Compare commits

...

59 Commits

Author SHA1 Message Date
Jan-Otto Kröpke
65d19f433e collector: fix flapping metrics if process is enabled. (#1643) 2024-09-27 11:09:17 +02:00
Jan-Otto Kröpke
2d334e4df0 installer: create config file, if config file location is customized (#1642) 2024-09-27 11:06:07 +02:00
Jan-Otto Kröpke
f442d6e22a filetime: add collector (#1639)
Signed-off-by: Jan-Otto Kröpke <mail@jkroepke.de>
2024-09-24 23:34:39 +02:00
Jan-Otto Kröpke
d43f6ffdec docs: remove push to quay.io
Signed-off-by: Jan-Otto Kröpke <github@jkroepke.de>
2024-09-22 11:38:12 +02:00
Jan-Otto Kröpke
9bea340c44 docs: remove old service.services-where CLI frag from docs (#1634) 2024-09-20 21:03:52 +02:00
Jan-Otto Kröpke
2635e5d8eb netframework: merge multiple collector into one (Click here for more information) (#1633) 2024-09-20 10:02:57 +02:00
Jan-Otto Kröpke
41ff5729df chore: Update github.com/prometheus/client_golang (#1631)
Signed-off-by: Jan-Otto Kröpke <mail@jkroepke.de>
2024-09-19 23:15:02 +02:00
Jan-Otto Kröpke
6097432d87 chore: remove replace (#1628) 2024-09-14 21:44:08 +02:00
Jan-Otto Kröpke
5f36a81613 cpu: Fetch performance counter via PDH.dll via feature toggle. (off by default) (#1627) 2024-09-13 23:10:57 +02:00
Jan-Otto Kröpke
2e4ba9984d perfdata: fix incorrect collector log lines (#1626) 2024-09-13 22:12:10 +02:00
Jan-Otto Kröpke
fb275a06fe service: fix label name in windows_service_state (#1625) 2024-09-12 19:35:12 +02:00
Jan-Otto Kröpke
064ea74b6f installer: fix arm64 msi installer (#1623) 2024-09-12 15:02:21 +02:00
Jan-Otto Kröpke
25b642b584 chore: remove test push pipelines (#1621) 2024-09-11 14:19:14 +02:00
Jan-Otto Kröpke
f712c07c38 chore: release 0.29.0.rc0 (#1600) 2024-09-11 00:34:10 +02:00
Jan-Otto Kröpke
83b0aa8f62 container: do not fail hard, if single containers can't be scraped (#1561) 2024-09-07 20:26:22 +02:00
dependabot[bot]
9780a6aec6 chore(deps): bump github.com/prometheus/common from 0.55.0 to 0.57.0 (#1603)
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Jan-Otto Kröpke <github@jkroepke.de>
2024-09-07 20:17:57 +02:00
Jan-Otto Kröpke
b3c0c58c17 installer: Add UI + Replace ADD_FIREWALL_EXCEPTION with ADDLOCAL=FirewallException (#1611) 2024-09-06 22:29:50 +02:00
Jan-Otto Kröpke
50687655bf chore(docs): firewall not enabled by default (#1610) 2024-09-05 13:01:18 +02:00
Jan-Otto Kröpke
26556950d0 Update pr-check.yaml
Signed-off-by: Jan-Otto Kröpke <github@jkroepke.de>
2024-09-05 12:45:23 +02:00
Jan-Otto Kröpke
f72147c4df fix: firewall not enabled by default
Signed-off-by: Jan-Otto Kröpke <github@jkroepke.de>
2024-09-05 12:42:51 +02:00
Jan-Otto Kröpke
2008dc5b23 collector: Skip collecting performance data if the enabled collectors don't request any. (#1604) 2024-09-03 10:11:58 +02:00
Jan-Otto Kröpke
37664cb19a dfsr: Fix DFS Replication Service Volumes collector (#1595) 2024-09-02 14:58:29 +02:00
Jan-Otto Kröpke
e6b74b690a chore: close stale issues (#1602) 2024-09-02 01:07:07 +02:00
PrometheusBot
7d2fc83abe Synchronize common files from prometheus/prometheus (#1601) 2024-09-01 20:23:24 +02:00
Jan-Otto Kröpke
9febf1e97c process: fix Access is denied errors (#1599) 2024-08-31 19:37:19 +02:00
Jan-Otto Kröpke
b53d91e048 cpu_info: Extend processor information (#1597) 2024-08-31 12:22:22 +02:00
Jan-Otto Kröpke
a5d1112fcd cache: fix windows_cache_copy_read_hits_total metric (#1591) 2024-08-31 08:25:37 +02:00
Jan-Otto Kröpke
d8f0665bdc process: introduce info metric; removed creating_process_id label from all process metric (click here for more information) (#1592) 2024-08-30 20:19:41 +02:00
Jan-Otto Kröpke
4f6e6e8b77 *: avoid using default wmi client. (#1590) 2024-08-30 00:26:15 +02:00
Jan-Otto Kröpke
3ce25ff1ef mscluster: merge multiple collector into one (Click here for more information) (#1585) 2024-08-29 22:03:05 +02:00
dependabot[bot]
c99ac2c5aa chore(deps): bump github.com/prometheus/client_golang (#1588)
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-08-27 21:12:58 +02:00
dependabot[bot]
c9510e8c1d chore(deps): bump github.com/Microsoft/hcsshim from 0.12.5 to 0.12.6 (#1587)
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-08-27 21:12:34 +02:00
Jan-Otto Kröpke
4484e96b66 Update bug_report.yaml
Signed-off-by: Jan-Otto Kröpke <github@jkroepke.de>
2024-08-27 20:33:11 +02:00
Jan-Otto Kröpke
9705ff0a24 Update bug_report.yaml
Signed-off-by: Jan-Otto Kröpke <github@jkroepke.de>
2024-08-27 20:32:05 +02:00
Jan-Otto Kröpke
89c832feb0 chore: pass context aware logger to collectors (#1582) 2024-08-24 19:14:38 +02:00
Jan-Otto Kröpke
fbead0fb79 terminal_services: remove old metric from docs (#1583) 2024-08-24 16:57:34 +02:00
Jan-Otto Kröpke
0f4ef8e781 chore: Update TEXTFILE_DIRS description in README (#1581) 2024-08-22 08:49:10 +02:00
Jan-Otto Kröpke
56709b9638 terminal_services: Avoid duplicate metrics by add session_id (#1576) 2024-08-20 19:24:08 +02:00
dependabot[bot]
2589e56f95 chore(deps): bump github.com/prometheus/client_golang from 1.19.1 to 1.20.0 (#1574)
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-08-19 17:23:39 +02:00
Jan-Otto Kröpke
4e460bc24c exchange: enable all collectors as default (#1572) 2024-08-17 21:00:05 +02:00
Jan-Otto Kröpke
b5ceb27836 time: fix windows_time_computed_time_offset_seconds docs (#1571)
Signed-off-by: Jan-Otto Kröpke <mail@jkroepke.de>
2024-08-17 20:07:25 +02:00
Jan-Otto Kröpke
f6965b10f4 mssql: fix nil panic, if YAML file is used a configuration (#1570) 2024-08-14 08:28:46 +02:00
dependabot[bot]
d7f052fb27 chore(deps): bump golang.org/x/sys from 0.23.0 to 0.24.0 (#1566)
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-08-12 14:24:45 +02:00
Jan-Otto Kröpke
ca4ad46e2d scheduled_task: do not report windows_scheduled_task_last_result for task that never run before (#1562) 2024-08-11 15:47:59 +02:00
Jan-Otto Kröpke
dd956c986b chore: Refactor Config Collector API (#1558) 2024-08-11 13:28:39 +02:00
Jan-Otto Kröpke
7bb16d2f5b textfile: disable collector by default (#1560) 2024-08-11 12:57:14 +02:00
Jan-Otto Kröpke
e478843faa chore: deprecate teradici_pcoip and vmware_blast collector (#1559) 2024-08-11 11:32:01 +02:00
Jan-Otto Kröpke
9b02e4a0ea chore: enable more linter (#1557) 2024-08-10 22:05:33 +02:00
Jan-Otto Kröpke
27a3553dac *: cleanup collector API 3 (#1556) 2024-08-10 20:02:07 +02:00
Jan-Otto Kröpke
b2548e02bd installer: do not enable V1 counters by default (#1555) 2024-08-10 14:39:11 +02:00
Jan-Otto Kröpke
0ada09ee3c *: Collector API cleanup 2 (#1552) 2024-08-05 23:40:32 +02:00
Jan-Otto Kröpke
3c360c05f3 Update pr-check.yaml
Signed-off-by: Jan-Otto Kröpke <github@jkroepke.de>
2024-08-05 20:01:59 +02:00
PrometheusBot
fe8e72e38f Synchronize common files from prometheus/prometheus (#1551) 2024-08-05 20:01:08 +02:00
dependabot[bot]
2d091c7187 chore(deps): bump golang.org/x/sys from 0.22.0 to 0.23.0 (#1549)
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-08-05 15:57:18 +02:00
dependabot[bot]
b4999eda4b chore(deps): bump actions/checkout from 3 to 4 (#1550)
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-08-05 15:57:10 +02:00
Jan-Otto Kröpke
d1e3a63f93 *: cleanup collector API 1 (#1547) 2024-08-05 15:50:41 +02:00
Jan-Otto Kröpke
dffc53eff8 terminal_services: Fix "The operation completed successfully." error (#1548) 2024-08-05 15:31:29 +02:00
Jan-Otto Kröpke
9026bc02ff Update pr-check.yaml
Signed-off-by: Jan-Otto Kröpke <github@jkroepke.de>
2024-08-05 13:28:39 +02:00
Jan-Otto Kröpke
8f2a45d832 printer: expose config struct properties (#1545) 2024-07-31 18:02:21 +02:00
197 changed files with 14722 additions and 11567 deletions

View File

@@ -1,6 +1,16 @@
root = true
[*.wxs]
[*]
charset = utf-8
end_of_line = lf
insert_final_newline = true
trim_trailing_whitespace = true
tab_width = 4
[*.{json,wxs,xml}]
indent_style = space
indent_size = 4
[*.{yml,yaml}]
indent_style = space
indent_size = 2

3
.gitattributes vendored Normal file
View File

@@ -0,0 +1,3 @@
*.go text eol=lf
*.sh text eol=lf
Makefile text eol=lf

View File

@@ -6,6 +6,27 @@ body:
attributes:
value: Thanks for taking the time to fill out this bug report!
- type: markdown
attributes:
value: |-
> [!NOTE]
> If you encounter "Counter not found" issues, try to re-build the performance counter first.
```
PS C:\WINDOWS\system32> cd c:\windows\system32
PS C:\windows\system32> lodctr /R
Error: Unable to rebuild performance counter setting from system backup store, error code is 2
PS C:\windows\system32> cd ..
PS C:\windows> cd syswow64
PS C:\windows\syswow64> lodctr /R
Info: Successfully rebuilt performance counter setting from system backup store
PS C:\windows\syswow64> winmgmt.exe /RESYNCPERF
```
----
- type: textarea
attributes:
label: Current Behavior

View File

@@ -33,25 +33,3 @@ jobs:
# 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: ''

View File

@@ -12,6 +12,8 @@ on:
- "tools/e2e-output.txt"
branches:
- master
- next
- main
pull_request:
paths:
- "go.mod"
@@ -21,9 +23,11 @@ on:
- "tools/e2e-output.txt"
branches:
- master
- next
- main
env:
PROMU_VER: '0.14.0'
VERSION_PROMU: '0.14.0'
PROMTOOL_VER: '2.43.0'
jobs:
@@ -40,9 +44,9 @@ jobs:
- 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 "$(go env GOPATH)\bin"
Invoke-WebRequest -Uri https://github.com/prometheus/promu/releases/download/v$($Env:VERSION_PROMU)/promu-$($Env:VERSION_PROMU).windows-amd64.zip -OutFile promu-$($Env:VERSION_PROMU).windows-amd64.zip
Expand-Archive -Path promu-$($Env:VERSION_PROMU).windows-amd64.zip -DestinationPath .
Copy-Item -Path promu-$($Env:VERSION_PROMU).windows-amd64\promu.exe -Destination "$(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 $env:GITHUB_PATH -Encoding utf8 -Append
@@ -64,9 +68,9 @@ jobs:
Expand-Archive -Path prometheus-$($Env:PROMTOOL_VER).windows-amd64.zip -DestinationPath .
Copy-Item -Path prometheus-$($Env:PROMTOOL_VER).windows-amd64\promtool.exe -Destination "$(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 "$(go env GOPATH)\bin"
Invoke-WebRequest -Uri https://github.com/prometheus/promu/releases/download/v$($Env:VERSION_PROMU)/promu-$($Env:VERSION_PROMU).windows-amd64.zip -OutFile promu-$($Env:VERSION_PROMU).windows-amd64.zip
Expand-Archive -Path promu-$($Env:VERSION_PROMU).windows-amd64.zip -DestinationPath .
Copy-Item -Path promu-$($Env:VERSION_PROMU).windows-amd64\promu.exe -Destination "$(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
@@ -100,5 +104,5 @@ jobs:
- name: golangci-lint
uses: golangci/golangci-lint-action@v6
with:
version: v1.58
args: "--timeout=5m --out-format github-actions,colored-line-number"
version: v1.60
args: "--max-same-issues=0"

View File

@@ -33,14 +33,16 @@ jobs:
name: check title prefix
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- uses: actions/checkout@v4
- name: check
run: |
PR_TITLE_PREFIX=$(echo "$PR_TITLE" | cut -d':' -f1)
if [[ ! -d "pkg/collector/$PR_TITLE_PREFIX" ]] || [[ "$PR_TITLE_PREFIX" == "chore" ]] || [[ "$PR_TITLE_PREFIX" == "*" ]]; then
echo "PR title must start with an name of an collector package"
echo "Example: 'logical_disk: description'"
exit 1
if [[ -d "pkg/collector/$PR_TITLE_PREFIX" ]] ||[[ -d "pkg/$PR_TITLE_PREFIX" ]] || [[ -d "$PR_TITLE_PREFIX" ]] || [[ "$PR_TITLE_PREFIX" == "chore" ]] || [[ "$PR_TITLE_PREFIX" == "chore(docs)" ]] || [[ "$PR_TITLE_PREFIX" == "chore(deps)" ]] || [[ "$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 }}
PR_TITLE: ${{ github.event.pull_request.title }}

View File

@@ -16,7 +16,10 @@ permissions:
packages: write
env:
PROMU_VER: '0.14.0'
VERSION_PROMU: '0.14.0'
VERSION_CONTAINERD: '1.7.21'
VERSION_BUILDKIT: '0.15.2'
VERSION_BUILDX: '0.16.2'
jobs:
build:
@@ -24,8 +27,7 @@ jobs:
steps:
- uses: actions/checkout@v4
with:
# fetch-depth required for gitversion in `Build` step
fetch-depth: 0
fetch-depth: '0'
- uses: actions/setup-go@v5
with:
@@ -34,41 +36,38 @@ jobs:
# 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-$version-windows-amd64.tar.gz -o containerd.tar.gz
curl.exe -L https://github.com/containerd/containerd/releases/download/v${{ env.VERSION_CONTAINERD }}/containerd-${{ env.VERSION_CONTAINERD }}-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-$version.windows-amd64.tar.gz -o buildkit.tar.gz
curl.exe -L https://github.com/moby/buildkit/releases/download/v${{ env.VERSION_BUILDKIT }}/buildkit-v${{ env.VERSION_BUILDKIT }}.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 $env:ProgramData\Docker\cli-plugins\docker-buildx.exe
curl.exe -L https://github.com/docker/buildx/releases/download/v${{ env.VERSION_BUILDX }}/buildx-v${{ env.VERSION_BUILDX }}.windows-amd64.exe -o $env:ProgramData\Docker\cli-plugins\docker-buildx.exe
- uses: docker/setup-buildx-action@v3
with:
driver: remote
endpoint: npipe:////./pipe/buildkitd
- name: Install WiX
run: dotnet tool install --global wix
- name: Install WiX extensions
run: |
wix extension add -g WixToolset.Util.wixext
wix extension add -g WixToolset.Ui.wixext
wix extension add -g WixToolset.Firewall.wixext
- name: Install Build deps
run: |
Invoke-WebRequest -Uri https://github.com/prometheus/promu/releases/download/v$($Env:PROMU_VER)/promu-$($Env:PROMU_VER).windows-amd64.zip -OutFile promu-$($Env:PROMU_VER).windows-amd64.zip
Expand-Archive -Path promu-$($Env:PROMU_VER).windows-amd64.zip -DestinationPath .
Copy-Item -Path promu-$($Env:PROMU_VER).windows-amd64\promu.exe -Destination "$(go env GOPATH)\bin"
Invoke-WebRequest -Uri https://github.com/prometheus/promu/releases/download/v$($Env:VERSION_PROMU)/promu-$($Env:VERSION_PROMU).windows-amd64.zip -OutFile promu-$($Env:VERSION_PROMU).windows-amd64.zip
Expand-Archive -Path promu-$($Env:VERSION_PROMU).windows-amd64.zip -DestinationPath .
Copy-Item -Path promu-$($Env:VERSION_PROMU).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
@@ -77,7 +76,7 @@ jobs:
run: |
$ErrorActionPreference = "Stop"
$Version = git describe --tag
$Version = git describe --tags --always
$Version = $Version -replace 'v', ''
# '+' symbols are invalid characters in image tags
$Version = $Version -replace '\+', '_'
@@ -92,12 +91,6 @@ jobs:
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"
@@ -113,6 +106,14 @@ jobs:
promu checksum output\
- name: Upload Artifacts
uses: actions/upload-artifact@v4
with:
name: windows_exporter_binaries
path: |
output\windows_exporter-*.exe
output\windows_exporter-*.msi
- name: Build Docker Artifacts
run: make build-all
env:

View File

@@ -10,7 +10,7 @@ on:
- master
env:
PROMU_VER: 'v0.14.0'
VERSION_PROMU: 'v0.14.0'
jobs:
codespell:

29
.github/workflows/stale-close.yml vendored Normal file
View File

@@ -0,0 +1,29 @@
name: 'Close stale issues and PRs'
on:
workflow_dispatch: {}
schedule:
- cron: '30 1 * * *'
permissions:
issues: write
pull-requests: write
jobs:
stale:
if: github.repository_owner == 'prometheus' || github.repository_owner == 'prometheus-community' # Don't run this workflow on forks.
runs-on: ubuntu-latest
steps:
- uses: actions/stale@28ca1036281a5e5922ead5184a1bbf96e5fc984e # v9.0.0
with:
repo-token: ${{ secrets.GITHUB_TOKEN }}
# opt out of defaults to avoid marking issues as stale and closing them
# https://github.com/actions/stale#days-before-close
# https://github.com/actions/stale#days-before-stale
days-before-stale: -1
days-before-close: -1
stale-pr-message: ''
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.'
operations-per-run: 30
# override days-before-stale, for only marking the pull requests as stale
days-before-issue-stale: 90
days-before-issue-close: 30
stale-pr-label: stale
exempt-pr-labels: keepalive

View File

@@ -1,21 +1,31 @@
name: 'Close stale issues and PRs'
name: Stale Check
on:
workflow_dispatch: {}
schedule:
- cron: '30 1 * * *'
- cron: '16 22 * * *'
permissions:
issues: write
pull-requests: write
jobs:
stale:
if: github.repository_owner == 'prometheus' || github.repository_owner == 'prometheus-community' # Don't run this workflow on forks.
runs-on: ubuntu-latest
steps:
- uses: actions/stale@v9
- uses: actions/stale@28ca1036281a5e5922ead5184a1bbf96e5fc984e # v9.0.0
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
repo-token: ${{ secrets.GITHUB_TOKEN }}
# opt out of defaults to avoid marking issues as stale and closing them
# https://github.com/actions/stale#days-before-close
# https://github.com/actions/stale#days-before-stale
days-before-stale: -1
days-before-close: -1
# Setting it to empty string to skip comments.
# https://github.com/actions/stale#stale-pr-message
# https://github.com/actions/stale#stale-issue-message
stale-pr-message: ''
stale-issue-message: ''
operations-per-run: 30
# override days-before-stale, for only marking the pull requests as stale
days-before-pr-stale: 60
stale-pr-label: stale
exempt-pr-labels: keepalive

View File

@@ -1,101 +1,74 @@
linters:
enable-all: true
disable:
- asasalint
- asciicheck
- bidichk
- bodyclose
- canonicalheader
- containedctx
- contextcheck
- copyloopvar
- cyclop
- decorder
- depguard
- dogsled
- dupl
- dupword
- durationcheck
- err113
- errchkjson
- errname
- errorlint
- execinquery
- exhaustive
- exhaustruct
- exportloopref
- fatcontext
- forbidigo
- forcetypeassert
- funlen
- gci
- ginkgolinter
- gocheckcompilerdirectives
- gochecknoglobals
- gochecknoinits
- gochecksumtype
- gocognit
- goconst
- gocritic
- gocyclo
- godot
- godox
- gofumpt
- goheader
- goimports
- gomoddirectives
- gomodguard
- goprintffuncname
- gosec
- gosimple
- gosmopolitan
- grouper
- importas
- inamedparam
- interfacebloat
- intrange
- ireturn
- gomnd
- lll
- maintidx
- makezero
- mirror
- misspell
- mnd
- musttag
- nakedret
- nestif
- nlreturn
- noctx
- nolintlint
- nonamedreturns
- nosprintfhostport
- paralleltest
- predeclared
- protogetter
- reassign
- rowserrcheck
- sloglint
- spancheck
- sqlclosecheck
- staticcheck
- stylecheck
- tagalign
- tagliatelle
- tenv
- testableexamples
- testifylint
- testpackage
- thelper
- tparallel
- usestdlibvars
- varnamelen
- wastedassign
- whitespace
- wrapcheck
- wsl
- zerologlint
- execinquery
- gomnd
run:
timeout: 5m
linters-settings:
gosec:
excludes:
- G115 # integer overflow conversion
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
forbidigo:
forbid:
- "^(fmt\\.Print(|f|ln)|print|println)$"
- p: "^syscall\\..*$"
msg: use golang.org/x/sys/windows instead of syscall
- p: "^windows\\.NewLazyDLL$"
msg: use NewLazySystemDLL instead NewLazyDLL
sloglint:
no-mixed-args: true
kv-only: false
attr-only: true
no-global: "all"
context: "scope"
static-msg: false
no-raw-keys: false
key-naming-case: snake
forbidden-keys:
- time
- level
- msg
- source
args-on-sep-lines: true
stylecheck:
checks: ["all", "-ST1003"]
issues:
exclude:
- don't use underscores in Go names
@@ -109,3 +82,7 @@ issues:
- text: "don't use ALL_CAPS in Go names; use CamelCase"
linters:
- revive
- path: pkg/perflib/
linters:
- godox
- stylecheck

View File

@@ -1,19 +1,24 @@
go:
version: 1.20
# Whenever the Go version is updated here,
# .github/workflows should also be updated.
version: 1.23
repository:
path: github.com/prometheus-community/windows_exporter
path: github.com/prometheus-community/windows_exporter
build:
binaries:
- name: windows_exporter
ldflags: |
-X github.com/prometheus/common/version.Version={{.Version}}
-X github.com/prometheus/common/version.Revision={{.Revision}}
-X github.com/prometheus/common/version.Branch={{.Branch}}
-X github.com/prometheus/common/version.BuildUser={{user}}@{{host}}
-X github.com/prometheus/common/version.BuildDate={{date "20060102-15:04:05"}}
binaries:
- name: windows_exporter
tags:
all:
- trimpath
ldflags: |
-X github.com/prometheus/common/version.Version={{.Version}}
-X github.com/prometheus/common/version.Revision={{.Revision}}
-X github.com/prometheus/common/version.Branch={{.Branch}}
-X github.com/prometheus/common/version.BuildUser={{user}}@{{host}}
-X github.com/prometheus/common/version.BuildDate={{date "20060102-15:04:05"}}
tarball:
files:
- LICENSE
files:
- LICENSE
crossbuild:
platforms:
- windows
platforms:
- windows

View File

@@ -7,7 +7,7 @@ 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)
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

View File

@@ -14,39 +14,29 @@ Name | Description | Enabled by default
[cache](docs/collector.cache.md) | Cache metrics |
[cpu](docs/collector.cpu.md) | CPU usage | &#10003;
[cpu_info](docs/collector.cpu_info.md) | CPU Information |
[cs](docs/collector.cs.md) | "Computer System" metrics (system properties, num cpus/total memory) | &#10003;
[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 |
[filetime](docs/collector.filetime.md) | FileTime 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 |
[license](docs/collector.license.md) | Windows license status |
[logical_disk](docs/collector.logical_disk.md) | Logical disks, disk I/O | &#10003;
[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 |
[memory](docs/collector.memory.md) | Memory usage metrics | &#10003;
[mscluster](docs/collector.mscluster.md) | MSCluster 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 |
[netframework_clrinterop](docs/collector.netframework_clrinterop.md) | .NET Framework Interop Metrics |
[netframework_clrjit](docs/collector.netframework_clrjit.md) | .NET Framework JIT metrics |
[netframework_clrloading](docs/collector.netframework_clrloading.md) | .NET Framework CLR Loading metrics |
[netframework_clrlocksandthreads](docs/collector.netframework_clrlocksandthreads.md) | .NET Framework locks and metrics threads |
[netframework_clrmemory](docs/collector.netframework_clrmemory.md) | .NET Framework Memory metrics |
[netframework_clrremoting](docs/collector.netframework_clrremoting.md) | .NET Framework Remoting metrics |
[netframework_clrsecurity](docs/collector.netframework_clrsecurity.md) | .NET Framework Security Check metrics |
[netframework](docs/collector.netframework.md) | .NET Framework metrics |
[net](docs/collector.net.md) | Network interface I/O | &#10003;
[os](docs/collector.os.md) | OS metrics (memory, processes, users) | &#10003;
[physical_disk](docs/collector.physical_disk.md) | physical disk metrics | &#10003;
[printer](docs/collector.printer.md) | Printer 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 |
@@ -60,7 +50,7 @@ Name | Description | Enabled by default
[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 | &#10003;
[textfile](docs/collector.textfile.md) | Read prometheus metrics from a text file |
[vmware_blast](docs/collector.vmware_blast.md) | VMware Blast session metrics |
[vmware](docs/collector.vmware.md) | Performance counters installed by the Vmware Guest agent |
@@ -98,64 +88,76 @@ windows_exporter accepts flags to configure certain behaviours. The ones configu
| `--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).
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.
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:
If the installer is run without any parameters, the exporter will run with default settings for enabled collectors, ports, etc.
| 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`. |
The installer provides a configuration file to customize the exporter.
Parameters are sent to the installer via `msiexec`. Example invocations:
The configuration file
* is located in the same directory as the exporter executable.
* has the YAML format and is provided with the `--config.file` parameter.
* can be used to enable or disable collectors, set collector-specific parameters, and set global parameters.
The following parameters are available:
| Name | Description |
|----------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `ENABLED_COLLECTORS` | As the `--collectors.enabled` flag, provide a comma-separated list of enabled collectors |
| `CONFIG_FILE` | Use the `--config.file` flag to specify a config file. If empty, no config file will be set. The special value `config.yaml` set the path to the config.yaml at install dir | |
| `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` | Use the `--collector.textfile.directories` flag to specify one or more directories, separated by commas, where the collector should read text files containing metrics |
| `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. For `--collectors.enabled` and `--config.file`, use the specialized properties `ENABLED_COLLECTORS` and `CONFIG_FILE` |
| `ADDLOCAL` | Enables features within the windows_exporter installer. Supported values: `FirewallException` |
| `REMOVE` | Disables features within the windows_exporter installer. Supported values: `FirewallException` |
Parameters are sent to the installer via `msiexec`.
On PowerShell, the `--%` should be passed before defining properties.
Example invocations:
```powershell
msiexec /i <path-to-msi-file> ENABLED_COLLECTORS=os,iis LISTEN_PORT=5000
msiexec /i <path-to-msi-file> --% ENABLED_COLLECTORS=os,iis LISTEN_PORT=5000
```
Example service collector with a custom query.
```powershell
msiexec /i <path-to-msi-file> ENABLED_COLLECTORS=os,service --% EXTRA_FLAGS="--collector.service.services-where ""Name LIKE 'sql%'"""
msiexec /i <path-to-msi-file> --% ENABLED_COLLECTORS=os,service EXTRA_FLAGS="--collectors.exchange.enabled=""ADAccessProcesses"""
```
Define a config file.
```powershell
msiexec /i <path-to-msi-file> --% CONFIG_FILE="D:\config.yaml"
```
On some older versions of Windows,
you may need to surround parameter values with double quotes to get the installation 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\windows_exporter.msi --% ENABLED_COLLECTORS="ad,iis,logon,memory,process,tcp,textfile,thermalzone" TEXTFILE_DIRS="C:\custom_metrics\"
```
To install the exporter with creating a firewall exception, use the following command:
```powershell
msiexec /i <path-to-msi-file> ADD_FIREWALL_EXCEPTION=yes
msiexec /i <path-to-msi-file> --% ADDLOCAL=FirewallException
```
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 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%'"""
msiexec /i <path-to-msi-file> ENABLED_COLLECTORS=os,service --% EXTRA_FLAGS="--collectors.exchange.enabled=""ADAccessProcesses"""
```
## Docker Implementation
The windows_exporter can be run as a Docker container. The Docker image is available on
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`
@@ -192,7 +194,7 @@ 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'"
.\windows_exporter.exe --collectors.enabled "service" --collector.service.include="windows_exporter"
### Enable only process collector and specify a custom query
@@ -218,10 +220,10 @@ If you need to skip TLS verification, you can use the `--config.file.insecure-sk
```yaml
collectors:
enabled: cpu,cs,net,service
enabled: cpu,net,service
collector:
service:
services-where: "Name='windows_exporter'"
include: windows_exporter
log:
level: warn
```

7
config.yaml Normal file
View File

@@ -0,0 +1,7 @@
collectors:
enabled: cpu,cpu_info,exchange,iis,logical_disk,logon,memory,net,os,process,remote_fx,service,system,tcp,time,terminal_services,textfile
collector:
service:
include: "windows_exporter"
log:
level: warn

View File

@@ -21,22 +21,11 @@ This directory contains documentation of the collectors in the windows_exporter,
- [`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)
- [`mscluster`](collector.mscluster.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)
- [`netframework_clrloading`](collector.netframework_clrloading.md)
- [`netframework_clrlocksandthreads`](collector.netframework_clrlocksandthreads.md)
- [`netframework_clrmemory`](collector.netframework_clrmemory.md)
- [`netframework_clrremoting`](collector.netframework_clrremoting.md)
- [`netframework_clrsecurity`](collector.netframework_clrsecurity.md)
- [`netframework`](collector.netframework.md)
- [`nps`](collector.nps.md)
- [`os`](collector.os.md)
- [`physical_disk`](collector.physical_disk.md)

View File

@@ -16,26 +16,22 @@ None
## Metrics
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`
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`
| Name | Description | Type | Labels |
|--------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------|-----------------|
| `windows_cpu_logical_processor` | Number of installed logical processors | counter | `core`, `state` |
| `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` |
| `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` |
### Example metric
Show frequency of host CPU cores

View File

@@ -15,13 +15,39 @@ 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`
| Name | Description | Type | Labels |
|--------------------------------------------|--------------------------------------|-------|--------------------------------------------------------------|
| `windows_cpu_info` | Labelled CPU information | gauge | `architecture`, `description`, `device_id`, `family`, `name` |
| `windows_cpu_info_core` | Number of cores per CPU | gauge | `device_id` |
| `windows_cpu_info_enabled_core` | Number of enabled cores per CPU | gauge | `device_id` |
| `windows_cpu_info_l2_cache_size` | Size of L2 cache per CPU | gauge | `device_id` |
| `windows_cpu_info_l3_cache_size` | Size of L3 cache per CPU | gauge | `device_id` |
| `windows_cpu_info_logical_processor` | Number of logical processors per CPU | gauge | `device_id` |
| `windows_cpu_info_thread` | Number of threads per CPU | gauge | `device_id` |
### 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
# HELP windows_cpu_info Labelled CPU information as provided by Win32_Processor
# TYPE windows_cpu_info gauge
windows_cpu_info{architecture="9",description="AMD64 Family 25 Model 33 Stepping 2",device_id="CPU0",family="107",name="AMD Ryzen 9 5900X 12-Core Processor"} 1
# HELP windows_cpu_info_core Number of cores per CPU
# TYPE windows_cpu_info_core gauge
windows_cpu_info_core{device_id="CPU0"} 12
# HELP windows_cpu_info_enabled_core Number of enabled cores per CPU
# TYPE windows_cpu_info_enabled_core gauge
windows_cpu_info_enabled_core{device_id="CPU0"} 12
# HELP windows_cpu_info_l2_cache_size Size of L2 cache per CPU
# TYPE windows_cpu_info_l2_cache_size gauge
windows_cpu_info_l2_cache_size{device_id="CPU0"} 6144
# HELP windows_cpu_info_l3_cache_size Size of L3 cache per CPU
# TYPE windows_cpu_info_l3_cache_size gauge
windows_cpu_info_l3_cache_size{device_id="CPU0"} 65536
# HELP windows_cpu_info_logical_processor Number of logical processors per CPU
# TYPE windows_cpu_info_logical_processor gauge
windows_cpu_info_logical_processor{device_id="CPU0"} 24
# HELP windows_cpu_info_thread Number of threads per CPU
# TYPE windows_cpu_info_thread gauge
windows_cpu_info_thread{device_id="CPU0"} 24
```
The value of the metric is irrelevant, but the labels expose some useful information on the CPU installed in each socket.

View File

@@ -1,5 +1,9 @@
# cs collector
> [!CAUTION]
> This collector is deprecated and will be removed in a future release.
> See https://github.com/prometheus-community/windows_exporter/pull/1596 for more information.
The cs collector exposes metrics detailing the hardware of the computer system
|||

View File

@@ -0,0 +1,36 @@
# filetime collector
The filetime collector exposes modified timestamps of files in the filesystem.
The collector
|||
-|-
Metric name prefix | `filetime`
Enabled by default? | No
## Flags
### `--collectors.filetime.file-patterns`
Comma-separated list of file patterns. Each pattern is a glob pattern that can contain `*`, `?`, and `**` (recursive).
See https://github.com/bmatcuk/doublestar#patterns for an extended description of the pattern syntax.
## Metrics
Name | Description | Type | Labels
-----|-------------|------|-------
`windows_filetime_mtime_timestamp_seconds` | File modification time | gauge | `file`
### Example metric
```
# HELP windows_filetime_mtime_timestamp_seconds File modification time
# TYPE windows_filetime_mtime_timestamp_seconds gauge
windows_filetime_mtime_timestamp_seconds{file="C:\\Users\\admin\\Desktop\\Dashboard.lnk"} 1.726434517e+09
```
## 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!_

View File

@@ -5,9 +5,9 @@ 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
Data source | Performance Counters
Classes | -
Enabled by default? | Yes
## Flags
@@ -15,46 +15,73 @@ 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
| 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_physical_free_bytes` | Bytes of physical memory currently unused and available | gauge | None |
| `windows_memory_physical_total_bytes` | Total bytes of physical memory available to the operating system. This value does not necessarily indicate the true amount of physical memory, but what is reported to the operating system as available to it | gauge | 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_process_memory_limit_bytes` | Maximum number of bytes of memory that can be allocated to a process | 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!_
Show memory usage for instance (%)
```
100 - 100 * windows_memory_physical_free_bytes{instance="localhost"} / windows_memory_physical_total_bytes
```
## Alerting examples
_This collector does not yet have alerting examples, we would appreciate your help adding them!_
**prometheus.rules**
```yaml
# Alert on hosts that have exhausted all available physical memory
- alert: MemoryExhausted
expr: windows_os_physical_memory_free_bytes == 0
for: 10m
labels:
severity: high
annotations:
summary: "Host {{ $labels.instance }} is out of memory"
description: "{{ $labels.instance }} has exhausted all available physical memory"
# Alert on hosts with greater than 90% memory usage
- alert: MemoryLow
expr: 100 - 100 * windows_memory_physical_free_bytes{instance="localhost"} / windows_memory_physical_total_bytes > 90
for: 10m
labels:
severity: warning
annotations:
summary: "Memory usage for host {{ $labels.instance }} is greater than 90%"
```

186
docs/collector.mscluster.md Normal file
View File

@@ -0,0 +1,186 @@
# mscluster_cluster collector
The MSCluster_Cluster class is a dynamic WMI class that represents a cluster.
|||
-|-
Metric name prefix | `mscluster`
Classes | `MSCluster_Cluster`,`MSCluster_Network`,`MSCluster_Node`,`MSCluster_Resource`,`MSCluster_ResourceGroup`
Enabled by default? | No
## Flags
### `--collectors.mscluster.enabled`
Comma-separated list of collectors to use, for example:
`--collectors.mscluster.enabled=cluster,network,node,resource,resouregroup`.
Matching is case-sensitive.
## Metrics
### Cluster
| Name | Description | Type | Labels |
|-------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------|--------|
| `mscluster_cluster_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` |
| `mscluster_cluster_AdminAccessPoint` | The type of the cluster administrative access point. | gauge | `name` |
| `mscluster_cluster_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` |
| `mscluster_cluster_AutoBalancerLevel` | Determines the level of aggressiveness of AutoBalancer. | gauge | `name` |
| `mscluster_cluster_AutoBalancerMode` | Determines whether or not the auto balancer is enabled. | gauge | `name` |
| `mscluster_cluster_BackupInProgress` | Indicates whether a backup is in progress. | gauge | `name` |
| `mscluster_cluster_BlockCacheSize` | CSV BlockCache Size in MB. | gauge | `name` |
| `mscluster_cluster_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` |
| `mscluster_cluster_ClusSvcRegroupOpeningTimeout` | Controls how long a node will wait on other nodes in the opening stage before deciding that they failed. | gauge | `name` |
| `mscluster_cluster_ClusSvcRegroupPruningTimeout` | Controls how long the membership leader will wait to reach full connectivity between cluster nodes. | gauge | `name` |
| `mscluster_cluster_ClusSvcRegroupStageTimeout` | Controls how long a node will wait on other nodes in a membership stage before deciding that they failed. | gauge | `name` |
| `mscluster_cluster_ClusSvcRegroupTickInMilliseconds` | Controls how frequently the membership algorithm is sending periodic membership messages. | gauge | `name` |
| `mscluster_cluster_ClusterEnforcedAntiAffinity` | Enables or disables hard enforcement of group anti-affinity classes. | gauge | `name` |
| `mscluster_cluster_ClusterFunctionalLevel` | The functional level the cluster is currently running in. | gauge | `name` |
| `mscluster_cluster_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` |
| `mscluster_cluster_ClusterLogLevel` | Controls the level of cluster logging. | gauge | `name` |
| `mscluster_cluster_ClusterLogSize` | Controls the maximum size of the cluster log files on each of the nodes. | gauge | `name` |
| `mscluster_cluster_ClusterUpgradeVersion` | Specifies the upgrade version the cluster is currently running in. | gauge | `name` |
| `mscluster_cluster_CrossSiteDelay` | Controls how long the cluster network driver waits in milliseconds between sending Cluster Service heartbeats across sites. | gauge | `name` |
| `mscluster_cluster_CrossSiteThreshold` | Controls how many Cluster Service heartbeats can be missed across sites before it determines that Cluster Service has stopped responding. | gauge | `name` |
| `mscluster_cluster_CrossSubnetDelay` | Controls how long the cluster network driver waits in milliseconds between sending Cluster Service heartbeats across subnets. | gauge | `name` |
| `mscluster_cluster_CrossSubnetThreshold` | Controls how many Cluster Service heartbeats can be missed across subnets before it determines that Cluster Service has stopped responding. | gauge | `name` |
| `mscluster_cluster_CsvBalancer` | Whether automatic balancing for CSV is enabled. | gauge | `name` |
| `mscluster_cluster_DatabaseReadWriteMode` | Sets the database read and write mode. | gauge | `name` |
| `mscluster_cluster_DefaultNetworkRole` | Provides access to the cluster's DefaultNetworkRole property. | gauge | `name` |
| `mscluster_cluster_DetectedCloudPlatform` | | gauge | `name` |
| `mscluster_cluster_DetectManagedEvents` | | gauge | `name` |
| `mscluster_cluster_DetectManagedEventsThreshold` | | gauge | `name` |
| `mscluster_cluster_DisableGroupPreferredOwnerRandomization` | | gauge | `name` |
| `mscluster_cluster_DrainOnShutdown` | Whether to drain the node when cluster service is being stopped. | gauge | `name` |
| `mscluster_cluster_DynamicQuorumEnabled` | Allows cluster service to adjust node weights as needed to increase availability. | gauge | `name` |
| `mscluster_cluster_EnableSharedVolumes` | Enables or disables cluster shared volumes on this cluster. | gauge | `name` |
| `mscluster_cluster_FixQuorum` | Provides access to the cluster's FixQuorum property, which specifies if the cluster is in a fix quorum state. | gauge | `name` |
| `mscluster_cluster_GracePeriodEnabled` | Whether the node grace period feature of this cluster is enabled. | gauge | `name` |
| `mscluster_cluster_GracePeriodTimeout` | The grace period timeout in milliseconds. | gauge | `name` |
| `mscluster_cluster_GroupDependencyTimeout` | The timeout after which a group will be brought online despite unsatisfied dependencies | gauge | `name` |
| `mscluster_cluster_HangRecoveryAction` | Controls the action to take if the user-mode processes have stopped responding. | gauge | `name` |
| `mscluster_cluster_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` |
| `mscluster_cluster_LogResourceControls` | Controls the logging of resource controls. | gauge | `name` |
| `mscluster_cluster_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` |
| `mscluster_cluster_MaxNumberOfNodes` | Indicates the maximum number of nodes that may participate in the Cluster. | gauge | `name` |
| `mscluster_cluster_MessageBufferLength` | The maximum unacknowledged message count for GEM. | gauge | `name` |
| `mscluster_cluster_MinimumNeverPreemptPriority` | Groups with this priority or higher cannot be preempted. | gauge | `name` |
| `mscluster_cluster_MinimumPreemptorPriority` | Minimum priority a cluster group must have to be able to preempt another group. | gauge | `name` |
| `mscluster_cluster_NetftIPSecEnabled` | Whether IPSec is enabled for cluster internal traffic. | gauge | `name` |
| `mscluster_cluster_PlacementOptions` | Various option flags to modify default placement behavior. | gauge | `name` |
| `mscluster_cluster_PlumbAllCrossSubnetRoutes` | Plumbs all possible cross subnet routes to all nodes. | gauge | `name` |
| `mscluster_cluster_PreventQuorum` | Whether the cluster will ignore group persistent state on startup. | gauge | `name` |
| `mscluster_cluster_QuarantineDuration` | The quarantine period timeout in milliseconds. | gauge | `name` |
| `mscluster_cluster_QuarantineThreshold` | Number of node failures before it will be quarantined. | gauge | `name` |
| `mscluster_cluster_QuorumArbitrationTimeMax` | Controls the maximum time necessary to decide the Quorum owner node. | gauge | `name` |
| `mscluster_cluster_QuorumArbitrationTimeMin` | Controls the minimum time necessary to decide the Quorum owner node. | gauge | `name` |
| `mscluster_cluster_QuorumLogFileSize` | This property is obsolete. | gauge | `name` |
| `mscluster_cluster_QuorumTypeValue` | Get the current quorum type value. -1: Unknown; 1: Node; 2: FileShareWitness; 3: Storage; 4: None | gauge | `name` |
| `mscluster_cluster_RequestReplyTimeout` | Controls the request reply time-out period. | gauge | `name` |
| `mscluster_cluster_ResiliencyDefaultPeriod` | The default resiliency period, in seconds, for the cluster. | gauge | `name` |
| `mscluster_cluster_ResiliencyLevel` | The resiliency level for the cluster. | gauge | `name` |
| `mscluster_cluster_ResourceDllDeadlockPeriod` | This property is obsolete. | gauge | `name` |
| `mscluster_cluster_RootMemoryReserved` | Controls the amount of memory reserved for the parent partition on all cluster nodes. | gauge | `name` |
| `mscluster_cluster_RouteHistoryLength` | The history length for routes to help finding network issues. | gauge | `name` |
| `mscluster_cluster_S2DBusTypes` | Bus types for storage spaces direct. | gauge | `name` |
| `mscluster_cluster_S2DCacheDesiredState` | Desired state of the storage spaces direct cache. | gauge | `name` |
| `mscluster_cluster_S2DCacheFlashReservePercent` | Percentage of allocated flash space to utilize when caching. | gauge | `name` |
| `mscluster_cluster_S2DCachePageSizeKBytes` | Page size in KB used by S2D cache. | gauge | `name` |
| `mscluster_cluster_S2DEnabled` | Whether direct attached storage (DAS) is enabled. | gauge | `name` |
| `mscluster_cluster_S2DIOLatencyThreshold` | The I/O latency threshold for storage spaces direct. | gauge | `name` |
| `mscluster_cluster_S2DOptimizations` | Optimization flags for storage spaces direct. | gauge | `name` |
| `mscluster_cluster_SameSubnetDelay` | Controls how long the cluster network driver waits in milliseconds between sending Cluster Service heartbeats on the same subnet. | gauge | `name` |
| `mscluster_cluster_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` |
| `mscluster_cluster_SecurityLevel` | Controls the level of security that should apply to intracluster messages. 0: Clear Text; 1: Sign; 2: Encrypt | gauge | `name` |
| `mscluster_cluster_SecurityLevelForStorage` | | gauge | `name` |
| `mscluster_cluster_SharedVolumeVssWriterOperationTimeout` | CSV VSS Writer operation timeout in seconds. | gauge | `name` |
| `mscluster_cluster_ShutdownTimeoutInMinutes` | The maximum time in minutes allowed for cluster resources to come offline during cluster service shutdown. | gauge | `name` |
| `mscluster_cluster_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` |
| `mscluster_cluster_WitnessDatabaseWriteTimeout` | Controls the maximum time in seconds that a cluster database write to a witness can take before the write is abandoned. | gauge | `name` |
| `mscluster_cluster_WitnessDynamicWeight` | The weight of the configured witness. | gauge | `name` |
| `mscluster_cluster_WitnessRestartInterval` | Controls the witness restart interval. | gauge | `name` |
### Network
| Name | Description | Type | Labels |
|-------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------|--------|
| `mscluster_network_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` |
| `mscluster_network_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` |
| `mscluster_network_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` |
| `mscluster_network_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` |
| `mscluster_network_State` | Provides the current state of the network. 1-1: Unknown; 0: Unavailable; 1: Down; 2: Partitioned; 3: Up | gauge | `name` |
### Network
| Name | Description | Type | Labels |
|----------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------|--------|
| `mscluster_node_BuildNumber` | Provides access to the node's BuildNumber property. | gauge | `name` |
| `mscluster_node_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` |
| `mscluster_node_DetectedCloudPlatform` | The dynamic vote weight of the node adjusted by dynamic quorum feature. | gauge | `name` |
| `mscluster_node_DynamicWeight` | The dynamic vote weight of the node adjusted by dynamic quorum feature. | gauge | `name` |
| `mscluster_node_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` |
| `mscluster_node_MajorVersion` | Provides access to the node's MajorVersion property, which specifies the major portion of the Windows version installed. | gauge | `name` |
| `mscluster_node_MinorVersion` | Provides access to the node's MinorVersion property, which specifies the minor portion of the Windows version installed. | gauge | `name` |
| `mscluster_node_NeedsPreventQuorum` | Whether the cluster service on that node should be started with prevent quorum flag. | gauge | `name` |
| `mscluster_node_NodeDrainStatus` | The current node drain status of a node. 0: Not Initiated; 1: In Progress; 2: Completed; 3: Failed | gauge | `name` |
| `mscluster_node_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` |
| `mscluster_node_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` |
| `mscluster_node_NodeWeight` | The vote weight of the node. | gauge | `name` |
| `mscluster_node_State` | Returns the current state of a node. -1: Unknown; 0: Up; 1: Down; 2: Paused; 3: Joining | gauge | `name` |
| `mscluster_node_StatusInformation` | The isolation or quarantine status of the node. | gauge | `name` |
### Resource
| Name | Description | Type | Labels |
|---------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------|--------------------------------------------|
| `mscluster_resource_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` |
| `mscluster_resource_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` |
| `mscluster_resource_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` |
| `mscluster_resource_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` |
| `mscluster_resource_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` |
| `mscluster_resource_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` |
| `mscluster_resource_MonitorProcessId` | Provides the process ID of the resource host service that is currently hosting the resource. | gauge | `type`, `owner_group`, `name` |
| `mscluster_resource_OwnerNode` | The node hosting the resource. | gauge | `type`, `owner_group`, `node_name`, `name` |
| `mscluster_resource_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` |
| `mscluster_resource_ResourceClass` | Gets or sets the resource class of a resource. 0: Unknown; 1: Storage; 2: Network; 32768: Unknown | gauge | `type`, `owner_group`, `name` |
| `mscluster_resource_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` |
| `mscluster_resource_RestartDelay` | Indicates the time delay before a failed resource is restarted. | gauge | `type`, `owner_group`, `name` |
| `mscluster_resource_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` |
| `mscluster_resource_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` |
| `mscluster_resource_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` |
| `mscluster_resource_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` |
| `mscluster_resource_Subclass` | Provides the list of references to nodes that can be the owner of this resource. | gauge | `type`, `owner_group`, `name` |
## ResourceGroup
| Name | Description | Type | Labels |
|-----------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------|---------------------|
| `mscluster_resourcegroup_AutoFailbackType` | Provides access to the group's AutoFailbackType property. | gauge | `name` |
| `mscluster_resourcegroup_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` |
| `mscluster_resourcegroup_ColdStartSetting` | Indicates whether a group can start after a cluster cold start. | gauge | `name` |
| `mscluster_resourcegroup_DefaultOwner` | Number of the last node the resource group was activated on or explicitly moved to. | gauge | `name` |
| `mscluster_resourcegroup_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` |
| `mscluster_resourcegroup_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` |
| `mscluster_resourcegroup_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` |
| `mscluster_resourcegroup_FailoverThreshold` | The FailoverThreshold property specifies the maximum number of failover attempts. | gauge | `name` |
| `mscluster_resourcegroup_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` |
| `mscluster_resourcegroup_GroupType` | The Type of the resource group. | gauge | `name` |
| `mscluster_resourcegroup_OwnerNode` | The node hosting the resource group. | gauge | `node_name`, `name` |
| `mscluster_resourcegroup_Priority` | Priority value of the resource group | gauge | `name` |
| `mscluster_resourcegroup_ResiliencyPeriod` | The resiliency period for this group, in seconds. | gauge | `name` |
| `mscluster_resourcegroup_State` | The current state of the resource group. -1: Unknown; 0: Online; 1: Offline; 2: Failed; 3: Partial Online; 4: Pending | gauge | `name` |
| `mscluster_resourcegroup_UpdateDomain` | | gauge | `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!_

View File

@@ -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!_

View File

@@ -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!_

View File

@@ -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!_

View File

@@ -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!_

View File

@@ -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!_

View File

@@ -0,0 +1,113 @@
# netframework collector
The netframework collector exposes metrics about dotnet framework.
| | |
|-------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| **Metric name prefix** | `netframework_clrexceptions` |
| **Classes** | `Win32_PerfRawData_NETFramework_NETCLRExceptions`, `Win32_PerfRawData_NETFramework_NETCLRInterop`, `Win32_PerfRawData_NETFramework_NETCLRJit`, `Win32_PerfRawData_NETFramework_NETCLRLoading`, `Win32_PerfRawData_NETFramework_NETCLRLocksAndThreads`, `Win32_PerfRawData_NETFramework_NETCLRMemory`, `Win32_PerfRawData_NETFramework_NETCLRRemoting`, `Win32_PerfRawData_NETFramework_NETCLRSecurity` |
| **Enabled by default?** | No |
## Flags
None
## Metrics
### CLR Exceptions
| 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` |
### CLR Interop
| 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` |
### CLR JIT
| Name | Description | Type | Labels |
|-----------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------|-----------|
| `windows_netframework_clrjit_jit_methods_total` | Displays the total number of methods JIT-compiled since the application started. This counter does not include pre-JIT-compiled methods. | counter | `process` |
| `windows_netframework_clrjit_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. | gauge | `process` |
| `windows_netframework_clrjit_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. | counter | `process` |
| `windows_netframework_clrjit_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 | counter | `process` |
### CLR Loading
| Name | Description | Type | Labels |
|-------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------|-----------|
| `windows_netframework_clrloading_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. | gauge | `process` |
| `windows_netframework_clrloading_appdomains_loaded_current` | Displays the current number of application domains loaded in this application. | gauge | `process` |
| `windows_netframework_clrloading_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. | gauge | `process` |
| `windows_netframework_clrloading_classes_loaded_current` | Displays the current number of classes loaded in all assemblies. | gauge | `process` |
| `windows_netframework_clrloading_appdomains_loaded_total` | Displays the peak number of application domains loaded since the application started. | counter | `process` |
| `windows_netframework_clrloading_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. | counter | `process` |
| `windows_netframework_clrloading_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. | counter | `process` |
| `windows_netframework_clrloading_classes_loaded_total` | Displays the cumulative number of classes loaded in all assemblies since the application started. | counter | `process` |
| `windows_netframework_clrloading_class_load_failures_total` | Displays the peak number of classes that have failed to load since the application started. | counter | `process` |
### CLR Locks and Threads
| Name | Description | Type | Labels |
|----------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------|-----------|
| `windows_netframework_clrlocksandthreads_current_queue_length` | Displays the total number of threads that are currently waiting to acquire a managed lock in the application. | gauge | `process` |
| `windows_netframework_clrlocksandthreads_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. | gauge | `process` |
| `windows_netframework_clrlocksandthreads_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. | gauge | `process` |
| `windows_netframework_clrlocksandthreads_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. | gauge | `process` |
| `windows_netframework_clrlocksandthreads_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. | counter | `process` |
| `windows_netframework_clrlocksandthreads_queue_length_total` | Displays the total number of threads that waited to acquire a managed lock since the application started. | counter | `process` |
| `windows_netframework_clrlocksandthreads_contentions_total` | Displays the total number of times that threads in the runtime have attempted to acquire a managed lock unsuccessfully. | counter | `process` |
### CLR Memory
| Name | Description | Type | Labels |
|----------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------|-----------|
| `windows_netframework_clrmemory_allocated_bytes_total` | Displays the total number of bytes allocated on the garbage collection heap. | counter | `process` |
| `windows_netframework_clrmemory_finalization_survivors` | Displays the number of garbage-collected objects that survive a collection because they are waiting to be finalized. | gauge | `process` |
| `windows_netframework_clrmemory_heap_size_bytes` | Displays the maximum bytes that can be allocated; it does not indicate the current number of bytes allocated. | gauge | `process` |
| `windows_netframework_clrmemory_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. | gauge | `process` |
| `windows_netframework_clrmemory_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. | gauge | `process` |
| `windows_netframework_clrmemory_collections_total` | Displays the number of times the generation objects are garbage collected since the application started. | counter | `process` |
| `windows_netframework_clrmemory_induced_gc_total` | Displays the peak number of times garbage collection was performed because of an explicit call to GC.Collect. | counter | `process` |
| `windows_netframework_clrmemory_number_pinned_objects` | Displays the number of pinned objects encountered in the last garbage collection. | gauge | `process` |
| `windows_netframework_clrmemory_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. | gauge | `process` |
| `windows_netframework_clrmemory_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. | gauge | `process` |
| `windows_netframework_clrmemory_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. | gauge | `process` |
| `windows_netframework_clrmemory_gc_time_percent` | Displays the percentage of time that was spent performing a garbage collection in the last sample. | gauge | `process` |
### CLR Remoting
| Name | Description | Type | Labels |
|-----------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------|---------|-----------|
| `windows_netframework_clrremoting_channels_total` | Displays the total number of remoting channels registered across all application domains since application started. | counter | `process` |
| `windows_netframework_clrremoting_context_bound_classes_loaded` | Displays the current number of context-bound classes that are loaded. | gauge | `process` |
| `windows_netframework_clrremoting_context_bound_objects_total` | Displays the total number of context-bound objects allocated. | counter | `process` |
| `windows_netframework_clrremoting_context_proxies_total` | Displays the total number of remoting proxy objects in this process since it started. | counter | `process` |
| `windows_netframework_clrremoting_contexts` | Displays the current number of remoting contexts in the application. | gauge | `process` |
| `windows_netframework_clrremoting_remote_calls_total` | Displays the total number of remote procedure calls invoked since the application started. | counter | `process` |
### CLR Security
| Name | Description | Type | Labels |
|-----------------------------------------------------------|-----------------------------------------------------------------------------------------------------------|---------|-----------|
| `windows_netframework_clrsecurity_link_time_checks_total` | Displays the total number of link-time code access security checks since the application started. | counter | `process` |
| `windows_netframework_clrsecurity_rt_checks_time_percent` | Displays the percentage of time spent performing runtime code access security checks in the last sample. | gauge | `process` |
| `windows_netframework_clrsecurity_stack_walk_depth` | Displays the depth of the stack during that last runtime code access security check. | gauge | `process` |
| `windows_netframework_clrsecurity_runtime_checks_total` | Displays the total number of runtime code access security checks performed since the application started. | 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!_

View File

@@ -1,31 +0,0 @@
# 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!_

View File

@@ -1,30 +0,0 @@
# 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!_

View File

@@ -1,31 +0,0 @@
# netframework_clrjit collector
The netframework_clrjit collector exposes metrics about the dotnet Just-in-Time compiler.
|||
-|-
Metric name prefix | `netframework_clrjit`
Classes | `Win32_PerfRawData_NETFramework_NETCLRJit`
Enabled by default? | No
## Flags
None
## Metrics
Name | Description | Type | Labels
-----|-------------|------|-------
`windows_netframework_clrjit_jit_methods_total` | Displays the total number of methods JIT-compiled since the application started. This counter does not include pre-JIT-compiled methods. | counter | `process`
`windows_netframework_clrjit_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. | gauge | `process`
`windows_netframework_clrjit_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. | counter | `process`
`windows_netframework_clrjit_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 | 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!_

View File

@@ -1,36 +0,0 @@
# netframework_clrloading collector
The netframework_clrloading collector exposes metrics about the dotnet loader.
|||
-|-
Metric name prefix | `netframework_clrloading`
Classes | `Win32_PerfRawData_NETFramework_NETCLRLoading`
Enabled by default? | No
## Flags
None
## Metrics
Name | Description | Type | Labels
-----|-------------|------|-------
`windows_netframework_clrloading_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. | gauge | `process`
`windows_netframework_clrloading_appdomains_loaded_current` | Displays the current number of application domains loaded in this application. | gauge | `process`
`windows_netframework_clrloading_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. | gauge | `process`
`windows_netframework_clrloading_classes_loaded_current` | Displays the current number of classes loaded in all assemblies. | gauge | `process`
`windows_netframework_clrloading_appdomains_loaded_total` | Displays the peak number of application domains loaded since the application started. | counter | `process`
`windows_netframework_clrloading_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. | counter | `process`
`windows_netframework_clrloading_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. | counter | `process`
`windows_netframework_clrloading_classes_loaded_total` | Displays the cumulative number of classes loaded in all assemblies since the application started. | counter | `process`
`windows_netframework_clrloading_class_load_failures_total` | Displays the peak number of classes that have failed to load since the application started. | 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!_

View File

@@ -1,34 +0,0 @@
# netframework_clrlocksandthreads collector
The netframework_clrlocksandthreads collector exposes metrics about locks and threads in dotnet applications.
|||
-|-
Metric name prefix | `netframework_clrlocksandthreads`
Classes | `Win32_PerfRawData_NETFramework_NETCLRLocksAndThreads`
Enabled by default? | No
## Flags
None
## Metrics
Name | Description | Type | Labels
-----|-------------|------|-------
`windows_netframework_clrlocksandthreads_current_queue_length` | Displays the total number of threads that are currently waiting to acquire a managed lock in the application. | gauge | `process`
`windows_netframework_clrlocksandthreads_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. | gauge | `process`
`windows_netframework_clrlocksandthreads_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. | gauge | `process`
`windows_netframework_clrlocksandthreads_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. | gauge | `process`
`windows_netframework_clrlocksandthreads_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. | counter | `process`
`windows_netframework_clrlocksandthreads_queue_length_total` | Displays the total number of threads that waited to acquire a managed lock since the application started. | counter | `process`
`windows_netframework_clrlocksandthreads_contentions_total` | Displays the total number of times that threads in the runtime have attempted to acquire a managed lock unsuccessfully. | 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!_

View File

@@ -1,39 +0,0 @@
# netframework_clrmemory collector
The netframework_clrmemory collector exposes metrics about memory in dotnet applications.
|||
-|-
Metric name prefix | `netframework_clrmemory`
Classes | `Win32_PerfRawData_NETFramework_NETCLRMemory`
Enabled by default? | No
## Flags
None
## Metrics
Name | Description | Type | Labels
-----|-------------|------|-------
`windows_netframework_clrmemory_allocated_bytes_total` | Displays the total number of bytes allocated on the garbage collection heap. | counter | `process`
`windows_netframework_clrmemory_finalization_survivors` | Displays the number of garbage-collected objects that survive a collection because they are waiting to be finalized. | gauge | `process`
`windows_netframework_clrmemory_heap_size_bytes` | Displays the maximum bytes that can be allocated; it does not indicate the current number of bytes allocated. | gauge | `process`
`windows_netframework_clrmemory_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. | gauge | `process`
`windows_netframework_clrmemory_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. | gauge | `process`
`windows_netframework_clrmemory_collections_total` | Displays the number of times the generation objects are garbage collected since the application started. | counter | `process`
`windows_netframework_clrmemory_induced_gc_total` | Displays the peak number of times garbage collection was performed because of an explicit call to GC.Collect. | counter | `process`
`windows_netframework_clrmemory_number_pinned_objects` | Displays the number of pinned objects encountered in the last garbage collection. | gauge | `process`
`windows_netframework_clrmemory_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. | gauge | `process`
`windows_netframework_clrmemory_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. | gauge | `process`
`windows_netframework_clrmemory_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. | gauge | `process`
`windows_netframework_clrmemory_gc_time_percent` | Displays the percentage of time that was spent performing a garbage collection in the last sample. | gauge | `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!_

View File

@@ -1,33 +0,0 @@
# netframework_clrremoting collector
The netframework_clrremoting collector exposes metrics about dotnet remoting.
|||
-|-
Metric name prefix | `netframework_clrremoting`
Classes | `Win32_PerfRawData_NETFramework_NETCLRRemoting`
Enabled by default? | No
## Flags
None
## Metrics
Name | Description | Type | Labels
-----|-------------|------|-------
`windows_netframework_clrremoting_channels_total` | Displays the total number of remoting channels registered across all application domains since application started. | counter | `process`
`windows_netframework_clrremoting_context_bound_classes_loaded` | Displays the current number of context-bound classes that are loaded. | gauge | `process`
`windows_netframework_clrremoting_context_bound_objects_total` | Displays the total number of context-bound objects allocated. | counter | `process`
`windows_netframework_clrremoting_context_proxies_total` | Displays the total number of remoting proxy objects in this process since it started. | counter | `process`
`windows_netframework_clrremoting_contexts` | Displays the current number of remoting contexts in the application. | gauge | `process`
`windows_netframework_clrremoting_remote_calls_total` | Displays the total number of remote procedure calls invoked since the application started. | 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!_

View File

@@ -1,31 +0,0 @@
# netframework_clrsecurity collector
The netframework_clrsecurity collector exposes metrics about security checks in dotnet applications
|||
-|-
Metric name prefix | `netframework_clrsecurity`
Classes | `Win32_PerfRawData_NETFramework_NETCLRSecurity`
Enabled by default? | No
## Flags
None
## Metrics
Name | Description | Type | Labels
-----|-------------|------|-------
`windows_netframework_clrsecurity_link_time_checks_total` | Displays the total number of link-time code access security checks since the application started. | counter | `process`
`windows_netframework_clrsecurity_rt_checks_time_percent` | Displays the percentage of time spent performing runtime code access security checks in the last sample. | gauge | `process`
`windows_netframework_clrsecurity_stack_walk_depth` | Displays the depth of the stack during that last runtime code access security check. | gauge | `process`
`windows_netframework_clrsecurity_runtime_checks_total` | Displays the total number of runtime code access security checks performed since the application started. | 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!_

View File

@@ -14,58 +14,26 @@ None
## Metrics
Name | Description | Type | Labels
-----|-------------|------|-------
`windows_os_info` | Contains full product name & version in labels. Note that the `major_version` for Windows 11 is "10"; a build number greater than 22000 represents Windows 11. | gauge | `product`, `version`, `major_version`, `minor_version`, `build_number`
`windows_os_paging_limit_bytes` | Total number of bytes that can be stored in the operating system paging files. 0 (zero) indicates that there are no paging files | gauge | None
`windows_os_paging_free_bytes` | Number of bytes that can be mapped into the operating system paging files without causing any other pages to be swapped out | gauge | None
`windows_os_physical_memory_free_bytes` | Bytes of physical memory currently unused and available | gauge | None
`windows_os_time` | Current time as reported by the operating system, in [Unix time](https://en.wikipedia.org/wiki/Unix_time). See [time.Unix()](https://golang.org/pkg/time/#Unix) for details | gauge | None
`windows_os_timezone` | Current timezone as reported by the operating system. See [time.Zone()](https://golang.org/pkg/time/#Time.Zone) for details | gauge | `timezone`
`windows_os_processes` | Number of process contexts currently loaded or running on the operating system | gauge | None
`windows_os_processes_limit` | Maximum number of process contexts the operating system can support. The default value set by the provider is 4294967295 (0xFFFFFFFF) | gauge | None
`windows_os_process_memory_limit_bytes` | Maximum number of bytes of memory that can be allocated to a process | gauge | None
`windows_os_users` | Number of user sessions for which the operating system is storing state information currently. For a list of current active logon sessions, see [`logon`](collector.logon.md) | gauge | None
`windows_os_virtual_memory_bytes` | Bytes of virtual memory | gauge | None
`windows_os_visible_memory_bytes` | Total bytes of physical memory available to the operating system. This value does not necessarily indicate the true amount of physical memory, but what is reported to the operating system as available to it | gauge | None
`windows_os_virtual_memory_free_bytes` | Bytes of virtual memory currently unused and available | gauge | None
| Name | Description | Type | Labels |
|---------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------|------------------------------------------------------------------------|
| `windows_os_info` | Contains full product name & version in labels. Note that the `major_version` for Windows 11 is "10"; a build number greater than 22000 represents Windows 11. | gauge | `product`, `version`, `major_version`, `minor_version`, `build_number` |
| `windows_os_paging_limit_bytes` | Total number of bytes that can be stored in the operating system paging files. 0 (zero) indicates that there are no paging files | gauge | None |
| `windows_os_paging_free_bytes` | Number of bytes that can be mapped into the operating system paging files without causing any other pages to be swapped out | gauge | None |
### Example metric
Show current number of processes
```
windows_os_processes{instance="localhost"}
# HELP windows_os_hostname Labelled system hostname information as provided by ComputerSystem.DNSHostName and ComputerSystem.Domain
# TYPE windows_os_hostname gauge
windows_os_hostname{domain="",fqdn="PC",hostname="PC"} 1
# HELP windows_os_info Contains full product name & version in labels. Note that the "major_version" for Windows 11 is \\"10\\"; a build number greater than 22000 represents Windows 11.
# TYPE windows_os_info gauge
windows_os_info{build_number="19045",major_version="10",minor_version="0",product="Windows 10 Pro",revision="4842",version="10.0.19045"} 1
```
## Useful queries
Find all devices not set to UTC timezone
```
windows_os_timezone{timezone != "UTC"}
```
Show memory usage for instance (%)
```
100 - 100 * windows_os_physical_memory_free_bytes{instance="localhost"} / windows_cs_physical_memory_bytes{instance="localhost"}
```
_This collector does not yet have useful queries, we would appreciate your help adding them!_
## Alerting examples
**prometheus.rules**
```yaml
# Alert on hosts that have exhausted all available physical memory
- alert: MemoryExhausted
expr: windows_os_physical_memory_free_bytes == 0
for: 10m
labels:
severity: high
annotations:
summary: "Host {{ $labels.instance }} is out of memory"
description: "{{ $labels.instance }} has exhausted all available physical memory"
# Alert on hosts with greater than 90% memory usage
- alert: MemoryLow
expr: 100 - 100 * windows_os_physical_memory_free_bytes / windows_cs_physical_memory_bytes > 90
for: 10m
labels:
severity: warning
annotations:
summary: "Memory usage for host {{ $labels.instance }} is greater than 90%"
```
_This collector does not yet have alerting examples, we would appreciate your help adding them!_

114
docs/collector.perfdata.md Normal file
View File

@@ -0,0 +1,114 @@
# Perfdata collector
The perfdata collector exposes any configured metric.
| | |
|---------------------|-------------------------|
| Metric name prefix | `perfdata` |
| Data source | Performance Data Helper |
| Enabled by default? | No |
## Flags
### `--collector.perfdata.objects`
Objects is a list of objects to collect metrics from. The value takes the form of a JSON array of strings. YAML is also supported.
The collector supports only english named counter. Localized counter-names are not supported.
#### Schema
YAML:
```yaml
- object: "Processor Information"
instances: ["*"]
instance_label: "core"
counters:
"% Processor Time": {}
- object: "Memory"
counters:
"Cache Faults/sec":
type: "counter"
```
JSON:
```json
[
{"object":"Processor Information","instance_label": "core","instances":["*"],"counters": {"% Processor Time": {}}},
{"object":"Memory","counters": {"Cache Faults/sec": {"type": "counter"}}}
]
```
#### name
ObjectName is the Object to query for, like Processor, DirectoryServices, LogicalDisk or similar.
The collector supports only english named counter. Localized counter-names are not supported.
#### instances
The instances key (this is an array) declares the instances of a counter you would like returned, it can be one or more values.
Example: Instances = `["C:","D:","E:"]`
This will return only for the instances C:, D: and E: where relevant. To get all instances of a Counter, use `["*"]` only.
Some Objects like `Memory` do not have instances to select from at all. In this case, the `instances` key can be omitted.
#### counters
The Counters key (this is an object) declares the counters of the ObjectName you would like returned, it can also be one or more values.
Example: Counters = `{"% Idle Time": {}, "% Disk Read Time": {}, "% Disk Write Time": {}}`
This must be specified for every counter you want the results. Wildcards are not supported.
#### counters Sub-Schema
##### type
This key is optional. It indicates the type of the counter. The value can be `counter` or `gauge`.
If not specified, the windows_exporter will try to determine the type based on the counter type.
### Example
```
# HELP windows_perfdata_memory_cache_faults_sec
# TYPE windows_perfdata_memory_cache_faults_sec counter
windows_perfdata_memory_cache_faults_sec 2.369977e+07
# HELP windows_perfdata_processor_information__processor_time
# TYPE windows_perfdata_processor_information__processor_time gauge
windows_perfdata_processor_information__processor_time{instance="0,0"} 1.7259640625e+11
windows_perfdata_processor_information__processor_time{instance="0,1"} 1.7576796875e+11
windows_perfdata_processor_information__processor_time{instance="0,10"} 2.2704234375e+11
windows_perfdata_processor_information__processor_time{instance="0,11"} 2.3069296875e+11
windows_perfdata_processor_information__processor_time{instance="0,12"} 2.3302265625e+11
windows_perfdata_processor_information__processor_time{instance="0,13"} 2.32851875e+11
windows_perfdata_processor_information__processor_time{instance="0,14"} 2.3282421875e+11
windows_perfdata_processor_information__processor_time{instance="0,15"} 2.3271234375e+11
windows_perfdata_processor_information__processor_time{instance="0,16"} 2.329590625e+11
windows_perfdata_processor_information__processor_time{instance="0,17"} 2.32800625e+11
windows_perfdata_processor_information__processor_time{instance="0,18"} 2.3194359375e+11
windows_perfdata_processor_information__processor_time{instance="0,19"} 2.32380625e+11
windows_perfdata_processor_information__processor_time{instance="0,2"} 1.954765625e+11
windows_perfdata_processor_information__processor_time{instance="0,20"} 2.3259765625e+11
windows_perfdata_processor_information__processor_time{instance="0,21"} 2.3268515625e+11
windows_perfdata_processor_information__processor_time{instance="0,22"} 2.3301765625e+11
windows_perfdata_processor_information__processor_time{instance="0,23"} 2.3264328125e+11
windows_perfdata_processor_information__processor_time{instance="0,3"} 1.94745625e+11
windows_perfdata_processor_information__processor_time{instance="0,4"} 2.2011453125e+11
windows_perfdata_processor_information__processor_time{instance="0,5"} 2.27244375e+11
windows_perfdata_processor_information__processor_time{instance="0,6"} 2.25501875e+11
windows_perfdata_processor_information__processor_time{instance="0,7"} 2.2995265625e+11
windows_perfdata_processor_information__processor_time{instance="0,8"} 2.2929890625e+11
windows_perfdata_processor_information__processor_time{instance="0,9"} 2.313540625e+11
windows_perfdata_processor_information__processor_time{instance="0,_Total"} 2.23009459635e+11
```
## Metrics
The perfdata collector returns metrics based on the user configuration.
The metrics are named based on the object name and the counter name.
The instance name is added as a label to the metric.

View File

@@ -37,11 +37,6 @@ Enables IIS process name queries. IIS process names are combined with their app
Disabled by default, and can be enabled with `--collector.process.iis=true`.
### `--collector.process.report-owner`
Enables reporting of the process owner. This is a potentially expensive operation.
Disabled by default, and can be enabled with `--collector.process.report-owner`.
### Example
To match all firefox processes: `--collector.process.include="firefox.*"`.
@@ -74,23 +69,24 @@ w3wp_Test
## Metrics
| Name | Description | Type | Labels |
|---------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------|-----------------------------------------------------------------|
| `windows_process_start_time` | Time of process start | gauge | `process`, `process_id`, `creating_process_id`, `owner` |
| `windows_process_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. | counter | `process`, `process_id`, `creating_process_id`, `owner`, `mode` |
| `windows_process_handles` | Total number of handles the process has open. This number is the sum of the handles currently open by each thread in the process. | gauge | `process`, `process_id`, `creating_process_id`, `owner` |
| `windows_process_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. | counter | `process`, `process_id`, `creating_process_id`, `owner`, `mode` |
| `windows_process_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. | counter | `process`, `process_id`, `creating_process_id`, `owner`, `mode` |
| `windows_process_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. | counter | `process`, `process_id`, `creating_process_id`, `owner` |
| `windows_process_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. | gauge | `process`, `process_id`, `creating_process_id`, `owner` |
| `windows_process_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. | gauge | `process`, `process_id`, `creating_process_id`, `owner`, `pool` |
| `windows_process_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. | gauge | `process`, `process_id`, `creating_process_id`, `owner` |
| `windows_process_private_bytes` | Current number of bytes this process has allocated that cannot be shared with other processes. | gauge | `process`, `process_id`, `creating_process_id`, `owner` |
| `windows_process_threads` | 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. | gauge | `process`, `process_id`, `creating_process_id`, `owner` |
| `windows_process_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. | gauge | `process`, `process_id`, `creating_process_id`, `owner` |
| `windows_process_working_set_private_bytes` | Size of the working set, in bytes, that is use for this process only and not shared nor shareable by other processes. | gauge | `process`, `process_id`, `creating_process_id`, `owner` |
| `windows_process_working_set_peak_bytes` | Maximum size, in bytes, of 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 will then be soft-faulted back into the Working Set before they leave main memory. | gauge | `process`, `process_id`, `creating_process_id`, `owner` |
| `windows_process_working_set_bytes` | 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. | gauge | `process`, `process_id`, `creating_process_id`, `owner` |
| Name | Description | Type | Labels |
|---------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------|---------------------------------------------------------------------------------------|
| `windows_process_info` | A metric with a constant '1' value labeled with process information | gauge | `process`, `process_id`, `creating_process_id`, `process_group_id`,`owner`, `cmdline` |
| `windows_process_start_time` | Time of process start | gauge | `process`, `process_id` |
| `windows_process_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. | counter | `process`, `process_id`, `mode` |
| `windows_process_handles` | Total number of handles the process has open. This number is the sum of the handles currently open by each thread in the process. | gauge | `process`, `process_id` |
| `windows_process_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. | counter | `process`, `process_id`, `mode` |
| `windows_process_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. | counter | `process`, `process_id`, `mode` |
| `windows_process_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. | counter | `process`, `process_id` |
| `windows_process_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. | gauge | `process`, `process_id` |
| `windows_process_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. | gauge | `process`, `process_id`, `pool` |
| `windows_process_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. | gauge | `process`, `process_id` |
| `windows_process_private_bytes` | Current number of bytes this process has allocated that cannot be shared with other processes. | gauge | `process`, `process_id` |
| `windows_process_threads` | 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. | gauge | `process`, `process_id` |
| `windows_process_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. | gauge | `process`, `process_id` |
| `windows_process_working_set_private_bytes` | Size of the working set, in bytes, that is use for this process only and not shared nor shareable by other processes. | gauge | `process`, `process_id` |
| `windows_process_working_set_peak_bytes` | Maximum size, in bytes, of 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 will then be soft-faulted back into the Working Set before they leave main memory. | gauge | `process`, `process_id` |
| `windows_process_working_set_bytes` | 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. | gauge | `process`, `process_id` |
### Example metric
_This collector does not yet have explained examples, we would appreciate your help adding them!_

View File

@@ -2,47 +2,24 @@
The service collector exposes metrics about Windows Services
The collector exists in 2 different version. Version 1 is using WMI to query all services and is able to provide additional
information. Version 2 is a more efficient solution by directly connecting to the service manager, but is not able to
provide additional information like `run_as` or start configuration
## Flags
### `--collector.service.services-where`
A WMI filter on which services to include. Recommended to keep down number of returned metrics.
Example: `--collector.service.services-where="Name='windows_exporter'"`
Example config win_exporter.yml for multiple services: `services-where: Name='SQLServer' OR Name='Couchbase' OR Name='Spooler' OR Name='ActiveMQ'`
### `--collector.service.use-api`
Uses API calls instead of WMI for performance optimization. **Note** the previous flag (`--collector.service.services-where`) won't have any effect on this mode.
### `--collector.service.v2`
Version 2 of the service collector. Is using API calls for performance optimization. **Note** the previous flag (`--collector.service.services-where`) won't have any effect on this mode.
For additional performance reasons, it doesn't provide any additional information like `run_as` or start configuration.
# collector V1
|||
-|-
Metric name prefix | `service`
Classes | [`Win32_Service`](https://msdn.microsoft.com/en-us/library/aa394418(v=vs.85).aspx)
Classes | none
Enabled by default? | Yes
## Flags
None
## Metrics
Name | Description | Type | Labels
-----|-------------|------|-------
`windows_service_info` | Contains service information in labels, constant 1 | gauge | name, display_name, process_id, run_as
`windows_service_state` | The state of the service, 1 if the current state, 0 otherwise | gauge | name, state
`windows_service_start_mode` | The start mode of the service, 1 if the current start mode, 0 otherwise | gauge | name, start_mode
`windows_service_status` | The status of the service, 1 if the current status, 0 otherwise | gauge | name, status
For the values of the `state`, `start_mode`, `status` and `run_as` labels, see below.
| Name | Description | Type | Labels |
|------------------------------|-----------------------------------------------------------------------------------------------|-------|---------------------------------------|
| `windows_service_info` | Contains service information run as user in labels, constant 1 | gauge | name, display_name, path_name, run_as |
| `windows_service_start_mode` | The start mode of the service, 1 if the current start mode, 0 otherwise | gauge | name, start_mode |
| `windows_service_state` | The state of the service, 1 if the current state, 0 otherwise | gauge | name, state |
| `windows_service_process` | Process of started service. The value is the creation time of the process as a unix timestamp | gauge | name, process_id |
### States
@@ -65,81 +42,50 @@ A service can have the following start modes:
- `manual`
- `disabled`
### Status (not available in API mode)
A service can have any of the following statuses:
- `ok`
- `error`
- `degraded`
- `unknown`
- `pred fail`
- `starting`
- `stopping`
- `service`
- `stressed`
- `nonrecover`
- `no contact`
- `lost comm`
Note that there is some overlap with service state.
### Run As
Account name under which a service runs. Depending on the service type, the account name may be in the form of "DomainName\Username" or UPN format ("Username@DomainName").
It corresponds to the `StartName` attribute of the `Win32_Service` class.
`StartName` attribute can be NULL and in such case the label is reported as an empty string. Notice that if the attribute is NULL the service is logged on as the `LocalSystem` account or, for kernel or system-level drive, it runs with a default object name created by the I/O system based on the service name, for example, DWDOM\Admin.
### Example metric
Lists the services that have a 'disabled' start mode.
```
windows_service_start_mode{exported_name=~"(mssqlserver|sqlserveragent)",start_mode="disabled"}
```
## Useful queries
Counts the number of Microsoft SQL Server/Agent Processes
```
count(windows_service_state{exported_name=~"(sqlserveragent|mssqlserver)",state="running"})
```
# collector V2
|||
-|-
Metric name prefix | `service`
Classes | none
Enabled by default? | No
## Metrics
Name | Description | Type | Labels
-----|-------------|------|-------
`windows_service_state` | The state of the service, 1 if the current state, 0 otherwise | gauge | name, display_name, state
### States
A service can be in the following states:
- `stopped`
- `start pending`
- `stop pending`
- `running`
- `continue pending`
- `pause pending`
- `paused`
- `unknown`
### Example metric
```
windows_service_state{display_name="Declared Configuration(DC) service",name="dcsvc",status="continue pending"} 0
windows_service_state{display_name="Declared Configuration(DC) service",name="dcsvc",status="pause pending"} 0
windows_service_state{display_name="Declared Configuration(DC) service",name="dcsvc",status="paused"} 0
windows_service_state{display_name="Declared Configuration(DC) service",name="dcsvc",status="running"} 0
windows_service_state{display_name="Declared Configuration(DC) service",name="dcsvc",status="start pending"} 0
windows_service_state{display_name="Declared Configuration(DC) service",name="dcsvc",status="stop pending"} 0
windows_service_state{display_name="Declared Configuration(DC) service",name="dcsvc",status="stopped"} 1
# HELP windows_service_info A metric with a constant '1' value labeled with service information
# TYPE windows_service_info gauge
windows_service_info{display_name="Declared Configuration(DC) service",name="dcsvc",path_name="C:\\WINDOWS\\system32\\svchost.exe -k netsvcs -p",run_as="LocalSystem"} 1
windows_service_info{display_name="Designs",name="Themes",path_name="C:\\WINDOWS\\System32\\svchost.exe -k netsvcs -p",run_as="LocalSystem"} 1
# HELP windows_service_process Process of started service. The value is the creation time of the process as a unix timestamp.
# TYPE windows_service_process gauge
windows_service_process{name="Themes",process_id="2856"} 1.7244891e+09
# HELP windows_service_start_mode The start mode of the service (StartMode)
# TYPE windows_service_start_mode gauge
windows_service_start_mode{name="Themes",start_mode="auto"} 1
windows_service_start_mode{name="Themes",start_mode="boot"} 0
windows_service_start_mode{name="Themes",start_mode="disabled"} 0
windows_service_start_mode{name="Themes",start_mode="manual"} 0
windows_service_start_mode{name="Themes",start_mode="system"} 0
windows_service_start_mode{name="dcsvc",start_mode="auto"} 0
windows_service_start_mode{name="dcsvc",start_mode="boot"} 0
windows_service_start_mode{name="dcsvc",start_mode="disabled"} 0
windows_service_start_mode{name="dcsvc",start_mode="manual"} 1
windows_service_start_mode{name="dcsvc",start_mode="system"} 0
# HELP windows_service_state The state of the service (State)
# TYPE windows_service_state gauge
windows_service_state{name="Themes",state="continue pending"} 0
windows_service_state{name="Themes",state="pause pending"} 0
windows_service_state{name="Themes",state="paused"} 0
windows_service_state{name="Themes",state="running"} 1
windows_service_state{name="Themes",state="start pending"} 0
windows_service_state{name="Themes",state="stop pending"} 0
windows_service_state{name="Themes",state="stopped"} 0
windows_service_state{name="dcsvc",state="continue pending"} 0
windows_service_state{name="dcsvc",state="pause pending"} 0
windows_service_state{name="dcsvc",state="paused"} 0
windows_service_state{name="dcsvc",state="running"} 0
windows_service_state{name="dcsvc",state="start pending"} 0
windows_service_state{name="dcsvc",state="stop pending"} 0
windows_service_state{name="dcsvc",state="stopped"} 1
```
## Useful queries
@@ -163,8 +109,8 @@ groups:
labels:
severity: high
annotations:
summary: "Service {{ $labels.exported_name }} down"
description: "Service {{ $labels.exported_name }} on instance {{ $labels.instance }} has been down for more than 3 minutes."
summary: "Service {{ $labels.name }} down"
description: "Service {{ $labels.name }} on instance {{ $labels.instance }} has been down for more than 3 minutes."
# Sends an alert when the 'mssqlserver' service is not in the running state for 3 minutes.
- alert: SQL Server DOWN
@@ -173,7 +119,7 @@ groups:
labels:
severity: high
annotations:
summary: "Service {{ $labels.exported_name }} down"
description: "Service {{ $labels.exported_name }} on instance {{ $labels.instance }} has been down for more than 3 minutes."
summary: "Service {{ $labels.name }} down"
description: "Service {{ $labels.name }} on instance {{ $labels.instance }} has been down for more than 3 minutes."
```
In this example, `instance` is the target label of the host. So each alert will be processed per host, which is then used in the alert description.

View File

@@ -5,8 +5,7 @@ The system collector exposes metrics about ...
|||
-|-
Metric name prefix | `system`
Data source | Perflib
Classes | [`Win32_PerfRawData_PerfOS_System`](https://web.archive.org/web/20050830140516/http://msdn.microsoft.com/library/en-us/wmisdk/wmi/win32_perfrawdata_perfos_system.asp)
Data source | Performance Counters
Enabled by default? | Yes
## Flags
@@ -15,14 +14,18 @@ None
## Metrics
Name | Description | Type | Labels
-----|-------------|------|-------
`windows_system_context_switches_total` | Total number of [context switches](https://en.wikipedia.org/wiki/Context_switch) | counter | None
`windows_system_exception_dispatches_total` | Total exceptions dispatched by the system | counter | None
`windows_system_processor_queue_length` | Number of threads in the processor queue. There is a single queue for processor time even on computers with multiple processors. | gauge | None
`windows_system_system_calls_total` | Total combined calls to Windows NT system service routines by all processes running on the computer | counter | None
`windows_system_system_up_time` | Time of last boot of system | gauge | None
`windows_system_threads` | Number of Windows system [threads](https://en.wikipedia.org/wiki/Thread_(computing)) | gauge | None
| Name | Description | Type | Labels |
|---------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------|--------|
| `windows_system_context_switches_total` | Total number of [context switches](https://en.wikipedia.org/wiki/Context_switch) | counter | None |
| `windows_system_exception_dispatches_total` | Total exceptions dispatched by the system | counter | None |
| `windows_system_processes` | Number of process contexts currently loaded or running on the operating system | gauge | None |
| `windows_system_process_limit` | The size of the user-mode portion of the virtual address space of the calling process, in bytes. This value depends on the type of process, the type of processor, and the configuration of the operating system. | gauge | None |
| `windows_system_processor_queue_length` | Number of threads in the processor queue. There is a single queue for processor time even on computers with multiple processors. | gauge | None |
| `windows_system_system_calls_total` | Total combined calls to Windows NT system service routines by all processes running on the computer | counter | None |
| `windows_system_system_up_time` | Time of last boot of system | gauge | None |
| `windows_system_threads` | Number of Windows system [threads](https://en.wikipedia.org/wiki/Thread_(computing)) | gauge | None |
### Example metric
Show current number of system threads
@@ -30,6 +33,11 @@ Show current number of system threads
windows_system_threads{instance="localhost"}
```
Show current number of processes
```
windows_system_processes{instance="localhost"}
```
## Useful queries
Find hosts that have rebooted in the last 24 hours
```

View File

@@ -19,7 +19,6 @@ None
| Name | Description | Type | Labels |
|------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------|-----------------|
| `windows_terminal_services_session_info` | Info about active WTS sessions | gauge | host,user,state |
| `windows_terminal_services_local_session_count` | Number of local Terminal Services sessions. | gauge | `session` |
| `windows_terminal_services_connection_broker_performance_total`* | The total number of connections handled by the Connection Brokers since the service started. | counter | `connection` |
| `windows_terminal_services_handles` | Total number of handles currently opened by this process. This number is the sum of the handles currently opened by each thread in this process. | gauge | `session_name` |
| `windows_terminal_services_page_fault_total` | Rate at which page faults occur in 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. The page may not be retrieved from disk if it is on the standby list and therefore already in main memory. The page also may not be retrieved if it is in use by another process which shares the page. | counter | `session_name` |

View File

@@ -5,11 +5,11 @@ If the Windows Time Service is stopped after collection has started, collector m
Please note the Time Service perflib counters are only available on [Windows Server 2016 or newer](https://docs.microsoft.com/en-us/windows-server/networking/windows-time-service/windows-server-2016-improvements).
|||
-|-
Metric name prefix | `time`
Data source | Perflib
Enabled by default? | No
| | |
|---------------------|---------|
| Metric name prefix | `time` |
| Data source | Perflib |
| Enabled by default? | No |
## Flags
@@ -17,14 +17,16 @@ None
## Metrics
Name | Description | Type | Labels
-----|-------------|------|-------
`windows_time_clock_frequency_Adjustment_ppb_total` | Total adjustment made to the local system clock frequency by W32Time in parts per billion (PPB) units. 1 PPB adjustment implies the system clock was adjusted at a rate of 1 nanosecond per second (1 ns/s). The smallest possible adjustment can vary and is expected to be in the order of 100's of PPB. | counter | None
`windows_time_computed_time_offset_seconds` | Absolute time offset between the system clock and the chosen time source, in seconds. | counter | None
`windows_time_ntp_client_time_sources` | Active number of NTP Time sources being used by the client. This is a count of active, distinct IP addresses of time servers that are responding to this client's requests. | gauge | None
`windows_time_ntp_round_trip_delay_seconds` | Total roundtrip delay experienced by the NTP client in receiving a response from the server for the most recent request, in seconds. This is the time elapsed on the NTP client between transmitting a request to the NTP server and receiving a valid response from the server. | gauge | None
`windows_time_ntp_server_outgoing_responses_total` | Total number of requests responded to by the NTP server. | counter | None
`windows_time_ntp_server_incoming_requests_total` | Total number of requests received by the NTP server. | counter | None
| Name | Description | Type | Labels |
|-----------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------|------------|
| `windows_time_clock_frequency_adjustment_ppb_total` | Total adjustment made to the local system clock frequency by W32Time in parts per billion (PPB) units. 1 PPB adjustment implies the system clock was adjusted at a rate of 1 nanosecond per second (1 ns/s). The smallest possible adjustment can vary and is expected to be in the order of 100's of PPB. | counter | None |
| `windows_time_computed_time_offset_seconds` | The absolute time offset between the system clock and the chosen time source, as computed by the W32Time service in microseconds. When a new valid sample is available, the computed time is updated with the time offset indicated by the sample. This time is the actual time offset of the local clock. W32Time initiates clock correction by using this offset and updates the computed time in between samples with the remaining time offset that needs to be applied to the local clock. Clock accuracy can be tracked by using this performance counter with a low polling interval (for example, 256 seconds or less) and looking for the counter value to be smaller than the desired clock accuracy limit. | gauge | None |
| `windows_time_ntp_client_time_sources` | Active number of NTP Time sources being used by the client. This is a count of active, distinct IP addresses of time servers that are responding to this client's requests. | gauge | None |
| `windows_time_ntp_round_trip_delay_seconds` | Total roundtrip delay experienced by the NTP client in receiving a response from the server for the most recent request, in seconds. This is the time elapsed on the NTP client between transmitting a request to the NTP server and receiving a valid response from the server. | gauge | None |
| `windows_time_ntp_server_outgoing_responses_total` | Total number of requests responded to by the NTP server. | counter | None |
| `windows_time_ntp_server_incoming_requests_total` | Total number of requests received by the NTP server. | counter | None |
| `windows_time_current_timestamp_seconds` | Current time as reported by the operating system, in [Unix time](https://en.wikipedia.org/wiki/Unix_time). See [time.Unix()](https://golang.org/pkg/time/#Unix) for details | gauge | None |
| `windows_time_timezone` | Current timezone as reported by the operating system. | gauge | `timezone` |
### Example metric
_This collector does not yet have explained examples, we would appreciate your help adding them!_

View File

@@ -1,10 +1,10 @@
---
# Note this is not an exhaustive list of all configuration values
collectors:
enabled: cpu,cs,logical_disk,net,os,service,system,textfile
enabled: cpu,cs,logical_disk,net,os,service,system
collector:
service:
services-where: Name='windows_exporter'
include: "windows_exporter"
scheduled_task:
include: /Microsoft/.+
log:

View File

@@ -4,51 +4,41 @@
package main
//goland:noinspection GoUnsortedImport
//nolint:gofumpt
import (
// Its important that we do these first so that we can register with the Windows service control ASAP to avoid timeouts
// Its important that we do these first so that we can register with the Windows service control ASAP to avoid timeouts.
"github.com/prometheus-community/windows_exporter/pkg/initiate"
"encoding/json"
"context"
"errors"
"fmt"
"log/slog"
"net/http"
"net/http/pprof"
"os"
"os/signal"
"os/user"
"runtime"
"sort"
"strings"
winlog "github.com/prometheus-community/windows_exporter/pkg/log"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus-community/windows_exporter/pkg/utils"
"github.com/prometheus-community/windows_exporter/pkg/wmi"
"time"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log/level"
"github.com/prometheus-community/windows_exporter/pkg/collector"
"github.com/prometheus-community/windows_exporter/pkg/config"
"github.com/prometheus-community/windows_exporter/pkg/httphandler"
winlog "github.com/prometheus-community/windows_exporter/pkg/log"
"github.com/prometheus-community/windows_exporter/pkg/log/flag"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus-community/windows_exporter/pkg/utils"
"github.com/prometheus/common/version"
"github.com/prometheus/exporter-toolkit/web"
webflag "github.com/prometheus/exporter-toolkit/web/kingpinflag"
"golang.org/x/sys/windows"
)
// https://learn.microsoft.com/en-us/windows/win32/procthread/process-security-and-access-rights
const PROCESS_ALL_ACCESS = windows.STANDARD_RIGHTS_REQUIRED | windows.SYNCHRONIZE | windows.SPECIFIC_RIGHTS_ALL
// Same struct prometheus uses for their /version endpoint.
// Separate copy to avoid pulling all of prometheus as a dependency
type prometheusVersion struct {
Version string `json:"version"`
Revision string `json:"revision"`
Branch string `json:"branch"`
BuildUser string `json:"buildUser"`
BuildDate string `json:"buildDate"`
GoVersion string `json:"goVersion"`
}
// Mapping of priority names to uin32 values required by windows.SetPriorityClass
// Mapping of priority names to uin32 values required by windows.SetPriorityClass.
var priorityStringToInt = map[string]uint32{
"realtime": windows.REALTIME_PRIORITY_CLASS,
"high": windows.HIGH_PRIORITY_CLASS,
@@ -58,30 +48,19 @@ var priorityStringToInt = map[string]uint32{
"low": windows.IDLE_PRIORITY_CLASS,
}
func setPriorityWindows(pid int, priority uint32) error {
handle, err := windows.OpenProcess(PROCESS_ALL_ACCESS, false, uint32(pid))
if err != nil {
return err
}
//nolint:errcheck
defer windows.CloseHandle(handle) // Technically this can fail, but we ignore it
err = windows.SetPriorityClass(handle, priority)
if err != nil {
return err
}
return nil
func main() {
os.Exit(run())
}
func main() {
func run() int {
app := kingpin.New("windows_exporter", "A metrics collector for Windows.")
var (
configFile = app.Flag(
"config.file",
"YAML configuration file to use. Values set in this file will be overridden by CLI flags.",
).String()
insecure_skip_verify = app.Flag(
insecureSkipVerify = app.Flag(
"config.file.insecure-skip-verify",
"Skip TLS verification in loading YAML configuration.",
).Default("false").Bool()
@@ -131,25 +110,41 @@ func main() {
// Load values from configuration file(s). Executable flags must first be parsed, in order
// to load the specified file(s).
kingpin.MustParse(app.Parse(os.Args[1:]))
logger, err := winlog.New(winlogConfig)
if err != nil {
_ = level.Error(logger).Log("err", err)
os.Exit(1)
if _, err := app.Parse(os.Args[1:]); err != nil {
//nolint:sloglint // we do not have an logger yet
slog.Error("Failed to parse CLI args",
slog.Any("err", err),
)
return 1
}
_ = level.Debug(logger).Log("msg", "Logging has Started")
logger, err := winlog.New(winlogConfig)
if err != nil {
//nolint:sloglint // we do not have an logger yet
slog.Error("failed to create logger",
slog.Any("err", err),
)
return 1
}
if *configFile != "" {
resolver, err := config.NewResolver(*configFile, logger, *insecure_skip_verify)
resolver, err := config.NewResolver(*configFile, logger, *insecureSkipVerify)
if err != nil {
_ = level.Error(logger).Log("msg", "could not load config file", "err", err)
os.Exit(1)
logger.Error("could not load config file",
slog.Any("err", err),
)
return 1
}
err = resolver.Bind(app, os.Args[1:])
if err != nil {
_ = level.Error(logger).Log("err", err)
os.Exit(1)
if err = resolver.Bind(app, os.Args[1:]); err != nil {
logger.Error("Failed to bind configuration",
slog.Any("err", err),
)
return 1
}
// NOTE: This is temporary fix for issue #1092, calling kingpin.Parse
@@ -158,138 +153,188 @@ func main() {
*webConfig.WebListenAddresses = (*webConfig.WebListenAddresses)[1:]
// Parse flags once more to include those discovered in configuration file(s).
kingpin.MustParse(app.Parse(os.Args[1:]))
if _, err = app.Parse(os.Args[1:]); err != nil {
logger.Error("Failed to parse CLI args from YAML file",
slog.Any("err", err),
)
return 1
}
logger, err = winlog.New(winlogConfig)
if err != nil {
_ = level.Error(logger).Log("err", err)
os.Exit(1)
//nolint:sloglint // we do not have an logger yet
slog.Error("failed to create logger",
slog.Any("err", err),
)
return 1
}
}
if *printCollectors {
collectorNames := collector.Available()
sort.Strings(collectorNames)
logger.Debug("Logging has Started")
fmt.Printf("Available collectors:\n")
for _, n := range collectorNames {
fmt.Printf(" - %s\n", n)
if *printCollectors {
printCollectorsToStdout()
return 0
}
// Only set process priority if a non-default and valid value has been set
if priority, ok := priorityStringToInt[*processPriority]; ok && priority != windows.NORMAL_PRIORITY_CLASS {
logger.Debug("setting process priority to " + *processPriority)
if err = setPriorityWindows(os.Getpid(), priority); err != nil {
logger.Error("failed to set process priority",
slog.Any("err", err),
)
return 1
}
}
enabledCollectorList := utils.ExpandEnabledCollectors(*enabledCollectors)
collectors.Enable(enabledCollectorList)
// Initialize collectors before loading
if err = collectors.Build(logger); err != nil {
logger.Error("Couldn't load collectors",
slog.Any("err", err),
)
return 1
}
if err = collectors.SetPerfCounterQuery(logger); err != nil {
logger.Error("Couldn't set performance counter query",
slog.Any("err", err),
)
return 1
}
logCurrentUser(logger)
logger.Info("Enabled collectors: " + strings.Join(enabledCollectorList, ", "))
if utils.PDHEnabled() {
logger.Info("Using performance data helper from PHD.dll for performance counter collection. This is in experimental state.")
}
mux := http.NewServeMux()
mux.Handle("GET /health", httphandler.NewHealthHandler())
mux.Handle("GET /version", httphandler.NewVersionHandler())
mux.Handle("GET "+*metricsPath, httphandler.New(logger, collectors, &httphandler.Options{
DisableExporterMetrics: *disableExporterMetrics,
TimeoutMargin: *timeoutMargin,
MaxRequests: *maxRequests,
}))
if *debugEnabled {
mux.HandleFunc("GET /debug/pprof/", pprof.Index)
mux.HandleFunc("GET /debug/pprof/cmdline", pprof.Cmdline)
mux.HandleFunc("GET /debug/pprof/profile", pprof.Profile)
mux.HandleFunc("GET /debug/pprof/symbol", pprof.Symbol)
mux.HandleFunc("GET /debug/pprof/trace", pprof.Trace)
}
logger.Info("Starting windows_exporter",
slog.String("version", version.Version),
slog.String("branch", version.Branch),
slog.String("revision", version.GetRevision()),
slog.String("goversion", version.GoVersion),
slog.String("builddate", version.BuildDate),
slog.Int("maxprocs", runtime.GOMAXPROCS(0)),
)
server := &http.Server{
ReadHeaderTimeout: 5 * time.Second,
IdleTimeout: 60 * time.Second,
ReadTimeout: 5 * time.Second,
WriteTimeout: 5 * time.Minute,
Handler: mux,
}
errCh := make(chan error, 1)
go func() {
if err := web.ListenAndServe(server, webConfig, logger); err != nil && !errors.Is(err, http.ErrServerClosed) {
errCh <- err
}
errCh <- nil
}()
ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt, os.Kill)
defer stop()
select {
case <-ctx.Done():
logger.Info("Shutting down windows_exporter via kill signal")
case <-initiate.StopCh:
logger.Info("Shutting down windows_exporter via service control")
case err := <-errCh:
if err != nil {
logger.Error("Failed to start windows_exporter",
slog.Any("err", err),
)
return 1
}
}
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
_ = server.Shutdown(ctx)
logger.Info("windows_exporter has shut down")
return 0
}
func printCollectorsToStdout() {
collectorNames := collector.Available()
sort.Strings(collectorNames)
fmt.Println("Available collectors:") //nolint:forbidigo
for _, n := range collectorNames {
fmt.Printf(" - %s\n", n) //nolint:forbidigo
}
}
func logCurrentUser(logger *slog.Logger) {
if u, err := user.Current(); err == nil {
logger.Info("Running as " + u.Username)
if strings.Contains(u.Username, "ContainerAdministrator") || strings.Contains(u.Username, "ContainerUser") {
logger.Warn("Running as a preconfigured Windows Container user. This may mean you do not have Windows HostProcess containers configured correctly and some functionality will not work as expected.")
}
return
}
// Only set process priority if a non-default and valid value has been set
if *processPriority != "normal" && priorityStringToInt[*processPriority] != 0 {
_ = level.Debug(logger).Log("msg", "setting process priority to "+*processPriority)
err = setPriorityWindows(os.Getpid(), priorityStringToInt[*processPriority])
if err != nil {
_ = level.Error(logger).Log("msg", "failed to set process priority", "err", err)
os.Exit(1)
}
}
if err = wmi.InitWbem(logger); err != nil {
_ = level.Error(logger).Log("err", err)
os.Exit(1)
}
enabledCollectorList := utils.ExpandEnabledCollectors(*enabledCollectors)
collectors.Enable(enabledCollectorList)
collectors.SetLogger(logger)
// Initialize collectors before loading
err = collectors.Build()
if err != nil {
_ = level.Error(logger).Log("msg", "Couldn't load collectors", "err", err)
os.Exit(1)
}
err = collectors.SetPerfCounterQuery()
if err != nil {
_ = level.Error(logger).Log("msg", "Couldn't set performance counter query", "err", err)
os.Exit(1)
}
if u, err := user.Current(); err != nil {
_ = level.Warn(logger).Log("msg", "Unable to determine which user is running this exporter. More info: https://github.com/golang/go/issues/37348")
} else {
_ = level.Info(logger).Log("msg", fmt.Sprintf("Running as %v", u.Username))
if strings.Contains(u.Username, "ContainerAdministrator") || strings.Contains(u.Username, "ContainerUser") {
_ = level.Warn(logger).Log("msg", "Running as a preconfigured Windows Container user. This may mean you do not have Windows HostProcess containers configured correctly and some functionality will not work as expected.")
}
}
_ = level.Info(logger).Log("msg", fmt.Sprintf("Enabled collectors: %v", strings.Join(enabledCollectorList, ", ")))
mux := http.NewServeMux()
mux.HandleFunc(*metricsPath, withConcurrencyLimit(*maxRequests, collectors.BuildServeHTTP(*disableExporterMetrics, *timeoutMargin)))
mux.HandleFunc("/health", func(w http.ResponseWriter, _ *http.Request) {
w.Header().Set("Content-Type", "application/json")
_, err := fmt.Fprintln(w, `{"status":"ok"}`)
if err != nil {
_ = level.Debug(logger).Log("msg", "Failed to write to stream", "err", err)
}
})
mux.HandleFunc("/version", func(w http.ResponseWriter, _ *http.Request) {
// we can't use "version" directly as it is a package, and not an object that
// can be serialized.
err := json.NewEncoder(w).Encode(prometheusVersion{
Version: version.Version,
Revision: version.Revision,
Branch: version.Branch,
BuildUser: version.BuildUser,
BuildDate: version.BuildDate,
GoVersion: version.GoVersion,
})
if err != nil {
http.Error(w, fmt.Sprintf("error encoding JSON: %s", err), http.StatusInternalServerError)
}
})
if *debugEnabled {
mux.HandleFunc("/debug/pprof/", pprof.Index)
mux.HandleFunc("/debug/pprof/cmdline", pprof.Cmdline)
mux.HandleFunc("/debug/pprof/profile", pprof.Profile)
mux.HandleFunc("/debug/pprof/symbol", pprof.Symbol)
mux.HandleFunc("/debug/pprof/trace", pprof.Trace)
}
_ = level.Info(logger).Log("msg", "Starting windows_exporter", "version", version.Info())
_ = level.Info(logger).Log("msg", "Build context", "build_context", version.BuildContext())
_ = level.Debug(logger).Log("msg", "Go MAXPROCS", "procs", runtime.GOMAXPROCS(0))
go func() {
server := &http.Server{Handler: mux}
if err := web.ListenAndServe(server, webConfig, logger); err != nil {
_ = level.Error(logger).Log("msg", "cannot start windows_exporter", "err", err)
os.Exit(1)
}
}()
for {
if <-initiate.StopCh {
_ = level.Info(logger).Log("msg", "Shutting down windows_exporter")
break
}
}
logger.Warn("Unable to determine which user is running this exporter. More info: https://github.com/golang/go/issues/37348")
}
func withConcurrencyLimit(n int, next http.HandlerFunc) http.HandlerFunc {
if n <= 0 {
return next
func setPriorityWindows(pid int, priority uint32) error {
// https://learn.microsoft.com/en-us/windows/win32/procthread/process-security-and-access-rights
handle, err := windows.OpenProcess(
windows.STANDARD_RIGHTS_REQUIRED|windows.SYNCHRONIZE|windows.SPECIFIC_RIGHTS_ALL,
false, uint32(pid),
)
if err != nil {
return fmt.Errorf("failed to open own process: %w", err)
}
sem := make(chan struct{}, n)
return func(w http.ResponseWriter, r *http.Request) {
select {
case sem <- struct{}{}:
defer func() { <-sem }()
default:
w.WriteHeader(http.StatusServiceUnavailable)
_, _ = w.Write([]byte("Too many concurrent requests"))
return
}
next(w, r)
if err = windows.SetPriorityClass(handle, priority); err != nil {
return fmt.Errorf("failed to set priority class: %w", err)
}
if err = windows.CloseHandle(handle); err != nil {
return fmt.Errorf("failed to close handle: %w", err)
}
return nil
}

45
go.mod
View File

@@ -1,52 +1,53 @@
module github.com/prometheus-community/windows_exporter
go 1.22
go 1.23
require (
github.com/Microsoft/hcsshim v0.12.5
github.com/Microsoft/hcsshim v0.12.7
github.com/alecthomas/kingpin/v2 v2.4.0
github.com/bmatcuk/doublestar/v4 v4.6.1
github.com/dimchansky/utfbom v1.1.1
github.com/go-kit/log v0.2.1
github.com/go-ole/go-ole v1.3.0
github.com/prometheus/client_golang v1.19.1
github.com/google/uuid v1.6.0
github.com/prometheus/client_golang v1.20.4
github.com/prometheus/client_model v0.6.1
github.com/prometheus/common v0.55.0
github.com/prometheus/exporter-toolkit v0.11.0
github.com/sirupsen/logrus v1.9.3 // indirect
github.com/prometheus/common v0.59.2-0.20240918152650-14bac55a992f
github.com/prometheus/exporter-toolkit v0.13.0
github.com/stretchr/testify v1.9.0
github.com/yusufpapurcu/wmi v1.2.4
go.opencensus.io v0.24.0 // indirect
golang.org/x/exp v0.0.0-20231110203233-9a3e6036ecaa
golang.org/x/sys v0.22.0
golang.org/x/sys v0.25.0
gopkg.in/yaml.v3 v3.0.1
)
require (
github.com/Microsoft/go-winio v0.6.2 // indirect
github.com/alecthomas/units v0.0.0-20211218093645-b94a6e3cc137 // indirect
github.com/alecthomas/units v0.0.0-20240626203959-61d1e3462e30 // indirect
github.com/beorn7/perks v1.0.1 // indirect
github.com/cespare/xxhash/v2 v2.2.0 // indirect
github.com/containerd/cgroups/v3 v3.0.2 // indirect
github.com/cespare/xxhash/v2 v2.3.0 // indirect
github.com/containerd/cgroups/v3 v3.0.3 // indirect
github.com/containerd/errdefs v0.1.0 // indirect
github.com/coreos/go-systemd/v22 v22.5.0 // indirect
github.com/davecgh/go-spew v1.1.1 // indirect
github.com/go-logfmt/logfmt v0.5.1 // indirect
github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
github.com/golang/protobuf v1.5.4 // indirect
github.com/jpillora/backoff v1.0.0 // indirect
github.com/klauspost/compress v1.17.10 // indirect
github.com/mdlayher/socket v0.5.1 // indirect
github.com/mdlayher/vsock v1.2.1 // indirect
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f // indirect
github.com/pkg/errors v0.9.1 // indirect
github.com/pmezard/go-difflib v1.0.0 // indirect
github.com/prometheus/procfs v0.15.1 // indirect
github.com/sirupsen/logrus v1.9.3 // indirect
github.com/xhit/go-str2duration/v2 v2.1.0 // indirect
golang.org/x/crypto v0.24.0 // indirect
golang.org/x/net v0.26.0 // indirect
golang.org/x/oauth2 v0.21.0 // indirect
golang.org/x/sync v0.7.0 // indirect
golang.org/x/text v0.16.0 // indirect
google.golang.org/genproto/googleapis/rpc v0.0.0-20240123012728-ef4313101c80 // indirect
google.golang.org/grpc v1.62.0 // indirect
go.opencensus.io v0.24.0 // indirect
golang.org/x/crypto v0.27.0 // indirect
golang.org/x/net v0.29.0 // indirect
golang.org/x/oauth2 v0.23.0 // indirect
golang.org/x/sync v0.8.0 // indirect
golang.org/x/text v0.18.0 // indirect
google.golang.org/genproto/googleapis/rpc v0.0.0-20240924160255-9d4c2d233b61 // indirect
google.golang.org/grpc v1.67.0 // indirect
google.golang.org/protobuf v1.34.2 // indirect
gopkg.in/yaml.v2 v2.4.0 // indirect
)

84
go.sum
View File

@@ -2,21 +2,23 @@ cloud.google.com/go v0.26.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMT
github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY=
github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU=
github.com/Microsoft/hcsshim v0.12.5 h1:bpTInLlDy/nDRWFVcefDZZ1+U8tS+rz3MxjKgu9boo0=
github.com/Microsoft/hcsshim v0.12.5/go.mod h1:tIUGego4G1EN5Hb6KC90aDYiUI2dqLSTTOCjVNpOgZ8=
github.com/Microsoft/hcsshim v0.12.7 h1:MP6R1spmjxTE4EU4J3YsrTxn8CjvN9qwjTKJXldFaRg=
github.com/Microsoft/hcsshim v0.12.7/go.mod h1:HPbAuJ9BvQYYZbB4yEQcyGIsTP5L4yHKeO9XO149AEM=
github.com/alecthomas/kingpin/v2 v2.4.0 h1:f48lwail6p8zpO1bC4TxtqACaGqHYA22qkHjHpqDjYY=
github.com/alecthomas/kingpin/v2 v2.4.0/go.mod h1:0gyi0zQnjuFk8xrkNKamJoyUo382HRL7ATRpFZCw6tE=
github.com/alecthomas/units v0.0.0-20211218093645-b94a6e3cc137 h1:s6gZFSlWYmbqAuRjVTiNNhvNRfY2Wxp9nhfyel4rklc=
github.com/alecthomas/units v0.0.0-20211218093645-b94a6e3cc137/go.mod h1:OMCwj8VM1Kc9e19TLln2VL61YJF0x1XFtfdL4JdbSyE=
github.com/alecthomas/units v0.0.0-20240626203959-61d1e3462e30 h1:t3eaIm0rUkzbrIewtiFmMK5RXHej2XnoXNhxVsAYUfg=
github.com/alecthomas/units v0.0.0-20240626203959-61d1e3462e30/go.mod h1:fvzegU4vN3H1qMT+8wDmzjAcDONcgo2/SZ/TyfdUOFs=
github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
github.com/bmatcuk/doublestar/v4 v4.6.1 h1:FH9SifrbvJhnlQpztAx++wlkk70QBf0iBWDwNy7PA4I=
github.com/bmatcuk/doublestar/v4 v4.6.1/go.mod h1:xBQ8jztBU6kakFMg+8WGxn0c6z1fTSPVIjEY1Wr7jzc=
github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
github.com/cespare/xxhash/v2 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj44=
github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc=
github.com/containerd/cgroups/v3 v3.0.2 h1:f5WFqIVSgo5IZmtTT3qVBo6TzI1ON6sycSBKkymb9L0=
github.com/containerd/cgroups/v3 v3.0.2/go.mod h1:JUgITrzdFqp42uI2ryGA+ge0ap/nxzYgkGmIcetmErE=
github.com/containerd/cgroups/v3 v3.0.3 h1:S5ByHZ/h9PMe5IOQoN7E+nMc2UcLEM/V48DGDJ9kip0=
github.com/containerd/cgroups/v3 v3.0.3/go.mod h1:8HBe7V3aWGLFPd/k03swSIsGjZhHI2WzJmticMgVuz0=
github.com/containerd/errdefs v0.1.0 h1:m0wCRBiu1WJT/Fr+iOoQHMQS/eP5myQ8lCv4Dz5ZURM=
github.com/containerd/errdefs v0.1.0/go.mod h1:YgWiiHtLmSeBrvpw+UfPijzbLaB77mEG1WwJTDETIV0=
github.com/coreos/go-systemd/v22 v22.5.0 h1:RrqgGjYQKalulkV8NGVIfkXQf6YYmOyiJKk8iXXhfZs=
@@ -30,10 +32,6 @@ github.com/envoyproxy/go-control-plane v0.9.0/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymF
github.com/envoyproxy/go-control-plane v0.9.1-0.20191026205805-5f8ba28d4473/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
github.com/envoyproxy/go-control-plane v0.9.4/go.mod h1:6rpuAdCZL397s3pYoYcLgu1mIlRU8Am5FuJP05cCM98=
github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c=
github.com/go-kit/log v0.2.1 h1:MRVx0/zhvdseW+Gza6N9rVzU/IVzaeE1SFI4raAhmBU=
github.com/go-kit/log v0.2.1/go.mod h1:NwTd00d/i8cPZ3xOwwiv2PO5MOcx78fFErGNcVmBjv0=
github.com/go-logfmt/logfmt v0.5.1 h1:otpy5pqBCBZ1ng9RQ0dPu4PN7ba75Y/aA+UpowDyNVA=
github.com/go-logfmt/logfmt v0.5.1/go.mod h1:WYhtIu8zTZfxdn5+rREduYbwxfcBr/Vr6KEVveWlfTs=
github.com/go-ole/go-ole v1.2.6/go.mod h1:pprOEPIfldk/42T2oK7lQ4v4JSDwmV0As9GaiUsvbm0=
github.com/go-ole/go-ole v1.3.0 h1:Dt6ye7+vXGIKZ7Xtk4s6/xVdGDQynvom7xCFEdWr6uE=
github.com/go-ole/go-ole v1.3.0/go.mod h1:5LS6F96DhAwUc7C+1HLexzMXY1xGRSryjyPPKW6zv78=
@@ -52,8 +50,6 @@ github.com/golang/protobuf v1.4.0-rc.4.0.20200313231945-b860323f09d0/go.mod h1:W
github.com/golang/protobuf v1.4.0/go.mod h1:jodUvKwWbYaEsadDk5Fwe5c77LiNKVO9IDvqG2KuDX0=
github.com/golang/protobuf v1.4.1/go.mod h1:U8fpvMrcmy5pZrNK1lt4xCsGvpyWQ/VVv6QDs8UjoX8=
github.com/golang/protobuf v1.4.3/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=
github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps=
github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M=
github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
@@ -63,12 +59,22 @@ github.com/google/go-cmp v0.5.3/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/
github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/jpillora/backoff v1.0.0 h1:uvFg412JmmHBHw7iwprIxkPMI+sGQ4kzOWsMeHnm2EA=
github.com/jpillora/backoff v1.0.0/go.mod h1:J/6gKK9jxlEcS3zixgDgUAsiuZ7yrSoa/FX5e0EB2j4=
github.com/klauspost/compress v1.17.10 h1:oXAz+Vh0PMUvJczoi+flxpnBEPxoER1IaAnU/NMPtT0=
github.com/klauspost/compress v1.17.10/go.mod h1:pMDklpSncoRMuLFrf1W9Ss9KT+0rH90U12bZKk7uwG0=
github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
github.com/mdlayher/socket v0.5.1 h1:VZaqt6RkGkt2OE9l3GcC6nZkqD3xKeQLyfleW/uBcos=
github.com/mdlayher/socket v0.5.1/go.mod h1:TjPLHI1UgwEv5J1B5q0zTZq12A/6H7nKmtTanQE37IQ=
github.com/mdlayher/vsock v1.2.1 h1:pC1mTJTvjo1r9n9fbm7S1j04rCgCzhCOS5DY0zqHlnQ=
github.com/mdlayher/vsock v1.2.1/go.mod h1:NRfCibel++DgeMD8z/hP+PPTjlNJsdPOmxcnENvE+SE=
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f h1:KUppIJq7/+SVif2QVs3tOP0zanoHgBEVAwHxUSIzRqU=
@@ -77,15 +83,15 @@ github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/prometheus/client_golang v1.19.1 h1:wZWJDwK+NameRJuPGDhlnFgx8e8HN3XHQeLaYJFJBOE=
github.com/prometheus/client_golang v1.19.1/go.mod h1:mP78NwGzrVks5S2H6ab8+ZZGJLZUq1hoULYBAYBw1Ho=
github.com/prometheus/client_golang v1.20.4 h1:Tgh3Yr67PaOv/uTqloMsCEdeuFTatm5zIq5+qNN23vI=
github.com/prometheus/client_golang v1.20.4/go.mod h1:PIEt8X02hGcP8JWbeHyeZ53Y/jReSnHgO035n//V5WE=
github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
github.com/prometheus/client_model v0.6.1 h1:ZKSh/rekM+n3CeS952MLRAdFwIKqeY8b62p8ais2e9E=
github.com/prometheus/client_model v0.6.1/go.mod h1:OrxVMOVHjw3lKMa8+x6HeMGkHMQyHDk9E3jmP2AmGiY=
github.com/prometheus/common v0.55.0 h1:KEi6DK7lXW/m7Ig5i47x0vRzuBsHuvJdi5ee6Y3G1dc=
github.com/prometheus/common v0.55.0/go.mod h1:2SECS4xJG1kd8XF9IcM1gMX6510RAEL65zxzNImwdc8=
github.com/prometheus/exporter-toolkit v0.11.0 h1:yNTsuZ0aNCNFQ3aFTD2uhPOvr4iD7fdBvKPAEGkNf+g=
github.com/prometheus/exporter-toolkit v0.11.0/go.mod h1:BVnENhnNecpwoTLiABx7mrPB/OLRIgN74qlQbV+FK1Q=
github.com/prometheus/common v0.59.2-0.20240918152650-14bac55a992f h1:3okwxT2ame6iNnOMGt2bH7JISqpwGn2KoMZ2bVFBQ6I=
github.com/prometheus/common v0.59.2-0.20240918152650-14bac55a992f/go.mod h1:GpWM7dewqmVYcd7SmRaiWVe9SSqjf0UrwnYnpEZNuT0=
github.com/prometheus/exporter-toolkit v0.13.0 h1:lmA0Q+8IaXgmFRKw09RldZmZdnvu9wwcDLIXGmTPw1c=
github.com/prometheus/exporter-toolkit v0.13.0/go.mod h1:2uop99EZl80KdXhv/MxVI2181fMcwlsumFOqBecGkG0=
github.com/prometheus/procfs v0.15.1 h1:YagwOFzUgYfKKHX6Dr+sHT7km/hxC76UB0learggepc=
github.com/prometheus/procfs v0.15.1/go.mod h1:fB45yRUv8NstnjriLhBQLuOUt+WW4BsoGhij/e3PBqk=
github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
@@ -95,11 +101,12 @@ github.com/sirupsen/logrus v1.9.3/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVs
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
github.com/stretchr/objx v0.5.2/go.mod h1:FRsXN1f5AsAjCGJKqEizvkpNtU+EGNCLh3NxZ/8L+MA=
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
github.com/xhit/go-str2duration/v2 v2.1.0 h1:lxklc02Drh6ynqX+DdPyp5pCKLUQpRT8bp8Ydu2Bstc=
@@ -110,11 +117,9 @@ go.opencensus.io v0.24.0 h1:y73uSU6J157QMP2kn2r30vwW1A2W2WFwSCGnAVxeaD0=
go.opencensus.io v0.24.0/go.mod h1:vNK8G9p7aAivkbmorf4v+7Hgx+Zs0yY+0fOtgBfjQKo=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
golang.org/x/crypto v0.24.0 h1:mnl8DM0o513X8fdIkmyFE/5hTYxbwYOjDS/+rK6qpRI=
golang.org/x/crypto v0.24.0/go.mod h1:Z1PMYSOR5nyMcyAVAIQSKCDwalqy85Aqn1x3Ws4L5DM=
golang.org/x/crypto v0.27.0 h1:GXm2NjJrPaiv/h1tb2UH8QfgC/hOf/+z0p6PT8o1w7A=
golang.org/x/crypto v0.27.0/go.mod h1:1Xngt8kV6Dvbssa53Ziq6Eqn0HqbZi5Z6R0ZpwQzt70=
golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
golang.org/x/exp v0.0.0-20231110203233-9a3e6036ecaa h1:FRnLl4eNAQl8hwxVVC17teOw8kdjVDVAiFMtgUdTSRQ=
golang.org/x/exp v0.0.0-20231110203233-9a3e6036ecaa/go.mod h1:zk2irFbV9DP96SEBUUAy67IdHUaZuSnrz1n472HUCLE=
golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
golang.org/x/lint v0.0.0-20190227174305-5b3e6a55c961/go.mod h1:wehouNa3lNwaWXcvxsM5YxQ5yQlVC4a0KAMCusXpPoU=
golang.org/x/lint v0.0.0-20190313153728-d0100b6bd8b3/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
@@ -124,16 +129,16 @@ golang.org/x/net v0.0.0-20190213061140-3a22650c66bd/go.mod h1:mL1N/T3taQHkDXs73r
golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/net v0.0.0-20201110031124-69a78807bb2b/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
golang.org/x/net v0.26.0 h1:soB7SVo0PWrY4vPW/+ay0jKDNScG2X9wFeYlXIvJsOQ=
golang.org/x/net v0.26.0/go.mod h1:5YKkiSynbBIh3p6iOc/vibscux0x38BZDkn8sCUPxHE=
golang.org/x/net v0.29.0 h1:5ORfpBpCs4HzDYoodCDBbwHzdR5UrLBZ3sOnUJmFoHo=
golang.org/x/net v0.29.0/go.mod h1:gLkgy8jTGERgjzMic6DS9+SP0ajcu6Xu3Orq/SpETg0=
golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
golang.org/x/oauth2 v0.21.0 h1:tsimM75w1tF/uws5rbeHzIWxEqElMehnc+iW793zsZs=
golang.org/x/oauth2 v0.21.0/go.mod h1:XYTD2NtWslqkgxebSiOHnXEap4TF09sJSc7H1sXbhtI=
golang.org/x/oauth2 v0.23.0 h1:PbgcYx2W7i4LvjJWEbf0ngHV6qJYr86PkAV3bXdLEbs=
golang.org/x/oauth2 v0.23.0/go.mod h1:XYTD2NtWslqkgxebSiOHnXEap4TF09sJSc7H1sXbhtI=
golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.7.0 h1:YsImfSBoP9QPYL0xyKJPq0gcaJdG3rInoqxTWbfQu9M=
golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
golang.org/x/sync v0.8.0 h1:3NFvSEYkUoMifnESzZl15y791HH1qU2xm6eCJU5ZPXQ=
golang.org/x/sync v0.8.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -141,12 +146,12 @@ golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7w
golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.1.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.22.0 h1:RI27ohtqKCnwULzJLqkv897zojh5/DwS/ENaMzUOaWI=
golang.org/x/sys v0.22.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.25.0 h1:r+8e+loiHxRqhXVl6ML1nO3l1+oFoWbnlu2Ehimmi34=
golang.org/x/sys v0.25.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.16.0 h1:a94ExnEXNtEwYLGJSIUxnWoxoRz/ZcCsV63ROupILh4=
golang.org/x/text v0.16.0/go.mod h1:GhwF1Be+LQoKShO3cGOHzqOgRrGaYc9AvblQOmPVHnI=
golang.org/x/text v0.18.0 h1:XvMDiNzPAl0jr17s6W9lcaIhGUfUORdGCNsuLmPG224=
golang.org/x/text v0.18.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
@@ -158,15 +163,15 @@ google.golang.org/appengine v1.4.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7
google.golang.org/genproto v0.0.0-20180817151627-c66870c02cf8/go.mod h1:JiN7NxoALGmiZfu7CAH4rXhgtRTLTxftemlI0sWmxmc=
google.golang.org/genproto v0.0.0-20190819201941-24fa4b261c55/go.mod h1:DMBHOl98Agz4BDEuKkezgsaosCRResVns1a3J2ZsMNc=
google.golang.org/genproto v0.0.0-20200526211855-cb27e3aa2013/go.mod h1:NbSheEEYHJ7i3ixzK3sjbqSGDJWnxyFXZblF3eUsNvo=
google.golang.org/genproto/googleapis/rpc v0.0.0-20240123012728-ef4313101c80 h1:AjyfHzEPEFp/NpvfN5g+KDla3EMojjhRVZc1i7cj+oM=
google.golang.org/genproto/googleapis/rpc v0.0.0-20240123012728-ef4313101c80/go.mod h1:PAREbraiVEVGVdTZsVWjSbbTtSyGbAgIIvni8a8CD5s=
google.golang.org/genproto/googleapis/rpc v0.0.0-20240924160255-9d4c2d233b61 h1:N9BgCIAUvn/M+p4NJccWPWb3BWh88+zyL0ll9HgbEeM=
google.golang.org/genproto/googleapis/rpc v0.0.0-20240924160255-9d4c2d233b61/go.mod h1:UqMtugtsSgubUsoxbuAoiCXvqvErP7Gf0so0mK9tHxU=
google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
google.golang.org/grpc v1.23.0/go.mod h1:Y5yQAOtifL1yxbo5wqy6BxZv8vAUGQwXBOALyacEbxg=
google.golang.org/grpc v1.25.1/go.mod h1:c3i+UQWmh7LiEpx4sFZnkU36qjEYZ0imhYfXVyQciAY=
google.golang.org/grpc v1.27.0/go.mod h1:qbnxyOmOxrQa7FizSgH+ReBfzJrCY1pSN7KXBS8abTk=
google.golang.org/grpc v1.33.2/go.mod h1:JMHMWHQWaTccqQQlmk3MJZS+GWXOdAesneDmEnv2fbc=
google.golang.org/grpc v1.62.0 h1:HQKZ/fa1bXkX1oFOvSjmZEUL8wLSaZTjCcLAlmZRtdk=
google.golang.org/grpc v1.62.0/go.mod h1:IWTG0VlJLCh1SkC58F7np9ka9mx/WNkjl4PGJaiq+QE=
google.golang.org/grpc v1.67.0 h1:IdH9y6PF5MPSdAntIcpjQ+tXO41pcQsfZV2RxtQgVcw=
google.golang.org/grpc v1.67.0/go.mod h1:1gLDyUQU7CTLJI90u3nXZ9ekeghjeM7pTDZlqFNg2AA=
google.golang.org/protobuf v0.0.0-20200109180630-ec00e32a8dfd/go.mod h1:DFci5gLYBciE7Vtevhsrf46CRTquxDuWsQurQQe4oz8=
google.golang.org/protobuf v0.0.0-20200221191635-4d8936d0db64/go.mod h1:kwYJMbMJ01Woi6D6+Kah6886xMZcty6N08ah7+eCXa0=
google.golang.org/protobuf v0.0.0-20200228230310-ab0ca4ff8a60/go.mod h1:cfTl7dwQJ+fmap5saPgwCLgHXTUD7jkjRqWcaiX5VyM=
@@ -181,7 +186,6 @@ google.golang.org/protobuf v1.34.2/go.mod h1:qYOHts0dSfpeUzUFpOMr/WGzszTmLH+DiWn
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

View File

@@ -28,7 +28,7 @@ Copy-Item -Force $PathToExecutable Work/windows_exporter.exe
Write-Verbose "Creating windows_exporter-${Version}-${Arch}.msi"
$wixArch = @{"amd64" = "x64"; "arm64" = "arm64"}[$Arch]
Invoke-Expression "wix build -arch $wixArch -o .\windows_exporter-$($Version)-$($Arch).msi .\windows_exporter.wxs -d Version=$($MsiVersion) -ext WixToolset.Firewall.wixext -ext WixToolset.Util.wixext"
Invoke-Expression "wix build -arch $wixArch -o .\windows_exporter-$($Version)-$($Arch).msi .\files.wxs .\main.wxs -d ProductName=windows_exporter -d Version=$($MsiVersion) -ext WixToolset.Firewall.wixext -ext WixToolset.UI.wixext -ext WixToolset.Util.wixext"
Write-Verbose "Done!"
Pop-Location

38
installer/files.wxs Normal file
View File

@@ -0,0 +1,38 @@
<Wix xmlns="http://wixtoolset.org/schemas/v4/wxs" xmlns:netfx="http://wixtoolset.org/schemas/v4/wxs/netfx"
xmlns:util="http://wixtoolset.org/schemas/v4/wxs/util">
<Fragment>
<DirectoryRef Id="APPLICATIONFOLDER">
<Component Transitive="yes">
<File Id="windows_exporter.exe" Name="windows_exporter.exe" Source="Work\windows_exporter.exe" KeyPath="yes" Vital="yes" Checksum="yes"/>
<ServiceInstall
Id="InstallExporterService"
Name="windows_exporter"
DisplayName="windows_exporter"
Description="Exports Prometheus metrics about the system"
ErrorControl="normal"
Start="auto"
Type="ownProcess"
Vital="yes"
Arguments="--log.file eventlog [ConfigFileFlag] [CollectorsFlag] [ListenFlag] [MetricsPathFlag] [TextfileDirsFlag] [ExtraFlags]">
<util:ServiceConfig
ResetPeriodInDays="1"
FirstFailureActionType="restart"
SecondFailureActionType="restart"
ThirdFailureActionType="restart"
RestartServiceDelayInSeconds="60"
/>
<ServiceDependency Id="wmiApSrv" />
</ServiceInstall>
<ServiceControl Id="ServiceStateControl" Name="windows_exporter" Remove="uninstall" Start="install" Stop="both"/>
</Component>
<Component Id="CreateTextfileDirectory" Directory="textfile_inputs" Guid="d03ef58a-9cbf-4165-ad39-d143e9b27e14">
<CreateFolder />
</Component>
</DirectoryRef>
<ComponentGroup Id="CG_Files">
<ComponentRef Id="windows_exporter.exe" />
<ComponentRef Id="CreateTextfileDirectory" />
</ComponentGroup>
</Fragment>
</Wix>

221
installer/main.wxs Normal file
View File

@@ -0,0 +1,221 @@
<?xml version="1.0"?>
<?ifndef Version?>
<?error Version must be defined?>
<?endif?>
<?if $(sys.BUILDARCH) = x64 or $(sys.BUILDARCH) = arm64 ?>
<?define PlatformProgramFilesFolder = "ProgramFiles64Folder" ?>
<?else ?>
<?define PlatformProgramFilesFolder = "ProgramFilesFolder" ?>
<?endif?>
<Wix xmlns="http://wixtoolset.org/schemas/v4/wxs"
xmlns:fw="http://wixtoolset.org/schemas/v4/wxs/firewall"
xmlns:ui="http://wixtoolset.org/schemas/v4/wxs/ui">
<Package UpgradeCode="66a6eb5b-1fc2-4b14-a362-5ceec6413308" Name="$(var.ProductName)" Version="$(var.Version)"
Manufacturer="prometheus-community" Language="1033" Scope="perMachine">
<SummaryInformation Manufacturer="prometheus-community" Description="$(var.ProductName) $(var.Version) installer" />
<Upgrade Id="66a6eb5b-1fc2-4b14-a362-5ceec6413308">
<UpgradeVersion IncludeMinimum="no"
Minimum="$(var.Version)"
OnlyDetect="no"
Property="NEWERVERSIONDETECTED" />
<UpgradeVersion IncludeMaximum="yes"
IncludeMinimum="yes"
Maximum="$(var.Version)"
Minimum="0.0.0.0"
Property="OLDERVERSIONBEINGUPGRADED" />
</Upgrade>
<CustomAction Id="set_maintenance" Property="MAINTENANCE" Value="true" />
<!-- Set to reinstall all features. -->
<CustomAction Id="set_reinstall_all_property"
Property="REINSTALL"
Value="ALL" />
<!-- "amus" will force reinstall all files.
See https://docs.microsoft.com/en-us/windows/desktop/Msi/reinstallmode -->
<CustomAction Id="set_reinstallmode_property"
Property="REINSTALLMODE"
Value="amus" />
<SetProperty
Id="CreateConfigFile"
Value="&quot;[%ComSpec]&quot; /c TYPE NUL >>&quot;[ConfigFile_NonDefault][ConfigFile_Default]&quot;"
Before="CreateConfigFile"
Sequence="execute"
Condition="ConfigFile_NonDefault OR ConfigFile_Default"
/>
<CustomAction
Id="CreateConfigFile"
BinaryRef="Wix4UtilCA_$(sys.BUILDARCHSHORT)"
DllEntry="WixQuietExec"
Execute="deferred"
Return="check"
Impersonate="no"
/>
<InstallExecuteSequence>
<!-- Set REINSTALL=all and REINSTALLMODE=amus if the user reruns the
MSI, which will force reinstalling all files and services. -->
<Custom Action="set_maintenance" Before="set_reinstall_all_property"
Condition="Installed AND (NOT REMOVE) AND (NOT UPGRADINGPRODUCTCODE)"/>
<Custom Action="set_reinstall_all_property" Before="set_reinstallmode_property" Condition="MAINTENANCE"/>
<Custom Action="set_reinstallmode_property" Before="LaunchConditions" Condition="MAINTENANCE"/>
<Custom Action="CreateConfigFile" Before="InstallServices" Condition="ConfigFile_NonDefault OR ConfigFile_Default" />
</InstallExecuteSequence>
<Media Id="1" Cabinet="windows_exporter.cab" EmbedCab="yes" />
<MajorUpgrade Schedule="afterInstallInitialize" DowngradeErrorMessage="A later version of [ProductName] is already installed. Setup will now exit." AllowSameVersionUpgrades="yes" />
<Property Id="ENABLED_COLLECTORS" Secure="yes" />
<SetProperty Id="CollectorsFlag" After="InstallFiles" Sequence="execute" Value="--collectors.enabled [ENABLED_COLLECTORS]" Condition="ENABLED_COLLECTORS" />
<Property Id="EXTRA_FLAGS" Secure="yes" />
<SetProperty Id="ExtraFlags" After="InstallFiles" Sequence="execute" Value="[EXTRA_FLAGS]" Condition="EXTRA_FLAGS" />
<Property Id="CONFIG_FILE" Secure="yes" Value="config.yaml" />
<SetProperty Id="ConfigFile_NonDefault" After="InstallFiles" Sequence="execute" Value="[CONFIG_FILE]" Condition="CONFIG_FILE AND CONFIG_FILE&lt;&gt;&quot;config.yaml&quot;" />
<SetProperty Id="ConfigFile_Default" After="InstallFiles" Sequence="execute" Value="[APPLICATIONFOLDER]config.yaml" Condition="CONFIG_FILE=&quot;config.yaml&quot;" />
<SetProperty Id="ConfigFileFlag" After="InstallFiles" Sequence="execute" Value="--config.file=&quot;[ConfigFile_NonDefault][ConfigFile_Default]&quot;" Condition="ConfigFile_NonDefault OR ConfigFile_Default" />
<Property Id="LISTEN_PORT" Secure="yes" Value="9182" />
<SetProperty Id="ListenFlag" After="InstallFiles" Sequence="execute" Value="--web.listen-address [LISTEN_ADDR]:[LISTEN_PORT]" Condition="LISTEN_ADDR&lt;&gt;&quot;&quot; OR LISTEN_PORT&lt;&gt;9182" />
<Property Id="METRICS_PATH" Secure="yes" />
<SetProperty Id="MetricsPathFlag" After="InstallFiles" Sequence="execute" Value="--telemetry.path [METRICS_PATH]" Condition="METRICS_PATH" />
<Property Id="REMOTE_ADDR" Secure="yes" />
<SetProperty Id="RemoteAddressFlag" After="InstallFiles" Sequence="execute" Value="[REMOTE_ADDR]" Condition="REMOTE_ADDR" />
<Property Id="TEXTFILE_DIRS" Secure="yes" />
<SetProperty Id="TextfileDirsFlag" After="InstallFiles" Sequence="execute" Value="--collector.textfile.directories [TEXTFILE_DIRS]" Condition="TEXTFILE_DIRS" />
<Property Id="ARPHELPLINK" Value="https://github.com/prometheus-community/windows_exporter/issues" />
<Property Id="ARPSIZE" Value="9000" />
<Property Id="ARPURLINFOABOUT" Value="https://github.com/prometheus-community/windows_exporter" />
<!--<Property Id="ARPNOMODIFY" Value="0" />-->
<!--<Property Id="ARPNOREPAIR" Value="1" />-->
<Property Id="START_MENU_FOLDER" Value="0" />
<Property Id="NOSTART" Value="0" />
<Feature
Id="DefaultFeature"
Level="1"
Title="$(var.ProductName) $(var.Version)"
Description="The binary and configuration files for $(var.ProductName)"
Display="expand"
ConfigurableDirectory="APPLICATIONFOLDER"
AllowAdvertise="no"
InstallDefault="local"
AllowAbsent="no"
>
<ComponentGroupRef Id="CG_Files" />
<Feature
Id="FirewallException"
Level="2"
Title="Firewall Exception"
Description="Allow $(var.ProductName) to listen on a port"
Display="expand"
AllowAdvertise="no"
AllowAbsent="yes">
<ComponentGroupRef Id="CG_FirewallException" />
</Feature>
</Feature>
<UI Id="FeatureTree">
<ui:WixUI Id="WixUI_FeatureTree" />
<UIRef Id="WixUI_ErrorProgressText" />
<Dialog Id="CustomPropertiesDlg" Width="370" Height="270" Title="windows_exporter configuration">
<Control Id="BannerBitmap" Type="Bitmap" X="0" Y="0" Width="370" Height="44" TabSkip="no" Text="!(loc.CustomizeDlgBannerBitmap)" />
<!--<Control Id="Text" Type="Text" X="25" Y="55" Width="320" Height="20" Text="Text" />-->
<Control Id="BannerLine" Type="Line" X="0" Y="44" Width="370" Height="0" />
<Control Id="BottomLine" Type="Line" X="0" Y="234" Width="370" Height="0" />
<Control Id="Description" Type="Text" X="25" Y="23" Width="280" Height="15" Transparent="yes" NoPrefix="yes" Text="This pages contains configuration related to windows_exporter" />
<Control Id="Title" Type="Text" X="15" Y="6" Width="210" Height="15" Transparent="yes" NoPrefix="yes" Text="{\WixUI_Font_Title}windows_exporter configuration" />
<!-- Edit box for property input -->
<!-- cpu,cs,logical_disk,physical_disk,net,os,service,system -->
<Control Id="PropertyEdit_ENABLED_COLLECTORS_Title1" Type="Text" X="25" Y="55" Width="300" Height="15" Transparent="yes" NoPrefix="yes" Text="Comma-separated list of collectors to use. Use '[\[]defaults[\]]' as a placeholder for all" />
<Control Id="PropertyEdit_ENABLED_COLLECTORS_Title2" Type="Text" X="25" Y="65" Width="300" Height="15" Transparent="yes" NoPrefix="yes" Text="the collectors enabled by default. If value is empty, the exporter default will be used." />
<Control Id="PropertyEdit_ENABLED_COLLECTORS" Type="Edit" X="24" Y="77" Width="300" Height="18" Property="ENABLED_COLLECTORS" Text="[ENABLED_COLLECTORS]" Indirect="no" />
<Control Id="PropertyEdit_EXTRA_FLAGS_Title" Type="Text" X="25" Y="100" Width="300" Height="15" Transparent="yes" NoPrefix="yes" Text="Additional command line flags" />
<Control Id="PropertyEdit_EXTRA_FLAGS" Type="Edit" X="24" Y="112" Width="300" Height="18" Property="EXTRA_FLAGS" Text="[EXTRA_FLAGS]" Indirect="no" />
<Control Id="PropertyEdit_LISTEN_PORT_Title" Type="Text" X="25" Y="135" Width="300" Height="15" Transparent="yes" NoPrefix="yes" Text="Port to listen" />
<Control Id="PropertyEdit_LISTEN_PORT" Type="Edit" X="24" Y="147" Width="300" Height="18" Property="LISTEN_PORT" Text="[LISTEN_PORT]" Indirect="no" />
<Control Id="PropertyEdit_CONFIG_FILE_Title1" Type="Text" X="25" Y="170" Width="300" Height="15" Transparent="yes" NoPrefix="yes" Text="Path to config file. If empty, no config will be used. If set to 'config.yaml', " />
<Control Id="PropertyEdit_CONFIG_FILE_Title2" Type="Text" X="25" Y="180" Width="300" Height="15" Transparent="yes" NoPrefix="yes" Text="then the config.yaml at the install path will be used." />
<Control Id="PropertyEdit_CONFIG_FILE" Type="Edit" X="24" Y="192" Width="300" Height="18" Property="CONFIG_FILE" Text="[CONFIG_FILE]" Indirect="no" />
<Control Id="Next" Type="PushButton" X="236" Y="243" Width="56" Height="17" Default="yes" Text="!(loc.WixUINext)">
<Publish Event="NewDialog" Value="VerifyReadyDlg" />
</Control>
<Control Id="Back" Type="PushButton" X="180" Y="243" Width="56" Height="17" Text="!(loc.WixUIBack)">
<Publish Event="NewDialog" Value="CustomizeDlg" />
</Control>
<Control Id="Cancel" Type="PushButton" X="304" Y="243" Width="56" Height="17" Cancel="yes" Text="!(loc.WixUICancel)">
<Publish Event="SpawnDialog" Value="CancelDlg" />
</Control>
</Dialog>
<!-- skip the license agreement dialog; higher Order takes priority (weird) -->
<Publish
Condition="NOT Installed"
Dialog="WelcomeDlg"
Control="Next"
Event="NewDialog"
Value="CustomizeDlg"
Order="10"/>
<Publish
Condition="NOT Installed"
Dialog="CustomizeDlg"
Control="Back"
Event="NewDialog"
Value="WelcomeDlg"
Order="10"/>
<Publish
Dialog="CustomizeDlg"
Control="Next"
Event="NewDialog"
Value="CustomPropertiesDlg"
Order="10"/>
<Publish
Dialog="VerifyReadyDlg"
Control="Back"
Event="NewDialog"
Value="CustomPropertiesDlg"
Order="10"/>
<!--CustomPropertyDlg-->
</UI>
<!-- InstallLocation key -->
<CustomAction Id="SetInstallLocation" Property="ARPINSTALLLOCATION" Value="[APPLICATIONFOLDER]" />
<StandardDirectory Id="ProgramFiles64Folder">
<Directory Id="APPLICATIONFOLDER" Name="windows_exporter">
<Directory Id="textfile_inputs" Name="textfile_inputs" />
</Directory>
</StandardDirectory>
<ComponentGroup Id="CG_FirewallException">
<Component Directory="APPLICATIONFOLDER" Id="C_FirewallException" Guid="9f522655-ac0e-42d2-a512-a7b19ebec7f7">
<fw:FirewallException
Id="MetricsEndpoint"
Name="$(var.ProductName)"
Description="$(var.ProductName) HTTP endpoint"
Program="[#windows_exporter.exe]"
Port="[LISTEN_PORT]"
Protocol="tcp">
<fw:RemoteAddress Value="[REMOTE_ADDR]" />
</fw:FirewallException>
</Component>
</ComponentGroup>
</Package>
</Wix>

View File

@@ -1,110 +0,0 @@
<Wix xmlns="http://wixtoolset.org/schemas/v4/wxs" xmlns:fw="http://wixtoolset.org/schemas/v4/wxs/firewall" xmlns:util="http://wixtoolset.org/schemas/v4/wxs/util">
<?if $(sys.BUILDARCH)=x64 ?>
<?define PlatformProgramFiles = "ProgramFiles64Folder" ?>
<?else?>
<?define PlatformProgramFiles = "ProgramFilesFolder" ?>
<?endif?>
<Package UpgradeCode="66a6eb5b-1fc2-4b14-a362-5ceec6413308" Name="windows_exporter" Version="$(var.Version)" Manufacturer="prometheus-community" Language="1033" Codepage="1252">
<SummaryInformation Manufacturer="prometheus-community" Description="windows_exporter $(var.Version) installer" />
<Media Id="1" Cabinet="windows_exporter.cab" EmbedCab="yes" />
<MajorUpgrade Schedule="afterInstallInitialize" DowngradeErrorMessage="A later version of [ProductName] is already installed. Setup will now exit." />
<Property Id="ENABLED_COLLECTORS" Secure="yes" />
<SetProperty Id="CollectorsFlag" After="InstallFiles" Sequence="execute" Value="--collectors.enabled [ENABLED_COLLECTORS]" Condition="ENABLED_COLLECTORS" />
<Property Id="EXTRA_FLAGS" Secure="yes" />
<SetProperty Id="ExtraFlags" After="InstallFiles" Sequence="execute" Value="[EXTRA_FLAGS]" Condition="EXTRA_FLAGS" />
<Property Id="ADD_FIREWALL_EXCEPTION" Secure="yes" />
<Property Id="ENABLE_V1_PERFORMANCE_COUNTERS" Secure="yes" Value="yes"/>
<Property Id="LISTEN_PORT" Secure="yes" Value="9182" />
<SetProperty Id="ListenFlag" After="InstallFiles" Sequence="execute" Value="--web.listen-address [LISTEN_ADDR]:[LISTEN_PORT]" Condition="LISTEN_ADDR&lt;&gt;&quot;&quot; OR LISTEN_PORT&lt;&gt;9182" />
<Property Id="METRICS_PATH" Secure="yes" />
<SetProperty Id="MetricsPathFlag" After="InstallFiles" Sequence="execute" Value="--telemetry.path [METRICS_PATH]" Condition="METRICS_PATH" />
<Property Id="REMOTE_ADDR" Secure="yes" />
<SetProperty Id="RemoteAddressFlag" After="InstallFiles" Sequence="execute" Value="[REMOTE_ADDR]" Condition="REMOTE_ADDR" />
<!-- https://github.com/prometheus-community/windows_exporter/issues/1318 -->
<!-- https://wixtoolset.org/docs/tools/wixext/quietexec/ -->
<SetProperty
Id="WixQuietExecCmdLine"
Value="&quot;[%ComSpec]&quot; /c reg delete HKLM\SYSTEM\CurrentControlSet\Services\EventLog\Application\windows_exporter /f"
Before="RemoveEventSource"
Sequence="execute"
/>
<CustomAction
Id="RemoveEventSource"
BinaryRef="Wix4UtilCA_$(sys.BUILDARCHSHORT)"
DllEntry="WixSilentExec"
Execute="deferred"
Impersonate="no"
Return="ignore"
/>
<InstallExecuteSequence>
<Custom Action="RemoveEventSource" After="InstallInitialize" />
</InstallExecuteSequence>
<SetProperty
Id="EnableV1PerformanceCounters"
Value="&quot;[%ComSpec]&quot; /c lodctr.exe /E:Lsa &amp; lodctr.exe /E:PerfProc &amp; lodctr.exe /R"
Before="EnableV1PerformanceCounters"
Sequence="execute"
/>
<CustomAction
Id="EnableV1PerformanceCounters"
BinaryRef="Wix4UtilCA_$(sys.BUILDARCHSHORT)"
DllEntry="WixSilentExec"
Execute="deferred"
Impersonate="no"
Return="check"
/>
<InstallExecuteSequence>
<Custom Action="EnableV1PerformanceCounters" Before="InstallFinalize" Condition="ENABLE_V1_PERFORMANCE_COUNTERS=&quot;yes&quot;"/>
</InstallExecuteSequence>
<Property Id="TEXTFILE_DIRS" Secure="yes" />
<SetProperty Id="TextfileDirsFlag" After="InstallFiles" Sequence="execute" Value="--collector.textfile.directories [TEXTFILE_DIRS]" Condition="TEXTFILE_DIRS" />
<ComponentGroup Id="Files">
<Component Directory="APPLICATIONROOTDIRECTORY">
<File Id="windows_exporter.exe" Name="windows_exporter.exe" Source="Work\windows_exporter.exe" KeyPath="yes" />
<ServiceInstall Id="InstallExporterService" Name="windows_exporter" DisplayName="windows_exporter" Description="Exports Prometheus metrics about the system" ErrorControl="normal" Start="auto" Type="ownProcess" Arguments="--log.file eventlog [CollectorsFlag] [ListenFlag] [MetricsPathFlag] [TextfileDirsFlag] [ExtraFlags]">
<util:ServiceConfig FirstFailureActionType="restart" SecondFailureActionType="restart" ThirdFailureActionType="restart" RestartServiceDelayInSeconds="60" />
<ServiceDependency Id="wmiApSrv" />
</ServiceInstall>
<ServiceControl Id="ServiceStateControl" Name="windows_exporter" Remove="uninstall" Start="install" Stop="both" />
</Component>
<Component Id="CreateTextfileDirectory" Directory="textfile_inputs" Guid="d03ef58a-9cbf-4165-ad39-d143e9b27e14">
<CreateFolder />
</Component>
</ComponentGroup>
<ComponentGroup Id="CG_FirewallException">
<Component Condition="ADD_FIREWALL_EXCEPTION=&quot;yes&quot;" Directory="APPLICATIONROOTDIRECTORY" Id="C_FirewallException" Guid="9f522655-ac0e-42d2-a512-a7b19ebec7f7">
<fw:FirewallException Id="MetricsEndpoint" Name="windows_exporter (HTTP [LISTEN_PORT])" Description="windows_exporter HTTP endpoint" Port="[LISTEN_PORT]" Protocol="tcp" IgnoreFailure="yes">
<fw:RemoteAddress Value="[REMOTE_ADDR]" />
</fw:FirewallException>
</Component>
</ComponentGroup>
<Feature Id="DefaultFeature" Level="1">
<ComponentGroupRef Id="Files" />
</Feature>
<Feature Id="FirewallException" Level="1">
<ComponentGroupRef Id="CG_FirewallException" />
</Feature>
<StandardDirectory Id="ProgramFiles64Folder">
<Directory Id="APPLICATIONROOTDIRECTORY" Name="windows_exporter">
<Directory Id="textfile_inputs" Name="textfile_inputs" />
</Directory>
</StandardDirectory>
</Package>
</Wix>

View File

@@ -32,7 +32,7 @@ spec:
command: ["powershell"]
args: ["New-NetFirewallRule", "-DisplayName", "'windows-exporter'", "-Direction", "inbound", "-Profile", "Any", "-Action", "Allow", "-LocalPort", "9182", "-Protocol", "TCP"]
containers:
- args:
- args:
- --config.file=%CONTAINER_SANDBOX_MOUNT_POINT%/config.yml
name: windows-exporter
image: ghcr.io/prometheus-community/windows-exporter:latest
@@ -65,4 +65,4 @@ data:
enabled: '[defaults],container'
collector:
service:
services-where: "Name='containerd' or Name='kubelet'"
include: "containerd|kubelet"

File diff suppressed because it is too large Load Diff

View File

@@ -4,15 +4,15 @@ package adcs
import (
"errors"
"log/slog"
"strings"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/go-kit/log/level"
"github.com/prometheus-community/windows_exporter/pkg/perflib"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus-community/windows_exporter/pkg/utils"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const Name = "adcs"
@@ -21,120 +21,126 @@ type Config struct{}
var ConfigDefaults = Config{}
type collector struct {
logger log.Logger
type Collector struct {
config Config
RequestsPerSecond *prometheus.Desc
RequestProcessingTime *prometheus.Desc
RetrievalsPerSecond *prometheus.Desc
RetrievalProcessingTime *prometheus.Desc
FailedRequestsPerSecond *prometheus.Desc
IssuedRequestsPerSecond *prometheus.Desc
PendingRequestsPerSecond *prometheus.Desc
RequestCryptographicSigningTime *prometheus.Desc
RequestPolicyModuleProcessingTime *prometheus.Desc
ChallengeResponsesPerSecond *prometheus.Desc
ChallengeResponseProcessingTime *prometheus.Desc
SignedCertificateTimestampListsPerSecond *prometheus.Desc
SignedCertificateTimestampListProcessingTime *prometheus.Desc
challengeResponseProcessingTime *prometheus.Desc
challengeResponsesPerSecond *prometheus.Desc
failedRequestsPerSecond *prometheus.Desc
issuedRequestsPerSecond *prometheus.Desc
pendingRequestsPerSecond *prometheus.Desc
requestCryptographicSigningTime *prometheus.Desc
requestPolicyModuleProcessingTime *prometheus.Desc
requestProcessingTime *prometheus.Desc
requestsPerSecond *prometheus.Desc
retrievalProcessingTime *prometheus.Desc
retrievalsPerSecond *prometheus.Desc
signedCertificateTimestampListProcessingTime *prometheus.Desc
signedCertificateTimestampListsPerSecond *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
func NewWithFlags(_ *kingpin.Application) *Collector {
return &Collector{}
}
func (c *collector) GetName() string {
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{"Certification Authority"}, nil
}
func (c *collector) Build() error {
c.RequestsPerSecond = prometheus.NewDesc(
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, _ *wmi.Client) error {
c.requestsPerSecond = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "requests_total"),
"Total certificate requests processed",
[]string{"cert_template"},
nil,
)
c.RequestProcessingTime = prometheus.NewDesc(
c.requestProcessingTime = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "request_processing_time_seconds"),
"Last time elapsed for certificate requests",
[]string{"cert_template"},
nil,
)
c.RetrievalsPerSecond = prometheus.NewDesc(
c.retrievalsPerSecond = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "retrievals_total"),
"Total certificate retrieval requests processed",
[]string{"cert_template"},
nil,
)
c.RetrievalProcessingTime = prometheus.NewDesc(
c.retrievalProcessingTime = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "retrievals_processing_time_seconds"),
"Last time elapsed for certificate retrieval request",
[]string{"cert_template"},
nil,
)
c.FailedRequestsPerSecond = prometheus.NewDesc(
c.failedRequestsPerSecond = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "failed_requests_total"),
"Total failed certificate requests processed",
[]string{"cert_template"},
nil,
)
c.IssuedRequestsPerSecond = prometheus.NewDesc(
c.issuedRequestsPerSecond = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "issued_requests_total"),
"Total issued certificate requests processed",
[]string{"cert_template"},
nil,
)
c.PendingRequestsPerSecond = prometheus.NewDesc(
c.pendingRequestsPerSecond = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "pending_requests_total"),
"Total pending certificate requests processed",
[]string{"cert_template"},
nil,
)
c.RequestCryptographicSigningTime = prometheus.NewDesc(
c.requestCryptographicSigningTime = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "request_cryptographic_signing_time_seconds"),
"Last time elapsed for signing operation request",
[]string{"cert_template"},
nil,
)
c.RequestPolicyModuleProcessingTime = prometheus.NewDesc(
c.requestPolicyModuleProcessingTime = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "request_policy_module_processing_time_seconds"),
"Last time elapsed for policy module processing request",
[]string{"cert_template"},
nil,
)
c.ChallengeResponsesPerSecond = prometheus.NewDesc(
c.challengeResponsesPerSecond = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "challenge_responses_total"),
"Total certificate challenge responses processed",
[]string{"cert_template"},
nil,
)
c.ChallengeResponseProcessingTime = prometheus.NewDesc(
c.challengeResponseProcessingTime = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "challenge_response_processing_time_seconds"),
"Last time elapsed for challenge response",
[]string{"cert_template"},
nil,
)
c.SignedCertificateTimestampListsPerSecond = prometheus.NewDesc(
c.signedCertificateTimestampListsPerSecond = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "signed_certificate_timestamp_lists_total"),
"Total Signed Certificate Timestamp Lists processed",
[]string{"cert_template"},
nil,
)
c.SignedCertificateTimestampListProcessingTime = prometheus.NewDesc(
c.signedCertificateTimestampListProcessingTime = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "signed_certificate_timestamp_list_processing_time_seconds"),
"Last time elapsed for Signed Certificate Timestamp List",
[]string{"cert_template"},
@@ -144,11 +150,16 @@ func (c *collector) Build() error {
return nil
}
func (c *collector) Collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
if err := c.collectADCSCounters(ctx, ch); err != nil {
_ = level.Error(c.logger).Log("msg", "failed collecting ADCS metrics", "err", err)
func (c *Collector) Collect(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
if err := c.collectADCSCounters(ctx, logger, ch); err != nil {
logger.Error("failed collecting ADCS metrics",
slog.Any("err", err),
)
return err
}
return nil
}
@@ -169,15 +180,18 @@ type perflibADCS struct {
SignedCertificateTimestampListProcessingTime float64 `perflib:"Signed Certificate Timestamp List processing time (ms)"`
}
func (c *collector) collectADCSCounters(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collectADCSCounters(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
dst := make([]perflibADCS, 0)
if _, ok := ctx.PerfObjects["Certification Authority"]; !ok {
return errors.New("perflib did not contain an entry for Certification Authority")
}
err := perflib.UnmarshalObject(ctx.PerfObjects["Certification Authority"], &dst, c.logger)
err := perflib.UnmarshalObject(ctx.PerfObjects["Certification Authority"], &dst, logger)
if err != nil {
return err
}
if len(dst) == 0 {
return errors.New("perflib query for Certification Authority (ADCS) returned empty result set")
}
@@ -188,79 +202,79 @@ func (c *collector) collectADCSCounters(ctx *types.ScrapeContext, ch chan<- prom
continue
}
ch <- prometheus.MustNewConstMetric(
c.RequestsPerSecond,
c.requestsPerSecond,
prometheus.CounterValue,
d.RequestsPerSecond,
d.Name,
)
ch <- prometheus.MustNewConstMetric(
c.RequestProcessingTime,
c.requestProcessingTime,
prometheus.GaugeValue,
utils.MilliSecToSec(d.RequestProcessingTime),
d.Name,
)
ch <- prometheus.MustNewConstMetric(
c.RetrievalsPerSecond,
c.retrievalsPerSecond,
prometheus.CounterValue,
d.RetrievalsPerSecond,
d.Name,
)
ch <- prometheus.MustNewConstMetric(
c.RetrievalProcessingTime,
c.retrievalProcessingTime,
prometheus.GaugeValue,
utils.MilliSecToSec(d.RetrievalProcessingTime),
d.Name,
)
ch <- prometheus.MustNewConstMetric(
c.FailedRequestsPerSecond,
c.failedRequestsPerSecond,
prometheus.CounterValue,
d.FailedRequestsPerSecond,
d.Name,
)
ch <- prometheus.MustNewConstMetric(
c.IssuedRequestsPerSecond,
c.issuedRequestsPerSecond,
prometheus.CounterValue,
d.IssuedRequestsPerSecond,
d.Name,
)
ch <- prometheus.MustNewConstMetric(
c.PendingRequestsPerSecond,
c.pendingRequestsPerSecond,
prometheus.CounterValue,
d.PendingRequestsPerSecond,
d.Name,
)
ch <- prometheus.MustNewConstMetric(
c.RequestCryptographicSigningTime,
c.requestCryptographicSigningTime,
prometheus.GaugeValue,
utils.MilliSecToSec(d.RequestCryptographicSigningTime),
d.Name,
)
ch <- prometheus.MustNewConstMetric(
c.RequestPolicyModuleProcessingTime,
c.requestPolicyModuleProcessingTime,
prometheus.GaugeValue,
utils.MilliSecToSec(d.RequestPolicyModuleProcessingTime),
d.Name,
)
ch <- prometheus.MustNewConstMetric(
c.ChallengeResponsesPerSecond,
c.challengeResponsesPerSecond,
prometheus.CounterValue,
d.ChallengeResponsesPerSecond,
d.Name,
)
ch <- prometheus.MustNewConstMetric(
c.ChallengeResponseProcessingTime,
c.challengeResponseProcessingTime,
prometheus.GaugeValue,
utils.MilliSecToSec(d.ChallengeResponseProcessingTime),
d.Name,
)
ch <- prometheus.MustNewConstMetric(
c.SignedCertificateTimestampListsPerSecond,
c.signedCertificateTimestampListsPerSecond,
prometheus.CounterValue,
d.SignedCertificateTimestampListsPerSecond,
d.Name,
)
ch <- prometheus.MustNewConstMetric(
c.SignedCertificateTimestampListProcessingTime,
c.signedCertificateTimestampListProcessingTime,
prometheus.GaugeValue,
utils.MilliSecToSec(d.SignedCertificateTimestampListProcessingTime),
d.Name,

View File

@@ -3,13 +3,14 @@
package adfs
import (
"log/slog"
"math"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/prometheus-community/windows_exporter/pkg/perflib"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const Name = "adfs"
@@ -18,20 +19,21 @@ type Config struct{}
var ConfigDefaults = Config{}
type collector struct {
logger log.Logger
type Collector struct {
config Config
adLoginConnectionFailures *prometheus.Desc
artifactDBFailures *prometheus.Desc
avgArtifactDBQueryTime *prometheus.Desc
avgConfigDBQueryTime *prometheus.Desc
certificateAuthentications *prometheus.Desc
configDBFailures *prometheus.Desc
deviceAuthentications *prometheus.Desc
externalAuthenticationFailures *prometheus.Desc
externalAuthentications *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
federationMetadataRequests *prometheus.Desc
oAuthAuthZRequests *prometheus.Desc
oAuthClientAuthentications *prometheus.Desc
oAuthClientAuthenticationsFailures *prometheus.Desc
@@ -50,45 +52,50 @@ type collector struct {
oAuthPasswordGrantRequestFailures *prometheus.Desc
oAuthPasswordGrantRequests *prometheus.Desc
oAuthTokenRequests *prometheus.Desc
passiveRequests *prometheus.Desc
passportAuthentications *prometheus.Desc
passwordChangeFailed *prometheus.Desc
passwordChangeSucceeded *prometheus.Desc
samlPTokenRequests *prometheus.Desc
ssoAuthenticationFailures *prometheus.Desc
ssoAuthentications *prometheus.Desc
wsfedTokenRequests *prometheus.Desc
wstrustTokenRequests *prometheus.Desc
tokenRequests *prometheus.Desc
upAuthenticationFailures *prometheus.Desc
upAuthentications *prometheus.Desc
externalAuthenticationFailures *prometheus.Desc
externalAuthentications *prometheus.Desc
artifactDBFailures *prometheus.Desc
avgArtifactDBQueryTime *prometheus.Desc
configDBFailures *prometheus.Desc
avgConfigDBQueryTime *prometheus.Desc
federationMetadataRequests *prometheus.Desc
windowsIntegratedAuthentications *prometheus.Desc
wsfedTokenRequests *prometheus.Desc
wstrustTokenRequests *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
func NewWithFlags(_ *kingpin.Application) *Collector {
return &Collector{}
}
func (c *collector) GetName() string {
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{"AD FS"}, nil
}
func (c *collector) Build() error {
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, _ *wmi.Client) error {
c.adLoginConnectionFailures = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "ad_login_connection_failures_total"),
"Total number of connection failures to an Active Directory domain controller",
@@ -397,9 +404,12 @@ type perflibADFS struct {
FederationMetadataRequests float64 `perflib:"Federation Metadata Requests"`
}
func (c *collector) Collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) Collect(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var adfsData []perflibADFS
err := perflib.UnmarshalObject(ctx.PerfObjects["AD FS"], &adfsData, c.logger)
err := perflib.UnmarshalObject(ctx.PerfObjects["AD FS"], &adfsData, logger)
if err != nil {
return err
}
@@ -661,5 +671,6 @@ func (c *collector) Collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metri
prometheus.CounterValue,
adfsData[0].FederationMetadataRequests,
)
return nil
}

View File

@@ -3,12 +3,14 @@
package cache
import (
"errors"
"log/slog"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/go-kit/log/level"
"github.com/prometheus-community/windows_exporter/pkg/perflib"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const Name = "cache"
@@ -17,247 +19,259 @@ type Config struct{}
var ConfigDefaults = Config{}
// A collector is a Prometheus collector for Perflib Cache metrics
type collector struct {
logger log.Logger
// A Collector is a Prometheus Collector for Perflib Cache metrics.
type Collector struct {
config Config
AsyncCopyReadsTotal *prometheus.Desc
AsyncDataMapsTotal *prometheus.Desc
AsyncFastReadsTotal *prometheus.Desc
AsyncMDLReadsTotal *prometheus.Desc
AsyncPinReadsTotal *prometheus.Desc
CopyReadHitsTotal *prometheus.Desc
CopyReadsTotal *prometheus.Desc
DataFlushesTotal *prometheus.Desc
DataFlushPagesTotal *prometheus.Desc
DataMapHitsPercent *prometheus.Desc
DataMapPinsTotal *prometheus.Desc
DataMapsTotal *prometheus.Desc
DirtyPages *prometheus.Desc
DirtyPageThreshold *prometheus.Desc
FastReadNotPossiblesTotal *prometheus.Desc
FastReadResourceMissesTotal *prometheus.Desc
FastReadsTotal *prometheus.Desc
LazyWriteFlushesTotal *prometheus.Desc
LazyWritePagesTotal *prometheus.Desc
MDLReadHitsTotal *prometheus.Desc
MDLReadsTotal *prometheus.Desc
PinReadHitsTotal *prometheus.Desc
PinReadsTotal *prometheus.Desc
ReadAheadsTotal *prometheus.Desc
SyncCopyReadsTotal *prometheus.Desc
SyncDataMapsTotal *prometheus.Desc
SyncFastReadsTotal *prometheus.Desc
SyncMDLReadsTotal *prometheus.Desc
SyncPinReadsTotal *prometheus.Desc
asyncCopyReadsTotal *prometheus.Desc
asyncDataMapsTotal *prometheus.Desc
asyncFastReadsTotal *prometheus.Desc
asyncMDLReadsTotal *prometheus.Desc
asyncPinReadsTotal *prometheus.Desc
copyReadHitsTotal *prometheus.Desc
copyReadsTotal *prometheus.Desc
dataFlushesTotal *prometheus.Desc
dataFlushPagesTotal *prometheus.Desc
dataMapHitsPercent *prometheus.Desc
dataMapPinsTotal *prometheus.Desc
dataMapsTotal *prometheus.Desc
dirtyPages *prometheus.Desc
dirtyPageThreshold *prometheus.Desc
fastReadNotPossiblesTotal *prometheus.Desc
fastReadResourceMissesTotal *prometheus.Desc
fastReadsTotal *prometheus.Desc
lazyWriteFlushesTotal *prometheus.Desc
lazyWritePagesTotal *prometheus.Desc
mdlReadHitsTotal *prometheus.Desc
mdlReadsTotal *prometheus.Desc
pinReadHitsTotal *prometheus.Desc
pinReadsTotal *prometheus.Desc
readAheadsTotal *prometheus.Desc
syncCopyReadsTotal *prometheus.Desc
syncDataMapsTotal *prometheus.Desc
syncFastReadsTotal *prometheus.Desc
syncMDLReadsTotal *prometheus.Desc
syncPinReadsTotal *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
func NewWithFlags(_ *kingpin.Application) *Collector {
return &Collector{}
}
func (c *collector) GetName() string {
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{"Cache"}, nil
}
func (c *collector) Build() error {
c.AsyncCopyReadsTotal = prometheus.NewDesc(
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, _ *wmi.Client) error {
c.asyncCopyReadsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "async_copy_reads_total"),
"(AsyncCopyReadsTotal)",
nil,
nil,
)
c.AsyncDataMapsTotal = prometheus.NewDesc(
c.asyncDataMapsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "async_data_maps_total"),
"(AsyncDataMapsTotal)",
nil,
nil,
)
c.AsyncFastReadsTotal = prometheus.NewDesc(
c.asyncFastReadsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "async_fast_reads_total"),
"(AsyncFastReadsTotal)",
nil,
nil,
)
c.AsyncMDLReadsTotal = prometheus.NewDesc(
c.asyncMDLReadsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "async_mdl_reads_total"),
"(AsyncMDLReadsTotal)",
nil,
nil,
)
c.AsyncPinReadsTotal = prometheus.NewDesc(
c.asyncPinReadsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "async_pin_reads_total"),
"(AsyncPinReadsTotal)",
nil,
nil,
)
c.CopyReadHitsTotal = prometheus.NewDesc(
c.copyReadHitsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "copy_read_hits_total"),
"(CopyReadHitsTotal)",
nil,
nil,
)
c.CopyReadsTotal = prometheus.NewDesc(
c.copyReadsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "copy_reads_total"),
"(CopyReadsTotal)",
nil,
nil,
)
c.DataFlushesTotal = prometheus.NewDesc(
c.dataFlushesTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "data_flushes_total"),
"(DataFlushesTotal)",
nil,
nil,
)
c.DataFlushPagesTotal = prometheus.NewDesc(
c.dataFlushPagesTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "data_flush_pages_total"),
"(DataFlushPagesTotal)",
nil,
nil,
)
c.DataMapHitsPercent = prometheus.NewDesc(
c.dataMapHitsPercent = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "data_map_hits_percent"),
"(DataMapHitsPercent)",
nil,
nil,
)
c.DataMapPinsTotal = prometheus.NewDesc(
c.dataMapPinsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "data_map_pins_total"),
"(DataMapPinsTotal)",
nil,
nil,
)
c.DataMapsTotal = prometheus.NewDesc(
c.dataMapsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "data_maps_total"),
"(DataMapsTotal)",
nil,
nil,
)
c.DirtyPages = prometheus.NewDesc(
c.dirtyPages = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "dirty_pages"),
"(DirtyPages)",
nil,
nil,
)
c.DirtyPageThreshold = prometheus.NewDesc(
c.dirtyPageThreshold = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "dirty_page_threshold"),
"(DirtyPageThreshold)",
nil,
nil,
)
c.FastReadNotPossiblesTotal = prometheus.NewDesc(
c.fastReadNotPossiblesTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "fast_read_not_possibles_total"),
"(FastReadNotPossiblesTotal)",
nil,
nil,
)
c.FastReadResourceMissesTotal = prometheus.NewDesc(
c.fastReadResourceMissesTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "fast_read_resource_misses_total"),
"(FastReadResourceMissesTotal)",
nil,
nil,
)
c.FastReadsTotal = prometheus.NewDesc(
c.fastReadsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "fast_reads_total"),
"(FastReadsTotal)",
nil,
nil,
)
c.LazyWriteFlushesTotal = prometheus.NewDesc(
c.lazyWriteFlushesTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "lazy_write_flushes_total"),
"(LazyWriteFlushesTotal)",
nil,
nil,
)
c.LazyWritePagesTotal = prometheus.NewDesc(
c.lazyWritePagesTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "lazy_write_pages_total"),
"(LazyWritePagesTotal)",
nil,
nil,
)
c.MDLReadHitsTotal = prometheus.NewDesc(
c.mdlReadHitsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "mdl_read_hits_total"),
"(MDLReadHitsTotal)",
nil,
nil,
)
c.MDLReadsTotal = prometheus.NewDesc(
c.mdlReadsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "mdl_reads_total"),
"(MDLReadsTotal)",
nil,
nil,
)
c.PinReadHitsTotal = prometheus.NewDesc(
c.pinReadHitsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "pin_read_hits_total"),
"(PinReadHitsTotal)",
nil,
nil,
)
c.PinReadsTotal = prometheus.NewDesc(
c.pinReadsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "pin_reads_total"),
"(PinReadsTotal)",
nil,
nil,
)
c.ReadAheadsTotal = prometheus.NewDesc(
c.readAheadsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "read_aheads_total"),
"(ReadAheadsTotal)",
nil,
nil,
)
c.SyncCopyReadsTotal = prometheus.NewDesc(
c.syncCopyReadsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "sync_copy_reads_total"),
"(SyncCopyReadsTotal)",
nil,
nil,
)
c.SyncDataMapsTotal = prometheus.NewDesc(
c.syncDataMapsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "sync_data_maps_total"),
"(SyncDataMapsTotal)",
nil,
nil,
)
c.SyncFastReadsTotal = prometheus.NewDesc(
c.syncFastReadsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "sync_fast_reads_total"),
"(SyncFastReadsTotal)",
nil,
nil,
)
c.SyncMDLReadsTotal = prometheus.NewDesc(
c.syncMDLReadsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "sync_mdl_reads_total"),
"(SyncMDLReadsTotal)",
nil,
nil,
)
c.SyncPinReadsTotal = prometheus.NewDesc(
c.syncPinReadsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "sync_pin_reads_total"),
"(SyncPinReadsTotal)",
nil,
nil,
)
return nil
}
// Collect implements the Collector interface
func (c *collector) Collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
if err := c.collect(ctx, ch); err != nil {
_ = level.Error(c.logger).Log("msg", "failed collecting cache metrics", "err", err)
// Collect implements the Collector interface.
func (c *Collector) Collect(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
if err := c.collect(ctx, logger, ch); err != nil {
logger.Error("failed collecting cache metrics",
slog.Any("err", err),
)
return err
}
return nil
}
@@ -295,182 +309,189 @@ type perflibCache struct {
SyncPinReadsTotal float64 `perflib:"Sync Pin Reads/sec"`
}
func (c *collector) collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collect(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var dst []perflibCache // Single-instance class, array is required but will have single entry.
if err := perflib.UnmarshalObject(ctx.PerfObjects["Cache"], &dst, c.logger); err != nil {
if err := perflib.UnmarshalObject(ctx.PerfObjects["Cache"], &dst, logger); err != nil {
return err
}
if len(dst) != 1 {
return errors.New("expected single instance of Cache")
}
ch <- prometheus.MustNewConstMetric(
c.AsyncCopyReadsTotal,
c.asyncCopyReadsTotal,
prometheus.CounterValue,
dst[0].AsyncCopyReadsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.AsyncDataMapsTotal,
c.asyncDataMapsTotal,
prometheus.CounterValue,
dst[0].AsyncDataMapsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.AsyncFastReadsTotal,
c.asyncFastReadsTotal,
prometheus.CounterValue,
dst[0].AsyncFastReadsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.AsyncMDLReadsTotal,
c.asyncMDLReadsTotal,
prometheus.CounterValue,
dst[0].AsyncMDLReadsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.AsyncPinReadsTotal,
c.asyncPinReadsTotal,
prometheus.CounterValue,
dst[0].AsyncPinReadsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.CopyReadHitsTotal,
c.copyReadHitsTotal,
prometheus.GaugeValue,
dst[0].CopyReadHitsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.CopyReadsTotal,
c.copyReadsTotal,
prometheus.CounterValue,
dst[0].CopyReadsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.DataFlushesTotal,
c.dataFlushesTotal,
prometheus.CounterValue,
dst[0].DataFlushesTotal,
)
ch <- prometheus.MustNewConstMetric(
c.DataFlushPagesTotal,
c.dataFlushPagesTotal,
prometheus.CounterValue,
dst[0].DataFlushPagesTotal,
)
ch <- prometheus.MustNewConstMetric(
c.DataMapHitsPercent,
c.dataMapHitsPercent,
prometheus.GaugeValue,
dst[0].DataMapHitsPercent,
)
ch <- prometheus.MustNewConstMetric(
c.DataMapPinsTotal,
c.dataMapPinsTotal,
prometheus.CounterValue,
dst[0].DataMapPinsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.DataMapsTotal,
c.dataMapsTotal,
prometheus.CounterValue,
dst[0].DataMapsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.DirtyPages,
c.dirtyPages,
prometheus.GaugeValue,
dst[0].DirtyPages,
)
ch <- prometheus.MustNewConstMetric(
c.DirtyPageThreshold,
c.dirtyPageThreshold,
prometheus.GaugeValue,
dst[0].DirtyPageThreshold,
)
ch <- prometheus.MustNewConstMetric(
c.FastReadNotPossiblesTotal,
c.fastReadNotPossiblesTotal,
prometheus.CounterValue,
dst[0].FastReadNotPossiblesTotal,
)
ch <- prometheus.MustNewConstMetric(
c.FastReadResourceMissesTotal,
c.fastReadResourceMissesTotal,
prometheus.CounterValue,
dst[0].FastReadResourceMissesTotal,
)
ch <- prometheus.MustNewConstMetric(
c.FastReadsTotal,
c.fastReadsTotal,
prometheus.CounterValue,
dst[0].FastReadsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.LazyWriteFlushesTotal,
c.lazyWriteFlushesTotal,
prometheus.CounterValue,
dst[0].LazyWriteFlushesTotal,
)
ch <- prometheus.MustNewConstMetric(
c.LazyWritePagesTotal,
c.lazyWritePagesTotal,
prometheus.CounterValue,
dst[0].LazyWritePagesTotal,
)
ch <- prometheus.MustNewConstMetric(
c.MDLReadHitsTotal,
c.mdlReadHitsTotal,
prometheus.CounterValue,
dst[0].MDLReadHitsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.MDLReadsTotal,
c.mdlReadsTotal,
prometheus.CounterValue,
dst[0].MDLReadsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.PinReadHitsTotal,
c.pinReadHitsTotal,
prometheus.CounterValue,
dst[0].PinReadHitsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.PinReadsTotal,
c.pinReadsTotal,
prometheus.CounterValue,
dst[0].PinReadsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.ReadAheadsTotal,
c.readAheadsTotal,
prometheus.CounterValue,
dst[0].ReadAheadsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.SyncCopyReadsTotal,
c.syncCopyReadsTotal,
prometheus.CounterValue,
dst[0].SyncCopyReadsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.SyncDataMapsTotal,
c.syncDataMapsTotal,
prometheus.CounterValue,
dst[0].SyncDataMapsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.SyncFastReadsTotal,
c.syncFastReadsTotal,
prometheus.CounterValue,
dst[0].SyncFastReadsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.SyncMDLReadsTotal,
c.syncMDLReadsTotal,
prometheus.CounterValue,
dst[0].SyncMDLReadsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.SyncPinReadsTotal,
c.syncPinReadsTotal,
prometheus.CounterValue,
dst[0].SyncPinReadsTotal,
)

12
pkg/collector/cache/cache_test.go vendored Normal file
View File

@@ -0,0 +1,12 @@
package cache_test
import (
"testing"
"github.com/prometheus-community/windows_exporter/pkg/collector/cache"
"github.com/prometheus-community/windows_exporter/pkg/testutils"
)
func BenchmarkCollector(b *testing.B) {
testutils.FuncBenchmarkCollector(b, cache.Name, cache.NewWithFlags)
}

View File

@@ -3,12 +3,13 @@
package collector
import (
"errors"
"fmt"
"log/slog"
"slices"
"strings"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/prometheus-community/windows_exporter/pkg/collector/ad"
"github.com/prometheus-community/windows_exporter/pkg/collector/adcs"
"github.com/prometheus-community/windows_exporter/pkg/collector/adfs"
@@ -22,30 +23,22 @@ import (
"github.com/prometheus-community/windows_exporter/pkg/collector/diskdrive"
"github.com/prometheus-community/windows_exporter/pkg/collector/dns"
"github.com/prometheus-community/windows_exporter/pkg/collector/exchange"
"github.com/prometheus-community/windows_exporter/pkg/collector/filetime"
"github.com/prometheus-community/windows_exporter/pkg/collector/fsrmquota"
"github.com/prometheus-community/windows_exporter/pkg/collector/hyperv"
"github.com/prometheus-community/windows_exporter/pkg/collector/iis"
"github.com/prometheus-community/windows_exporter/pkg/collector/license"
"github.com/prometheus-community/windows_exporter/pkg/collector/logical_disk"
"github.com/prometheus-community/windows_exporter/pkg/collector/logon"
"github.com/prometheus-community/windows_exporter/pkg/collector/memory"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_cluster"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_network"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_node"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_resource"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_resourcegroup"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster"
"github.com/prometheus-community/windows_exporter/pkg/collector/msmq"
"github.com/prometheus-community/windows_exporter/pkg/collector/mssql"
"github.com/prometheus-community/windows_exporter/pkg/collector/net"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrexceptions"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrinterop"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrjit"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrloading"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrlocksandthreads"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrmemory"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrremoting"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrsecurity"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework"
"github.com/prometheus-community/windows_exporter/pkg/collector/nps"
"github.com/prometheus-community/windows_exporter/pkg/collector/os"
"github.com/prometheus-community/windows_exporter/pkg/collector/perfdata"
"github.com/prometheus-community/windows_exporter/pkg/collector/physical_disk"
"github.com/prometheus-community/windows_exporter/pkg/collector/printer"
"github.com/prometheus-community/windows_exporter/pkg/collector/process"
@@ -66,20 +59,14 @@ import (
"github.com/prometheus-community/windows_exporter/pkg/collector/vmware_blast"
"github.com/prometheus-community/windows_exporter/pkg/perflib"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/yusufpapurcu/wmi"
)
type Collectors struct {
logger log.Logger
// NewWithFlags To be called by the exporter for collector initialization before running kingpin.Parse.
func NewWithFlags(app *kingpin.Application) *MetricCollectors {
collectors := map[string]Collector{}
collectors map[string]types.Collector
perfCounterQuery string
}
// NewWithFlags To be called by the exporter for collector initialization before running kingpin.Parse
func NewWithFlags(app *kingpin.Application) Collectors {
collectors := map[string]types.Collector{}
for name, builder := range Map {
for name, builder := range BuildersWithFlags {
collectors[name] = builder(app)
}
@@ -89,84 +76,70 @@ func NewWithFlags(app *kingpin.Application) Collectors {
// NewWithConfig To be called by the external libraries for collector initialization without running kingpin.Parse
//
//goland:noinspection GoUnusedExportedFunction
func NewWithConfig(logger log.Logger, config Config) Collectors {
collectors := map[string]types.Collector{}
collectors[ad.Name] = ad.New(logger, &config.Ad)
collectors[adcs.Name] = adcs.New(logger, &config.Adcs)
collectors[adfs.Name] = adfs.New(logger, &config.Adfs)
collectors[cache.Name] = cache.New(logger, &config.Cache)
collectors[container.Name] = container.New(logger, &config.Container)
collectors[cpu.Name] = cpu.New(logger, &config.Cpu)
collectors[cpu_info.Name] = cpu_info.New(logger, &config.CpuInfo)
collectors[cs.Name] = cs.New(logger, &config.Cs)
collectors[dfsr.Name] = dfsr.New(logger, &config.Dfsr)
collectors[dhcp.Name] = dhcp.New(logger, &config.Dhcp)
collectors[diskdrive.Name] = diskdrive.New(logger, &config.Diskdrive)
collectors[dns.Name] = dns.New(logger, &config.Dns)
collectors[exchange.Name] = exchange.New(logger, &config.Exchange)
collectors[exchange.Name] = exchange.New(logger, &config.Fsrmquota)
collectors[hyperv.Name] = hyperv.New(logger, &config.Hyperv)
collectors[iis.Name] = iis.New(logger, &config.Iis)
collectors[license.Name] = license.New(logger, &config.License)
collectors[logical_disk.Name] = logical_disk.New(logger, &config.LogicalDisk)
collectors[logon.Name] = logon.New(logger, &config.Logon)
collectors[memory.Name] = memory.New(logger, &config.Memory)
collectors[mscluster_cluster.Name] = mscluster_cluster.New(logger, &config.MsclusterCluster)
collectors[mscluster_network.Name] = mscluster_network.New(logger, &config.MsclusterNetwork)
collectors[mscluster_node.Name] = mscluster_node.New(logger, &config.MsclusterNode)
collectors[mscluster_resource.Name] = mscluster_resource.New(logger, &config.MsclusterResource)
collectors[mscluster_resourcegroup.Name] = mscluster_resourcegroup.New(logger, &config.MsclusterResourceGroup)
collectors[msmq.Name] = msmq.New(logger, &config.Msmq)
collectors[mssql.Name] = mssql.New(logger, &config.Mssql)
collectors[net.Name] = net.New(logger, &config.Net)
collectors[netframework_clrexceptions.Name] = netframework_clrexceptions.New(logger, &config.NetframeworkClrexceptions)
collectors[netframework_clrinterop.Name] = netframework_clrinterop.New(logger, &config.NetframeworkClrinterop)
collectors[netframework_clrjit.Name] = netframework_clrjit.New(logger, &config.NetframeworkClrjit)
collectors[netframework_clrloading.Name] = netframework_clrloading.New(logger, &config.NetframeworkClrloading)
collectors[netframework_clrlocksandthreads.Name] = netframework_clrlocksandthreads.New(logger, &config.NetframeworkClrlocksandthreads)
collectors[netframework_clrmemory.Name] = netframework_clrmemory.New(logger, &config.NetframeworkClrmemory)
collectors[netframework_clrremoting.Name] = netframework_clrremoting.New(logger, &config.NetframeworkClrremoting)
collectors[netframework_clrsecurity.Name] = netframework_clrsecurity.New(logger, &config.NetframeworkClrsecurity)
collectors[nps.Name] = nps.New(logger, &config.Nps)
collectors[os.Name] = os.New(logger, &config.Os)
collectors[physical_disk.Name] = physical_disk.New(logger, &config.PhysicalDisk)
collectors[printer.Name] = printer.New(logger, &config.Printer)
collectors[process.Name] = process.New(logger, &config.Process)
collectors[remote_fx.Name] = remote_fx.New(logger, &config.RemoteFx)
collectors[scheduled_task.Name] = scheduled_task.New(logger, &config.ScheduledTask)
collectors[service.Name] = service.New(logger, &config.Service)
collectors[smb.Name] = smb.New(logger, &config.Smb)
collectors[smbclient.Name] = smbclient.New(logger, &config.SmbClient)
collectors[smtp.Name] = smtp.New(logger, &config.Smtp)
collectors[system.Name] = system.New(logger, &config.System)
collectors[teradici_pcoip.Name] = teradici_pcoip.New(logger, &config.TeradiciPcoip)
collectors[tcp.Name] = tcp.New(logger, &config.Tcp)
collectors[terminal_services.Name] = terminal_services.New(logger, &config.TerminalServices)
collectors[textfile.Name] = textfile.New(logger, &config.Textfile)
collectors[thermalzone.Name] = thermalzone.New(logger, &config.Thermalzone)
collectors[time.Name] = time.New(logger, &config.Time)
collectors[vmware.Name] = vmware.New(logger, &config.Vmware)
collectors[vmware_blast.Name] = vmware_blast.New(logger, &config.VmwareBlast)
func NewWithConfig(config Config) *MetricCollectors {
collectors := Map{}
collectors[ad.Name] = ad.New(&config.AD)
collectors[adcs.Name] = adcs.New(&config.ADCS)
collectors[adfs.Name] = adfs.New(&config.ADFS)
collectors[cache.Name] = cache.New(&config.Cache)
collectors[container.Name] = container.New(&config.Container)
collectors[cpu.Name] = cpu.New(&config.CPU)
collectors[cpu_info.Name] = cpu_info.New(&config.CPUInfo)
collectors[cs.Name] = cs.New(&config.Cs)
collectors[dfsr.Name] = dfsr.New(&config.DFSR)
collectors[dhcp.Name] = dhcp.New(&config.Dhcp)
collectors[diskdrive.Name] = diskdrive.New(&config.DiskDrive)
collectors[dns.Name] = dns.New(&config.DNS)
collectors[exchange.Name] = exchange.New(&config.Exchange)
collectors[filetime.Name] = filetime.New(&config.Filetime)
collectors[fsrmquota.Name] = fsrmquota.New(&config.Fsrmquota)
collectors[hyperv.Name] = hyperv.New(&config.Hyperv)
collectors[iis.Name] = iis.New(&config.IIS)
collectors[license.Name] = license.New(&config.License)
collectors[logical_disk.Name] = logical_disk.New(&config.LogicalDisk)
collectors[logon.Name] = logon.New(&config.Logon)
collectors[memory.Name] = memory.New(&config.Memory)
collectors[mscluster.Name] = mscluster.New(&config.Mscluster)
collectors[msmq.Name] = msmq.New(&config.Msmq)
collectors[mssql.Name] = mssql.New(&config.Mssql)
collectors[net.Name] = net.New(&config.Net)
collectors[netframework.Name] = netframework.New(&config.NetFramework)
collectors[nps.Name] = nps.New(&config.Nps)
collectors[os.Name] = os.New(&config.Os)
collectors[perfdata.Name] = perfdata.New(&config.PerfData)
collectors[physical_disk.Name] = physical_disk.New(&config.PhysicalDisk)
collectors[printer.Name] = printer.New(&config.Printer)
collectors[process.Name] = process.New(&config.Process)
collectors[remote_fx.Name] = remote_fx.New(&config.RemoteFx)
collectors[scheduled_task.Name] = scheduled_task.New(&config.ScheduledTask)
collectors[service.Name] = service.New(&config.Service)
collectors[smb.Name] = smb.New(&config.SMB)
collectors[smbclient.Name] = smbclient.New(&config.SMBClient)
collectors[smtp.Name] = smtp.New(&config.SMTP)
collectors[system.Name] = system.New(&config.System)
collectors[teradici_pcoip.Name] = teradici_pcoip.New(&config.TeradiciPcoip)
collectors[tcp.Name] = tcp.New(&config.TCP)
collectors[terminal_services.Name] = terminal_services.New(&config.TerminalServices)
collectors[textfile.Name] = textfile.New(&config.Textfile)
collectors[thermalzone.Name] = thermalzone.New(&config.Thermalzone)
collectors[time.Name] = time.New(&config.Time)
collectors[vmware.Name] = vmware.New(&config.Vmware)
collectors[vmware_blast.Name] = vmware_blast.New(&config.VmwareBlast)
return New(collectors)
}
// New To be called by the external libraries for collector initialization
func New(collectors map[string]types.Collector) Collectors {
return Collectors{
collectors: collectors,
// New To be called by the external libraries for collector initialization.
func New(collectors Map) *MetricCollectors {
return &MetricCollectors{
Collectors: collectors,
WMIClient: &wmi.Client{
AllowMissingFields: true,
},
}
}
func (c *Collectors) SetLogger(logger log.Logger) {
c.logger = logger
for _, collector := range c.collectors {
collector.SetLogger(logger)
}
}
func (c *Collectors) SetPerfCounterQuery() error {
func (c *MetricCollectors) SetPerfCounterQuery(logger *slog.Logger) error {
var (
err error
@@ -174,10 +147,10 @@ func (c *Collectors) SetPerfCounterQuery() error {
perfIndicies []string
)
perfCounterDependencies := make([]string, 0, len(c.collectors))
perfCounterDependencies := make([]string, 0, len(c.Collectors))
for _, collector := range c.collectors {
perfCounterNames, err = collector.GetPerfCounter()
for _, collector := range c.Collectors {
perfCounterNames, err = collector.GetPerfCounter(logger)
if err != nil {
return err
}
@@ -190,38 +163,67 @@ func (c *Collectors) SetPerfCounterQuery() error {
perfCounterDependencies = append(perfCounterDependencies, strings.Join(perfIndicies, " "))
}
c.perfCounterQuery = strings.Join(perfCounterDependencies, " ")
c.PerfCounterQuery = strings.Join(perfCounterDependencies, " ")
return nil
}
// Enable removes all collectors that not enabledCollectors
func (c *Collectors) Enable(enabledCollectors []string) {
for name := range c.collectors {
// Enable removes all collectors that not enabledCollectors.
func (c *MetricCollectors) Enable(enabledCollectors []string) {
for name := range c.Collectors {
if !slices.Contains(enabledCollectors, name) {
delete(c.collectors, name)
delete(c.Collectors, name)
}
}
}
// Build To be called by the exporter for collector initialization
func (c *Collectors) Build() error {
// Build To be called by the exporter for collector initialization.
func (c *MetricCollectors) Build(logger *slog.Logger) error {
var err error
for _, collector := range c.collectors {
if err = collector.Build(); err != nil {
return err
c.WMIClient.SWbemServicesClient, err = wmi.InitializeSWbemServices(c.WMIClient)
if err != nil {
return fmt.Errorf("initialize SWbemServices: %w", err)
}
for _, collector := range c.Collectors {
if err = collector.Build(logger, c.WMIClient); err != nil {
return fmt.Errorf("error build collector %s: %w", collector.GetName(), err)
}
}
return nil
}
// PrepareScrapeContext creates a ScrapeContext to be used during a single scrape
func (c *Collectors) PrepareScrapeContext() (*types.ScrapeContext, error) {
objs, err := perflib.GetPerflibSnapshot(c.perfCounterQuery)
// PrepareScrapeContext creates a ScrapeContext to be used during a single scrape.
func (c *MetricCollectors) PrepareScrapeContext() (*types.ScrapeContext, error) {
if c.PerfCounterQuery == "" { // if perfCounterQuery is empty, no perf counters are needed.
return &types.ScrapeContext{}, nil
}
objs, err := perflib.GetPerflibSnapshot(c.PerfCounterQuery)
if err != nil {
return nil, err
}
return &types.ScrapeContext{PerfObjects: objs}, nil
}
// Close To be called by the exporter for collector cleanup.
func (c *MetricCollectors) Close(logger *slog.Logger) error {
errs := make([]error, 0, len(c.Collectors))
for _, collector := range c.Collectors {
if err := collector.Close(logger); err != nil {
errs = append(errs, err)
}
}
if c.WMIClient != nil && c.WMIClient.SWbemServicesClient != nil {
if err := c.WMIClient.SWbemServicesClient.Close(); err != nil {
errs = append(errs, err)
}
}
return errors.Join(errs...)
}

View File

@@ -14,30 +14,22 @@ import (
"github.com/prometheus-community/windows_exporter/pkg/collector/diskdrive"
"github.com/prometheus-community/windows_exporter/pkg/collector/dns"
"github.com/prometheus-community/windows_exporter/pkg/collector/exchange"
"github.com/prometheus-community/windows_exporter/pkg/collector/filetime"
"github.com/prometheus-community/windows_exporter/pkg/collector/fsrmquota"
"github.com/prometheus-community/windows_exporter/pkg/collector/hyperv"
"github.com/prometheus-community/windows_exporter/pkg/collector/iis"
"github.com/prometheus-community/windows_exporter/pkg/collector/license"
"github.com/prometheus-community/windows_exporter/pkg/collector/logical_disk"
"github.com/prometheus-community/windows_exporter/pkg/collector/logon"
"github.com/prometheus-community/windows_exporter/pkg/collector/memory"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_cluster"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_network"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_node"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_resource"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_resourcegroup"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster"
"github.com/prometheus-community/windows_exporter/pkg/collector/msmq"
"github.com/prometheus-community/windows_exporter/pkg/collector/mssql"
"github.com/prometheus-community/windows_exporter/pkg/collector/net"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrexceptions"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrinterop"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrjit"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrloading"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrlocksandthreads"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrmemory"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrremoting"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrsecurity"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework"
"github.com/prometheus-community/windows_exporter/pkg/collector/nps"
"github.com/prometheus-community/windows_exporter/pkg/collector/os"
"github.com/prometheus-community/windows_exporter/pkg/collector/perfdata"
"github.com/prometheus-community/windows_exporter/pkg/collector/physical_disk"
"github.com/prometheus-community/windows_exporter/pkg/collector/printer"
"github.com/prometheus-community/windows_exporter/pkg/collector/process"
@@ -59,122 +51,104 @@ import (
)
type Config struct {
Ad ad.Config `yaml:"ad"`
Adcs adcs.Config `yaml:"adcs"`
Adfs adfs.Config `yaml:"adfs"`
Cache cache.Config `yaml:"cache"`
Container container.Config `yaml:"container"`
Cpu cpu.Config `yaml:"cpu"`
CpuInfo cpu_info.Config `yaml:"cpu_info"`
Cs cs.Config `yaml:"cs"`
Dfsr dfsr.Config `yaml:"dfsr"`
Dhcp dhcp.Config `yaml:"dhcp"`
Diskdrive diskdrive.Config `yaml:"diskdrive"`
Dns dns.Config `yaml:"dns"`
Exchange exchange.Config `yaml:"exchange"`
Fsrmquota exchange.Config `yaml:"fsrmquota"`
Hyperv hyperv.Config `yaml:"hyperv"`
Iis iis.Config `yaml:"iis"`
License license.Config `yaml:"license"`
LogicalDisk logical_disk.Config `yaml:"logical_disk"`
Logon logon.Config `yaml:"logon"`
Memory memory.Config `yaml:"memory"`
MsclusterCluster mscluster_cluster.Config `yaml:"mscluster_cluster"`
MsclusterNetwork mscluster_network.Config `yaml:"mscluster_network"`
MsclusterNode mscluster_node.Config `yaml:"mscluster_node"`
MsclusterResource mscluster_resource.Config `yaml:"mscluster_resource"`
MsclusterResourceGroup mscluster_resourcegroup.Config `yaml:"mscluster_resourcegroup"`
Msmq msmq.Config `yaml:"msmq"`
Mssql mssql.Config `yaml:"mssql"`
Net net.Config `yaml:"net"`
NetframeworkClrexceptions netframework_clrexceptions.Config `yaml:"netframework_clrexceptions"`
NetframeworkClrinterop netframework_clrinterop.Config `yaml:"netframework_clrinterop"`
NetframeworkClrjit netframework_clrjit.Config `yaml:"netframework_clrjit"`
NetframeworkClrloading netframework_clrloading.Config `yaml:"netframework_clrloading"`
NetframeworkClrlocksandthreads netframework_clrlocksandthreads.Config `yaml:"netframework_clrlocksandthreads"`
NetframeworkClrmemory netframework_clrmemory.Config `yaml:"netframework_clrmemory"`
NetframeworkClrremoting netframework_clrremoting.Config `yaml:"netframework_clrremoting"`
NetframeworkClrsecurity netframework_clrsecurity.Config `yaml:"netframework_clrsecurity"`
Nps nps.Config `yaml:"nps"`
Os os.Config `yaml:"os"`
PhysicalDisk physical_disk.Config `yaml:"physical_disk"`
Printer printer.Config `yaml:"printer"`
Process process.Config `yaml:"process"`
RemoteFx remote_fx.Config `yaml:"remote_fx"`
ScheduledTask scheduled_task.Config `yaml:"scheduled_task"`
Service service.Config `yaml:"service"`
Smb smb.Config `yaml:"smb"`
SmbClient smbclient.Config `yaml:"smbclient"`
Smtp smtp.Config `yaml:"smtp"`
System system.Config `yaml:"system"`
TeradiciPcoip teradici_pcoip.Config `yaml:"teradici_pcoip"`
Tcp tcp.Config `yaml:"tcp"`
TerminalServices terminal_services.Config `yaml:"terminal_services"`
Textfile textfile.Config `yaml:"textfile"`
Thermalzone thermalzone.Config `yaml:"thermalzone"`
Time time.Config `yaml:"time"`
Vmware vmware.Config `yaml:"vmware"`
VmwareBlast vmware_blast.Config `yaml:"vmware_blast"`
AD ad.Config `yaml:"ad"`
ADCS adcs.Config `yaml:"adcs"`
ADFS adfs.Config `yaml:"adfs"`
Cache cache.Config `yaml:"cache"`
Container container.Config `yaml:"container"`
CPU cpu.Config `yaml:"cpu"`
CPUInfo cpu_info.Config `yaml:"cpu_info"`
Cs cs.Config `yaml:"cs"`
DFSR dfsr.Config `yaml:"dfsr"`
Dhcp dhcp.Config `yaml:"dhcp"`
DiskDrive diskdrive.Config `yaml:"diskdrive"` //nolint:tagliatelle
DNS dns.Config `yaml:"dns"`
Exchange exchange.Config `yaml:"exchange"`
Filetime filetime.Config `yaml:"filetime"`
Fsrmquota fsrmquota.Config `yaml:"fsrmquota"`
Hyperv hyperv.Config `yaml:"hyperv"`
IIS iis.Config `yaml:"iis"`
License license.Config `yaml:"license"`
LogicalDisk logical_disk.Config `yaml:"logical_disk"`
Logon logon.Config `yaml:"logon"`
Memory memory.Config `yaml:"memory"`
Mscluster mscluster.Config `yaml:"mscluster"`
Msmq msmq.Config `yaml:"msmq"`
Mssql mssql.Config `yaml:"mssql"`
Net net.Config `yaml:"net"`
NetFramework netframework.Config `yaml:"net_framework"`
Nps nps.Config `yaml:"nps"`
Os os.Config `yaml:"os"`
PerfData perfdata.Config `yaml:"perf_data"`
PhysicalDisk physical_disk.Config `yaml:"physical_disk"`
Printer printer.Config `yaml:"printer"`
Process process.Config `yaml:"process"`
RemoteFx remote_fx.Config `yaml:"remote_fx"`
ScheduledTask scheduled_task.Config `yaml:"scheduled_task"`
Service service.Config `yaml:"service"`
SMB smb.Config `yaml:"smb"`
SMBClient smbclient.Config `yaml:"smbclient"` //nolint:tagliatelle
SMTP smtp.Config `yaml:"smtp"`
System system.Config `yaml:"system"`
TeradiciPcoip teradici_pcoip.Config `yaml:"teradici_pcoip"`
TCP tcp.Config `yaml:"tcp"`
TerminalServices terminal_services.Config `yaml:"terminal_services"`
Textfile textfile.Config `yaml:"textfile"`
Thermalzone thermalzone.Config `yaml:"thermalzone"`
Time time.Config `yaml:"time"`
Vmware vmware.Config `yaml:"vmware"`
VmwareBlast vmware_blast.Config `yaml:"vmware_blast"`
}
// ConfigDefaults Is an interface to be used by the external libraries. It holds all ConfigDefaults form all collectors
//
//goland:noinspection GoUnusedGlobalVariable
var ConfigDefaults = Config{
Ad: ad.ConfigDefaults,
Adcs: adcs.ConfigDefaults,
Adfs: adfs.ConfigDefaults,
Cache: cache.ConfigDefaults,
Container: container.ConfigDefaults,
Cpu: cpu.ConfigDefaults,
CpuInfo: cpu_info.ConfigDefaults,
Cs: cs.ConfigDefaults,
Dfsr: dfsr.ConfigDefaults,
Dhcp: dhcp.ConfigDefaults,
Diskdrive: diskdrive.ConfigDefaults,
Dns: dns.ConfigDefaults,
Exchange: exchange.ConfigDefaults,
Fsrmquota: exchange.ConfigDefaults,
Hyperv: hyperv.ConfigDefaults,
Iis: iis.ConfigDefaults,
License: license.ConfigDefaults,
LogicalDisk: logical_disk.ConfigDefaults,
Logon: logon.ConfigDefaults,
Memory: memory.ConfigDefaults,
MsclusterCluster: mscluster_cluster.ConfigDefaults,
MsclusterNetwork: mscluster_network.ConfigDefaults,
MsclusterNode: mscluster_node.ConfigDefaults,
MsclusterResource: mscluster_resource.ConfigDefaults,
MsclusterResourceGroup: mscluster_resourcegroup.ConfigDefaults,
Msmq: msmq.ConfigDefaults,
Mssql: mssql.ConfigDefaults,
Net: net.ConfigDefaults,
NetframeworkClrexceptions: netframework_clrexceptions.ConfigDefaults,
NetframeworkClrinterop: netframework_clrinterop.ConfigDefaults,
NetframeworkClrjit: netframework_clrjit.ConfigDefaults,
NetframeworkClrloading: netframework_clrloading.ConfigDefaults,
NetframeworkClrlocksandthreads: netframework_clrlocksandthreads.ConfigDefaults,
NetframeworkClrmemory: netframework_clrmemory.ConfigDefaults,
NetframeworkClrremoting: netframework_clrremoting.ConfigDefaults,
NetframeworkClrsecurity: netframework_clrsecurity.ConfigDefaults,
Nps: nps.ConfigDefaults,
Os: os.ConfigDefaults,
PhysicalDisk: physical_disk.ConfigDefaults,
Printer: printer.ConfigDefaults,
Process: process.ConfigDefaults,
RemoteFx: remote_fx.ConfigDefaults,
ScheduledTask: scheduled_task.ConfigDefaults,
Service: service.ConfigDefaults,
Smb: smb.ConfigDefaults,
SmbClient: smbclient.ConfigDefaults,
Smtp: smtp.ConfigDefaults,
System: system.ConfigDefaults,
TeradiciPcoip: teradici_pcoip.ConfigDefaults,
Tcp: tcp.ConfigDefaults,
TerminalServices: terminal_services.ConfigDefaults,
Textfile: textfile.ConfigDefaults,
Thermalzone: thermalzone.ConfigDefaults,
Time: time.ConfigDefaults,
Vmware: vmware.ConfigDefaults,
VmwareBlast: vmware_blast.ConfigDefaults,
AD: ad.ConfigDefaults,
ADCS: adcs.ConfigDefaults,
ADFS: adfs.ConfigDefaults,
Cache: cache.ConfigDefaults,
Container: container.ConfigDefaults,
CPU: cpu.ConfigDefaults,
CPUInfo: cpu_info.ConfigDefaults,
Cs: cs.ConfigDefaults,
DFSR: dfsr.ConfigDefaults,
Dhcp: dhcp.ConfigDefaults,
DiskDrive: diskdrive.ConfigDefaults,
DNS: dns.ConfigDefaults,
Exchange: exchange.ConfigDefaults,
Filetime: filetime.ConfigDefaults,
Fsrmquota: fsrmquota.ConfigDefaults,
Hyperv: hyperv.ConfigDefaults,
IIS: iis.ConfigDefaults,
License: license.ConfigDefaults,
LogicalDisk: logical_disk.ConfigDefaults,
Logon: logon.ConfigDefaults,
Memory: memory.ConfigDefaults,
Mscluster: mscluster.ConfigDefaults,
Msmq: msmq.ConfigDefaults,
Mssql: mssql.ConfigDefaults,
Net: net.ConfigDefaults,
NetFramework: netframework.ConfigDefaults,
Nps: nps.ConfigDefaults,
Os: os.ConfigDefaults,
PerfData: perfdata.ConfigDefaults,
PhysicalDisk: physical_disk.ConfigDefaults,
Printer: printer.ConfigDefaults,
Process: process.ConfigDefaults,
RemoteFx: remote_fx.ConfigDefaults,
ScheduledTask: scheduled_task.ConfigDefaults,
Service: service.ConfigDefaults,
SMB: smb.ConfigDefaults,
SMBClient: smbclient.ConfigDefaults,
SMTP: smtp.ConfigDefaults,
System: system.ConfigDefaults,
TeradiciPcoip: teradici_pcoip.ConfigDefaults,
TCP: tcp.ConfigDefaults,
TerminalServices: terminal_services.ConfigDefaults,
Textfile: textfile.ConfigDefaults,
Thermalzone: thermalzone.ConfigDefaults,
Time: time.ConfigDefaults,
Vmware: vmware.ConfigDefaults,
VmwareBlast: vmware_blast.ConfigDefaults,
}

View File

@@ -3,15 +3,17 @@
package container
import (
"errors"
"fmt"
"log/slog"
"strings"
"github.com/Microsoft/hcsshim"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/go-kit/log/level"
"github.com/prometheus-community/windows_exporter/pkg/perflib"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const Name = "container"
@@ -20,364 +22,424 @@ type Config struct{}
var ConfigDefaults = Config{}
// A collector is a Prometheus collector for containers metrics
type collector struct {
logger log.Logger
// A Collector is a Prometheus Collector for containers metrics.
type Collector struct {
config Config
// Presence
ContainerAvailable *prometheus.Desc
containerAvailable *prometheus.Desc
// Number of containers
ContainersCount *prometheus.Desc
// memory
UsageCommitBytes *prometheus.Desc
UsageCommitPeakBytes *prometheus.Desc
UsagePrivateWorkingSetBytes *prometheus.Desc
containersCount *prometheus.Desc
// Memory
usageCommitBytes *prometheus.Desc
usageCommitPeakBytes *prometheus.Desc
usagePrivateWorkingSetBytes *prometheus.Desc
// CPU
RuntimeTotal *prometheus.Desc
RuntimeUser *prometheus.Desc
RuntimeKernel *prometheus.Desc
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
bytesReceived *prometheus.Desc
bytesSent *prometheus.Desc
packetsReceived *prometheus.Desc
packetsSent *prometheus.Desc
droppedPacketsIncoming *prometheus.Desc
droppedPacketsOutgoing *prometheus.Desc
// Storage
ReadCountNormalized *prometheus.Desc
ReadSizeBytes *prometheus.Desc
WriteCountNormalized *prometheus.Desc
WriteSizeBytes *prometheus.Desc
readCountNormalized *prometheus.Desc
readSizeBytes *prometheus.Desc
writeCountNormalized *prometheus.Desc
writeSizeBytes *prometheus.Desc
}
// New constructs a new collector
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
// New constructs a new Collector.
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
func NewWithFlags(_ *kingpin.Application) *Collector {
return &Collector{}
}
func (c *collector) GetName() string {
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{}, nil
}
func (c *collector) Build() error {
c.ContainerAvailable = prometheus.NewDesc(
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, _ *wmi.Client) error {
c.containerAvailable = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "available"),
"Available",
[]string{"container_id"},
nil,
)
c.ContainersCount = prometheus.NewDesc(
c.containersCount = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "count"),
"Number of containers",
nil,
nil,
)
c.UsageCommitBytes = prometheus.NewDesc(
c.usageCommitBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "memory_usage_commit_bytes"),
"Memory Usage Commit Bytes",
[]string{"container_id"},
nil,
)
c.UsageCommitPeakBytes = prometheus.NewDesc(
c.usageCommitPeakBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "memory_usage_commit_peak_bytes"),
"Memory Usage Commit Peak Bytes",
[]string{"container_id"},
nil,
)
c.UsagePrivateWorkingSetBytes = prometheus.NewDesc(
c.usagePrivateWorkingSetBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "memory_usage_private_working_set_bytes"),
"Memory Usage Private Working Set Bytes",
[]string{"container_id"},
nil,
)
c.RuntimeTotal = prometheus.NewDesc(
c.runtimeTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "cpu_usage_seconds_total"),
"Total Run time in Seconds",
[]string{"container_id"},
nil,
)
c.RuntimeUser = prometheus.NewDesc(
c.runtimeUser = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "cpu_usage_seconds_usermode"),
"Run Time in User mode in Seconds",
[]string{"container_id"},
nil,
)
c.RuntimeKernel = prometheus.NewDesc(
c.runtimeKernel = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "cpu_usage_seconds_kernelmode"),
"Run time in Kernel mode in Seconds",
[]string{"container_id"},
nil,
)
c.BytesReceived = prometheus.NewDesc(
c.bytesReceived = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "network_receive_bytes_total"),
"Bytes Received on Interface",
[]string{"container_id", "interface"},
nil,
)
c.BytesSent = prometheus.NewDesc(
c.bytesSent = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "network_transmit_bytes_total"),
"Bytes Sent on Interface",
[]string{"container_id", "interface"},
nil,
)
c.PacketsReceived = prometheus.NewDesc(
c.packetsReceived = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "network_receive_packets_total"),
"Packets Received on Interface",
[]string{"container_id", "interface"},
nil,
)
c.PacketsSent = prometheus.NewDesc(
c.packetsSent = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "network_transmit_packets_total"),
"Packets Sent on Interface",
[]string{"container_id", "interface"},
nil,
)
c.DroppedPacketsIncoming = prometheus.NewDesc(
c.droppedPacketsIncoming = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "network_receive_packets_dropped_total"),
"Dropped Incoming Packets on Interface",
[]string{"container_id", "interface"},
nil,
)
c.DroppedPacketsOutgoing = prometheus.NewDesc(
c.droppedPacketsOutgoing = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "network_transmit_packets_dropped_total"),
"Dropped Outgoing Packets on Interface",
[]string{"container_id", "interface"},
nil,
)
c.ReadCountNormalized = prometheus.NewDesc(
c.readCountNormalized = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "storage_read_count_normalized_total"),
"Read Count Normalized",
[]string{"container_id"},
nil,
)
c.ReadSizeBytes = prometheus.NewDesc(
c.readSizeBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "storage_read_size_bytes_total"),
"Read Size Bytes",
[]string{"container_id"},
nil,
)
c.WriteCountNormalized = prometheus.NewDesc(
c.writeCountNormalized = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "storage_write_count_normalized_total"),
"Write Count Normalized",
[]string{"container_id"},
nil,
)
c.WriteSizeBytes = prometheus.NewDesc(
c.writeSizeBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "storage_write_size_bytes_total"),
"Write Size Bytes",
[]string{"container_id"},
nil,
)
return 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 collector metrics", "err", err)
func (c *Collector) Collect(_ *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
if err := c.collect(logger, ch); err != nil {
logger.Error("failed collecting collector metrics",
slog.Any("err", err),
)
return err
}
return nil
}
// containerClose closes the container resource
func (c *collector) containerClose(container hcsshim.Container) {
err := container.Close()
if err != nil {
_ = level.Error(c.logger).Log("err", err)
}
}
func (c *collector) collect(ch chan<- prometheus.Metric) error {
func (c *Collector) collect(logger *slog.Logger, ch chan<- prometheus.Metric) error {
// Types Container is passed to get the containers compute systems only
containers, err := hcsshim.GetContainers(hcsshim.ComputeSystemQuery{Types: []string{"Container"}})
if err != nil {
_ = level.Error(c.logger).Log("msg", "Err in Getting containers", "err", err)
logger.Error("Err in Getting containers",
slog.Any("err", err),
)
return err
}
count := len(containers)
ch <- prometheus.MustNewConstMetric(
c.ContainersCount,
c.containersCount,
prometheus.GaugeValue,
float64(count),
)
if count == 0 {
return nil
}
containerPrefixes := make(map[string]string)
collectErrors := make([]error, 0, len(containers))
for _, containerDetails := range containers {
// https://stackoverflow.com/questions/45617758/proper-way-to-release-resources-with-defer-in-a-loop
func() {
container, err := hcsshim.OpenContainer(containerDetails.ID)
if container != nil {
defer c.containerClose(container)
}
if err != nil {
_ = level.Error(c.logger).Log("msg", "err in opening container", "containerId", containerDetails.ID, "err", err)
return
containerIdWithPrefix := getContainerIdWithPrefix(containerDetails)
if err = c.collectContainer(logger, ch, containerDetails, containerIdWithPrefix); err != nil {
if hcsshim.IsNotExist(err) {
logger.Debug("err in fetching container statistics",
slog.String("container_id", containerDetails.ID),
slog.Any("err", err),
)
} else {
logger.Error("err in fetching container statistics",
slog.String("container_id", containerDetails.ID),
slog.Any("err", err),
)
collectErrors = append(collectErrors, err)
}
cstats, err := container.Statistics()
if err != nil {
_ = level.Error(c.logger).Log("msg", "err in fetching container Statistics", "containerId", containerDetails.ID, "err", err)
return
}
continue
}
containerIdWithPrefix := getContainerIdWithPrefix(containerDetails)
containerPrefixes[containerDetails.ID] = containerIdWithPrefix
ch <- prometheus.MustNewConstMetric(
c.ContainerAvailable,
prometheus.CounterValue,
1,
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.UsageCommitBytes,
prometheus.GaugeValue,
float64(cstats.Memory.UsageCommitBytes),
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.UsageCommitPeakBytes,
prometheus.GaugeValue,
float64(cstats.Memory.UsageCommitPeakBytes),
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.UsagePrivateWorkingSetBytes,
prometheus.GaugeValue,
float64(cstats.Memory.UsagePrivateWorkingSetBytes),
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.RuntimeTotal,
prometheus.CounterValue,
float64(cstats.Processor.TotalRuntime100ns)*perflib.TicksToSecondScaleFactor,
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.RuntimeUser,
prometheus.CounterValue,
float64(cstats.Processor.RuntimeUser100ns)*perflib.TicksToSecondScaleFactor,
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.RuntimeKernel,
prometheus.CounterValue,
float64(cstats.Processor.RuntimeKernel100ns)*perflib.TicksToSecondScaleFactor,
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.ReadCountNormalized,
prometheus.CounterValue,
float64(cstats.Storage.ReadCountNormalized),
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.ReadSizeBytes,
prometheus.CounterValue,
float64(cstats.Storage.ReadSizeBytes),
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.WriteCountNormalized,
prometheus.CounterValue,
float64(cstats.Storage.WriteCountNormalized),
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.WriteSizeBytes,
prometheus.CounterValue,
float64(cstats.Storage.WriteSizeBytes),
containerIdWithPrefix,
)
}()
containerPrefixes[containerDetails.ID] = containerIdWithPrefix
}
if err = c.collectNetworkMetrics(logger, ch, containerPrefixes); err != nil {
return fmt.Errorf("error in fetching container network statistics: %w", err)
}
if len(collectErrors) > 0 {
return fmt.Errorf("errors while fetching container statistics: %w", errors.Join(collectErrors...))
}
return nil
}
func (c *Collector) collectContainer(logger *slog.Logger, ch chan<- prometheus.Metric, containerDetails hcsshim.ContainerProperties, containerIdWithPrefix string) error {
container, err := hcsshim.OpenContainer(containerDetails.ID)
if err != nil {
return fmt.Errorf("error in opening container: %w", err)
}
defer func() {
if container == nil {
return
}
if err := container.Close(); err != nil {
logger.Error("error in closing container",
slog.Any("err", err),
)
}
}()
containerStats, err := container.Statistics()
if err != nil {
return fmt.Errorf("error in fetching container statistics: %w", err)
}
ch <- prometheus.MustNewConstMetric(
c.containerAvailable,
prometheus.CounterValue,
1,
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.usageCommitBytes,
prometheus.GaugeValue,
float64(containerStats.Memory.UsageCommitBytes),
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.usageCommitPeakBytes,
prometheus.GaugeValue,
float64(containerStats.Memory.UsageCommitPeakBytes),
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.usagePrivateWorkingSetBytes,
prometheus.GaugeValue,
float64(containerStats.Memory.UsagePrivateWorkingSetBytes),
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.runtimeTotal,
prometheus.CounterValue,
float64(containerStats.Processor.TotalRuntime100ns)*perflib.TicksToSecondScaleFactor,
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.runtimeUser,
prometheus.CounterValue,
float64(containerStats.Processor.RuntimeUser100ns)*perflib.TicksToSecondScaleFactor,
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.runtimeKernel,
prometheus.CounterValue,
float64(containerStats.Processor.RuntimeKernel100ns)*perflib.TicksToSecondScaleFactor,
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.readCountNormalized,
prometheus.CounterValue,
float64(containerStats.Storage.ReadCountNormalized),
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.readSizeBytes,
prometheus.CounterValue,
float64(containerStats.Storage.ReadSizeBytes),
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.writeCountNormalized,
prometheus.CounterValue,
float64(containerStats.Storage.WriteCountNormalized),
containerIdWithPrefix,
)
ch <- prometheus.MustNewConstMetric(
c.writeSizeBytes,
prometheus.CounterValue,
float64(containerStats.Storage.WriteSizeBytes),
containerIdWithPrefix,
)
return nil
}
// collectNetworkMetrics collects network metrics for containers.
// With HNSv2, the network stats must be collected from hcsshim.HNSListEndpointRequest.
// Network statistics from the container.Statistics() are providing data only, if HNSv1 is used.
// Ref: https://github.com/prometheus-community/windows_exporter/pull/1218
func (c *Collector) collectNetworkMetrics(logger *slog.Logger, ch chan<- prometheus.Metric, containerPrefixes map[string]string) error {
hnsEndpoints, err := hcsshim.HNSListEndpointRequest()
if err != nil {
_ = level.Warn(c.logger).Log("msg", "Failed to collect network stats for containers")
logger.Warn("Failed to collect network stats for containers")
return err
}
if len(hnsEndpoints) == 0 {
_ = level.Info(c.logger).Log("msg", "No network stats for containers to collect")
logger.Info("No network stats for containers to collect")
return nil
}
for _, endpoint := range hnsEndpoints {
endpointStats, err := hcsshim.GetHNSEndpointStats(endpoint.Id)
if err != nil {
_ = level.Warn(c.logger).Log("msg", "Failed to collect network stats for interface "+endpoint.Id, "err", err)
logger.Warn("Failed to collect network stats for interface "+endpoint.Id,
slog.Any("err", err),
)
continue
}
for _, containerId := range endpoint.SharedContainers {
containerIdWithPrefix, ok := containerPrefixes[containerId]
endpointId := strings.ToUpper(endpoint.Id)
if !ok {
_ = level.Warn(c.logger).Log("msg", "Failed to collect network stats for container "+containerId)
logger.Debug("Failed to collect network stats for container " + containerId)
continue
}
endpointId := strings.ToUpper(endpoint.Id)
ch <- prometheus.MustNewConstMetric(
c.BytesReceived,
c.bytesReceived,
prometheus.CounterValue,
float64(endpointStats.BytesReceived),
containerIdWithPrefix, endpointId,
)
ch <- prometheus.MustNewConstMetric(
c.BytesSent,
c.bytesSent,
prometheus.CounterValue,
float64(endpointStats.BytesSent),
containerIdWithPrefix, endpointId,
)
ch <- prometheus.MustNewConstMetric(
c.PacketsReceived,
c.packetsReceived,
prometheus.CounterValue,
float64(endpointStats.PacketsReceived),
containerIdWithPrefix, endpointId,
)
ch <- prometheus.MustNewConstMetric(
c.PacketsSent,
c.packetsSent,
prometheus.CounterValue,
float64(endpointStats.PacketsSent),
containerIdWithPrefix, endpointId,
)
ch <- prometheus.MustNewConstMetric(
c.DroppedPacketsIncoming,
c.droppedPacketsIncoming,
prometheus.CounterValue,
float64(endpointStats.DroppedPacketsIncoming),
containerIdWithPrefix, endpointId,
)
ch <- prometheus.MustNewConstMetric(
c.DroppedPacketsOutgoing,
c.droppedPacketsOutgoing,
prometheus.CounterValue,
float64(endpointStats.DroppedPacketsOutgoing),
containerIdWithPrefix, endpointId,

View File

@@ -0,0 +1,28 @@
package cpu
// Processor performance counters.
const (
C1TimeSeconds = "% C1 Time"
C2TimeSeconds = "% C2 Time"
C3TimeSeconds = "% C3 Time"
C1TransitionsTotal = "C1 Transitions/sec"
C2TransitionsTotal = "C2 Transitions/sec"
C3TransitionsTotal = "C3 Transitions/sec"
ClockInterruptsTotal = "Clock Interrupts/sec"
DPCsQueuedTotal = "DPCs Queued/sec"
DPCTimeSeconds = "% DPC Time"
IdleBreakEventsTotal = "Idle Break Events/sec"
IdleTimeSeconds = "% Idle Time"
InterruptsTotal = "Interrupts/sec"
InterruptTimeSeconds = "% Interrupt Time"
ParkingStatus = "Parking Status"
PerformanceLimitPercent = "% Performance Limit"
PriorityTimeSeconds = "% Priority Time"
PrivilegedTimeSeconds = "% Privileged Time"
PrivilegedUtilitySeconds = "% Privileged Utility"
ProcessorFrequencyMHz = "Processor Frequency"
ProcessorPerformance = "% Processor Performance"
ProcessorTimeSeconds = "% Processor Time"
ProcessorUtilityRate = "% Processor Utility"
UserTimeSeconds = "% User Time"
)

View File

@@ -3,14 +3,17 @@
package cpu
import (
"fmt"
"log/slog"
"strings"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/prometheus-community/windows_exporter/pkg/perfdata"
"github.com/prometheus-community/windows_exporter/pkg/perflib"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus-community/windows_exporter/pkg/winversion"
"github.com/prometheus-community/windows_exporter/pkg/utils"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const Name = "cpu"
@@ -19,160 +22,200 @@ type Config struct{}
var ConfigDefaults = Config{}
type collector struct {
logger log.Logger
type Collector struct {
config Config
CStateSecondsTotal *prometheus.Desc
TimeTotal *prometheus.Desc
InterruptsTotal *prometheus.Desc
DPCsTotal *prometheus.Desc
perfDataCollector *perfdata.Collector
ClockInterruptsTotal *prometheus.Desc
IdleBreakEventsTotal *prometheus.Desc
ParkingStatus *prometheus.Desc
ProcessorFrequencyMHz *prometheus.Desc
ProcessorMaxFrequencyMHz *prometheus.Desc
ProcessorPerformance *prometheus.Desc
ProcessorMPerf *prometheus.Desc
ProcessorRTC *prometheus.Desc
ProcessorUtility *prometheus.Desc
ProcessorPrivUtility *prometheus.Desc
logicalProcessors *prometheus.Desc
cStateSecondsTotal *prometheus.Desc
timeTotal *prometheus.Desc
interruptsTotal *prometheus.Desc
dpcsTotal *prometheus.Desc
clockInterruptsTotal *prometheus.Desc
idleBreakEventsTotal *prometheus.Desc
parkingStatus *prometheus.Desc
processorFrequencyMHz *prometheus.Desc
processorPerformance *prometheus.Desc
processorMPerf *prometheus.Desc
processorRTC *prometheus.Desc
processorUtility *prometheus.Desc
processorPrivilegedUtility *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
func NewWithFlags(_ *kingpin.Application) *Collector {
return &Collector{}
}
func (c *collector) GetName() string {
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) {
if winversion.WindowsVersionFloat > 6.05 {
return []string{"Processor Information"}, nil
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
if utils.PDHEnabled() {
return []string{}, nil
}
return []string{"Processor"}, nil
return []string{"Processor Information"}, nil
}
func (c *collector) Build() error {
c.CStateSecondsTotal = prometheus.NewDesc(
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, _ *wmi.Client) error {
if utils.PDHEnabled() {
counters := []string{
C1TimeSeconds,
C2TimeSeconds,
C3TimeSeconds,
C1TransitionsTotal,
C2TransitionsTotal,
C3TransitionsTotal,
ClockInterruptsTotal,
DPCsQueuedTotal,
DPCTimeSeconds,
IdleBreakEventsTotal,
IdleTimeSeconds,
InterruptsTotal,
InterruptTimeSeconds,
ParkingStatus,
PerformanceLimitPercent,
PriorityTimeSeconds,
PrivilegedTimeSeconds,
PrivilegedUtilitySeconds,
ProcessorFrequencyMHz,
ProcessorPerformance,
ProcessorTimeSeconds,
ProcessorUtilityRate,
UserTimeSeconds,
}
var err error
c.perfDataCollector, err = perfdata.NewCollector("Processor Information", []string{"*"}, counters)
if err != nil {
return fmt.Errorf("failed to create Processor Information collector: %w", err)
}
}
c.logicalProcessors = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "logical_processor"),
"Total number of logical processors",
nil,
nil,
)
c.cStateSecondsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "cstate_seconds_total"),
"Time spent in low-power idle state",
[]string{"core", "state"},
nil,
)
c.TimeTotal = prometheus.NewDesc(
c.timeTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "time_total"),
"Time that processor spent in different modes (dpc, idle, interrupt, privileged, user)",
[]string{"core", "mode"},
nil,
)
c.InterruptsTotal = prometheus.NewDesc(
c.interruptsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "interrupts_total"),
"Total number of received and serviced hardware interrupts",
[]string{"core"},
nil,
)
c.DPCsTotal = prometheus.NewDesc(
c.dpcsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "dpcs_total"),
"Total number of received and serviced deferred procedure calls (DPCs)",
[]string{"core"},
nil,
)
// 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 winversion.WindowsVersionFloat < 6.05 {
return nil
}
c.CStateSecondsTotal = prometheus.NewDesc(
c.cStateSecondsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "cstate_seconds_total"),
"Time spent in low-power idle state",
[]string{"core", "state"},
nil,
)
c.TimeTotal = prometheus.NewDesc(
c.timeTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "time_total"),
"Time that processor spent in different modes (dpc, idle, interrupt, privileged, user)",
[]string{"core", "mode"},
nil,
)
c.InterruptsTotal = prometheus.NewDesc(
c.interruptsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "interrupts_total"),
"Total number of received and serviced hardware interrupts",
[]string{"core"},
nil,
)
c.DPCsTotal = prometheus.NewDesc(
c.dpcsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "dpcs_total"),
"Total number of received and serviced deferred procedure calls (DPCs)",
[]string{"core"},
nil,
)
c.ClockInterruptsTotal = prometheus.NewDesc(
c.clockInterruptsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "clock_interrupts_total"),
"Total number of received and serviced clock tick interrupts",
[]string{"core"},
nil,
)
c.IdleBreakEventsTotal = prometheus.NewDesc(
c.idleBreakEventsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "idle_break_events_total"),
"Total number of time processor was woken from idle",
[]string{"core"},
nil,
)
c.ParkingStatus = prometheus.NewDesc(
c.parkingStatus = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "parking_status"),
"Parking Status represents whether a processor is parked or not",
[]string{"core"},
nil,
)
c.ProcessorFrequencyMHz = prometheus.NewDesc(
c.processorFrequencyMHz = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "core_frequency_mhz"),
"Core frequency in megahertz",
[]string{"core"},
nil,
)
c.ProcessorPerformance = prometheus.NewDesc(
c.processorPerformance = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "processor_performance_total"),
"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,
)
c.ProcessorMPerf = prometheus.NewDesc(
c.processorMPerf = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "processor_mperf_total"),
"Processor MPerf is the number of TSC ticks incremented while executing instructions",
[]string{"core"},
nil,
)
c.ProcessorRTC = prometheus.NewDesc(
c.processorRTC = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "processor_rtc_total"),
"Processor RTC represents the number of RTC ticks made since the system booted. It should consistently be 64e6, and can be used to properly derive Processor Utility Rate",
[]string{"core"},
nil,
)
c.ProcessorUtility = prometheus.NewDesc(
c.processorUtility = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "processor_utility_total"),
"Processor Utility represents is the amount of time the core spends executing instructions",
[]string{"core"},
nil,
)
c.ProcessorPrivUtility = prometheus.NewDesc(
c.processorPrivilegedUtility = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "processor_privileged_utility_total"),
"Processor Privileged Utility represents is the amount of time the core has spent executing instructions inside the kernel",
[]string{"core"},
@@ -182,111 +225,14 @@ func (c *collector) Build() error {
return nil
}
func (c *collector) Collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
if winversion.WindowsVersionFloat > 6.05 {
return c.CollectFull(ctx, ch)
func (c *Collector) Collect(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
if utils.PDHEnabled() {
return c.collectPDH(ch)
}
return c.CollectBasic(ctx, ch)
}
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"`
PercentC1Time float64 `perflib:"% C1 Time"`
PercentC2Time float64 `perflib:"% C2 Time"`
PercentC3Time 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 *collector) CollectBasic(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
data := make([]perflibProcessor, 0)
err := perflib.UnmarshalObject(ctx.PerfObjects["Processor"], &data, c.logger)
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
return c.collectFull(ctx, logger, ch)
}
type perflibProcessorInformation struct {
@@ -318,138 +264,290 @@ type perflibProcessorInformation struct {
UserTimeSeconds float64 `perflib:"% User Time"`
}
func (c *collector) CollectFull(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collectFull(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
data := make([]perflibProcessorInformation, 0)
err := perflib.UnmarshalObject(ctx.PerfObjects["Processor Information"], &data, c.logger)
err := perflib.UnmarshalObject(ctx.PerfObjects["Processor Information"], &data, logger)
if err != nil {
return err
}
var coreCount float64
for _, cpu := range data {
if strings.Contains(strings.ToLower(cpu.Name), "_total") {
continue
}
core := cpu.Name
coreCount++
ch <- prometheus.MustNewConstMetric(
c.CStateSecondsTotal,
c.cStateSecondsTotal,
prometheus.CounterValue,
cpu.C1TimeSeconds,
core, "c1",
)
ch <- prometheus.MustNewConstMetric(
c.CStateSecondsTotal,
c.cStateSecondsTotal,
prometheus.CounterValue,
cpu.C2TimeSeconds,
core, "c2",
)
ch <- prometheus.MustNewConstMetric(
c.CStateSecondsTotal,
c.cStateSecondsTotal,
prometheus.CounterValue,
cpu.C3TimeSeconds,
core, "c3",
)
ch <- prometheus.MustNewConstMetric(
c.TimeTotal,
c.timeTotal,
prometheus.CounterValue,
cpu.IdleTimeSeconds,
core, "idle",
)
ch <- prometheus.MustNewConstMetric(
c.TimeTotal,
c.timeTotal,
prometheus.CounterValue,
cpu.InterruptTimeSeconds,
core, "interrupt",
)
ch <- prometheus.MustNewConstMetric(
c.TimeTotal,
c.timeTotal,
prometheus.CounterValue,
cpu.DPCTimeSeconds,
core, "dpc",
)
ch <- prometheus.MustNewConstMetric(
c.TimeTotal,
c.timeTotal,
prometheus.CounterValue,
cpu.PrivilegedTimeSeconds,
core, "privileged",
)
ch <- prometheus.MustNewConstMetric(
c.TimeTotal,
c.timeTotal,
prometheus.CounterValue,
cpu.UserTimeSeconds,
core, "user",
)
ch <- prometheus.MustNewConstMetric(
c.InterruptsTotal,
c.interruptsTotal,
prometheus.CounterValue,
cpu.InterruptsTotal,
core,
)
ch <- prometheus.MustNewConstMetric(
c.DPCsTotal,
c.dpcsTotal,
prometheus.CounterValue,
cpu.DPCsQueuedTotal,
core,
)
ch <- prometheus.MustNewConstMetric(
c.ClockInterruptsTotal,
c.clockInterruptsTotal,
prometheus.CounterValue,
cpu.ClockInterruptsTotal,
core,
)
ch <- prometheus.MustNewConstMetric(
c.IdleBreakEventsTotal,
c.idleBreakEventsTotal,
prometheus.CounterValue,
cpu.IdleBreakEventsTotal,
core,
)
ch <- prometheus.MustNewConstMetric(
c.ParkingStatus,
c.parkingStatus,
prometheus.GaugeValue,
cpu.ParkingStatus,
core,
)
ch <- prometheus.MustNewConstMetric(
c.ProcessorFrequencyMHz,
c.processorFrequencyMHz,
prometheus.GaugeValue,
cpu.ProcessorFrequencyMHz,
core,
)
ch <- prometheus.MustNewConstMetric(
c.ProcessorPerformance,
c.processorPerformance,
prometheus.CounterValue,
cpu.ProcessorPerformance,
core,
)
ch <- prometheus.MustNewConstMetric(
c.ProcessorMPerf,
c.processorMPerf,
prometheus.CounterValue,
cpu.ProcessorMPerf,
core,
)
ch <- prometheus.MustNewConstMetric(
c.ProcessorRTC,
c.processorRTC,
prometheus.CounterValue,
cpu.ProcessorRTC,
core,
)
ch <- prometheus.MustNewConstMetric(
c.ProcessorUtility,
c.processorUtility,
prometheus.CounterValue,
cpu.ProcessorUtilityRate,
core,
)
ch <- prometheus.MustNewConstMetric(
c.ProcessorPrivUtility,
c.processorPrivilegedUtility,
prometheus.CounterValue,
cpu.PrivilegedUtilitySeconds,
core,
)
}
ch <- prometheus.MustNewConstMetric(
c.logicalProcessors,
prometheus.GaugeValue,
coreCount,
)
return nil
}
func (c *Collector) collectPDH(ch chan<- prometheus.Metric) error {
data, err := c.perfDataCollector.Collect()
if err != nil {
return fmt.Errorf("failed to collect Processor Information metrics: %w", err)
}
var coreCount float64
for core, coreData := range data {
coreCount++
ch <- prometheus.MustNewConstMetric(
c.cStateSecondsTotal,
prometheus.CounterValue,
coreData[C1TimeSeconds].FirstValue,
core, "c1",
)
ch <- prometheus.MustNewConstMetric(
c.cStateSecondsTotal,
prometheus.CounterValue,
coreData[C2TimeSeconds].FirstValue,
core, "c2",
)
ch <- prometheus.MustNewConstMetric(
c.cStateSecondsTotal,
prometheus.CounterValue,
coreData[C3TimeSeconds].FirstValue,
core, "c3",
)
ch <- prometheus.MustNewConstMetric(
c.timeTotal,
prometheus.CounterValue,
coreData[IdleTimeSeconds].FirstValue,
core, "idle",
)
ch <- prometheus.MustNewConstMetric(
c.timeTotal,
prometheus.CounterValue,
coreData[InterruptTimeSeconds].FirstValue,
core, "interrupt",
)
ch <- prometheus.MustNewConstMetric(
c.timeTotal,
prometheus.CounterValue,
coreData[DPCTimeSeconds].FirstValue,
core, "dpc",
)
ch <- prometheus.MustNewConstMetric(
c.timeTotal,
prometheus.CounterValue,
coreData[PrivilegedTimeSeconds].FirstValue,
core, "privileged",
)
ch <- prometheus.MustNewConstMetric(
c.timeTotal,
prometheus.CounterValue,
coreData[UserTimeSeconds].FirstValue,
core, "user",
)
ch <- prometheus.MustNewConstMetric(
c.interruptsTotal,
prometheus.CounterValue,
coreData[InterruptsTotal].FirstValue,
core,
)
ch <- prometheus.MustNewConstMetric(
c.dpcsTotal,
prometheus.CounterValue,
coreData[DPCsQueuedTotal].FirstValue,
core,
)
ch <- prometheus.MustNewConstMetric(
c.clockInterruptsTotal,
prometheus.CounterValue,
coreData[ClockInterruptsTotal].FirstValue,
core,
)
ch <- prometheus.MustNewConstMetric(
c.idleBreakEventsTotal,
prometheus.CounterValue,
coreData[IdleBreakEventsTotal].FirstValue,
core,
)
ch <- prometheus.MustNewConstMetric(
c.parkingStatus,
prometheus.GaugeValue,
coreData[ParkingStatus].FirstValue,
core,
)
ch <- prometheus.MustNewConstMetric(
c.processorFrequencyMHz,
prometheus.GaugeValue,
coreData[ProcessorFrequencyMHz].FirstValue,
core,
)
ch <- prometheus.MustNewConstMetric(
c.processorPerformance,
prometheus.CounterValue,
coreData[ProcessorPerformance].FirstValue,
core,
)
ch <- prometheus.MustNewConstMetric(
c.processorMPerf,
prometheus.CounterValue,
coreData[ProcessorPerformance].SecondValue,
core,
)
ch <- prometheus.MustNewConstMetric(
c.processorRTC,
prometheus.CounterValue,
coreData[ProcessorUtilityRate].SecondValue,
core,
)
ch <- prometheus.MustNewConstMetric(
c.processorUtility,
prometheus.CounterValue,
coreData[ProcessorUtilityRate].FirstValue,
core,
)
ch <- prometheus.MustNewConstMetric(
c.processorPrivilegedUtility,
prometheus.CounterValue,
coreData[PrivilegedUtilitySeconds].FirstValue,
core,
)
}
ch <- prometheus.MustNewConstMetric(
c.logicalProcessors,
prometheus.GaugeValue,
coreCount,
)
return nil
}

View File

@@ -4,103 +4,175 @@ package cpu_info
import (
"errors"
"log/slog"
"strconv"
"strings"
"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/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const (
Name = "cpu_info"
// If you are adding additional labels to the metric, make sure that they get added in here as well. See below for explanation.
win32ProcessorQuery = "SELECT Architecture, DeviceId, Description, Family, L2CacheSize, L3CacheSize, Name FROM Win32_Processor"
)
type Config struct{}
var ConfigDefaults = Config{}
// A collector is a Prometheus collector for a few WMI metrics in Win32_Processor
type collector struct {
logger log.Logger
// A Collector is a Prometheus Collector for a few WMI metrics in Win32_Processor.
type Collector struct {
config Config
CpuInfo *prometheus.Desc
wmiClient *wmi.Client
cpuInfo *prometheus.Desc
cpuCoreCount *prometheus.Desc
cpuEnabledCoreCount *prometheus.Desc
cpuLogicalProcessorsCount *prometheus.Desc
cpuThreadCount *prometheus.Desc
cpuL2CacheSize *prometheus.Desc
cpuL3CacheSize *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
func NewWithFlags(_ *kingpin.Application) *Collector {
return &Collector{}
}
func (c *collector) GetName() string {
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{}, nil
}
func (c *collector) Build() error {
c.CpuInfo = prometheus.NewDesc(
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, wmiClient *wmi.Client) error {
if wmiClient == nil || wmiClient.SWbemServicesClient == nil {
return errors.New("wmiClient or SWbemServicesClient is nil")
}
c.wmiClient = wmiClient
c.cpuInfo = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, "", Name),
"Labelled CPU information as provided provided by Win32_Processor",
"Labelled CPU information as provided by Win32_Processor",
[]string{
"architecture",
"device_id",
"description",
"family",
"l2_cache_size",
"l3_cache_size",
"name",
},
nil,
)
c.cpuThreadCount = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "thread"),
"Number of threads per CPU",
[]string{
"device_id",
},
nil,
)
c.cpuCoreCount = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "core"),
"Number of cores per CPU",
[]string{
"device_id",
},
nil,
)
c.cpuEnabledCoreCount = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "enabled_core"),
"Number of enabled cores per CPU",
[]string{
"device_id",
},
nil,
)
c.cpuLogicalProcessorsCount = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "logical_processor"),
"Number of logical processors per CPU",
[]string{
"device_id",
},
nil,
)
c.cpuL2CacheSize = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "l2_cache_size"),
"Size of L2 cache per CPU",
[]string{
"device_id",
},
nil,
)
c.cpuL3CacheSize = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "l3_cache_size"),
"Size of L3 cache per CPU",
[]string{
"device_id",
},
nil,
)
return nil
}
type win32_Processor struct {
Architecture uint32
DeviceID string
Description string
Family uint16
L2CacheSize uint32
L3CacheSize uint32
Name string
type win32Processor struct {
Architecture uint32
DeviceID string
Description string
Family uint16
L2CacheSize uint32
L3CacheSize uint32
Name string
ThreadCount uint32
NumberOfCores uint32
NumberOfEnabledCore uint32
NumberOfLogicalProcessors uint32
}
// 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 {
func (c *Collector) Collect(_ *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
if err := c.collect(ch); err != nil {
_ = level.Error(c.logger).Log("msg", "failed collecting cpu_info metrics", "err", err)
logger.Error("failed collecting cpu_info metrics",
slog.Any("err", err),
)
return err
}
return nil
}
func (c *collector) collect(ch chan<- prometheus.Metric) error {
var dst []win32_Processor
func (c *Collector) collect(ch chan<- prometheus.Metric) error {
var dst []win32Processor
// We use a static query here because the provided methods in wmi.go all issue a SELECT *;
// This results in the time-consuming LoadPercentage field being read which seems to measure each CPU
// serially over a 1 second interval, so the scrape time is at least 1s * num_sockets
if err := wmi.Query(win32ProcessorQuery, &dst); err != nil {
if err := c.wmiClient.Query("SELECT Architecture, DeviceId, Description, Family, L2CacheSize, L3CacheSize, Name, ThreadCount, NumberOfCores, NumberOfEnabledCore, NumberOfLogicalProcessors FROM Win32_Processor", &dst); err != nil {
return err
}
if len(dst) == 0 {
return errors.New("WMI query returned empty result set")
}
@@ -108,17 +180,51 @@ func (c *collector) collect(ch chan<- prometheus.Metric) error {
// Some CPUs end up exposing trailing spaces for certain strings, so clean them up
for _, processor := range dst {
ch <- prometheus.MustNewConstMetric(
c.CpuInfo,
c.cpuInfo,
prometheus.GaugeValue,
1.0,
strconv.Itoa(int(processor.Architecture)),
strings.TrimRight(processor.DeviceID, " "),
strings.TrimRight(processor.Description, " "),
strconv.Itoa(int(processor.Family)),
strconv.Itoa(int(processor.L2CacheSize)),
strconv.Itoa(int(processor.L3CacheSize)),
strings.TrimRight(processor.Name, " "),
)
ch <- prometheus.MustNewConstMetric(
c.cpuCoreCount,
prometheus.GaugeValue,
float64(processor.NumberOfCores),
strings.TrimRight(processor.DeviceID, " "),
)
ch <- prometheus.MustNewConstMetric(
c.cpuEnabledCoreCount,
prometheus.GaugeValue,
float64(processor.NumberOfEnabledCore),
strings.TrimRight(processor.DeviceID, " "),
)
ch <- prometheus.MustNewConstMetric(
c.cpuLogicalProcessorsCount,
prometheus.GaugeValue,
float64(processor.NumberOfLogicalProcessors),
strings.TrimRight(processor.DeviceID, " "),
)
ch <- prometheus.MustNewConstMetric(
c.cpuThreadCount,
prometheus.GaugeValue,
float64(processor.ThreadCount),
strings.TrimRight(processor.DeviceID, " "),
)
ch <- prometheus.MustNewConstMetric(
c.cpuL2CacheSize,
prometheus.GaugeValue,
float64(processor.L2CacheSize),
strings.TrimRight(processor.DeviceID, " "),
)
ch <- prometheus.MustNewConstMetric(
c.cpuL3CacheSize,
prometheus.GaugeValue,
float64(processor.L3CacheSize),
strings.TrimRight(processor.DeviceID, " "),
)
}
return nil

View File

@@ -0,0 +1,12 @@
package cpu_info_test
import (
"testing"
"github.com/prometheus-community/windows_exporter/pkg/collector/cpu_info"
"github.com/prometheus-community/windows_exporter/pkg/testutils"
)
func BenchmarkCollector(b *testing.B) {
testutils.FuncBenchmarkCollector(b, cpu_info.Name, cpu_info.NewWithFlags)
}

View File

@@ -3,12 +3,13 @@
package cs
import (
"log/slog"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/go-kit/log/level"
"github.com/prometheus-community/windows_exporter/pkg/headers/sysinfoapi"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const Name = "cs"
@@ -17,53 +18,70 @@ type Config struct{}
var ConfigDefaults = Config{}
// A collector is a Prometheus collector for WMI metrics
type collector struct {
logger log.Logger
// A Collector is a Prometheus Collector for WMI metrics.
type Collector struct {
config Config
PhysicalMemoryBytes *prometheus.Desc
LogicalProcessors *prometheus.Desc
Hostname *prometheus.Desc
// physicalMemoryBytes
// Deprecated: Use windows_cpu_logical_processor instead
physicalMemoryBytes *prometheus.Desc
// logicalProcessors
// Deprecated: Use windows_physical_memory_total_bytes instead
logicalProcessors *prometheus.Desc
// hostname
// Deprecated: Use windows_os_hostname instead
hostname *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
func NewWithFlags(_ *kingpin.Application) *Collector {
return &Collector{}
}
func (c *collector) GetName() string {
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{}, nil
}
func (c *collector) Build() error {
c.LogicalProcessors = prometheus.NewDesc(
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(logger *slog.Logger, _ *wmi.Client) error {
logger.Warn("The cs collector is deprecated and will be removed in a future release. " +
"Logical processors has been moved to cpu_info collector. " +
"Physical memory has been moved to memory collector. " +
"Hostname has been moved to os collector.")
c.logicalProcessors = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "logical_processors"),
"ComputerSystem.NumberOfLogicalProcessors",
"Deprecated: Use windows_cpu_logical_processor instead",
nil,
nil,
)
c.PhysicalMemoryBytes = prometheus.NewDesc(
c.physicalMemoryBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "physical_memory_bytes"),
"ComputerSystem.TotalPhysicalMemory",
"Deprecated: Use windows_physical_memory_total_bytes instead",
nil,
nil,
)
c.Hostname = prometheus.NewDesc(
c.hostname = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "hostname"),
"Labelled system hostname information as provided by ComputerSystem.DNSHostName and ComputerSystem.Domain",
"Deprecated: Use windows_os_hostname instead",
[]string{
"hostname",
"domain",
@@ -71,20 +89,27 @@ func (c *collector) Build() error {
},
nil,
)
return 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 {
func (c *Collector) Collect(_ *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
if err := c.collect(ch); err != nil {
_ = level.Error(c.logger).Log("msg", "failed collecting cs metrics", "err", err)
logger.Error("failed collecting cs metrics",
slog.Any("err", err),
)
return err
}
return nil
}
func (c *collector) collect(ch chan<- prometheus.Metric) error {
func (c *Collector) collect(ch chan<- prometheus.Metric) error {
// Get systeminfo for number of processors
systemInfo := sysinfoapi.GetSystemInfo()
@@ -95,13 +120,13 @@ func (c *collector) collect(ch chan<- prometheus.Metric) error {
}
ch <- prometheus.MustNewConstMetric(
c.LogicalProcessors,
c.logicalProcessors,
prometheus.GaugeValue,
float64(systemInfo.NumberOfProcessors),
)
ch <- prometheus.MustNewConstMetric(
c.PhysicalMemoryBytes,
c.physicalMemoryBytes,
prometheus.GaugeValue,
float64(mem.TotalPhys),
)
@@ -110,17 +135,19 @@ func (c *collector) collect(ch chan<- prometheus.Metric) error {
if err != nil {
return err
}
domain, err := sysinfoapi.GetComputerName(sysinfoapi.ComputerNameDNSDomain)
if err != nil {
return err
}
fqdn, err := sysinfoapi.GetComputerName(sysinfoapi.ComputerNameDNSFullyQualified)
if err != nil {
return err
}
ch <- prometheus.MustNewConstMetric(
c.Hostname,
c.hostname,
prometheus.GaugeValue,
1.0,
hostname,

File diff suppressed because it is too large Load Diff

View File

@@ -3,11 +3,13 @@
package dhcp
import (
"log/slog"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/prometheus-community/windows_exporter/pkg/perflib"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const Name = "dhcp"
@@ -16,210 +18,217 @@ type Config struct{}
var ConfigDefaults = Config{}
// A collector is a Prometheus collector perflib DHCP metrics
type collector struct {
logger log.Logger
// A Collector is a Prometheus Collector perflib DHCP metrics.
type Collector struct {
config Config
PacketsReceivedTotal *prometheus.Desc
DuplicatesDroppedTotal *prometheus.Desc
PacketsExpiredTotal *prometheus.Desc
ActiveQueueLength *prometheus.Desc
ConflictCheckQueueLength *prometheus.Desc
DiscoversTotal *prometheus.Desc
OffersTotal *prometheus.Desc
RequestsTotal *prometheus.Desc
InformsTotal *prometheus.Desc
AcksTotal *prometheus.Desc
NacksTotal *prometheus.Desc
DeclinesTotal *prometheus.Desc
ReleasesTotal *prometheus.Desc
OfferQueueLength *prometheus.Desc
DeniedDueToMatch *prometheus.Desc
DeniedDueToNonMatch *prometheus.Desc
FailoverBndupdSentTotal *prometheus.Desc
FailoverBndupdReceivedTotal *prometheus.Desc
FailoverBndackSentTotal *prometheus.Desc
FailoverBndackReceivedTotal *prometheus.Desc
FailoverBndupdPendingOutboundQueue *prometheus.Desc
FailoverTransitionsCommunicationinterruptedState *prometheus.Desc
FailoverTransitionsPartnerdownState *prometheus.Desc
FailoverTransitionsRecoverState *prometheus.Desc
FailoverBndupdDropped *prometheus.Desc
acksTotal *prometheus.Desc
activeQueueLength *prometheus.Desc
conflictCheckQueueLength *prometheus.Desc
declinesTotal *prometheus.Desc
deniedDueToMatch *prometheus.Desc
deniedDueToNonMatch *prometheus.Desc
discoversTotal *prometheus.Desc
duplicatesDroppedTotal *prometheus.Desc
failoverBndackReceivedTotal *prometheus.Desc
failoverBndackSentTotal *prometheus.Desc
failoverBndupdDropped *prometheus.Desc
failoverBndupdPendingOutboundQueue *prometheus.Desc
failoverBndupdReceivedTotal *prometheus.Desc
failoverBndupdSentTotal *prometheus.Desc
failoverTransitionsCommunicationInterruptedState *prometheus.Desc
failoverTransitionsPartnerDownState *prometheus.Desc
failoverTransitionsRecoverState *prometheus.Desc
informsTotal *prometheus.Desc
nACKsTotal *prometheus.Desc
offerQueueLength *prometheus.Desc
offersTotal *prometheus.Desc
packetsExpiredTotal *prometheus.Desc
packetsReceivedTotal *prometheus.Desc
releasesTotal *prometheus.Desc
requestsTotal *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
func NewWithFlags(_ *kingpin.Application) *Collector {
return &Collector{}
}
func (c *collector) GetName() string {
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{"DHCP Server"}, nil
}
func (c *collector) Build() error {
c.PacketsReceivedTotal = prometheus.NewDesc(
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, _ *wmi.Client) error {
c.packetsReceivedTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "packets_received_total"),
"Total number of packets received by the DHCP server (PacketsReceivedTotal)",
nil,
nil,
)
c.DuplicatesDroppedTotal = prometheus.NewDesc(
c.duplicatesDroppedTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "duplicates_dropped_total"),
"Total number of duplicate packets received by the DHCP server (DuplicatesDroppedTotal)",
nil,
nil,
)
c.PacketsExpiredTotal = prometheus.NewDesc(
c.packetsExpiredTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "packets_expired_total"),
"Total number of packets expired in the DHCP server message queue (PacketsExpiredTotal)",
nil,
nil,
)
c.ActiveQueueLength = prometheus.NewDesc(
c.activeQueueLength = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "active_queue_length"),
"Number of packets in the processing queue of the DHCP server (ActiveQueueLength)",
nil,
nil,
)
c.ConflictCheckQueueLength = prometheus.NewDesc(
c.conflictCheckQueueLength = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "conflict_check_queue_length"),
"Number of packets in the DHCP server queue waiting on conflict detection (ping). (ConflictCheckQueueLength)",
nil,
nil,
)
c.DiscoversTotal = prometheus.NewDesc(
c.discoversTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "discovers_total"),
"Total DHCP Discovers received by the DHCP server (DiscoversTotal)",
nil,
nil,
)
c.OffersTotal = prometheus.NewDesc(
c.offersTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "offers_total"),
"Total DHCP Offers sent by the DHCP server (OffersTotal)",
nil,
nil,
)
c.RequestsTotal = prometheus.NewDesc(
c.requestsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "requests_total"),
"Total DHCP Requests received by the DHCP server (RequestsTotal)",
nil,
nil,
)
c.InformsTotal = prometheus.NewDesc(
c.informsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "informs_total"),
"Total DHCP Informs received by the DHCP server (InformsTotal)",
nil,
nil,
)
c.AcksTotal = prometheus.NewDesc(
c.acksTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "acks_total"),
"Total DHCP Acks sent by the DHCP server (AcksTotal)",
nil,
nil,
)
c.NacksTotal = prometheus.NewDesc(
c.nACKsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "nacks_total"),
"Total DHCP Nacks sent by the DHCP server (NacksTotal)",
nil,
nil,
)
c.DeclinesTotal = prometheus.NewDesc(
c.declinesTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "declines_total"),
"Total DHCP Declines received by the DHCP server (DeclinesTotal)",
nil,
nil,
)
c.ReleasesTotal = prometheus.NewDesc(
c.releasesTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "releases_total"),
"Total DHCP Releases received by the DHCP server (ReleasesTotal)",
nil,
nil,
)
c.OfferQueueLength = prometheus.NewDesc(
c.offerQueueLength = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "offer_queue_length"),
"Number of packets in the offer queue of the DHCP server (OfferQueueLength)",
nil,
nil,
)
c.DeniedDueToMatch = prometheus.NewDesc(
c.deniedDueToMatch = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "denied_due_to_match_total"),
"Total number of DHCP requests denied, based on matches from the Deny list (DeniedDueToMatch)",
nil,
nil,
)
c.DeniedDueToNonMatch = prometheus.NewDesc(
c.deniedDueToNonMatch = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "denied_due_to_nonmatch_total"),
"Total number of DHCP requests denied, based on non-matches from the Allow list (DeniedDueToNonMatch)",
nil,
nil,
)
c.FailoverBndupdSentTotal = prometheus.NewDesc(
c.failoverBndupdSentTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "failover_bndupd_sent_total"),
"Number of DHCP fail over Binding Update messages sent (FailoverBndupdSentTotal)",
nil,
nil,
)
c.FailoverBndupdReceivedTotal = prometheus.NewDesc(
c.failoverBndupdReceivedTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "failover_bndupd_received_total"),
"Number of DHCP fail over Binding Update messages received (FailoverBndupdReceivedTotal)",
nil,
nil,
)
c.FailoverBndackSentTotal = prometheus.NewDesc(
c.failoverBndackSentTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "failover_bndack_sent_total"),
"Number of DHCP fail over Binding Ack messages sent (FailoverBndackSentTotal)",
nil,
nil,
)
c.FailoverBndackReceivedTotal = prometheus.NewDesc(
c.failoverBndackReceivedTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "failover_bndack_received_total"),
"Number of DHCP fail over Binding Ack messages received (FailoverBndackReceivedTotal)",
nil,
nil,
)
c.FailoverBndupdPendingOutboundQueue = prometheus.NewDesc(
c.failoverBndupdPendingOutboundQueue = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "failover_bndupd_pending_in_outbound_queue"),
"Number of pending outbound DHCP fail over Binding Update messages (FailoverBndupdPendingOutboundQueue)",
nil,
nil,
)
c.FailoverTransitionsCommunicationinterruptedState = prometheus.NewDesc(
c.failoverTransitionsCommunicationInterruptedState = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "failover_transitions_communicationinterrupted_state_total"),
"Total number of transitions into COMMUNICATION INTERRUPTED state (FailoverTransitionsCommunicationinterruptedState)",
nil,
nil,
)
c.FailoverTransitionsPartnerdownState = prometheus.NewDesc(
c.failoverTransitionsPartnerDownState = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "failover_transitions_partnerdown_state_total"),
"Total number of transitions into PARTNER DOWN state (FailoverTransitionsPartnerdownState)",
nil,
nil,
)
c.FailoverTransitionsRecoverState = prometheus.NewDesc(
c.failoverTransitionsRecoverState = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "failover_transitions_recover_total"),
"Total number of transitions into RECOVER state (FailoverTransitionsRecoverState)",
nil,
nil,
)
c.FailoverBndupdDropped = prometheus.NewDesc(
c.failoverBndupdDropped = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "failover_bndupd_dropped_total"),
"Total number of DHCP fail over Binding Updates dropped (FailoverBndupdDropped)",
nil,
nil,
)
return nil
}
@@ -254,158 +263,161 @@ type dhcpPerf struct {
FailoverBndupdDropped float64 `perflib:"Failover: BndUpd Dropped."`
}
func (c *collector) Collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) Collect(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var dhcpPerfs []dhcpPerf
if err := perflib.UnmarshalObject(ctx.PerfObjects["DHCP Server"], &dhcpPerfs, c.logger); err != nil {
if err := perflib.UnmarshalObject(ctx.PerfObjects["DHCP Server"], &dhcpPerfs, logger); err != nil {
return err
}
ch <- prometheus.MustNewConstMetric(
c.PacketsReceivedTotal,
c.packetsReceivedTotal,
prometheus.CounterValue,
dhcpPerfs[0].PacketsReceivedTotal,
)
ch <- prometheus.MustNewConstMetric(
c.DuplicatesDroppedTotal,
c.duplicatesDroppedTotal,
prometheus.CounterValue,
dhcpPerfs[0].DuplicatesDroppedTotal,
)
ch <- prometheus.MustNewConstMetric(
c.PacketsExpiredTotal,
c.packetsExpiredTotal,
prometheus.CounterValue,
dhcpPerfs[0].PacketsExpiredTotal,
)
ch <- prometheus.MustNewConstMetric(
c.ActiveQueueLength,
c.activeQueueLength,
prometheus.GaugeValue,
dhcpPerfs[0].ActiveQueueLength,
)
ch <- prometheus.MustNewConstMetric(
c.ConflictCheckQueueLength,
c.conflictCheckQueueLength,
prometheus.GaugeValue,
dhcpPerfs[0].ConflictCheckQueueLength,
)
ch <- prometheus.MustNewConstMetric(
c.DiscoversTotal,
c.discoversTotal,
prometheus.CounterValue,
dhcpPerfs[0].DiscoversTotal,
)
ch <- prometheus.MustNewConstMetric(
c.OffersTotal,
c.offersTotal,
prometheus.CounterValue,
dhcpPerfs[0].OffersTotal,
)
ch <- prometheus.MustNewConstMetric(
c.RequestsTotal,
c.requestsTotal,
prometheus.CounterValue,
dhcpPerfs[0].RequestsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.InformsTotal,
c.informsTotal,
prometheus.CounterValue,
dhcpPerfs[0].InformsTotal,
)
ch <- prometheus.MustNewConstMetric(
c.AcksTotal,
c.acksTotal,
prometheus.CounterValue,
dhcpPerfs[0].AcksTotal,
)
ch <- prometheus.MustNewConstMetric(
c.NacksTotal,
c.nACKsTotal,
prometheus.CounterValue,
dhcpPerfs[0].NacksTotal,
)
ch <- prometheus.MustNewConstMetric(
c.DeclinesTotal,
c.declinesTotal,
prometheus.CounterValue,
dhcpPerfs[0].DeclinesTotal,
)
ch <- prometheus.MustNewConstMetric(
c.ReleasesTotal,
c.releasesTotal,
prometheus.CounterValue,
dhcpPerfs[0].ReleasesTotal,
)
ch <- prometheus.MustNewConstMetric(
c.OfferQueueLength,
c.offerQueueLength,
prometheus.GaugeValue,
dhcpPerfs[0].OfferQueueLength,
)
ch <- prometheus.MustNewConstMetric(
c.DeniedDueToMatch,
c.deniedDueToMatch,
prometheus.CounterValue,
dhcpPerfs[0].DeniedDueToMatch,
)
ch <- prometheus.MustNewConstMetric(
c.DeniedDueToNonMatch,
c.deniedDueToNonMatch,
prometheus.CounterValue,
dhcpPerfs[0].DeniedDueToNonMatch,
)
ch <- prometheus.MustNewConstMetric(
c.FailoverBndupdSentTotal,
c.failoverBndupdSentTotal,
prometheus.CounterValue,
dhcpPerfs[0].FailoverBndupdSentTotal,
)
ch <- prometheus.MustNewConstMetric(
c.FailoverBndupdReceivedTotal,
c.failoverBndupdReceivedTotal,
prometheus.CounterValue,
dhcpPerfs[0].FailoverBndupdReceivedTotal,
)
ch <- prometheus.MustNewConstMetric(
c.FailoverBndackSentTotal,
c.failoverBndackSentTotal,
prometheus.CounterValue,
dhcpPerfs[0].FailoverBndackSentTotal,
)
ch <- prometheus.MustNewConstMetric(
c.FailoverBndackReceivedTotal,
c.failoverBndackReceivedTotal,
prometheus.CounterValue,
dhcpPerfs[0].FailoverBndackReceivedTotal,
)
ch <- prometheus.MustNewConstMetric(
c.FailoverBndupdPendingOutboundQueue,
c.failoverBndupdPendingOutboundQueue,
prometheus.GaugeValue,
dhcpPerfs[0].FailoverBndupdPendingOutboundQueue,
)
ch <- prometheus.MustNewConstMetric(
c.FailoverTransitionsCommunicationinterruptedState,
c.failoverTransitionsCommunicationInterruptedState,
prometheus.CounterValue,
dhcpPerfs[0].FailoverTransitionsCommunicationinterruptedState,
)
ch <- prometheus.MustNewConstMetric(
c.FailoverTransitionsPartnerdownState,
c.failoverTransitionsPartnerDownState,
prometheus.CounterValue,
dhcpPerfs[0].FailoverTransitionsPartnerdownState,
)
ch <- prometheus.MustNewConstMetric(
c.FailoverTransitionsRecoverState,
c.failoverTransitionsRecoverState,
prometheus.CounterValue,
dhcpPerfs[0].FailoverTransitionsRecoverState,
)
ch <- prometheus.MustNewConstMetric(
c.FailoverBndupdDropped,
c.failoverBndupdDropped,
prometheus.CounterValue,
dhcpPerfs[0].FailoverBndupdDropped,
)

View File

@@ -4,14 +4,13 @@ package diskdrive
import (
"errors"
"log/slog"
"strings"
"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/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const (
@@ -23,41 +22,53 @@ type Config struct{}
var ConfigDefaults = Config{}
// A collector is a Prometheus collector for a few WMI metrics in Win32_DiskDrive
type collector struct {
logger log.Logger
// A Collector is a Prometheus Collector for a few WMI metrics in Win32_DiskDrive.
type Collector struct {
config Config
wmiClient *wmi.Client
DiskInfo *prometheus.Desc
Status *prometheus.Desc
Size *prometheus.Desc
Partitions *prometheus.Desc
Availability *prometheus.Desc
availability *prometheus.Desc
diskInfo *prometheus.Desc
partitions *prometheus.Desc
size *prometheus.Desc
status *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
func NewWithFlags(_ *kingpin.Application) *Collector {
return &Collector{}
}
func (c *collector) GetName() string {
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{}, nil
}
func (c *collector) Build() error {
c.DiskInfo = prometheus.NewDesc(
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, wmiClient *wmi.Client) error {
if wmiClient == nil || wmiClient.SWbemServicesClient == nil {
return errors.New("wmiClient or SWbemServicesClient is nil")
}
c.wmiClient = wmiClient
c.diskInfo = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "info"),
"General drive information",
[]string{
@@ -68,25 +79,25 @@ func (c *collector) Build() error {
},
nil,
)
c.Status = prometheus.NewDesc(
c.status = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "status"),
"Status of the drive",
[]string{"name", "status"},
nil,
)
c.Size = prometheus.NewDesc(
c.size = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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.",
[]string{"name"},
nil,
)
c.Partitions = prometheus.NewDesc(
c.partitions = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "partitions"),
"Number of partitions",
[]string{"name"},
nil,
)
c.Availability = prometheus.NewDesc(
c.availability = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "availability"),
"Availability Status",
[]string{"name", "availability"},
@@ -96,7 +107,7 @@ func (c *collector) Build() error {
return nil
}
type Win32_DiskDrive struct {
type win32_DiskDrive struct {
DeviceID string
Model string
Size uint64
@@ -149,33 +160,39 @@ var (
)
// 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 {
func (c *Collector) Collect(_ *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
if err := c.collect(ch); err != nil {
_ = level.Error(c.logger).Log("msg", "failed collecting disk_drive_info metrics", "err", err)
logger.Error("failed collecting disk_drive_info metrics",
slog.Any("err", err),
)
return err
}
return nil
}
func (c *collector) collect(ch chan<- prometheus.Metric) error {
var dst []Win32_DiskDrive
func (c *Collector) collect(ch chan<- prometheus.Metric) error {
var dst []win32_DiskDrive
if err := wmi.Query(win32DiskQuery, &dst); err != nil {
if err := c.wmiClient.Query(win32DiskQuery, &dst); err != nil {
return err
}
if len(dst) == 0 {
return errors.New("WMI query returned empty result set")
}
for _, disk := range dst {
ch <- prometheus.MustNewConstMetric(
c.DiskInfo,
c.diskInfo,
prometheus.GaugeValue,
1.0,
strings.Trim(disk.DeviceID, "\\.\\"),
strings.Trim(disk.DeviceID, "\\.\\"), //nolint:staticcheck
strings.TrimRight(disk.Model, " "),
strings.TrimRight(disk.Caption, " "),
strings.TrimRight(disk.Name, "\\.\\"),
strings.TrimRight(disk.Name, "\\.\\"), //nolint:staticcheck
)
for _, status := range allDiskStatus {
@@ -185,26 +202,26 @@ func (c *collector) collect(ch chan<- prometheus.Metric) error {
}
ch <- prometheus.MustNewConstMetric(
c.Status,
c.status,
prometheus.GaugeValue,
isCurrentState,
strings.Trim(disk.Name, "\\.\\"),
strings.Trim(disk.Name, "\\.\\"), //nolint:staticcheck
status,
)
}
ch <- prometheus.MustNewConstMetric(
c.Size,
c.size,
prometheus.GaugeValue,
float64(disk.Size),
strings.Trim(disk.Name, "\\.\\"),
strings.Trim(disk.Name, "\\.\\"), //nolint:staticcheck
)
ch <- prometheus.MustNewConstMetric(
c.Partitions,
c.partitions,
prometheus.GaugeValue,
float64(disk.Partitions),
strings.Trim(disk.Name, "\\.\\"),
strings.Trim(disk.Name, "\\.\\"), //nolint:staticcheck
)
for availNum, val := range availMap {
@@ -213,10 +230,10 @@ func (c *collector) collect(ch chan<- prometheus.Metric) error {
isCurrentState = 1.0
}
ch <- prometheus.MustNewConstMetric(
c.Availability,
c.availability,
prometheus.GaugeValue,
isCurrentState,
strings.Trim(disk.Name, "\\.\\"),
strings.Trim(disk.Name, "\\.\\"), //nolint:staticcheck
val,
)
}

View File

@@ -4,13 +4,12 @@ package dns
import (
"errors"
"log/slog"
"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/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const Name = "dns"
@@ -19,199 +18,218 @@ type Config struct{}
var ConfigDefaults = Config{}
// A collector is a Prometheus collector for WMI Win32_PerfRawData_DNS_DNS metrics
type collector struct {
logger log.Logger
// A Collector is a Prometheus Collector for WMI Win32_PerfRawData_DNS_DNS metrics.
type Collector struct {
config Config
wmiClient *wmi.Client
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
dynamicUpdatesFailures *prometheus.Desc
dynamicUpdatesQueued *prometheus.Desc
dynamicUpdatesReceived *prometheus.Desc
memoryUsedBytes *prometheus.Desc
notifyReceived *prometheus.Desc
notifySent *prometheus.Desc
queries *prometheus.Desc
recursiveQueries *prometheus.Desc
recursiveQueryFailures *prometheus.Desc
recursiveQuerySendTimeouts *prometheus.Desc
responses *prometheus.Desc
secureUpdateFailures *prometheus.Desc
secureUpdateReceived *prometheus.Desc
unmatchedResponsesReceived *prometheus.Desc
winsQueries *prometheus.Desc
winsResponses *prometheus.Desc
zoneTransferFailures *prometheus.Desc
zoneTransferRequestsReceived *prometheus.Desc
zoneTransferRequestsSent *prometheus.Desc
zoneTransferResponsesReceived *prometheus.Desc
zoneTransferSuccessReceived *prometheus.Desc
zoneTransferSuccessSent *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
func NewWithFlags(_ *kingpin.Application) *Collector {
return &Collector{}
}
func (c *collector) GetName() string {
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{}, nil
}
func (c *collector) Build() error {
c.ZoneTransferRequestsReceived = prometheus.NewDesc(
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, wmiClient *wmi.Client) error {
if wmiClient == nil || wmiClient.SWbemServicesClient == nil {
return errors.New("wmiClient or SWbemServicesClient is nil")
}
c.wmiClient = wmiClient
c.zoneTransferRequestsReceived = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "zone_transfer_requests_received_total"),
"Number of zone transfer requests (AXFR/IXFR) received by the master DNS server",
[]string{"qtype"},
nil,
)
c.ZoneTransferRequestsSent = prometheus.NewDesc(
c.zoneTransferRequestsSent = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "zone_transfer_requests_sent_total"),
"Number of zone transfer requests (AXFR/IXFR) sent by the secondary DNS server",
[]string{"qtype"},
nil,
)
c.ZoneTransferResponsesReceived = prometheus.NewDesc(
c.zoneTransferResponsesReceived = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "zone_transfer_response_received_total"),
"Number of zone transfer responses (AXFR/IXFR) received by the secondary DNS server",
[]string{"qtype"},
nil,
)
c.ZoneTransferSuccessReceived = prometheus.NewDesc(
c.zoneTransferSuccessReceived = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "zone_transfer_success_received_total"),
"Number of successful zone transfers (AXFR/IXFR) received by the secondary DNS server",
[]string{"qtype", "protocol"},
nil,
)
c.ZoneTransferSuccessSent = prometheus.NewDesc(
c.zoneTransferSuccessSent = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "zone_transfer_success_sent_total"),
"Number of successful zone transfers (AXFR/IXFR) of the master DNS server",
[]string{"qtype"},
nil,
)
c.ZoneTransferFailures = prometheus.NewDesc(
c.zoneTransferFailures = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "zone_transfer_failures_total"),
"Number of failed zone transfers of the master DNS server",
nil,
nil,
)
c.MemoryUsedBytes = prometheus.NewDesc(
c.memoryUsedBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "memory_used_bytes"),
"Current memory used by DNS server",
[]string{"area"},
nil,
)
c.DynamicUpdatesQueued = prometheus.NewDesc(
c.dynamicUpdatesQueued = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "dynamic_updates_queued"),
"Number of dynamic updates queued by the DNS server",
nil,
nil,
)
c.DynamicUpdatesReceived = prometheus.NewDesc(
c.dynamicUpdatesReceived = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "dynamic_updates_received_total"),
"Number of secure update requests received by the DNS server",
[]string{"operation"},
nil,
)
c.DynamicUpdatesFailures = prometheus.NewDesc(
c.dynamicUpdatesFailures = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "dynamic_updates_failures_total"),
"Number of dynamic updates which timed out or were rejected by the DNS server",
[]string{"reason"},
nil,
)
c.NotifyReceived = prometheus.NewDesc(
c.notifyReceived = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "notify_received_total"),
"Number of notifies received by the secondary DNS server",
nil,
nil,
)
c.NotifySent = prometheus.NewDesc(
c.notifySent = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "notify_sent_total"),
"Number of notifies sent by the master DNS server",
nil,
nil,
)
c.SecureUpdateFailures = prometheus.NewDesc(
c.secureUpdateFailures = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "secure_update_failures_total"),
"Number of secure updates that failed on the DNS server",
nil,
nil,
)
c.SecureUpdateReceived = prometheus.NewDesc(
c.secureUpdateReceived = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "secure_update_received_total"),
"Number of secure update requests received by the DNS server",
nil,
nil,
)
c.Queries = prometheus.NewDesc(
c.queries = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "queries_total"),
"Number of queries received by DNS server",
[]string{"protocol"},
nil,
)
c.Responses = prometheus.NewDesc(
c.responses = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "responses_total"),
"Number of responses sent by DNS server",
[]string{"protocol"},
nil,
)
c.RecursiveQueries = prometheus.NewDesc(
c.recursiveQueries = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "recursive_queries_total"),
"Number of recursive queries received by DNS server",
nil,
nil,
)
c.RecursiveQueryFailures = prometheus.NewDesc(
c.recursiveQueryFailures = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "recursive_query_failures_total"),
"Number of recursive query failures",
nil,
nil,
)
c.RecursiveQuerySendTimeouts = prometheus.NewDesc(
c.recursiveQuerySendTimeouts = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "recursive_query_send_timeouts_total"),
"Number of recursive query sending timeouts",
nil,
nil,
)
c.WinsQueries = prometheus.NewDesc(
c.winsQueries = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "wins_queries_total"),
"Number of WINS lookup requests received by the server",
[]string{"direction"},
nil,
)
c.WinsResponses = prometheus.NewDesc(
c.winsResponses = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "wins_responses_total"),
"Number of WINS lookup responses sent by the server",
[]string{"direction"},
nil,
)
c.UnmatchedResponsesReceived = prometheus.NewDesc(
c.unmatchedResponsesReceived = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "unmatched_responses_total"),
"Number of response packets received by the DNS server that do not match any outstanding remote query",
nil,
nil,
)
return 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 {
func (c *Collector) Collect(_ *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
if err := c.collect(ch); err != nil {
_ = level.Error(c.logger).Log("msg", "failed collecting dns metrics", "err", err)
logger.Error("failed collecting dns metrics",
slog.Any("err", err),
)
return err
}
return nil
}
@@ -261,77 +279,77 @@ type Win32_PerfRawData_DNS_DNS struct {
ZoneTransferSOARequestSent uint32
}
func (c *collector) collect(ch chan<- prometheus.Metric) error {
func (c *Collector) collect(ch chan<- prometheus.Metric) error {
var dst []Win32_PerfRawData_DNS_DNS
q := wmi.QueryAll(&dst, c.logger)
if err := wmi.Query(q, &dst); err != nil {
if err := c.wmiClient.Query("SELECT * FROM Win32_PerfRawData_DNS_DNS", &dst); err != nil {
return err
}
if len(dst) == 0 {
return errors.New("WMI query returned empty result set")
}
ch <- prometheus.MustNewConstMetric(
c.ZoneTransferRequestsReceived,
c.zoneTransferRequestsReceived,
prometheus.CounterValue,
float64(dst[0].AXFRRequestReceived),
"full",
)
ch <- prometheus.MustNewConstMetric(
c.ZoneTransferRequestsReceived,
c.zoneTransferRequestsReceived,
prometheus.CounterValue,
float64(dst[0].IXFRRequestReceived),
"incremental",
)
ch <- prometheus.MustNewConstMetric(
c.ZoneTransferRequestsSent,
c.zoneTransferRequestsSent,
prometheus.CounterValue,
float64(dst[0].AXFRRequestSent),
"full",
)
ch <- prometheus.MustNewConstMetric(
c.ZoneTransferRequestsSent,
c.zoneTransferRequestsSent,
prometheus.CounterValue,
float64(dst[0].IXFRRequestSent),
"incremental",
)
ch <- prometheus.MustNewConstMetric(
c.ZoneTransferRequestsSent,
c.zoneTransferRequestsSent,
prometheus.CounterValue,
float64(dst[0].ZoneTransferSOARequestSent),
"soa",
)
ch <- prometheus.MustNewConstMetric(
c.ZoneTransferResponsesReceived,
c.zoneTransferResponsesReceived,
prometheus.CounterValue,
float64(dst[0].AXFRResponseReceived),
"full",
)
ch <- prometheus.MustNewConstMetric(
c.ZoneTransferResponsesReceived,
c.zoneTransferResponsesReceived,
prometheus.CounterValue,
float64(dst[0].IXFRResponseReceived),
"incremental",
)
ch <- prometheus.MustNewConstMetric(
c.ZoneTransferSuccessReceived,
c.zoneTransferSuccessReceived,
prometheus.CounterValue,
float64(dst[0].AXFRSuccessReceived),
"full",
"tcp",
)
ch <- prometheus.MustNewConstMetric(
c.ZoneTransferSuccessReceived,
c.zoneTransferSuccessReceived,
prometheus.CounterValue,
float64(dst[0].IXFRTCPSuccessReceived),
"incremental",
"tcp",
)
ch <- prometheus.MustNewConstMetric(
c.ZoneTransferSuccessReceived,
c.zoneTransferSuccessReceived,
prometheus.CounterValue,
float64(dst[0].IXFRTCPSuccessReceived),
"incremental",
@@ -339,183 +357,183 @@ func (c *collector) collect(ch chan<- prometheus.Metric) error {
)
ch <- prometheus.MustNewConstMetric(
c.ZoneTransferSuccessSent,
c.zoneTransferSuccessSent,
prometheus.CounterValue,
float64(dst[0].AXFRSuccessSent),
"full",
)
ch <- prometheus.MustNewConstMetric(
c.ZoneTransferSuccessSent,
c.zoneTransferSuccessSent,
prometheus.CounterValue,
float64(dst[0].IXFRSuccessSent),
"incremental",
)
ch <- prometheus.MustNewConstMetric(
c.ZoneTransferFailures,
c.zoneTransferFailures,
prometheus.CounterValue,
float64(dst[0].ZoneTransferFailure),
)
ch <- prometheus.MustNewConstMetric(
c.MemoryUsedBytes,
c.memoryUsedBytes,
prometheus.GaugeValue,
float64(dst[0].CachingMemory),
"caching",
)
ch <- prometheus.MustNewConstMetric(
c.MemoryUsedBytes,
c.memoryUsedBytes,
prometheus.GaugeValue,
float64(dst[0].DatabaseNodeMemory),
"database_node",
)
ch <- prometheus.MustNewConstMetric(
c.MemoryUsedBytes,
c.memoryUsedBytes,
prometheus.GaugeValue,
float64(dst[0].NbstatMemory),
"nbstat",
)
ch <- prometheus.MustNewConstMetric(
c.MemoryUsedBytes,
c.memoryUsedBytes,
prometheus.GaugeValue,
float64(dst[0].RecordFlowMemory),
"record_flow",
)
ch <- prometheus.MustNewConstMetric(
c.MemoryUsedBytes,
c.memoryUsedBytes,
prometheus.GaugeValue,
float64(dst[0].TCPMessageMemory),
"tcp_message",
)
ch <- prometheus.MustNewConstMetric(
c.MemoryUsedBytes,
c.memoryUsedBytes,
prometheus.GaugeValue,
float64(dst[0].UDPMessageMemory),
"udp_message",
)
ch <- prometheus.MustNewConstMetric(
c.DynamicUpdatesReceived,
c.dynamicUpdatesReceived,
prometheus.CounterValue,
float64(dst[0].DynamicUpdateNoOperation),
"noop",
)
ch <- prometheus.MustNewConstMetric(
c.DynamicUpdatesReceived,
c.dynamicUpdatesReceived,
prometheus.CounterValue,
float64(dst[0].DynamicUpdateWrittentoDatabase),
"written",
)
ch <- prometheus.MustNewConstMetric(
c.DynamicUpdatesQueued,
c.dynamicUpdatesQueued,
prometheus.GaugeValue,
float64(dst[0].DynamicUpdateQueued),
)
ch <- prometheus.MustNewConstMetric(
c.DynamicUpdatesFailures,
c.dynamicUpdatesFailures,
prometheus.CounterValue,
float64(dst[0].DynamicUpdateRejected),
"rejected",
)
ch <- prometheus.MustNewConstMetric(
c.DynamicUpdatesFailures,
c.dynamicUpdatesFailures,
prometheus.CounterValue,
float64(dst[0].DynamicUpdateTimeOuts),
"timeout",
)
ch <- prometheus.MustNewConstMetric(
c.NotifyReceived,
c.notifyReceived,
prometheus.CounterValue,
float64(dst[0].NotifyReceived),
)
ch <- prometheus.MustNewConstMetric(
c.NotifySent,
c.notifySent,
prometheus.CounterValue,
float64(dst[0].NotifySent),
)
ch <- prometheus.MustNewConstMetric(
c.RecursiveQueries,
c.recursiveQueries,
prometheus.CounterValue,
float64(dst[0].RecursiveQueries),
)
ch <- prometheus.MustNewConstMetric(
c.RecursiveQueryFailures,
c.recursiveQueryFailures,
prometheus.CounterValue,
float64(dst[0].RecursiveQueryFailure),
)
ch <- prometheus.MustNewConstMetric(
c.RecursiveQuerySendTimeouts,
c.recursiveQuerySendTimeouts,
prometheus.CounterValue,
float64(dst[0].RecursiveSendTimeOuts),
)
ch <- prometheus.MustNewConstMetric(
c.Queries,
c.queries,
prometheus.CounterValue,
float64(dst[0].TCPQueryReceived),
"tcp",
)
ch <- prometheus.MustNewConstMetric(
c.Queries,
c.queries,
prometheus.CounterValue,
float64(dst[0].UDPQueryReceived),
"udp",
)
ch <- prometheus.MustNewConstMetric(
c.Responses,
c.responses,
prometheus.CounterValue,
float64(dst[0].TCPResponseSent),
"tcp",
)
ch <- prometheus.MustNewConstMetric(
c.Responses,
c.responses,
prometheus.CounterValue,
float64(dst[0].UDPResponseSent),
"udp",
)
ch <- prometheus.MustNewConstMetric(
c.UnmatchedResponsesReceived,
c.unmatchedResponsesReceived,
prometheus.CounterValue,
float64(dst[0].UnmatchedResponsesReceived),
)
ch <- prometheus.MustNewConstMetric(
c.WinsQueries,
c.winsQueries,
prometheus.CounterValue,
float64(dst[0].WINSLookupReceived),
"forward",
)
ch <- prometheus.MustNewConstMetric(
c.WinsQueries,
c.winsQueries,
prometheus.CounterValue,
float64(dst[0].WINSReverseLookupReceived),
"reverse",
)
ch <- prometheus.MustNewConstMetric(
c.WinsResponses,
c.winsResponses,
prometheus.CounterValue,
float64(dst[0].WINSResponseSent),
"forward",
)
ch <- prometheus.MustNewConstMetric(
c.WinsResponses,
c.winsResponses,
prometheus.CounterValue,
float64(dst[0].WINSReverseResponseSent),
"reverse",
)
ch <- prometheus.MustNewConstMetric(
c.SecureUpdateFailures,
c.secureUpdateFailures,
prometheus.CounterValue,
float64(dst[0].SecureUpdateFailure),
)
ch <- prometheus.MustNewConstMetric(
c.SecureUpdateReceived,
c.secureUpdateReceived,
prometheus.CounterValue,
float64(dst[0].SecureUpdateReceived),
)

View File

@@ -4,132 +4,161 @@ package exchange
import (
"fmt"
"log/slog"
"os"
"slices"
"strings"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/go-kit/log/level"
"github.com/prometheus-community/windows_exporter/pkg/perflib"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus-community/windows_exporter/pkg/utils"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const (
Name = "exchange"
FlagExchangeListAllCollectors = "collectors.exchange.list"
FlagExchangeCollectorsEnabled = "collectors.exchange.enabled"
)
const Name = "exchange"
type Config struct {
CollectorsEnabled string `yaml:"collectors_enabled"`
CollectorsEnabled []string `yaml:"collectors_enabled"`
}
var ConfigDefaults = Config{
CollectorsEnabled: "",
CollectorsEnabled: []string{
"ADAccessProcesses",
"TransportQueues",
"HttpProxy",
"ActiveSync",
"AvailabilityService",
"OutlookWebAccess",
"Autodiscover",
"WorkloadManagement",
"RpcClientAccess",
"MapiHttpEmsmdb",
},
}
type collector struct {
logger log.Logger
type Collector struct {
config Config
exchangeListAllCollectors *bool
exchangeCollectorsEnabled *string
LDAPReadTime *prometheus.Desc
LDAPSearchTime *prometheus.Desc
LDAPWriteTime *prometheus.Desc
LDAPTimeoutErrorsPerSec *prometheus.Desc
LongRunningLDAPOperationsPerMin *prometheus.Desc
ExternalActiveRemoteDeliveryQueueLength *prometheus.Desc
InternalActiveRemoteDeliveryQueueLength *prometheus.Desc
ActiveMailboxDeliveryQueueLength *prometheus.Desc
RetryMailboxDeliveryQueueLength *prometheus.Desc
UnreachableQueueLength *prometheus.Desc
ExternalLargestDeliveryQueueLength *prometheus.Desc
InternalLargestDeliveryQueueLength *prometheus.Desc
PoisonQueueLength *prometheus.Desc
MailboxServerLocatorAverageLatency *prometheus.Desc
AverageAuthenticationLatency *prometheus.Desc
AverageCASProcessingLatency *prometheus.Desc
MailboxServerProxyFailureRate *prometheus.Desc
OutstandingProxyRequests *prometheus.Desc
ProxyRequestsPerSec *prometheus.Desc
ActiveSyncRequestsPerSec *prometheus.Desc
PingCommandsPending *prometheus.Desc
SyncCommandsPerSec *prometheus.Desc
AvailabilityRequestsSec *prometheus.Desc
CurrentUniqueUsers *prometheus.Desc
OWARequestsPerSec *prometheus.Desc
AutodiscoverRequestsPerSec *prometheus.Desc
ActiveTasks *prometheus.Desc
CompletedTasks *prometheus.Desc
QueuedTasks *prometheus.Desc
YieldedTasks *prometheus.Desc
IsActive *prometheus.Desc
RPCAveragedLatency *prometheus.Desc
RPCRequests *prometheus.Desc
ActiveUserCount *prometheus.Desc
ConnectionCount *prometheus.Desc
RPCOperationsPerSec *prometheus.Desc
UserCount *prometheus.Desc
ActiveUserCountMapiHttpEmsmdb *prometheus.Desc
enabledCollectors []string
activeMailboxDeliveryQueueLength *prometheus.Desc
activeSyncRequestsPerSec *prometheus.Desc
activeTasks *prometheus.Desc
activeUserCount *prometheus.Desc
activeUserCountMapiHttpEmsMDB *prometheus.Desc
autoDiscoverRequestsPerSec *prometheus.Desc
availabilityRequestsSec *prometheus.Desc
averageAuthenticationLatency *prometheus.Desc
averageCASProcessingLatency *prometheus.Desc
completedTasks *prometheus.Desc
connectionCount *prometheus.Desc
currentUniqueUsers *prometheus.Desc
externalActiveRemoteDeliveryQueueLength *prometheus.Desc
externalLargestDeliveryQueueLength *prometheus.Desc
internalActiveRemoteDeliveryQueueLength *prometheus.Desc
internalLargestDeliveryQueueLength *prometheus.Desc
isActive *prometheus.Desc
ldapReadTime *prometheus.Desc
ldapSearchTime *prometheus.Desc
ldapTimeoutErrorsPerSec *prometheus.Desc
ldapWriteTime *prometheus.Desc
longRunningLDAPOperationsPerMin *prometheus.Desc
mailboxServerLocatorAverageLatency *prometheus.Desc
mailboxServerProxyFailureRate *prometheus.Desc
outstandingProxyRequests *prometheus.Desc
owaRequestsPerSec *prometheus.Desc
pingCommandsPending *prometheus.Desc
poisonQueueLength *prometheus.Desc
proxyRequestsPerSec *prometheus.Desc
queuedTasks *prometheus.Desc
retryMailboxDeliveryQueueLength *prometheus.Desc
rpcAveragedLatency *prometheus.Desc
rpcOperationsPerSec *prometheus.Desc
rpcRequests *prometheus.Desc
syncCommandsPerSec *prometheus.Desc
unreachableQueueLength *prometheus.Desc
userCount *prometheus.Desc
yieldedTasks *prometheus.Desc
}
// All available collector functions
var exchangeAllCollectorNames = []string{
"ADAccessProcesses",
"TransportQueues",
"HttpProxy",
"ActiveSync",
"AvailabilityService",
"OutlookWebAccess",
"Autodiscover",
"WorkloadManagement",
"RpcClientAccess",
"MapiHttpEmsmdb",
}
func New(logger log.Logger, config *Config) types.Collector {
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
exchangeListAllCollectors := false
c := &collector{
exchangeCollectorsEnabled: &config.CollectorsEnabled,
exchangeListAllCollectors: &exchangeListAllCollectors,
if config.CollectorsEnabled == nil {
config.CollectorsEnabled = ConfigDefaults.CollectorsEnabled
}
c.SetLogger(logger)
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(app *kingpin.Application) types.Collector {
return &collector{
exchangeListAllCollectors: app.Flag(
FlagExchangeListAllCollectors,
"List the collectors along with their perflib object name/ids",
).Bool(),
exchangeCollectorsEnabled: app.Flag(
FlagExchangeCollectorsEnabled,
"Comma-separated list of collectors to use. Defaults to all, if not specified.",
).Default(ConfigDefaults.CollectorsEnabled).String(),
func NewWithFlags(app *kingpin.Application) *Collector {
c := &Collector{
config: ConfigDefaults,
}
c.config.CollectorsEnabled = make([]string, 0)
var listAllCollectors bool
var collectorsEnabled string
app.Flag(
"collectors.exchange.list",
"List the collectors along with their perflib object name/ids",
).BoolVar(&listAllCollectors)
app.Flag(
"collectors.exchange.enabled",
"Comma-separated list of collectors to use. Defaults to all, if not specified.",
).Default(strings.Join(ConfigDefaults.CollectorsEnabled, ",")).StringVar(&collectorsEnabled)
app.PreAction(func(*kingpin.ParseContext) error {
if listAllCollectors {
collectorDesc := map[string]string{
"ADAccessProcesses": "[19108] MSExchange ADAccess Processes",
"TransportQueues": "[20524] MSExchangeTransport Queues",
"HttpProxy": "[36934] MSExchange HttpProxy",
"ActiveSync": "[25138] MSExchange ActiveSync",
"AvailabilityService": "[24914] MSExchange Availability Service",
"OutlookWebAccess": "[24618] MSExchange OWA",
"Autodiscover": "[29240] MSExchange Autodiscover",
"WorkloadManagement": "[19430] MSExchange WorkloadManagement Workloads",
"RpcClientAccess": "[29336] MSExchange RpcClientAccess",
"MapiHttpEmsmdb": "[26463] MSExchange MapiHttp Emsmdb",
}
sb := strings.Builder{}
sb.WriteString(fmt.Sprintf("%-32s %-32s\n", "Collector Name", "[PerfID] Perflib Object"))
for _, cname := range ConfigDefaults.CollectorsEnabled {
sb.WriteString(fmt.Sprintf("%-32s %-32s\n", cname, collectorDesc[cname]))
}
app.UsageTemplate(sb.String()).Usage(nil)
os.Exit(0)
}
return nil
})
app.Action(func(*kingpin.ParseContext) error {
c.config.CollectorsEnabled = strings.Split(collectorsEnabled, ",")
return nil
})
return c
}
func (c *collector) GetName() string {
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{
"MSExchange ADAccess Processes",
"MSExchangeTransport Queues",
@@ -144,7 +173,11 @@ func (c *collector) GetPerfCounter() ([]string, error) {
}, nil
}
func (c *collector) Build() error {
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, _ *wmi.Client) error {
// desc creates a new prometheus description
desc := func(metricName string, description string, labels ...string) *prometheus.Desc {
return prometheus.NewDesc(
@@ -155,88 +188,52 @@ func (c *collector) Build() error {
)
}
c.RPCAveragedLatency = desc("rpc_avg_latency_sec", "The latency (sec) averaged for the past 1024 packets")
c.RPCRequests = desc("rpc_requests", "Number of client requests currently being processed by the RPC Client Access service")
c.ActiveUserCount = desc("rpc_active_user_count", "Number of unique users that have shown some kind of activity in the last 2 minutes")
c.ConnectionCount = desc("rpc_connection_count", "Total number of client connections maintained")
c.RPCOperationsPerSec = desc("rpc_operations_total", "The rate at which RPC operations occur")
c.UserCount = desc("rpc_user_count", "Number of users")
c.LDAPReadTime = desc("ldap_read_time_sec", "Time (sec) to send an LDAP read request and receive a response", "name")
c.LDAPSearchTime = desc("ldap_search_time_sec", "Time (sec) to send an LDAP search request and receive a response", "name")
c.LDAPWriteTime = desc("ldap_write_time_sec", "Time (sec) to send an LDAP Add/Modify/Delete request and receive a response", "name")
c.LDAPTimeoutErrorsPerSec = desc("ldap_timeout_errors_total", "Total number of LDAP timeout errors", "name")
c.LongRunningLDAPOperationsPerMin = desc("ldap_long_running_ops_per_sec", "Long Running LDAP operations per second", "name")
c.ExternalActiveRemoteDeliveryQueueLength = desc("transport_queues_external_active_remote_delivery", "External Active Remote Delivery Queue length", "name")
c.InternalActiveRemoteDeliveryQueueLength = desc("transport_queues_internal_active_remote_delivery", "Internal Active Remote Delivery Queue length", "name")
c.ActiveMailboxDeliveryQueueLength = desc("transport_queues_active_mailbox_delivery", "Active Mailbox Delivery Queue length", "name")
c.RetryMailboxDeliveryQueueLength = desc("transport_queues_retry_mailbox_delivery", "Retry Mailbox Delivery Queue length", "name")
c.UnreachableQueueLength = desc("transport_queues_unreachable", "Unreachable Queue length", "name")
c.ExternalLargestDeliveryQueueLength = desc("transport_queues_external_largest_delivery", "External Largest Delivery Queue length", "name")
c.InternalLargestDeliveryQueueLength = desc("transport_queues_internal_largest_delivery", "Internal Largest Delivery Queue length", "name")
c.PoisonQueueLength = desc("transport_queues_poison", "Poison Queue length", "name")
c.MailboxServerLocatorAverageLatency = desc("http_proxy_mailbox_server_locator_avg_latency_sec", "Average latency (sec) of MailboxServerLocator web service calls", "name")
c.AverageAuthenticationLatency = desc("http_proxy_avg_auth_latency", "Average time spent authenticating CAS requests over the last 200 samples", "name")
c.OutstandingProxyRequests = desc("http_proxy_outstanding_proxy_requests", "Number of concurrent outstanding proxy requests", "name")
c.ProxyRequestsPerSec = desc("http_proxy_requests_total", "Number of proxy requests processed each second", "name")
c.AvailabilityRequestsSec = desc("avail_service_requests_per_sec", "Number of requests serviced per second")
c.CurrentUniqueUsers = desc("owa_current_unique_users", "Number of unique users currently logged on to Outlook Web App")
c.OWARequestsPerSec = desc("owa_requests_total", "Number of requests handled by Outlook Web App per second")
c.AutodiscoverRequestsPerSec = desc("autodiscover_requests_total", "Number of autodiscover service requests processed each second")
c.ActiveTasks = desc("workload_active_tasks", "Number of active tasks currently running in the background for workload management", "name")
c.CompletedTasks = desc("workload_completed_tasks", "Number of workload management tasks that have been completed", "name")
c.QueuedTasks = desc("workload_queued_tasks", "Number of workload management tasks that are currently queued up waiting to be processed", "name")
c.YieldedTasks = desc("workload_yielded_tasks", "The total number of tasks that have been yielded by a workload", "name")
c.IsActive = desc("workload_is_active", "Active indicates whether the workload is in an active (1) or paused (0) state", "name")
c.ActiveSyncRequestsPerSec = desc("activesync_requests_total", "Num HTTP requests received from the client via ASP.NET per sec. Shows Current user load")
c.AverageCASProcessingLatency = desc("http_proxy_avg_cas_proccessing_latency_sec", "Average latency (sec) of CAS processing time over the last 200 reqs", "name")
c.MailboxServerProxyFailureRate = desc("http_proxy_mailbox_proxy_failure_rate", "% of failures between this CAS and MBX servers over the last 200 samples", "name")
c.PingCommandsPending = desc("activesync_ping_cmds_pending", "Number of ping commands currently pending in the queue")
c.SyncCommandsPerSec = desc("activesync_sync_cmds_total", "Number of sync commands processed per second. Clients use this command to synchronize items within a folder")
c.ActiveUserCountMapiHttpEmsmdb = desc("mapihttp_emsmdb_active_user_count", "Number of unique outlook users that have shown some kind of activity in the last 2 minutes")
c.enabledCollectors = make([]string, 0, len(exchangeAllCollectorNames))
collectorDesc := map[string]string{
"ADAccessProcesses": "[19108] MSExchange ADAccess Processes",
"TransportQueues": "[20524] MSExchangeTransport Queues",
"HttpProxy": "[36934] MSExchange HttpProxy",
"ActiveSync": "[25138] MSExchange ActiveSync",
"AvailabilityService": "[24914] MSExchange Availability Service",
"OutlookWebAccess": "[24618] MSExchange OWA",
"Autodiscover": "[29240] MSExchange Autodiscover",
"WorkloadManagement": "[19430] MSExchange WorkloadManagement Workloads",
"RpcClientAccess": "[29336] MSExchange RpcClientAccess",
"MapiHttpEmsmdb": "[26463] MSExchange MapiHttp Emsmdb",
}
if *c.exchangeListAllCollectors {
fmt.Printf("%-32s %-32s\n", "Collector Name", "[PerfID] Perflib Object")
for _, cname := range exchangeAllCollectorNames {
fmt.Printf("%-32s %-32s\n", cname, collectorDesc[cname])
}
os.Exit(0)
}
if utils.IsEmpty(c.exchangeCollectorsEnabled) {
for _, collectorName := range exchangeAllCollectorNames {
c.enabledCollectors = append(c.enabledCollectors, collectorName)
}
} else {
for _, collectorName := range strings.Split(*c.exchangeCollectorsEnabled, ",") {
if slices.Contains(exchangeAllCollectorNames, collectorName) {
c.enabledCollectors = append(c.enabledCollectors, collectorName)
} else {
return fmt.Errorf("unknown exchange collector: %s", collectorName)
}
}
}
c.rpcAveragedLatency = desc("rpc_avg_latency_sec", "The latency (sec) averaged for the past 1024 packets")
c.rpcRequests = desc("rpc_requests", "Number of client requests currently being processed by the RPC Client Access service")
c.activeUserCount = desc("rpc_active_user_count", "Number of unique users that have shown some kind of activity in the last 2 minutes")
c.connectionCount = desc("rpc_connection_count", "Total number of client connections maintained")
c.rpcOperationsPerSec = desc("rpc_operations_total", "The rate at which RPC operations occur")
c.userCount = desc("rpc_user_count", "Number of users")
c.ldapReadTime = desc("ldap_read_time_sec", "Time (sec) to send an LDAP read request and receive a response", "name")
c.ldapSearchTime = desc("ldap_search_time_sec", "Time (sec) to send an LDAP search request and receive a response", "name")
c.ldapWriteTime = desc("ldap_write_time_sec", "Time (sec) to send an LDAP Add/Modify/Delete request and receive a response", "name")
c.ldapTimeoutErrorsPerSec = desc("ldap_timeout_errors_total", "Total number of LDAP timeout errors", "name")
c.longRunningLDAPOperationsPerMin = desc("ldap_long_running_ops_per_sec", "Long Running LDAP operations per second", "name")
c.externalActiveRemoteDeliveryQueueLength = desc("transport_queues_external_active_remote_delivery", "External Active Remote Delivery Queue length", "name")
c.internalActiveRemoteDeliveryQueueLength = desc("transport_queues_internal_active_remote_delivery", "Internal Active Remote Delivery Queue length", "name")
c.activeMailboxDeliveryQueueLength = desc("transport_queues_active_mailbox_delivery", "Active Mailbox Delivery Queue length", "name")
c.retryMailboxDeliveryQueueLength = desc("transport_queues_retry_mailbox_delivery", "Retry Mailbox Delivery Queue length", "name")
c.unreachableQueueLength = desc("transport_queues_unreachable", "Unreachable Queue length", "name")
c.externalLargestDeliveryQueueLength = desc("transport_queues_external_largest_delivery", "External Largest Delivery Queue length", "name")
c.internalLargestDeliveryQueueLength = desc("transport_queues_internal_largest_delivery", "Internal Largest Delivery Queue length", "name")
c.poisonQueueLength = desc("transport_queues_poison", "Poison Queue length", "name")
c.mailboxServerLocatorAverageLatency = desc("http_proxy_mailbox_server_locator_avg_latency_sec", "Average latency (sec) of MailboxServerLocator web service calls", "name")
c.averageAuthenticationLatency = desc("http_proxy_avg_auth_latency", "Average time spent authenticating CAS requests over the last 200 samples", "name")
c.outstandingProxyRequests = desc("http_proxy_outstanding_proxy_requests", "Number of concurrent outstanding proxy requests", "name")
c.proxyRequestsPerSec = desc("http_proxy_requests_total", "Number of proxy requests processed each second", "name")
c.availabilityRequestsSec = desc("avail_service_requests_per_sec", "Number of requests serviced per second")
c.currentUniqueUsers = desc("owa_current_unique_users", "Number of unique users currently logged on to Outlook Web App")
c.owaRequestsPerSec = desc("owa_requests_total", "Number of requests handled by Outlook Web App per second")
c.autoDiscoverRequestsPerSec = desc("autodiscover_requests_total", "Number of autodiscover service requests processed each second")
c.activeTasks = desc("workload_active_tasks", "Number of active tasks currently running in the background for workload management", "name")
c.completedTasks = desc("workload_completed_tasks", "Number of workload management tasks that have been completed", "name")
c.queuedTasks = desc("workload_queued_tasks", "Number of workload management tasks that are currently queued up waiting to be processed", "name")
c.yieldedTasks = desc("workload_yielded_tasks", "The total number of tasks that have been yielded by a workload", "name")
c.isActive = desc("workload_is_active", "Active indicates whether the workload is in an active (1) or paused (0) state", "name")
c.activeSyncRequestsPerSec = desc("activesync_requests_total", "Num HTTP requests received from the client via ASP.NET per sec. Shows Current user load")
c.averageCASProcessingLatency = desc("http_proxy_avg_cas_processing_latency_sec", "Average latency (sec) of CAS processing time over the last 200 reqs", "name")
c.mailboxServerProxyFailureRate = desc("http_proxy_mailbox_proxy_failure_rate", "% of failures between this CAS and MBX servers over the last 200 samples", "name")
c.pingCommandsPending = desc("activesync_ping_cmds_pending", "Number of ping commands currently pending in the queue")
c.syncCommandsPerSec = desc("activesync_sync_cmds_total", "Number of sync commands processed per second. Clients use this command to synchronize items within a folder")
c.activeUserCountMapiHttpEmsMDB = desc("mapihttp_emsmdb_active_user_count", "Number of unique outlook users that have shown some kind of activity in the last 2 minutes")
return nil
}
// Collect collects exchange metrics and sends them to prometheus
func (c *collector) Collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
collectorFuncs := map[string]func(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error{
// Collect collects exchange metrics and sends them to prometheus.
func (c *Collector) Collect(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
collectorFuncs := map[string]func(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error{
"ADAccessProcesses": c.collectADAccessProcesses,
"TransportQueues": c.collectTransportQueues,
"HttpProxy": c.collectHTTPProxy,
@@ -249,16 +246,20 @@ func (c *collector) Collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metri
"MapiHttpEmsmdb": c.collectMapiHttpEmsmdb,
}
for _, collectorName := range c.enabledCollectors {
if err := collectorFuncs[collectorName](ctx, ch); err != nil {
_ = level.Error(c.logger).Log("msg", "Error in "+collectorName, "err", err)
for _, collectorName := range c.config.CollectorsEnabled {
if err := collectorFuncs[collectorName](ctx, logger, ch); err != nil {
logger.Error("Error in "+collectorName,
slog.Any("err", err),
)
return err
}
}
return nil
}
// Perflib: [19108] MSExchange ADAccess Processes
// Perflib: [19108] MSExchange ADAccess Processes.
type perflibADAccessProcesses struct {
Name string
@@ -269,13 +270,17 @@ type perflibADAccessProcesses struct {
LongRunningLDAPOperationsPerMin float64 `perflib:"Long Running LDAP Operations/min"`
}
func (c *collector) collectADAccessProcesses(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collectADAccessProcesses(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var data []perflibADAccessProcesses
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange ADAccess Processes"], &data, c.logger); err != nil {
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange ADAccess Processes"], &data, logger); err != nil {
return err
}
labelUseCount := make(map[string]int)
for _, proc := range data {
labelName := c.toLabelName(proc.Name)
if strings.HasSuffix(labelName, "_total") {
@@ -289,61 +294,66 @@ func (c *collector) collectADAccessProcesses(ctx *types.ScrapeContext, ch chan<-
labelName = fmt.Sprintf("%s_%d", labelName, labelUseCount[labelName])
}
ch <- prometheus.MustNewConstMetric(
c.LDAPReadTime,
c.ldapReadTime,
prometheus.CounterValue,
c.msToSec(proc.LDAPReadTime),
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.LDAPSearchTime,
c.ldapSearchTime,
prometheus.CounterValue,
c.msToSec(proc.LDAPSearchTime),
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.LDAPWriteTime,
c.ldapWriteTime,
prometheus.CounterValue,
c.msToSec(proc.LDAPWriteTime),
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.LDAPTimeoutErrorsPerSec,
c.ldapTimeoutErrorsPerSec,
prometheus.CounterValue,
proc.LDAPTimeoutErrorsPerSec,
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.LongRunningLDAPOperationsPerMin,
c.longRunningLDAPOperationsPerMin,
prometheus.CounterValue,
proc.LongRunningLDAPOperationsPerMin*60,
labelName,
)
}
return nil
}
// Perflib: [24914] MSExchange Availability Service
// Perflib: [24914] MSExchange Availability Service.
type perflibAvailabilityService struct {
RequestsSec float64 `perflib:"Availability Requests (sec)"`
}
func (c *collector) collectAvailabilityService(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collectAvailabilityService(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var data []perflibAvailabilityService
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange Availability Service"], &data, c.logger); err != nil {
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange Availability Service"], &data, logger); err != nil {
return err
}
for _, availservice := range data {
ch <- prometheus.MustNewConstMetric(
c.AvailabilityRequestsSec,
c.availabilityRequestsSec,
prometheus.CounterValue,
availservice.RequestsSec,
)
}
return nil
}
// Perflib: [36934] MSExchange HttpProxy
// Perflib: [36934] MSExchange HttpProxy.
type perflibHTTPProxy struct {
Name string
@@ -355,115 +365,127 @@ type perflibHTTPProxy struct {
ProxyRequestsPerSec float64 `perflib:"Proxy Requests/Sec"`
}
func (c *collector) collectHTTPProxy(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collectHTTPProxy(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var data []perflibHTTPProxy
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange HttpProxy"], &data, c.logger); err != nil {
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange HttpProxy"], &data, logger); err != nil {
return err
}
for _, instance := range data {
labelName := c.toLabelName(instance.Name)
ch <- prometheus.MustNewConstMetric(
c.MailboxServerLocatorAverageLatency,
c.mailboxServerLocatorAverageLatency,
prometheus.GaugeValue,
c.msToSec(instance.MailboxServerLocatorAverageLatency),
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.AverageAuthenticationLatency,
c.averageAuthenticationLatency,
prometheus.GaugeValue,
instance.AverageAuthenticationLatency,
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.AverageCASProcessingLatency,
c.averageCASProcessingLatency,
prometheus.GaugeValue,
c.msToSec(instance.AverageCASProcessingLatency),
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.MailboxServerProxyFailureRate,
c.mailboxServerProxyFailureRate,
prometheus.GaugeValue,
instance.MailboxServerProxyFailureRate,
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.OutstandingProxyRequests,
c.outstandingProxyRequests,
prometheus.GaugeValue,
instance.OutstandingProxyRequests,
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.ProxyRequestsPerSec,
c.proxyRequestsPerSec,
prometheus.CounterValue,
instance.ProxyRequestsPerSec,
labelName,
)
}
return nil
}
// Perflib: [24618] MSExchange OWA
// Perflib: [24618] MSExchange OWA.
type perflibOWA struct {
CurrentUniqueUsers float64 `perflib:"Current Unique Users"`
RequestsPerSec float64 `perflib:"Requests/sec"`
}
func (c *collector) collectOWA(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collectOWA(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var data []perflibOWA
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange OWA"], &data, c.logger); err != nil {
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange OWA"], &data, logger); err != nil {
return err
}
for _, owa := range data {
ch <- prometheus.MustNewConstMetric(
c.CurrentUniqueUsers,
c.currentUniqueUsers,
prometheus.GaugeValue,
owa.CurrentUniqueUsers,
)
ch <- prometheus.MustNewConstMetric(
c.OWARequestsPerSec,
c.owaRequestsPerSec,
prometheus.CounterValue,
owa.RequestsPerSec,
)
}
return nil
}
// Perflib: [25138] MSExchange ActiveSync
// Perflib: [25138] MSExchange ActiveSync.
type perflibActiveSync struct {
RequestsPerSec float64 `perflib:"Requests/sec"`
PingCommandsPending float64 `perflib:"Ping Commands Pending"`
SyncCommandsPerSec float64 `perflib:"Sync Commands/sec"`
}
func (c *collector) collectActiveSync(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collectActiveSync(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var data []perflibActiveSync
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange ActiveSync"], &data, c.logger); err != nil {
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange ActiveSync"], &data, logger); err != nil {
return err
}
for _, instance := range data {
ch <- prometheus.MustNewConstMetric(
c.ActiveSyncRequestsPerSec,
c.activeSyncRequestsPerSec,
prometheus.CounterValue,
instance.RequestsPerSec,
)
ch <- prometheus.MustNewConstMetric(
c.PingCommandsPending,
c.pingCommandsPending,
prometheus.GaugeValue,
instance.PingCommandsPending,
)
ch <- prometheus.MustNewConstMetric(
c.SyncCommandsPerSec,
c.syncCommandsPerSec,
prometheus.CounterValue,
instance.SyncCommandsPerSec,
)
}
return nil
}
// Perflib: [29366] MSExchange RpcClientAccess
// Perflib: [29366] MSExchange RpcClientAccess.
type perflibRPCClientAccess struct {
RPCAveragedLatency float64 `perflib:"RPC Averaged Latency"`
RPCRequests float64 `perflib:"RPC Requests"`
@@ -473,40 +495,43 @@ type perflibRPCClientAccess struct {
UserCount float64 `perflib:"User Count"`
}
func (c *collector) collectRPC(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collectRPC(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var data []perflibRPCClientAccess
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange RpcClientAccess"], &data, c.logger); err != nil {
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange RpcClientAccess"], &data, logger); err != nil {
return err
}
for _, rpc := range data {
ch <- prometheus.MustNewConstMetric(
c.RPCAveragedLatency,
c.rpcAveragedLatency,
prometheus.GaugeValue,
c.msToSec(rpc.RPCAveragedLatency),
)
ch <- prometheus.MustNewConstMetric(
c.RPCRequests,
c.rpcRequests,
prometheus.GaugeValue,
rpc.RPCRequests,
)
ch <- prometheus.MustNewConstMetric(
c.ActiveUserCount,
c.activeUserCount,
prometheus.GaugeValue,
rpc.ActiveUserCount,
)
ch <- prometheus.MustNewConstMetric(
c.ConnectionCount,
c.connectionCount,
prometheus.GaugeValue,
rpc.ConnectionCount,
)
ch <- prometheus.MustNewConstMetric(
c.RPCOperationsPerSec,
c.rpcOperationsPerSec,
prometheus.CounterValue,
rpc.RPCOperationsPerSec,
)
ch <- prometheus.MustNewConstMetric(
c.UserCount,
c.userCount,
prometheus.GaugeValue,
rpc.UserCount,
)
@@ -515,7 +540,7 @@ func (c *collector) collectRPC(ctx *types.ScrapeContext, ch chan<- prometheus.Me
return nil
}
// Perflib: [20524] MSExchangeTransport Queues
// Perflib: [20524] MSExchangeTransport Queues.
type perflibTransportQueues struct {
Name string
@@ -529,9 +554,12 @@ type perflibTransportQueues struct {
PoisonQueueLength float64 `perflib:"Poison Queue Length"`
}
func (c *collector) collectTransportQueues(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collectTransportQueues(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var data []perflibTransportQueues
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchangeTransport Queues"], &data, c.logger); err != nil {
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchangeTransport Queues"], &data, logger); err != nil {
return err
}
@@ -541,58 +569,59 @@ func (c *collector) collectTransportQueues(ctx *types.ScrapeContext, ch chan<- p
continue
}
ch <- prometheus.MustNewConstMetric(
c.ExternalActiveRemoteDeliveryQueueLength,
c.externalActiveRemoteDeliveryQueueLength,
prometheus.GaugeValue,
queue.ExternalActiveRemoteDeliveryQueueLength,
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.InternalActiveRemoteDeliveryQueueLength,
c.internalActiveRemoteDeliveryQueueLength,
prometheus.GaugeValue,
queue.InternalActiveRemoteDeliveryQueueLength,
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.ActiveMailboxDeliveryQueueLength,
c.activeMailboxDeliveryQueueLength,
prometheus.GaugeValue,
queue.ActiveMailboxDeliveryQueueLength,
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.RetryMailboxDeliveryQueueLength,
c.retryMailboxDeliveryQueueLength,
prometheus.GaugeValue,
queue.RetryMailboxDeliveryQueueLength,
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.UnreachableQueueLength,
c.unreachableQueueLength,
prometheus.GaugeValue,
queue.UnreachableQueueLength,
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.ExternalLargestDeliveryQueueLength,
c.externalLargestDeliveryQueueLength,
prometheus.GaugeValue,
queue.ExternalLargestDeliveryQueueLength,
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.InternalLargestDeliveryQueueLength,
c.internalLargestDeliveryQueueLength,
prometheus.GaugeValue,
queue.InternalLargestDeliveryQueueLength,
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.PoisonQueueLength,
c.poisonQueueLength,
prometheus.GaugeValue,
queue.PoisonQueueLength,
labelName,
)
}
return nil
}
// Perflib: [19430] MSExchange WorkloadManagement Workloads
// Perflib: [19430] MSExchange WorkloadManagement Workloads.
type perflibWorkloadManagementWorkloads struct {
Name string
@@ -603,9 +632,12 @@ type perflibWorkloadManagementWorkloads struct {
IsActive float64 `perflib:"Active"`
}
func (c *collector) collectWorkloadManagementWorkloads(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collectWorkloadManagementWorkloads(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var data []perflibWorkloadManagementWorkloads
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange WorkloadManagement Workloads"], &data, c.logger); err != nil {
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange WorkloadManagement Workloads"], &data, logger); err != nil {
return err
}
@@ -615,31 +647,31 @@ func (c *collector) collectWorkloadManagementWorkloads(ctx *types.ScrapeContext,
continue
}
ch <- prometheus.MustNewConstMetric(
c.ActiveTasks,
c.activeTasks,
prometheus.GaugeValue,
instance.ActiveTasks,
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.CompletedTasks,
c.completedTasks,
prometheus.CounterValue,
instance.CompletedTasks,
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.QueuedTasks,
c.queuedTasks,
prometheus.CounterValue,
instance.QueuedTasks,
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.YieldedTasks,
c.yieldedTasks,
prometheus.CounterValue,
instance.YieldedTasks,
labelName,
)
ch <- prometheus.MustNewConstMetric(
c.IsActive,
c.isActive,
prometheus.GaugeValue,
instance.IsActive,
labelName,
@@ -649,40 +681,48 @@ func (c *collector) collectWorkloadManagementWorkloads(ctx *types.ScrapeContext,
return nil
}
// [29240] MSExchangeAutodiscover
// [29240] MSExchangeAutodiscover.
type perflibAutodiscover struct {
RequestsPerSec float64 `perflib:"Requests/sec"`
}
func (c *collector) collectAutoDiscover(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collectAutoDiscover(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var data []perflibAutodiscover
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchangeAutodiscover"], &data, c.logger); err != nil {
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchangeAutodiscover"], &data, logger); err != nil {
return err
}
for _, autodisc := range data {
ch <- prometheus.MustNewConstMetric(
c.AutodiscoverRequestsPerSec,
c.autoDiscoverRequestsPerSec,
prometheus.CounterValue,
autodisc.RequestsPerSec,
)
}
return nil
}
// perflib [26463] MSExchange MapiHttp Emsmdb
// perflib [26463] MSExchange MapiHttp Emsmdb.
type perflibMapiHttpEmsmdb struct {
ActiveUserCount float64 `perflib:"Active User Count"`
}
func (c *collector) collectMapiHttpEmsmdb(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collectMapiHttpEmsmdb(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var data []perflibMapiHttpEmsmdb
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange MapiHttp Emsmdb"], &data, c.logger); err != nil {
if err := perflib.UnmarshalObject(ctx.PerfObjects["MSExchange MapiHttp Emsmdb"], &data, logger); err != nil {
return err
}
for _, mapihttp := range data {
ch <- prometheus.MustNewConstMetric(
c.ActiveUserCountMapiHttpEmsmdb,
c.activeUserCountMapiHttpEmsMDB,
prometheus.GaugeValue,
mapihttp.ActiveUserCount,
)
@@ -691,14 +731,15 @@ func (c *collector) collectMapiHttpEmsmdb(ctx *types.ScrapeContext, ch chan<- pr
return nil
}
// toLabelName converts strings to lowercase and replaces all whitespaces and dots with underscores
func (c *collector) toLabelName(name string) string {
// toLabelName converts strings to lowercase and replaces all whitespaces and dots with underscores.
func (c *Collector) toLabelName(name string) string {
s := strings.ReplaceAll(strings.Join(strings.Fields(strings.ToLower(name)), "_"), ".", "_")
s = strings.ReplaceAll(s, "__", "_")
return s
}
// msToSec converts from ms to seconds
func (c *collector) msToSec(t float64) float64 {
// msToSec converts from ms to seconds.
func (c *Collector) msToSec(t float64) float64 {
return t / 1000
}

View File

@@ -0,0 +1,175 @@
//go:build windows
package filetime
import (
"fmt"
"log/slog"
"os"
"path/filepath"
"strings"
"sync"
"github.com/alecthomas/kingpin/v2"
"github.com/bmatcuk/doublestar/v4"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const Name = "filetime"
type Config struct {
filePatterns []string
}
var ConfigDefaults = Config{
filePatterns: []string{},
}
// A Collector is a Prometheus Collector for collecting file times.
type Collector struct {
config Config
fileMTime *prometheus.Desc
}
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
if config.filePatterns == nil {
config.filePatterns = ConfigDefaults.filePatterns
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(app *kingpin.Application) *Collector {
c := &Collector{
config: ConfigDefaults,
}
c.config.filePatterns = make([]string, 0)
var filePatterns string
app.Flag(
"collectors.filetime.file-patterns",
"Comma-separated list of file patterns. Each pattern is a glob pattern that can contain `*`, `?`, and `**` (recursive). See https://github.com/bmatcuk/doublestar#patterns",
).Default(strings.Join(ConfigDefaults.filePatterns, ",")).StringVar(&filePatterns)
app.Action(func(*kingpin.ParseContext) error {
// doublestar.Glob() requires forward slashes
c.config.filePatterns = strings.Split(filepath.ToSlash(filePatterns), ",")
return nil
})
return c
}
func (c *Collector) GetName() string {
return Name
}
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{}, nil
}
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(logger *slog.Logger, _ *wmi.Client) error {
logger.Info("filetime collector is in an experimental state! It may subject to change.",
slog.String("collector", Name),
)
c.fileMTime = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "mtime_timestamp_seconds"),
"File modification time",
[]string{"file"},
nil,
)
for _, filePattern := range c.config.filePatterns {
basePath, pattern := doublestar.SplitPattern(filePattern)
_, err := doublestar.Glob(os.DirFS(basePath), pattern, doublestar.WithFilesOnly())
if err != nil {
return fmt.Errorf("invalid glob pattern: %w", err)
}
}
return nil
}
// Collect sends the metric values for each metric
// to the provided prometheus Metric channel.
func (c *Collector) Collect(_ *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
return c.collectGlob(logger, ch)
}
// collectWin32 collects file times for each file path in the config. It using Win32 FindFirstFile and FindNextFile.
func (c *Collector) collectGlob(logger *slog.Logger, ch chan<- prometheus.Metric) error {
wg := sync.WaitGroup{}
for _, filePattern := range c.config.filePatterns {
wg.Add(1)
go func(filePattern string) {
defer wg.Done()
if err := c.collectGlobFilePath(logger, ch, filePattern); err != nil {
logger.Error("failed collecting metrics for filepath",
slog.String("filepath", filePattern),
slog.Any("err", err),
)
}
}(filePattern)
}
wg.Wait()
return nil
}
func (c *Collector) collectGlobFilePath(logger *slog.Logger, ch chan<- prometheus.Metric, filePattern string) error {
basePath, pattern := doublestar.SplitPattern(filePattern)
basePathFS := os.DirFS(basePath)
matches, err := doublestar.Glob(basePathFS, pattern, doublestar.WithFilesOnly())
if err != nil {
return fmt.Errorf("failed to glob: %w", err)
}
for _, match := range matches {
filePath := filepath.Join(basePath, match)
fileInfo, err := os.Stat(filePath)
if err != nil {
logger.Warn("failed to state file",
slog.String("file", filePath),
slog.Any("err", err),
)
continue
}
ch <- prometheus.MustNewConstMetric(
c.fileMTime,
prometheus.GaugeValue,
float64(fileInfo.ModTime().UTC().Unix()),
filePath,
)
}
return nil
}

View File

@@ -0,0 +1,12 @@
package filetime_test
import (
"testing"
"github.com/prometheus-community/windows_exporter/pkg/collector/filetime"
"github.com/prometheus-community/windows_exporter/pkg/testutils"
)
func BenchmarkCollector(b *testing.B) {
testutils.FuncBenchmarkCollector(b, filetime.Name, filetime.NewWithFlags)
}

View File

@@ -3,14 +3,14 @@
package fsrmquota
import (
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus-community/windows_exporter/pkg/utils"
"github.com/prometheus-community/windows_exporter/pkg/wmi"
"errors"
"log/slog"
"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/utils"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const Name = "fsrmquota"
@@ -19,109 +19,127 @@ type Config struct{}
var ConfigDefaults = Config{}
type collector struct {
logger log.Logger
type Collector struct {
config Config
wmiClient *wmi.Client
QuotasCount *prometheus.Desc
Path *prometheus.Desc
PeakUsage *prometheus.Desc
Size *prometheus.Desc
Usage *prometheus.Desc
quotasCount *prometheus.Desc
peakUsage *prometheus.Desc
size *prometheus.Desc
usage *prometheus.Desc
Description *prometheus.Desc
Disabled *prometheus.Desc
MatchesTemplate *prometheus.Desc
SoftLimit *prometheus.Desc
Template *prometheus.Desc
description *prometheus.Desc
disabled *prometheus.Desc
matchesTemplate *prometheus.Desc
softLimit *prometheus.Desc
template *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
func NewWithFlags(_ *kingpin.Application) *Collector {
return &Collector{}
}
func (c *collector) GetName() string {
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{}, nil
}
func (c *collector) Build() error {
c.QuotasCount = prometheus.NewDesc(
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, wmiClient *wmi.Client) error {
if wmiClient == nil || wmiClient.SWbemServicesClient == nil {
return errors.New("wmiClient or SWbemServicesClient is nil")
}
c.wmiClient = wmiClient
c.quotasCount = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "count"),
"Number of Quotas",
nil,
nil,
)
c.PeakUsage = prometheus.NewDesc(
c.peakUsage = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "peak_usage_bytes"),
"The highest amount of disk space usage charged to this quota. (PeakUsage)",
[]string{"path", "template"},
nil,
)
c.Size = prometheus.NewDesc(
c.size = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "size_bytes"),
"The size of the quota. (Size)",
[]string{"path", "template"},
nil,
)
c.Usage = prometheus.NewDesc(
c.usage = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "usage_bytes"),
"The current amount of disk space usage charged to this quota. (Usage)",
[]string{"path", "template"},
nil,
)
c.Description = prometheus.NewDesc(
c.description = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "description"),
"Description of the quota (Description)",
[]string{"path", "template", "description"},
nil,
)
c.Disabled = prometheus.NewDesc(
c.disabled = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "disabled"),
"If 1, the quota is disabled. The default value is 0. (Disabled)",
[]string{"path", "template"},
nil,
)
c.SoftLimit = prometheus.NewDesc(
c.softLimit = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "softlimit"),
"If 1, the quota is a soft limit. If 0, the quota is a hard limit. The default value is 0. Optional (SoftLimit)",
[]string{"path", "template"},
nil,
)
c.Template = prometheus.NewDesc(
c.template = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "template"),
"Quota template name. (Template)",
[]string{"path", "template"},
nil,
)
c.MatchesTemplate = prometheus.NewDesc(
c.matchesTemplate = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "matchestemplate"),
"If 1, the property values of this quota match those values of the template from which it was derived. (MatchesTemplate)",
[]string{"path", "template"},
nil,
)
return 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 {
func (c *Collector) Collect(_ *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
if err := c.collect(ch); err != nil {
_ = level.Error(c.logger).Log("msg", "failed collecting fsrmquota metrics", "err", err)
logger.Error("failed collecting fsrmquota metrics",
slog.Any("err", err),
)
return err
}
return nil
}
@@ -142,66 +160,64 @@ type MSFT_FSRMQuota struct {
SoftLimit bool
}
func (c *collector) collect(ch chan<- prometheus.Metric) error {
func (c *Collector) collect(ch chan<- prometheus.Metric) error {
var dst []MSFT_FSRMQuota
q := wmi.QueryAll(&dst, c.logger)
var count int
if err := wmi.QueryNamespace(q, &dst, "root/microsoft/windows/fsrm"); err != nil {
if err := c.wmiClient.Query("SELECT * FROM MSFT_FSRMQuota", &dst, nil, "root/microsoft/windows/fsrm"); err != nil {
return err
}
for _, quota := range dst {
count++
path := quota.Path
template := quota.Template
Description := quota.Description
ch <- prometheus.MustNewConstMetric(
c.PeakUsage,
c.peakUsage,
prometheus.GaugeValue,
float64(quota.PeakUsage),
path,
template,
)
ch <- prometheus.MustNewConstMetric(
c.Size,
c.size,
prometheus.GaugeValue,
float64(quota.Size),
path,
template,
)
ch <- prometheus.MustNewConstMetric(
c.Usage,
c.usage,
prometheus.GaugeValue,
float64(quota.Usage),
path,
template,
)
ch <- prometheus.MustNewConstMetric(
c.Description,
c.description,
prometheus.GaugeValue,
1.0,
path, template, Description,
)
ch <- prometheus.MustNewConstMetric(
c.Disabled,
c.disabled,
prometheus.GaugeValue,
utils.BoolToFloat(quota.Disabled),
path,
template,
)
ch <- prometheus.MustNewConstMetric(
c.MatchesTemplate,
c.matchesTemplate,
prometheus.GaugeValue,
utils.BoolToFloat(quota.MatchesTemplate),
path,
template,
)
ch <- prometheus.MustNewConstMetric(
c.SoftLimit,
c.softLimit,
prometheus.GaugeValue,
utils.BoolToFloat(quota.SoftLimit),
path,
@@ -210,9 +226,10 @@ func (c *collector) collect(ch chan<- prometheus.Metric) error {
}
ch <- prometheus.MustNewConstMetric(
c.QuotasCount,
c.quotasCount,
prometheus.GaugeValue,
float64(count),
)
return nil
}

View File

@@ -1,84 +0,0 @@
//go:build windows
package collector
import (
"fmt"
stdlog "log"
"net/http"
"strconv"
"time"
"github.com/go-kit/log"
"github.com/go-kit/log/level"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/client_golang/prometheus/collectors"
"github.com/prometheus/client_golang/prometheus/collectors/version"
"github.com/prometheus/client_golang/prometheus/promhttp"
)
func (c *Collectors) BuildServeHTTP(disableExporterMetrics bool, timeoutMargin float64) http.HandlerFunc {
collectorFactory := func(timeout time.Duration, requestedCollectors []string) (error, *Prometheus) {
filteredCollectors := make(map[string]types.Collector)
// scrape all enabled collectors if no collector is requested
if len(requestedCollectors) == 0 {
filteredCollectors = c.collectors
}
for _, name := range requestedCollectors {
col, exists := c.collectors[name]
if !exists {
return fmt.Errorf("unavailable collector: %s", name), nil
}
filteredCollectors[name] = col
}
filtered := Collectors{
logger: c.logger,
collectors: filteredCollectors,
perfCounterQuery: c.perfCounterQuery,
}
return nil, NewPrometheus(timeout, &filtered, c.logger)
}
return func(w http.ResponseWriter, r *http.Request) {
const defaultTimeout = 10.0
var timeoutSeconds float64
if v := r.Header.Get("X-Prometheus-Scrape-Timeout-Seconds"); v != "" {
var err error
timeoutSeconds, err = strconv.ParseFloat(v, 64)
if err != nil {
_ = level.Warn(c.logger).Log("msg", fmt.Sprintf("Couldn't parse X-Prometheus-Scrape-Timeout-Seconds: %q. Defaulting timeout to %f", v, defaultTimeout))
}
}
if timeoutSeconds == 0 {
timeoutSeconds = defaultTimeout
}
timeoutSeconds = timeoutSeconds - timeoutMargin
reg := prometheus.NewRegistry()
err, wc := collectorFactory(time.Duration(timeoutSeconds*float64(time.Second)), r.URL.Query()["collect[]"])
if err != nil {
_ = level.Warn(c.logger).Log("msg", "Couldn't create filtered metrics handler", "err", err)
w.WriteHeader(http.StatusBadRequest)
w.Write([]byte(fmt.Sprintf("Couldn't create filtered metrics handler: %s", err))) //nolint:errcheck
return
}
reg.MustRegister(wc)
if !disableExporterMetrics {
reg.MustRegister(
collectors.NewProcessCollector(collectors.ProcessCollectorOpts{}),
collectors.NewGoCollector(),
version.NewCollector("windows_exporter"),
)
}
h := promhttp.HandlerFor(reg, promhttp.HandlerOpts{
ErrorLog: stdlog.New(log.NewStdlibAdapter(level.Error(c.logger)), "", stdlog.Lshortfile),
})
h.ServeHTTP(w, r)
}
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -6,6 +6,8 @@ import (
)
func TestIISDeduplication(t *testing.T) {
t.Parallel()
start := []perflibAPP_POOL_WAS{
{
Name: "foo",

View File

@@ -3,13 +3,13 @@
package license
import (
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/go-kit/log/level"
"github.com/prometheus/client_golang/prometheus"
"log/slog"
"github.com/alecthomas/kingpin/v2"
"github.com/prometheus-community/windows_exporter/pkg/headers/slc"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const Name = "license"
@@ -26,37 +26,43 @@ type Config struct{}
var ConfigDefaults = Config{}
// A collector is a Prometheus collector for WMI Win32_PerfRawData_DNS_DNS metrics
type collector struct {
logger log.Logger
// A Collector is a Prometheus Collector for WMI Win32_PerfRawData_DNS_DNS metrics.
type Collector struct {
config Config
LicenseStatus *prometheus.Desc
licenseStatus *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
func NewWithFlags(_ *kingpin.Application) *Collector {
return &Collector{}
}
func (c *collector) GetName() string {
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{}, nil
}
func (c *collector) Build() error {
c.LicenseStatus = prometheus.NewDesc(
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, _ *wmi.Client) error {
c.licenseStatus = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "status"),
"Status of windows license",
[]string{"state"},
@@ -68,15 +74,20 @@ func (c *collector) Build() error {
// 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 {
func (c *Collector) Collect(_ *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
if err := c.collect(ch); err != nil {
_ = level.Error(c.logger).Log("msg", "failed collecting license metrics", "err", err)
logger.Error("failed collecting license metrics",
slog.Any("err", err),
)
return err
}
return nil
}
func (c *collector) collect(ch chan<- prometheus.Metric) error {
func (c *Collector) collect(ch chan<- prometheus.Metric) error {
status, err := slc.SLIsWindowsGenuineLocal()
if err != nil {
return err
@@ -88,7 +99,7 @@ func (c *collector) collect(ch chan<- prometheus.Metric) error {
val = 1.0
}
ch <- prometheus.MustNewConstMetric(c.LicenseStatus, prometheus.GaugeValue, val, v)
ch <- prometheus.MustNewConstMetric(c.licenseStatus, prometheus.GaugeValue, val, v)
}
return nil

View File

@@ -5,66 +5,54 @@ package logical_disk
import (
"encoding/binary"
"fmt"
"log/slog"
"regexp"
"slices"
"strconv"
"strings"
"golang.org/x/sys/windows"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/go-kit/log/level"
"github.com/prometheus-community/windows_exporter/pkg/perflib"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
"golang.org/x/sys/windows"
)
const (
Name = "logical_disk"
FlagLogicalDiskVolumeExclude = "collector.logical_disk.volume-exclude"
FlagLogicalDiskVolumeInclude = "collector.logical_disk.volume-include"
)
const Name = "logical_disk"
type Config struct {
VolumeInclude string `yaml:"volume_include"`
VolumeExclude string `yaml:"volume_exclude"`
VolumeInclude *regexp.Regexp `yaml:"volume_include"`
VolumeExclude *regexp.Regexp `yaml:"volume_exclude"`
}
var ConfigDefaults = Config{
VolumeInclude: ".+",
VolumeExclude: "",
VolumeInclude: types.RegExpAny,
VolumeExclude: types.RegExpEmpty,
}
// A collector is a Prometheus collector for perflib logicalDisk metrics
type collector struct {
logger log.Logger
// A Collector is a Prometheus Collector for perflib logicalDisk metrics.
type Collector struct {
config Config
volumeInclude *string
volumeExclude *string
Information *prometheus.Desc
ReadOnly *prometheus.Desc
RequestsQueued *prometheus.Desc
AvgReadQueue *prometheus.Desc
AvgWriteQueue *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
volumeIncludePattern *regexp.Regexp
volumeExcludePattern *regexp.Regexp
avgReadQueue *prometheus.Desc
avgWriteQueue *prometheus.Desc
freeSpace *prometheus.Desc
idleTime *prometheus.Desc
information *prometheus.Desc
readBytesTotal *prometheus.Desc
readLatency *prometheus.Desc
readOnly *prometheus.Desc
readsTotal *prometheus.Desc
readTime *prometheus.Desc
readWriteLatency *prometheus.Desc
requestsQueued *prometheus.Desc
splitIOs *prometheus.Desc
totalSpace *prometheus.Desc
writeBytesTotal *prometheus.Desc
writeLatency *prometheus.Desc
writesTotal *prometheus.Desc
writeTime *prometheus.Desc
}
type volumeInfo struct {
@@ -75,198 +63,220 @@ type volumeInfo struct {
readonly float64
}
func New(logger log.Logger, config *Config) types.Collector {
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &collector{
volumeExclude: &config.VolumeExclude,
volumeInclude: &config.VolumeInclude,
if config.VolumeExclude == nil {
config.VolumeExclude = ConfigDefaults.VolumeExclude
}
c.SetLogger(logger)
return c
}
func NewWithFlags(app *kingpin.Application) types.Collector {
c := &collector{
volumeInclude: app.Flag(
FlagLogicalDiskVolumeInclude,
"Regexp of volumes to include. Volume name must both match include and not match exclude to be included.",
).Default(ConfigDefaults.VolumeInclude).String(),
volumeExclude: app.Flag(
FlagLogicalDiskVolumeExclude,
"Regexp of volumes to exclude. Volume name must both match include and not match exclude to be included.",
).Default(ConfigDefaults.VolumeExclude).String(),
if config.VolumeInclude == nil {
config.VolumeInclude = ConfigDefaults.VolumeInclude
}
c := &Collector{
config: *config,
}
return c
}
func (c *collector) GetName() string {
func NewWithFlags(app *kingpin.Application) *Collector {
c := &Collector{
config: ConfigDefaults,
}
var volumeExclude, volumeInclude string
app.Flag(
"collector.logical_disk.volume-exclude",
"Regexp of volumes to exclude. Volume name must both match include and not match exclude to be included.",
).Default(c.config.VolumeExclude.String()).StringVar(&volumeExclude)
app.Flag(
"collector.logical_disk.volume-include",
"Regexp of volumes to include. Volume name must both match include and not match exclude to be included.",
).Default(c.config.VolumeInclude.String()).StringVar(&volumeInclude)
app.Action(func(*kingpin.ParseContext) error {
var err error
c.config.VolumeExclude, err = regexp.Compile(fmt.Sprintf("^(?:%s)$", volumeExclude))
if err != nil {
return fmt.Errorf("collector.logical_disk.volume-exclude: %w", err)
}
c.config.VolumeInclude, err = regexp.Compile(fmt.Sprintf("^(?:%s)$", volumeInclude))
if err != nil {
return fmt.Errorf("collector.logical_disk.volume-include: %w", err)
}
return nil
})
return c
}
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{"LogicalDisk"}, nil
}
func (c *collector) Build() error {
c.Information = prometheus.NewDesc(
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, _ *wmi.Client) error {
c.information = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "info"),
"A metric with a constant '1' value labeled with logical disk information",
[]string{"disk", "type", "volume", "volume_name", "filesystem", "serial_number"},
nil,
)
c.ReadOnly = prometheus.NewDesc(
c.readOnly = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "readonly"),
"Whether the logical disk is read-only",
[]string{"volume"},
nil,
)
c.RequestsQueued = prometheus.NewDesc(
c.requestsQueued = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "requests_queued"),
"The number of requests queued to the disk (LogicalDisk.CurrentDiskQueueLength)",
[]string{"volume"},
nil,
)
c.AvgReadQueue = prometheus.NewDesc(
c.avgReadQueue = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "avg_read_requests_queued"),
"Average number of read requests that were queued for the selected disk during the sample interval (LogicalDisk.AvgDiskReadQueueLength)",
[]string{"volume"},
nil,
)
c.AvgWriteQueue = prometheus.NewDesc(
c.avgWriteQueue = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "avg_write_requests_queued"),
"Average number of write requests that were queued for the selected disk during the sample interval (LogicalDisk.AvgDiskWriteQueueLength)",
[]string{"volume"},
nil,
)
c.ReadBytesTotal = prometheus.NewDesc(
c.readBytesTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "read_bytes_total"),
"The number of bytes transferred from the disk during read operations (LogicalDisk.DiskReadBytesPerSec)",
[]string{"volume"},
nil,
)
c.ReadsTotal = prometheus.NewDesc(
c.readsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "reads_total"),
"The number of read operations on the disk (LogicalDisk.DiskReadsPerSec)",
[]string{"volume"},
nil,
)
c.WriteBytesTotal = prometheus.NewDesc(
c.writeBytesTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "write_bytes_total"),
"The number of bytes transferred to the disk during write operations (LogicalDisk.DiskWriteBytesPerSec)",
[]string{"volume"},
nil,
)
c.WritesTotal = prometheus.NewDesc(
c.writesTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "writes_total"),
"The number of write operations on the disk (LogicalDisk.DiskWritesPerSec)",
[]string{"volume"},
nil,
)
c.ReadTime = prometheus.NewDesc(
c.readTime = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "read_seconds_total"),
"Seconds that the disk was busy servicing read requests (LogicalDisk.PercentDiskReadTime)",
[]string{"volume"},
nil,
)
c.WriteTime = prometheus.NewDesc(
c.writeTime = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "write_seconds_total"),
"Seconds that the disk was busy servicing write requests (LogicalDisk.PercentDiskWriteTime)",
[]string{"volume"},
nil,
)
c.FreeSpace = prometheus.NewDesc(
c.freeSpace = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "free_bytes"),
"Free space in bytes, updates every 10-15 min (LogicalDisk.PercentFreeSpace)",
[]string{"volume"},
nil,
)
c.TotalSpace = prometheus.NewDesc(
c.totalSpace = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "size_bytes"),
"Total space in bytes, updates every 10-15 min (LogicalDisk.PercentFreeSpace_Base)",
[]string{"volume"},
nil,
)
c.IdleTime = prometheus.NewDesc(
c.idleTime = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "idle_seconds_total"),
"Seconds that the disk was idle (LogicalDisk.PercentIdleTime)",
[]string{"volume"},
nil,
)
c.SplitIOs = prometheus.NewDesc(
c.splitIOs = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "split_ios_total"),
"The number of I/Os to the disk were split into multiple I/Os (LogicalDisk.SplitIOPerSec)",
[]string{"volume"},
nil,
)
c.ReadLatency = prometheus.NewDesc(
c.readLatency = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "read_latency_seconds_total"),
"Shows the average time, in seconds, of a read operation from the disk (LogicalDisk.AvgDiskSecPerRead)",
[]string{"volume"},
nil,
)
c.WriteLatency = prometheus.NewDesc(
c.writeLatency = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "write_latency_seconds_total"),
"Shows the average time, in seconds, of a write operation to the disk (LogicalDisk.AvgDiskSecPerWrite)",
[]string{"volume"},
nil,
)
c.ReadWriteLatency = prometheus.NewDesc(
c.readWriteLatency = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "read_write_latency_seconds_total"),
"Shows the time, in seconds, of the average disk transfer (LogicalDisk.AvgDiskSecPerTransfer)",
[]string{"volume"},
nil,
)
var err error
c.volumeIncludePattern, err = regexp.Compile(fmt.Sprintf("^(?:%s)$", *c.volumeInclude))
if err != nil {
return err
}
c.volumeExcludePattern, err = regexp.Compile(fmt.Sprintf("^(?:%s)$", *c.volumeExclude))
if err != nil {
return err
}
return nil
}
// Collect sends the metric values for each metric
// to the provided prometheus Metric channel.
func (c *collector) Collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
if err := c.collect(ctx, ch); err != nil {
_ = level.Error(c.logger).Log("msg", "failed collecting logical_disk metrics", "err", err)
func (c *Collector) Collect(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
if err := c.collect(ctx, logger, ch); err != nil {
logger.Error("failed collecting logical_disk metrics",
slog.Any("err", 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
// - https://msdn.microsoft.com/en-us/library/ms803973.aspx - LogicalDisk object reference.
type logicalDisk struct {
Name string
CurrentDiskQueueLength float64 `perflib:"Current Disk Queue Length"`
@@ -287,7 +297,9 @@ type logicalDisk struct {
AvgDiskSecPerTransfer float64 `perflib:"Avg. Disk sec/Transfer"`
}
func (c *collector) collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collect(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var (
err error
diskID string
@@ -295,29 +307,33 @@ func (c *collector) collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metri
dst []logicalDisk
)
if err = perflib.UnmarshalObject(ctx.PerfObjects["LogicalDisk"], &dst, c.logger); err != nil {
if err = perflib.UnmarshalObject(ctx.PerfObjects["LogicalDisk"], &dst, logger); err != nil {
return err
}
for _, volume := range dst {
if volume.Name == "_Total" ||
c.volumeExcludePattern.MatchString(volume.Name) ||
!c.volumeIncludePattern.MatchString(volume.Name) {
c.config.VolumeExclude.MatchString(volume.Name) ||
!c.config.VolumeInclude.MatchString(volume.Name) {
continue
}
diskID, err = getDiskIDByVolume(volume.Name)
if err != nil {
_ = level.Warn(c.logger).Log("msg", "failed to get disk ID for "+volume.Name, "err", err)
logger.Warn("failed to get disk ID for "+volume.Name,
slog.Any("err", err),
)
}
info, err = getVolumeInfo(volume.Name)
if err != nil {
_ = level.Warn(c.logger).Log("msg", "failed to get volume information for %s"+volume.Name, "err", err)
logger.Warn("failed to get volume information for %s"+volume.Name,
slog.Any("err", err),
)
}
ch <- prometheus.MustNewConstMetric(
c.Information,
c.information,
prometheus.GaugeValue,
1,
diskID,
@@ -329,112 +345,112 @@ func (c *collector) collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metri
)
ch <- prometheus.MustNewConstMetric(
c.RequestsQueued,
c.requestsQueued,
prometheus.GaugeValue,
volume.CurrentDiskQueueLength,
volume.Name,
)
ch <- prometheus.MustNewConstMetric(
c.AvgReadQueue,
c.avgReadQueue,
prometheus.GaugeValue,
volume.AvgDiskReadQueueLength*perflib.TicksToSecondScaleFactor,
volume.Name,
)
ch <- prometheus.MustNewConstMetric(
c.AvgWriteQueue,
c.avgWriteQueue,
prometheus.GaugeValue,
volume.AvgDiskWriteQueueLength*perflib.TicksToSecondScaleFactor,
volume.Name,
)
ch <- prometheus.MustNewConstMetric(
c.ReadBytesTotal,
c.readBytesTotal,
prometheus.CounterValue,
volume.DiskReadBytesPerSec,
volume.Name,
)
ch <- prometheus.MustNewConstMetric(
c.ReadsTotal,
c.readsTotal,
prometheus.CounterValue,
volume.DiskReadsPerSec,
volume.Name,
)
ch <- prometheus.MustNewConstMetric(
c.WriteBytesTotal,
c.writeBytesTotal,
prometheus.CounterValue,
volume.DiskWriteBytesPerSec,
volume.Name,
)
ch <- prometheus.MustNewConstMetric(
c.WritesTotal,
c.writesTotal,
prometheus.CounterValue,
volume.DiskWritesPerSec,
volume.Name,
)
ch <- prometheus.MustNewConstMetric(
c.ReadTime,
c.readTime,
prometheus.CounterValue,
volume.PercentDiskReadTime,
volume.Name,
)
ch <- prometheus.MustNewConstMetric(
c.WriteTime,
c.writeTime,
prometheus.CounterValue,
volume.PercentDiskWriteTime,
volume.Name,
)
ch <- prometheus.MustNewConstMetric(
c.FreeSpace,
c.freeSpace,
prometheus.GaugeValue,
volume.PercentFreeSpace_Base*1024*1024,
volume.Name,
)
ch <- prometheus.MustNewConstMetric(
c.TotalSpace,
c.totalSpace,
prometheus.GaugeValue,
volume.PercentFreeSpace*1024*1024,
volume.Name,
)
ch <- prometheus.MustNewConstMetric(
c.IdleTime,
c.idleTime,
prometheus.CounterValue,
volume.PercentIdleTime,
volume.Name,
)
ch <- prometheus.MustNewConstMetric(
c.SplitIOs,
c.splitIOs,
prometheus.CounterValue,
volume.SplitIOPerSec,
volume.Name,
)
ch <- prometheus.MustNewConstMetric(
c.ReadLatency,
c.readLatency,
prometheus.CounterValue,
volume.AvgDiskSecPerRead*perflib.TicksToSecondScaleFactor,
volume.Name,
)
ch <- prometheus.MustNewConstMetric(
c.WriteLatency,
c.writeLatency,
prometheus.CounterValue,
volume.AvgDiskSecPerWrite*perflib.TicksToSecondScaleFactor,
volume.Name,
)
ch <- prometheus.MustNewConstMetric(
c.ReadWriteLatency,
c.readWriteLatency,
prometheus.CounterValue,
volume.AvgDiskSecPerTransfer*perflib.TicksToSecondScaleFactor,
volume.Name,
@@ -472,15 +488,16 @@ const diskExtentSize = 24
func getDiskIDByVolume(rootDrive string) (string, error) {
// Open a volume handle to the Disk Root.
var err error
var f windows.Handle
// mode has to include FILE_SHARE permission to allow concurrent access to the disk.
// use 0 as access mode to avoid admin permission.
mode := uint32(windows.FILE_SHARE_READ | windows.FILE_SHARE_WRITE | windows.FILE_SHARE_DELETE)
f, err = windows.CreateFile(
windows.StringToUTF16Ptr(`\\.\`+rootDrive),
0, mode, nil, windows.OPEN_EXISTING, uint32(windows.FILE_ATTRIBUTE_READONLY), 0)
if err != nil {
return "", err
}
@@ -491,6 +508,7 @@ func getDiskIDByVolume(rootDrive string) (string, error) {
volumeDiskExtents := make([]byte, 16*1024)
var bytesReturned uint32
err = windows.DeviceIoControl(f, controlCode, nil, 0, &volumeDiskExtents[0], uint32(len(volumeDiskExtents)), &bytesReturned, nil)
if err != nil {
return "", fmt.Errorf("could not identify physical drive for %s: %w", rootDrive, err)
@@ -529,7 +547,6 @@ func getVolumeInfo(rootDrive string) (volumeInfo, error) {
err := windows.GetVolumeInformation(volPath, &volBufLabel[0], uint32(len(volBufLabel)),
&volSerialNum, nil, &fsFlags, &volBufType[0], uint32(len(volBufType)))
if err != nil {
if driveType != windows.DRIVE_CDROM && driveType != windows.DRIVE_REMOVABLE {
return volumeInfo{}, err

View File

@@ -9,8 +9,8 @@ import (
)
func BenchmarkCollector(b *testing.B) {
// Whitelist is not set in testing context (kingpin flags not parsed), causing the collector to skip all disks.
// Whitelist is not set in testing context (kingpin flags not parsed), causing the Collector to skip all disks.
localVolumeInclude := ".+"
kingpin.CommandLine.GetArg(logical_disk.FlagLogicalDiskVolumeInclude).StringVar(&localVolumeInclude)
kingpin.CommandLine.GetArg("collector.logical_disk.volume-include").StringVar(&localVolumeInclude)
testutils.FuncBenchmarkCollector(b, "logical_disk", logical_disk.NewWithFlags)
}

View File

@@ -4,14 +4,12 @@ package logon
import (
"errors"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus-community/windows_exporter/pkg/wmi"
"log/slog"
"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/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const Name = "logon"
@@ -20,52 +18,70 @@ type Config struct{}
var ConfigDefaults = Config{}
// A collector is a Prometheus collector for WMI metrics
type collector struct {
logger log.Logger
// A Collector is a Prometheus Collector for WMI metrics.
type Collector struct {
config Config
wmiClient *wmi.Client
LogonType *prometheus.Desc
logonType *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
func NewWithFlags(_ *kingpin.Application) *Collector {
return &Collector{}
}
func (c *collector) GetName() string {
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{}, nil
}
func (c *collector) Build() error {
c.LogonType = prometheus.NewDesc(
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, wmiClient *wmi.Client) error {
if wmiClient == nil || wmiClient.SWbemServicesClient == nil {
return errors.New("wmiClient or SWbemServicesClient is nil")
}
c.wmiClient = wmiClient
c.logonType = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "logon_type"),
"Number of active logon sessions (LogonSession.LogonType)",
[]string{"status"},
nil,
)
return 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 {
func (c *Collector) Collect(_ *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
if err := c.collect(ch); err != nil {
_ = level.Error(c.logger).Log("msg", "failed collecting user metrics", "err", err)
logger.Error("failed collecting user metrics",
slog.Any("err", err),
)
return err
}
return nil
}
@@ -75,12 +91,12 @@ type Win32_LogonSession struct {
LogonType uint32
}
func (c *collector) collect(ch chan<- prometheus.Metric) error {
func (c *Collector) collect(ch chan<- prometheus.Metric) error {
var dst []Win32_LogonSession
q := wmi.QueryAll(&dst, c.logger)
if err := wmi.Query(q, &dst); err != nil {
if err := c.wmiClient.Query("SELECT * FROM Win32_LogonSession", &dst); err != nil {
return err
}
if len(dst) == 0 {
return errors.New("WMI query returned empty result set")
}
@@ -132,94 +148,95 @@ 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
}

View File

@@ -8,6 +8,6 @@ import (
)
func BenchmarkCollector(b *testing.B) {
// No context name required as collector source is WMI
// No context name required as Collector source is WMI
testutils.FuncBenchmarkCollector(b, logon.Name, logon.NewWithFlags)
}

View File

@@ -1,6 +1,10 @@
package collector
import (
"maps"
"slices"
"github.com/alecthomas/kingpin/v2"
"github.com/prometheus-community/windows_exporter/pkg/collector/ad"
"github.com/prometheus-community/windows_exporter/pkg/collector/adcs"
"github.com/prometheus-community/windows_exporter/pkg/collector/adfs"
@@ -14,6 +18,7 @@ import (
"github.com/prometheus-community/windows_exporter/pkg/collector/diskdrive"
"github.com/prometheus-community/windows_exporter/pkg/collector/dns"
"github.com/prometheus-community/windows_exporter/pkg/collector/exchange"
"github.com/prometheus-community/windows_exporter/pkg/collector/filetime"
"github.com/prometheus-community/windows_exporter/pkg/collector/fsrmquota"
"github.com/prometheus-community/windows_exporter/pkg/collector/hyperv"
"github.com/prometheus-community/windows_exporter/pkg/collector/iis"
@@ -21,24 +26,14 @@ import (
"github.com/prometheus-community/windows_exporter/pkg/collector/logical_disk"
"github.com/prometheus-community/windows_exporter/pkg/collector/logon"
"github.com/prometheus-community/windows_exporter/pkg/collector/memory"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_cluster"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_network"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_node"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_resource"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_resourcegroup"
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster"
"github.com/prometheus-community/windows_exporter/pkg/collector/msmq"
"github.com/prometheus-community/windows_exporter/pkg/collector/mssql"
"github.com/prometheus-community/windows_exporter/pkg/collector/net"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrexceptions"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrinterop"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrjit"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrloading"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrlocksandthreads"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrmemory"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrremoting"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework_clrsecurity"
"github.com/prometheus-community/windows_exporter/pkg/collector/netframework"
"github.com/prometheus-community/windows_exporter/pkg/collector/nps"
"github.com/prometheus-community/windows_exporter/pkg/collector/os"
"github.com/prometheus-community/windows_exporter/pkg/collector/perfdata"
"github.com/prometheus-community/windows_exporter/pkg/collector/physical_disk"
"github.com/prometheus-community/windows_exporter/pkg/collector/printer"
"github.com/prometheus-community/windows_exporter/pkg/collector/process"
@@ -57,70 +52,64 @@ import (
"github.com/prometheus-community/windows_exporter/pkg/collector/time"
"github.com/prometheus-community/windows_exporter/pkg/collector/vmware"
"github.com/prometheus-community/windows_exporter/pkg/collector/vmware_blast"
"github.com/prometheus-community/windows_exporter/pkg/types"
"golang.org/x/exp/maps"
)
var Map = map[string]types.CollectorBuilderWithFlags{
ad.Name: ad.NewWithFlags,
adcs.Name: adcs.NewWithFlags,
adfs.Name: adfs.NewWithFlags,
cache.Name: cache.NewWithFlags,
container.Name: container.NewWithFlags,
cpu.Name: cpu.NewWithFlags,
cpu_info.Name: cpu_info.NewWithFlags,
cs.Name: cs.NewWithFlags,
dfsr.Name: dfsr.NewWithFlags,
dhcp.Name: dhcp.NewWithFlags,
diskdrive.Name: diskdrive.NewWithFlags,
dns.Name: dns.NewWithFlags,
exchange.Name: exchange.NewWithFlags,
fsrmquota.Name: fsrmquota.NewWithFlags,
hyperv.Name: hyperv.NewWithFlags,
iis.Name: iis.NewWithFlags,
license.Name: license.NewWithFlags,
logical_disk.Name: logical_disk.NewWithFlags,
logon.Name: logon.NewWithFlags,
memory.Name: memory.NewWithFlags,
mscluster_cluster.Name: mscluster_cluster.NewWithFlags,
mscluster_network.Name: mscluster_network.NewWithFlags,
mscluster_node.Name: mscluster_node.NewWithFlags,
mscluster_resource.Name: mscluster_resource.NewWithFlags,
mscluster_resourcegroup.Name: mscluster_resourcegroup.NewWithFlags,
msmq.Name: msmq.NewWithFlags,
mssql.Name: mssql.NewWithFlags,
net.Name: net.NewWithFlags,
netframework_clrexceptions.Name: netframework_clrexceptions.NewWithFlags,
netframework_clrinterop.Name: netframework_clrinterop.NewWithFlags,
netframework_clrjit.Name: netframework_clrjit.NewWithFlags,
netframework_clrloading.Name: netframework_clrloading.NewWithFlags,
netframework_clrlocksandthreads.Name: netframework_clrlocksandthreads.NewWithFlags,
netframework_clrmemory.Name: netframework_clrmemory.NewWithFlags,
netframework_clrremoting.Name: netframework_clrremoting.NewWithFlags,
netframework_clrsecurity.Name: netframework_clrsecurity.NewWithFlags,
nps.Name: nps.NewWithFlags,
os.Name: os.NewWithFlags,
physical_disk.Name: physical_disk.NewWithFlags,
printer.Name: printer.NewWithFlags,
process.Name: process.NewWithFlags,
remote_fx.Name: remote_fx.NewWithFlags,
scheduled_task.Name: scheduled_task.NewWithFlags,
service.Name: service.NewWithFlags,
smb.Name: smb.NewWithFlags,
smbclient.Name: smbclient.NewWithFlags,
smtp.Name: smtp.NewWithFlags,
system.Name: system.NewWithFlags,
teradici_pcoip.Name: teradici_pcoip.NewWithFlags,
tcp.Name: tcp.NewWithFlags,
terminal_services.Name: terminal_services.NewWithFlags,
textfile.Name: textfile.NewWithFlags,
thermalzone.Name: thermalzone.NewWithFlags,
time.Name: time.NewWithFlags,
vmware.Name: vmware.NewWithFlags,
vmware_blast.Name: vmware_blast.NewWithFlags,
func NewBuilderWithFlags[C Collector](fn BuilderWithFlags[C]) BuilderWithFlags[Collector] {
return func(app *kingpin.Application) Collector {
return fn(app)
}
}
var BuildersWithFlags = map[string]BuilderWithFlags[Collector]{
ad.Name: NewBuilderWithFlags(ad.NewWithFlags),
adcs.Name: NewBuilderWithFlags(adcs.NewWithFlags),
adfs.Name: NewBuilderWithFlags(adfs.NewWithFlags),
cache.Name: NewBuilderWithFlags(cache.NewWithFlags),
container.Name: NewBuilderWithFlags(container.NewWithFlags),
cpu.Name: NewBuilderWithFlags(cpu.NewWithFlags),
cpu_info.Name: NewBuilderWithFlags(cpu_info.NewWithFlags),
cs.Name: NewBuilderWithFlags(cs.NewWithFlags),
dfsr.Name: NewBuilderWithFlags(dfsr.NewWithFlags),
dhcp.Name: NewBuilderWithFlags(dhcp.NewWithFlags),
diskdrive.Name: NewBuilderWithFlags(diskdrive.NewWithFlags),
dns.Name: NewBuilderWithFlags(dns.NewWithFlags),
exchange.Name: NewBuilderWithFlags(exchange.NewWithFlags),
filetime.Name: NewBuilderWithFlags(filetime.NewWithFlags),
fsrmquota.Name: NewBuilderWithFlags(fsrmquota.NewWithFlags),
hyperv.Name: NewBuilderWithFlags(hyperv.NewWithFlags),
iis.Name: NewBuilderWithFlags(iis.NewWithFlags),
license.Name: NewBuilderWithFlags(license.NewWithFlags),
logical_disk.Name: NewBuilderWithFlags(logical_disk.NewWithFlags),
logon.Name: NewBuilderWithFlags(logon.NewWithFlags),
memory.Name: NewBuilderWithFlags(memory.NewWithFlags),
mscluster.Name: NewBuilderWithFlags(mscluster.NewWithFlags),
msmq.Name: NewBuilderWithFlags(msmq.NewWithFlags),
mssql.Name: NewBuilderWithFlags(mssql.NewWithFlags),
net.Name: NewBuilderWithFlags(net.NewWithFlags),
netframework.Name: NewBuilderWithFlags(netframework.NewWithFlags),
nps.Name: NewBuilderWithFlags(nps.NewWithFlags),
os.Name: NewBuilderWithFlags(os.NewWithFlags),
perfdata.Name: NewBuilderWithFlags(perfdata.NewWithFlags),
physical_disk.Name: NewBuilderWithFlags(physical_disk.NewWithFlags),
printer.Name: NewBuilderWithFlags(printer.NewWithFlags),
process.Name: NewBuilderWithFlags(process.NewWithFlags),
remote_fx.Name: NewBuilderWithFlags(remote_fx.NewWithFlags),
scheduled_task.Name: NewBuilderWithFlags(scheduled_task.NewWithFlags),
service.Name: NewBuilderWithFlags(service.NewWithFlags),
smb.Name: NewBuilderWithFlags(smb.NewWithFlags),
smbclient.Name: NewBuilderWithFlags(smbclient.NewWithFlags),
smtp.Name: NewBuilderWithFlags(smtp.NewWithFlags),
system.Name: NewBuilderWithFlags(system.NewWithFlags),
teradici_pcoip.Name: NewBuilderWithFlags(teradici_pcoip.NewWithFlags),
tcp.Name: NewBuilderWithFlags(tcp.NewWithFlags),
terminal_services.Name: NewBuilderWithFlags(terminal_services.NewWithFlags),
textfile.Name: NewBuilderWithFlags(textfile.NewWithFlags),
thermalzone.Name: NewBuilderWithFlags(thermalzone.NewWithFlags),
time.Name: NewBuilderWithFlags(time.NewWithFlags),
vmware.Name: NewBuilderWithFlags(vmware.NewWithFlags),
vmware_blast.Name: NewBuilderWithFlags(vmware_blast.NewWithFlags),
}
func Available() []string {
return maps.Keys(Map)
return slices.Sorted(maps.Keys(BuildersWithFlags))
}

View File

@@ -6,12 +6,16 @@
package memory
import (
"errors"
"fmt"
"log/slog"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/go-kit/log/level"
"github.com/prometheus-community/windows_exporter/pkg/headers/sysinfoapi"
"github.com/prometheus-community/windows_exporter/pkg/perflib"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const Name = "memory"
@@ -20,281 +24,355 @@ type Config struct{}
var ConfigDefaults = Config{}
// A collector is a Prometheus collector for perflib Memory metrics
type collector struct {
logger log.Logger
// A Collector is a Prometheus Collector for perflib Memory metrics.
type Collector struct {
config Config
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
// Performance metrics
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
poolNonPagedAllocationsTotal *prometheus.Desc
poolNonPagedBytes *prometheus.Desc
poolPagedAllocationsTotal *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
// Global memory status
processMemoryLimitBytes *prometheus.Desc
physicalMemoryTotalBytes *prometheus.Desc
physicalMemoryFreeBytes *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
func NewWithFlags(_ *kingpin.Application) *Collector {
return &Collector{}
}
func (c *collector) GetName() string {
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{"Memory"}, nil
}
func (c *collector) Build() error {
c.AvailableBytes = prometheus.NewDesc(
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, _ *wmi.Client) error {
c.availableBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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,
)
c.CacheBytes = prometheus.NewDesc(
c.cacheBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "cache_bytes"),
"(CacheBytes)",
nil,
nil,
)
c.CacheBytesPeak = prometheus.NewDesc(
c.cacheBytesPeak = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "cache_bytes_peak"),
"(CacheBytesPeak)",
nil,
nil,
)
c.CacheFaultsTotal = prometheus.NewDesc(
c.cacheFaultsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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) (Cache Faults/sec)",
nil,
nil,
)
c.CommitLimit = prometheus.NewDesc(
c.commitLimit = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "commit_limit"),
"(CommitLimit)",
nil,
nil,
)
c.CommittedBytes = prometheus.NewDesc(
c.committedBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "committed_bytes"),
"(CommittedBytes)",
nil,
nil,
)
c.DemandZeroFaultsTotal = prometheus.NewDesc(
c.demandZeroFaultsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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 (Demand Zero Faults/sec)",
nil,
nil,
)
c.FreeAndZeroPageListBytes = prometheus.NewDesc(
c.freeAndZeroPageListBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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 (FreeAndZeroPageListBytes)",
nil,
nil,
)
c.FreeSystemPageTableEntries = prometheus.NewDesc(
c.freeSystemPageTableEntries = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "free_system_page_table_entries"),
"(FreeSystemPageTableEntries)",
nil,
nil,
)
c.ModifiedPageListBytes = prometheus.NewDesc(
c.modifiedPageListBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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 (ModifiedPageListBytes)",
nil,
nil,
)
c.PageFaultsTotal = prometheus.NewDesc(
c.pageFaultsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "page_faults_total"),
"Overall rate at which faulted pages are handled by the processor (Page Faults/sec)",
nil,
nil,
)
c.SwapPageReadsTotal = prometheus.NewDesc(
c.swapPageReadsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "swap_page_reads_total"),
"Number of disk page reads (a single read operation reading several pages is still only counted once) (PageReadsPersec)",
nil,
nil,
)
c.SwapPagesReadTotal = prometheus.NewDesc(
c.swapPagesReadTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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,
)
c.SwapPagesWrittenTotal = prometheus.NewDesc(
c.swapPagesWrittenTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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,
)
c.SwapPageOperationsTotal = prometheus.NewDesc(
c.swapPageOperationsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "swap_page_operations_total"),
"Total number of swap page read and writes (PagesPersec)",
nil,
nil,
)
c.SwapPageWritesTotal = prometheus.NewDesc(
c.swapPageWritesTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "swap_page_writes_total"),
"Number of disk page writes (a single write operation writing several pages is still only counted once) (PageWritesPersec)",
nil,
nil,
)
c.PoolNonpagedAllocsTotal = prometheus.NewDesc(
c.poolNonPagedAllocationsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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,
)
c.PoolNonpagedBytes = prometheus.NewDesc(
c.poolNonPagedBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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 (PoolNonpagedBytes)",
nil,
nil,
)
c.PoolPagedAllocsTotal = prometheus.NewDesc(
c.poolPagedAllocationsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "pool_paged_allocs_total"),
"Number of calls to allocate space in the paged pool, regardless of the amount of space allocated in each call (PoolPagedAllocs)",
nil,
nil,
)
c.PoolPagedBytes = prometheus.NewDesc(
c.poolPagedBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "pool_paged_bytes"),
"(PoolPagedBytes)",
nil,
nil,
)
c.PoolPagedResidentBytes = prometheus.NewDesc(
c.poolPagedResidentBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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 (PoolPagedResidentBytes)",
nil,
nil,
)
c.StandbyCacheCoreBytes = prometheus.NewDesc(
c.standbyCacheCoreBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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 (StandbyCacheCoreBytes)",
nil,
nil,
)
c.StandbyCacheNormalPriorityBytes = prometheus.NewDesc(
c.standbyCacheNormalPriorityBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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 (StandbyCacheNormalPriorityBytes)",
nil,
nil,
)
c.StandbyCacheReserveBytes = prometheus.NewDesc(
c.standbyCacheReserveBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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 (StandbyCacheReserveBytes)",
nil,
nil,
)
c.SystemCacheResidentBytes = prometheus.NewDesc(
c.systemCacheResidentBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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 (SystemCacheResidentBytes)",
nil,
nil,
)
c.SystemCodeResidentBytes = prometheus.NewDesc(
c.systemCodeResidentBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "system_code_resident_bytes"),
"The size, in bytes, of the pageable operating system code that is currently resident and active in physical memory (SystemCodeResidentBytes)",
nil,
nil,
)
c.SystemCodeTotalBytes = prometheus.NewDesc(
c.systemCodeTotalBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "system_code_total_bytes"),
"The size, in bytes, of the pageable operating system code currently mapped into the system virtual address space (SystemCodeTotalBytes)",
nil,
nil,
)
c.SystemDriverResidentBytes = prometheus.NewDesc(
c.systemDriverResidentBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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 (SystemDriverResidentBytes)",
nil,
nil,
)
c.SystemDriverTotalBytes = prometheus.NewDesc(
c.systemDriverTotalBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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 (SystemDriverTotalBytes)",
nil,
nil,
)
c.TransitionFaultsTotal = prometheus.NewDesc(
c.transitionFaultsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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 (TransitionFaultsPersec)",
nil,
nil,
)
c.TransitionPagesRepurposedTotal = prometheus.NewDesc(
c.transitionPagesRepurposedTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "transition_pages_repurposed_total"),
"Transition Pages RePurposed is the rate at which the number of transition cache pages were reused for a different purpose (TransitionPagesRePurposedPersec)",
nil,
nil,
)
c.WriteCopiesTotal = prometheus.NewDesc(
c.writeCopiesTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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,
)
c.processMemoryLimitBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "process_memory_limit_bytes"),
"The size of the user-mode portion of the virtual address space of the calling process, in bytes. This value depends on the type of process, the type of processor, and the configuration of the operating system.",
nil,
nil,
)
c.physicalMemoryTotalBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "physical_total_bytes"),
"The amount of actual physical memory, in bytes.",
nil,
nil,
)
c.physicalMemoryFreeBytes = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "physical_free_bytes"),
"The amount of physical memory currently available, in bytes. This is the amount of physical memory that can be immediately reused without having to write its contents to disk first. It is the sum of the size of the standby, free, and zero lists.",
nil,
nil,
)
return nil
}
// Collect sends the metric values for each metric
// to the provided prometheus Metric channel.
func (c *collector) Collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
if err := c.collect(ctx, ch); err != nil {
_ = level.Error(c.logger).Log("msg", "failed collecting memory metrics", "err", err)
return err
func (c *Collector) Collect(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
errs := make([]error, 0, 2)
if err := c.collectPerformanceData(ctx, logger, ch); err != nil {
logger.Error("failed collecting memory metrics",
slog.Any("err", err),
)
errs = append(errs, err)
}
if err := c.collectGlobalMemoryStatus(ch); err != nil {
logger.Error("failed collecting memory metrics",
slog.Any("err", err),
)
errs = append(errs, err)
}
return errors.Join(errs...)
}
func (c *Collector) collectGlobalMemoryStatus(ch chan<- prometheus.Metric) error {
memoryStatusEx, err := sysinfoapi.GlobalMemoryStatusEx()
if err != nil {
return fmt.Errorf("failed to get memory status: %w", err)
}
ch <- prometheus.MustNewConstMetric(
c.processMemoryLimitBytes,
prometheus.GaugeValue,
float64(memoryStatusEx.TotalVirtual),
)
ch <- prometheus.MustNewConstMetric(
c.physicalMemoryTotalBytes,
prometheus.GaugeValue,
float64(memoryStatusEx.TotalPhys),
)
ch <- prometheus.MustNewConstMetric(
c.physicalMemoryFreeBytes,
prometheus.GaugeValue,
float64(memoryStatusEx.AvailPhys),
)
return nil
}
@@ -335,200 +413,203 @@ type memory struct {
WriteCopiesPersec float64 `perflib:"Write Copies/sec"`
}
func (c *collector) collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collectPerformanceData(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var dst []memory
if err := perflib.UnmarshalObject(ctx.PerfObjects["Memory"], &dst, c.logger); err != nil {
if err := perflib.UnmarshalObject(ctx.PerfObjects["Memory"], &dst, logger); err != nil {
return err
}
ch <- prometheus.MustNewConstMetric(
c.AvailableBytes,
c.availableBytes,
prometheus.GaugeValue,
dst[0].AvailableBytes,
)
ch <- prometheus.MustNewConstMetric(
c.CacheBytes,
c.cacheBytes,
prometheus.GaugeValue,
dst[0].CacheBytes,
)
ch <- prometheus.MustNewConstMetric(
c.CacheBytesPeak,
c.cacheBytesPeak,
prometheus.GaugeValue,
dst[0].CacheBytesPeak,
)
ch <- prometheus.MustNewConstMetric(
c.CacheFaultsTotal,
c.cacheFaultsTotal,
prometheus.CounterValue,
dst[0].CacheFaultsPersec,
)
ch <- prometheus.MustNewConstMetric(
c.CommitLimit,
c.commitLimit,
prometheus.GaugeValue,
dst[0].CommitLimit,
)
ch <- prometheus.MustNewConstMetric(
c.CommittedBytes,
c.committedBytes,
prometheus.GaugeValue,
dst[0].CommittedBytes,
)
ch <- prometheus.MustNewConstMetric(
c.DemandZeroFaultsTotal,
c.demandZeroFaultsTotal,
prometheus.CounterValue,
dst[0].DemandZeroFaultsPersec,
)
ch <- prometheus.MustNewConstMetric(
c.FreeAndZeroPageListBytes,
c.freeAndZeroPageListBytes,
prometheus.GaugeValue,
dst[0].FreeAndZeroPageListBytes,
)
ch <- prometheus.MustNewConstMetric(
c.FreeSystemPageTableEntries,
c.freeSystemPageTableEntries,
prometheus.GaugeValue,
dst[0].FreeSystemPageTableEntries,
)
ch <- prometheus.MustNewConstMetric(
c.ModifiedPageListBytes,
c.modifiedPageListBytes,
prometheus.GaugeValue,
dst[0].ModifiedPageListBytes,
)
ch <- prometheus.MustNewConstMetric(
c.PageFaultsTotal,
c.pageFaultsTotal,
prometheus.CounterValue,
dst[0].PageFaultsPersec,
)
ch <- prometheus.MustNewConstMetric(
c.SwapPageReadsTotal,
c.swapPageReadsTotal,
prometheus.CounterValue,
dst[0].PageReadsPersec,
)
ch <- prometheus.MustNewConstMetric(
c.SwapPagesReadTotal,
c.swapPagesReadTotal,
prometheus.CounterValue,
dst[0].PagesInputPersec,
)
ch <- prometheus.MustNewConstMetric(
c.SwapPagesWrittenTotal,
c.swapPagesWrittenTotal,
prometheus.CounterValue,
dst[0].PagesOutputPersec,
)
ch <- prometheus.MustNewConstMetric(
c.SwapPageOperationsTotal,
c.swapPageOperationsTotal,
prometheus.CounterValue,
dst[0].PagesPersec,
)
ch <- prometheus.MustNewConstMetric(
c.SwapPageWritesTotal,
c.swapPageWritesTotal,
prometheus.CounterValue,
dst[0].PageWritesPersec,
)
ch <- prometheus.MustNewConstMetric(
c.PoolNonpagedAllocsTotal,
c.poolNonPagedAllocationsTotal,
prometheus.GaugeValue,
dst[0].PoolNonpagedAllocs,
)
ch <- prometheus.MustNewConstMetric(
c.PoolNonpagedBytes,
c.poolNonPagedBytes,
prometheus.GaugeValue,
dst[0].PoolNonpagedBytes,
)
ch <- prometheus.MustNewConstMetric(
c.PoolPagedAllocsTotal,
c.poolPagedAllocationsTotal,
prometheus.CounterValue,
dst[0].PoolPagedAllocs,
)
ch <- prometheus.MustNewConstMetric(
c.PoolPagedBytes,
c.poolPagedBytes,
prometheus.GaugeValue,
dst[0].PoolPagedBytes,
)
ch <- prometheus.MustNewConstMetric(
c.PoolPagedResidentBytes,
c.poolPagedResidentBytes,
prometheus.GaugeValue,
dst[0].PoolPagedResidentBytes,
)
ch <- prometheus.MustNewConstMetric(
c.StandbyCacheCoreBytes,
c.standbyCacheCoreBytes,
prometheus.GaugeValue,
dst[0].StandbyCacheCoreBytes,
)
ch <- prometheus.MustNewConstMetric(
c.StandbyCacheNormalPriorityBytes,
c.standbyCacheNormalPriorityBytes,
prometheus.GaugeValue,
dst[0].StandbyCacheNormalPriorityBytes,
)
ch <- prometheus.MustNewConstMetric(
c.StandbyCacheReserveBytes,
c.standbyCacheReserveBytes,
prometheus.GaugeValue,
dst[0].StandbyCacheReserveBytes,
)
ch <- prometheus.MustNewConstMetric(
c.SystemCacheResidentBytes,
c.systemCacheResidentBytes,
prometheus.GaugeValue,
dst[0].SystemCacheResidentBytes,
)
ch <- prometheus.MustNewConstMetric(
c.SystemCodeResidentBytes,
c.systemCodeResidentBytes,
prometheus.GaugeValue,
dst[0].SystemCodeResidentBytes,
)
ch <- prometheus.MustNewConstMetric(
c.SystemCodeTotalBytes,
c.systemCodeTotalBytes,
prometheus.GaugeValue,
dst[0].SystemCodeTotalBytes,
)
ch <- prometheus.MustNewConstMetric(
c.SystemDriverResidentBytes,
c.systemDriverResidentBytes,
prometheus.GaugeValue,
dst[0].SystemDriverResidentBytes,
)
ch <- prometheus.MustNewConstMetric(
c.SystemDriverTotalBytes,
c.systemDriverTotalBytes,
prometheus.GaugeValue,
dst[0].SystemDriverTotalBytes,
)
ch <- prometheus.MustNewConstMetric(
c.TransitionFaultsTotal,
c.transitionFaultsTotal,
prometheus.CounterValue,
dst[0].TransitionFaultsPersec,
)
ch <- prometheus.MustNewConstMetric(
c.TransitionPagesRepurposedTotal,
c.transitionPagesRepurposedTotal,
prometheus.CounterValue,
dst[0].TransitionPagesRePurposedPersec,
)
ch <- prometheus.MustNewConstMetric(
c.WriteCopiesTotal,
c.writeCopiesTotal,
prometheus.CounterValue,
dst[0].WriteCopiesPersec,
)

View File

@@ -0,0 +1,302 @@
package mscluster
import (
"errors"
"fmt"
"log/slog"
"slices"
"strings"
"github.com/alecthomas/kingpin/v2"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const Name = "mscluster"
type Config struct {
CollectorsEnabled []string `yaml:"collectors_enabled"`
}
var ConfigDefaults = Config{
CollectorsEnabled: []string{
"cluster",
"network",
"node",
"resource",
"resourcegroup",
},
}
// A Collector is a Prometheus Collector for WMI MSCluster_Cluster metrics.
type Collector struct {
config Config
wmiClient *wmi.Client
// cluster
clusterAddEvictDelay *prometheus.Desc
clusterAdminAccessPoint *prometheus.Desc
clusterAutoAssignNodeSite *prometheus.Desc
clusterAutoBalancerLevel *prometheus.Desc
clusterAutoBalancerMode *prometheus.Desc
clusterBackupInProgress *prometheus.Desc
clusterBlockCacheSize *prometheus.Desc
clusterClusSvcHangTimeout *prometheus.Desc
clusterClusSvcRegroupOpeningTimeout *prometheus.Desc
clusterClusSvcRegroupPruningTimeout *prometheus.Desc
clusterClusSvcRegroupStageTimeout *prometheus.Desc
clusterClusSvcRegroupTickInMilliseconds *prometheus.Desc
clusterClusterEnforcedAntiAffinity *prometheus.Desc
clusterClusterFunctionalLevel *prometheus.Desc
clusterClusterGroupWaitDelay *prometheus.Desc
clusterClusterLogLevel *prometheus.Desc
clusterClusterLogSize *prometheus.Desc
clusterClusterUpgradeVersion *prometheus.Desc
clusterCrossSiteDelay *prometheus.Desc
clusterCrossSiteThreshold *prometheus.Desc
clusterCrossSubnetDelay *prometheus.Desc
clusterCrossSubnetThreshold *prometheus.Desc
clusterCsvBalancer *prometheus.Desc
clusterDatabaseReadWriteMode *prometheus.Desc
clusterDefaultNetworkRole *prometheus.Desc
clusterDetectedCloudPlatform *prometheus.Desc
clusterDetectManagedEvents *prometheus.Desc
clusterDetectManagedEventsThreshold *prometheus.Desc
clusterDisableGroupPreferredOwnerRandomization *prometheus.Desc
clusterDrainOnShutdown *prometheus.Desc
clusterDynamicQuorumEnabled *prometheus.Desc
clusterEnableSharedVolumes *prometheus.Desc
clusterFixQuorum *prometheus.Desc
clusterGracePeriodEnabled *prometheus.Desc
clusterGracePeriodTimeout *prometheus.Desc
clusterGroupDependencyTimeout *prometheus.Desc
clusterHangRecoveryAction *prometheus.Desc
clusterIgnorePersistentStateOnStartup *prometheus.Desc
clusterLogResourceControls *prometheus.Desc
clusterLowerQuorumPriorityNodeId *prometheus.Desc
clusterMaxNumberOfNodes *prometheus.Desc
clusterMessageBufferLength *prometheus.Desc
clusterMinimumNeverPreemptPriority *prometheus.Desc
clusterMinimumPreemptorPriority *prometheus.Desc
clusterNetftIPSecEnabled *prometheus.Desc
clusterPlacementOptions *prometheus.Desc
clusterPlumbAllCrossSubnetRoutes *prometheus.Desc
clusterPreventQuorum *prometheus.Desc
clusterQuarantineDuration *prometheus.Desc
clusterQuarantineThreshold *prometheus.Desc
clusterQuorumArbitrationTimeMax *prometheus.Desc
clusterQuorumArbitrationTimeMin *prometheus.Desc
clusterQuorumLogFileSize *prometheus.Desc
clusterQuorumTypeValue *prometheus.Desc
clusterRequestReplyTimeout *prometheus.Desc
clusterResiliencyDefaultPeriod *prometheus.Desc
clusterResiliencyLevel *prometheus.Desc
clusterResourceDllDeadlockPeriod *prometheus.Desc
clusterRootMemoryReserved *prometheus.Desc
clusterRouteHistoryLength *prometheus.Desc
clusterS2DBusTypes *prometheus.Desc
clusterS2DCacheDesiredState *prometheus.Desc
clusterS2DCacheFlashReservePercent *prometheus.Desc
clusterS2DCachePageSizeKBytes *prometheus.Desc
clusterS2DEnabled *prometheus.Desc
clusterS2DIOLatencyThreshold *prometheus.Desc
clusterS2DOptimizations *prometheus.Desc
clusterSameSubnetDelay *prometheus.Desc
clusterSameSubnetThreshold *prometheus.Desc
clusterSecurityLevel *prometheus.Desc
clusterSecurityLevelForStorage *prometheus.Desc
clusterSharedVolumeVssWriterOperationTimeout *prometheus.Desc
clusterShutdownTimeoutInMinutes *prometheus.Desc
clusterUseClientAccessNetworksForSharedVolumes *prometheus.Desc
clusterWitnessDatabaseWriteTimeout *prometheus.Desc
clusterWitnessDynamicWeight *prometheus.Desc
clusterWitnessRestartInterval *prometheus.Desc
// network
networkCharacteristics *prometheus.Desc
networkFlags *prometheus.Desc
networkMetric *prometheus.Desc
networkRole *prometheus.Desc
networkState *prometheus.Desc
// node
nodeBuildNumber *prometheus.Desc
nodeCharacteristics *prometheus.Desc
nodeDetectedCloudPlatform *prometheus.Desc
nodeDynamicWeight *prometheus.Desc
nodeFlags *prometheus.Desc
nodeMajorVersion *prometheus.Desc
nodeMinorVersion *prometheus.Desc
nodeNeedsPreventQuorum *prometheus.Desc
nodeNodeDrainStatus *prometheus.Desc
nodeNodeHighestVersion *prometheus.Desc
nodeNodeLowestVersion *prometheus.Desc
nodeNodeWeight *prometheus.Desc
nodeState *prometheus.Desc
nodeStatusInformation *prometheus.Desc
resourceCharacteristics *prometheus.Desc
resourceDeadlockTimeout *prometheus.Desc
resourceEmbeddedFailureAction *prometheus.Desc
resourceFlags *prometheus.Desc
resourceIsAlivePollInterval *prometheus.Desc
resourceLooksAlivePollInterval *prometheus.Desc
resourceMonitorProcessId *prometheus.Desc
resourceOwnerNode *prometheus.Desc
resourcePendingTimeout *prometheus.Desc
resourceResourceClass *prometheus.Desc
resourceRestartAction *prometheus.Desc
resourceRestartDelay *prometheus.Desc
resourceRestartPeriod *prometheus.Desc
resourceRestartThreshold *prometheus.Desc
resourceRetryPeriodOnFailure *prometheus.Desc
resourceState *prometheus.Desc
resourceSubClass *prometheus.Desc
// ResourceGroup
resourceGroupAutoFailbackType *prometheus.Desc
resourceGroupCharacteristics *prometheus.Desc
resourceGroupColdStartSetting *prometheus.Desc
resourceGroupDefaultOwner *prometheus.Desc
resourceGroupFailbackWindowEnd *prometheus.Desc
resourceGroupFailbackWindowStart *prometheus.Desc
resourceGroupFailOverPeriod *prometheus.Desc
resourceGroupFailOverThreshold *prometheus.Desc
resourceGroupFlags *prometheus.Desc
resourceGroupGroupType *prometheus.Desc
resourceGroupOwnerNode *prometheus.Desc
resourceGroupPriority *prometheus.Desc
resourceGroupResiliencyPeriod *prometheus.Desc
resourceGroupState *prometheus.Desc
}
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
if config.CollectorsEnabled == nil {
config.CollectorsEnabled = ConfigDefaults.CollectorsEnabled
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(app *kingpin.Application) *Collector {
c := &Collector{
config: ConfigDefaults,
}
c.config.CollectorsEnabled = make([]string, 0)
var collectorsEnabled string
app.Flag(
"collectors.mscluster.enabled",
"Comma-separated list of collectors to use.",
).Default(strings.Join(ConfigDefaults.CollectorsEnabled, ",")).StringVar(&collectorsEnabled)
app.Action(func(*kingpin.ParseContext) error {
c.config.CollectorsEnabled = strings.Split(collectorsEnabled, ",")
return nil
})
return c
}
func (c *Collector) GetName() string {
return Name
}
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{"Memory"}, nil
}
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, wmiClient *wmi.Client) error {
if len(c.config.CollectorsEnabled) == 0 {
return nil
}
if wmiClient == nil || wmiClient.SWbemServicesClient == nil {
return errors.New("wmiClient or SWbemServicesClient is nil")
}
c.wmiClient = wmiClient
if slices.Contains(c.config.CollectorsEnabled, "cluster") {
c.buildCluster()
}
if slices.Contains(c.config.CollectorsEnabled, "network") {
c.buildNetwork()
}
if slices.Contains(c.config.CollectorsEnabled, "node") {
c.buildNode()
}
if slices.Contains(c.config.CollectorsEnabled, "resource") {
c.buildResource()
}
if slices.Contains(c.config.CollectorsEnabled, "resourcegroup") {
c.buildResourceGroup()
}
return nil
}
// Collect sends the metric values for each metric
// to the provided prometheus Metric channel.
func (c *Collector) Collect(_ *types.ScrapeContext, _ *slog.Logger, ch chan<- prometheus.Metric) error {
if len(c.config.CollectorsEnabled) == 0 {
return nil
}
var (
err error
errs []error
nodeNames []string
)
if slices.Contains(c.config.CollectorsEnabled, "cluster") {
if err = c.collectCluster(ch); err != nil {
errs = append(errs, fmt.Errorf("failed to collect cluster metrics: %w", err))
}
}
if slices.Contains(c.config.CollectorsEnabled, "network") {
if err = c.collectNetwork(ch); err != nil {
errs = append(errs, fmt.Errorf("failed to collect network metrics: %w", err))
}
}
if slices.Contains(c.config.CollectorsEnabled, "node") {
if nodeNames, err = c.collectNode(ch); err != nil {
errs = append(errs, fmt.Errorf("failed to collect node metrics: %w", err))
}
}
if slices.Contains(c.config.CollectorsEnabled, "resource") {
if err = c.collectResource(ch, nodeNames); err != nil {
errs = append(errs, fmt.Errorf("failed to collect resource metrics: %w", err))
}
}
if slices.Contains(c.config.CollectorsEnabled, "resourcegroup") {
if err = c.collectResourceGroup(ch, nodeNames); err != nil {
errs = append(errs, fmt.Errorf("failed to collect resource group metrics: %w", err))
}
}
return errors.Join(errs...)
}

View File

@@ -0,0 +1,102 @@
package mscluster
import (
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus/client_golang/prometheus"
)
const nameNetwork = Name + "_network"
// msClusterNetwork represents the MSCluster_Network WMI class
// - https://docs.microsoft.com/en-us/previous-versions/windows/desktop/cluswmi/mscluster-network
type msClusterNetwork struct {
Name string
Characteristics uint
Flags uint
Metric uint
Role uint
State uint
}
func (c *Collector) buildNetwork() {
c.networkCharacteristics = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNetwork, "characteristics"),
"Provides the characteristics of the network.",
[]string{"name"},
nil,
)
c.networkFlags = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNetwork, "flags"),
"Provides access to the flags set for the node. ",
[]string{"name"},
nil,
)
c.networkMetric = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNetwork, "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.",
[]string{"name"},
nil,
)
c.networkRole = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNetwork, "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 ",
[]string{"name"},
nil,
)
c.networkState = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNetwork, "state"),
"Provides the current state of the network. 1-1: Unknown; 0: Unavailable; 1: Down; 2: Partitioned; 3: Up",
[]string{"name"},
nil,
)
}
// Collect sends the metric values for each metric
// to the provided prometheus metric channel.
func (c *Collector) collectNetwork(ch chan<- prometheus.Metric) error {
var dst []msClusterNetwork
if err := c.wmiClient.Query("SELECT * FROM MSCluster_Network", &dst, nil, "root/MSCluster"); err != nil {
return err
}
for _, v := range dst {
ch <- prometheus.MustNewConstMetric(
c.networkCharacteristics,
prometheus.GaugeValue,
float64(v.Characteristics),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.networkFlags,
prometheus.GaugeValue,
float64(v.Flags),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.networkMetric,
prometheus.GaugeValue,
float64(v.Metric),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.networkRole,
prometheus.GaugeValue,
float64(v.Role),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.networkState,
prometheus.GaugeValue,
float64(v.State),
v.Name,
)
}
return nil
}

View File

@@ -1,156 +1,15 @@
package mscluster_node
package mscluster
import (
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus-community/windows_exporter/pkg/wmi"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/prometheus/client_golang/prometheus"
)
const Name = "mscluster_node"
const nameNode = Name + "_node"
type Config struct{}
var ConfigDefaults = Config{}
// Variable used by mscluster_resource and mscluster_resourcegroup
var NodeName []string
// A collector is a Prometheus collector for WMI MSCluster_Node metrics
type collector struct {
logger log.Logger
BuildNumber *prometheus.Desc
Characteristics *prometheus.Desc
DetectedCloudPlatform *prometheus.Desc
DynamicWeight *prometheus.Desc
Flags *prometheus.Desc
MajorVersion *prometheus.Desc
MinorVersion *prometheus.Desc
NeedsPreventQuorum *prometheus.Desc
NodeDrainStatus *prometheus.Desc
NodeHighestVersion *prometheus.Desc
NodeLowestVersion *prometheus.Desc
NodeWeight *prometheus.Desc
State *prometheus.Desc
StatusInformation *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
}
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{"Memory"}, nil
}
func (c *collector) Build() error {
c.BuildNumber = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "build_number"),
"Provides access to the node's BuildNumber property.",
[]string{"name"},
nil,
)
c.Characteristics = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "characteristics"),
"Provides access to the characteristics set for the node.",
[]string{"name"},
nil,
)
c.DetectedCloudPlatform = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "detected_cloud_platform"),
"(DetectedCloudPlatform)",
[]string{"name"},
nil,
)
c.DynamicWeight = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "dynamic_weight"),
"The dynamic vote weight of the node adjusted by dynamic quorum feature.",
[]string{"name"},
nil,
)
c.Flags = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "flags"),
"Provides access to the flags set for the node.",
[]string{"name"},
nil,
)
c.MajorVersion = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "major_version"),
"Provides access to the node's MajorVersion property, which specifies the major portion of the Windows version installed.",
[]string{"name"},
nil,
)
c.MinorVersion = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "minor_version"),
"Provides access to the node's MinorVersion property, which specifies the minor portion of the Windows version installed.",
[]string{"name"},
nil,
)
c.NeedsPreventQuorum = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "needs_prevent_quorum"),
"Whether the cluster service on that node should be started with prevent quorum flag.",
[]string{"name"},
nil,
)
c.NodeDrainStatus = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "node_drain_status"),
"The current node drain status of a node. 0: Not Initiated; 1: In Progress; 2: Completed; 3: Failed",
[]string{"name"},
nil,
)
c.NodeHighestVersion = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "node_highest_version"),
"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.",
[]string{"name"},
nil,
)
c.NodeLowestVersion = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "node_lowest_version"),
"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.",
[]string{"name"},
nil,
)
c.NodeWeight = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "node_weight"),
"The vote weight of the node.",
[]string{"name"},
nil,
)
c.State = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "state"),
"Returns the current state of a node. -1: Unknown; 0: Up; 1: Down; 2: Paused; 3: Joining",
[]string{"name"},
nil,
)
c.StatusInformation = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "status_information"),
"The isolation or quarantine status of the node.",
[]string{"name"},
nil,
)
return nil
}
// MSCluster_Node docs:
// msClusterNode represents the MSCluster_Node WMI class
// - https://docs.microsoft.com/en-us/previous-versions/windows/desktop/cluswmi/mscluster-node
type MSCluster_Node struct {
type msClusterNode struct {
Name string
BuildNumber uint
@@ -169,119 +28,205 @@ type MSCluster_Node struct {
StatusInformation uint
}
func (c *Collector) buildNode() {
c.nodeBuildNumber = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNode, "build_number"),
"Provides access to the node's BuildNumber property.",
[]string{"name"},
nil,
)
c.nodeCharacteristics = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNode, "characteristics"),
"Provides access to the characteristics set for the node.",
[]string{"name"},
nil,
)
c.nodeDetectedCloudPlatform = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNode, "detected_cloud_platform"),
"(DetectedCloudPlatform)",
[]string{"name"},
nil,
)
c.nodeDynamicWeight = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNode, "dynamic_weight"),
"The dynamic vote weight of the node adjusted by dynamic quorum feature.",
[]string{"name"},
nil,
)
c.nodeFlags = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNode, "flags"),
"Provides access to the flags set for the node.",
[]string{"name"},
nil,
)
c.nodeMajorVersion = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNode, "major_version"),
"Provides access to the node's MajorVersion property, which specifies the major portion of the Windows version installed.",
[]string{"name"},
nil,
)
c.nodeMinorVersion = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNode, "minor_version"),
"Provides access to the node's MinorVersion property, which specifies the minor portion of the Windows version installed.",
[]string{"name"},
nil,
)
c.nodeNeedsPreventQuorum = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNode, "needs_prevent_quorum"),
"Whether the cluster service on that node should be started with prevent quorum flag.",
[]string{"name"},
nil,
)
c.nodeNodeDrainStatus = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNode, "node_drain_status"),
"The current node drain status of a node. 0: Not Initiated; 1: In Progress; 2: Completed; 3: Failed",
[]string{"name"},
nil,
)
c.nodeNodeHighestVersion = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNode, "node_highest_version"),
"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.",
[]string{"name"},
nil,
)
c.nodeNodeLowestVersion = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNode, "node_lowest_version"),
"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.",
[]string{"name"},
nil,
)
c.nodeNodeWeight = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNode, "node_weight"),
"The vote weight of the node.",
[]string{"name"},
nil,
)
c.nodeState = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNode, "state"),
"Returns the current state of a node. -1: Unknown; 0: Up; 1: Down; 2: Paused; 3: Joining",
[]string{"name"},
nil,
)
c.nodeStatusInformation = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameNode, "status_information"),
"The isolation or quarantine status of the node.",
[]string{"name"},
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 {
var dst []MSCluster_Node
q := wmi.QueryAll(&dst, c.logger)
if err := wmi.QueryNamespace(q, &dst, "root/MSCluster"); err != nil {
return err
func (c *Collector) collectNode(ch chan<- prometheus.Metric) ([]string, error) {
var dst []msClusterNode
if err := c.wmiClient.Query("SELECT * FROM MSCluster_Node", &dst, nil, "root/MSCluster"); err != nil {
return nil, err
}
NodeName = []string{}
nodeNames := make([]string, 0, len(dst))
for _, v := range dst {
ch <- prometheus.MustNewConstMetric(
c.BuildNumber,
c.nodeBuildNumber,
prometheus.GaugeValue,
float64(v.BuildNumber),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.Characteristics,
c.nodeCharacteristics,
prometheus.GaugeValue,
float64(v.Characteristics),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.DetectedCloudPlatform,
c.nodeDetectedCloudPlatform,
prometheus.GaugeValue,
float64(v.DetectedCloudPlatform),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.DynamicWeight,
c.nodeDynamicWeight,
prometheus.GaugeValue,
float64(v.DynamicWeight),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.Flags,
c.nodeFlags,
prometheus.GaugeValue,
float64(v.Flags),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.MajorVersion,
c.nodeMajorVersion,
prometheus.GaugeValue,
float64(v.MajorVersion),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.MinorVersion,
c.nodeMinorVersion,
prometheus.GaugeValue,
float64(v.MinorVersion),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.NeedsPreventQuorum,
c.nodeNeedsPreventQuorum,
prometheus.GaugeValue,
float64(v.NeedsPreventQuorum),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.NodeDrainStatus,
c.nodeNodeDrainStatus,
prometheus.GaugeValue,
float64(v.NodeDrainStatus),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.NodeHighestVersion,
c.nodeNodeHighestVersion,
prometheus.GaugeValue,
float64(v.NodeHighestVersion),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.NodeLowestVersion,
c.nodeNodeLowestVersion,
prometheus.GaugeValue,
float64(v.NodeLowestVersion),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.NodeWeight,
c.nodeNodeWeight,
prometheus.GaugeValue,
float64(v.NodeWeight),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.State,
c.nodeState,
prometheus.GaugeValue,
float64(v.State),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.StatusInformation,
c.nodeStatusInformation,
prometheus.GaugeValue,
float64(v.StatusInformation),
v.Name,
)
NodeName = append(NodeName, v.Name)
nodeNames = append(nodeNames, v.Name)
}
return nil
return nodeNames, nil
}

View File

@@ -1,181 +1,15 @@
package mscluster_resource
package mscluster
import (
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_node"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus-community/windows_exporter/pkg/wmi"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/prometheus/client_golang/prometheus"
)
const Name = "mscluster_resource"
const nameResource = Name + "_resource"
type Config struct{}
var ConfigDefaults = Config{}
// A collector is a Prometheus collector for WMI MSCluster_Resource metrics
type collector struct {
logger log.Logger
Characteristics *prometheus.Desc
DeadlockTimeout *prometheus.Desc
EmbeddedFailureAction *prometheus.Desc
Flags *prometheus.Desc
IsAlivePollInterval *prometheus.Desc
LooksAlivePollInterval *prometheus.Desc
MonitorProcessId *prometheus.Desc
OwnerNode *prometheus.Desc
PendingTimeout *prometheus.Desc
ResourceClass *prometheus.Desc
RestartAction *prometheus.Desc
RestartDelay *prometheus.Desc
RestartPeriod *prometheus.Desc
RestartThreshold *prometheus.Desc
RetryPeriodOnFailure *prometheus.Desc
State *prometheus.Desc
Subclass *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
}
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{"Memory"}, nil
}
func (c *collector) Build() error {
c.Characteristics = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "characteristics"),
"Provides the characteristics of the object.",
[]string{"type", "owner_group", "name"},
nil,
)
c.DeadlockTimeout = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "deadlock_timeout"),
"Indicates the length of time to wait, in milliseconds, before declaring a deadlock in any call into a resource.",
[]string{"type", "owner_group", "name"},
nil,
)
c.EmbeddedFailureAction = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "embedded_failure_action"),
"The time, in milliseconds, that a resource should remain in a failed state before the Cluster service attempts to restart it.",
[]string{"type", "owner_group", "name"},
nil,
)
c.Flags = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "flags"),
"Provides access to the flags set for the object.",
[]string{"type", "owner_group", "name"},
nil,
)
c.IsAlivePollInterval = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "is_alive_poll_interval"),
"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.",
[]string{"type", "owner_group", "name"},
nil,
)
c.LooksAlivePollInterval = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "looks_alive_poll_interval"),
"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.",
[]string{"type", "owner_group", "name"},
nil,
)
c.MonitorProcessId = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "monitor_process_id"),
"Provides the process ID of the resource host service that is currently hosting the resource.",
[]string{"type", "owner_group", "name"},
nil,
)
c.OwnerNode = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "owner_node"),
"The node hosting the resource. 0: Not hosted; 1: Hosted",
[]string{"type", "owner_group", "node_name", "name"},
nil,
)
c.OwnerNode = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "owner_node"),
"The node hosting the resource. 0: Not hosted; 1: Hosted",
[]string{"type", "owner_group", "node_name", "name"},
nil,
)
c.PendingTimeout = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "pending_timeout"),
"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.",
[]string{"type", "owner_group", "name"},
nil,
)
c.ResourceClass = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "resource_class"),
"Gets or sets the resource class of a resource. 0: Unknown; 1: Storage; 2: Network; 32768: Unknown ",
[]string{"type", "owner_group", "name"},
nil,
)
c.RestartAction = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "restart_action"),
"Provides access to the resource's RestartAction property, which is the action to be taken by the Cluster Service if the resource fails.",
[]string{"type", "owner_group", "name"},
nil,
)
c.RestartDelay = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "restart_delay"),
"Indicates the time delay before a failed resource is restarted.",
[]string{"type", "owner_group", "name"},
nil,
)
c.RestartPeriod = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "restart_period"),
"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.",
[]string{"type", "owner_group", "name"},
nil,
)
c.RestartThreshold = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "restart_threshold"),
"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.",
[]string{"type", "owner_group", "name"},
nil,
)
c.RetryPeriodOnFailure = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "retry_period_on_failure"),
"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.",
[]string{"type", "owner_group", "name"},
nil,
)
c.State = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, 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 ",
[]string{"type", "owner_group", "name"},
nil,
)
c.Subclass = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "subclass"),
"Provides the list of references to nodes that can be the owner of this resource.",
[]string{"type", "owner_group", "name"},
nil,
)
return nil
}
// MSCluster_Resource docs:
// msClusterResource represents the MSCluster_Resource WMI class
// - https://docs.microsoft.com/en-us/previous-versions/windows/desktop/cluswmi/mscluster-resource
type MSCluster_Resource struct {
type msClusterResource struct {
Name string
Type string
OwnerGroup string
@@ -199,139 +33,247 @@ type MSCluster_Resource struct {
Subclass uint
}
func (c *Collector) buildResource() {
c.resourceCharacteristics = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "characteristics"),
"Provides the characteristics of the object.",
[]string{"type", "owner_group", "name"},
nil,
)
c.resourceDeadlockTimeout = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "deadlock_timeout"),
"Indicates the length of time to wait, in milliseconds, before declaring a deadlock in any call into a resource.",
[]string{"type", "owner_group", "name"},
nil,
)
c.resourceEmbeddedFailureAction = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "embedded_failure_action"),
"The time, in milliseconds, that a resource should remain in a failed state before the Cluster service attempts to restart it.",
[]string{"type", "owner_group", "name"},
nil,
)
c.resourceFlags = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "flags"),
"Provides access to the flags set for the object.",
[]string{"type", "owner_group", "name"},
nil,
)
c.resourceIsAlivePollInterval = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "is_alive_poll_interval"),
"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.",
[]string{"type", "owner_group", "name"},
nil,
)
c.resourceLooksAlivePollInterval = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "looks_alive_poll_interval"),
"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.",
[]string{"type", "owner_group", "name"},
nil,
)
c.resourceMonitorProcessId = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "monitor_process_id"),
"Provides the process ID of the resource host service that is currently hosting the resource.",
[]string{"type", "owner_group", "name"},
nil,
)
c.resourceOwnerNode = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "owner_node"),
"The node hosting the resource. 0: Not hosted; 1: Hosted",
[]string{"type", "owner_group", "node_name", "name"},
nil,
)
c.resourceOwnerNode = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "owner_node"),
"The node hosting the resource. 0: Not hosted; 1: Hosted",
[]string{"type", "owner_group", "node_name", "name"},
nil,
)
c.resourcePendingTimeout = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "pending_timeout"),
"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.",
[]string{"type", "owner_group", "name"},
nil,
)
c.resourceResourceClass = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "resource_class"),
"Gets or sets the resource class of a resource. 0: Unknown; 1: Storage; 2: Network; 32768: Unknown ",
[]string{"type", "owner_group", "name"},
nil,
)
c.resourceRestartAction = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "restart_action"),
"Provides access to the resource's RestartAction property, which is the action to be taken by the Cluster Service if the resource fails.",
[]string{"type", "owner_group", "name"},
nil,
)
c.resourceRestartDelay = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "restart_delay"),
"Indicates the time delay before a failed resource is restarted.",
[]string{"type", "owner_group", "name"},
nil,
)
c.resourceRestartPeriod = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "restart_period"),
"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.",
[]string{"type", "owner_group", "name"},
nil,
)
c.resourceRestartThreshold = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "restart_threshold"),
"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.",
[]string{"type", "owner_group", "name"},
nil,
)
c.resourceRetryPeriodOnFailure = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "retry_period_on_failure"),
"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.",
[]string{"type", "owner_group", "name"},
nil,
)
c.resourceState = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "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 ",
[]string{"type", "owner_group", "name"},
nil,
)
c.resourceSubClass = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResource, "subclass"),
"Provides the list of references to nodes that can be the owner of this resource.",
[]string{"type", "owner_group", "name"},
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 {
var dst []MSCluster_Resource
q := wmi.QueryAll(&dst, c.logger)
if err := wmi.QueryNamespace(q, &dst, "root/MSCluster"); err != nil {
func (c *Collector) collectResource(ch chan<- prometheus.Metric, nodeNames []string) error {
var dst []msClusterResource
if err := c.wmiClient.Query("SELECT * FROM MSCluster_Resource", &dst, nil, "root/MSCluster"); err != nil {
return err
}
for _, v := range dst {
ch <- prometheus.MustNewConstMetric(
c.Characteristics,
c.resourceCharacteristics,
prometheus.GaugeValue,
float64(v.Characteristics),
v.Type, v.OwnerGroup, v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.DeadlockTimeout,
c.resourceDeadlockTimeout,
prometheus.GaugeValue,
float64(v.DeadlockTimeout),
v.Type, v.OwnerGroup, v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.EmbeddedFailureAction,
c.resourceEmbeddedFailureAction,
prometheus.GaugeValue,
float64(v.EmbeddedFailureAction),
v.Type, v.OwnerGroup, v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.Flags,
c.resourceFlags,
prometheus.GaugeValue,
float64(v.Flags),
v.Type, v.OwnerGroup, v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.IsAlivePollInterval,
c.resourceIsAlivePollInterval,
prometheus.GaugeValue,
float64(v.IsAlivePollInterval),
v.Type, v.OwnerGroup, v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.LooksAlivePollInterval,
c.resourceLooksAlivePollInterval,
prometheus.GaugeValue,
float64(v.LooksAlivePollInterval),
v.Type, v.OwnerGroup, v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.MonitorProcessId,
c.resourceMonitorProcessId,
prometheus.GaugeValue,
float64(v.MonitorProcessId),
v.Type, v.OwnerGroup, v.Name,
)
if mscluster_node.NodeName != nil {
for _, node_name := range mscluster_node.NodeName {
isCurrentState := 0.0
if v.OwnerNode == node_name {
isCurrentState = 1.0
}
ch <- prometheus.MustNewConstMetric(
c.OwnerNode,
prometheus.GaugeValue,
isCurrentState,
v.Type, v.OwnerGroup, node_name, v.Name,
)
for _, nodeName := range nodeNames {
isCurrentState := 0.0
if v.OwnerNode == nodeName {
isCurrentState = 1.0
}
ch <- prometheus.MustNewConstMetric(
c.resourceOwnerNode,
prometheus.GaugeValue,
isCurrentState,
v.Type, v.OwnerGroup, nodeName, v.Name,
)
}
ch <- prometheus.MustNewConstMetric(
c.PendingTimeout,
c.resourcePendingTimeout,
prometheus.GaugeValue,
float64(v.PendingTimeout),
v.Type, v.OwnerGroup, v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.ResourceClass,
c.resourceResourceClass,
prometheus.GaugeValue,
float64(v.ResourceClass),
v.Type, v.OwnerGroup, v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.RestartAction,
c.resourceRestartAction,
prometheus.GaugeValue,
float64(v.RestartAction),
v.Type, v.OwnerGroup, v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.RestartDelay,
c.resourceRestartDelay,
prometheus.GaugeValue,
float64(v.RestartDelay),
v.Type, v.OwnerGroup, v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.RestartPeriod,
c.resourceRestartPeriod,
prometheus.GaugeValue,
float64(v.RestartPeriod),
v.Type, v.OwnerGroup, v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.RestartThreshold,
c.resourceRestartThreshold,
prometheus.GaugeValue,
float64(v.RestartThreshold),
v.Type, v.OwnerGroup, v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.RetryPeriodOnFailure,
c.resourceRetryPeriodOnFailure,
prometheus.GaugeValue,
float64(v.RetryPeriodOnFailure),
v.Type, v.OwnerGroup, v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.State,
c.resourceState,
prometheus.GaugeValue,
float64(v.State),
v.Type, v.OwnerGroup, v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.Subclass,
c.resourceSubClass,
prometheus.GaugeValue,
float64(v.Subclass),
v.Type, v.OwnerGroup, v.Name,

View File

@@ -0,0 +1,240 @@
package mscluster
import (
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus/client_golang/prometheus"
)
const nameResourceGroup = Name + "_resourcegroup"
// msClusterResourceGroup represents the MSCluster_ResourceGroup WMI class
// - https://docs.microsoft.com/en-us/previous-versions/windows/desktop/cluswmi/mscluster-resourcegroup
type msClusterResourceGroup struct {
Name string
AutoFailbackType uint
Characteristics uint
ColdStartSetting uint
DefaultOwner uint
FailbackWindowEnd int
FailbackWindowStart int
FailoverPeriod uint
FailoverThreshold uint
Flags uint
GroupType uint
OwnerNode string
Priority uint
ResiliencyPeriod uint
State uint
}
func (c *Collector) buildResourceGroup() {
c.resourceGroupAutoFailbackType = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResourceGroup, "auto_failback_type"),
"Provides access to the group's AutoFailbackType property.",
[]string{"name"},
nil,
)
c.resourceGroupCharacteristics = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResourceGroup, "characteristics"),
"Provides the characteristics of the group.",
[]string{"name"},
nil,
)
c.resourceGroupColdStartSetting = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResourceGroup, "cold_start_setting"),
"Indicates whether a group can start after a cluster cold start.",
[]string{"name"},
nil,
)
c.resourceGroupDefaultOwner = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResourceGroup, "default_owner"),
"Number of the last node the resource group was activated on or explicitly moved to.",
[]string{"name"},
nil,
)
c.resourceGroupFailbackWindowEnd = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResourceGroup, "failback_window_end"),
"The FailbackWindowEnd property provides the latest time that the group can be moved back to the node identified as its preferred node.",
[]string{"name"},
nil,
)
c.resourceGroupFailbackWindowStart = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResourceGroup, "failback_window_start"),
"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.",
[]string{"name"},
nil,
)
c.resourceGroupFailOverPeriod = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResourceGroup, "failover_period"),
"The FailoverPeriod property specifies a number of hours during which a maximum number of failover attempts, specified by the FailoverThreshold property, can occur.",
[]string{"name"},
nil,
)
c.resourceGroupFailOverThreshold = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResourceGroup, "failover_threshold"),
"The FailoverThreshold property specifies the maximum number of failover attempts.",
[]string{"name"},
nil,
)
c.resourceGroupFlags = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResourceGroup, "flags"),
"Provides access to the flags set for the group. ",
[]string{"name"},
nil,
)
c.resourceGroupGroupType = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResourceGroup, "group_type"),
"The Type of the resource group.",
[]string{"name"},
nil,
)
c.resourceGroupOwnerNode = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResourceGroup, "owner_node"),
"The node hosting the resource group. 0: Not hosted; 1: Hosted",
[]string{"node_name", "name"},
nil,
)
c.resourceGroupOwnerNode = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResourceGroup, "owner_node"),
"The node hosting the resource group. 0: Not hosted; 1: Hosted",
[]string{"node_name", "name"},
nil,
)
c.resourceGroupPriority = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResourceGroup, "priority"),
"Priority value of the resource group",
[]string{"name"},
nil,
)
c.resourceGroupResiliencyPeriod = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResourceGroup, "resiliency_period"),
"The resiliency period for this group, in seconds.",
[]string{"name"},
nil,
)
c.resourceGroupState = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, nameResourceGroup, "state"),
"The current state of the resource group. -1: Unknown; 0: Online; 1: Offline; 2: Failed; 3: Partial Online; 4: Pending",
[]string{"name"},
nil,
)
}
// Collect sends the metric values for each metric
// to the provided prometheus Metric channel.
func (c *Collector) collectResourceGroup(ch chan<- prometheus.Metric, nodeNames []string) error {
var dst []msClusterResourceGroup
if err := c.wmiClient.Query("SELECT * FROM MSCluster_ResourceGroup", &dst, nil, "root/MSCluster"); err != nil {
return err
}
for _, v := range dst {
ch <- prometheus.MustNewConstMetric(
c.resourceGroupAutoFailbackType,
prometheus.GaugeValue,
float64(v.AutoFailbackType),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.resourceGroupCharacteristics,
prometheus.GaugeValue,
float64(v.Characteristics),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.resourceGroupColdStartSetting,
prometheus.GaugeValue,
float64(v.ColdStartSetting),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.resourceGroupDefaultOwner,
prometheus.GaugeValue,
float64(v.DefaultOwner),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.resourceGroupFailbackWindowEnd,
prometheus.GaugeValue,
float64(v.FailbackWindowEnd),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.resourceGroupFailbackWindowStart,
prometheus.GaugeValue,
float64(v.FailbackWindowStart),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.resourceGroupFailOverPeriod,
prometheus.GaugeValue,
float64(v.FailoverPeriod),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.resourceGroupFailOverThreshold,
prometheus.GaugeValue,
float64(v.FailoverThreshold),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.resourceGroupFlags,
prometheus.GaugeValue,
float64(v.Flags),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.resourceGroupGroupType,
prometheus.GaugeValue,
float64(v.GroupType),
v.Name,
)
for _, nodeName := range nodeNames {
isCurrentState := 0.0
if v.OwnerNode == nodeName {
isCurrentState = 1.0
}
ch <- prometheus.MustNewConstMetric(
c.resourceGroupOwnerNode,
prometheus.GaugeValue,
isCurrentState,
nodeName, v.Name,
)
}
ch <- prometheus.MustNewConstMetric(
c.resourceGroupPriority,
prometheus.GaugeValue,
float64(v.Priority),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.resourceGroupResiliencyPeriod,
prometheus.GaugeValue,
float64(v.ResiliencyPeriod),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.resourceGroupState,
prometheus.GaugeValue,
float64(v.State),
v.Name,
)
}
return nil
}

View File

@@ -1,144 +0,0 @@
package mscluster_network
import (
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus-community/windows_exporter/pkg/wmi"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/prometheus/client_golang/prometheus"
)
const Name = "mscluster_network"
type Config struct{}
var ConfigDefaults = Config{}
// A collector is a Prometheus collector for WMI MSCluster_Network metrics
type collector struct {
logger log.Logger
Characteristics *prometheus.Desc
Flags *prometheus.Desc
Metric *prometheus.Desc
Role *prometheus.Desc
State *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
}
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{"Memory"}, nil
}
func (c *collector) Build() error {
c.Characteristics = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "characteristics"),
"Provides the characteristics of the network.",
[]string{"name"},
nil,
)
c.Flags = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "flags"),
"Provides access to the flags set for the node. ",
[]string{"name"},
nil,
)
c.Metric = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, 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.",
[]string{"name"},
nil,
)
c.Role = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, 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 ",
[]string{"name"},
nil,
)
c.State = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "state"),
"Provides the current state of the network. 1-1: Unknown; 0: Unavailable; 1: Down; 2: Partitioned; 3: Up",
[]string{"name"},
nil,
)
return nil
}
// MSCluster_Network docs:
// - https://docs.microsoft.com/en-us/previous-versions/windows/desktop/cluswmi/mscluster-network
type MSCluster_Network struct {
Name string
Characteristics uint
Flags uint
Metric uint
Role uint
State uint
}
// 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 {
var dst []MSCluster_Network
q := wmi.QueryAll(&dst, c.logger)
if err := wmi.QueryNamespace(q, &dst, "root/MSCluster"); err != nil {
return err
}
for _, v := range dst {
ch <- prometheus.MustNewConstMetric(
c.Characteristics,
prometheus.GaugeValue,
float64(v.Characteristics),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.Flags,
prometheus.GaugeValue,
float64(v.Flags),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.Metric,
prometheus.GaugeValue,
float64(v.Metric),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.Role,
prometheus.GaugeValue,
float64(v.Role),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.State,
prometheus.GaugeValue,
float64(v.State),
v.Name,
)
}
return nil
}

View File

@@ -1,298 +0,0 @@
package mscluster_resourcegroup
import (
"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_node"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus-community/windows_exporter/pkg/wmi"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/prometheus/client_golang/prometheus"
)
const Name = "mscluster_resourcegroup"
type Config struct{}
var ConfigDefaults = Config{}
// A collector is a Prometheus collector for WMI MSCluster_ResourceGroup metrics
type collector struct {
logger log.Logger
AutoFailbackType *prometheus.Desc
Characteristics *prometheus.Desc
ColdStartSetting *prometheus.Desc
DefaultOwner *prometheus.Desc
FailbackWindowEnd *prometheus.Desc
FailbackWindowStart *prometheus.Desc
FailoverPeriod *prometheus.Desc
FailoverThreshold *prometheus.Desc
FaultDomain *prometheus.Desc
Flags *prometheus.Desc
GroupType *prometheus.Desc
PlacementOptions *prometheus.Desc
OwnerNode *prometheus.Desc
Priority *prometheus.Desc
ResiliencyPeriod *prometheus.Desc
State *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
}
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{"Memory"}, nil
}
func (c *collector) Build() error {
c.AutoFailbackType = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "auto_failback_type"),
"Provides access to the group's AutoFailbackType property.",
[]string{"name"},
nil,
)
c.Characteristics = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "characteristics"),
"Provides the characteristics of the group.",
[]string{"name"},
nil,
)
c.ColdStartSetting = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "cold_start_setting"),
"Indicates whether a group can start after a cluster cold start.",
[]string{"name"},
nil,
)
c.DefaultOwner = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "default_owner"),
"Number of the last node the resource group was activated on or explicitly moved to.",
[]string{"name"},
nil,
)
c.FailbackWindowEnd = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "failback_window_end"),
"The FailbackWindowEnd property provides the latest time that the group can be moved back to the node identified as its preferred node.",
[]string{"name"},
nil,
)
c.FailbackWindowStart = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "failback_window_start"),
"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.",
[]string{"name"},
nil,
)
c.FailoverPeriod = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "failover_period"),
"The FailoverPeriod property specifies a number of hours during which a maximum number of failover attempts, specified by the FailoverThreshold property, can occur.",
[]string{"name"},
nil,
)
c.FailoverThreshold = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "failover_threshold"),
"The FailoverThreshold property specifies the maximum number of failover attempts.",
[]string{"name"},
nil,
)
c.Flags = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "flags"),
"Provides access to the flags set for the group. ",
[]string{"name"},
nil,
)
c.GroupType = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "group_type"),
"The Type of the resource group.",
[]string{"name"},
nil,
)
c.OwnerNode = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "owner_node"),
"The node hosting the resource group. 0: Not hosted; 1: Hosted",
[]string{"node_name", "name"},
nil,
)
c.OwnerNode = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "owner_node"),
"The node hosting the resource group. 0: Not hosted; 1: Hosted",
[]string{"node_name", "name"},
nil,
)
c.Priority = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "priority"),
"Priority value of the resource group",
[]string{"name"},
nil,
)
c.ResiliencyPeriod = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "resiliency_period"),
"The resiliency period for this group, in seconds.",
[]string{"name"},
nil,
)
c.State = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "state"),
"The current state of the resource group. -1: Unknown; 0: Online; 1: Offline; 2: Failed; 3: Partial Online; 4: Pending",
[]string{"name"},
nil,
)
return nil
}
// MSCluster_ResourceGroup docs:
// - https://docs.microsoft.com/en-us/previous-versions/windows/desktop/cluswmi/mscluster-resourcegroup
type MSCluster_ResourceGroup struct {
Name string
AutoFailbackType uint
Characteristics uint
ColdStartSetting uint
DefaultOwner uint
FailbackWindowEnd int
FailbackWindowStart int
FailoverPeriod uint
FailoverThreshold uint
Flags uint
GroupType uint
OwnerNode string
Priority uint
ResiliencyPeriod uint
State uint
}
// 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 {
var dst []MSCluster_ResourceGroup
q := wmi.QueryAll(&dst, c.logger)
if err := wmi.QueryNamespace(q, &dst, "root/MSCluster"); err != nil {
return err
}
for _, v := range dst {
ch <- prometheus.MustNewConstMetric(
c.AutoFailbackType,
prometheus.GaugeValue,
float64(v.AutoFailbackType),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.Characteristics,
prometheus.GaugeValue,
float64(v.Characteristics),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.ColdStartSetting,
prometheus.GaugeValue,
float64(v.ColdStartSetting),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.DefaultOwner,
prometheus.GaugeValue,
float64(v.DefaultOwner),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.FailbackWindowEnd,
prometheus.GaugeValue,
float64(v.FailbackWindowEnd),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.FailbackWindowStart,
prometheus.GaugeValue,
float64(v.FailbackWindowStart),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.FailoverPeriod,
prometheus.GaugeValue,
float64(v.FailoverPeriod),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.FailoverThreshold,
prometheus.GaugeValue,
float64(v.FailoverThreshold),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.Flags,
prometheus.GaugeValue,
float64(v.Flags),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.GroupType,
prometheus.GaugeValue,
float64(v.GroupType),
v.Name,
)
if mscluster_node.NodeName != nil {
for _, node_name := range mscluster_node.NodeName {
isCurrentState := 0.0
if v.OwnerNode == node_name {
isCurrentState = 1.0
}
ch <- prometheus.MustNewConstMetric(
c.OwnerNode,
prometheus.GaugeValue,
isCurrentState,
node_name, v.Name,
)
}
}
ch <- prometheus.MustNewConstMetric(
c.Priority,
prometheus.GaugeValue,
float64(v.Priority),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.ResiliencyPeriod,
prometheus.GaugeValue,
float64(v.ResiliencyPeriod),
v.Name,
)
ch <- prometheus.MustNewConstMetric(
c.State,
prometheus.GaugeValue,
float64(v.State),
v.Name,
)
}
return nil
}

View File

@@ -3,160 +3,184 @@
package msmq
import (
"errors"
"log/slog"
"strings"
"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/utils"
"github.com/prometheus-community/windows_exporter/pkg/wmi"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const (
Name = "msmq"
FlagMsmqWhereClause = "collector.msmq.msmq-where"
)
const Name = "msmq"
type Config struct {
QueryWhereClause string `yaml:"query_where_clause"`
QueryWhereClause *string `yaml:"query_where_clause"`
}
var ConfigDefaults = Config{
QueryWhereClause: "",
QueryWhereClause: utils.ToPTR(""),
}
// A collector is a Prometheus collector for WMI Win32_PerfRawData_MSMQ_MSMQQueue metrics
type collector struct {
logger log.Logger
// A Collector is a Prometheus Collector for WMI Win32_PerfRawData_MSMQ_MSMQQueue metrics.
type Collector struct {
config Config
wmiClient *wmi.Client
queryWhereClause *string
BytesinJournalQueue *prometheus.Desc
BytesinQueue *prometheus.Desc
MessagesinJournalQueue *prometheus.Desc
MessagesinQueue *prometheus.Desc
bytesInJournalQueue *prometheus.Desc
bytesInQueue *prometheus.Desc
messagesInJournalQueue *prometheus.Desc
messagesInQueue *prometheus.Desc
}
func New(logger log.Logger, config *Config) types.Collector {
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &collector{
queryWhereClause: &config.QueryWhereClause,
if config.QueryWhereClause == nil {
config.QueryWhereClause = ConfigDefaults.QueryWhereClause
}
c.SetLogger(logger)
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(app *kingpin.Application) types.Collector {
return &collector{
queryWhereClause: app.
Flag(FlagMsmqWhereClause, "WQL 'where' clause to use in WMI metrics query. Limits the response to the msmqs you specify and reduces the size of the response.").
Default(ConfigDefaults.QueryWhereClause).String(),
func NewWithFlags(app *kingpin.Application) *Collector {
c := &Collector{
config: ConfigDefaults,
}
app.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.").
Default(*c.config.QueryWhereClause).StringVar(c.config.QueryWhereClause)
return c
}
func (c *collector) GetName() string {
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{}, nil
}
func (c *collector) Build() error {
if utils.IsEmpty(c.queryWhereClause) {
_ = level.Warn(c.logger).Log("msg", "No where-clause specified for msmq collector. This will generate a very large number of metrics!")
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(logger *slog.Logger, wmiClient *wmi.Client) error {
logger = logger.With(slog.String("collector", Name))
if wmiClient == nil || wmiClient.SWbemServicesClient == nil {
return errors.New("wmiClient or SWbemServicesClient is nil")
}
c.BytesinJournalQueue = prometheus.NewDesc(
c.wmiClient = wmiClient
if *c.config.QueryWhereClause == "" {
logger.Warn("No where-clause specified for msmq collector. This will generate a very large number of metrics!")
}
c.bytesInJournalQueue = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "bytes_in_journal_queue"),
"Size of queue journal in bytes",
[]string{"name"},
nil,
)
c.BytesinQueue = prometheus.NewDesc(
c.bytesInQueue = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "bytes_in_queue"),
"Size of queue in bytes",
[]string{"name"},
nil,
)
c.MessagesinJournalQueue = prometheus.NewDesc(
c.messagesInJournalQueue = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "messages_in_journal_queue"),
"Count messages in queue journal",
[]string{"name"},
nil,
)
c.MessagesinQueue = prometheus.NewDesc(
c.messagesInQueue = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "messages_in_queue"),
"Count messages in queue",
[]string{"name"},
nil,
)
return 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 {
func (c *Collector) Collect(_ *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
if err := c.collect(ch); err != nil {
_ = level.Error(c.logger).Log("msg", "failed collecting msmq metrics", "err", err)
logger.Error("failed collecting msmq metrics",
slog.Any("err", err),
)
return err
}
return nil
}
type Win32_PerfRawData_MSMQ_MSMQQueue struct {
type msmqQueue struct {
Name string
BytesinJournalQueue uint64
BytesinQueue uint64
MessagesinJournalQueue uint64
MessagesinQueue uint64
BytesInJournalQueue uint64
BytesInQueue uint64
MessagesInJournalQueue uint64
MessagesInQueue uint64
}
func (c *collector) collect(ch chan<- prometheus.Metric) error {
var dst []Win32_PerfRawData_MSMQ_MSMQQueue
q := wmi.QueryAllWhere(&dst, *c.queryWhereClause, c.logger)
if err := wmi.Query(q, &dst); err != nil {
func (c *Collector) collect(ch chan<- prometheus.Metric) error {
var dst []msmqQueue
query := "SELECT * FROM Win32_PerfRawData_MSMQ_MSMQQueue"
if *c.config.QueryWhereClause != "" {
query += " WHERE " + *c.config.QueryWhereClause
}
if err := c.wmiClient.Query(query, &dst); err != nil {
return err
}
for _, msmq := range dst {
ch <- prometheus.MustNewConstMetric(
c.BytesinJournalQueue,
c.bytesInJournalQueue,
prometheus.GaugeValue,
float64(msmq.BytesinJournalQueue),
float64(msmq.BytesInJournalQueue),
strings.ToLower(msmq.Name),
)
ch <- prometheus.MustNewConstMetric(
c.BytesinQueue,
c.bytesInQueue,
prometheus.GaugeValue,
float64(msmq.BytesinQueue),
float64(msmq.BytesInQueue),
strings.ToLower(msmq.Name),
)
ch <- prometheus.MustNewConstMetric(
c.MessagesinJournalQueue,
c.messagesInJournalQueue,
prometheus.GaugeValue,
float64(msmq.MessagesinJournalQueue),
float64(msmq.MessagesInJournalQueue),
strings.ToLower(msmq.Name),
)
ch <- prometheus.MustNewConstMetric(
c.MessagesinQueue,
c.messagesInQueue,
prometheus.GaugeValue,
float64(msmq.MessagesinQueue),
float64(msmq.MessagesInQueue),
strings.ToLower(msmq.Name),
)
}
return nil
}

View File

@@ -8,6 +8,6 @@ import (
)
func BenchmarkCollector(b *testing.B) {
// No context name required as collector source is WMI
// No context name required as Collector source is WMI
testutils.FuncBenchmarkCollector(b, msmq.Name, msmq.NewWithFlags)
}

File diff suppressed because it is too large Load Diff

View File

@@ -4,202 +4,212 @@ package net
import (
"fmt"
"log/slog"
"regexp"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/go-kit/log/level"
"github.com/prometheus-community/windows_exporter/pkg/perflib"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const (
Name = "net"
FlagNicExclude = "collector.net.nic-exclude"
FlagNicInclude = "collector.net.nic-include"
)
const Name = "net"
type Config struct {
NicInclude string `yaml:"nic_include"`
NicExclude string `yaml:"nic_exclude"`
NicExclude *regexp.Regexp `yaml:"nic_exclude"`
NicInclude *regexp.Regexp `yaml:"nic_include"`
}
var ConfigDefaults = Config{
NicInclude: ".+",
NicExclude: "",
NicExclude: types.RegExpEmpty,
NicInclude: types.RegExpAny,
}
var nicNameToUnderscore = regexp.MustCompile("[^a-zA-Z0-9]")
// A collector is a Prometheus collector for Perflib Network Interface metrics
type collector struct {
logger log.Logger
// A Collector is a Prometheus Collector for Perflib Network Interface metrics.
type Collector struct {
config Config
nicInclude *string
nicExclude *string
BytesReceivedTotal *prometheus.Desc
BytesSentTotal *prometheus.Desc
BytesTotal *prometheus.Desc
OutputQueueLength *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
nicIncludePattern *regexp.Regexp
nicExcludePattern *regexp.Regexp
bytesReceivedTotal *prometheus.Desc
bytesSentTotal *prometheus.Desc
bytesTotal *prometheus.Desc
outputQueueLength *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
}
func New(logger log.Logger, config *Config) types.Collector {
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &collector{
nicExclude: &config.NicExclude,
nicInclude: &config.NicInclude,
if config.NicExclude == nil {
config.NicExclude = ConfigDefaults.NicExclude
}
c.SetLogger(logger)
return c
}
func NewWithFlags(app *kingpin.Application) types.Collector {
c := &collector{
nicInclude: app.Flag(
FlagNicInclude,
"Regexp of NIC:s to include. NIC name must both match include and not match exclude to be included.",
).Default(ConfigDefaults.NicInclude).String(),
if config.NicInclude == nil {
config.NicInclude = ConfigDefaults.NicInclude
}
nicExclude: app.Flag(
FlagNicExclude,
"Regexp of NIC:s to exclude. NIC name must both match include and not match exclude to be included.",
).Default(ConfigDefaults.NicExclude).String(),
c := &Collector{
config: *config,
}
return c
}
func (c *collector) GetName() string {
func NewWithFlags(app *kingpin.Application) *Collector {
c := &Collector{
config: ConfigDefaults,
}
var nicExclude, nicInclude string
app.Flag(
"collector.net.nic-exclude",
"Regexp of NIC:s to exclude. NIC name must both match include and not match exclude to be included.",
).Default(c.config.NicExclude.String()).StringVar(&nicExclude)
app.Flag(
"collector.net.nic-include",
"Regexp of NIC:s to include. NIC name must both match include and not match exclude to be included.",
).Default(c.config.NicInclude.String()).StringVar(&nicInclude)
app.Action(func(*kingpin.ParseContext) error {
var err error
c.config.NicExclude, err = regexp.Compile(fmt.Sprintf("^(?:%s)$", nicExclude))
if err != nil {
return fmt.Errorf("collector.net.nic-exclude: %w", err)
}
c.config.NicInclude, err = regexp.Compile(fmt.Sprintf("^(?:%s)$", nicInclude))
if err != nil {
return fmt.Errorf("collector.net.nic-include: %w", err)
}
return nil
})
return c
}
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) {
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{"Network Interface"}, nil
}
func (c *collector) Build() error {
c.BytesReceivedTotal = prometheus.NewDesc(
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, _ *wmi.Client) error {
c.bytesReceivedTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "bytes_received_total"),
"(Network.BytesReceivedPerSec)",
[]string{"nic"},
nil,
)
c.BytesSentTotal = prometheus.NewDesc(
c.bytesSentTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "bytes_sent_total"),
"(Network.BytesSentPerSec)",
[]string{"nic"},
nil,
)
c.BytesTotal = prometheus.NewDesc(
c.bytesTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "bytes_total"),
"(Network.BytesTotalPerSec)",
[]string{"nic"},
nil,
)
c.OutputQueueLength = prometheus.NewDesc(
c.outputQueueLength = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "output_queue_length_packets"),
"(Network.OutputQueueLength)",
[]string{"nic"},
nil,
)
c.PacketsOutboundDiscarded = prometheus.NewDesc(
c.packetsOutboundDiscarded = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "packets_outbound_discarded_total"),
"(Network.PacketsOutboundDiscarded)",
[]string{"nic"},
nil,
)
c.PacketsOutboundErrors = prometheus.NewDesc(
c.packetsOutboundErrors = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "packets_outbound_errors_total"),
"(Network.PacketsOutboundErrors)",
[]string{"nic"},
nil,
)
c.PacketsReceivedDiscarded = prometheus.NewDesc(
c.packetsReceivedDiscarded = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "packets_received_discarded_total"),
"(Network.PacketsReceivedDiscarded)",
[]string{"nic"},
nil,
)
c.PacketsReceivedErrors = prometheus.NewDesc(
c.packetsReceivedErrors = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "packets_received_errors_total"),
"(Network.PacketsReceivedErrors)",
[]string{"nic"},
nil,
)
c.PacketsReceivedTotal = prometheus.NewDesc(
c.packetsReceivedTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "packets_received_total"),
"(Network.PacketsReceivedPerSec)",
[]string{"nic"},
nil,
)
c.PacketsReceivedUnknown = prometheus.NewDesc(
c.packetsReceivedUnknown = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "packets_received_unknown_total"),
"(Network.PacketsReceivedUnknown)",
[]string{"nic"},
nil,
)
c.PacketsTotal = prometheus.NewDesc(
c.packetsTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "packets_total"),
"(Network.PacketsPerSec)",
[]string{"nic"},
nil,
)
c.PacketsSentTotal = prometheus.NewDesc(
c.packetsSentTotal = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "packets_sent_total"),
"(Network.PacketsSentPerSec)",
[]string{"nic"},
nil,
)
c.CurrentBandwidth = prometheus.NewDesc(
c.currentBandwidth = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "current_bandwidth_bytes"),
"(Network.CurrentBandwidth)",
[]string{"nic"},
nil,
)
var err error
c.nicIncludePattern, err = regexp.Compile(fmt.Sprintf("^(?:%s)$", *c.nicInclude))
if err != nil {
return err
}
c.nicExcludePattern, err = regexp.Compile(fmt.Sprintf("^(?:%s)$", *c.nicExclude))
if err != nil {
return err
}
return nil
}
// Collect sends the metric values for each metric
// to the provided prometheus Metric channel.
func (c *collector) Collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
if err := c.collect(ctx, ch); err != nil {
_ = level.Error(c.logger).Log("msg", "failed collecting net metrics", "err", err)
func (c *Collector) Collect(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
if err := c.collect(ctx, logger, ch); err != nil {
logger.Error("failed collecting net metrics",
slog.Any("err", err),
)
return err
}
return nil
}
@@ -228,16 +238,18 @@ type networkInterface struct {
CurrentBandwidth float64 `perflib:"Current Bandwidth"`
}
func (c *collector) collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metric) error {
func (c *Collector) collect(ctx *types.ScrapeContext, logger *slog.Logger, ch chan<- prometheus.Metric) error {
logger = logger.With(slog.String("collector", Name))
var dst []networkInterface
if err := perflib.UnmarshalObject(ctx.PerfObjects["Network Interface"], &dst, c.logger); err != nil {
if err := perflib.UnmarshalObject(ctx.PerfObjects["Network Interface"], &dst, logger); err != nil {
return err
}
for _, nic := range dst {
if c.nicExcludePattern.MatchString(nic.Name) ||
!c.nicIncludePattern.MatchString(nic.Name) {
if c.config.NicExclude.MatchString(nic.Name) ||
!c.config.NicInclude.MatchString(nic.Name) {
continue
}
@@ -248,83 +260,84 @@ func (c *collector) collect(ctx *types.ScrapeContext, ch chan<- prometheus.Metri
// Counters
ch <- prometheus.MustNewConstMetric(
c.BytesReceivedTotal,
c.bytesReceivedTotal,
prometheus.CounterValue,
nic.BytesReceivedPerSec,
name,
)
ch <- prometheus.MustNewConstMetric(
c.BytesSentTotal,
c.bytesSentTotal,
prometheus.CounterValue,
nic.BytesSentPerSec,
name,
)
ch <- prometheus.MustNewConstMetric(
c.BytesTotal,
c.bytesTotal,
prometheus.CounterValue,
nic.BytesTotalPerSec,
name,
)
ch <- prometheus.MustNewConstMetric(
c.OutputQueueLength,
c.outputQueueLength,
prometheus.GaugeValue,
nic.OutputQueueLength,
name,
)
ch <- prometheus.MustNewConstMetric(
c.PacketsOutboundDiscarded,
c.packetsOutboundDiscarded,
prometheus.CounterValue,
nic.PacketsOutboundDiscarded,
name,
)
ch <- prometheus.MustNewConstMetric(
c.PacketsOutboundErrors,
c.packetsOutboundErrors,
prometheus.CounterValue,
nic.PacketsOutboundErrors,
name,
)
ch <- prometheus.MustNewConstMetric(
c.PacketsTotal,
c.packetsTotal,
prometheus.CounterValue,
nic.PacketsPerSec,
name,
)
ch <- prometheus.MustNewConstMetric(
c.PacketsReceivedDiscarded,
c.packetsReceivedDiscarded,
prometheus.CounterValue,
nic.PacketsReceivedDiscarded,
name,
)
ch <- prometheus.MustNewConstMetric(
c.PacketsReceivedErrors,
c.packetsReceivedErrors,
prometheus.CounterValue,
nic.PacketsReceivedErrors,
name,
)
ch <- prometheus.MustNewConstMetric(
c.PacketsReceivedTotal,
c.packetsReceivedTotal,
prometheus.CounterValue,
nic.PacketsReceivedPerSec,
name,
)
ch <- prometheus.MustNewConstMetric(
c.PacketsReceivedUnknown,
c.packetsReceivedUnknown,
prometheus.CounterValue,
nic.PacketsReceivedUnknown,
name,
)
ch <- prometheus.MustNewConstMetric(
c.PacketsSentTotal,
c.packetsSentTotal,
prometheus.CounterValue,
nic.PacketsSentPerSec,
name,
)
ch <- prometheus.MustNewConstMetric(
c.CurrentBandwidth,
c.currentBandwidth,
prometheus.GaugeValue,
nic.CurrentBandwidth/8,
name,
)
}
return nil
}

View File

@@ -11,9 +11,9 @@ import (
)
func BenchmarkCollector(b *testing.B) {
// Include is not set in testing context (kingpin flags not parsed), causing the collector to skip all interfaces.
// PrinterInclude is not set in testing context (kingpin flags not parsed), causing the collector to skip all interfaces.
localNicInclude := ".+"
kingpin.CommandLine.GetArg(net.FlagNicInclude).StringVar(&localNicInclude)
kingpin.CommandLine.GetArg("collector.net.nic-include").StringVar(&localNicInclude)
testutils.FuncBenchmarkCollector(b, net.Name, net.NewWithFlags)
}

View File

@@ -7,6 +7,8 @@ import (
)
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",
}

View File

@@ -0,0 +1,245 @@
//go:build windows
package netframework
import (
"errors"
"fmt"
"log/slog"
"slices"
"github.com/alecthomas/kingpin/v2"
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus/client_golang/prometheus"
"github.com/yusufpapurcu/wmi"
)
const Name = "netframework"
type Config struct {
CollectorsEnabled []string `yaml:"collectors_enabled"`
}
var ConfigDefaults = Config{
CollectorsEnabled: []string{
collectorClrExceptions,
collectorClrInterop,
collectorClrJIT,
collectorClrLoading,
collectorClrLocksAndThreads,
collectorClrMemory,
collectorClrRemoting,
collectorClrSecurity,
},
}
const (
collectorClrExceptions = "clrexceptions"
collectorClrInterop = "clrinterop"
collectorClrJIT = "clrjit"
collectorClrLoading = "clrloading"
collectorClrLocksAndThreads = "clrlocksandthreads"
collectorClrMemory = "clrmemory"
collectorClrRemoting = "clrremoting"
collectorClrSecurity = "clrsecurity"
)
// A Collector is a Prometheus Collector for WMI Win32_PerfRawData_NETFramework_NETCLRExceptions metrics.
type Collector struct {
config Config
wmiClient *wmi.Client
// clrexceptions
numberOfExceptionsThrown *prometheus.Desc
numberOfFilters *prometheus.Desc
numberOfFinally *prometheus.Desc
throwToCatchDepth *prometheus.Desc
// clrinterop
numberOfCCWs *prometheus.Desc
numberOfMarshalling *prometheus.Desc
numberOfStubs *prometheus.Desc
// clrjit
numberOfMethodsJitted *prometheus.Desc
timeInJit *prometheus.Desc
standardJitFailures *prometheus.Desc
totalNumberOfILBytesJitted *prometheus.Desc
// clrloading
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
// clrlocksandthreads
currentQueueLength *prometheus.Desc
numberOfCurrentLogicalThreads *prometheus.Desc
numberOfCurrentPhysicalThreads *prometheus.Desc
numberOfCurrentRecognizedThreads *prometheus.Desc
numberOfTotalRecognizedThreads *prometheus.Desc
queueLengthPeak *prometheus.Desc
totalNumberOfContentions *prometheus.Desc
// clrmemory
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
// clrremoting
channels *prometheus.Desc
contextBoundClassesLoaded *prometheus.Desc
contextBoundObjects *prometheus.Desc
contextProxies *prometheus.Desc
contexts *prometheus.Desc
totalRemoteCalls *prometheus.Desc
// clrsecurity
numberLinkTimeChecks *prometheus.Desc
timeInRTChecks *prometheus.Desc
stackWalkDepth *prometheus.Desc
totalRuntimeChecks *prometheus.Desc
}
func New(config *Config) *Collector {
if config == nil {
config = &ConfigDefaults
}
c := &Collector{
config: *config,
}
return c
}
func NewWithFlags(_ *kingpin.Application) *Collector {
return &Collector{}
}
func (c *Collector) GetName() string {
return Name
}
func (c *Collector) GetPerfCounter(_ *slog.Logger) ([]string, error) {
return []string{}, nil
}
func (c *Collector) Close(_ *slog.Logger) error {
return nil
}
func (c *Collector) Build(_ *slog.Logger, wmiClient *wmi.Client) error {
if wmiClient == nil || wmiClient.SWbemServicesClient == nil {
return errors.New("wmiClient or SWbemServicesClient is nil")
}
c.wmiClient = wmiClient
if slices.Contains(c.config.CollectorsEnabled, collectorClrExceptions) {
c.buildClrExceptions()
}
if slices.Contains(c.config.CollectorsEnabled, collectorClrInterop) {
c.buildClrInterop()
}
if slices.Contains(c.config.CollectorsEnabled, collectorClrJIT) {
c.buildClrJIT()
}
if slices.Contains(c.config.CollectorsEnabled, collectorClrLoading) {
c.buildClrLoading()
}
if slices.Contains(c.config.CollectorsEnabled, collectorClrLocksAndThreads) {
c.buildClrLocksAndThreads()
}
if slices.Contains(c.config.CollectorsEnabled, collectorClrMemory) {
c.buildClrMemory()
}
if slices.Contains(c.config.CollectorsEnabled, collectorClrRemoting) {
c.buildClrRemoting()
}
if slices.Contains(c.config.CollectorsEnabled, collectorClrSecurity) {
c.buildClrSecurity()
}
return nil
}
// Collect sends the metric values for each metric
// to the provided prometheus Metric channel.
func (c *Collector) Collect(_ *types.ScrapeContext, _ *slog.Logger, ch chan<- prometheus.Metric) error {
var (
err error
errs []error
)
if slices.Contains(c.config.CollectorsEnabled, collectorClrExceptions) {
if err = c.collectClrExceptions(ch); err != nil {
errs = append(errs, fmt.Errorf("failed to collect %s metrics: %w", collectorClrExceptions, err))
}
}
if slices.Contains(c.config.CollectorsEnabled, collectorClrInterop) {
if err = c.collectClrInterop(ch); err != nil {
errs = append(errs, fmt.Errorf("failed to collect %s metrics: %w", collectorClrInterop, err))
}
}
if slices.Contains(c.config.CollectorsEnabled, collectorClrJIT) {
if err = c.collectClrJIT(ch); err != nil {
errs = append(errs, fmt.Errorf("failed to collect %s metrics: %w", collectorClrJIT, err))
}
}
if slices.Contains(c.config.CollectorsEnabled, collectorClrLoading) {
if err = c.collectClrLoading(ch); err != nil {
errs = append(errs, fmt.Errorf("failed to collect %s metrics: %w", collectorClrLoading, err))
}
}
if slices.Contains(c.config.CollectorsEnabled, collectorClrLocksAndThreads) {
if err = c.collectClrLocksAndThreads(ch); err != nil {
errs = append(errs, fmt.Errorf("failed to collect %s metrics: %w", collectorClrLocksAndThreads, err))
}
}
if slices.Contains(c.config.CollectorsEnabled, collectorClrMemory) {
if err = c.collectClrMemory(ch); err != nil {
errs = append(errs, fmt.Errorf("failed to collect %s metrics: %w", collectorClrMemory, err))
}
}
if slices.Contains(c.config.CollectorsEnabled, collectorClrRemoting) {
if err = c.collectClrRemoting(ch); err != nil {
errs = append(errs, fmt.Errorf("failed to collect %s metrics: %w", collectorClrRemoting, err))
}
}
if slices.Contains(c.config.CollectorsEnabled, collectorClrSecurity) {
if err = c.collectClrSecurity(ch); err != nil {
errs = append(errs, fmt.Errorf("failed to collect %s metrics: %w", collectorClrSecurity, err))
}
}
return errors.Join(errs...)
}

View File

@@ -1,91 +1,37 @@
//go:build windows
package netframework_clrexceptions
package netframework
import (
"github.com/prometheus-community/windows_exporter/pkg/types"
"github.com/prometheus-community/windows_exporter/pkg/wmi"
"github.com/alecthomas/kingpin/v2"
"github.com/go-kit/log"
"github.com/go-kit/log/level"
"github.com/prometheus/client_golang/prometheus"
)
const Name = "netframework_clrexceptions"
type Config struct{}
var ConfigDefaults = Config{}
// A collector is a Prometheus collector for WMI Win32_PerfRawData_NETFramework_NETCLRExceptions metrics
type collector struct {
logger log.Logger
NumberofExcepsThrown *prometheus.Desc
NumberofFilters *prometheus.Desc
NumberofFinallys *prometheus.Desc
ThrowToCatchDepth *prometheus.Desc
}
func New(logger log.Logger, _ *Config) types.Collector {
c := &collector{}
c.SetLogger(logger)
return c
}
func NewWithFlags(_ *kingpin.Application) types.Collector {
return &collector{}
}
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) Build() error {
c.NumberofExcepsThrown = prometheus.NewDesc(
func (c *Collector) buildClrExceptions() {
c.numberOfExceptionsThrown = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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,
)
c.NumberofFilters = prometheus.NewDesc(
c.numberOfFilters = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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,
)
c.NumberofFinallys = prometheus.NewDesc(
c.numberOfFinally = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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,
)
c.ThrowToCatchDepth = prometheus.NewDesc(
c.throwToCatchDepth = prometheus.NewDesc(
prometheus.BuildFQName(types.Namespace, Name, "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,
)
return 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 win32_perfrawdata_netframework_netclrexceptions metrics", "err", err)
return err
}
return nil
}
type Win32_PerfRawData_NETFramework_NETCLRExceptions struct {
@@ -98,42 +44,40 @@ type Win32_PerfRawData_NETFramework_NETCLRExceptions struct {
ThrowToCatchDepthPersec uint32
}
func (c *collector) collect(ch chan<- prometheus.Metric) error {
func (c *Collector) collectClrExceptions(ch chan<- prometheus.Metric) error {
var dst []Win32_PerfRawData_NETFramework_NETCLRExceptions
q := wmi.QueryAll(&dst, c.logger)
if err := wmi.Query(q, &dst); err != nil {
if err := c.wmiClient.Query("SELECT * FROM Win32_PerfRawData_NETFramework_NETCLRExceptions", &dst); err != nil {
return err
}
for _, process := range dst {
if process.Name == "_Global_" {
continue
}
ch <- prometheus.MustNewConstMetric(
c.NumberofExcepsThrown,
c.numberOfExceptionsThrown,
prometheus.CounterValue,
float64(process.NumberofExcepsThrown),
process.Name,
)
ch <- prometheus.MustNewConstMetric(
c.NumberofFilters,
c.numberOfFilters,
prometheus.CounterValue,
float64(process.NumberofFiltersPersec),
process.Name,
)
ch <- prometheus.MustNewConstMetric(
c.NumberofFinallys,
c.numberOfFinally,
prometheus.CounterValue,
float64(process.NumberofFinallysPersec),
process.Name,
)
ch <- prometheus.MustNewConstMetric(
c.ThrowToCatchDepth,
c.throwToCatchDepth,
prometheus.CounterValue,
float64(process.ThrowToCatchDepthPersec),
process.Name,

Some files were not shown because too many files have changed in this diff Show More