Files
kube-prometheus/assets/prometheus/rules/kubernetes.rules.yaml

107 lines
4.4 KiB
YAML

groups:
- name: kubernetes.rules
rules:
- record: pod_name:container_memory_usage_bytes:sum
expr: sum(container_memory_usage_bytes{container_name!="POD",pod_name!=""}) BY
(pod_name)
- record: pod_name:container_spec_cpu_shares:sum
expr: sum(container_spec_cpu_shares{container_name!="POD",pod_name!=""}) BY (pod_name)
- record: pod_name:container_cpu_usage:sum
expr: sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name!=""}[5m]))
BY (pod_name)
- record: pod_name:container_fs_usage_bytes:sum
expr: sum(container_fs_usage_bytes{container_name!="POD",pod_name!=""}) BY (pod_name)
- record: namespace:container_memory_usage_bytes:sum
expr: sum(container_memory_usage_bytes{container_name!=""}) BY (namespace)
- record: namespace:container_spec_cpu_shares:sum
expr: sum(container_spec_cpu_shares{container_name!=""}) BY (namespace)
- record: namespace:container_cpu_usage:sum
expr: sum(rate(container_cpu_usage_seconds_total{container_name!="POD"}[5m]))
BY (namespace)
- record: cluster:memory_usage:ratio
expr: sum(container_memory_usage_bytes{container_name!="POD",pod_name!=""}) BY
(cluster) / sum(machine_memory_bytes) BY (cluster)
- record: cluster:container_spec_cpu_shares:ratio
expr: sum(container_spec_cpu_shares{container_name!="POD",pod_name!=""}) / 1000
/ sum(machine_cpu_cores)
- record: cluster:container_cpu_usage:ratio
expr: sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name!=""}[5m]))
/ sum(machine_cpu_cores)
- record: apiserver_latency_seconds:quantile
expr: histogram_quantile(0.99, rate(apiserver_request_latencies_bucket[5m])) /
1e+06
labels:
quantile: "0.99"
- record: apiserver_latency:quantile_seconds
expr: histogram_quantile(0.9, rate(apiserver_request_latencies_bucket[5m])) /
1e+06
labels:
quantile: "0.9"
- record: apiserver_latency_seconds:quantile
expr: histogram_quantile(0.5, rate(apiserver_request_latencies_bucket[5m])) /
1e+06
labels:
quantile: "0.5"
- alert: APIServerLatencyHigh
expr: apiserver_latency_seconds:quantile{quantile="0.99",subresource!="log",verb!~"^(?:WATCH|WATCHLIST|PROXY|CONNECT)$"}
> 1
for: 10m
labels:
severity: warning
annotations:
description: the API server has a 99th percentile latency of {{ $value }} seconds
for {{$labels.verb}} {{$labels.resource}}
summary: API server high latency
- alert: APIServerLatencyHigh
expr: apiserver_latency_seconds:quantile{quantile="0.99",subresource!="log",verb!~"^(?:WATCH|WATCHLIST|PROXY|CONNECT)$"}
> 4
for: 10m
labels:
severity: critical
annotations:
description: the API server has a 99th percentile latency of {{ $value }} seconds
for {{$labels.verb}} {{$labels.resource}}
summary: API server high latency
- alert: APIServerErrorsHigh
expr: rate(apiserver_request_count{code=~"^(?:5..)$"}[5m]) / rate(apiserver_request_count[5m])
* 100 > 2
for: 10m
labels:
severity: warning
annotations:
description: API server returns errors for {{ $value }}% of requests
summary: API server request errors
- alert: APIServerErrorsHigh
expr: rate(apiserver_request_count{code=~"^(?:5..)$"}[5m]) / rate(apiserver_request_count[5m])
* 100 > 5
for: 10m
labels:
severity: critical
annotations:
description: API server returns errors for {{ $value }}% of requests
- alert: K8SApiserverDown
expr: absent(up{job="apiserver"} == 1)
for: 20m
labels:
severity: critical
annotations:
description: No API servers are reachable or all have disappeared from service
discovery
summary: No API servers are reachable
- alert: K8sCertificateExpirationNotice
labels:
severity: warning
annotations:
description: Kubernetes API Certificate is expiring soon (less than 7 days)
summary: Kubernetes API Certificate is expiering soon
expr: sum(apiserver_client_certificate_expiration_seconds_bucket{le="604800"}) > 0
- alert: K8sCertificateExpirationNotice
labels:
severity: critical
annotations:
description: Kubernetes API Certificate is expiring in less than 1 day
summary: Kubernetes API Certificate is expiering
expr: sum(apiserver_client_certificate_expiration_seconds_bucket{le="86400"}) > 0