763 lines
31 KiB
YAML
763 lines
31 KiB
YAML
---
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PodMonitor
|
|
metadata:
|
|
name: metrics
|
|
spec:
|
|
namespaceSelector: {}
|
|
selector: {}
|
|
podMetricsEndpoints:
|
|
- port: exporter
|
|
- port: metrics
|
|
---
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: Alertmanager
|
|
metadata:
|
|
name: alertmanager
|
|
spec:
|
|
nodeSelector:
|
|
dedicated: monitoring
|
|
tolerations:
|
|
- key: dedicated
|
|
operator: Equal
|
|
value: monitoring
|
|
effect: NoSchedule
|
|
replicas: 3
|
|
serviceAccountName: alertmanager
|
|
externalUrl: http://am.k-space.ee/
|
|
routePrefix: "/"
|
|
securityContext:
|
|
fsGroup: 2000
|
|
runAsGroup: 2000
|
|
runAsNonRoot: true
|
|
runAsUser: 1000
|
|
---
|
|
apiVersion: v1
|
|
kind: ServiceAccount
|
|
metadata:
|
|
name: alertmanager
|
|
---
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: Prometheus
|
|
metadata:
|
|
name: prometheus
|
|
spec:
|
|
nodeSelector:
|
|
dedicated: monitoring
|
|
tolerations:
|
|
- key: dedicated
|
|
operator: Equal
|
|
value: monitoring
|
|
effect: NoSchedule
|
|
alerting:
|
|
alertmanagers:
|
|
- namespace: prometheus-operator
|
|
name: alertmanager
|
|
port: http
|
|
pathPrefix: "/"
|
|
apiVersion: v2
|
|
externalUrl: "http://prom.k-space.ee/"
|
|
replicas: 2
|
|
shards: 1
|
|
serviceAccountName: prometheus
|
|
securityContext:
|
|
fsGroup: 2000
|
|
runAsGroup: 2000
|
|
runAsNonRoot: true
|
|
runAsUser: 1000
|
|
serviceMonitorNamespaceSelector: {}
|
|
serviceMonitorSelector: {}
|
|
podMonitorNamespaceSelector: {}
|
|
podMonitorSelector: {}
|
|
probeNamespaceSelector: {}
|
|
probeSelector: {}
|
|
ruleNamespaceSelector: {}
|
|
ruleSelector: {}
|
|
retentionSize: 80GB
|
|
storage:
|
|
volumeClaimTemplate:
|
|
spec:
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
resources:
|
|
requests:
|
|
storage: 100Gi
|
|
storageClassName: local-path
|
|
---
|
|
apiVersion: v1
|
|
kind: ServiceAccount
|
|
metadata:
|
|
name: prometheus
|
|
---
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRole
|
|
metadata:
|
|
name: prometheus
|
|
rules:
|
|
- apiGroups: [""]
|
|
resources:
|
|
- nodes
|
|
- nodes/metrics
|
|
- services
|
|
- endpoints
|
|
- pods
|
|
verbs: ["get", "list", "watch"]
|
|
- apiGroups: [""]
|
|
resources:
|
|
- configmaps
|
|
verbs: ["get"]
|
|
- apiGroups:
|
|
- networking.k8s.io
|
|
resources:
|
|
- ingresses
|
|
verbs: ["get", "list", "watch"]
|
|
- nonResourceURLs: ["/metrics"]
|
|
verbs: ["get"]
|
|
---
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRoleBinding
|
|
metadata:
|
|
name: prometheus
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: ClusterRole
|
|
name: prometheus
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: prometheus
|
|
namespace: prometheus-operator
|
|
---
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: prometheus
|
|
spec:
|
|
groups:
|
|
- name: prometheus
|
|
rules:
|
|
- alert: PrometheusJobMissing
|
|
annotations:
|
|
description: "A Prometheus job has disappeared\n VALUE = {{ $value }}\n \
|
|
\ LABELS = {{ $labels }}"
|
|
summary: Prometheus job missing (instance {{ $labels.instance }})
|
|
expr: absent(up{job="prometheus-operator/prometheus"})
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusTargetMissing
|
|
annotations:
|
|
description: "A Prometheus target has disappeared. An exporter might be crashed.\n\
|
|
\ VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus target missing (instance {{ $labels.instance }})
|
|
expr: up == 0
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusAllTargetsMissing
|
|
annotations:
|
|
description: "A Prometheus job does not have living target anymore.\n VALUE\
|
|
\ = {{ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus all targets missing (instance {{ $labels.instance }})
|
|
expr: count by (job) (up) == 0
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusConfigurationReloadFailure
|
|
annotations:
|
|
description: "Prometheus configuration reload error\n VALUE = {{ $value }}\n\
|
|
\ LABELS = {{ $labels }}"
|
|
summary: Prometheus configuration reload failure (instance {{ $labels.instance
|
|
}})
|
|
expr: prometheus_config_last_reload_successful != 1
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusTooManyRestarts
|
|
annotations:
|
|
description: "Prometheus has restarted more than twice in the last 15 minutes.\
|
|
\ It might be crashlooping.\n VALUE = {{ $value }}\n LABELS = {{ $labels\
|
|
\ }}"
|
|
summary: Prometheus too many restarts (instance {{ $labels.instance }})
|
|
expr: changes(process_start_time_seconds{job=~"prometheus|pushgateway|alertmanager"}[15m])
|
|
> 2
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusAlertmanagerJobMissing
|
|
annotations:
|
|
description: "A Prometheus AlertManager job has disappeared\n VALUE = {{\
|
|
\ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus AlertManager job missing (instance {{ $labels.instance
|
|
}})
|
|
expr: absent(up{job="prometheus-operator/alertmanager"})
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusAlertmanagerConfigurationReloadFailure
|
|
annotations:
|
|
description: "AlertManager configuration reload error\n VALUE = {{ $value\
|
|
\ }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus AlertManager configuration reload failure (instance {{
|
|
$labels.instance }})
|
|
expr: alertmanager_config_last_reload_successful != 1
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusAlertmanagerConfigNotSynced
|
|
annotations:
|
|
description: "Configurations of AlertManager cluster instances are out of\
|
|
\ sync\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus AlertManager config not synced (instance {{ $labels.instance
|
|
}})
|
|
expr: count(count_values("config_hash", alertmanager_config_hash)) > 1
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusNotConnectedToAlertmanager
|
|
annotations:
|
|
description: "Prometheus cannot connect the alertmanager\n VALUE = {{ $value\
|
|
\ }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus not connected to alertmanager (instance {{ $labels.instance
|
|
}})
|
|
expr: prometheus_notifications_alertmanagers_discovered < 1
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusRuleEvaluationFailures
|
|
annotations:
|
|
description: "Prometheus encountered {{ $value }} rule evaluation failures,\
|
|
\ leading to potentially ignored alerts.\n VALUE = {{ $value }}\n LABELS\
|
|
\ = {{ $labels }}"
|
|
summary: Prometheus rule evaluation failures (instance {{ $labels.instance
|
|
}})
|
|
expr: increase(prometheus_rule_evaluation_failures_total[3m]) > 0
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusTemplateTextExpansionFailures
|
|
annotations:
|
|
description: "Prometheus encountered {{ $value }} template text expansion\
|
|
\ failures\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus template text expansion failures (instance {{ $labels.instance
|
|
}})
|
|
expr: increase(prometheus_template_text_expansion_failures_total[3m]) > 0
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusRuleEvaluationSlow
|
|
annotations:
|
|
description: "Prometheus rule evaluation took more time than the scheduled\
|
|
\ interval. It indicates a slower storage backend access or too complex\
|
|
\ query.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus rule evaluation slow (instance {{ $labels.instance }})
|
|
expr: prometheus_rule_group_last_duration_seconds > prometheus_rule_group_interval_seconds
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusNotificationsBacklog
|
|
annotations:
|
|
description: "The Prometheus notification queue has not been empty for 10\
|
|
\ minutes\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus notifications backlog (instance {{ $labels.instance }})
|
|
expr: min_over_time(prometheus_notifications_queue_length[10m]) > 0
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusAlertmanagerNotificationFailing
|
|
annotations:
|
|
description: "Alertmanager is failing sending notifications\n VALUE = {{\
|
|
\ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus AlertManager notification failing (instance {{ $labels.instance
|
|
}})
|
|
expr: rate(alertmanager_notifications_failed_total[1m]) > 0
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusTargetEmpty
|
|
annotations:
|
|
description: "Prometheus has no target in service discovery\n VALUE = {{\
|
|
\ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus target empty (instance {{ $labels.instance }})
|
|
expr: prometheus_sd_discovered_targets == 0
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusLargeScrape
|
|
annotations:
|
|
description: "Prometheus has many scrapes that exceed the sample limit\n \
|
|
\ VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus large scrape (instance {{ $labels.instance }})
|
|
expr: increase(prometheus_target_scrapes_exceeded_sample_limit_total[10m]) >
|
|
10
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusTargetScrapeDuplicate
|
|
annotations:
|
|
description: "Prometheus has many samples rejected due to duplicate timestamps\
|
|
\ but different values\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus target scrape duplicate (instance {{ $labels.instance
|
|
}})
|
|
expr: increase(prometheus_target_scrapes_sample_duplicate_timestamp_total[5m])
|
|
> 0
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusTsdbCheckpointCreationFailures
|
|
annotations:
|
|
description: "Prometheus encountered {{ $value }} checkpoint creation failures\n\
|
|
\ VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus TSDB checkpoint creation failures (instance {{ $labels.instance
|
|
}})
|
|
expr: increase(prometheus_tsdb_checkpoint_creations_failed_total[1m]) > 0
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusTsdbCheckpointDeletionFailures
|
|
annotations:
|
|
description: "Prometheus encountered {{ $value }} checkpoint deletion failures\n\
|
|
\ VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus TSDB checkpoint deletion failures (instance {{ $labels.instance
|
|
}})
|
|
expr: increase(prometheus_tsdb_checkpoint_deletions_failed_total[1m]) > 0
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusTsdbCompactionsFailed
|
|
annotations:
|
|
description: "Prometheus encountered {{ $value }} TSDB compactions failures\n\
|
|
\ VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus TSDB compactions failed (instance {{ $labels.instance
|
|
}})
|
|
expr: increase(prometheus_tsdb_compactions_failed_total[1m]) > 0
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusTsdbHeadTruncationsFailed
|
|
annotations:
|
|
description: "Prometheus encountered {{ $value }} TSDB head truncation failures\n\
|
|
\ VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus TSDB head truncations failed (instance {{ $labels.instance
|
|
}})
|
|
expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) > 0
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusTsdbReloadFailures
|
|
annotations:
|
|
description: "Prometheus encountered {{ $value }} TSDB reload failures\n \
|
|
\ VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus TSDB reload failures (instance {{ $labels.instance }})
|
|
expr: increase(prometheus_tsdb_reloads_failures_total[1m]) > 0
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusTsdbWalCorruptions
|
|
annotations:
|
|
description: "Prometheus encountered {{ $value }} TSDB WAL corruptions\n \
|
|
\ VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus TSDB WAL is corrupt, make sure there is enough disk space
|
|
and wipe /data/wal
|
|
expr: increase(prometheus_tsdb_wal_corruptions_total[2h]) > 0
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusTsdbWalTruncationsFailed
|
|
annotations:
|
|
description: "Prometheus encountered {{ $value }} TSDB WAL truncation failures\n\
|
|
\ VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
summary: Prometheus TSDB WAL truncations failed (instance {{ $labels.instance
|
|
}})
|
|
expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) > 0
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
---
|
|
apiVersion: networking.k8s.io/v1
|
|
kind: Ingress
|
|
metadata:
|
|
name: prometheus
|
|
annotations:
|
|
cert-manager.io/cluster-issuer: default
|
|
traefik.ingress.kubernetes.io/router.entrypoints: websecure
|
|
traefik.ingress.kubernetes.io/router.tls: "true"
|
|
external-dns.alpha.kubernetes.io/target: traefik.k-space.ee
|
|
traefik.ingress.kubernetes.io/router.middlewares: traefik-sso@kubernetescrd
|
|
spec:
|
|
rules:
|
|
- host: prom.k-space.ee
|
|
http:
|
|
paths:
|
|
- pathType: Prefix
|
|
path: "/"
|
|
backend:
|
|
service:
|
|
name: prometheus-operated
|
|
port:
|
|
number: 9090
|
|
tls:
|
|
- hosts:
|
|
- prom.k-space.ee
|
|
secretName: prom-tls
|
|
---
|
|
apiVersion: networking.k8s.io/v1
|
|
kind: Ingress
|
|
metadata:
|
|
name: alertmanager
|
|
annotations:
|
|
cert-manager.io/cluster-issuer: default
|
|
traefik.ingress.kubernetes.io/router.entrypoints: websecure
|
|
traefik.ingress.kubernetes.io/router.tls: "true"
|
|
external-dns.alpha.kubernetes.io/target: traefik.k-space.ee
|
|
traefik.ingress.kubernetes.io/router.middlewares: traefik-sso@kubernetescrd
|
|
spec:
|
|
rules:
|
|
- host: am.k-space.ee
|
|
http:
|
|
paths:
|
|
- pathType: Prefix
|
|
path: "/"
|
|
backend:
|
|
service:
|
|
name: alertmanager-operated
|
|
port:
|
|
number: 9093
|
|
tls:
|
|
- hosts:
|
|
- am.k-space.ee
|
|
secretName: alertmanager-tls
|
|
---
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PodMonitor
|
|
metadata:
|
|
name: prometheus
|
|
spec:
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: prometheus
|
|
podMetricsEndpoints:
|
|
- port: web
|
|
---
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PodMonitor
|
|
metadata:
|
|
name: alertmanager
|
|
spec:
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: alertmanager
|
|
podMetricsEndpoints:
|
|
- port: web
|
|
---
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PodMonitor
|
|
metadata:
|
|
name: operator
|
|
spec:
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: prometheus-operator
|
|
podMetricsEndpoints:
|
|
- port: http
|
|
---
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: kubelet
|
|
spec:
|
|
endpoints:
|
|
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
|
honorLabels: true
|
|
interval: 30s
|
|
port: https-metrics
|
|
scheme: https
|
|
tlsConfig:
|
|
insecureSkipVerify: true
|
|
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
|
honorLabels: true
|
|
interval: 30s
|
|
path: /metrics/cadvisor
|
|
port: https-metrics
|
|
scheme: https
|
|
tlsConfig:
|
|
insecureSkipVerify: true
|
|
namespaceSelector:
|
|
matchNames:
|
|
- kube-system
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: kubelet
|
|
---
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-state-metrics
|
|
spec:
|
|
groups:
|
|
- name: kube-state-metrics
|
|
rules:
|
|
- alert: KubernetesNodeReady
|
|
expr: kube_node_status_condition{condition="Ready",status="true"} == 0
|
|
for: 10m
|
|
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: 2m
|
|
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: 2m
|
|
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: 2m
|
|
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: KubernetesOutOfCapacity
|
|
expr: sum by (node) ((kube_pod_status_phase{phase="Running"} == 1) + on(uid) group_left(node) (0 * kube_pod_info{pod_template_hash=""})) / sum by (node) (kube_node_status_allocatable{resource="pods"}) * 100 > 90
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes out of capacity (instance {{ $labels.instance }})
|
|
description: "{{ $labels.node }} is out of capacity\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesContainerOomKiller
|
|
expr: (kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason="OOMKilled"}[10m]) == 1
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes container oom killer (instance {{ $labels.instance }})
|
|
description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has been OOMKilled {{ $value }} times in the last 10 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesJobFailed
|
|
expr: kube_job_status_failed > 0
|
|
for: 0m
|
|
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: 0m
|
|
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: 2m
|
|
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: 2m
|
|
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: 0m
|
|
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: 0m
|
|
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: 1m
|
|
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_horizontalpodautoscaler_status_condition{status="false", condition="AbleToScale"} == 1
|
|
for: 2m
|
|
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_horizontalpodautoscaler_status_condition{status="false", condition="ScalingActive"} == 1
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes HPA metric availability (instance {{ $labels.instance }})
|
|
description: "HPA is not able to collect metrics\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesHpaScaleCapability
|
|
expr: kube_horizontalpodautoscaler_status_desired_replicas >= kube_horizontalpodautoscaler_spec_max_replicas
|
|
for: 2m
|
|
labels:
|
|
severity: info
|
|
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"})[15m:1m]) > 0
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes Pod not healthy (instance {{ $labels.instance }})
|
|
description: "Pod has been in a non-ready state for longer than 15 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesPodCrashLooping
|
|
expr: increase(kube_pod_container_status_restarts_total[1m]) > 3
|
|
for: 2m
|
|
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: 10m
|
|
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: 10m
|
|
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: 10m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes StatefulSet replicas mismatch (instance {{ $labels.instance }})
|
|
description: "A StatefulSet does not match the expected number of replicas.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesDeploymentGenerationMismatch
|
|
expr: kube_deployment_status_observed_generation != kube_deployment_metadata_generation
|
|
for: 10m
|
|
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: 10m
|
|
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: 10m
|
|
labels:
|
|
severity: warning
|
|
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: 10m
|
|
labels:
|
|
severity: warning
|
|
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: 1m
|
|
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: 0m
|
|
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: KubernetesJobSlowCompletion
|
|
expr: kube_job_spec_completions - kube_job_status_succeeded > 0
|
|
for: 12h
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes job slow completion (instance {{ $labels.instance }})
|
|
description: "Kubernetes Job {{ $labels.namespace }}/{{ $labels.job_name }} did not complete in time.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesApiServerErrors
|
|
expr: sum(rate(apiserver_request_total{job="apiserver",code=~"^(?:5..)$"}[1m])) / sum(rate(apiserver_request_total{job="apiserver"}[1m])) * 100 > 3
|
|
for: 2m
|
|
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).."}[1m])) by (instance, job) / sum(rate(rest_client_requests_total[1m])) by (instance, job)) * 100 > 1
|
|
for: 2m
|
|
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: 0m
|
|
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: 0m
|
|
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 = {{ $labels }}"
|
|
- alert: KubernetesApiServerLatency
|
|
expr: histogram_quantile(0.99, sum(rate(apiserver_request_latencies_bucket{subresource!="log",verb!~"^(?:CONNECT|WATCHLIST|WATCH|PROXY)$"} [10m])) WITHOUT (instance, resource)) / 1e+06 > 1
|
|
for: 2m
|
|
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 }}"
|