01 Alert Rules整理
文件系统使用率：
node_filesystem_free_bytes{mountpoint=~"(/|/u01)"}/node_filesystem_size_bytes{mountpoint=~"(/|/u01)"}*100
参考：https://awesome-prometheus-alerts.grep.to/rules#host-and-hardware
- alert: PrometheusTargetMissing
expr: up == 0
for: 5m
labels:
severity: critical
annotations:
summary: "Prometheus target missing (instance {{ $labels.instance }})"
description: "A Prometheus target has disappeared. An exporter might be crashed.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusConfigurationReloadFailure
expr: prometheus_config_last_reload_successful != 1
for: 5m
labels:
severity: warning
annotations:
summary: "Prometheus configuration reload failure (instance {{ $labels.instance }})"
description: "Prometheus configuration reload error\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusTooManyRestarts
expr: changes(process_start_time_seconds{job=~"expose-prometheus-metrics|pushgateway|expose-alertmanager-metrics"}[15m]) > 2
for: 5m
labels:
severity: warning
annotations:
summary: "Prometheus too many restarts (instance {{ $labels.instance }})"
description: "Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusAlertmanagerConfigurationReloadFailure
expr: alertmanager_config_last_reload_successful != 1
for: 5m
labels:
severity: warning
annotations:
summary: "Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }})"
description: "AlertManager configuration reload error\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusAlertmanagerConfigNotSynced
expr: count(count_values("config_hash", alertmanager_config_hash)) > 1
for: 5m
labels:
severity: warning
annotations:
summary: "Prometheus AlertManager config not synced (instance {{ $labels.instance }})"
description: "Configurations of AlertManager cluster instances are out of sync\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusNotConnectedToAlertmanager
expr: prometheus_notifications_alertmanagers_discovered < 1
for: 5m
labels:
severity: critical
annotations:
summary: "Prometheus not connected to alertmanager (instance {{ $labels.instance }})"
description: "Prometheus cannot connect the alertmanager\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusRuleEvaluationFailures
expr: increase(prometheus_rule_evaluation_failures_total[3m]) > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Prometheus rule evaluation failures (instance {{ $labels.instance }})"
description: "Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusTemplateTextExpansionFailures
expr: increase(prometheus_template_text_expansion_failures_total[3m]) > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Prometheus template text expansion failures (instance {{ $labels.instance }})"
description: "Prometheus encountered {{ $value }} template text expansion failures\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusRuleEvaluationSlow
expr: prometheus_rule_group_last_duration_seconds > prometheus_rule_group_interval_seconds
for: 5m
labels:
severity: warning
annotations:
summary: "Prometheus rule evaluation slow (instance {{ $labels.instance }})"
description: "Prometheus rule evaluation took more time than the scheduled interval. I indicates a slower storage backend access or too complex query.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusNotificationsBacklog
expr: min_over_time(prometheus_notifications_queue_length[10m]) > 0
for: 5m
labels:
severity: warning
annotations:
summary: "Prometheus notifications backlog (instance {{ $labels.instance }})"
description: "The Prometheus notification queue has not been empty for 10 minutes\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusAlertmanagerNotificationFailing
expr: rate(alertmanager_notifications_failed_total[1m]) > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Prometheus AlertManager notification failing (instance {{ $labels.instance }})"
description: "Alertmanager is failing sending notifications\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusTargetScrapingSlow
expr: prometheus_target_interval_length_seconds{quantile="0.9"} > 60
for: 5m
labels:
severity: warning
annotations:
summary: "Prometheus target scraping slow (instance {{ $labels.instance }})"
description: "Prometheus is scraping exporters slowly\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusLargeScrape
expr: increase(prometheus_target_scrapes_exceeded_sample_limit_total[10m]) > 10
for: 5m
labels:
severity: warning
annotations:
summary: "Prometheus large scrape (instance {{ $labels.instance }})"
description: "Prometheus has many scrapes that exceed the sample limit\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusTargetScrapeDuplicate
expr: increase(prometheus_target_scrapes_sample_duplicate_timestamp_total[5m]) > 0
for: 5m
labels:
severity: warning
annotations:
summary: "Prometheus target scrape duplicate (instance {{ $labels.instance }})"
description: "Prometheus has many samples rejected due to duplicate timestamps but different values\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusTsdbCheckpointCreationFailures
expr: increase(prometheus_tsdb_checkpoint_creations_failed_total[3m]) > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Prometheus TSDB checkpoint creation failures (instance {{ $labels.instance }})"
description: "Prometheus encountered {{ $value }} checkpoint creation failures\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusTsdbCheckpointDeletionFailures
expr: increase(prometheus_tsdb_checkpoint_deletions_failed_total[3m]) > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Prometheus TSDB checkpoint deletion failures (instance {{ $labels.instance }})"
description: "Prometheus encountered {{ $value }} checkpoint deletion failures\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusTsdbCompactionsFailed
expr: increase(prometheus_tsdb_compactions_failed_total[3m]) > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Prometheus TSDB compactions failed (instance {{ $labels.instance }})"
description: "Prometheus encountered {{ $value }} TSDB compactions failures\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusTsdbHeadTruncationsFailed
expr: increase(prometheus_tsdb_head_truncations_failed_total[3m]) > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Prometheus TSDB head truncations failed (instance {{ $labels.instance }})"
description: "Prometheus encountered {{ $value }} TSDB head truncation failures\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusTsdbReloadFailures
expr: increase(prometheus_tsdb_reloads_failures_total[3m]) > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Prometheus TSDB reload failures (instance {{ $labels.instance }})"
description: "Prometheus encountered {{ $value }} TSDB reload failures\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusTsdbWalCorruptions
expr: increase(prometheus_tsdb_wal_corruptions_total[3m]) > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Prometheus TSDB WAL corruptions (instance {{ $labels.instance }})"
description: "Prometheus encountered {{ $value }} TSDB WAL corruptions\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusTsdbWalTruncationsFailed
expr: increase(prometheus_tsdb_wal_truncations_failed_total[3m]) > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }})"
description: "Prometheus encountered {{ $value }} TSDB WAL truncation failures\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: MysqlDown
expr: mysql_up == 0
for: 5m
labels:
severity: critical
annotations:
summary: "MySQL down (instance {{ $labels.instance }})"
description: "MySQL instance is down on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: MysqlTooManyConnections
expr: avg by (instance) (max_over_time(mysql_global_status_threads_connected[5m])) / avg by (instance) (mysql_global_variables_max_connections) * 100 > 80
for: 5m
labels:
severity: warning
annotations:
summary: "MySQL too many connections (instance {{ $labels.instance }})"
description: "More than 80% of MySQL connections are in use on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: MysqlHighThreadsRunning
expr: avg by (instance) (max_over_time(mysql_global_status_threads_running[5m])) / avg by (instance) (mysql_global_variables_max_connections) * 100 > 60
for: 5m
labels:
severity: warning
annotations:
summary: "MySQL high threads running (instance {{ $labels.instance }})"
description: "More than 60% of MySQL connections are in running state on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: MysqlSlaveIoThreadNotRunning
expr: mysql_slave_status_master_server_id > 0 and ON (instance) mysql_slave_status_slave_io_running == 0
for: 5m
labels:
severity: critical
annotations:
summary: "MySQL Slave IO thread not running (instance {{ $labels.instance }})"
description: "MySQL Slave IO thread not running on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: MysqlSlaveSqlThreadNotRunning
expr: mysql_slave_status_master_server_id > 0 and ON (instance) mysql_slave_status_slave_sql_running == 0
for: 5m
labels:
severity: critical
annotations:
summary: "MySQL Slave SQL thread not running (instance {{ $labels.instance }})"
description: "MySQL Slave SQL thread not running on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: MysqlSlaveReplicationLag
expr: mysql_slave_status_master_server_id > 0 and ON (instance) (mysql_slave_status_seconds_behind_master - mysql_slave_status_sql_delay) > 300
for: 5m
labels:
severity: warning
annotations:
summary: "MySQL Slave replication lag (instance {{ $labels.instance }})"
description: "MysqL replication lag on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: MysqlSlowQueries
expr: mysql_global_status_slow_queries > 0
for: 5m
labels:
severity: warning
annotations:
summary: "MySQL slow queries (instance {{ $labels.instance }})"
description: "MySQL server is having some slow queries.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: MysqlRestarted
expr: mysql_global_status_uptime < 60
for: 5m
labels:
severity: warning
annotations:
summary: "MySQL restarted (instance {{ $labels.instance }})"
description: "MySQL has just been restarted, less than one minute ago on {{ $labels.instance }}.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KafkaTopicsReplicas
expr: sum(kafka_topic_partition_in_sync_replica) by (topic) < 3
for: 5m
labels:
severity: critical
annotations:
summary: "Kafka topics replicas (instance {{ $labels.instance }})"
description: "Kafka topic in-sync partition\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KafkaConsumersGroup
expr: sum(kafka_consumergroup_lag) by (consumergroup) > 50
for: 5m
labels:
severity: critical
annotations:
summary: "Kafka consumers group (instance {{ $labels.instance }})"
description: "Kafka consumers group\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: NginxHighHttp4xxErrorRate
expr: sum(rate(nginx_http_requests_total{status=~"^4.."}[1m])) / sum(rate(nginx_http_requests_total[1m])) * 100 > 5
for: 5m
labels:
severity: critical
annotations:
summary: "Nginx high HTTP 4xx error rate (instance {{ $labels.instance }})"
description: "Too many HTTP requests with status 4xx (> 5%)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: NginxHighHttp5xxErrorRate
expr: sum(rate(nginx_http_requests_total{status=~"^5.."}[1m])) / sum(rate(nginx_http_requests_total[1m])) * 100 > 5
for: 5m
labels:
severity: critical
annotations:
summary: "Nginx high HTTP 5xx error rate (instance {{ $labels.instance }})"
description: "Too many HTTP requests with status 5xx (> 5%)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: NginxLatencyHigh
expr: histogram_quantile(0.99, sum(rate(nginx_http_request_duration_seconds_bucket[30m])) by (host, node)) > 10
for: 5m
labels:
severity: warning
annotations:
summary: "Nginx latency high (instance {{ $labels.instance }})"
description: "Nginx p99 latency is higher than 10 seconds\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesNodeReady
expr: kube_node_status_condition{condition="Ready",status="true"} == 0
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes Node ready (instance {{ $labels.instance }})"
description: "Node {{ $labels.node }} has been unready for a long time\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesMemoryPressure
expr: kube_node_status_condition{condition="MemoryPressure",status="true"} == 1
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes memory pressure (instance {{ $labels.instance }})"
description: "{{ $labels.node }} has MemoryPressure condition\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesDiskPressure
expr: kube_node_status_condition{condition="DiskPressure",status="true"} == 1
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes disk pressure (instance {{ $labels.instance }})"
description: "{{ $labels.node }} has DiskPressure condition\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesOutOfDisk
expr: kube_node_status_condition{condition="OutOfDisk",status="true"} == 1
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes out of disk (instance {{ $labels.instance }})"
description: "{{ $labels.node }} has OutOfDisk condition\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesJobFailed
expr: kube_job_status_failed > 0
for: 5m
labels:
severity: warning
annotations:
summary: "Kubernetes Job failed (instance {{ $labels.instance }})"
description: "Job {{$labels.namespace}}/{{$labels.exported_job}} failed to complete\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesCronjobSuspended
expr: kube_cronjob_spec_suspend != 0
for: 5m
labels:
severity: warning
annotations:
summary: "Kubernetes CronJob suspended (instance {{ $labels.instance }})"
description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is suspended\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesPersistentvolumeclaimPending
expr: kube_persistentvolumeclaim_status_phase{phase="Pending"} == 1
for: 5m
labels:
severity: warning
annotations:
summary: "Kubernetes PersistentVolumeClaim pending (instance {{ $labels.instance }})"
description: "PersistentVolumeClaim {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is pending\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesVolumeOutOfDiskSpace
expr: kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes * 100 < 10
for: 5m
labels:
severity: warning
annotations:
summary: "Kubernetes Volume out of disk space (instance {{ $labels.instance }})"
description: "Volume is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesVolumeFullInFourDays
expr: predict_linear(kubelet_volume_stats_available_bytes[6h], 4 * 24 * 3600) < 0
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes Volume full in four days (instance {{ $labels.instance }})"
description: "{{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is expected to fill up within four days. Currently {{ $value | humanize }}% is available.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesPersistentvolumeError
expr: kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"} > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes PersistentVolume error (instance {{ $labels.instance }})"
description: "Persistent volume is in bad state\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesStatefulsetDown
expr: (kube_statefulset_status_replicas_ready / kube_statefulset_status_replicas_current) != 1
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes StatefulSet down (instance {{ $labels.instance }})"
description: "A StatefulSet went down\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesHpaScalingAbility
expr: kube_hpa_status_condition{condition="false", status="AbleToScale"} == 1
for: 5m
labels:
severity: warning
annotations:
summary: "Kubernetes HPA scaling ability (instance {{ $labels.instance }})"
description: "Pod is unable to scale\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesHpaMetricAvailability
expr: kube_hpa_status_condition{condition="false", status="ScalingActive"} == 1
for: 5m
labels:
severity: warning
annotations:
summary: "Kubernetes HPA metric availability (instance {{ $labels.instance }})"
description: "HPA is not able to colelct metrics\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesHpaScaleCapability
expr: kube_hpa_status_desired_replicas >= kube_hpa_spec_max_replicas
for: 5m
labels:
severity: warning
annotations:
summary: "Kubernetes HPA scale capability (instance {{ $labels.instance }})"
description: "The maximum number of desired Pods has been hit\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesPodNotHealthy
expr: min_over_time(sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"})[1h:]) > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes Pod not healthy (instance {{ $labels.instance }})"
description: "Pod has been in a non-ready state for longer than an hour.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesPodCrashLooping
expr: rate(kube_pod_container_status_restarts_total[15m]) * 60 * 5 > 5
for: 5m
labels:
severity: warning
annotations:
summary: "Kubernetes pod crash looping (instance {{ $labels.instance }})"
description: "Pod {{ $labels.pod }} is crash looping\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesReplicassetMismatch
expr: kube_replicaset_spec_replicas != kube_replicaset_status_ready_replicas
for: 5m
labels:
severity: warning
annotations:
summary: "Kubernetes ReplicasSet mismatch (instance {{ $labels.instance }})"
description: "Deployment Replicas mismatch\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesDeploymentReplicasMismatch
expr: kube_deployment_spec_replicas != kube_deployment_status_replicas_available
for: 5m
labels:
severity: warning
annotations:
summary: "Kubernetes Deployment replicas mismatch (instance {{ $labels.instance }})"
description: "Deployment Replicas mismatch\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesStatefulsetReplicasMismatch
expr: kube_statefulset_status_replicas_ready != kube_statefulset_status_replicas
for: 5m
labels:
severity: warning
annotations:
summary: "Kubernetes StatefulSet replicas mismatch (instance {{ $labels.instance }})"
description: "A StatefulSet has not matched the expected number of replicas for longer than 15 minutes.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesDeploymentGenerationMismatch
expr: kube_deployment_status_observed_generation != kube_deployment_metadata_generation
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes Deployment generation mismatch (instance {{ $labels.instance }})"
description: "A Deployment has failed but has not been rolled back.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesStatefulsetGenerationMismatch
expr: kube_statefulset_status_observed_generation != kube_statefulset_metadata_generation
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes StatefulSet generation mismatch (instance {{ $labels.instance }})"
description: "A StatefulSet has failed but has not been rolled back.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesStatefulsetUpdateNotRolledOut
expr: max without (revision) (kube_statefulset_status_current_revision unless kube_statefulset_status_update_revision) * (kube_statefulset_replicas != kube_statefulset_status_replicas_updated)
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes StatefulSet update not rolled out (instance {{ $labels.instance }})"
description: "StatefulSet update has not been rolled out.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesDaemonsetRolloutStuck
expr: kube_daemonset_status_number_ready / kube_daemonset_status_desired_number_scheduled * 100 < 100 or kube_daemonset_status_desired_number_scheduled - kube_daemonset_status_current_number_scheduled > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes DaemonSet rollout stuck (instance {{ $labels.instance }})"
description: "Some Pods of DaemonSet are not scheduled or not ready\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesDaemonsetMisscheduled
expr: kube_daemonset_status_number_misscheduled > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes DaemonSet misscheduled (instance {{ $labels.instance }})"
description: "Some DaemonSet Pods are running where they are not supposed to run\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesCronjobTooLong
expr: time() - kube_cronjob_next_schedule_time > 3600
for: 5m
labels:
severity: warning
annotations:
summary: "Kubernetes CronJob too long (instance {{ $labels.instance }})"
description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking more than 1h to complete.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesJobCompletion
expr: kube_job_spec_completions - kube_job_status_succeeded > 0 or kube_job_status_failed > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes job completion (instance {{ $labels.instance }})"
description: "Kubernetes Job failed to complete\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesApiServerErrors
expr: sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[2m])) / sum(rate(apiserver_request_count{job="apiserver"}[2m])) * 100 > 3
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes API server errors (instance {{ $labels.instance }})"
description: "Kubernetes API server is experiencing high error rate\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesApiClientErrors
expr: (sum(rate(rest_client_requests_total{code=~"(4|5).."}[2m])) by (instance, job) / sum(rate(rest_client_requests_total[2m])) by (instance, job)) * 100 > 1
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes API client errors (instance {{ $labels.instance }})"
description: "Kubernetes API client is experiencing high error rate\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesClientCertificateExpiresNextWeek
expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 7*24*60*60
for: 5m
labels:
severity: warning
annotations:
summary: "Kubernetes client certificate expires next week (instance {{ $labels.instance }})"
description: "A client certificate used to authenticate to the apiserver is expiring next week.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesClientCertificateExpiresSoon
expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 24*60*60
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes client certificate expires soon (instance {{ $labels.instance }})"
description: "A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesApiServerLatency
expr: histogram_quantile(0.99, sum(apiserver_request_latencies_bucket{verb!~"CONNECT|WATCHLIST|WATCH|PROXY"}) WITHOUT (instance, resource)) / 1e+06 > 1
for: 5m
labels:
severity: warning
annotations:
summary: "Kubernetes API server latency (instance {{ $labels.instance }})"
description: "Kubernetes API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: CephState
expr: ceph_health_status != 0
for: 5m
labels:
severity: critical
annotations:
summary: "Ceph State (instance {{ $labels.instance }})"
description: "Ceph instance unhealthy\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: CephMonitorClockSkew
expr: abs(ceph_monitor_clock_skew_seconds) > 0.2
for: 5m
labels:
severity: warning
annotations:
summary: "Ceph monitor clock skew (instance {{ $labels.instance }})"
description: "Ceph monitor clock skew detected. Please check ntp and hardware clock settings\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: CephMonitorLowSpace
expr: ceph_monitor_avail_percent < 10
for: 5m
labels:
severity: warning
annotations:
summary: "Ceph monitor low space (instance {{ $labels.instance }})"
description: "Ceph monitor storage is low.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: CephOsdDown
expr: ceph_osd_up == 0
for: 5m
labels:
severity: critical
annotations:
summary: "Ceph OSD Down (instance {{ $labels.instance }})"
description: "Ceph Object Storage Daemon Down\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: CephHighOsdLatency
expr: ceph_osd_perf_apply_latency_seconds > 10
for: 5m
labels:
severity: warning
annotations:
summary: "Ceph high OSD latency (instance {{ $labels.instance }})"
description: "Ceph Object Storage Daemon latetncy is high. Please check if it doesn't stuck in weird state.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: CephOsdLowSpace
expr: ceph_osd_utilization > 90
for: 5m
labels:
severity: warning
annotations:
summary: "Ceph OSD low space (instance {{ $labels.instance }})"
description: "Ceph Object Storage Daemon is going out of space. Please add more disks.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: CephOsdReweighted
expr: ceph_osd_weight < 1
for: 5m
labels:
severity: warning
annotations:
summary: "Ceph OSD reweighted (instance {{ $labels.instance }})"
description: "Ceph Object Storage Daemon take ttoo much time to resize.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: CephPgDown
expr: ceph_pg_down > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Ceph PG down (instance {{ $labels.instance }})"
description: "Some Ceph placement groups are down. Please ensure that all the data are available.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: CephPgIncomplete
expr: ceph_pg_incomplete > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Ceph PG incomplete (instance {{ $labels.instance }})"
description: "Some Ceph placement groups are incomplete. Please ensure that all the data are available.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: CephPgInconsistant
expr: ceph_pg_inconsistent > 0
for: 5m
labels:
severity: warning
annotations:
summary: "Ceph PG inconsistant (instance {{ $labels.instance }})"
description: "Some Ceph placement groups are inconsitent. Data is available but inconsistent across nodes.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: CephPgActivationLong
expr: ceph_pg_activating > 0
for: 5m
labels:
severity: warning
annotations:
summary: "Ceph PG activation long (instance {{ $labels.instance }})"
description: "Some Ceph placement groups are too long to activate.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: CephPgBackfillFull
expr: ceph_pg_backfill_toofull > 0
for: 5m
labels:
severity: warning
annotations:
summary: "Ceph PG backfill full (instance {{ $labels.instance }})"
description: "Some Ceph placement groups are located on full Object Storage Daemon on cluster. Those PGs can be unavailable shortly. Please check OSDs, change weight or reconfigure CRUSH rules.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: CephPgUnavailable
expr: ceph_pg_total - ceph_pg_active > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Ceph PG unavailable (instance {{ $labels.instance }})"
description: "Some Ceph placement groups are unavailable.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: ThanosCompactionHalted
expr: thanos_compactor_halted == 1
for: 5m
labels:
severity: critical
annotations:
summary: "Thanos compaction halted (instance {{ $labels.instance }})"
description: "Thanos compaction has failed to run and is now halted.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: ThanosCompactBucketOperationFailure
expr: rate(thanos_objstore_bucket_operation_failures_total[1m]) > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Thanos compact bucket operation failure (instance {{ $labels.instance }})"
description: "Thanos compaction has failing storage operations\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: ThanosCompactNotRun
expr: (time() - thanos_objstore_bucket_last_successful_upload_time) > 24*60*60
for: 5m
labels:
severity: critical
annotations:
summary: "Thanos compact not run (instance {{ $labels.instance }})"
description: "Thanos compaction has not run in 24 hours.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostOutOfMemory
expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
# expr: (1 - sum by(instance) (node_memory_MemAvailable_bytes) / sum by(instance) (node_memory_MemTotal_bytes)) * 100 >= 80
for: 5m
labels:
severity: warning
annotations:
summary: "Host out of memory (instance {{ $labels.instance }})"
description: "Node memory is filling up (< 10% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostMemoryUnderMemoryPressure
expr: rate(node_vmstat_pgmajfault[5m]) > 1000
for: 5m
labels:
severity: warning
annotations:
summary: "Host memory under memory pressure (instance {{ $labels.instance }})"
description: "The node is under heavy memory pressure. High rate of major page faults\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostUnusualNetworkThroughputIn
expr: sum by (instance) (irate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100
for: 5m
labels:
severity: warning
annotations:
summary: "Host unusual network throughput in (instance {{ $labels.instance }})"
description: "Host network interfaces are probably receiving too much data (> 100 MB/s)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostUnusualNetworkThroughputOut
expr: sum by (instance) (irate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100
for: 5m
labels:
severity: warning
annotations:
summary: "Host unusual network throughput out (instance {{ $labels.instance }})"
description: "Host network interfaces are probably sending too much data (> 100 MB/s)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostUnusualDiskReadRate
expr: sum by (instance) (irate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50
for: 5m
labels:
severity: warning
annotations:
summary: "Host unusual disk read rate (instance {{ $labels.instance }})"
description: "Disk is probably reading too much data (> 50 MB/s)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostUnusualDiskWriteRate
expr: sum by (instance) (irate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50
for: 5m
labels:
severity: warning
annotations:
summary: "Host unusual disk write rate (instance {{ $labels.instance }})"
description: "Disk is probably writing too much data (> 50 MB/s)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostOutOfDiskSpace
expr: node_filesystem_avail_bytes{mountpoint=~"(/|/u01)"} / node_filesystem_size_bytes{mountpoint=~"(/|/u01)"} * 100 < 10
for: 5m
labels:
severity: warning
annotations:
summary: "Host out of disk space (instance {{ $labels.instance }})"
description: "Disk is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostDiskWillFillIn24Hours
expr: predict_linear(node_filesystem_free_bytes{fstype!~"tmpfs"}[1h], 24 * 3600) < 0
for: 5m
labels:
severity: warning
annotations:
summary: "Host disk will fill in 24 hours (instance {{ $labels.instance }})"
description: "Disk will fill in 24 hours at current write rate\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostOutOfInodes
expr: node_filesystem_files_free{mountpoint=~"(/|/u01)"} / node_filesystem_files{mountpoint=~"(/|/u01)"} * 100 < 10
for: 5m
labels:
severity: warning
annotations:
summary: "Host out of inodes (instance {{ $labels.instance }})"
description: "Disk is almost running out of available inodes (< 10% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostUnusualDiskReadLatency
expr: rate(node_disk_read_time_seconds_total[2m]) / rate(node_disk_reads_completed_total[2m]) > 100
for: 5m
labels:
severity: warning
annotations:
summary: "Host unusual disk read latency (instance {{ $labels.instance }})"
description: "Disk latency is growing (read operations > 100ms)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostUnusualDiskWriteLatency
expr: rate(node_disk_write_time_seconds_total[2m]) / rate(node_disk_writes_completed_total[2m]) > 100
for: 5m
labels:
severity: warning
annotations:
summary: "Host unusual disk write latency (instance {{ $labels.instance }})"
description: "Disk latency is growing (write operations > 100ms)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostHighCpuLoad
expr: 100 - (avg by(instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
#expr: sum by(node) (node_load1) / sum by(node) (machine_cpu_cores) * 100 > 100
for: 5m
labels:
severity: warning
annotations:
summary: "Host high CPU load (instance {{ $labels.instance }})"
description: "CPU load is > 80%\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
# 1000 context switches is an arbitrary number.
# Alert threshold depends on nature of application.
# Please read: https://github.com/samber/awesome-prometheus-alerts/issues/58
- alert: HostContextSwitching
expr: (rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 1000
for: 5m
labels:
severity: warning
annotations:
summary: "Host context switching (instance {{ $labels.instance }})"
description: "Context switching is growing on node (> 1000 / s)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostSwapIsFillingUp
expr: (1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80
for: 5m
labels:
severity: warning
annotations:
summary: "Host swap is filling up (instance {{ $labels.instance }})"
description: "Swap is filling up (>80%)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostSystemdServiceCrashed
expr: node_systemd_unit_state{state="failed"} == 1
for: 5m
labels:
severity: warning
annotations:
summary: "Host SystemD service crashed (instance {{ $labels.instance }})"
description: "SystemD service crashed\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostPhysicalComponentTooHot
expr: node_hwmon_temp_celsius > 75
for: 5m
labels:
severity: warning
annotations:
summary: "Host physical component too hot (instance {{ $labels.instance }})"
description: "Physical hardware component too hot\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostNodeOvertemperatureAlarm
expr: node_hwmon_temp_alarm == 1
for: 5m
labels:
severity: critical
annotations:
summary: "Host node overtemperature alarm (instance {{ $labels.instance }})"
description: "Physical node temperature alarm triggered\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostRaidArrayGotInactive
expr: node_md_state{state="inactive"} > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Host RAID array got inactive (instance {{ $labels.instance }})"
description: "RAID array {{ $labels.device }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostKernelVersionDeviations
expr: count(sum(label_replace(node_uname_info, "kernel", "$1", "release", "([0-9]+.[0-9]+).[0-9]+.*")) by (kernel)) > 1
for: 5m
labels:
severity: warning
annotations:
summary: "Host kernel version deviations (instance {{ $labels.instance }})"
description: "Different kernel versions are running\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostNetworkReceiveErrors
expr: increase(node_network_receive_errs_total[5m]) > 0
for: 5m
labels:
severity: warning
annotations:
summary: "Host Network Receive Errors (instance {{ $labels.instance }})"
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive errors in the last five minutes.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}'
- alert: HostNetworkTransmitErrors
expr: increase(node_network_transmit_errs_total[5m]) > 0
for: 5m
labels:
severity: warning
annotations:
summary: "Host Network Transmit Errors (instance {{ $labels.instance }})"
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit errors in the last five minutes.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}'
- alert: BlackboxProbeFailed
expr: probe_success == 0
for: 5m
labels:
severity: critical
annotations:
summary: "Blackbox probe failed (instance {{ $labels.instance }})"
description: "Probe failed\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: BlackboxSlowProbe
expr: avg_over_time(probe_duration_seconds[1m]) > 1
for: 5m
labels:
severity: warning
annotations:
summary: "Blackbox slow probe (instance {{ $labels.instance }})"
description: "Blackbox probe took more than 1s to complete\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: BlackboxProbeHttpFailure
expr: probe_http_status_code <= 199 OR probe_http_status_code >= 400
for: 5m
labels:
severity: critical
annotations:
summary: "Blackbox probe HTTP failure (instance {{ $labels.instance }})"
description: "HTTP status code is not 200-399\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: BlackboxSslCertificateWillExpireSoon
expr: probe_ssl_earliest_cert_expiry - time() < 86400 * 15
for: 5m
labels:
severity: warning
annotations:
summary: "Blackbox SSL certificate will expire soon (instance {{ $labels.instance }})"
description: "SSL certificate expires in 15 days\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: BlackboxSslCertificateExpired
expr: probe_ssl_earliest_cert_expiry - time() <= 0
for: 5m
labels:
severity: critical
annotations:
summary: "Blackbox SSL certificate expired (instance {{ $labels.instance }})"
description: "SSL certificate has expired already\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: BlackboxProbeSlowHttp
expr: avg_over_time(probe_http_duration_seconds[1m]) > 1
for: 5m
labels:
severity: warning
annotations:
summary: "Blackbox probe slow HTTP (instance {{ $labels.instance }})"
description: "HTTP request took more than 1s\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: BlackboxProbeSlowPing
expr: avg_over_time(probe_icmp_duration_seconds[1m]) > 1
for: 5m
labels:
severity: warning
annotations:
summary: "Blackbox probe slow ping (instance {{ $labels.instance }})"
description: "Blackbox ping took more than 1s\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: MysqlDown
expr: mysql_up == 0
for: 5m
labels:
severity: critical
annotations:
summary: "MySQL down (instance {{ $labels.instance }})"
description: "MySQL instance is down on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: MysqlTooManyConnections
expr: avg by (instance) (max_over_time(mysql_global_status_threads_connected[5m])) / avg by (instance) (mysql_global_variables_max_connections) * 100 > 80
for: 5m
labels:
severity: warning
annotations:
summary: "MySQL too many connections (instance {{ $labels.instance }})"
description: "More than 80% of MySQL connections are in use on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: MysqlHighThreadsRunning
expr: avg by (instance) (max_over_time(mysql_global_status_threads_running[5m])) / avg by (instance) (mysql_global_variables_max_connections) * 100 > 60
for: 5m
labels:
severity: warning
annotations:
summary: "MySQL high threads running (instance {{ $labels.instance }})"
description: "More than 60% of MySQL connections are in running state on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: EtcdNoLeader
expr: etcd_server_has_leader != 1
for: 5m
labels:
severity: critical
annotations:
summary: "Etcd no Leader (instance {{ $labels.instance }})"
description: "Etcd cluster have no leader\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: EtcdHighNumberOfLeaderChanges
expr: increase(etcd_server_leader_changes_seen_total[1h]) > 3
for: 5m
labels:
severity: warning
annotations:
summary: "Etcd high number of leader changes (instance {{ $labels.instance }})"
description: "Etcd leader changed more than 3 times during last hour\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: EtcdHighNumberOfFailedGrpcRequests
expr: sum(rate(grpc_server_handled_total{grpc_code!="OK"}[5m])) BY (grpc_service, grpc_method) / sum(rate(grpc_server_handled_total[5m])) BY (grpc_service, grpc_method) > 0.01
for: 5m
labels:
severity: warning
annotations:
summary: "Etcd high number of failed GRPC requests (instance {{ $labels.instance }})"
description: "More than 1% GRPC request failure detected in Etcd for 5 minutes\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: EtcdHighNumberOfFailedGrpcRequests
expr: sum(rate(grpc_server_handled_total{grpc_code!="OK"}[5m])) BY (grpc_service, grpc_method) / sum(rate(grpc_server_handled_total[5m])) BY (grpc_service, grpc_method) > 0.01
for: 5m
labels:
severity: warning
annotations:
summary: "Etcd high number of failed GRPC requests (instance {{ $labels.instance }})"
description: "More than 1% GRPC request failure detected in Etcd for 5 minutes\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: EtcdMemberCommunicationSlow
expr: histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket[5m])) > 0.15
for: 5m
labels:
severity: warning
annotations:
summary: "Etcd member communication slow (instance {{ $labels.instance }})"
description: "Etcd member communication slowing down, 99th percentil is over 0.15s for 5 minutes\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: EtcdHighNumberOfFailedProposals
expr: increase(etcd_server_proposals_failed_total[1h]) > 5
for: 5m
labels:
severity: warning
annotations:
summary: "Etcd high number of failed proposals (instance {{ $labels.instance }})"
description: "Etcd server got more than 5 failed proposals past hour\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: EtcdHighFsyncDurations
expr: histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m])) > 0.5
for: 5m
labels:
severity: warning
annotations:
summary: "Etcd high fsync durations (instance {{ $labels.instance }})"
description: "Etcd WAL fsync duration increasing, 99th percentil is over 0.5s for 5 minutes\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: EtcdHighCommitDurations
expr: histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[5m])) > 0.25
for: 5m
labels:
severity: warning
annotations:
summary: "Etcd high commit durations (instance {{ $labels.instance }})"
description: "Etcd commit duration increasing, 99th percentil is over 0.25s for 5 minutes\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: CorednsPanicCount
expr: increase(coredns_panic_count_total[10m]) > 0
for: 5m
labels:
severity: critical
annotations:
summary: "CoreDNS Panic Count (instance {{ $labels.instance }})"
description: "Number of CoreDNS panics encountered\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"