sendnrw/windows_exporter
2
0
Fork 0
mirror of https://github.com/prometheus-community/windows_exporter.git synced 2026-10-18 18:49:05 +02:00
Code Issues Packages Projects Releases Wiki Activity
Files
fcb7cf32beb9b5c2d40a5022f35133c818d7a44c
windows_exporter/contrib/mixin/tests/optional.test.yaml
T
Jan-Otto Kröpke d819362150 mixin: add alerts for the opt-in collectors 
Every optional collector of the mixin now has alerts, generated only with
that collector enabled in _config.collectors: clock source, disk drive
status, page file usage, license status, scheduled task results, pending
updates, Hyper-V WMI and replication health, failover cluster nodes,
resources, groups and shared volumes, Storage Spaces pool and virtual disk
health, DHCP scope exhaustion and DNS zone transfer failures. The alerts
of the pagefile, diskdrive and license collectors join the memory, disk
and system groups; the other collectors get a group of their own.

New knobs: taskSelector, sharedVolumeSelector, pagefileUsageThreshold,
dhcpScopeFreeWarningThreshold, dhcpScopeFreeCriticalThreshold and
updatePendingDuration. The test configuration enables every optional
collector and tests/optional.test.yaml covers the new alerts.

Signed-off-by: Jan-Otto Kröpke <mail@jkroepke.de>
2026-10-17 02:28:35 +00:00

509 lines
35 KiB
YAML
Raw Blame History

# Alerts of the opt-in collectors, rendered with tests/config.libsonnet.
rule_files:
- custom_rules.yaml
- custom_alerts.yaml
evaluation_interval: 1m
group_eval_order:
- windows-exporter-recording
- windows-memory
- windows-disk
- windows-system
- windows-time
- windows-scheduled-task
- windows-update
- windows-hyperv
- windows-cluster
- windows-storage-spaces
- windows-dhcp
- windows-dns
tests:
- name: Page file usage fires above the custom threshold and resolves after keep_firing_for
interval: 1m
input_series:
- series: 'windows_pagefile_free_bytes{job="windows-custom", instance="host:9182", cluster="test", file="C:\\pagefile.sys"}'
values: '20x19 50x10'
- series: 'windows_pagefile_limit_bytes{job="windows-custom", instance="host:9182", cluster="test", file="C:\\pagefile.sys"}'
values: '100x30'
- series: 'windows_pagefile_free_bytes{job="windows-custom", instance="host:9182", cluster="test", file="D:\\pagefile.sys"}'
values: '30x30'
- series: 'windows_pagefile_limit_bytes{job="windows-custom", instance="host:9182", cluster="test", file="D:\\pagefile.sys"}'
values: '100x30'
- series: 'windows_pagefile_free_bytes{job="windows-custom", instance="host:9182", cluster="test", file="E:\\pagefile.sys"}'
values: '0x30'
- series: 'windows_pagefile_limit_bytes{job="windows-custom", instance="host:9182", cluster="test", file="E:\\pagefile.sys"}'
values: '0x30'
alert_rule_test:
- {alertname: WindowsPagefileAlmostFull, eval_time: 14m, exp_alerts: []}
- alertname: WindowsPagefileAlmostFull
eval_time: 15m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'host:9182', cluster: test, file: 'C:\pagefile.sys', severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowspagefilealmostfull/
summary: Windows page file is almost full
description: 'Page file C:\pagefile.sys on host:9182 has been more than 75% in use for 15 minutes.'
- alertname: WindowsPagefileAlmostFull
eval_time: 24m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'host:9182', cluster: test, file: 'C:\pagefile.sys', severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowspagefilealmostfull/
summary: Windows page file is almost full
description: 'Page file C:\pagefile.sys on host:9182 has been more than 75% in use for 15 minutes.'
- {alertname: WindowsPagefileAlmostFull, eval_time: 25m, exp_alerts: []}
- name: Disk drive status reports the status the drive has, resolves at once and skips Unknown, and the license alert waits an hour
interval: 1m
input_series:
- series: 'windows_diskdrive_status{job="windows-custom", instance="host:9182", cluster="test", device_id="\\\\.\\PHYSICALDRIVE0", status="OK"}'
values: '0x9 1x10'
- series: 'windows_diskdrive_status{job="windows-custom", instance="host:9182", cluster="test", device_id="\\\\.\\PHYSICALDRIVE0", status="Pred Fail"}'
values: '1x9 0x10'
- series: 'windows_diskdrive_status{job="windows-custom", instance="host:9182", cluster="test", device_id="\\\\.\\PHYSICALDRIVE2", status="OK"}'
values: '0x20'
- series: 'windows_diskdrive_status{job="windows-custom", instance="host:9182", cluster="test", device_id="\\\\.\\PHYSICALDRIVE2", status="Unknown"}'
values: '1x20'
- series: 'windows_diskdrive_status{job="windows-custom", instance="host:9182", cluster="test", device_id="\\\\.\\PHYSICALDRIVE1", status="OK"}'
values: '1x10'
- series: 'windows_diskdrive_status{job="windows-custom", instance="host:9182", cluster="test", device_id="\\\\.\\PHYSICALDRIVE1", status="Pred Fail"}'
values: '0x10'
- series: 'windows_license_status{job="windows-custom", instance="host:9182", cluster="test", state="genuine"}'
values: '0x60'
- series: 'windows_license_status{job="windows-custom", instance="host:9182", cluster="test", state="invalid_license"}'
values: '1x60'
- series: 'windows_license_status{job="windows-custom", instance="licensed:9182", cluster="test", state="genuine"}'
values: '1x60'
- series: 'windows_license_status{job="windows-custom", instance="licensed:9182", cluster="test", state="invalid_license"}'
values: '0x60'
alert_rule_test:
- {alertname: WindowsDiskDriveNotOK, eval_time: 4m, exp_alerts: []}
- alertname: WindowsDiskDriveNotOK
eval_time: 5m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'host:9182', cluster: test, device_id: '\\.\PHYSICALDRIVE0', status: Pred Fail, severity: page}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsdiskdrivenotok/
summary: Windows disk drive is not healthy
description: 'Disk drive \\.\PHYSICALDRIVE0 on host:9182 has reported status Pred Fail for 5 minutes.'
- alertname: WindowsDiskDriveNotOK
eval_time: 9m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'host:9182', cluster: test, device_id: '\\.\PHYSICALDRIVE0', status: Pred Fail, severity: page}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsdiskdrivenotok/
summary: Windows disk drive is not healthy
description: 'Disk drive \\.\PHYSICALDRIVE0 on host:9182 has reported status Pred Fail for 5 minutes.'
- {alertname: WindowsDiskDriveNotOK, eval_time: 10m, exp_alerts: []}
- {alertname: WindowsLicenseNotGenuine, eval_time: 59m, exp_alerts: []}
- alertname: WindowsLicenseNotGenuine
eval_time: 60m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'host:9182', cluster: test, state: invalid_license, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowslicensenotgenuine/
summary: Windows license is not genuine
description: 'Windows on host:9182 has reported license status invalid_license for 1 hour.'
- name: Clock source alert names the local source and ignores NTP and domain sources
interval: 1m
input_series:
- series: 'windows_time_clock_sync_source{job="windows-custom", instance="host:9182", cluster="test", type="Local CMOS Clock"}'
values: '1x10'
- series: 'windows_time_clock_sync_source{job="windows-custom", instance="host:9182", cluster="test", type="NTP"}'
values: '0x10'
- series: 'windows_time_clock_sync_source{job="windows-custom", instance="dc:9182", cluster="test", type="NT5DS"}'
values: '1x10'
- series: 'windows_time_clock_sync_source{job="windows-custom", instance="dc:9182", cluster="test", type="NoSync"}'
values: '0x10'
alert_rule_test:
- {alertname: WindowsClockSourceLocal, eval_time: 9m, exp_alerts: []}
- alertname: WindowsClockSourceLocal
eval_time: 10m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'host:9182', cluster: test, type: Local CMOS Clock, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsclocksourcelocal/
summary: Windows clock has no external time source
description: 'Windows Time on host:9182 has used Local CMOS Clock as its clock source for 10 minutes.'
- name: Scheduled task alert fires for unmapped and terminated results after an hour and skips disabled and deselected tasks
interval: 1m
input_series:
- series: 'windows_scheduled_task_last_result_status{job="windows-custom", instance="host:9182", cluster="test", task="/Backup", status="unknown"}'
values: '1x60'
- series: 'windows_scheduled_task_last_result_status{job="windows-custom", instance="host:9182", cluster="test", task="/Backup", status="success"}'
values: '0x60'
- series: 'windows_scheduled_task_last_result_status{job="windows-custom", instance="host:9182", cluster="test", task="/Cleanup", status="terminated"}'
values: '1x60'
- series: 'windows_scheduled_task_last_result_status{job="windows-custom", instance="host:9182", cluster="test", task="/Report", status="has_not_run"}'
values: '1x60'
- series: 'windows_scheduled_task_last_result_status{job="windows-custom", instance="host:9182", cluster="test", task="/Report", status="unknown"}'
values: '0x60'
- series: 'windows_scheduled_task_last_result_status{job="windows-custom", instance="host:9182", cluster="test", task="/Ignored/Flaky", status="unknown"}'
values: '1x60'
- series: 'windows_scheduled_task_last_result_status{job="windows-custom", instance="host:9182", cluster="test", task="/Retired", status="unknown"}'
values: '1x60'
- series: 'windows_scheduled_task_state{job="windows-custom", instance="host:9182", cluster="test", task="/Retired", state="disabled"}'
values: '1x60'
- series: 'windows_scheduled_task_state{job="windows-custom", instance="host:9182", cluster="test", task="/Retired", state="ready"}'
values: '0x60'
- series: 'windows_scheduled_task_state{job="windows-custom", instance="host:9182", cluster="test", task="/Backup", state="disabled"}'
values: '0x60'
- series: 'windows_scheduled_task_state{job="windows-custom", instance="host:9182", cluster="test", task="/Backup", state="ready"}'
values: '1x60'
alert_rule_test:
- {alertname: WindowsScheduledTaskFailed, eval_time: 59m, exp_alerts: []}
- alertname: WindowsScheduledTaskFailed
eval_time: 60m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'host:9182', cluster: test, task: /Backup, status: unknown, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsscheduledtaskfailed/
summary: Windows scheduled task did not succeed
description: 'The last run of task /Backup on host:9182 ended with result unknown, and the task has not succeeded in the hour since.'
- exp_labels: {job: windows-custom, instance: 'host:9182', cluster: test, task: /Cleanup, status: terminated, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsscheduledtaskfailed/
summary: Windows scheduled task did not succeed
description: 'The last run of task /Cleanup on host:9182 ended with result terminated, and the task has not succeeded in the hour since.'
- name: Pending updates fire as info after the configured duration and count installations only
interval: 1m
input_series:
- series: 'windows_update_pending_info{job="windows-custom", instance="host:9182", cluster="test", id="a", revision="1", category="Security Updates", severity="Critical", title="KB1", deployment_action="installation"}'
values: '1x2880'
- series: 'windows_update_pending_info{job="windows-custom", instance="host:9182", cluster="test", id="b", revision="1", category="Updates", severity="", title="KB2", deployment_action="installation"}'
values: '1x2880'
- series: 'windows_update_pending_info{job="windows-custom", instance="host:9182", cluster="test", id="c", revision="1", category="Updates", severity="", title="KB3", deployment_action="uninstallation"}'
values: '1x2880'
- series: 'windows_update_pending_info{job="windows-custom", instance="clean:9182", cluster="test", id="d", revision="1", category="Updates", severity="", title="KB4", deployment_action="uninstallation"}'
values: '1x2880'
alert_rule_test:
- {alertname: WindowsUpdatesPending, eval_time: 47h, exp_alerts: []}
- alertname: WindowsUpdatesPending
eval_time: 48h
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'host:9182', cluster: test, deployment_action: installation, severity: info}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsupdatespending/
summary: Windows updates are waiting for installation
description: 'host:9182 has had 2 updates waiting for installation for 2d.'
- name: Hyper-V alerts cover the WMI namespace and both replication health levels
interval: 1m
input_series:
- series: 'windows_hyperv_wmi_health{job="windows-custom", instance="hv:9182", cluster="test"}'
values: '0x15'
- series: 'windows_hyperv_replica_vm_health{job="windows-custom", instance="hv:9182", cluster="test", vm="web", vm_id="1", relationship="primary"}'
values: '3x15'
- series: 'windows_hyperv_replica_vm_health{job="windows-custom", instance="hv:9182", cluster="test", vm="db", vm_id="2", relationship="extended"}'
values: '2x15'
- series: 'windows_hyperv_replica_vm_health{job="windows-custom", instance="hv:9182", cluster="test", vm="dev", vm_id="3", relationship="primary"}'
values: '0x15'
alert_rule_test:
- {alertname: WindowsHyperVWMIUnhealthy, eval_time: 9m, exp_alerts: []}
- alertname: WindowsHyperVWMIUnhealthy
eval_time: 10m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'hv:9182', cluster: test, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowshypervwmiunhealthy/
summary: Hyper-V WMI namespace is not responding
description: 'The Hyper-V WMI namespace on hv:9182 has not responded for 10 minutes; Hyper-V metrics are missing.'
- {alertname: WindowsHyperVReplicationCritical, eval_time: 4m, exp_alerts: []}
- alertname: WindowsHyperVReplicationCritical
eval_time: 5m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'hv:9182', cluster: test, vm: web, vm_id: '1', relationship: primary, severity: page}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowshypervreplicationcritical/
summary: Hyper-V replication is critical
description: 'Replication of virtual machine web (primary) on hv:9182 has been in critical health for 5 minutes.'
- {alertname: WindowsHyperVReplicationWarning, eval_time: 14m, exp_alerts: []}
- alertname: WindowsHyperVReplicationWarning
eval_time: 15m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'hv:9182', cluster: test, vm: db, vm_id: '2', relationship: extended, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowshypervreplicationwarning/
summary: Hyper-V replication has a warning
description: 'Replication of virtual machine db (extended) on hv:9182 has been in warning health for 15 minutes.'
- name: Cluster alerts fire for down nodes, failed resources and groups, and nearly full shared volumes
interval: 1m
input_series:
- series: 'windows_mscluster_node_state{job="windows-custom", instance="node1:9182", cluster="test", node="node2"}'
values: '1x30'
- series: 'windows_mscluster_node_state{job="windows-custom", instance="node1:9182", cluster="test", node="node1"}'
values: '0x30'
- series: 'windows_mscluster_node_state{job="windows-custom", instance="node3:9182", cluster="test", node="node2"}'
values: '1x30'
- series: 'windows_mscluster_resource_state{job="windows-custom", instance="node1:9182", cluster="test", type="IP Address", resource_group="SQL", resource="SQL IP"}'
values: '4x30'
- series: 'windows_mscluster_resource_state{job="windows-custom", instance="node1:9182", cluster="test", type="Network Name", resource_group="SQL", resource="SQL Name"}'
values: '3x30'
- series: 'windows_mscluster_resourcegroup_state{job="windows-custom", instance="node1:9182", cluster="test", resource_group="SQL"}'
values: '2x30'
- series: 'windows_mscluster_resourcegroup_state{job="windows-custom", instance="node1:9182", cluster="test", resource_group="Cluster Group"}'
values: '1x30'
- series: 'windows_mscluster_shared_volumes_free_bytes{job="windows-custom", instance="node1:9182", cluster="test", shared_volume="Volume1", volume_guid="g1"}'
values: '15x19 50x10'
- series: 'windows_mscluster_shared_volumes_total_bytes{job="windows-custom", instance="node1:9182", cluster="test", shared_volume="Volume1", volume_guid="g1"}'
values: '100x30'
- series: 'windows_mscluster_shared_volumes_free_bytes{job="windows-custom", instance="node1:9182", cluster="test", shared_volume="Volume2", volume_guid="g2"}'
values: '5x30'
- series: 'windows_mscluster_shared_volumes_total_bytes{job="windows-custom", instance="node1:9182", cluster="test", shared_volume="Volume2", volume_guid="g2"}'
values: '100x30'
- series: 'windows_mscluster_shared_volumes_free_bytes{job="windows-custom", instance="node1:9182", cluster="test", shared_volume="ClusterPerformanceHistory", volume_guid="g3"}'
values: '1x30'
- series: 'windows_mscluster_shared_volumes_total_bytes{job="windows-custom", instance="node1:9182", cluster="test", shared_volume="ClusterPerformanceHistory", volume_guid="g3"}'
values: '100x30'
- series: 'windows_mscluster_shared_volumes_free_bytes{job="windows-custom", instance="node1:9182", cluster="test", shared_volume="Empty", volume_guid="g4"}'
values: '0x30'
- series: 'windows_mscluster_shared_volumes_total_bytes{job="windows-custom", instance="node1:9182", cluster="test", shared_volume="Empty", volume_guid="g4"}'
values: '0x30'
alert_rule_test:
- {alertname: WindowsClusterNodeDown, eval_time: 4m, exp_alerts: []}
- alertname: WindowsClusterNodeDown
eval_time: 5m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'node1:9182', cluster: test, node: node2, severity: page}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsclusternodedown/
summary: Failover cluster node is down
description: 'Cluster node node2 has been down for 5 minutes, as reported by node1:9182.'
- exp_labels: {job: windows-custom, instance: 'node3:9182', cluster: test, node: node2, severity: page}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsclusternodedown/
summary: Failover cluster node is down
description: 'Cluster node node2 has been down for 5 minutes, as reported by node3:9182.'
- alertname: WindowsClusterResourceFailed
eval_time: 5m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'node1:9182', cluster: test, type: IP Address, resource_group: SQL, resource: SQL IP, severity: page}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsclusterresourcefailed/
summary: Failover cluster resource has failed
description: 'Cluster resource SQL IP (IP Address) in group SQL has been in the failed state for 5 minutes, as reported by node1:9182.'
- alertname: WindowsClusterResourceGroupFailed
eval_time: 5m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'node1:9182', cluster: test, resource_group: SQL, severity: page}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsclusterresourcegroupfailed/
summary: Failover cluster resource group has failed
description: 'Cluster resource group SQL has been in the failed state for 5 minutes, as reported by node1:9182.'
- {alertname: WindowsClusterSharedVolumeAlmostFull, eval_time: 14m, exp_alerts: []}
- alertname: WindowsClusterSharedVolumeAlmostFull
eval_time: 15m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'node1:9182', cluster: test, shared_volume: Volume1, volume_guid: g1, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsclustersharedvolumealmostfull/
summary: Cluster shared volume is almost full
description: 'Cluster shared volume Volume1 has had less than 20% free space for 15 minutes, as reported by node1:9182.'
- exp_labels: {job: windows-custom, instance: 'node1:9182', cluster: test, shared_volume: Volume2, volume_guid: g2, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsclustersharedvolumealmostfull/
summary: Cluster shared volume is almost full
description: 'Cluster shared volume Volume2 has had less than 20% free space for 15 minutes, as reported by node1:9182.'
- exp_labels: {job: windows-custom, instance: 'node1:9182', cluster: test, shared_volume: Volume2, volume_guid: g2, severity: page}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsclustersharedvolumealmostfull/
summary: Cluster shared volume is almost full
description: 'Cluster shared volume Volume2 has had less than 10% free space for 15 minutes, as reported by node1:9182.'
- alertname: WindowsClusterSharedVolumeAlmostFull
eval_time: 24m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'node1:9182', cluster: test, shared_volume: Volume1, volume_guid: g1, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsclustersharedvolumealmostfull/
summary: Cluster shared volume is almost full
description: 'Cluster shared volume Volume1 has had less than 20% free space for 15 minutes, as reported by node1:9182.'
- exp_labels: {job: windows-custom, instance: 'node1:9182', cluster: test, shared_volume: Volume2, volume_guid: g2, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsclustersharedvolumealmostfull/
summary: Cluster shared volume is almost full
description: 'Cluster shared volume Volume2 has had less than 20% free space for 15 minutes, as reported by node1:9182.'
- exp_labels: {job: windows-custom, instance: 'node1:9182', cluster: test, shared_volume: Volume2, volume_guid: g2, severity: page}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsclustersharedvolumealmostfull/
summary: Cluster shared volume is almost full
description: 'Cluster shared volume Volume2 has had less than 10% free space for 15 minutes, as reported by node1:9182.'
- alertname: WindowsClusterSharedVolumeAlmostFull
eval_time: 25m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'node1:9182', cluster: test, shared_volume: Volume2, volume_guid: g2, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsclustersharedvolumealmostfull/
summary: Cluster shared volume is almost full
description: 'Cluster shared volume Volume2 has had less than 20% free space for 15 minutes, as reported by node1:9182.'
- exp_labels: {job: windows-custom, instance: 'node1:9182', cluster: test, shared_volume: Volume2, volume_guid: g2, severity: page}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsclustersharedvolumealmostfull/
summary: Cluster shared volume is almost full
description: 'Cluster shared volume Volume2 has had less than 10% free space for 15 minutes, as reported by node1:9182.'
- name: Storage Spaces alerts skip the primordial pool and separate warning from unhealthy
interval: 1m
input_series:
- series: 'windows_storage_spaces_pool_health_status{job="windows-custom", instance="host:9182", cluster="test", pool="Pool A", unique_id="a"}'
values: '2x15'
- series: 'windows_storage_spaces_pool_info{job="windows-custom", instance="host:9182", cluster="test", pool="Pool A", unique_id="a", primordial="false"}'
values: '1x15'
- series: 'windows_storage_spaces_pool_health_status{job="windows-custom", instance="host:9182", cluster="test", pool="Pool B", unique_id="b"}'
values: '1x15'
- series: 'windows_storage_spaces_pool_info{job="windows-custom", instance="host:9182", cluster="test", pool="Pool B", unique_id="b", primordial="false"}'
values: '1x15'
- series: 'windows_storage_spaces_pool_health_status{job="windows-custom", instance="host:9182", cluster="test", pool="Primordial", unique_id="p"}'
values: '2x15'
- series: 'windows_storage_spaces_pool_info{job="windows-custom", instance="host:9182", cluster="test", pool="Primordial", unique_id="p", primordial="true"}'
values: '1x15'
- series: 'windows_storage_spaces_virtual_disk_health_status{job="windows-custom", instance="host:9182", cluster="test", virtual_disk="Data", unique_id="v1"}'
values: '2x15'
- series: 'windows_storage_spaces_virtual_disk_health_status{job="windows-custom", instance="host:9182", cluster="test", virtual_disk="Logs", unique_id="v2"}'
values: '1x15'
- series: 'windows_storage_spaces_virtual_disk_health_status{job="windows-custom", instance="host:9182", cluster="test", virtual_disk="Scratch", unique_id="v3"}'
values: '0x15'
alert_rule_test:
- {alertname: WindowsStoragePoolUnhealthy, eval_time: 9m, exp_alerts: []}
- alertname: WindowsStoragePoolUnhealthy
eval_time: 10m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'host:9182', cluster: test, pool: Pool A, unique_id: a, severity: page}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsstoragepoolunhealthy/
summary: Storage pool is unhealthy
description: 'Storage pool Pool A on host:9182 has reported unhealthy status for 10 minutes.'
- exp_labels: {job: windows-custom, instance: 'host:9182', cluster: test, pool: Pool B, unique_id: b, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsstoragepoolunhealthy/
summary: Storage pool has a health warning
description: 'Storage pool Pool B on host:9182 has reported warning status for 10 minutes.'
- alertname: WindowsStorageVirtualDiskUnhealthy
eval_time: 10m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'host:9182', cluster: test, virtual_disk: Data, unique_id: v1, severity: page}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsstoragevirtualdiskunhealthy/
summary: Storage Spaces virtual disk is unhealthy
description: 'Virtual disk Data on host:9182 has reported unhealthy status for 10 minutes.'
- exp_labels: {job: windows-custom, instance: 'host:9182', cluster: test, virtual_disk: Logs, unique_id: v2, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsstoragevirtualdiskunhealthy/
summary: Storage Spaces virtual disk has a health warning
description: 'Virtual disk Logs on host:9182 has reported warning status for 10 minutes.'
- name: DHCP scope exhaustion counts active scopes only and uses both thresholds
interval: 1m
input_series:
- series: 'windows_dhcp_scope_addresses_free{job="windows-custom", instance="dhcp:9182", cluster="test", scope="10.0.0.0/24"}'
values: '10x19 50x10'
- series: 'windows_dhcp_scope_addresses_in_use{job="windows-custom", instance="dhcp:9182", cluster="test", scope="10.0.0.0/24"}'
values: '90x19 50x10'
- series: 'windows_dhcp_scope_state{job="windows-custom", instance="dhcp:9182", cluster="test", scope="10.0.0.0/24", state="Enabled"}'
values: '1x30'
- series: 'windows_dhcp_scope_state{job="windows-custom", instance="dhcp:9182", cluster="test", scope="10.0.0.0/24", state="Disabled"}'
values: '0x30'
- series: 'windows_dhcp_scope_addresses_free{job="windows-custom", instance="dhcp:9182", cluster="test", scope="10.0.1.0/24"}'
values: '2x30'
- series: 'windows_dhcp_scope_addresses_in_use{job="windows-custom", instance="dhcp:9182", cluster="test", scope="10.0.1.0/24"}'
values: '98x30'
- series: 'windows_dhcp_scope_state{job="windows-custom", instance="dhcp:9182", cluster="test", scope="10.0.1.0/24", state="EnabledSwitched"}'
values: '1x30'
- series: 'windows_dhcp_scope_addresses_free{job="windows-custom", instance="dhcp:9182", cluster="test", scope="10.0.2.0/24"}'
values: '0x30'
- series: 'windows_dhcp_scope_addresses_in_use{job="windows-custom", instance="dhcp:9182", cluster="test", scope="10.0.2.0/24"}'
values: '100x30'
- series: 'windows_dhcp_scope_state{job="windows-custom", instance="dhcp:9182", cluster="test", scope="10.0.2.0/24", state="Disabled"}'
values: '1x30'
- series: 'windows_dhcp_scope_state{job="windows-custom", instance="dhcp:9182", cluster="test", scope="10.0.2.0/24", state="Enabled"}'
values: '0x30'
- series: 'windows_dhcp_scope_addresses_free{job="windows-custom", instance="dhcp:9182", cluster="test", scope="10.0.3.0/24"}'
values: '0x30'
- series: 'windows_dhcp_scope_addresses_in_use{job="windows-custom", instance="dhcp:9182", cluster="test", scope="10.0.3.0/24"}'
values: '0x30'
- series: 'windows_dhcp_scope_state{job="windows-custom", instance="dhcp:9182", cluster="test", scope="10.0.3.0/24", state="Enabled"}'
values: '1x30'
alert_rule_test:
- {alertname: WindowsDHCPScopeAlmostExhausted, eval_time: 14m, exp_alerts: []}
- alertname: WindowsDHCPScopeAlmostExhausted
eval_time: 15m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'dhcp:9182', cluster: test, scope: 10.0.0.0/24, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsdhcpscopealmostexhausted/
summary: DHCP scope is almost exhausted
description: 'DHCP scope 10.0.0.0/24 on dhcp:9182 has had less than 20% free addresses for 15 minutes.'
- exp_labels: {job: windows-custom, instance: 'dhcp:9182', cluster: test, scope: 10.0.1.0/24, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsdhcpscopealmostexhausted/
summary: DHCP scope is almost exhausted
description: 'DHCP scope 10.0.1.0/24 on dhcp:9182 has had less than 20% free addresses for 15 minutes.'
- exp_labels: {job: windows-custom, instance: 'dhcp:9182', cluster: test, scope: 10.0.1.0/24, severity: page}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsdhcpscopealmostexhausted/
summary: DHCP scope is almost exhausted
description: 'DHCP scope 10.0.1.0/24 on dhcp:9182 has had less than 5% free addresses for 15 minutes.'
- alertname: WindowsDHCPScopeAlmostExhausted
eval_time: 24m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'dhcp:9182', cluster: test, scope: 10.0.0.0/24, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsdhcpscopealmostexhausted/
summary: DHCP scope is almost exhausted
description: 'DHCP scope 10.0.0.0/24 on dhcp:9182 has had less than 20% free addresses for 15 minutes.'
- exp_labels: {job: windows-custom, instance: 'dhcp:9182', cluster: test, scope: 10.0.1.0/24, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsdhcpscopealmostexhausted/
summary: DHCP scope is almost exhausted
description: 'DHCP scope 10.0.1.0/24 on dhcp:9182 has had less than 20% free addresses for 15 minutes.'
- exp_labels: {job: windows-custom, instance: 'dhcp:9182', cluster: test, scope: 10.0.1.0/24, severity: page}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsdhcpscopealmostexhausted/
summary: DHCP scope is almost exhausted
description: 'DHCP scope 10.0.1.0/24 on dhcp:9182 has had less than 5% free addresses for 15 minutes.'
- alertname: WindowsDHCPScopeAlmostExhausted
eval_time: 25m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'dhcp:9182', cluster: test, scope: 10.0.1.0/24, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsdhcpscopealmostexhausted/
summary: DHCP scope is almost exhausted
description: 'DHCP scope 10.0.1.0/24 on dhcp:9182 has had less than 20% free addresses for 15 minutes.'
- exp_labels: {job: windows-custom, instance: 'dhcp:9182', cluster: test, scope: 10.0.1.0/24, severity: page}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsdhcpscopealmostexhausted/
summary: DHCP scope is almost exhausted
description: 'DHCP scope 10.0.1.0/24 on dhcp:9182 has had less than 5% free addresses for 15 minutes.'
- name: DNS zone transfer failures fire on a rising counter and resolve after keep_firing_for
interval: 1m
input_series:
- series: 'windows_dns_zone_transfer_failures_total{job="windows-custom", instance="dns:9182", cluster="test"}'
values: '0+6x20 120x15'
- series: 'windows_dns_zone_transfer_failures_total{job="windows-custom", instance="quiet:9182", cluster="test"}'
values: '7x36'
- series: 'windows_dns_zone_transfer_failures_total{job="windows-custom", instance="scanned:9182", cluster="test"}'
values: '0+1x36'
alert_rule_test:
- {alertname: WindowsDNSZoneTransferFailures, eval_time: 16m, exp_alerts: []}
- alertname: WindowsDNSZoneTransferFailures
eval_time: 17m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'dns:9182', cluster: test, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsdnszonetransferfailures/
summary: DNS zone transfers are failing
description: 'Zone transfers from DNS server dns:9182 have been failing for 15 minutes.'
- alertname: WindowsDNSZoneTransferFailures
eval_time: 25m
exp_alerts:
- exp_labels: {job: windows-custom, instance: 'dns:9182', cluster: test, severity: warning}
exp_annotations:
runbook_url: https://runbooks.example.com/windows/windowsdnszonetransferfailures/
summary: DNS zone transfers are failing
description: 'Zone transfers from DNS server dns:9182 have been failing for 15 minutes.'
- {alertname: WindowsDNSZoneTransferFailures, eval_time: 26m, exp_alerts: []}
Reference in New Issue View Git Blame Copy Permalink