mirror of
https://github.com/prometheus-community/windows_exporter.git
synced 2026-10-19 19:19:04 +02:00
Jan-Otto Kröpke
d6afd48819
WindowsHostRebooted compares against the last boot time of the previous hour instead of the sample of ten minutes ago, so a scrape gap during the reboot no longer suppresses the alert. WindowsServiceNotRunning joins with ignoring() so instances with the same name in different clusters do not match each other. Replacing the removed networkErrorRateThreshold or networkDiscardRateThreshold knobs now fails with a message naming the ratio thresholds. The network error and discard runbooks describe the packet ratio, the service runbooks explain PID reuse, shared host processes and selector exclusions, and the tests cover alert recovery, a reboot after a scrape gap and a service name repeated across clusters. Signed-off-by: Jan-Otto Kröpke <mail@jkroepke.de>
582 lines
34 KiB
YAML
582 lines
34 KiB
YAML
rule_files:
|
||
- ../windows_rules.yaml
|
||
- ../windows_alerts.yaml
|
||
evaluation_interval: 1m
|
||
group_eval_order:
|
||
- windows-exporter-recording
|
||
- windows-exporter
|
||
- windows-cpu
|
||
- windows-memory
|
||
- windows-disk
|
||
- windows-network
|
||
- windows-service
|
||
- windows-system
|
||
- windows-active-directory
|
||
- windows-time
|
||
|
||
tests:
|
||
- name: Commit pressure, disk latency and network failures wait and recover
|
||
interval: 1m
|
||
input_series:
|
||
- series: 'windows_memory_committed_bytes{job="windows_exporter", instance="host:9182", cluster="a"}'
|
||
values: '95x20 50x10'
|
||
- series: 'windows_memory_commit_limit_bytes{job="windows_exporter", instance="host:9182", cluster="a"}'
|
||
values: '100x31'
|
||
- series: 'windows_logical_disk_read_seconds_total{job="windows_exporter", instance="host:9182", cluster="a", volume="C:"}'
|
||
values: '0+12x20 252x10'
|
||
- series: 'windows_logical_disk_reads_total{job="windows_exporter", instance="host:9182", cluster="a", volume="C:"}'
|
||
values: '0+120x31'
|
||
- series: 'windows_logical_disk_write_seconds_total{job="windows_exporter", instance="host:9182", cluster="a", volume="C:"}'
|
||
values: '0+24x20 504x10'
|
||
- series: 'windows_logical_disk_writes_total{job="windows_exporter", instance="host:9182", cluster="a", volume="C:"}'
|
||
values: '0+240x31'
|
||
- series: 'windows_net_packets_received_errors_total{job="windows_exporter", instance="host:9182", cluster="a", nic="Ethernet"}'
|
||
values: '0+120x20 2520x10'
|
||
- series: 'windows_net_packets_outbound_errors_total{job="windows_exporter", instance="host:9182", cluster="a", nic="Ethernet"}'
|
||
values: '0x31'
|
||
- series: 'windows_net_packets_received_discarded_total{job="windows_exporter", instance="host:9182", cluster="a", nic="Ethernet"}'
|
||
values: '0x31'
|
||
- series: 'windows_net_packets_outbound_discarded_total{job="windows_exporter", instance="host:9182", cluster="a", nic="Ethernet"}'
|
||
values: '0+120x20 2520x10'
|
||
- series: 'windows_net_packets_received_total{job="windows_exporter", instance="host:9182", cluster="a", nic="Ethernet"}'
|
||
values: '0+3000x31'
|
||
- series: 'windows_net_packets_sent_total{job="windows_exporter", instance="host:9182", cluster="a", nic="Ethernet"}'
|
||
values: '0+3000x31'
|
||
alert_rule_test:
|
||
- {alertname: WindowsMemoryCommitHighUsage, eval_time: 14m, exp_alerts: []}
|
||
- alertname: WindowsMemoryCommitHighUsage
|
||
eval_time: 15m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', cluster: a, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsmemorycommithighusage/
|
||
summary: Windows memory commit usage is high
|
||
description: 'Committed memory on host:9182 has exceeded 90% of the commit limit for 15 minutes.'
|
||
- {alertname: WindowsMemoryCommitHighUsage, eval_time: 25m, exp_alerts: [{exp_labels: {job: windows_exporter, instance: 'host:9182', cluster: a, severity: warning}, exp_annotations: {runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsmemorycommithighusage/, summary: Windows memory commit usage is high, description: 'Committed memory on host:9182 has exceeded 90% of the commit limit for 15 minutes.'}}]}
|
||
- {alertname: WindowsMemoryCommitHighUsage, eval_time: 26m, exp_alerts: []}
|
||
- {alertname: WindowsDiskReadLatencyHigh, eval_time: 15m, exp_alerts: []}
|
||
- alertname: WindowsDiskReadLatencyHigh
|
||
eval_time: 16m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', cluster: a, volume: 'C:', severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsdiskreadlatencyhigh/
|
||
summary: Windows disk read latency is high
|
||
description: 'Volume C: on host:9182 has averaged more than 0.05 seconds per read operation for 15 minutes.'
|
||
- {alertname: WindowsDiskReadLatencyHigh, eval_time: 30m, exp_alerts: []}
|
||
- {alertname: WindowsDiskWriteLatencyHigh, eval_time: 15m, exp_alerts: []}
|
||
- alertname: WindowsDiskWriteLatencyHigh
|
||
eval_time: 16m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', cluster: a, volume: 'C:', severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsdiskwritelatencyhigh/
|
||
summary: Windows disk write latency is high
|
||
description: 'Volume C: on host:9182 has averaged more than 0.05 seconds per write operation for 15 minutes.'
|
||
- {alertname: WindowsDiskWriteLatencyHigh, eval_time: 30m, exp_alerts: []}
|
||
- {alertname: WindowsNetworkErrors, eval_time: 15m, exp_alerts: []}
|
||
- alertname: WindowsNetworkErrors
|
||
eval_time: 16m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', cluster: a, nic: Ethernet, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsnetworkerrors/
|
||
summary: Windows network packet errors are high
|
||
description: 'Packet errors on interface Ethernet on host:9182 have exceeded 1% of all packets for 15 minutes.'
|
||
- {alertname: WindowsNetworkErrors, eval_time: 30m, exp_alerts: []}
|
||
- {alertname: WindowsNetworkDiscards, eval_time: 15m, exp_alerts: []}
|
||
- alertname: WindowsNetworkDiscards
|
||
eval_time: 16m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', cluster: a, nic: Ethernet, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsnetworkdiscards/
|
||
summary: Windows network packet discards are high
|
||
description: 'Packet discards on interface Ethernet on host:9182 have exceeded 1% of all packets for 15 minutes.'
|
||
- {alertname: WindowsNetworkDiscards, eval_time: 30m, exp_alerts: []}
|
||
|
||
- name: New resource alerts stay quiet at exact thresholds and clock alerts are disabled
|
||
interval: 1m
|
||
input_series:
|
||
- series: 'windows_memory_committed_bytes{job="windows_exporter", instance="host:9182"}'
|
||
values: '90x20'
|
||
- series: 'windows_memory_commit_limit_bytes{job="windows_exporter", instance="host:9182"}'
|
||
values: '100x20'
|
||
- series: 'windows_logical_disk_read_seconds_total{job="windows_exporter", instance="host:9182", volume="C:"}'
|
||
values: '0+6x20'
|
||
- series: 'windows_logical_disk_reads_total{job="windows_exporter", instance="host:9182", volume="C:"}'
|
||
values: '0+120x20'
|
||
- series: 'windows_logical_disk_write_seconds_total{job="windows_exporter", instance="host:9182", volume="C:"}'
|
||
values: '0+6x20'
|
||
- series: 'windows_logical_disk_writes_total{job="windows_exporter", instance="host:9182", volume="C:"}'
|
||
values: '0+120x20'
|
||
- series: 'windows_net_packets_received_errors_total{job="windows_exporter", instance="host:9182", nic="Ethernet"}'
|
||
values: '0+30x20'
|
||
- series: 'windows_net_packets_outbound_errors_total{job="windows_exporter", instance="host:9182", nic="Ethernet"}'
|
||
values: '0+30x20'
|
||
- series: 'windows_net_packets_received_discarded_total{job="windows_exporter", instance="host:9182", nic="Ethernet"}'
|
||
values: '0+30x20'
|
||
- series: 'windows_net_packets_outbound_discarded_total{job="windows_exporter", instance="host:9182", nic="Ethernet"}'
|
||
values: '0+30x20'
|
||
- series: 'windows_net_packets_received_total{job="windows_exporter", instance="host:9182", nic="Ethernet"}'
|
||
values: '0+3600x20'
|
||
- series: 'windows_net_packets_sent_total{job="windows_exporter", instance="host:9182", nic="Ethernet"}'
|
||
values: '0+3600x20'
|
||
- series: 'windows_time_ntp_client_time_sources{job="windows_exporter", instance="host:9182"}'
|
||
values: '0x20'
|
||
- series: 'windows_time_computed_time_offset_seconds{job="windows_exporter", instance="host:9182"}'
|
||
values: '1x20'
|
||
alert_rule_test:
|
||
- {alertname: WindowsMemoryCommitHighUsage, eval_time: 20m, exp_alerts: []}
|
||
- {alertname: WindowsDiskReadLatencyHigh, eval_time: 20m, exp_alerts: []}
|
||
- {alertname: WindowsDiskWriteLatencyHigh, eval_time: 20m, exp_alerts: []}
|
||
- {alertname: WindowsNetworkErrors, eval_time: 20m, exp_alerts: []}
|
||
- {alertname: WindowsNetworkDiscards, eval_time: 20m, exp_alerts: []}
|
||
- {alertname: WindowsClockNotSynchronising, eval_time: 20m, exp_alerts: []}
|
||
- {alertname: WindowsClockSkewDetected, eval_time: 20m, exp_alerts: []}
|
||
- name: Exporter and collector failures wait five minutes and recover
|
||
interval: 1m
|
||
input_series:
|
||
- series: 'up{job="windows_exporter", instance="host:9182"}'
|
||
values: '0x5 1x5'
|
||
- series: 'up{job="other", instance="other:9182"}'
|
||
values: '0x10'
|
||
- series: 'windows_exporter_collector_success{job="windows_exporter", instance="host:9182", collector="cpu"}'
|
||
values: '0x5 1x5'
|
||
alert_rule_test:
|
||
- alertname: WindowsExporterDown
|
||
eval_time: 4m
|
||
exp_alerts: []
|
||
- alertname: WindowsExporterDown
|
||
eval_time: 5m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', severity: critical}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsexporterdown/
|
||
summary: Windows exporter is unreachable
|
||
description: 'Prometheus cannot scrape Windows exporter on host:9182 (job windows_exporter).'
|
||
- alertname: WindowsExporterDown
|
||
eval_time: 6m
|
||
exp_alerts: []
|
||
- alertname: WindowsCollectorFailed
|
||
eval_time: 4m
|
||
exp_alerts: []
|
||
- alertname: WindowsCollectorFailed
|
||
eval_time: 5m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', collector: cpu, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowscollectorfailed/
|
||
summary: Windows collector failed
|
||
description: 'Collector cpu on host:9182 has failed for at least 5 minutes.'
|
||
- alertname: WindowsCollectorFailed
|
||
eval_time: 6m
|
||
exp_alerts: []
|
||
|
||
- name: Resource alerts use recording rules and wait fifteen minutes
|
||
interval: 1m
|
||
input_series:
|
||
- series: 'windows_cpu_time_seconds_total{job="windows_exporter", instance="host:9182", cluster="a", core="0", mode="idle"}'
|
||
values: '0+3x20 120+60x10'
|
||
- series: 'windows_memory_available_bytes{job="windows_exporter", instance="host:9182", cluster="a"}'
|
||
values: '5x20 50x10'
|
||
- series: 'windows_memory_physical_total_bytes{job="windows_exporter", instance="host:9182", cluster="a"}'
|
||
values: '100x31'
|
||
alert_rule_test:
|
||
- alertname: WindowsCPUHighUsage
|
||
eval_time: 15m
|
||
exp_alerts: []
|
||
- alertname: WindowsCPUHighUsage
|
||
eval_time: 16m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', cluster: a, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowscpuhighusage/
|
||
summary: Windows CPU usage is high
|
||
description: 'CPU usage on host:9182 has exceeded 90% for 15 minutes.'
|
||
- alertname: WindowsCPUHighUsage
|
||
eval_time: 30m
|
||
exp_alerts: []
|
||
- alertname: WindowsMemoryHighUsage
|
||
eval_time: 14m
|
||
exp_alerts: []
|
||
- alertname: WindowsMemoryHighUsage
|
||
eval_time: 15m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', cluster: a, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsmemoryhighusage/
|
||
summary: Windows memory usage is high
|
||
description: 'Physical memory usage on host:9182 has exceeded 90% for 15 minutes.'
|
||
- alertname: WindowsMemoryHighUsage
|
||
eval_time: 26m
|
||
exp_alerts: []
|
||
|
||
- name: Disk alerts retain volume labels and fire at both severity levels
|
||
interval: 1m
|
||
input_series:
|
||
- series: 'windows_logical_disk_free_bytes{job="windows_exporter", instance="host:9182", volume="C:"}'
|
||
values: '3x15 30x10'
|
||
- series: 'windows_logical_disk_size_bytes{job="windows_exporter", instance="host:9182", volume="C:"}'
|
||
values: '100x26'
|
||
alert_rule_test:
|
||
- alertname: WindowsDiskAlmostFull
|
||
eval_time: 14m
|
||
exp_alerts: []
|
||
- alertname: WindowsDiskAlmostFull
|
||
eval_time: 15m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', volume: 'C:', severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsdiskalmostfull/
|
||
summary: Windows disk space is low
|
||
description: 'Volume C: on host:9182 has less than 10% free space. Windows may delay space metrics by 10–15 minutes.'
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', volume: 'C:', severity: critical}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsdiskalmostfull/
|
||
summary: Windows disk space is low
|
||
description: 'Volume C: on host:9182 has less than 5% free space. Windows may delay space metrics by 10–15 minutes.'
|
||
- alertname: WindowsDiskAlmostFull
|
||
eval_time: 21m
|
||
exp_alerts: []
|
||
|
||
- name: Healthy resources at the exact thresholds do not fire
|
||
interval: 1m
|
||
input_series:
|
||
- series: 'windows_cpu_time_seconds_total{job="windows_exporter", instance="host:9182", core="0", mode="idle"}'
|
||
values: '0+6x20'
|
||
- series: 'windows_memory_available_bytes{job="windows_exporter", instance="host:9182"}'
|
||
values: '10x20'
|
||
- series: 'windows_memory_physical_total_bytes{job="windows_exporter", instance="host:9182"}'
|
||
values: '100x20'
|
||
- series: 'windows_logical_disk_free_bytes{job="windows_exporter", instance="host:9182", volume="C:"}'
|
||
values: '10x20'
|
||
- series: 'windows_logical_disk_size_bytes{job="windows_exporter", instance="host:9182", volume="C:"}'
|
||
values: '100x20'
|
||
alert_rule_test:
|
||
- {alertname: WindowsCPUHighUsage, eval_time: 20m, exp_alerts: []}
|
||
- {alertname: WindowsMemoryHighUsage, eval_time: 20m, exp_alerts: []}
|
||
- {alertname: WindowsDiskAlmostFull, eval_time: 20m, exp_alerts: []}
|
||
|
||
- name: Prediction fires only for low and declining disk space
|
||
interval: 1m
|
||
input_series:
|
||
- series: 'windows_logical_disk_free_bytes{job="windows_exporter", instance="host:9182", cluster="a", volume="C:"}'
|
||
values: '1000-1x420'
|
||
- series: 'windows_logical_disk_size_bytes{job="windows_exporter", instance="host:9182", cluster="a", volume="C:"}'
|
||
values: '20000x420'
|
||
- series: 'windows_logical_disk_free_bytes{job="windows_exporter", instance="host:9182", cluster="a", volume="D:"}'
|
||
values: '1000x420'
|
||
- series: 'windows_logical_disk_size_bytes{job="windows_exporter", instance="host:9182", cluster="a", volume="D:"}'
|
||
values: '20000x420'
|
||
- series: 'windows_logical_disk_free_bytes{job="windows_exporter", instance="host:9182", cluster="a", volume="E:"}'
|
||
values: '500+1x420'
|
||
- series: 'windows_logical_disk_size_bytes{job="windows_exporter", instance="host:9182", cluster="a", volume="E:"}'
|
||
values: '20000x420'
|
||
- series: 'windows_logical_disk_free_bytes{job="windows_exporter", instance="host:9182", cluster="b", volume="C:"}'
|
||
values: '1000x420'
|
||
- series: 'windows_logical_disk_size_bytes{job="windows_exporter", instance="host:9182", cluster="b", volume="C:"}'
|
||
values: '20000x420'
|
||
alert_rule_test:
|
||
- alertname: WindowsDiskFillingUp
|
||
eval_time: 60m
|
||
exp_alerts: []
|
||
- alertname: WindowsDiskFillingUp
|
||
eval_time: 61m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', cluster: a, volume: 'C:', severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsdiskfillingup/
|
||
summary: Windows disk is predicted to fill up
|
||
description: 'Volume C: on host:9182 is predicted to fill within 24 hours.'
|
||
- alertname: WindowsDiskFillingUp
|
||
eval_time: 7h
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', cluster: a, volume: 'C:', severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsdiskfillingup/
|
||
summary: Windows disk is predicted to fill up
|
||
description: 'Volume C: on host:9182 is predicted to fill within 24 hours.'
|
||
|
||
- name: Missing collector metrics do not produce resource alerts
|
||
interval: 1m
|
||
input_series:
|
||
- series: 'up{job="windows_exporter", instance="host:9182"}'
|
||
values: '1x70'
|
||
alert_rule_test:
|
||
- {alertname: WindowsCPUHighUsage, eval_time: 70m, exp_alerts: []}
|
||
- {alertname: WindowsMemoryHighUsage, eval_time: 70m, exp_alerts: []}
|
||
- {alertname: WindowsDiskAlmostFull, eval_time: 70m, exp_alerts: []}
|
||
- {alertname: WindowsDiskFillingUp, eval_time: 70m, exp_alerts: []}
|
||
|
||
- name: Collector and scrape queue timeouts wait ten minutes and recover without keep_firing_for
|
||
interval: 1m
|
||
input_series:
|
||
- series: 'windows_exporter_collector_timeout{job="windows_exporter", instance="host:9182", collector="service"}'
|
||
values: '1x10 0x5'
|
||
- series: 'windows_exporter_collector_timeout{job="windows_exporter", instance="host:9182", collector="cpu"}'
|
||
values: '0x15'
|
||
- series: 'windows_exporter_scrape_queue_timeout{job="windows_exporter", instance="host:9182"}'
|
||
values: '1x10 0x5'
|
||
alert_rule_test:
|
||
- {alertname: WindowsCollectorTimeout, eval_time: 9m, exp_alerts: []}
|
||
- alertname: WindowsCollectorTimeout
|
||
eval_time: 10m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', collector: service, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowscollectortimeout/
|
||
summary: Windows collector exceeds the scrape timeout
|
||
description: 'Collector service on host:9182 has not finished within the scrape timeout for 10 minutes.'
|
||
- {alertname: WindowsCollectorTimeout, eval_time: 11m, exp_alerts: []}
|
||
- {alertname: WindowsScrapeQueueTimeout, eval_time: 9m, exp_alerts: []}
|
||
- alertname: WindowsScrapeQueueTimeout
|
||
eval_time: 10m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsscrapequeuetimeout/
|
||
summary: Windows exporter scrapes time out in the queue
|
||
description: 'Scrapes of host:9182 have timed out waiting for an earlier scrape to finish for 10 minutes.'
|
||
- {alertname: WindowsScrapeQueueTimeout, eval_time: 11m, exp_alerts: []}
|
||
|
||
- name: CPU saturation and paging use recordings, wait fifteen minutes and keep firing five
|
||
interval: 1m
|
||
input_series:
|
||
- series: 'windows_system_processor_queue_length{job="windows_exporter", instance="host:9182", cluster="a"}'
|
||
values: '9x25 0x10'
|
||
- series: 'windows_cpu_time_seconds_total{job="windows_exporter", instance="host:9182", cluster="a", core="0", mode="idle"}'
|
||
values: '0+60x35'
|
||
- series: 'windows_cpu_time_seconds_total{job="windows_exporter", instance="host:9182", cluster="a", core="1", mode="idle"}'
|
||
values: '0+60x35'
|
||
- series: 'windows_cpu_time_seconds_total{job="windows_exporter", instance="host:9182", cluster="a", core="2", mode="idle"}'
|
||
values: '0+60x35'
|
||
- series: 'windows_memory_swap_page_operations_total{job="windows_exporter", instance="host:9182", cluster="a"}'
|
||
values: '0+90000x20 1800000x15'
|
||
alert_rule_test:
|
||
- {alertname: WindowsCPUSaturation, eval_time: 14m, exp_alerts: []}
|
||
- alertname: WindowsCPUSaturation
|
||
eval_time: 15m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', cluster: a, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowscpusaturation/
|
||
summary: Windows processor queue is long
|
||
description: 'More than 2 threads per logical processor have been waiting for CPU time on host:9182 for 15 minutes.'
|
||
- alertname: WindowsCPUSaturation
|
||
eval_time: 31m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', cluster: a, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowscpusaturation/
|
||
summary: Windows processor queue is long
|
||
description: 'More than 2 threads per logical processor have been waiting for CPU time on host:9182 for 15 minutes.'
|
||
- {alertname: WindowsCPUSaturation, eval_time: 32m, exp_alerts: []}
|
||
- {alertname: WindowsMemoryPagingHigh, eval_time: 18m, exp_alerts: []}
|
||
- alertname: WindowsMemoryPagingHigh
|
||
eval_time: 19m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', cluster: a, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsmemorypaginghigh/
|
||
summary: Windows memory paging is high
|
||
description: 'Paging on host:9182 has exceeded 1000 pages per second for 15 minutes.'
|
||
- alertname: WindowsMemoryPagingHigh
|
||
eval_time: 26m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', cluster: a, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsmemorypaginghigh/
|
||
summary: Windows memory paging is high
|
||
description: 'Paging on host:9182 has exceeded 1000 pages per second for 15 minutes.'
|
||
- {alertname: WindowsMemoryPagingHigh, eval_time: 27m, exp_alerts: []}
|
||
|
||
- name: Network utilization fires in one direction and interface flapping counts status changes
|
||
interval: 1m
|
||
input_series:
|
||
- series: 'windows_net_bytes_received_total{job="windows_exporter", instance="host:9182", nic="Ethernet"}'
|
||
values: '0+6000x20 120000x15'
|
||
- series: 'windows_net_bytes_sent_total{job="windows_exporter", instance="host:9182", nic="Ethernet"}'
|
||
values: '0x36'
|
||
- series: 'windows_net_current_bandwidth_bytes{job="windows_exporter", instance="host:9182", nic="Ethernet"}'
|
||
values: '100x36'
|
||
- series: 'windows_net_nic_operation_status{job="windows_exporter", instance="host:9182", nic="Ethernet", status="up"}'
|
||
values: '1 0 1 0 1 0 1 0 1 0 1x10'
|
||
- series: 'windows_net_nic_operation_status{job="windows_exporter", instance="host:9182", nic="Ethernet", status="down"}'
|
||
values: '0 1 0 1 0 1 0 1 0 1 0x10'
|
||
- series: 'windows_net_nic_operation_status{job="windows_exporter", instance="host:9182", nic="Wi-Fi", status="up"}'
|
||
values: '0x21'
|
||
alert_rule_test:
|
||
- {alertname: WindowsNetworkUtilizationHigh, eval_time: 19m, exp_alerts: []}
|
||
- alertname: WindowsNetworkUtilizationHigh
|
||
eval_time: 20m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', nic: Ethernet, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsnetworkutilizationhigh/
|
||
summary: Windows network interface utilization is high
|
||
description: 'Traffic on interface Ethernet on host:9182 has exceeded 90% of its bandwidth in at least one direction for 15 minutes.'
|
||
- alertname: WindowsNetworkUtilizationHigh
|
||
eval_time: 25m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', nic: Ethernet, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsnetworkutilizationhigh/
|
||
summary: Windows network interface utilization is high
|
||
description: 'Traffic on interface Ethernet on host:9182 has exceeded 90% of its bandwidth in at least one direction for 15 minutes.'
|
||
- {alertname: WindowsNetworkUtilizationHigh, eval_time: 26m, exp_alerts: []}
|
||
- {alertname: WindowsNetworkInterfaceFlapping, eval_time: 4m, exp_alerts: []}
|
||
- alertname: WindowsNetworkInterfaceFlapping
|
||
eval_time: 5m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', nic: Ethernet, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsnetworkinterfaceflapping/
|
||
summary: Windows network interface is flapping
|
||
description: 'Interface Ethernet on host:9182 has changed its operational status more than twice in 5m.'
|
||
- {alertname: WindowsNetworkInterfaceFlapping, eval_time: 17m, exp_alerts: []}
|
||
|
||
- name: Service alerts skip trigger-start and manual services and count restarts by process
|
||
interval: 1m
|
||
input_series:
|
||
- series: 'windows_service_state{job="windows_exporter", instance="host:9182", service="Spooler", state="running"}'
|
||
values: '0x15 1x8'
|
||
- series: 'windows_service_start_mode{job="windows_exporter", instance="host:9182", service="Spooler", start_mode="auto"}'
|
||
values: '1x23'
|
||
- series: 'windows_service_info{job="windows_exporter", instance="host:9182", service="Spooler", trigger_start="false", delayed_start="false"}'
|
||
values: '1x23'
|
||
- series: 'windows_service_state{job="windows_exporter", instance="host:9182", service="dcsvc", state="running"}'
|
||
values: '0x23'
|
||
- series: 'windows_service_start_mode{job="windows_exporter", instance="host:9182", service="dcsvc", start_mode="auto"}'
|
||
values: '1x23'
|
||
- series: 'windows_service_info{job="windows_exporter", instance="host:9182", service="dcsvc", trigger_start="true", delayed_start="false"}'
|
||
values: '1x23'
|
||
- series: 'windows_service_state{job="windows_exporter", instance="host:9182", service="RemoteRegistry", state="running"}'
|
||
values: '0x23'
|
||
- series: 'windows_service_start_mode{job="windows_exporter", instance="host:9182", service="RemoteRegistry", start_mode="manual"}'
|
||
values: '1x23'
|
||
- series: 'windows_service_start_mode{job="windows_exporter", instance="host:9182", service="RemoteRegistry", start_mode="auto"}'
|
||
values: '0x23'
|
||
- series: 'windows_service_process{job="windows_exporter", instance="host:9182", service="W3SVC", process_id="100"}'
|
||
values: '1000x4 _x19'
|
||
- series: 'windows_service_process{job="windows_exporter", instance="host:9182", service="W3SVC", process_id="200"}'
|
||
values: '_x5 2000x4 _x14'
|
||
- series: 'windows_service_process{job="windows_exporter", instance="host:9182", service="W3SVC", process_id="300"}'
|
||
values: '_x10 3000x4 _x9'
|
||
- series: 'windows_service_process{job="windows_exporter", instance="host:9182", service="W3SVC", process_id="400"}'
|
||
values: '_x15 4000x9'
|
||
- series: 'windows_service_process{job="windows_exporter", instance="host:9182", service="Spooler", process_id="500"}'
|
||
values: '_x16 5000x8'
|
||
alert_rule_test:
|
||
- {alertname: WindowsServiceNotRunning, eval_time: 14m, exp_alerts: []}
|
||
- alertname: WindowsServiceNotRunning
|
||
eval_time: 15m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', service: Spooler, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsservicenotrunning/
|
||
summary: Windows automatic service is not running
|
||
description: 'Service Spooler on host:9182 starts automatically but has not been running for 15 minutes.'
|
||
- {alertname: WindowsServiceNotRunning, eval_time: 16m, exp_alerts: []}
|
||
- {alertname: WindowsServiceCrashLooping, eval_time: 14m, exp_alerts: []}
|
||
- alertname: WindowsServiceCrashLooping
|
||
eval_time: 15m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', service: W3SVC, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsservicecrashlooping/
|
||
summary: Windows service is restarting repeatedly
|
||
description: 'Service W3SVC on host:9182 has restarted more than 2 times in 15 minutes.'
|
||
- alertname: WindowsServiceCrashLooping
|
||
eval_time: 23m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', service: W3SVC, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsservicecrashlooping/
|
||
summary: Windows service is restarting repeatedly
|
||
description: 'Service W3SVC on host:9182 has restarted more than 2 times in 15 minutes.'
|
||
- {alertname: WindowsServiceCrashLooping, eval_time: 24m, exp_alerts: []}
|
||
|
||
- name: Service alert matches within a cluster when instance names repeat across clusters
|
||
interval: 1m
|
||
input_series:
|
||
- series: 'windows_service_state{job="windows_exporter", instance="host:9182", cluster="a", service="Spooler", state="running"}'
|
||
values: '0x20'
|
||
- series: 'windows_service_start_mode{job="windows_exporter", instance="host:9182", cluster="a", service="Spooler", start_mode="auto"}'
|
||
values: '1x20'
|
||
- series: 'windows_service_info{job="windows_exporter", instance="host:9182", cluster="a", service="Spooler", trigger_start="false", delayed_start="false"}'
|
||
values: '1x20'
|
||
- series: 'windows_service_state{job="windows_exporter", instance="host:9182", cluster="b", service="Spooler", state="running"}'
|
||
values: '1x20'
|
||
- series: 'windows_service_start_mode{job="windows_exporter", instance="host:9182", cluster="b", service="Spooler", start_mode="auto"}'
|
||
values: '1x20'
|
||
- series: 'windows_service_info{job="windows_exporter", instance="host:9182", cluster="b", service="Spooler", trigger_start="false", delayed_start="false"}'
|
||
values: '1x20'
|
||
- series: 'windows_service_state{job="windows_exporter", instance="host:9182", cluster="c", service="Spooler", state="running"}'
|
||
values: '0x20'
|
||
- series: 'windows_service_start_mode{job="windows_exporter", instance="host:9182", cluster="c", service="Spooler", start_mode="auto"}'
|
||
values: '1x20'
|
||
- series: 'windows_service_info{job="windows_exporter", instance="host:9182", cluster="c", service="Spooler", trigger_start="true", delayed_start="false"}'
|
||
values: '1x20'
|
||
alert_rule_test:
|
||
- alertname: WindowsServiceNotRunning
|
||
eval_time: 20m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', cluster: a, service: Spooler, severity: warning}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowsservicenotrunning/
|
||
summary: Windows automatic service is not running
|
||
description: 'Service Spooler on host:9182 starts automatically but has not been running for 15 minutes.'
|
||
|
||
- name: Host reboot fires once for the first ten minutes after a new boot time
|
||
interval: 1m
|
||
input_series:
|
||
- series: 'windows_system_boot_time_timestamp{job="windows_exporter", instance="host:9182"}'
|
||
values: '-100000x10 540x15'
|
||
- series: 'windows_system_boot_time_timestamp{job="windows_exporter", instance="steady:9182"}'
|
||
values: '-100000x25'
|
||
alert_rule_test:
|
||
- {alertname: WindowsHostRebooted, eval_time: 10m, exp_alerts: []}
|
||
- alertname: WindowsHostRebooted
|
||
eval_time: 11m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', severity: info}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowshostrebooted/
|
||
summary: Windows host has rebooted
|
||
description: 'host:9182 rebooted 2m 0s ago.'
|
||
- alertname: WindowsHostRebooted
|
||
eval_time: 18m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', severity: info}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowshostrebooted/
|
||
summary: Windows host has rebooted
|
||
description: 'host:9182 rebooted 9m 0s ago.'
|
||
- {alertname: WindowsHostRebooted, eval_time: 19m, exp_alerts: []}
|
||
|
||
- name: Host reboot fires after a scrape gap longer than ten minutes
|
||
interval: 1m
|
||
input_series:
|
||
- series: 'windows_system_boot_time_timestamp{job="windows_exporter", instance="host:9182"}'
|
||
values: '-100000x5 stale _x11 960x20'
|
||
alert_rule_test:
|
||
- {alertname: WindowsHostRebooted, eval_time: 17m, exp_alerts: []}
|
||
- alertname: WindowsHostRebooted
|
||
eval_time: 18m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', severity: info}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowshostrebooted/
|
||
summary: Windows host has rebooted
|
||
description: 'host:9182 rebooted 2m 0s ago.'
|
||
- alertname: WindowsHostRebooted
|
||
eval_time: 25m
|
||
exp_alerts:
|
||
- exp_labels: {job: windows_exporter, instance: 'host:9182', severity: info}
|
||
exp_annotations:
|
||
runbook_url: https://prometheus-community.github.io/windows_exporter/runbooks/windowshostrebooted/
|
||
summary: Windows host has rebooted
|
||
description: 'host:9182 rebooted 9m 0s ago.'
|
||
- {alertname: WindowsHostRebooted, eval_time: 26m, exp_alerts: []}
|