XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-24 10:26:58 +08:00
Code Issues Projects Releases Packages Wiki Activity

Publish

Browse source
This commit is contained in:
samber 2024-05-13 08:33:30 +00:00
parent 2547288c13
commit 84b0569c97
1 changed files with 37 additions and 37 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

74
dist/rules/clickhouse/embedded-exporter.yml vendored
View file

@ -1,7 +1,10 @@
groups: groups:
- name: EmbeddedExporter - name: EmbeddedExporter
rules: rules:
- alert: ClickHouseMemoryUsageCritical
- alert: ClickhouseMemoryUsageCritical
expr: 'ClickHouseAsyncMetrics_CGroupMemoryUsed / ClickHouseAsyncMetrics_CGroupMemoryTotal * 100 > 90' expr: 'ClickHouseAsyncMetrics_CGroupMemoryUsed / ClickHouseAsyncMetrics_CGroupMemoryTotal * 100 > 90'
for: 5m for: 5m
labels: labels:
@ -10,122 +13,119 @@ groups:
summary: ClickHouse Memory Usage Critical (instance {{ $labels.instance }}) summary: ClickHouse Memory Usage Critical (instance {{ $labels.instance }})
description: "Memory usage is critically high, over 90%.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "Memory usage is critically high, over 90%.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ClickHouseMemoryUsageWarning - alert: ClickhouseMemoryUsageWarning
expr: 'ClickHouseAsyncMetrics_CGroupMemoryUsed / ClickHouseAsyncMetrics_CGroupMemoryTotal * 100 > 80' expr: 'ClickHouseAsyncMetrics_CGroupMemoryUsed / ClickHouseAsyncMetrics_CGroupMemoryTotal * 100 > 80'
for: 5m for: 5m
labels: labels:
severity: warning severity: warning
annotations: annotations:
summary: ClickHouse Memory Usage Warning (instance {{ $labels.instance }}) summary: ClickHouse Memory Usage Warning (instance {{ $labels.instance }})
description: "Memory usage is over 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "Memory usage is over 80%.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ClickHouseDiskSpaceLowDefault - alert: ClickhouseDiskSpaceLowOnDefault
expr: 'ClickHouseAsyncMetrics_DiskAvailable_default / (ClickHouseAsyncMetrics_DiskAvailable_default + ClickHouseAsyncMetrics_DiskUsed_default) * 100 < 20' expr: 'ClickHouseAsyncMetrics_DiskAvailable_default / (ClickHouseAsyncMetrics_DiskAvailable_default + ClickHouseAsyncMetrics_DiskUsed_default) * 100 < 20'
for: 2m for: 2m
labels: labels:
severity: warning severity: warning
annotations: annotations:
summary: ClickHouse Disk Space Low on Default (instance {{ $labels.instance }}) summary: ClickHouse Disk Space Low on Default (instance {{ $labels.instance }})
description: "Disk space on default is below 20%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "Disk space on default is below 20%.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ClickHouseDiskSpaceCriticalDefault - alert: ClickhouseDiskSpaceCriticalOnDefault
expr: 'ClickHouseAsyncMetrics_DiskAvailable_default / (ClickHouseAsyncMetrics_DiskAvailable_default + ClickHouseAsyncMetrics_DiskUsed_default) * 100 < 10' expr: 'ClickHouseAsyncMetrics_DiskAvailable_default / (ClickHouseAsyncMetrics_DiskAvailable_default + ClickHouseAsyncMetrics_DiskUsed_default) * 100 < 10'
for: 2m for: 2m
labels: labels:
severity: critical severity: critical
annotations: annotations:
summary: ClickHouse Disk Space Critical on Default Disk (instance {{ $labels.instance }}) summary: ClickHouse Disk Space Critical on Default (instance {{ $labels.instance }})
description: "Disk space on default disk is critically low, below 10%.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "Disk space on default disk is critically low, below 10%.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ClickHouseDiskSpaceLowBackups - alert: ClickhouseDiskSpaceLowOnBackups
expr: 'ClickHouseAsyncMetrics_DiskAvailable_backups / (ClickHouseAsyncMetrics_DiskAvailable_backups + ClickHouseAsyncMetrics_DiskUsed_backups) * 100 < 20' expr: 'ClickHouseAsyncMetrics_DiskAvailable_backups / (ClickHouseAsyncMetrics_DiskAvailable_backups + ClickHouseAsyncMetrics_DiskUsed_backups) * 100 < 20'
for: 2m for: 2m
labels: labels:
severity: warning severity: warning
annotations: annotations:
summary: ClickHouse Disk Space Low on Backups (instance {{ $labels.instance }}) summary: ClickHouse Disk Space Low on Backups (instance {{ $labels.instance }})
description: "Disk space on backups is below 20%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "Disk space on backups is below 20%.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ClickHouseReplicaErrors - alert: ClickhouseReplicaErrors
expr: 'ClickHouseErrorMetric_ALL_REPLICAS_ARE_STALE == 1 or ClickHouseErrorMetric_ALL_REPLICAS_LOST == 1' expr: 'ClickHouseErrorMetric_ALL_REPLICAS_ARE_STALE == 1 or ClickHouseErrorMetric_ALL_REPLICAS_LOST == 1'
for: 0m for: 0m
labels: labels:
severity: critical severity: critical
annotations: annotations:
summary: ClickHouse Replica Errors Detected (instance {{ $labels.instance }}) summary: ClickHouse Replica Errors (instance {{ $labels.instance }})
description: "Critical replica errors detected, either all replicas are stale or lost.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "Critical replica errors detected, either all replicas are stale or lost.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ClickHouseNoAvailableReplicas - alert: ClickhouseNoAvailableReplicas
expr: 'ClickHouseErrorMetric_NO_AVAILABLE_REPLICA == 1' expr: 'ClickHouseErrorMetric_NO_AVAILABLE_REPLICA == 1'
for: 0m for: 0m
labels: labels:
severity: critical severity: critical
annotations: annotations:
summary: No Available Replicas in ClickHouse (instance {{ $labels.instance }}) summary: ClickHouse No Available Replicas (instance {{ $labels.instance }})
description: "No available replicas in ClickHouse.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "No available replicas in ClickHouse.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ClickHouseNoLiveReplicas - alert: ClickhouseNoLiveReplicas
expr: 'ClickHouseErrorMetric_TOO_FEW_LIVE_REPLICAS == 1' expr: 'ClickHouseErrorMetric_TOO_FEW_LIVE_REPLICAS == 1'
for: 0m for: 0m
labels: labels:
severity: critical severity: critical
annotations: annotations:
summary: No Live Replicas in ClickHouse (instance {{ $labels.instance }}) summary: ClickHouse No Live Replicas (instance {{ $labels.instance }})
description: "There are too few live replicas available, risking data loss and service disruption.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "There are too few live replicas available, risking data loss and service disruption.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ClickhouseHighNetworkTraffic
- alert: ClickHouseNetworkUsageHigh expr: 'ClickHouseMetrics_NetworkSend > 250 or ClickHouseMetrics_NetworkReceive > 250'
expr: 'ClickHouseMetrics_NetworkSend > 1000 or ClickHouseMetrics_NetworkReceive > 1000'
for: 5m for: 5m
labels: labels:
severity: warning severity: warning
annotations: annotations:
summary: High Network Traffic in ClickHouse (instance {{ $labels.instance }}) summary: ClickHouse High Network Traffic (instance {{ $labels.instance }})
description: "Network traffic is unusually high, may affect cluster performance.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "Network traffic is unusually high, may affect cluster performance.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ClickHouseHighTCPConnections - alert: ClickhouseHighTcpConnections
expr: 'ClickHouseMetrics_TCPConnection > 1500' expr: 'ClickHouseMetrics_TCPConnection > 400'
for: 5m for: 5m
labels: labels:
severity: warning severity: warning
annotations: annotations:
summary: High TCP Connections in ClickHouse (instance {{ $labels.instance }}) summary: ClickHouse High TCP Connections (instance {{ $labels.instance }})
description: "High number of TCP connections, indicating heavy client or inter-cluster communication.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "High number of TCP connections, indicating heavy client or inter-cluster communication.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ClickHouseInterserverConnectionIssues - alert: ClickhouseInterserverConnectionIssues
expr: 'increase(ClickHouseMetrics_InterserverConnection[5m]) > 0' expr: 'increase(ClickHouseMetrics_InterserverConnection[5m]) > 0'
for: 0m for: 1m
labels: labels:
severity: warning severity: warning
annotations: annotations:
summary: Interserver Connection Issues in ClickHouse (instance {{ $labels.instance }}) summary: ClickHouse Interserver Connection Issues (instance {{ $labels.instance }})
description: "An increase in interserver connections may indicate replication or distributed query handling issues.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "An increase in interserver connections may indicate replication or distributed query handling issues.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ClickHouseZooKeeperConnectionIssues - alert: ClickhouseZookeeperConnectionIssues
expr: 'avg(ClickHouseMetrics_ZooKeeperSession) != 1' expr: 'avg(ClickHouseMetrics_ZooKeeperSession) != 1'
for: 5m for: 3m
labels: labels:
severity: warning severity: warning
annotations: annotations:
summary: ZooKeeper Connection Issues in ClickHouse (instance {{ $labels.instance }}) summary: ClickHouse ZooKeeper Connection Issues (instance {{ $labels.instance }})
description: "ClickHouse is experiencing issues with ZooKeeper connections, which may affect cluster state and coordination.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "ClickHouse is experiencing issues with ZooKeeper connections, which may affect cluster state and coordination.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ClickHouseAuthenticationFailures - alert: ClickhouseAuthenticationFailures
expr: 'increase(ClickHouseErrorMetric_AUTHENTICATION_FAILED[5m]) > 0' expr: 'increase(ClickHouseErrorMetric_AUTHENTICATION_FAILED[5m]) > 0'
for: 0m for: 0m
labels: labels:
severity: critical severity: info
annotations: annotations:
summary: Authentication Failures in ClickHouse (instance {{ $labels.instance }}) summary: ClickHouse Authentication Failures (instance {{ $labels.instance }})
description: "Authentication failures detected, indicating potential security issues or misconfiguration.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "Authentication failures detected, indicating potential security issues or misconfiguration.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ClickHouseAccessDeniedErrors - alert: ClickhouseAccessDeniedErrors
expr: 'increase(ClickHouseErrorMetric_RESOURCE_ACCESS_DENIED[5m]) > 0' expr: 'increase(ClickHouseErrorMetric_RESOURCE_ACCESS_DENIED[5m]) > 0'
for: 1m for: 0m
labels: labels:
severity: critical severity: info
annotations: annotations:
summary: Access Denied Errors in ClickHouse (instance {{ $labels.instance }}) summary: ClickHouse Access Denied Errors (instance {{ $labels.instance }})
description: "Access denied errors have been logged, which could indicate permission issues or unauthorized access attempts.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "Access denied errors have been logged, which could indicate permission issues or unauthorized access attempts.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"