apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
creationTimestamp: null
labels:
app: kube-prometheus-stack
release: prometheus-operator
name: geosphere-prometheus-rules
spec:
groups:
# - name: ./example.rules
# rules:
# - alert: ExampleAlert
# expr: vector(1)
# labels:
# severity: warning
# annotations:
# summary: "Example Alert"
# description: "A test prometheus rule that always fires"
# Most of the below rules taken from
# https://awesome-prometheus-alerts.grep.to/rules.html
- name: geosphere-nginx-ingress.rules
rules:
- 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
ruleGroup: geosphere-nginx-ingress-controller
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
ruleGroup: geosphere-nginx-ingress-controller
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
ruleGroup: geosphere-nginx-ingress-controller
annotations:
summary: "Nginx latency high (instance {{ $labels.instance }})"
description: "Nginx p99 latency is higher than 10 seconds\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- name: geosphere-prometheus-checks.rules
rules:
- alert: PrometheusTooManyRestarts
expr: changes(process_start_time_seconds{job=~"prometheus|pushgateway|alertmanager"}[15m]) > 2
for: 5m
labels:
severity: warning
ruleGroup: geosphere-prometheus
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
ruleGroup: geosphere-prometheus
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
ruleGroup: geosphere-prometheus
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: PrometheusRuleEvaluationFailures
expr: increase(prometheus_rule_evaluation_failures_total[3m]) > 0
for: 5m
labels:
severity: critical
ruleGroup: geosphere-prometheus
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
ruleGroup: geosphere-prometheus
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
ruleGroup: geosphere-prometheus
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
ruleGroup: geosphere-prometheus
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
ruleGroup: geosphere-prometheus
annotations:
summary: "Prometheus AlertManager notification failing (instance {{ $labels.instance }})"
description: "Alertmanager is failing sending notifications\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusTargetEmpty
expr: prometheus_sd_discovered_targets == 0
for: 5m
labels:
severity: critical
ruleGroup: geosphere-prometheus
annotations:
summary: "Prometheus target empty (instance {{ $labels.instance }})"
description: "Prometheus has no target in service discovery\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: PrometheusTargetScrapingSlow
expr: prometheus_target_interval_length_seconds{quantile="0.9"} > 60
for: 5m
labels:
severity: warning
ruleGroup: geosphere-prometheus
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
ruleGroup: geosphere-prometheus
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
ruleGroup: geosphere-prometheus
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
ruleGroup: geosphere-prometheus
annotations:
summary: "Prometheus TSDB checkpoint creation failures (instance {{ $labels.instance }})"
description: "Prometheus encountered {{ $value }} checkpoint creation failures\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- name: geosphere-node.rules
rules:
- alert: HostOutOfMemory
expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
for: 5m
labels:
severity: warning
ruleGroup: geosphere-node
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[1m]) > 1000
for: 5m
labels:
severity: warning
ruleGroup: geosphere-node
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
ruleGroup: geosphere-node
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
ruleGroup: geosphere-node
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[5m])) / 1024 / 1024 > 150
for: 5m
labels:
severity: warning
ruleGroup: geosphere-node
annotations:
summary: "Host unusual disk read rate (instance {{ $labels.instance }})"
description: "Disk is probably reading too much data (> 150 MB/s)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostUnusualDiskWriteRate
expr: sum by (instance) (irate(node_disk_written_bytes_total[5m])) / 1024 / 1024 > 300
for: 5m
labels:
severity: warning
ruleGroup: geosphere-node
annotations:
summary: "Host unusual disk write rate (instance {{ $labels.instance }})"
description: "Disk is probably writing too much data (> 300 MB/s)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostOutOfDiskSpace
expr: (node_filesystem_avail_bytes{mountpoint="/"} * 100) / node_filesystem_size_bytes{mountpoint="/"} < 10
for: 5m
labels:
severity: warning
ruleGroup: geosphere-node
annotations:
summary: "Host out of disk space (instance {{ $labels.instance }})"
description: "Disk is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostDiskWillFillIn4Hours
expr: predict_linear(node_filesystem_free_bytes{fstype!~"tmpfs"}[1h], 4 * 3600) < 0
for: 5m
labels:
severity: warning
ruleGroup: geosphere-node
annotations:
summary: "Host disk will fill in 4 hours (instance {{ $labels.instance }})"
description: "Disk will fill in 4 hours at current write rate\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostOutOfInodes
expr: node_filesystem_files_free{mountpoint ="/"} / node_filesystem_files{mountpoint ="/"} * 100 < 10
for: 5m
labels:
severity: warning
ruleGroup: geosphere-node
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[1m]) / rate(node_disk_reads_completed_total[1m]) > 100
for: 5m
labels:
severity: warning
ruleGroup: geosphere-node
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[1m]) / rate(node_disk_writes_completed_total[1m]) > 100
for: 5m
labels:
severity: warning
ruleGroup: geosphere-node
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
for: 5m
labels:
severity: warning
ruleGroup: geosphere-node
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.
# Changed to 6000 as kubekorner was sitting at ~3500
# 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"})) > 6000
for: 5m
labels:
severity: warning
ruleGroup: geosphere-node
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
ruleGroup: geosphere-node
annotations:
summary: "Host swap is filling up (instance {{ $labels.instance }})"
description: "Swap is filling up (>80%)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostOomKillDetected
expr: increase(node_vmstat_oom_kill[5m]) > 0
for: 5m
labels:
severity: warning
ruleGroup: geosphere-node
annotations:
summary: "Host OOM kill detected (instance {{ $labels.instance }})"
description: "OOM kill detected\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostNetworkReceiveErrors
expr: increase(node_network_receive_errs_total[5m]) > 0
for: 5m
labels:
severity: warning
ruleGroup: geosphere-node
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
ruleGroup: geosphere-node
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 }}'
- name: geosphere-general-kubernetes.rules
rules:
- alert: KubernetesNodeReady
expr: kube_node_status_condition{condition="Ready",status="true"} == 0
for: 5m
labels:
severity: critical
ruleGroup: geosphere-kubernetes
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
ruleGroup: geosphere-kubernetes
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
ruleGroup: geosphere-kubernetes
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
ruleGroup: geosphere-kubernetes
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
ruleGroup: geosphere-kubernetes
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
ruleGroup: geosphere-kubernetes
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
ruleGroup: geosphere-kubernetes
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
ruleGroup: geosphere-kubernetes
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
ruleGroup: geosphere-kubernetes
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
ruleGroup: geosphere-kubernetes
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
ruleGroup: geosphere-kubernetes
annotations:
summary: "Kubernetes StatefulSet down (instance {{ $labels.instance }})"
description: "A StatefulSet went down\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:5m]) > 0
# for: 5m
# labels:
# severity: critical
# ruleGroup: geosphere-kubernetes
# 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
ruleGroup: geosphere-kubernetes
annotations:
summary: "Kubernetes pod crash looping (instance {{ $labels.instance }})"
description: "Pod {{ $labels.pod }} is crash looping\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesDeploymentGenerationMismatch
expr: kube_deployment_status_observed_generation != kube_deployment_metadata_generation
for: 5m
labels:
severity: critical
ruleGroup: geosphere-kubernetes
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: KubernetesCronjobTooLong
# expr: time() - kube_cronjob_next_schedule_time > 3600
# for: 5m
# labels:
# severity: warning
# ruleGroup: geosphere-kubernetes
# 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_status_failed > 0
# expr: kube_job_spec_completions - kube_job_status_succeeded > 0 or kube_job_status_failed > 0
for: 5m
labels:
severity: critical
ruleGroup: geosphere-kubernetes
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
ruleGroup: geosphere-kubernetes
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
ruleGroup: geosphere-kubernetes
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
ruleGroup: geosphere-kubernetes
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
ruleGroup: geosphere-kubernetes
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
ruleGroup: geosphere-kubernetes
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 }}"