XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-25 02:46:59 +08:00
Code Issues Projects Releases Packages Wiki Activity

fix: remove duplicated rule

Browse source
This commit is contained in:
Samuel Berthe 2025-02-19 15:25:22 +01:00
parent 0f4b45d127
commit 6838196343
No known key found for this signature in database
GPG key ID: 64863511FFBD0E3C
1 changed files with 31 additions and 38 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

69
_data/rules.yml
View file

@ -137,30 +137,30 @@ groups:
rules: rules:
- name: Host out of memory - name: Host out of memory
description: Node memory is filling up (< 10% left) description: Node memory is filling up (< 10% left)
query: '(node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes < .10)' query: "(node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes < .10)"
severity: warning severity: warning
for: 2m for: 2m
- name: Host memory under memory pressure - name: Host memory under memory pressure
description: The node is under heavy memory pressure. High rate of loading memory pages from disk. description: The node is under heavy memory pressure. High rate of loading memory pages from disk.
query: '(rate(node_vmstat_pgmajfault[5m]) > 1000)' query: "(rate(node_vmstat_pgmajfault[5m]) > 1000)"
severity: warning severity: warning
- name: Host Memory is underutilized - name: Host Memory is underutilized
description: "Node memory usage is < 20% for 1 week. Consider reducing memory space. (instance {{ $labels.instance }})" description: "Node memory usage is < 20% for 1 week. Consider reducing memory space. (instance {{ $labels.instance }})"
query: 'min_over_time(node_memory_MemFree_bytes[1w]) > node_memory_MemTotal_bytes * .8' query: "min_over_time(node_memory_MemFree_bytes[1w]) > node_memory_MemTotal_bytes * .8"
severity: info severity: info
comments: | comments: |
You may want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly You may want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly
- name: Host unusual network throughput in - name: Host unusual network throughput in
description: Host receive bandwidth is high (>80%). description: Host receive bandwidth is high (>80%).
query: '((rate(node_network_receive_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)' query: "((rate(node_network_receive_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)"
severity: warning severity: warning
- name: Host unusual network throughput out - name: Host unusual network throughput out
description: Host transmit bandwidth is high (>80%) description: Host transmit bandwidth is high (>80%)
query: '((rate(node_network_transmit_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)' query: "((rate(node_network_transmit_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)"
severity: warning severity: warning
- name: Host unusual disk read rate - name: Host unusual disk read rate
description: Disk is too busy (IO wait > 80%) description: Disk is too busy (IO wait > 80%)
query: '(rate(node_disk_io_time_seconds_total[5m]) > .80)' query: "(rate(node_disk_io_time_seconds_total[5m]) > .80)"
severity: warning severity: warning
- name: Host out of disk space - name: Host out of disk space
description: Disk is almost full (< 10% left) description: Disk is almost full (< 10% left)
@ -182,7 +182,7 @@ groups:
for: 2m for: 2m
- name: Host out of inodes - name: Host out of inodes
description: Disk is almost running out of available inodes (< 10% left) description: Disk is almost running out of available inodes (< 10% left)
query: '(node_filesystem_files_free / node_filesystem_files < .10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0)' query: "(node_filesystem_files_free / node_filesystem_files < .10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0)"
severity: critical severity: critical
for: 2m for: 2m
- name: Host filesystem device error - name: Host filesystem device error
@ -197,12 +197,12 @@ groups:
for: 2m for: 2m
- name: Host unusual disk read latency - name: Host unusual disk read latency
description: Disk latency is growing (read operations > 100ms) description: Disk latency is growing (read operations > 100ms)
query: '(rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 0.1 and rate(node_disk_reads_completed_total[1m]) > 0' query: "(rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 0.1 and rate(node_disk_reads_completed_total[1m]) > 0"
severity: warning severity: warning
for: 2m for: 2m
- name: Host unusual disk write latency - name: Host unusual disk write latency
description: Disk latency is growing (write operations > 100ms) description: Disk latency is growing (write operations > 100ms)
query: '(rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 0.1 and rate(node_disk_writes_completed_total[1m]) > 0)' query: "(rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 0.1 and rate(node_disk_writes_completed_total[1m]) > 0)"
severity: warning severity: warning
for: 2m for: 2m
- name: Host high CPU load - name: Host high CPU load
@ -227,7 +227,7 @@ groups:
severity: warning severity: warning
- name: Host unusual disk IO - name: Host unusual disk IO
description: "Disk usage >80%. Check storage for issues or increase IOPS capabilities. Check storage for issues." description: "Disk usage >80%. Check storage for issues or increase IOPS capabilities. Check storage for issues."
query: 'rate(node_disk_io_time_seconds_total[5m]) > 0.8' query: "rate(node_disk_io_time_seconds_total[5m]) > 0.8"
severity: warning severity: warning
for: 5m for: 5m
- name: Host context switching high - name: Host context switching high
@ -240,7 +240,7 @@ groups:
Please read: https://github.com/samber/awesome-prometheus-alerts/issues/58 Please read: https://github.com/samber/awesome-prometheus-alerts/issues/58
- name: Host swap is filling up - name: Host swap is filling up
description: Swap is filling up (>80%) description: Swap is filling up (>80%)
query: '((1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80)' query: "((1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80)"
severity: warning severity: warning
for: 2m for: 2m
- name: Host systemd service crashed - name: Host systemd service crashed
@ -249,12 +249,12 @@ groups:
severity: warning severity: warning
- name: Host physical component too hot - name: Host physical component too hot
description: "Physical hardware component too hot" description: "Physical hardware component too hot"
query: 'node_hwmon_temp_celsius > node_hwmon_temp_max_celsius' query: "node_hwmon_temp_celsius > node_hwmon_temp_max_celsius"
severity: warning severity: warning
for: 5m for: 5m
- name: Host node overtemperature alarm - name: Host node overtemperature alarm
description: "Physical node temperature alarm triggered" description: "Physical node temperature alarm triggered"
query: '((node_hwmon_temp_crit_alarm_celsius == 1) or (node_hwmon_temp_alarm == 1))' query: "((node_hwmon_temp_crit_alarm_celsius == 1) or (node_hwmon_temp_alarm == 1))"
severity: critical severity: critical
- name: Host software RAID insufficient drives - name: Host software RAID insufficient drives
description: "MD RAID array {{ $labels.device }} on {{ $labels.instance }} has insufficient drives remaining." description: "MD RAID array {{ $labels.device }} on {{ $labels.instance }} has insufficient drives remaining."
@ -267,53 +267,53 @@ groups:
for: 2m for: 2m
- name: Host kernel version deviations - name: Host kernel version deviations
description: Kernel version for {{ $labels.instance }} has changed. description: Kernel version for {{ $labels.instance }} has changed.
query: 'changes(node_uname_info[1h]) > 0' query: "changes(node_uname_info[1h]) > 0"
severity: info severity: info
- name: Host OOM kill detected - name: Host OOM kill detected
description: OOM kill detected description: OOM kill detected
query: '(increase(node_vmstat_oom_kill[1m]) > 0)' query: "(increase(node_vmstat_oom_kill[1m]) > 0)"
severity: warning severity: warning
- name: Host EDAC Correctable Errors detected - name: Host EDAC Correctable Errors detected
description: 'Host {{ $labels.instance }} has had {{ printf "%.0f" $value }} correctable memory errors reported by EDAC in the last 5 minutes.' description: 'Host {{ $labels.instance }} has had {{ printf "%.0f" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'
query: '(increase(node_edac_correctable_errors_total[1m]) > 0)' query: "(increase(node_edac_correctable_errors_total[1m]) > 0)"
severity: info severity: info
- name: Host EDAC Uncorrectable Errors detected - name: Host EDAC Uncorrectable Errors detected
description: 'Host {{ $labels.instance }} has had {{ printf "%.0f" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.' description: 'Host {{ $labels.instance }} has had {{ printf "%.0f" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'
query: '(node_edac_uncorrectable_errors_total > 0)' query: "(node_edac_uncorrectable_errors_total > 0)"
severity: warning severity: warning
- name: Host Network Receive Errors - name: Host Network Receive Errors
description: 'Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive errors in the last two minutes.' description: 'Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive errors in the last two minutes.'
query: '(rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01)' query: "(rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01)"
severity: warning severity: warning
for: 2m for: 2m
- name: Host Network Transmit Errors - name: Host Network Transmit Errors
description: 'Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit errors in the last two minutes.' description: 'Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit errors in the last two minutes.'
query: '(rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01)' query: "(rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01)"
severity: warning severity: warning
for: 2m for: 2m
- name: Host Network Bond Degraded - name: Host Network Bond Degraded
description: 'Bond "{{ $labels.device }}" degraded on "{{ $labels.instance }}".' description: 'Bond "{{ $labels.device }}" degraded on "{{ $labels.instance }}".'
query: '((node_bonding_active - node_bonding_slaves) != 0)' query: "((node_bonding_active - node_bonding_slaves) != 0)"
severity: warning severity: warning
for: 2m for: 2m
- name: Host conntrack limit - name: Host conntrack limit
description: "The number of conntrack is approaching limit" description: "The number of conntrack is approaching limit"
query: '(node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8)' query: "(node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8)"
severity: warning severity: warning
for: 5m for: 5m
- name: Host clock skew - name: Host clock skew
description: "Clock skew detected. Clock is out of sync. Ensure NTP is configured correctly on this host." description: "Clock skew detected. Clock is out of sync. Ensure NTP is configured correctly on this host."
query: '((node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0))' query: "((node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0))"
severity: warning severity: warning
for: 10m for: 10m
- name: Host clock not synchronising - name: Host clock not synchronising
description: "Clock not synchronising. Ensure NTP is configured on this host." description: "Clock not synchronising. Ensure NTP is configured on this host."
query: '(min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16)' query: "(min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16)"
severity: warning severity: warning
for: 2m for: 2m
- name: Host requires reboot - name: Host requires reboot
description: "{{ $labels.instance }} requires a reboot." description: "{{ $labels.instance }} requires a reboot."
query: '(node_reboot_required > 0)' query: "(node_reboot_required > 0)"
severity: info severity: info
for: 4h for: 4h
@ -341,19 +341,19 @@ groups:
severity: warning severity: warning
- name: SMART status - name: SMART status
description: Device has a SMART status failure on {{ $labels.instance }} drive {{ $labels.device }}) description: Device has a SMART status failure on {{ $labels.instance }} drive {{ $labels.device }})
query: 'smartctl_device_smart_status != 1' query: "smartctl_device_smart_status != 1"
severity: critical severity: critical
- name: SMART critical warning - name: SMART critical warning
description: Disk controller has critical warning on {{ $labels.instance }} drive {{ $labels.device }}) description: Disk controller has critical warning on {{ $labels.instance }} drive {{ $labels.device }})
query: 'smartctl_device_critical_warning > 0' query: "smartctl_device_critical_warning > 0"
severity: critical severity: critical
- name: SMART media errors - name: SMART media errors
description: Disk controller detected media errors on {{ $labels.instance }} drive {{ $labels.device }}) description: Disk controller detected media errors on {{ $labels.instance }} drive {{ $labels.device }})
query: 'smartctl_device_media_errors > 0' query: "smartctl_device_media_errors > 0"
severity: critical severity: critical
- name: SMART Wearout Indicator - name: SMART Wearout Indicator
description: Device is wearing out on {{ $labels.instance }} drive {{ $labels.device }}) description: Device is wearing out on {{ $labels.instance }} drive {{ $labels.device }})
query: 'smartctl_device_available_spare < smartctl_device_available_spare_threshold' query: "smartctl_device_available_spare < smartctl_device_available_spare_threshold"
severity: critical severity: critical
- name: Docker containers - name: Docker containers
@ -1174,7 +1174,7 @@ groups:
rules: rules:
- name: Meilisearch index is empty - name: Meilisearch index is empty
description: Meilisearch instance is down description: Meilisearch instance is down
query: 'meilisearch_index_docs_count == 0' query: "meilisearch_index_docs_count == 0"
severity: warning severity: warning
- name: Meilisearch http response time - name: Meilisearch http response time
description: Meilisearch http response time is too high description: Meilisearch http response time is too high
@ -1413,7 +1413,6 @@ groups:
severity: info severity: info
for: 0m for: 0m
- name: Zookeeper - name: Zookeeper
exporters: exporters:
- name: cloudflare/kafka_zookeeper_exporter - name: cloudflare/kafka_zookeeper_exporter
@ -1539,11 +1538,6 @@ groups:
query: "gnatsd_varz_connections > 100" query: "gnatsd_varz_connections > 100"
severity: warning severity: warning
for: 3m for: 3m
- name: Nats high pending bytes
description: High number of NATS pending bytes ({{ $value }}) for {{ $labels.instance }}
query: "gnatsd_connz_pending_bytes > 100000"
severity: warning
for: 3m
- name: Nats high subscriptions count - name: Nats high subscriptions count
description: High number of NATS subscriptions ({{ $value }}) for {{ $labels.instance }} description: High number of NATS subscriptions ({{ $value }}) for {{ $labels.instance }}
query: "gnatsd_connz_subscriptions > 50" query: "gnatsd_connz_subscriptions > 50"
@ -1635,7 +1629,6 @@ groups:
severity: critical severity: critical
for: 5m for: 5m
- name: Solr - name: Solr
exporters: exporters:
- name: embedded exporter - name: embedded exporter
@ -2129,7 +2122,7 @@ groups:
severity: warning severity: warning
- name: Kubernetes HPA scale maximum - name: Kubernetes HPA scale maximum
description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has hit maximum number of desired pods description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has hit maximum number of desired pods
query: '(kube_horizontalpodautoscaler_status_desired_replicas >= kube_horizontalpodautoscaler_spec_max_replicas) and (kube_horizontalpodautoscaler_spec_max_replicas > 1) and (kube_horizontalpodautoscaler_spec_min_replicas != kube_horizontalpodautoscaler_spec_max_replicas)' query: "(kube_horizontalpodautoscaler_status_desired_replicas >= kube_horizontalpodautoscaler_spec_max_replicas) and (kube_horizontalpodautoscaler_spec_max_replicas > 1) and (kube_horizontalpodautoscaler_spec_min_replicas != kube_horizontalpodautoscaler_spec_max_replicas)"
severity: info severity: info
for: 2m for: 2m
- name: Kubernetes HPA underutilized - name: Kubernetes HPA underutilized
@ -3021,7 +3014,7 @@ groups:
rules: rules:
- name: Grafana Alloy service down - name: Grafana Alloy service down
description: Alloy on (instance {{ $labels.instance }}) is not responding or has stopped running. description: Alloy on (instance {{ $labels.instance }}) is not responding or has stopped running.
query: 'count by (instance) (alloy_build_info) unless count by (instance) (alloy_build_info offset 2m) ' query: "count by (instance) (alloy_build_info) unless count by (instance) (alloy_build_info offset 2m) "
severity: critical severity: critical
- name: Jenkins - name: Jenkins