||
@@ -8,8 +8,6 @@ Metric name prefix | `logon`
|
||||
Classes | [`Win32_LogonSession`](https://docs.microsoft.com/en-us/windows/win32/cimwin32prov/win32-logonsession)
|
||||
Enabled by default? | No
|
||||
|
||||
> :warning: **On some deployments, this collector seems to have some memory/timeout issues**: See [#583](https://github.com/prometheus-community/windows_exporter/issues/583)
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
@@ -18,18 +16,18 @@ None
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_logon_logon_type` | Number of active user logon sessions | gauge | status
|
||||
`wmi_logon_logon_type` | Number of active user logon sessions | gauge | status
|
||||
|
||||
### Example metric
|
||||
Query the total number of interactive logon sessions
|
||||
```
|
||||
windows_logon_logon_type{status="interactive"}
|
||||
wmi_logon_logon_type{status="interactive"}
|
||||
```
|
||||
|
||||
## Useful queries
|
||||
Query the total number of local and remote (I.E. Terminal Services) interactive sessions.
|
||||
```
|
||||
windows_logon_logon_type{status=~"interactive|remote_interactive"}
|
||||
wmi_logon_logon_type{status=~"interactive|remoteinteractive"}
|
||||
```
|
||||
|
||||
## Alerting examples
|
||||
|
||||
@@ -1,60 +1,62 @@
|
||||
# memory collector
|
||||
|
||||
The memory collector exposes metrics about system memory usage
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `memory`
|
||||
Data source | Perflib
|
||||
Classes | `Win32_PerfRawData_PerfOS_Memory`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_memory_available_bytes` | The amount of physical memory immediately available for allocation to a process or for system use. It is equal to the sum of memory assigned to the standby (cached), free and zero page lists | gauge | None
|
||||
`windows_memory_cache_bytes` | Number of bytes currently being used by the file system cache | gauge | None
|
||||
`windows_memory_cache_bytes_peak` | Maximum number of CacheBytes after the system was last restarted | gauge | None
|
||||
`windows_memory_cache_faults_total` | Number of faults which occur when a page sought in the file system cache is not found there and must be retrieved from elsewhere in memory (soft fault) or from disk (hard fault) | counter | None
|
||||
`windows_memory_commit_limit` | Amount of virtual memory, in bytes, that can be committed without having to extend the paging file(s) | gauge | None
|
||||
`windows_memory_committed_bytes` | Amount of committed virtual memory, in bytes | gauge | None
|
||||
`windows_memory_demand_zero_faults_total` | The number of zeroed pages required to satisfy faults. Zeroed pages, pages emptied of previously stored data and filled with zeros, are a security feature of Windows that prevent processes from seeing data stored by earlier processes that used the memory space | counter | None
|
||||
`windows_memory_free_and_zero_page_list_bytes` | The amount of physical memory, in bytes, that is assigned to the free and zero page lists. This memory does not contain cached data. It is immediately available for allocation to a process or for system use | gauge | None
|
||||
`windows_memory_free_system_page_table_entries` | Number of page table entries not being used by the system | gauge | None
|
||||
`windows_memory_modified_page_list_bytes` | The amount of physical memory, in bytes, that is assigned to the modified page list. This memory contains cached data and code that is not actively in use by processes, the system and the system cache. This memory needs to be written out before it will be available for allocation to a process or for system use | gauge | None
|
||||
`windows_memory_page_faults_total` | Overall rate at which faulted pages are handled by the processor | counter | None
|
||||
`windows_memory_swap_page_reads_total` | Number of disk page reads (a single read operation reading several pages is still only counted once) | counter | None
|
||||
`windows_memory_swap_pages_read_total` | Number of pages read across all page reads (ie counting all pages read even if they are read in a single operation) | counter | None
|
||||
`windows_memory_swap_pages_written_total` | Number of pages written across all page writes (ie counting all pages written even if they are written in a single operation) | counter | None
|
||||
`windows_memory_swap_page_operations_total` | Total number of swap page read and writes (PagesPersec) | counter | None
|
||||
`windows_memory_swap_page_writes_total` | Number of disk page writes (a single write operation writing several pages is still only counted once) | counter | None
|
||||
`windows_memory_pool_nonpaged_allocs_total` | The number of calls to allocate space in the nonpaged pool. The nonpaged pool is an area of system memory area for objects that cannot be written to disk, and must remain in physical memory as long as they are allocated | counter | None
|
||||
`windows_memory_pool_nonpaged_bytes` | Number of bytes in the non-paged pool, an area of the system virtual memory that is used for objects that cannot be written to disk, but must remain in physical memory as long as they are allocated | gauge | None
|
||||
`windows_memory_pool_paged_allocs_total` | Number of calls to allocate space in the paged pool, regardless of the amount of space allocated in each call | counter | None
|
||||
`windows_memory_pool_paged_bytes` | Number of bytes in the paged pool | gauge | None
|
||||
`windows_memory_pool_paged_resident_bytes` | The size, in bytes, of the portion of the paged pool that is currently resident and active in physical memory. The paged pool is an area of the system virtual memory that is used for objects that can be written to disk when they are not being used | gauge | None
|
||||
`windows_memory_standby_cache_core_bytes` | The amount of physical memory, in bytes, that is assigned to the core standby cache page lists. This memory contains cached data and code that is not actively in use by processes, the system and the system cache. It is immediately available for allocation to a process or for system use. If the system runs out of available free and zero memory, memory on lower priority standby cache page lists will be repurposed before memory on higher priority standby cache page lists | gauge | None
|
||||
`windows_memory_standby_cache_normal_priority_bytes` | The amount of physical memory, in bytes, that is assigned to the normal priority standby cache page lists. This memory contains cached data and code that is not actively in use by processes, the system and the system cache. It is immediately available for allocation to a process or for system use. If the system runs out of available free and zero memory, memory on lower priority standby cache page lists will be repurposed before memory on higher priority standby cache page lists | gauge | None
|
||||
`windows_memory_standby_cache_reserve_bytes` | The amount of physical memory, in bytes, that is assigned to the reserve standby cache page lists. This memory contains cached data and code that is not actively in use by processes, the system and the system cache. It is immediately available for allocation to a process or for system use. If the system runs out of available free and zero memory, memory on lower priority standby cache page lists will be repurposed before memory on higher priority standby cache page lists | gauge | None
|
||||
`windows_memory_system_cache_resident_bytes` | The size, in bytes, of the portion of the system file cache which is currently resident and active in physical memory | gauge | None
|
||||
`windows_memory_system_code_resident_bytes` | The size, in bytes, of the pageable operating system code that is currently resident and active in physical memory. This value is a component of Memory\\System Code Total Bytes. Memory\\System Code Resident Bytes (and Memory\\System Code Total Bytes) does not include code that must remain in physical memory and cannot be written to disk | gauge | None
|
||||
`windows_memory_system_code_total_bytes` | The size, in bytes, of the pageable operating system code currently mapped into the system virtual address space. This value is calculated by summing the bytes in Ntoskrnl.exe, Hal.dll, the boot drivers, and file systems loaded by Ntldr/osloader. This counter does not include code that must remain in physical memory and cannot be written to disk | gauge | None
|
||||
`windows_memory_system_driver_resident_bytes` | The size, in bytes, of the pageable physical memory being used by device drivers. It is the working set (physical memory area) of the drivers. This value is a component of Memory\\System Driver Total Bytes, which also includes driver memory that has been written to disk. Neither Memory\\System Driver Resident Bytes nor Memory\\System Driver Total Bytes includes memory that cannot be written to disk | gauge | None
|
||||
`windows_memory_system_driver_total_bytes` | The size, in bytes, of the pageable virtual memory currently being used by device drivers. Pageable memory can be written to disk when it is not being used. It includes both physical memory (Memory\\System Driver Resident Bytes) and code and data paged to disk. It is a component of Memory\\System Code Total Bytes | gauge | None
|
||||
`windows_memory_transition_faults_total` | Number of faults rate at which page faults are resolved by recovering pages that were being used by another process sharing the page, or were on the modified page list or the standby list, or were being written to disk at the time of the page fault. The pages were recovered without additional disk activity. Transition faults are counted in numbers of faults; because only one page is faulted in each operation, it is also equal to the number of pages faulted | counter | None
|
||||
`windows_memory_transition_pages_repurposed_total` | Transition Pages RePurposed is the rate at which the number of transition cache pages were reused for a different purpose. These pages would have otherwise remained in the page cache to provide a (fast) soft fault (instead of retrieving it from backing store) in the event the page was accessed in the future | counter | None
|
||||
`windows_memory_write_copies_total` | The number of page faults caused by attempting to write that were satisfied by copying the page from elsewhere in physical memory | counter | None
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
# memory collector
|
||||
|
||||
The memory collector exposes metrics about system memory usage
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `memory`
|
||||
Data source | Perflib
|
||||
Classes | `Win32_PerfRawData_PerfOS_Memory`
|
||||
Enabled by default? | Yes
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`wmi_cs_logical_processors` | Number of installed logical processors | gauge | None
|
||||
`wmi_cs_physical_memory_bytes` | Total installed physical memory | gauge | None
|
||||
`wmi_memory_available_bytes` | The amount of physical memory immediately available for allocation to a process or for system use. It is equal to the sum of memory assigned to the standby (cached), free and zero page lists | gauge | None
|
||||
`wmi_memory_cache_bytes` | Number of bytes currently being used by the file system cache | gauge | None
|
||||
`wmi_memory_cache_bytes_peak` | Maximum number of CacheBytes after the system was last restarted | gauge | None
|
||||
`wmi_memory_cache_faults_total` | Number of faults which occur when a page sought in the file system cache is not found there and must be retrieved from elsewhere in memory (soft fault) or from disk (hard fault) | gauge | None
|
||||
`wmi_memory_commit_limit` | Amount of virtual memory, in bytes, that can be committed without having to extend the paging file(s) | gauge | None
|
||||
`wmi_memory_committed_bytes` | Amount of committed virtual memory, in bytes | gauge | None
|
||||
`wmi_memory_demand_zero_faults_total` | The number of zeroed pages required to satisfy faults. Zeroed pages, pages emptied of previously stored data and filled with zeros, are a security feature of Windows that prevent processes from seeing data stored by earlier processes that used the memory space | gauge | None
|
||||
`wmi_memory_free_and_zero_page_list_bytes` | _Not yet documented_ | gauge | None
|
||||
`wmi_memory_free_system_page_table_entries` | Number of page table entries not being used by the system | gauge | None
|
||||
`wmi_memory_modified_page_list_bytes` | _Not yet documented_ | gauge | None
|
||||
`wmi_memory_page_faults_total` | Overall rate at which faulted pages are handled by the processor | gauge | None
|
||||
`wmi_memory_swap_page_reads_total` | Number of disk page reads (a single read operation reading several pages is still only counted once) | gauge | None
|
||||
`wmi_memory_swap_pages_read_total` | Number of pages read across all page reads (ie counting all pages read even if they are read in a single operation) | gauge | None
|
||||
`wmi_memory_swap_pages_written_total` | Number of pages written across all page writes (ie counting all pages written even if they are written in a single operation) | gauge | None
|
||||
`wmi_memory_swap_page_operations_total` | Total number of swap page read and writes (PagesPersec) | gauge | None
|
||||
`wmi_memory_swap_page_writes_total` | Number of disk page writes (a single write operation writing several pages is still only counted once) | gauge | None
|
||||
`wmi_memory_pool_nonpaged_allocs_total` | The number of calls to allocate space in the nonpaged pool. The nonpaged pool is an area of system memory area for objects that cannot be written to disk, and must remain in physical memory as long as they are allocated | gauge | None
|
||||
`wmi_memory_pool_nonpaged_bytes_total` | Number of bytes in the non-paged pool | gauge | None
|
||||
`wmi_memory_pool_paged_allocs_total` | Number of calls to allocate space in the paged pool, regardless of the amount of space allocated in each call | gauge | None
|
||||
`wmi_memory_pool_paged_bytes` | Number of bytes in the paged pool | gauge | None
|
||||
`wmi_memory_pool_paged_resident_bytes` | _Not yet documented_ | gauge | None
|
||||
`wmi_memory_standby_cache_core_bytes` | _Not yet documented_ | gauge | None
|
||||
`wmi_memory_standby_cache_normal_priority_bytes` | _Not yet documented_ | gauge | None
|
||||
`wmi_memory_standby_cache_reserve_bytes` | _Not yet documented_ | gauge | None
|
||||
`wmi_memory_system_cache_resident_bytes` | _Not yet documented_ | gauge | None
|
||||
`wmi_memory_system_code_resident_bytes` | _Not yet documented_ | gauge | None
|
||||
`wmi_memory_system_code_total_bytes` | _Not yet documented_ | gauge | None
|
||||
`wmi_memory_system_driver_resident_bytes` | _Not yet documented_ | gauge | None
|
||||
`wmi_memory_system_driver_total_bytes` | _Not yet documented_ | gauge | None
|
||||
`wmi_memory_transition_faults_total` | _Not yet documented_ | gauge | None
|
||||
`wmi_memory_transition_pages_repurposed_total` | _Not yet documented_ | gauge | None
|
||||
`wmi_memory_write_copies_total` | The number of page faults caused by attempting to write that were satisfied by copying the page from elsewhere in physical memory | gauge | None
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
|
||||
@@ -1,104 +0,0 @@
|
||||
# mscluster_cluster collector
|
||||
|
||||
The MSCluster_Cluster class is a dynamic WMI class that represents a cluster.
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `mscluster_cluster`
|
||||
Classes | `MSCluster_Cluster`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`AddEvictDelay` | Provides access to the cluster's AddEvictDelay property, which is the number a seconds that a new node is delayed after an eviction of another node. | gauge | `name`
|
||||
`AdminAccessPoint` | The type of the cluster administrative access point. | gauge | `name`
|
||||
`AutoAssignNodeSite` | Determines whether or not the cluster will attempt to automatically assign nodes to sites based on networks and Active Directory Site information. | gauge | `name`
|
||||
`AutoBalancerLevel` | Determines the level of aggressiveness of AutoBalancer. | gauge | `name`
|
||||
`AutoBalancerMode` | Determines whether or not the auto balancer is enabled. | gauge | `name`
|
||||
`BackupInProgress` | Indicates whether a backup is in progress. | gauge | `name`
|
||||
`BlockCacheSize` | CSV BlockCache Size in MB. | gauge | `name`
|
||||
`ClusSvcHangTimeout` | Controls how long the cluster network driver waits between Failover Cluster Service heartbeats before it determines that the Failover Cluster Service has stopped responding. | gauge | `name`
|
||||
`ClusSvcRegroupOpeningTimeout` | Controls how long a node will wait on other nodes in the opening stage before deciding that they failed. | gauge | `name`
|
||||
`ClusSvcRegroupPruningTimeout` | Controls how long the membership leader will wait to reach full connectivity between cluster nodes. | gauge | `name`
|
||||
`ClusSvcRegroupStageTimeout` | Controls how long a node will wait on other nodes in a membership stage before deciding that they failed. | gauge | `name`
|
||||
`ClusSvcRegroupTickInMilliseconds` | Controls how frequently the membership algorithm is sending periodic membership messages. | gauge | `name`
|
||||
`ClusterEnforcedAntiAffinity` | Enables or disables hard enforcement of group anti-affinity classes. | gauge | `name`
|
||||
`ClusterFunctionalLevel` | The functional level the cluster is currently running in. | gauge | `name`
|
||||
`ClusterGroupWaitDelay` | Maximum time in seconds that a group waits for its preferred node to come online during cluster startup before coming online on a different node. | gauge | `name`
|
||||
`ClusterLogLevel` | Controls the level of cluster logging. | gauge | `name`
|
||||
`ClusterLogSize` | Controls the maximum size of the cluster log files on each of the nodes. | gauge | `name`
|
||||
`ClusterUpgradeVersion` | Specifies the upgrade version the cluster is currently running in. | gauge | `name`
|
||||
`CrossSiteDelay` | Controls how long the cluster network driver waits in milliseconds between sending Cluster Service heartbeats across sites. | gauge | `name`
|
||||
`CrossSiteThreshold` | Controls how many Cluster Service heartbeats can be missed across sites before it determines that Cluster Service has stopped responding. | gauge | `name`
|
||||
`CrossSubnetDelay` | Controls how long the cluster network driver waits in milliseconds between sending Cluster Service heartbeats across subnets. | gauge | `name`
|
||||
`CrossSubnetThreshold` | Controls how many Cluster Service heartbeats can be missed across subnets before it determines that Cluster Service has stopped responding. | gauge | `name`
|
||||
`CsvBalancer` | Whether automatic balancing for CSV is enabled. | gauge | `name`
|
||||
`DatabaseReadWriteMode` | Sets the database read and write mode. | gauge | `name`
|
||||
`DefaultNetworkRole` | Provides access to the cluster's DefaultNetworkRole property. | gauge | `name`
|
||||
`DetectedCloudPlatform` | | gauge | `name`
|
||||
`DetectManagedEvents` | | gauge | `name`
|
||||
`DetectManagedEventsThreshold` | | gauge | `name`
|
||||
`DisableGroupPreferredOwnerRandomization` | | gauge | `name`
|
||||
`DrainOnShutdown` | Whether to drain the node when cluster service is being stopped. | gauge | `name`
|
||||
`DynamicQuorumEnabled` | Allows cluster service to adjust node weights as needed to increase availability. | gauge | `name`
|
||||
`EnableSharedVolumes` | Enables or disables cluster shared volumes on this cluster. | gauge | `name`
|
||||
`FixQuorum` | Provides access to the cluster's FixQuorum property, which specifies if the cluster is in a fix quorum state. | gauge | `name`
|
||||
`GracePeriodEnabled` | Whether the node grace period feature of this cluster is enabled. | gauge | `name`
|
||||
`GracePeriodTimeout` | The grace period timeout in milliseconds. | gauge | `name`
|
||||
`GroupDependencyTimeout` | The timeout after which a group will be brought online despite unsatisfied dependencies | gauge | `name`
|
||||
`HangRecoveryAction` | Controls the action to take if the user-mode processes have stopped responding. | gauge | `name`
|
||||
`IgnorePersistentStateOnStartup` | Provides access to the cluster's IgnorePersistentStateOnStartup property, which specifies whether the cluster will bring online groups that were online when the cluster was shut down. | gauge | `name`
|
||||
`LogResourceControls` | Controls the logging of resource controls. | gauge | `name`
|
||||
`LowerQuorumPriorityNodeId` | Specifies the Node ID that has a lower priority when voting for quorum is performed. If the quorum vote is split 50/50%, the specified node's vote would be ignored to break the tie. If this is not set then the cluster will pick a node at random to break the tie. | gauge | `name`
|
||||
`MaxNumberOfNodes` | Indicates the maximum number of nodes that may participate in the Cluster. | gauge | `name`
|
||||
`MessageBufferLength` | The maximum unacknowledged message count for GEM. | gauge | `name`
|
||||
`MinimumNeverPreemptPriority` | Groups with this priority or higher cannot be preempted. | gauge | `name`
|
||||
`MinimumPreemptorPriority` | Minimum priority a cluster group must have to be able to preempt another group. | gauge | `name`
|
||||
`NetftIPSecEnabled` | Whether IPSec is enabled for cluster internal traffic. | gauge | `name`
|
||||
`PlacementOptions` | Various option flags to modify default placement behavior. | gauge | `name`
|
||||
`PlumbAllCrossSubnetRoutes` | Plumbs all possible cross subnet routes to all nodes. | gauge | `name`
|
||||
`PreventQuorum` | Whether the cluster will ignore group persistent state on startup. | gauge | `name`
|
||||
`QuarantineDuration` | The quarantine period timeout in milliseconds. | gauge | `name`
|
||||
`QuarantineThreshold` | Number of node failures before it will be quarantined. | gauge | `name`
|
||||
`QuorumArbitrationTimeMax` | Controls the maximum time necessary to decide the Quorum owner node. | gauge | `name`
|
||||
`QuorumArbitrationTimeMin` | Controls the minimum time necessary to decide the Quorum owner node. | gauge | `name`
|
||||
`QuorumLogFileSize` | This property is obsolete. | gauge | `name`
|
||||
`QuorumTypeValue` | Get the current quorum type value. -1: Unknown; 1: Node; 2: FileShareWitness; 3: Storage; 4: None | gauge | `name`
|
||||
`RequestReplyTimeout` | Controls the request reply time-out period. | gauge | `name`
|
||||
`ResiliencyDefaultPeriod` | The default resiliency period, in seconds, for the cluster. | gauge | `name`
|
||||
`ResiliencyLevel` | The resiliency level for the cluster. | gauge | `name`
|
||||
`ResourceDllDeadlockPeriod` | This property is obsolete. | gauge | `name`
|
||||
`RootMemoryReserved` | Controls the amount of memory reserved for the parent partition on all cluster nodes. | gauge | `name`
|
||||
`RouteHistoryLength` | The history length for routes to help finding network issues. | gauge | `name`
|
||||
`S2DBusTypes` | Bus types for storage spaces direct. | gauge | `name`
|
||||
`S2DCacheDesiredState` | Desired state of the storage spaces direct cache. | gauge | `name`
|
||||
`S2DCacheFlashReservePercent` | Percentage of allocated flash space to utilize when caching. | gauge | `name`
|
||||
`S2DCachePageSizeKBytes` | Page size in KB used by S2D cache. | gauge | `name`
|
||||
`S2DEnabled` | Whether direct attached storage (DAS) is enabled. | gauge | `name`
|
||||
`S2DIOLatencyThreshold` | The I/O latency threshold for storage spaces direct. | gauge | `name`
|
||||
`S2DOptimizations` | Optimization flags for storage spaces direct. | gauge | `name`
|
||||
`SameSubnetDelay` | Controls how long the cluster network driver waits in milliseconds between sending Cluster Service heartbeats on the same subnet. | gauge | `name`
|
||||
`SameSubnetThreshold` | Controls how many Cluster Service heartbeats can be missed on the same subnet before it determines that Cluster Service has stopped responding. | gauge | `name`
|
||||
`SecurityLevel` | Controls the level of security that should apply to intracluster messages. 0: Clear Text; 1: Sign; 2: Encrypt | gauge | `name`
|
||||
`SecurityLevelForStorage` | | gauge | `name`
|
||||
`SharedVolumeVssWriterOperationTimeout` | CSV VSS Writer operation timeout in seconds. | gauge | `name`
|
||||
`ShutdownTimeoutInMinutes` | The maximum time in minutes allowed for cluster resources to come offline during cluster service shutdown. | gauge | `name`
|
||||
`UseClientAccessNetworksForSharedVolumes` | Whether the use of client access networks for cluster shared volumes feature of this cluster is enabled. 0: Disabled; 1: Enabled; 2: Auto | gauge | `name`
|
||||
`WitnessDatabaseWriteTimeout` | Controls the maximum time in seconds that a cluster database write to a witness can take before the write is abandoned. | gauge | `name`
|
||||
`WitnessDynamicWeight` | The weight of the configured witness. | gauge | `name`
|
||||
`WitnessRestartInterval` | Controls the witness restart interval. | gauge | `name`
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
@@ -1,32 +0,0 @@
|
||||
# mscluster_network collector
|
||||
|
||||
The MSCluster_Network class is a dynamic WMI class that represents cluster networks.
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `mscluster_network`
|
||||
Classes | `MSCluster_Network`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`Characteristics` | Provides the characteristics of the network. The cluster defines characteristics only for resources. For a description of these characteristics, see [CLUSCTL_RESOURCE_GET_CHARACTERISTICS](https://msdn.microsoft.com/library/aa367466). | gauge | `name`
|
||||
`Flags` | Provides access to the flags set for the network. The cluster defines flags only for resources. For a description of these flags, see [CLUSCTL_RESOURCE_GET_FLAGS](https://docs.microsoft.com/en-us/previous-versions/windows/desktop/mscs/clusctl-resource-get-flags). | gauge | `name`
|
||||
`Metric` | The metric of a cluster network (networks with lower values are used first). If this value is set, then the AutoMetric property is set to false. | gauge | `name`
|
||||
`Role` | Provides access to the network's Role property. The Role property describes the role of the network in the cluster. 0: None; 1: Cluster; 2: Client; 3: Both | gauge | `name`
|
||||
`State` | Provides the current state of the network. 1-1: Unknown; 0: Unavailable; 1: Down; 2: Partitioned; 3: Up | gauge | `name`
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
@@ -1,41 +0,0 @@
|
||||
# mscluster_node collector
|
||||
|
||||
The MSCluster_Node class is a dynamic WMI class that represents a cluster node.
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `mscluster_node`
|
||||
Classes | `MSCluster_Node`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`BuildNumber` | Provides access to the node's BuildNumber property. | gauge | `name`
|
||||
`Characteristics` | Provides access to the characteristics set for the node. For a list of possible characteristics, see [CLUSCTL_NODE_GET_CHARACTERISTICS](https://docs.microsoft.com/en-us/previous-versions/windows/desktop/mscs/clusctl-node-get-characteristics). | gauge | `name`
|
||||
`DetectedCloudPlatform` | The dynamic vote weight of the node adjusted by dynamic quorum feature. | gauge | `name`
|
||||
`DynamicWeight` | The dynamic vote weight of the node adjusted by dynamic quorum feature. | gauge | `name`
|
||||
`Flags` | Provides access to the flags set for the node. For a list of possible characteristics, see [CLUSCTL_NODE_GET_FLAGS](https://docs.microsoft.com/en-us/previous-versions/windows/desktop/mscs/clusctl-node-get-flags). | gauge | `name`
|
||||
`MajorVersion` | Provides access to the node's MajorVersion property, which specifies the major portion of the Windows version installed. | gauge | `name`
|
||||
`MinorVersion` | Provides access to the node's MinorVersion property, which specifies the minor portion of the Windows version installed. | gauge | `name`
|
||||
`NeedsPreventQuorum` | Whether the cluster service on that node should be started with prevent quorum flag. | gauge | `name`
|
||||
`NodeDrainStatus` | The current node drain status of a node. 0: Not Initiated; 1: In Progress; 2: Completed; 3: Failed | gauge | `name`
|
||||
`NodeHighestVersion` | Provides access to the node's NodeHighestVersion property, which specifies the highest possible version of the cluster service with which the node can join or communicate. | gauge | `name`
|
||||
`NodeLowestVersion` | Provides access to the node's NodeLowestVersion property, which specifies the lowest possible version of the cluster service with which the node can join or communicate. | gauge | `name`
|
||||
`NodeWeight` | The vote weight of the node. | gauge | `name`
|
||||
`State` | Returns the current state of a node. -1: Unknown; 0: Up; 1: Down; 2: Paused; 3: Joining | gauge | `name`
|
||||
`StatusInformation` | The isolation or quarantine status of the node. | gauge | `name`
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
@@ -1,50 +0,0 @@
|
||||
# mscluster_resource collector
|
||||
|
||||
The MSCluster_resource class is a dynamic WMI class that represents a cluster resource.
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `mscluster_resource`
|
||||
Classes | `MSCluster_Resource`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`Characteristics` | Provides the characteristics of the object. The cluster defines characteristics only for resources. For a description of these characteristics, see [CLUSCTL_RESOURCE_GET_CHARACTERISTICS](https://docs.microsoft.com/en-us/previous-versions/windows/desktop/mscs/clusctl-resource-get-characteristics). | gauge | `type`, `owner_group`, `name`
|
||||
`DeadlockTimeout` | Indicates the length of time to wait, in milliseconds, before declaring a deadlock in any call into a resource. | gauge | `type`, `owner_group`, `name`
|
||||
`EmbeddedFailureAction` | The time, in milliseconds, that a resource should remain in a failed state before the Cluster service attempts to restart it. | gauge | `type`, `owner_group`, `name`
|
||||
`Flags` | Provides access to the flags set for the object. The cluster defines flags only for resources. For a description of these flags, see [CLUSCTL_RESOURCE_GET_FLAGS](https://docs.microsoft.com/en-us/previous-versions/windows/desktop/mscs/clusctl-resource-get-flags). | gauge | `type`, `owner_group`, `name`
|
||||
`IsAlivePollInterval` | Provides access to the resource's IsAlivePollInterval property, which is the recommended interval in milliseconds at which the Cluster Service should poll the resource to determine whether it is operational. If the property is set to 0xFFFFFFFF, the Cluster Service uses the IsAlivePollInterval property for the resource type associated with the resource. | gauge | `type`, `owner_group`, `name`
|
||||
`LooksAlivePollInterval` | Provides access to the resource's LooksAlivePollInterval property, which is the recommended interval in milliseconds at which the Cluster Service should poll the resource to determine whether it appears operational. If the property is set to 0xFFFFFFFF, the Cluster Service uses the LooksAlivePollInterval property for the resource type associated with the resource. | gauge | `type`, `owner_group`, `name`
|
||||
`MonitorProcessId` | Provides the process ID of the resource host service that is currently hosting the resource. | gauge | `type`, `owner_group`, `name`
|
||||
`OwnerNode` | The node hosting the resource. | gauge | `type`, `owner_group`, `node_name`, `name`
|
||||
`PendingTimeout` | Provides access to the resource's PendingTimeout property. If a resource cannot be brought online or taken offline in the number of milliseconds specified by the PendingTimeout property, the resource is forcibly terminated. | gauge | `type`, `owner_group`, `name`
|
||||
`ResourceClass` | Gets or sets the resource class of a resource. 0: Unknown; 1: Storage; 2: Network; 32768: Unknown | gauge | `type`, `owner_group`, `name`
|
||||
`RestartAction` | Provides access to the resource's RestartAction property, which is the action to be taken by the Cluster Service if the resource fails. | gauge | `type`, `owner_group`, `name`
|
||||
`RestartDelay` | Indicates the time delay before a failed resource is restarted. | gauge | `type`, `owner_group`, `name`
|
||||
`RestartPeriod` | Provides access to the resource's RestartPeriod property, which is interval of time, in milliseconds, during which a specified number of restart attempts can be made on a nonresponsive resource. | gauge | `type`, `owner_group`, `name`
|
||||
`RestartThreshold` | Provides access to the resource's RestartThreshold property which is the maximum number of restart attempts that can be made on a resource within an interval defined by the RestartPeriod property before the Cluster Service initiates the action specified by the RestartAction property. | gauge | `type`, `owner_group`, `name`
|
||||
`RetryPeriodOnFailure` | Provides access to the resource's RetryPeriodOnFailure property, which is the interval of time (in milliseconds) that a resource should remain in a failed state before the Cluster service attempts to restart it. | gauge | `type`, `owner_group`, `name`
|
||||
`State` | The current state of the resource. -1: Unknown; 0: Inherited; 1: Initializing; 2: Online; 3: Offline; 4: Failed; 128: Pending; 129: Online Pending; 130: Offline Pending | gauge | `type`, `owner_group`, `name`
|
||||
`Subclass` | Provides the list of references to nodes that can be the owner of this resource. | gauge | `type`, `owner_group`, `name`
|
||||
|
||||
### Example metric
|
||||
Query the state of all cluster resource owned by node1
|
||||
```
|
||||
windows_mscluster_resource_owner_node{node_name="node1"}
|
||||
```
|
||||
|
||||
## Useful queries
|
||||
Counts the number of Network Name cluster resource
|
||||
```
|
||||
count(windows_mscluster_resource_state{type="Network Name"})
|
||||
```
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
@@ -1,48 +0,0 @@
|
||||
# mscluster_resourcegroup collector
|
||||
|
||||
The MSCluster_ResourceGroup class is a dynamic WMI class that represents a cluster group.
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `mscluster_resourcegroup`
|
||||
Classes | `MSCluster_ResourceGroup`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`AutoFailbackType` | Provides access to the group's AutoFailbackType property. | gauge | `name`
|
||||
`Characteristics` | Provides the characteristics of the group. The cluster defines characteristics only for resources. For a description of these characteristics, see [CLUSCTL_RESOURCE_GET_CHARACTERISTICS](https://docs.microsoft.com/en-us/previous-versions/windows/desktop/mscs/clusctl-resource-get-characteristics). | gauge | `name`
|
||||
`ColdStartSetting` | Indicates whether a group can start after a cluster cold start. | gauge | `name`
|
||||
`DefaultOwner` | Number of the last node the resource group was activated on or explicitly moved to. | gauge | `name`
|
||||
`FailbackWindowEnd` | The FailbackWindowEnd property provides the latest time that the group can be moved back to the node identified as its preferred node. | gauge | `name`
|
||||
`FailbackWindowStart` | The FailbackWindowStart property provides the earliest time (that is, local time as kept by the cluster) that the group can be moved back to the node identified as its preferred node. | gauge | `name`
|
||||
`FailoverPeriod` | The FailoverPeriod property specifies a number of hours during which a maximum number of failover attempts, specified by the FailoverThreshold property, can occur. | gauge | `name`
|
||||
`FailoverThreshold` | The FailoverThreshold property specifies the maximum number of failover attempts. | gauge | `name`
|
||||
`Flags` | Provides access to the flags set for the group. The cluster defines flags only for resources. For a description of these flags, see [CLUSCTL_RESOURCE_GET_FLAGS](https://docs.microsoft.com/en-us/previous-versions/windows/desktop/mscs/clusctl-resource-get-flags). | gauge | `name`
|
||||
`GroupType` | The Type of the resource group. | gauge | `name`
|
||||
`OwnerNode` | The node hosting the resource group. | gauge | `node_name`, `name`
|
||||
`Priority` | Priority value of the resource group | gauge | `name`
|
||||
`ResiliencyPeriod` | The resiliency period for this group, in seconds. | gauge | `name`
|
||||
`State` | The current state of the resource group. -1: Unknown; 0: Online; 1: Offline; 2: Failed; 3: Partial Online; 4: Pending | gauge | `name`
|
||||
`UpdateDomain` | | gauge | `name`
|
||||
|
||||
### Example metric
|
||||
Query the state of all cluster group owned by node1
|
||||
```
|
||||
windows_mscluster_resourcegroup_owner_node{node_name="node1"}
|
||||
```
|
||||
|
||||
## Useful queries
|
||||
Counts the number of cluster group by type
|
||||
```
|
||||
count_values("count", windows_mscluster_resourcegroup_group_type)
|
||||
```
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
@@ -1,33 +1,33 @@
|
||||
# msmq collector
|
||||
|
||||
The msmq collector exposes metrics about the queues on a MSMQ server
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `msmq`
|
||||
Classes | `Win32_PerfRawData_MSMQ_MSMQQueue`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
### `--collector.msmq.msmq-where`
|
||||
|
||||
A WMI filter on which queues to include. `%` is a wildcard, and can be used to match on substrings.
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_msmq_bytes_in_journal_queue` | Size of queue journal in bytes | gauge | `name`
|
||||
`windows_msmq_bytes_in_queue` | Size of queue in bytes | gauge | `name`
|
||||
`windows_msmq_messages_in_journal_queue` | Count messages in queue journal | gauge | `name`
|
||||
`windows_msmq_messages_in_queue` | Count messages in queue | gauge | `name`
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
# msmq collector
|
||||
|
||||
The msmq collector exposes metrics about the queues on a MSMQ server
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `msmq`
|
||||
Classes | `Win32_PerfRawData_MSMQ_MSMQQueue`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
### `--collector.msmq.msmq-where`
|
||||
|
||||
A WMI filter on which queues to include. `%` is a wildcard, and can be used to match on substrings.
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`wmi_msmq_bytes_in_journal_queue` | Size of queue journal in bytes | gauge | `name`
|
||||
`wmi_msmq_bytes_in_queue` | Size of queue in bytes | gauge | `name`
|
||||
`wmi_msmq_messages_in_journal_queue` | Count messages in queue journal | gauge | `name`
|
||||
`wmi_msmq_messages_in_queue` | Count messages in queue | gauge | `name`
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
|
||||
@@ -1,314 +1,275 @@
|
||||
# mssql collector
|
||||
|
||||
The mssql collector exposes metrics about the MSSQL server
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `mssql`
|
||||
Classes | [`Win32_PerfRawData_MSSQLSERVER_SQLServerAccessMethods`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-access-methods-object)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerAvailabilityReplica`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-availability-replica)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerBufferManager`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-buffer-manager-object)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerDatabaseReplica`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-database-replica)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerDatabases`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-databases-object?view=sql-server-2017)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerGeneralStatistics`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-general-statistics-object)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerLocks`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-locks-object)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerMemoryManager`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-memory-manager-object)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerSQLStatistics`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-sql-statistics-object)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerSQLErrors`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-sql-errors-object)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerTransactions`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-transactions-object)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerWaitStatistics`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-wait-statistics-object)
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
### `--collectors.mssql.classes-enabled`
|
||||
|
||||
Comma-separated list of MSSQL WMI classes to use. Supported values are `accessmethods`, `availreplica`, `bufman`, `databases`, `dbreplica`, `genstats`, `locks`, `memmgr`, `sqlstats`, `sqlerrors`, `transactions`, and `waitstats`.
|
||||
|
||||
### `--collectors.mssql.class-print`
|
||||
|
||||
If true, print available mssql WMI classes and exit. Only displays if the mssql collector is enabled.
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_mssql_collector_duration_seconds` | The time taken for each sub-collector to return | gauge | `collector`, `mssql_instance`
|
||||
`windows_mssql_collector_success` | 1 if sub-collector succeeded, 0 otherwise | gauge | `collector`, `mssql_instance`
|
||||
`windows_mssql_accessmethods_au_batch_cleanups` | The total number of batches that were completed successfully by the background task that cleans up deferred dropped allocation units | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_au_cleanups` | The total number of allocation units that were successfully dropped the background task that cleans up deferred dropped allocation units. Each allocation unit drop requires multiple batches | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_by_reference_lob_creates` | The total count of large object (lob) values that were passed by reference. By-reference lobs are used in certain bulk operations to avoid the cost of passing them by value | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_by_reference_lob_uses` | The total count of by-reference lob values that were used. By-reference lobs are used in certain bulk operations to avoid the cost of passing them by-value | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_lob_read_aheads` | The total count of lob pages on which readahead was issued | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_column_value_pulls` | The total count of column values that were pulled in-row from off-row | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_column_value_pushes` | The total count of column values that were pushed from in-row to off-row | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_deferred_dropped_aus` | The total number of allocation units waiting to be dropped by the background task that cleans up deferred dropped allocation units | gauge | `mssql_instance`
|
||||
`windows_mssql_accessmethods_deferred_dropped_rowsets` | The number of rowsets created as a result of aborted online index build operations that are waiting to be dropped by the background task that cleans up deferred dropped rowsets | gauge | `mssql_instance`
|
||||
`windows_mssql_accessmethods_dropped_rowset_cleanups` | The number of rowsets per second created as a result of aborted online index build operations that were successfully dropped by the background task that cleans up deferred dropped rowsets | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_dropped_rowset_skips` | The number of rowsets per second created as a result of aborted online index build operations that were skipped by the background task that cleans up deferred dropped rowsets created | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_extent_deallocations` | Number of extents deallocated per second in all databases in this instance of SQL Server | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_extent_allocations` | Number of extents allocated per second in all databases in this instance of SQL Server | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_au_batch_cleanup_failures` | The number of batches per second that failed and required retry, by the background task that cleans up deferred dropped allocation units. Failure could be due to lack of memory or disk space, hardware failure and other reasons | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_leaf_page_cookie_failures` | The number of times that a leaf page cookie could not be used during an index search since changes happened on the leaf page. The cookie is used to speed up index search | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_tree_page_cookie_failures` | The number of times that a tree page cookie could not be used during an index search since changes happened on the parent pages of those tree pages. The cookie is used to speed up index search | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_forwarded_records` | Number of records per second fetched through forwarded record pointers | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_free_space_page_fetches` | Number of pages fetched per second by free space scans. These scans search for free space within pages already allocated to an allocation unit, to satisfy requests to insert or modify record fragments | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_free_space_scans` | Number of scans per second that were initiated to search for free space within pages already allocated to an allocation unit to insert or modify record fragment. Each scan may find multiple pages | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_full_scans` | Number of unrestricted full scans per second. These can be either base-table or full-index scans | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_index_searches` | Number of index searches per second. These are used to start a range scan, reposition a range scan, revalidate a scan point, fetch a single index record, and search down the index to locate where to insert a new row | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_insysxact_waits` | Number of times a reader needs to wait for a page because the InSysXact bit is set | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_lob_handle_creates` | Count of temporary lobs created | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_lob_handle_destroys` | Count of temporary lobs destroyed | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_lob_ss_provider_creates` | Count of LOB Storage Service Providers (LobSSP) created. One worktable created per LobSSP | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_lob_ss_provider_destroys` | Count of LobSSP destroyed | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_lob_ss_provider_truncations` | Count of LobSSP truncated | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_mixed_page_allocations` | Number of pages allocated per second from mixed extents. These could be used for storing the IAM pages and the first eight pages that are allocated to an allocation unit | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_page_compression_attempts` | Number of pages evaluated for page-level compression. Includes pages that were not compressed because significant savings could be achieved. Includes all objects in the instance of SQL Server | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_page_deallocations` | Number of pages deallocated per second in all databases in this instance of SQL Server. These include pages from mixed extents and uniform extents | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_page_allocations` | Number of pages allocated per second in all databases in this instance of SQL Server. These include pages allocations from both mixed extents and uniform extents | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_page_compressions` | Number of data pages that are compressed by using PAGE compression. Includes all objects in the instance of SQL Server | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_page_splits` | Number of page splits per second that occur as the result of overflowing index pages | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_probe_scans` | Number of probe scans per second that are used to find at most one single qualified row in an index or base table directly | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_range_scans` | Number of qualified range scans through indexes per second | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_scan_point_revalidations` | Number of times per second that the scan point had to be revalidated to continue the scan | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_ghost_record_skips` | Number of ghosted records per second skipped during scans | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_table_lock_escalations` | Number of times locks on a table were escalated to the TABLE or HoBT granularity | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_leaf_page_cookie_uses` | Number of times a leaf page cookie is used successfully during an index search since no change happened on the leaf page. The cookie is used to speed up index search | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_tree_page_cookie_uses` | Number of times a tree page cookie is used successfully during an index search since no change happened on the parent page of the tree page. The cookie is used to speed up index search | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_workfile_creates` | Number of work files created per second. For example, work files could be used to store temporary results for hash joins and hash aggregates | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_worktables_creates` | Number of work tables created per second. For example, work tables could be used to store temporary results for query spool, lob variables, XML variables, and cursors | counter | `mssql_instance`
|
||||
`windows_mssql_accessmethods_worktables_from_cache_ratio` | Percentage of work tables created where the initial two pages of the work table were not allocated but were immediately available from the work table cache | counter | `mssql_instance`
|
||||
`windows_mssql_availreplica_received_from_replica_bytes` | Number of bytes received from the availability replica per second. Pings and status updates will generate network traffic even on databases with no user updates | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_availreplica_sent_to_replica_bytes` | Number of bytes sent to the remote availability replica per second. On the primary replica this is the number of bytes sent to the secondary replica. On the secondary replica this is the number of bytes sent to the primary replica | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_availreplica_sent_to_transport_bytes` | Actual number of bytes sent per second over the network to the remote availability replica. On the primary replica this is the number of bytes sent to the secondary replica. On the secondary replica this is the number of bytes sent to the primary replica | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_availreplica_initiated_flow_controls` | Time in milliseconds that log stream messages waited for send flow control, in the last second | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_availreplica_flow_control_wait_seconds` | Number of times flow-control initiated in the last second. Flow Control Time (ms/sec) divided by Flow Control/sec is the average time per wait | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_availreplica_receives_from_replica` | Number of Always On messages received from thereplica per second | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_availreplica_resent_messages` | Number of Always On messages resent in the last second | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_availreplica_sends_to_replica` | Number of Always On messages sent to this availability replica per second | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_availreplica_sends_to_transport` | Actual number of Always On messages sent per second over the network to the remote availability replica | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_bufman_background_writer_pages` | Number of pages flushed to enforce the recovery interval settings | counter | `mssql_instance`
|
||||
`windows_mssql_bufman_buffer_cache_hit_ratio` | Indicates the percentage of pages found in the buffer cache without having to read from disk. The ratio is the total number of cache hits divided by the total number of cache lookups over the last few thousand page accesses | gauge | `mssql_instance`
|
||||
`windows_mssql_bufman_checkpoint_pages` | Indicates the number of pages flushed to disk per second by a checkpoint or other operation that require all dirty pages to be flushed | counter | `mssql_instance`
|
||||
`windows_mssql_bufman_database_pages` | Indicates the number of pages in the buffer pool with database content | gauge | `mssql_instance`
|
||||
`windows_mssql_bufman_extension_allocated_pages` | Total number of non-free cache pages in the buffer pool extension file | gauge | `mssql_instance`
|
||||
`windows_mssql_bufman_extension_free_pages` | Total number of free cache pages in the buffer pool extension file | gauge | `mssql_instance`
|
||||
`windows_mssql_bufman_extension_in_use_as_percentage` | _Not yet documented_ | gauge | `mssql_instance`
|
||||
`windows_mssql_bufman_extension_outstanding_io` | Percentage of the buffer pool extension paging file occupied by buffer manager pages | gauge | `mssql_instance`
|
||||
`windows_mssql_bufman_extension_page_evictions` | Number of pages evicted from the buffer pool extension file per second | counter | `mssql_instance`
|
||||
`windows_mssql_bufman_extension_page_reads` | Number of pages read from the buffer pool extension file per second | counter | `mssql_instance`
|
||||
`windows_mssql_bufman_extension_page_unreferenced_seconds` | Average seconds a page will stay in the buffer pool extension without references to it | gauge | `mssql_instance`
|
||||
`windows_mssql_bufman_extension_page_writes` | Number of pages written to the buffer pool extension file per second | counter | `mssql_instance`
|
||||
`windows_mssql_bufman_free_list_stalls` | Indicates the number of requests per second that had to wait for a free page | counter | `mssql_instance`
|
||||
`windows_mssql_bufman_integral_controller_slope` | The slope that integral controller for the buffer pool last used, times -10 billion | gauge | `mssql_instance`
|
||||
`windows_mssql_bufman_lazywrites` | Indicates the number of buffers written per second by the buffer manager's lazy writer | counter | `mssql_instance`
|
||||
`windows_mssql_bufman_page_life_expectancy_seconds` | Indicates the number of seconds a page will stay in the buffer pool without references | gauge | `mssql_instance`
|
||||
`windows_mssql_bufman_page_lookups` | Indicates the number of requests per second to find a page in the buffer pool | counter | `mssql_instance`
|
||||
`windows_mssql_bufman_page_reads` | Indicates the number of physical database page reads that are issued per second | counter | `mssql_instance`
|
||||
`windows_mssql_bufman_page_writes` | Indicates the number of physical database page writes that are issued per second | counter | `mssql_instance`
|
||||
`windows_mssql_bufman_read_ahead_pages` | Indicates the number of pages read per second in anticipation of use | counter | `mssql_instance`
|
||||
`windows_mssql_bufman_read_ahead_issuing_seconds` | Time (microseconds) spent issuing readahead | counter | `mssql_instance`
|
||||
`windows_mssql_bufman_target_pages` | Ideal number of pages in the buffer pool | gauge | `mssql_instance`
|
||||
`windows_mssql_dbreplica_database_flow_control_wait_seconds` | _Not yet documented_ | gauge | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_database_initiated_flow_controls` | _Not yet documented_ | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_received_file_bytes` | _Not yet documented_ | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_group_commits` | _Not yet documented_ | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_group_commit_stall_seconds` | _Not yet documented_ | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_log_apply_pending_queue` | _Not yet documented_ | gauge | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_log_apply_ready_queue` | _Not yet documented_ | gauge | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_log_compressed_bytes` | _Not yet documented_ | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_log_decompressed_bytes` | _Not yet documented_ | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_log_received_bytes` | _Not yet documented_ | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_log_compression_cachehits` | _Not yet documented_ | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_log_compression_cachemisses` | _Not yet documented_ | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_log_compressions` | _Not yet documented_ | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_log_decompressions` | _Not yet documented_ | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_log_remaining_for_undo` | The amount of log, in bytes, remaining to complete the undo phase | gauge | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_log_send_queue` | Amount of log records in the log files of the primary database, in kilobytes, that haven't been sent to the secondary replica | gauge | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_mirrored_write_transactions` | Number of transactions that were written to the primary database and then waited to commit until the log was sent to the secondary database, in the last second | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_recovery_queue_records` | Amount of log records in the log files of the secondary replica that have not been redone | gauge | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_redo_blocks` | Number of times the redo thread was blocked on locks held by readers of the database | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_redo_remaining_bytes` | The amount of log, in kilobytes, remaining to be redone to finish the reverting phase | gauge | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_redone_bytes` | Amount of log records redone on the secondary database in the last second | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_redones` | _Not yet documented_ | counter | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_total_log_requiring_undo` | Total kilobytes of log that must be undone | gauge | `mssql_instance`, `replica`
|
||||
`windows_mssql_dbreplica_transaction_delay_seconds` | Delay in waiting for unterminated commit acknowledgment for all the current transactions | gauge | `mssql_instance`, `replica`
|
||||
`windows_mssql_databases_active_transactions` | Number of active transactions for the database | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_backup_restore_operations` | Read/write throughput for backup and restore operations of a database per second | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_bulk_copy_rows` | Number of rows bulk copied per second | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_bulk_copy_bytes` | Amount of data bulk copied (in kilobytes) per second | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_commit_table_entries` | he size (row count) of the in-memory portion of the commit table for the database | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_data_files_size_bytes` | Cumulative size (in kilobytes) of all the data files in the database including any automatic growth. Monitoring this counter is useful, for example, for determining the correct size of tempdb | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_dbcc_logical_scan_bytes` | Number of logical read scan bytes per second for database console commands (DBCC) | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_group_commit_stall_seconds` | Group stall time (microseconds) per second | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_flushed_bytes` | Total number of log bytes flushed | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_cache_hit_ratio` | Percentage of log cache reads satisfied from the log cache | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_cache_reads` | Reads performed per second through the log manager cache | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_files_size_bytes` | Cumulative size (in kilobytes) of all the transaction log files in the database | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_files_used_size_bytes` | The cumulative used size of all the log files in the database | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_flushes` | Total wait time (in milliseconds) to flush the log. On an Always On secondary database, this value indicates the wait time for log records to be hardened to disk | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_flush_waits` | Number of commits per second waiting for the log flush | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_flush_wait_seconds` | Number of commits per second waiting for the log flush | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_flush_write_seconds` | Time in milliseconds for performing writes of log flushes that were completed in the last second | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_growths` | Total number of times the transaction log for the database has been expanded | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_pool_cache_misses` | Number of requests for which the log block was not available in the log pool | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_pool_disk_reads` | Number of disk reads that the log pool issued to fetch log blocks | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_pool_hash_deletes` | Rate of raw hash entry deletes from the Log Pool | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_pool_hash_inserts` | Rate of raw hash entry inserts into the Log Pool | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_pool_invalid_hash_entries` | Rate of hash lookups failing due to being invalid | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_pool_log_scan_pushes` | Rate of Log block pushes by log scans, which may come from disk or memory | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_pool_log_writer_pushes` | Rate of Log block pushes by log writer thread | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_pool_empty_free_pool_pushes` | Rate of Log block push fails due to empty free pool | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_pool_low_memory_pushes` | Rate of Log block push fails due to being low on memory | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_pool_no_free_buffer_pushes` | Rate of Log block push fails due to free buffer unavailable | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_pool_req_behind_trunc` | Log pool cache misses due to block requested being behind truncation LSN | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_pool_requests_old_vlf` | Log Pool requests that were not in the last VLF of the log | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_pool_requests` | The number of log-block requests processed by the log pool | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_pool_total_active_log_bytes` | Current total active log stored in the shared cache buffer manager in bytes | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_pool_total_shared_pool_bytes` | Current total memory usage of the shared cache buffer manager in bytes | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_shrinks` | Total number of log shrinks for this database | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_truncations` | The number of times the transaction log has been truncated (in Simple Recovery Model) | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_log_used_percent` | Percentage of space in the log that is in use | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_pending_repl_transactions` | Number of transactions in the transaction log of the publication database marked for replication, but not yet delivered to the distribution database | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_repl_transactions` | Number of transactions per second read out of the transaction log of the publication database and delivered to the distribution database | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_shrink_data_movement_bytes` | Amount of data being moved per second by autoshrink operations, or DBCC SHRINKDATABASE or DBCC SHRINKFILE statements | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_tracked_transactions` | Number of committed transactions recorded in the commit table for the database | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_transactions` | Number of transactions started for the database per second | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_write_transactions` | Number of transactions that wrote to the database and committed, in the last second | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_xtp_controller_dlc_fetch_latency_seconds` | Average latency in microseconds between log blocks entering the Direct Log Consumer and being retrieved by the XTP controller, per second | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_xtp_controller_dlc_peak_latency_seconds` | The largest recorded latency, in microseconds, of a fetch from the Direct Log Consumer by the XTP controller | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_xtp_controller_log_processed_bytes` | The amount of log bytes processed by the XTP controller thread, per second | counter | `mssql_instance`, `database`
|
||||
`windows_mssql_databases_xtp_memory_used_bytes` | The amount of memory used by XTP in the database | gauge | `mssql_instance`, `database`
|
||||
`windows_mssql_genstats_active_temp_tables` | Number of temporary tables/table variables in use | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_connection_resets` | Total number of logins started from the connection pool | counter | `mssql_instance`
|
||||
`windows_mssql_genstats_event_notifications_delayed_drop` | Number of event notifications waiting to be dropped by a system thread | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_http_authenticated_requests` | Number of authenticated HTTP requests started per second | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_logical_connections` | Number of logical connections to the system | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_logins` | Total number of logins started per second. This does not include pooled connections | counter | `mssql_instance`
|
||||
`windows_mssql_genstats_logouts` | Total number of logout operations started per second | counter | `mssql_instance`
|
||||
`windows_mssql_genstats_mars_deadlocks` | Number of MARS deadlocks detected | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_non_atomic_yields` | Number of non-atomic yields per second | counter | `mssql_instance`
|
||||
`windows_mssql_genstats_blocked_processes` | Number of currently blocked processes | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_soap_empty_requests` | Number of empty SOAP requests started per second | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_soap_method_invocations` | Number of SOAP method invocations started per second | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_soap_session_initiate_requests` | Number of SOAP Session initiate requests started per second | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_soap_session_terminate_requests` | Number of SOAP Session terminate requests started per second | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_soapsql_requests` | Number of SOAP SQL requests started per second | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_soapwsdl_requests` | Number of SOAP Web Service Description Language requests started per second | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_sql_trace_io_provider_lock_waits` | Number of waits for the File IO Provider lock per second | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_tempdb_recovery_unit_ids_generated` | Number of duplicate tempdb recovery unit id generated | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_tempdb_rowset_ids_generated` | Number of duplicate tempdb rowset id generated | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_temp_tables_creations` | Number of temporary tables/table variables created per second | counter | `mssql_instance`
|
||||
`windows_mssql_genstats_temp_tables_awaiting_destruction` | Number of temporary tables/table variables waiting to be destroyed by the cleanup system thread | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_trace_event_notification_queue_size` | Number of trace event notification instances waiting in the internal queue to be sent through Service Broker | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_transactions` | Number of transaction enlistments (local, DTC, bound all combined) | gauge | `mssql_instance`
|
||||
`windows_mssql_genstats_user_connections` | Counts the number of users currently connected to SQL Server | gauge | `mssql_instance`
|
||||
`windows_mssql_locks_average_wait_seconds` | Average amount of wait time (in milliseconds) for each lock request that resulted in a wait | gauge | `mssql_instance`, `resource`
|
||||
`windows_mssql_locks_lock_requests` | Number of new locks and lock conversions per second requested from the lock manager | counter | `mssql_instance`, `resource`
|
||||
`windows_mssql_locks_lock_timeouts` | Number of lock requests per second that timed out, including requests for NOWAIT locks | counter | `mssql_instance`, `resource`
|
||||
`windows_mssql_locks_lock_timeouts_excluding_NOWAIT` | Number of lock requests per second that timed out, but excluding requests for NOWAIT locks | counter | `mssql_instance`, `resource`
|
||||
`windows_mssql_locks_lock_waits` | Total wait time (in milliseconds) for locks in the last second | counter | `mssql_instance`, `resource`
|
||||
`windows_mssql_locks_lock_wait_seconds` | Number of lock requests per second that required the caller to wait | gauge | `mssql_instance`, `resource`
|
||||
`windows_mssql_locks_deadlocks` | Number of lock requests per second that resulted in a deadlock | counter | `mssql_instance`, `resource`
|
||||
`windows_mssql_memmgr_connection_memory_bytes` | Specifies the total amount of dynamic memory the server is using for maintaining connections | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_database_cache_memory_bytes` | Specifies the amount of memory the server is currently using for the database pages cache | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_external_benefit_of_memory` | An internal estimation of the performance benefit from adding memory to a specific cache | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_free_memory_bytes` | Specifies the amount of committed memory currently not used by the server | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_granted_workspace_memory_bytes` | Specifies the total amount of memory currently granted to executing processes, such as hash, sort, bulk copy, and index creation operations | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_lock_blocks` | Specifies the current number of lock blocks in use on the server (refreshed periodically). A lock block represents an individual locked resource, such as a table, page, or row | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_allocated_lock_blocks` | Specifies the current number of allocated lock blocks. At server startup, the number of allocated lock blocks plus the number of allocated lock owner blocks depends on the SQL Server Locks configuration option. If more lock blocks are needed, the value increases | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_lock_memory_bytes` | Specifies the total amount of dynamic memory the server is using for locks | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_lock_owner_blocks` | Specifies the current number of allocated lock owner blocks. At server startup, the number of allocated lock owner blocks and the number of allocated lock blocks depend on the SQL Server Locks configuration option. If more lock owner blocks are needed, the value increases dynamically | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_allocated_lock_owner_blocks` | _Not yet documented_ | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_log_pool_memory_bytes` | Total amount of dynamic memory the server is using for Log Pool | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_maximum_workspace_memory_bytes` | Indicates the maximum amount of memory available for executing processes, such as hash, sort, bulk copy, and index creation operations | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_outstanding_memory_grants` | Specifies the total number of processes that have successfully acquired a workspace memory grant | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_pending_memory_grants` | Specifies the total number of processes waiting for a workspace memory grant | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_optimizer_memory_bytes` | Specifies the total amount of dynamic memory the server is using for query optimization | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_reserved_server_memory_bytes` | ndicates the amount of memory the server has reserved for future usage. This counter shows the current unused amount of memory initially granted that is shown in Granted Workspace Memory | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_sql_cache_memory_bytes` | Specifies the total amount of dynamic memory the server is using for the dynamic SQL cache | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_stolen_server_memory_bytes` | Specifies the amount of memory the server is using for purposes other than database pages | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_target_server_memory_bytes` | Indicates the ideal amount of memory the server can consume | gauge | `mssql_instance`
|
||||
`windows_mssql_memmgr_total_server_memory_bytes` | Specifies the amount of memory the server has committed using the memory manager | gauge | `mssql_instance`
|
||||
`windows_mssql_sqlstats_auto_parameterization_attempts` | Number of failed auto-parameterization attempts per second. This should be small. Note that auto-parameterizations are also known as simple parameterizations in later versions of SQL Server | counter | `mssql_instance`
|
||||
`windows_mssql_sqlstats_batch_requests` | _Not yet documented_ | counter | `mssql_instance`
|
||||
`windows_mssql_sqlstats_failed_auto_parameterization_attempts` | _Not yet documented_ | counter | `mssql_instance`
|
||||
`windows_mssql_sqlstats_forced_parameterizations` | Number of successful forced parameterizations per second | counter | `mssql_instance`
|
||||
`windows_mssql_sqlstats_guided_plan_executions` | Number of plan executions per second in which the query plan has been generated by using a plan guide | counter | `mssql_instance`
|
||||
`windows_mssql_sqlstats_misguided_plan_executions` | Number of plan executions per second in which a plan guide could not be honored during plan generation | counter | `mssql_instance`
|
||||
`windows_mssql_sqlstats_safe_auto_parameterization_attempts` | Number of safe auto-parameterization attempts per second | counter | `mssql_instance`
|
||||
`windows_mssql_sqlstats_sql_attentions` | Number of attentions per second | counter | `mssql_instance`
|
||||
`windows_mssql_sqlstats_sql_compilations` | Number of SQL compilations per second | counter | `mssql_instance`
|
||||
`windows_mssql_sqlstats_sql_recompilations` | Number of statement recompiles per second | counter | `mssql_instance`
|
||||
`windows_mssql_sqlstats_unsafe_auto_parameterization_attempts` | Number of unsafe auto-parameterization attempts per second. | counter | `mssql_instance`
|
||||
`windows_mssql_sql_errors_total` | Information for all errors | counter | `mssql_instance`, `resource`
|
||||
`windows_mssql_transactions_tempdb_free_space_bytes` | The amount of space (in kilobytes) available in tempdb | gauge | `mssql_instance`
|
||||
`windows_mssql_transactions_longest_transaction_running_seconds` | The length of time (in seconds) since the start of the transaction that has been active longer than any other current transaction | gauge | `mssql_instance`
|
||||
`windows_mssql_transactions_nonsnapshot_version_active_total` | The number of currently active transactions that are not using snapshot isolation level and have made data modifications that have generated row versions in the tempdb version store | counter | `mssql_instance`
|
||||
`windows_mssql_transactions_snapshot_active_total` | The number of currently active transactions using the snapshot isolation level | counter | `mssql_instance`
|
||||
`windows_mssql_transactions_active` | The number of currently active transactions of all types | gauge | `mssql_instance`
|
||||
`windows_mssql_transactions_update_conflicts_total` | The percentage of those transactions using the snapshot isolation level that have encountered update conflicts within the last second | counter | `mssql_instance`
|
||||
`windows_mssql_transactions_update_snapshot_active_total` | The number of currently active transactions using the snapshot isolation level and have modified data | counter | `mssql_instance`
|
||||
`windows_mssql_transactions_version_cleanup_rate_bytes` | The rate (in kilobytes per second) at which row versions are removed from the snapshot isolation version store in tempdb | gauge | `mssql_instance`
|
||||
`windows_mssql_transactions_version_generation_rate_bytes` | The rate (in kilobytes per second) at which new row versions are added to the snapshot isolation version store in tempdb | gauge | `mssql_instance`
|
||||
`windows_mssql_transactions_version_store_size_bytes` | he amount of space (in kilobytes) in tempdb being used to store snapshot isolation level row versions | gauge | `mssql_instance`
|
||||
`windows_mssql_transactions_version_store_units` | The number of active allocation units in the snapshot isolation version store in tempdb | counter | `mssql_instance`
|
||||
`windows_mssql_transactions_version_store_creation_units` | The number of allocation units that have been created in the snapshot isolation store since the instance of the Database Engine was started | counter | `mssql_instance`
|
||||
`windows_mssql_transactions_version_store_truncation_units` | The number of allocation units that have been removed from the snapshot isolation store since the instance of the Database Engine was started | counter | `mssql_instance`
|
||||
`windows_mssql_waitstats_lock_waits` | Statistics for processes waiting on a lock | gauge | `mssql_instance`, `item`
|
||||
`windows_mssql_waitstats_memory_grant_queue_waits` | Statistics for processes waiting for memory grant to become available | gauge | `mssql_instance`, `item`
|
||||
`windows_mssql_waitstats_thread_safe_memory_objects_waits` | Statistics for processes waiting on thread-safe memory allocators | gauge | `mssql_instance`, `item`
|
||||
`windows_mssql_waitstats_log_write_waits` | Statistics for processes waiting for log buffer to be written | gauge | `mssql_instance`, `item`
|
||||
`windows_mssql_waitstats_log_buffer_waits` | Statistics for processes waiting for log buffer to be available | gauge | `mssql_instance`, `item`
|
||||
`windows_mssql_waitstats_network_io_waits` | Statistics relevant to wait on network I/O | gauge | `mssql_instance`, `item`
|
||||
`windows_mssql_waitstats_page_io_latch_waits` | Statistics relevant to page I/O latches | gauge | `mssql_instance`, `item`
|
||||
`windows_mssql_waitstats_page_latch_waits` | Statistics relevant to page latches, not including I/O latches | gauge | `mssql_instance`, `item`
|
||||
`windows_mssql_waitstats_nonpage_latch_waits` | Statistics relevant to non-page latches | gauge | `mssql_instance`, `item`
|
||||
`windows_mssql_waitstats_wait_for_the_worker_waits` | Statistics relevant to processes waiting for worker to become available | gauge | `mssql_instance`, `item`
|
||||
`windows_mssql_waitstats_workspace_synchronization_waits` | Statistics relevant to processes synchronizing access to workspace | gauge | `mssql_instance`, `item`
|
||||
`windows_mssql_waitstats_transaction_ownership_waits` | Statistics relevant to processes synchronizing access to transaction | gauge | `mssql_instance`, `item`
|
||||
|
||||
### Example metric
|
||||
|
||||
Query Full table scans
|
||||
|
||||
```
|
||||
rate(windows_mssql_accessmethods_full_scans{instance='host:9182'}[$__rate_interval])
|
||||
|
||||
```
|
||||
## Useful queries
|
||||
|
||||
### Database file size
|
||||
This collector retrieves the two values (data file and log file) and sums the total in PromQL to give the Database file size.
|
||||
|
||||
```
|
||||
windows_mssql_databases_data_files_size_bytes{database='DatabaseName',instance='host:9182'} + windows_mssql_databases_log_files_size_bytes{database='DatabaseName',instance='host:9182'}
|
||||
|
||||
```
|
||||
|
||||
### Buffer Cache Hit Ratio
|
||||
|
||||
When you read the counter in perfmon you will get the the percentage pages found in the buffer cache. This percentage is calculated internally based on the total number of cache hits divided by the total number of cache lookups over the last few thousand page accesses.
|
||||
This collector retrieves the two internal values separately. In order to calculate the Buffer Cache Hit Ratio in PromQL.
|
||||
|
||||
```
|
||||
windows_mssql_bufman_buffer_cache_hits{instance="host:9182", mssql_instance="MSSQLSERVER"} /
|
||||
windows_mssql_bufman_buffer_cache_lookups{instance="host:9182", mssql_instance="MSSQLSERVER"}
|
||||
```
|
||||
|
||||
This principal can be used for following metrics too:
|
||||
- AccessMethodsWorktablesFromCacheHitRatio
|
||||
- accessmethods_worktables_from_cache_hits
|
||||
- accessmethods_worktables_from_cache_lookups
|
||||
- LogCacheHitRatio
|
||||
- databases_log_cache_hits
|
||||
- databases_log_cache_lookups
|
||||
- AverageLockWaitTime
|
||||
- locks_wait_time_seconds
|
||||
- locks_count
|
||||
|
||||
## Alerting examples
|
||||
|
||||
```
|
||||
groups:
|
||||
- name: database_alerts
|
||||
rules:
|
||||
- alert: DatabaseSizeExceeded
|
||||
expr: windows_mssql_databases_data_files_size_bytes{database='DatabaseName',instance='host:9182'} + windows_mssql_databases_log_files_size_bytes{database='DatabaseName',instance='host:9182'} > 1e10 # 10 GB in bytes
|
||||
for: 5m # Trigger the alert if the condition persists for 5 mins
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "SQl EXpress Database size exceeded 10GB"
|
||||
description: "The database size has grown larger than 10GB. Instance: {{ $labels.instance }}"
|
||||
|
||||
```
|
||||
# mssql collector
|
||||
|
||||
The mssql collector exposes metrics about the MSSQL server
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `mssql`
|
||||
Classes | [`Win32_PerfRawData_MSSQLSERVER_SQLServerAccessMethods`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-access-methods-object)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerAvailabilityReplica`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-availability-replica)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerBufferManager`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-buffer-manager-object)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerDatabaseReplica`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-database-replica)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerDatabases`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-databases-object?view=sql-server-2017)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerGeneralStatistics`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-general-statistics-object)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerLocks`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-locks-object)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerMemoryManager`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-memory-manager-object)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerSQLStatistics`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-sql-statistics-object)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerSQLErrors`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-sql-errors-object)<br/>[`Win32_PerfRawData_MSSQLSERVER_SQLServerTransactions`](https://docs.microsoft.com/en-us/sql/relational-databases/performance-monitor/sql-server-transactions-object)
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
### `--collectors.mssql.classes-enabled`
|
||||
|
||||
Comma-separated list of MSSQL WMI classes to use. Supported values are `accessmethods`, `availreplica`, `bufman`, `databases`, `dbreplica`, `genstats`, `locks`, `memmgr`, `sqlstats`, `sqlerrors` and `transactions`.
|
||||
|
||||
### `--collectors.mssql.class-print`
|
||||
|
||||
If true, print available mssql WMI classes and exit. Only displays if the mssql collector is enabled.
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`wmi_mssql_collector_duration_seconds` | The time taken for each sub-collector to return | counter | `collector`, `instance`
|
||||
`wmi_mssql_collector_success` | 1 if sub-collector succeeded, 0 otherwise | counter | `collector`, `instance`
|
||||
`wmi_mssql_accessmethods_au_batch_cleanups` | The total number of batches that were completed successfully by the background task that cleans up deferred dropped allocation units | counter | `instance`
|
||||
`wmi_mssql_accessmethods_au_cleanups` | The total number of allocation units that were successfully dropped the background task that cleans up deferred dropped allocation units. Each allocation unit drop requires multiple batches | counter | `instance`
|
||||
`wmi_mssql_accessmethods_by_reference_lob_creates` | The total count of large object (lob) values that were passed by reference. By-reference lobs are used in certain bulk operations to avoid the cost of passing them by value | counter | `instance`
|
||||
`wmi_mssql_accessmethods_by_reference_lob_uses` | The total count of by-reference lob values that were used. By-reference lobs are used in certain bulk operations to avoid the cost of passing them by-value | counter | `instance`
|
||||
`wmi_mssql_accessmethods_lob_read_aheads` | The total count of lob pages on which readahead was issued | counter | `instance`
|
||||
`wmi_mssql_accessmethods_column_value_pulls` | The total count of column values that were pulled in-row from off-row | counter | `instance`
|
||||
`wmi_mssql_accessmethods_column_value_pushes` | The total count of column values that were pushed from in-row to off-row | counter | `instance`
|
||||
`wmi_mssql_accessmethods_deferred_dropped_aus` | The total number of allocation units waiting to be dropped by the background task that cleans up deferred dropped allocation units | counter | `instance`
|
||||
`wmi_mssql_accessmethods_deferred_dropped_rowsets` | The number of rowsets created as a result of aborted online index build operations that are waiting to be dropped by the background task that cleans up deferred dropped rowsets | counter | `instance`
|
||||
`wmi_mssql_accessmethods_dropped_rowset_cleanups` | The number of rowsets per second created as a result of aborted online index build operations that were successfully dropped by the background task that cleans up deferred dropped rowsets | counter | `instance`
|
||||
`wmi_mssql_accessmethods_dropped_rowset_skips` | The number of rowsets per second created as a result of aborted online index build operations that were skipped by the background task that cleans up deferred dropped rowsets created | counter | `instance`
|
||||
`wmi_mssql_accessmethods_extent_deallocations` | Number of extents deallocated per second in all databases in this instance of SQL Server | counter | `instance`
|
||||
`wmi_mssql_accessmethods_extent_allocations` | Number of extents allocated per second in all databases in this instance of SQL Server | counter | `instance`
|
||||
`wmi_mssql_accessmethods_au_batch_cleanup_failures` | The number of batches per second that failed and required retry, by the background task that cleans up deferred dropped allocation units. Failure could be due to lack of memory or disk space, hardware failure and other reasons | counter | `instance`
|
||||
`wmi_mssql_accessmethods_leaf_page_cookie_failures` | The number of times that a leaf page cookie could not be used during an index search since changes happened on the leaf page. The cookie is used to speed up index search | counter | `instance`
|
||||
`wmi_mssql_accessmethods_tree_page_cookie_failures` | The number of times that a tree page cookie could not be used during an index search since changes happened on the parent pages of those tree pages. The cookie is used to speed up index search | counter | `instance`
|
||||
`wmi_mssql_accessmethods_forwarded_records` | Number of records per second fetched through forwarded record pointers | counter | `instance`
|
||||
`wmi_mssql_accessmethods_free_space_page_fetches` | Number of pages fetched per second by free space scans. These scans search for free space within pages already allocated to an allocation unit, to satisfy requests to insert or modify record fragments | counter | `instance`
|
||||
`wmi_mssql_accessmethods_free_space_scans` | Number of scans per second that were initiated to search for free space within pages already allocated to an allocation unit to insert or modify record fragment. Each scan may find multiple pages | counter | `instance`
|
||||
`wmi_mssql_accessmethods_full_scans` | Number of unrestricted full scans per second. These can be either base-table or full-index scans | counter | `instance`
|
||||
`wmi_mssql_accessmethods_index_searches` | Number of index searches per second. These are used to start a range scan, reposition a range scan, revalidate a scan point, fetch a single index record, and search down the index to locate where to insert a new row | counter | `instance`
|
||||
`wmi_mssql_accessmethods_insysxact_waits` | Number of times a reader needs to wait for a page because the InSysXact bit is set | counter | `instance`
|
||||
`wmi_mssql_accessmethods_lob_handle_creates` | Count of temporary lobs created | counter | `instance`
|
||||
`wmi_mssql_accessmethods_lob_handle_destroys` | Count of temporary lobs destroyed | counter | `instance`
|
||||
`wmi_mssql_accessmethods_lob_ss_provider_creates` | Count of LOB Storage Service Providers (LobSSP) created. One worktable created per LobSSP | counter | `instance`
|
||||
`wmi_mssql_accessmethods_lob_ss_provider_destroys` | Count of LobSSP destroyed | counter | `instance`
|
||||
`wmi_mssql_accessmethods_lob_ss_provider_truncations` | Count of LobSSP truncated | counter | `instance`
|
||||
`wmi_mssql_accessmethods_mixed_page_allocations` | Number of pages allocated per second from mixed extents. These could be used for storing the IAM pages and the first eight pages that are allocated to an allocation unit | counter | `instance`
|
||||
`wmi_mssql_accessmethods_page_compression_attempts` | Number of pages evaluated for page-level compression. Includes pages that were not compressed because significant savings could be achieved. Includes all objects in the instance of SQL Server | counter | `instance`
|
||||
`wmi_mssql_accessmethods_page_deallocations` | Number of pages deallocated per second in all databases in this instance of SQL Server. These include pages from mixed extents and uniform extents | counter | `instance`
|
||||
`wmi_mssql_accessmethods_page_allocations` | Number of pages allocated per second in all databases in this instance of SQL Server. These include pages allocations from both mixed extents and uniform extents | counter | `instance`
|
||||
`wmi_mssql_accessmethods_page_compressions` | Number of data pages that are compressed by using PAGE compression. Includes all objects in the instance of SQL Server | counter | `instance`
|
||||
`wmi_mssql_accessmethods_page_splits` | Number of page splits per second that occur as the result of overflowing index pages | counter | `instance`
|
||||
`wmi_mssql_accessmethods_probe_scans` | Number of probe scans per second that are used to find at most one single qualified row in an index or base table directly | counter | `instance`
|
||||
`wmi_mssql_accessmethods_range_scans` | Number of qualified range scans through indexes per second | counter | `instance`
|
||||
`wmi_mssql_accessmethods_scan_point_revalidations` | Number of times per second that the scan point had to be revalidated to continue the scan | counter | `instance`
|
||||
`wmi_mssql_accessmethods_ghost_record_skips` | Number of ghosted records per second skipped during scans | counter | `instance`
|
||||
`wmi_mssql_accessmethods_table_lock_escalations` | Number of times locks on a table were escalated to the TABLE or HoBT granularity | counter | `instance`
|
||||
`wmi_mssql_accessmethods_leaf_page_cookie_uses` | Number of times a leaf page cookie is used successfully during an index search since no change happened on the leaf page. The cookie is used to speed up index search | counter | `instance`
|
||||
`wmi_mssql_accessmethods_tree_page_cookie_uses` | Number of times a tree page cookie is used successfully during an index search since no change happened on the parent page of the tree page. The cookie is used to speed up index search | counter | `instance`
|
||||
`wmi_mssql_accessmethods_workfile_creates` | Number of work files created per second. For example, work files could be used to store temporary results for hash joins and hash aggregates | counter | `instance`
|
||||
`wmi_mssql_accessmethods_worktables_creates` | Number of work tables created per second. For example, work tables could be used to store temporary results for query spool, lob variables, XML variables, and cursors | counter | `instance`
|
||||
`wmi_mssql_accessmethods_worktables_from_cache_ratio` | Percentage of work tables created where the initial two pages of the work table were not allocated but were immediately available from the work table cache | counter | `instance`
|
||||
`wmi_mssql_availreplica_received_from_replica_bytes` | Number of bytes received from the availability replica per second. Pings and status updates will generate network traffic even on databases with no user updates | counter | `instance`, `replica`
|
||||
`wmi_mssql_availreplica_sent_to_replica_bytes` | Number of bytes sent to the remote availability replica per second. On the primary replica this is the number of bytes sent to the secondary replica. On the secondary replica this is the number of bytes sent to the primary replica | counter | `instance`, `replica`
|
||||
`wmi_mssql_availreplica_sent_to_transport_bytes` | Actual number of bytes sent per second over the network to the remote availability replica. On the primary replica this is the number of bytes sent to the secondary replica. On the secondary replica this is the number of bytes sent to the primary replica | counter | `instance`, `replica`
|
||||
`wmi_mssql_availreplica_initiated_flow_controls` | Time in milliseconds that log stream messages waited for send flow control, in the last second | counter | `instance`, `replica`
|
||||
`wmi_mssql_availreplica_flow_control_wait_seconds` | Number of times flow-control initiated in the last second. Flow Control Time (ms/sec) divided by Flow Control/sec is the average time per wait | counter | `instance`, `replica`
|
||||
`wmi_mssql_availreplica_receives_from_replica` | Number of Always On messages received from thereplica per second | counter | `instance`, `replica`
|
||||
`wmi_mssql_availreplica_resent_messages` | Number of Always On messages resent in the last second | counter | `instance`, `replica`
|
||||
`wmi_mssql_availreplica_sends_to_replica` | Number of Always On messages sent to this availability replica per second | counter | `instance`, `replica`
|
||||
`wmi_mssql_availreplica_sends_to_transport` | Actual number of Always On messages sent per second over the network to the remote availability replica | counter | `instance`, `replica`
|
||||
`wmi_mssql_bufman_background_writer_pages` | Number of pages flushed to enforce the recovery interval settings | counter | `instance`
|
||||
`wmi_mssql_bufman_buffer_cache_hit_ratio` | Indicates the percentage of pages found in the buffer cache without having to read from disk. The ratio is the total number of cache hits divided by the total number of cache lookups over the last few thousand page accesses | counter | `instance`
|
||||
`wmi_mssql_bufman_checkpoint_pages` | Indicates the number of pages flushed to disk per second by a checkpoint or other operation that require all dirty pages to be flushed | counter | `instance`
|
||||
`wmi_mssql_bufman_database_pages` | Indicates the number of pages in the buffer pool with database content | counter | `instance`
|
||||
`wmi_mssql_bufman_extension_allocated_pages` | Total number of non-free cache pages in the buffer pool extension file | counter | `instance`
|
||||
`wmi_mssql_bufman_extension_free_pages` | Total number of free cache pages in the buffer pool extension file | counter | `instance`
|
||||
`wmi_mssql_bufman_extension_in_use_as_percentage` | _Not yet documented_ | counter | `instance`
|
||||
`wmi_mssql_bufman_extension_outstanding_io` | Percentage of the buffer pool extension paging file occupied by buffer manager pages | counter | `instance`
|
||||
`wmi_mssql_bufman_extension_page_evictions` | Number of pages evicted from the buffer pool extension file per second | counter | `instance`
|
||||
`wmi_mssql_bufman_extension_page_reads` | Number of pages read from the buffer pool extension file per second | counter | `instance`
|
||||
`wmi_mssql_bufman_extension_page_unreferenced_seconds` | Average seconds a page will stay in the buffer pool extension without references to it | counter | `instance`
|
||||
`wmi_mssql_bufman_extension_page_writes` | Number of pages written to the buffer pool extension file per second | counter | `instance`
|
||||
`wmi_mssql_bufman_free_list_stalls` | Indicates the number of requests per second that had to wait for a free page | counter | `instance`
|
||||
`wmi_mssql_bufman_integral_controller_slope` | The slope that integral controller for the buffer pool last used, times -10 billion | counter | `instance`
|
||||
`wmi_mssql_bufman_lazywrites` | Indicates the number of buffers written per second by the buffer manager's lazy writer | counter | `instance`
|
||||
`wmi_mssql_bufman_page_life_expectancy_seconds` | Indicates the number of seconds a page will stay in the buffer pool without references | counter | `instance`
|
||||
`wmi_mssql_bufman_page_lookups` | Indicates the number of requests per second to find a page in the buffer pool | counter | `instance`
|
||||
`wmi_mssql_bufman_page_reads` | Indicates the number of physical database page reads that are issued per second | counter | `instance`
|
||||
`wmi_mssql_bufman_page_writes` | Indicates the number of physical database page writes that are issued per second | counter | `instance`
|
||||
`wmi_mssql_bufman_read_ahead_pages` | Indicates the number of pages read per second in anticipation of use | counter | `instance`
|
||||
`wmi_mssql_bufman_read_ahead_issuing_seconds` | Time (microseconds) spent issuing readahead | counter | `instance`
|
||||
`wmi_mssql_bufman_target_pages` | Ideal number of pages in the buffer pool | counter | `instance`
|
||||
`wmi_mssql_dbreplica_database_flow_control_wait_seconds` | _Not yet documented_ | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_database_initiated_flow_controls` | _Not yet documented_ | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_received_file_bytes` | _Not yet documented_ | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_group_commits` | _Not yet documented_ | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_group_commit_stall_seconds` | _Not yet documented_ | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_log_apply_pending_queue` | _Not yet documented_ | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_log_apply_ready_queue` | _Not yet documented_ | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_log_compressed_bytes` | _Not yet documented_ | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_log_decompressed_bytes` | _Not yet documented_ | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_log_received_bytes` | _Not yet documented_ | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_log_compression_cachehits` | _Not yet documented_ | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_log_compression_cachemisses` | _Not yet documented_ | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_log_compressions` | _Not yet documented_ | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_log_decompressions` | _Not yet documented_ | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_log_remaining_for_undo` | The amount of log, in bytes, remaining to complete the undo phase | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_log_send_queue` | Amount of log records in the log files of the primary database, in kilobytes, that haven't been sent to the secondary replica | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_mirrored_write_transactions` | Number of transactions that were written to the primary database and then waited to commit until the log was sent to the secondary database, in the last second | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_recovery_queue_records` | Amount of log records in the log files of the secondary replica that have not been redone | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_redo_blocks` | Number of times the redo thread was blocked on locks held by readers of the database | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_redo_remaining_bytes` | The amount of log, in kilobytes, remaining to be redone to finish the reverting phase | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_redone_bytes` | Amount of log records redone on the secondary database in the last second | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_redones` | _Not yet documented_ | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_total_log_requiring_undo` | Total kilobytes of log that must be undone | counter | `instance`, `replica`
|
||||
`wmi_mssql_dbreplica_transaction_delay_seconds` | Delay in waiting for unterminated commit acknowledgment for all the current transactions | counter | `instance`, `replica`
|
||||
`wmi_mssql_databases_active_transactions` | Number of active transactions for the database | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_backup_restore_operations` | Read/write throughput for backup and restore operations of a database per second | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_bulk_copy_rows` | Number of rows bulk copied per second | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_bulk_copy_bytes` | Amount of data bulk copied (in kilobytes) per second | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_commit_table_entries` | he size (row count) of the in-memory portion of the commit table for the database | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_data_files_size_bytes` | Cumulative size (in kilobytes) of all the data files in the database including any automatic growth. Monitoring this counter is useful, for example, for determining the correct size of tempdb | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_dbcc_logical_scan_bytes` | Number of logical read scan bytes per second for database console commands (DBCC) | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_group_commit_stall_seconds` | Group stall time (microseconds) per second | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_flushed_bytes` | Total number of log bytes flushed | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_cache_hit_ratio` | Percentage of log cache reads satisfied from the log cache | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_cache_reads` | Reads performed per second through the log manager cache | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_files_size_bytes` | Cumulative size (in kilobytes) of all the transaction log files in the database | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_files_used_size_bytes` | The cumulative used size of all the log files in the database | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_flushes` | Total wait time (in milliseconds) to flush the log. On an Always On secondary database, this value indicates the wait time for log records to be hardened to disk | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_flush_waits` | Number of commits per second waiting for the log flush | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_flush_wait_seconds` | Number of commits per second waiting for the log flush | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_flush_write_seconds` | Time in milliseconds for performing writes of log flushes that were completed in the last second | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_growths` | Total number of times the transaction log for the database has been expanded | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_pool_cache_misses` | Number of requests for which the log block was not available in the log pool | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_pool_disk_reads` | Number of disk reads that the log pool issued to fetch log blocks | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_pool_hash_deletes` | Rate of raw hash entry deletes from the Log Pool | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_pool_hash_inserts` | Rate of raw hash entry inserts into the Log Pool | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_pool_invalid_hash_entries` | Rate of hash lookups failing due to being invalid | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_pool_log_scan_pushes` | Rate of Log block pushes by log scans, which may come from disk or memory | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_pool_log_writer_pushes` | Rate of Log block pushes by log writer thread | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_pool_empty_free_pool_pushes` | Rate of Log block push fails due to empty free pool | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_pool_low_memory_pushes` | Rate of Log block push fails due to being low on memory | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_pool_no_free_buffer_pushes` | Rate of Log block push fails due to free buffer unavailable | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_pool_req_behind_trunc` | Log pool cache misses due to block requested being behind truncation LSN | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_pool_requests_old_vlf` | Log Pool requests that were not in the last VLF of the log | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_pool_requests` | The number of log-block requests processed by the log pool | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_pool_total_active_log_bytes` | Current total active log stored in the shared cache buffer manager in bytes | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_pool_total_shared_pool_bytes` | Current total memory usage of the shared cache buffer manager in bytes | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_shrinks` | Total number of log shrinks for this database | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_truncations` | The number of times the transaction log has been truncated (in Simple Recovery Model) | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_log_used_percent` | Percentage of space in the log that is in use | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_pending_repl_transactions` | Number of transactions in the transaction log of the publication database marked for replication, but not yet delivered to the distribution database | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_repl_transactions` | Number of transactions per second read out of the transaction log of the publication database and delivered to the distribution database | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_shrink_data_movement_bytes` | Amount of data being moved per second by autoshrink operations, or DBCC SHRINKDATABASE or DBCC SHRINKFILE statements | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_tracked_transactions` | Number of committed transactions recorded in the commit table for the database | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_transactions` | Number of transactions started for the database per second | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_write_transactions` | Number of transactions that wrote to the database and committed, in the last second | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_xtp_controller_dlc_fetch_latency_seconds` | Average latency in microseconds between log blocks entering the Direct Log Consumer and being retrieved by the XTP controller, per second | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_xtp_controller_dlc_peak_latency_seconds` | The largest recorded latency, in microseconds, of a fetch from the Direct Log Consumer by the XTP controller | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_xtp_controller_log_processed_bytes` | The amount of log bytes processed by the XTP controller thread, per second | counter | `instance`, `database`
|
||||
`wmi_mssql_databases_xtp_memory_used_bytes` | The amount of memory used by XTP in the database | counter | `instance`, `database`
|
||||
`wmi_mssql_genstats_active_temp_tables` | Number of temporary tables/table variables in use | counter | `instance`
|
||||
`wmi_mssql_genstats_connection_resets` | Total number of logins started from the connection pool | counter | `instance`
|
||||
`wmi_mssql_genstats_event_notifications_delayed_drop` | Number of event notifications waiting to be dropped by a system thread | counter | `instance`
|
||||
`wmi_mssql_genstats_http_authenticated_requests` | Number of authenticated HTTP requests started per second | counter | `instance`
|
||||
`wmi_mssql_genstats_logical_connections` | Number of logical connections to the system | counter | `instance`
|
||||
`wmi_mssql_genstats_logins` | Total number of logins started per second. This does not include pooled connections | counter | `instance`
|
||||
`wmi_mssql_genstats_logouts` | Total number of logout operations started per second | counter | `instance`
|
||||
`wmi_mssql_genstats_mars_deadlocks` | Number of MARS deadlocks detected | counter | `instance`
|
||||
`wmi_mssql_genstats_non_atomic_yields` | Number of non-atomic yields per second | counter | `instance`
|
||||
`wmi_mssql_genstats_blocked_processes` | Number of currently blocked processes | counter | `instance`
|
||||
`wmi_mssql_genstats_soap_empty_requests` | Number of empty SOAP requests started per second | counter | `instance`
|
||||
`wmi_mssql_genstats_soap_method_invocations` | Number of SOAP method invocations started per second | counter | `instance`
|
||||
`wmi_mssql_genstats_soap_session_initiate_requests` | Number of SOAP Session initiate requests started per second | counter | `instance`
|
||||
`wmi_mssql_genstats_soap_session_terminate_requests` | Number of SOAP Session terminate requests started per second | counter | `instance`
|
||||
`wmi_mssql_genstats_soapsql_requests` | Number of SOAP SQL requests started per second | counter | `instance`
|
||||
`wmi_mssql_genstats_soapwsdl_requests` | Number of SOAP Web Service Description Language requests started per second | counter | `instance`
|
||||
`wmi_mssql_genstats_sql_trace_io_provider_lock_waits` | Number of waits for the File IO Provider lock per second | counter | `instance`
|
||||
`wmi_mssql_genstats_tempdb_recovery_unit_ids_generated` | Number of duplicate tempdb recovery unit id generated | counter | `instance`
|
||||
`wmi_mssql_genstats_tempdb_rowset_ids_generated` | Number of duplicate tempdb rowset id generated | counter | `instance`
|
||||
`wmi_mssql_genstats_temp_tables_creations` | Number of temporary tables/table variables created per second | counter | `instance`
|
||||
`wmi_mssql_genstats_temp_tables_awaiting_destruction` | Number of temporary tables/table variables waiting to be destroyed by the cleanup system thread | counter | `instance`
|
||||
`wmi_mssql_genstats_trace_event_notification_queue_size` | Number of trace event notification instances waiting in the internal queue to be sent through Service Broker | counter | `instance`
|
||||
`wmi_mssql_genstats_transactions` | Number of transaction enlistments (local, DTC, bound all combined) | counter | `instance`
|
||||
`wmi_mssql_genstats_user_connections` | Counts the number of users currently connected to SQL Server | counter | `instance`
|
||||
`wmi_mssql_locks_average_wait_seconds` | Average amount of wait time (in milliseconds) for each lock request that resulted in a wait | counter | `instance`, `resource`
|
||||
`wmi_mssql_locks_lock_requests` | Number of new locks and lock conversions per second requested from the lock manager | counter | `instance`, `resource`
|
||||
`wmi_mssql_locks_lock_timeouts` | Number of lock requests per second that timed out, but excluding requests for NOWAIT locks | counter | `instance`, `resource`
|
||||
`wmi_mssql_locks_lock_timeouts_excluding_NOWAIT` | Number of lock requests per second that timed out, including requests for NOWAIT locks | counter | `instance`, `resource`
|
||||
`wmi_mssql_locks_lock_waits` | Total wait time (in milliseconds) for locks in the last second | counter | `instance`, `resource`
|
||||
`wmi_mssql_locks_lock_wait_seconds` | Number of lock requests per second that required the caller to wait | counter | `instance`, `resource`
|
||||
`wmi_mssql_locks_deadlocks` | Number of lock requests per second that resulted in a deadlock | counter | `instance`, `resource`
|
||||
`wmi_mssql_memmgr_connection_memory_bytes` | Specifies the total amount of dynamic memory the server is using for maintaining connections | counter | `instance`
|
||||
`wmi_mssql_memmgr_database_cache_memory_bytes` | Specifies the amount of memory the server is currently using for the database pages cache | counter | `instance`
|
||||
`wmi_mssql_memmgr_external_benefit_of_memory` | An internal estimation of the performance benefit from adding memory to a specific cache | counter | `instance`
|
||||
`wmi_mssql_memmgr_free_memory_bytes` | Specifies the amount of committed memory currently not used by the server | counter | `instance`
|
||||
`wmi_mssql_memmgr_granted_workspace_memory_bytes` | Specifies the total amount of memory currently granted to executing processes, such as hash, sort, bulk copy, and index creation operations | counter | `instance`
|
||||
`wmi_mssql_memmgr_lock_blocks` | Specifies the current number of lock blocks in use on the server (refreshed periodically). A lock block represents an individual locked resource, such as a table, page, or row | counter | `instance`
|
||||
`wmi_mssql_memmgr_allocated_lock_blocks` | Specifies the current number of allocated lock blocks. At server startup, the number of allocated lock blocks plus the number of allocated lock owner blocks depends on the SQL Server Locks configuration option. If more lock blocks are needed, the value increases | counter | `instance`
|
||||
`wmi_mssql_memmgr_lock_memory_bytes` | Specifies the total amount of dynamic memory the server is using for locks | counter | `instance`
|
||||
`wmi_mssql_memmgr_lock_owner_blocks` | Specifies the current number of allocated lock owner blocks. At server startup, the number of allocated lock owner blocks and the number of allocated lock blocks depend on the SQL Server Locks configuration option. If more lock owner blocks are needed, the value increases dynamically | counter | `instance`
|
||||
`wmi_mssql_memmgr_allocated_lock_owner_blocks` | _Not yet documented_ | counter | `instance`
|
||||
`wmi_mssql_memmgr_log_pool_memory_bytes` | Total amount of dynamic memory the server is using for Log Pool | counter | `instance`
|
||||
`wmi_mssql_memmgr_maximum_workspace_memory_bytes` | Indicates the maximum amount of memory available for executing processes, such as hash, sort, bulk copy, and index creation operations | counter | `instance`
|
||||
`wmi_mssql_memmgr_outstanding_memory_grants` | Specifies the total number of processes that have successfully acquired a workspace memory grant | counter | `instance`
|
||||
`wmi_mssql_memmgr_pending_memory_grants` | Specifies the total number of processes waiting for a workspace memory grant | counter | `instance`
|
||||
`wmi_mssql_memmgr_optimizer_memory_bytes` | Specifies the total amount of dynamic memory the server is using for query optimization | counter | `instance`
|
||||
`wmi_mssql_memmgr_reserved_server_memory_bytes` | ndicates the amount of memory the server has reserved for future usage. This counter shows the current unused amount of memory initially granted that is shown in Granted Workspace Memory | counter | `instance`
|
||||
`wmi_mssql_memmgr_sql_cache_memory_bytes` | Specifies the total amount of dynamic memory the server is using for the dynamic SQL cache | counter | `instance`
|
||||
`wmi_mssql_memmgr_stolen_server_memory_bytes` | Specifies the amount of memory the server is using for purposes other than database pages | counter | `instance`
|
||||
`wmi_mssql_memmgr_target_server_memory_bytes` | Indicates the ideal amount of memory the server can consume | counter | `instance`
|
||||
`wmi_mssql_memmgr_total_server_memory_bytes` | Specifies the amount of memory the server has committed using the memory manager | counter | `instance`
|
||||
`wmi_mssql_sqlstats_auto_parameterization_attempts` | Number of failed auto-parameterization attempts per second. This should be small. Note that auto-parameterizations are also known as simple parameterizations in later versions of SQL Server | counter | `instance`
|
||||
`wmi_mssql_sqlstats_batch_requests` | _Not yet documented_ | counter | `instance`
|
||||
`wmi_mssql_sqlstats_failed_auto_parameterization_attempts` | _Not yet documented_ | counter | `instance`
|
||||
`wmi_mssql_sqlstats_forced_parameterizations` | Number of successful forced parameterizations per second | counter | `instance`
|
||||
`wmi_mssql_sqlstats_guided_plan_executions` | Number of plan executions per second in which the query plan has been generated by using a plan guide | counter | `instance`
|
||||
`wmi_mssql_sqlstats_misguided_plan_executions` | Number of plan executions per second in which a plan guide could not be honored during plan generation | counter | `instance`
|
||||
`wmi_mssql_sqlstats_safe_auto_parameterization_attempts` | Number of safe auto-parameterization attempts per second | counter | `instance`
|
||||
`wmi_mssql_sqlstats_sql_attentions` | Number of attentions per second | counter | `instance`
|
||||
`wmi_mssql_sqlstats_sql_compilations` | Number of SQL compilations per second | counter | `instance`
|
||||
`wmi_mssql_sqlstats_sql_recompilations` | Number of statement recompiles per second | counter | `instance`
|
||||
`wmi_mssql_sqlstats_unsafe_auto_parameterization_attempts` | Number of unsafe auto-parameterization attempts per second. | counter | `instance`
|
||||
`wmi_mssql_sql_errors_total` | Information for all errors | counter | `instance`, `resource`
|
||||
`wmi_mssql_transactions_tempdb_free_space_bytes` | The amount of space (in kilobytes) available in tempdb | gauge | `instance`
|
||||
`wmi_mssql_transactions_longest_transaction_running_seconds` | The length of time (in seconds) since the start of the transaction that has been active longer than any other current transaction | gauge | `instance`
|
||||
`wmi_mssql_transactions_nonsnapshot_version_active_total` | The number of currently active transactions that are not using snapshot isolation level and have made data modifications that have generated row versions in the tempdb version store | counter | `instance`
|
||||
`wmi_mssql_transactions_snapshot_active_total` | The number of currently active transactions using the snapshot isolation level | counter | `instance`
|
||||
`wmi_mssql_transactions_active_total` | The number of currently active transactions of all types | counter | `instance`
|
||||
`wmi_mssql_transactions_update_conflicts_total` | The percentage of those transactions using the snapshot isolation level that have encountered update conflicts within the last second | counter | `instance`
|
||||
`wmi_mssql_transactions_update_snapshot_active_total` | The number of currently active transactions using the snapshot isolation level and have modified data | counter | `instance`
|
||||
`wmi_mssql_transactions_version_cleanup_rate_bytes` | The rate (in kilobytes per second) at which row versions are removed from the snapshot isolation version store in tempdb | gauge | `instance`
|
||||
`wmi_mssql_transactions_version_generation_rate_bytes` | The rate (in kilobytes per second) at which new row versions are added to the snapshot isolation version store in tempdb | gauge | `instance`
|
||||
`wmi_mssql_transactions_version_store_size_bytes` | he amount of space (in kilobytes) in tempdb being used to store snapshot isolation level row versions | gauge | `instance`
|
||||
`wmi_mssql_transactions_version_store_units` | The number of active allocation units in the snapshot isolation version store in tempdb | counter | `instance`
|
||||
`wmi_mssql_transactions_version_store_creation_units` | The number of allocation units that have been created in the snapshot isolation store since the instance of the Database Engine was started | counter | `instance`
|
||||
`wmi_mssql_transactions_version_store_truncation_units` | The number of allocation units that have been removed from the snapshot isolation store since the instance of the Database Engine was started | counter | `instance`
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
|
||||
### Buffer Cache Hit Ratio
|
||||
|
||||
When you read the counter in perfmon you will get the the percentage pages found in the buffer cache. This percentage is calculated internally based on the total number of cache hits divided by the total number of cache lookups over the last few thousand page accesses.
|
||||
This collector retrieves the two internal values separately. In order to calculate the Buffer Cache Hit Ratio in PromQL.
|
||||
|
||||
```
|
||||
wmi_mssql_bufman_buffer_cache_hits{instance="host:9182", exported_instance="MSSQLSERVER"} /
|
||||
wmi_mssql_bufman_buffer_cache_lookups{instance="host:9182", exported_instance="MSSQLSERVER"}
|
||||
```
|
||||
|
||||
This principal can be used for following metrics too:
|
||||
- AccessMethodsWorktablesFromCacheHitRatio
|
||||
- accessmethods_worktables_from_cache_hits
|
||||
- accessmethods_worktables_from_cache_lookups
|
||||
- LogCacheHitRatio
|
||||
- databases_log_cache_hits
|
||||
- databases_log_cache_lookups
|
||||
- AverageLockWaitTime
|
||||
- locks_wait_time_seconds
|
||||
- locks_count
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
|
||||
@@ -1,63 +1,62 @@
|
||||
# net collector
|
||||
|
||||
The net collector exposes metrics about network interfaces
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `net`
|
||||
Data source | Perflib
|
||||
Classes | [`Win32_PerfRawData_Tcpip_NetworkInterface`](https://technet.microsoft.com/en-us/security/aa394340(v=vs.80))
|
||||
Enabled by default? | Yes
|
||||
|
||||
## Flags
|
||||
|
||||
### `--collector.net.nic-include`
|
||||
|
||||
If given, an interface name needs to match the include regexp in order for the corresponding metrics to be reported
|
||||
|
||||
### `--collector.net.nic-exclude`
|
||||
|
||||
If given, an interface name needs to *not* match the exclude regexp in order for the corresponding metrics to be reported
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_net_bytes_received_total` | Total bytes received by interface | counter | `nic`
|
||||
`windows_net_bytes_sent_total` | Total bytes transmitted by interface | counter | `nic`
|
||||
`windows_net_bytes_total` | Total bytes received and transmitted by interface | counter | `nic`
|
||||
`windows_net_output_queue_length_packets` | Length of the output packet queue (in packets). If this is longer than 2, delays occur. | gauge | `nic`
|
||||
`windows_net_packets_outbound_discarded_total` | Total outbound packets that were chosen to be discarded even though no errors had been detected to prevent transmission | counter | `nic`
|
||||
`windows_net_packets_outbound_errors_total` | Total packets that could not be transmitted due to errors | counter | `nic`
|
||||
`windows_net_packets_received_discarded_total` | Total inbound packets that were chosen to be discarded even though no errors had been detected to prevent delivery | counter | `nic`
|
||||
`windows_net_packets_received_errors_total` | Total packets that could not be received due to errors | counter | `nic`
|
||||
`windows_net_packets_received_total` | Total packets received by interface | counter | `nic`
|
||||
`windows_net_packets_received_unknown_total` | Total packets received by interface that were discarded because of an unknown or unsupported protocol | counter | `nic`
|
||||
`windows_net_packets_total` | Total packets received and transmitted by interface | counter | `nic`
|
||||
`windows_net_packets_sent_total` | Total packets transmitted by interface | counter | `nic`
|
||||
`windows_net_current_bandwidth_bytes` | Estimate of the interface's current bandwidth in bytes per second | gauge | `nic`
|
||||
|
||||
### Example metric
|
||||
Query the rate of transmitted network traffic
|
||||
```
|
||||
rate(windows_net_bytes_sent_total{instance="localhost"}[2m])
|
||||
```
|
||||
|
||||
## Useful queries
|
||||
Get total utilisation of network interface as a percentage
|
||||
```
|
||||
rate(windows_net_bytes_total{instance="localhost", nic="Microsoft_Hyper_V_Network_Adapter__1"}[2m]) / windows_net_current_bandwidth_bytes{instance="localhost", nic="Microsoft_Hyper_V_Network_Adapter__1"} * 100
|
||||
```
|
||||
|
||||
## Alerting examples
|
||||
**prometheus.rules**
|
||||
```yaml
|
||||
- alert: NetInterfaceUsage
|
||||
expr: rate(windows_net_bytes_total[2m]) / windows_net_current_bandwidth_bytes * 100 > 95
|
||||
for: 10m
|
||||
labels:
|
||||
severity: high
|
||||
annotations:
|
||||
summary: "Network Interface Usage (instance {{ $labels.instance }})"
|
||||
description: "Network traffic usage is greater than 95% for interface {{ $labels.nic }}\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
```
|
||||
# net collector
|
||||
|
||||
The net collector exposes metrics about network interfaces
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `net`
|
||||
Data source | Perflib
|
||||
Classes | [`Win32_PerfRawData_Tcpip_NetworkInterface`](https://technet.microsoft.com/en-us/security/aa394340(v=vs.80))
|
||||
Enabled by default? | Yes
|
||||
|
||||
## Flags
|
||||
|
||||
### `--collector.net.nic-whitelist`
|
||||
|
||||
If given, an interface name needs to match the whitelist regexp in order for the corresponding metrics to be reported
|
||||
|
||||
### `--collector.net.nic-blacklist`
|
||||
|
||||
If given, an interface name needs to *not* match the blacklist regexp in order for the corresponding metrics to be reported
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`wmi_net_bytes_received_total` | Total bytes received by interface | counter | `nic`
|
||||
`wmi_net_bytes_sent_total` | Total bytes transmitted by interface | counter | `nic`
|
||||
`wmi_net_bytes_total` | Total bytes received and transmitted by interface | counter | `nic`
|
||||
`wmi_net_packets_outbound_discarded` | Total outbound packets that were chosen to be discarded even though no errors had been detected to prevent transmission | counter | `nic`
|
||||
`wmi_net_packets_outbound_errors` | Total packets that could not be transmitted due to errors | counter | `nic`
|
||||
`wmi_net_packets_received_discarded` | Total inbound packets that were chosen to be discarded even though no errors had been detected to prevent delivery | counter | `nic`
|
||||
`wmi_net_packets_received_errors` | Total packets that could not be received due to errors | counter | `nic`
|
||||
`wmi_net_packets_received_total` | Total packets received by interface | counter | `nic`
|
||||
`wmi_net_packets_received_unknown` | Total packets received by interface that were discarded because of an unknown or unsupported protocol | counter | `nic`
|
||||
`wmi_net_packets_total` | Total packets received and transmitted by interface | counter | `nic`
|
||||
`wmi_net_packets_sent_total` | Total packets transmitted by interface | counter | `nic`
|
||||
`wmi_net_current_bandwidth` | Estimate of the interface's current bandwidth in bits per second (bps) | gauge | `nic`
|
||||
|
||||
### Example metric
|
||||
Query the rate of transmitted network traffic
|
||||
```
|
||||
rate(wmi_net_bytes_sent_total{instance="localhost"}[2m])
|
||||
```
|
||||
|
||||
## Useful queries
|
||||
Get total utilisation of network interface as a percentage
|
||||
```
|
||||
rate(wmi_net_bytes_total{instance="localhost", nic="Microsoft_Hyper_V_Network_Adapter__1"}[2m]) * 8 / wmi_net_current_bandwidth{instance="locahost", nic="Microsoft_Hyper_V_Network_Adapter__1"} * 100
|
||||
```
|
||||
|
||||
## Alerting examples
|
||||
**prometheus.rules**
|
||||
```yaml
|
||||
- alert: NetInterfaceUsage
|
||||
expr: rate(wmi_net_bytes_total[2m]) * 8 / wmi_net_current_bandwidth * 100 > 95
|
||||
for: 10m
|
||||
labels:
|
||||
severity: high
|
||||
annotations:
|
||||
summary: "Network Interface Usage (instance {{ $labels.instance }})"
|
||||
description: "Network traffic usage is greater than 95% for interface {{ $labels.nic }}\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
```
|
||||
|
||||
@@ -1,31 +1,32 @@
|
||||
# netframework_clrexceptions collector
|
||||
|
||||
The netframework_clrexceptions collector exposes metrics about CLR exceptions in the dotnet framework.
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `netframework_clrexceptions`
|
||||
Classes | `Win32_PerfRawData_NETFramework_NETCLRExceptions`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_netframework_clrexceptions_exceptions_thrown_total` | Displays the total number of exceptions thrown since the application started. This includes both .NET exceptions and unmanaged exceptions that are converted into .NET exceptions. | counter | `process`
|
||||
`windows_netframework_clrexceptions_exceptions_filters_total` | Displays the total number of .NET exception filters executed. An exception filter evaluates regardless of whether an exception is handled. | counter | `process`
|
||||
`windows_netframework_clrexceptions_exceptions_finallys_total` | Displays the total number of finally blocks executed. Only the finally blocks executed for an exception are counted; finally blocks on normal code paths are not counted by this counter. | counter | `process`
|
||||
`windows_netframework_clrexceptions_throw_to_catch_depth_total` | Displays the total number of stack frames traversed, from the frame that threw the exception to the frame that handled the exception. | counter | `process`
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
# netframework_clrexceptions collector
|
||||
|
||||
The netframework_clrexceptions collector exposes metrics about CLR exceptions in the dotnet framework.
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `netframework_clrexceptions`
|
||||
Classes | `Win32_PerfRawData_NETFramework_NETCLRExceptions`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`wmi_...` | ... | counter/gauge/histogram/summary | ...
|
||||
`wmi_netframework_clrexceptions_exceptions_thrown_total` | Displays the total number of exceptions thrown since the application started. This includes both .NET exceptions and unmanaged exceptions that are converted into .NET exceptions. | counter | `process`
|
||||
`wmi_netframework_clrexceptions_exceptions_filters_total` | Displays the total number of .NET exception filters executed. An exception filter evaluates regardless of whether an exception is handled. | counter | `process`
|
||||
`wmi_netframework_clrexceptions_exceptions_finallys_total` | Displays the total number of finally blocks executed. Only the finally blocks executed for an exception are counted; finally blocks on normal code paths are not counted by this counter. | counter | `process`
|
||||
`wmi_netframework_clrexceptions_throw_to_catch_depth_total` | Displays the total number of stack frames traversed, from the frame that threw the exception to the frame that handled the exception. | counter | `process`
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
|
||||
@@ -1,30 +1,31 @@
|
||||
# netframework_clrinterop collector
|
||||
|
||||
The netframework_clrinterop collector exposes metrics about interop between the dotnet framework and outside components.
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `netframework_clrinterop`
|
||||
Classes | `Win32_PerfRawData_NETFramework_NETCLRInterop`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`windows_netframework_clrinterop_com_callable_wrappers_total` | Displays the current number of COM callable wrappers (CCWs). A CCW is a proxy for a managed object being referenced from an unmanaged COM client. | counter | `process`
|
||||
`windows_netframework_clrinterop_interop_marshalling_total` | Displays the total number of times arguments and return values have been marshaled from managed to unmanaged code, and vice versa, since the application started. | counter | `process`
|
||||
`windows_netframework_clrinterop_interop_stubs_created_total` | Displays the current number of stubs created by the common language runtime. Stubs are responsible for marshaling arguments and return values from managed to unmanaged code, and vice versa, during a COM interop call or a platform invoke call. | counter | `process`
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
# netframework_clrinterop collector
|
||||
|
||||
The netframework_clrinterop collector exposes metrics about interop between the dotnet framework and outside components.
|
||||
|
||||
|||
|
||||
-|-
|
||||
Metric name prefix | `netframework_clrinterop`
|
||||
Classes | `Win32_PerfRawData_NETFramework_NETCLRInterop`
|
||||
Enabled by default? | No
|
||||
|
||||
## Flags
|
||||
|
||||
None
|
||||
|
||||
## Metrics
|
||||
|
||||
Name | Description | Type | Labels
|
||||
-----|-------------|------|-------
|
||||
`wmi_...` | ... | counter/gauge/histogram/summary | ...
|
||||
`wmi_netframework_clrinterop_com_callable_wrappers_total` | Displays the current number of COM callable wrappers (CCWs). A CCW is a proxy for a managed object being referenced from an unmanaged COM client. | counter | `process`
|
||||
`wmi_netframework_clrinterop_interop_marshalling_total` | Displays the total number of times arguments and return values have been marshaled from managed to unmanaged code, and vice versa, since the application started. | counter | `process`
|
||||
`wmi_netframework_clrinterop_interop_stubs_created_total` | Displays the current number of stubs created by the common language runtime. Stubs are responsible for marshaling arguments and return values from managed to unmanaged code, and vice versa, during a COM interop call or a platform invoke call. | counter | `process`
|
||||
|
||||
### Example metric
|
||||
_This collector does not yet have explained examples, we would appreciate your help adding them!_
|
||||
|
||||
## Useful queries
|
||||
_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
|
||||
|
||||
## Alerting examples
|
||||
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user