| Rule |
State |
Error |
Last Evaluation |
Evaluation Time |
| record: namespace:container_cpu_usage_seconds_total:sum_rate
expr: sum by(namespace) (rate(container_cpu_usage_seconds_total{container!="POD",image!="",job="kubelet",metrics_path="/metrics/cadvisor"}[5m]))
|
ok
|
|
6.138s ago
|
3.811ms |
| record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate
expr: sum by(cluster, namespace, pod, container) (rate(container_cpu_usage_seconds_total{container!="POD",image!="",job="kubelet",metrics_path="/metrics/cadvisor"}[5m])) * on(cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=""}))
|
ok
|
|
6.135s ago
|
6.337ms |
| record: node_namespace_pod_container:container_memory_working_set_bytes
expr: container_memory_working_set_bytes{image!="",job="kubelet",metrics_path="/metrics/cadvisor"} * on(namespace, pod) group_left(node) topk by(namespace, pod) (1, max by(namespace, pod, node) (kube_pod_info{node!=""}))
|
ok
|
|
6.128s ago
|
10.27ms |
| record: node_namespace_pod_container:container_memory_rss
expr: container_memory_rss{image!="",job="kubelet",metrics_path="/metrics/cadvisor"} * on(namespace, pod) group_left(node) topk by(namespace, pod) (1, max by(namespace, pod, node) (kube_pod_info{node!=""}))
|
ok
|
|
6.118s ago
|
10.75ms |
| record: node_namespace_pod_container:container_memory_cache
expr: container_memory_cache{image!="",job="kubelet",metrics_path="/metrics/cadvisor"} * on(namespace, pod) group_left(node) topk by(namespace, pod) (1, max by(namespace, pod, node) (kube_pod_info{node!=""}))
|
ok
|
|
6.107s ago
|
9.852ms |
| record: node_namespace_pod_container:container_memory_swap
expr: container_memory_swap{image!="",job="kubelet",metrics_path="/metrics/cadvisor"} * on(namespace, pod) group_left(node) topk by(namespace, pod) (1, max by(namespace, pod, node) (kube_pod_info{node!=""}))
|
ok
|
|
6.098s ago
|
10.15ms |
| record: namespace:container_memory_usage_bytes:sum
expr: sum by(namespace) (container_memory_usage_bytes{container!="POD",image!="",job="kubelet",metrics_path="/metrics/cadvisor"})
|
ok
|
|
6.087s ago
|
2.613ms |
| record: namespace:kube_pod_container_resource_requests_memory_bytes:sum
expr: sum by(namespace) (sum by(namespace, pod) (max by(namespace, pod, container) (kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"}) * on(namespace, pod) group_left() max by(namespace, pod) (kube_pod_status_phase{phase=~"Pending|Running"} == 1)))
|
ok
|
|
6.085s ago
|
4.364ms |
| record: namespace:kube_pod_container_resource_requests_cpu_cores:sum
expr: sum by(namespace) (sum by(namespace, pod) (max by(namespace, pod, container) (kube_pod_container_resource_requests_cpu_cores{job="kube-state-metrics"}) * on(namespace, pod) group_left() max by(namespace, pod) (kube_pod_status_phase{phase=~"Pending|Running"} == 1)))
|
ok
|
|
6.081s ago
|
3.508ms |
| record: namespace_workload_pod:kube_pod_owner:relabel
expr: max by(cluster, namespace, workload, pod) (label_replace(label_replace(kube_pod_owner{job="kube-state-metrics",owner_kind="ReplicaSet"}, "replicaset", "$1", "owner_name", "(.*)") * on(replicaset, namespace) group_left(owner_name) topk by(replicaset, namespace) (1, max by(replicaset, namespace, owner_name) (kube_replicaset_owner{job="kube-state-metrics"})), "workload", "$1", "owner_name", "(.*)"))
labels:
workload_type: deployment
|
ok
|
|
6.077s ago
|
5.527ms |
| record: namespace_workload_pod:kube_pod_owner:relabel
expr: max by(cluster, namespace, workload, pod) (label_replace(kube_pod_owner{job="kube-state-metrics",owner_kind="DaemonSet"}, "workload", "$1", "owner_name", "(.*)"))
labels:
workload_type: daemonset
|
ok
|
|
6.072s ago
|
791.2us |
| record: namespace_workload_pod:kube_pod_owner:relabel
expr: max by(cluster, namespace, workload, pod) (label_replace(kube_pod_owner{job="kube-state-metrics",owner_kind="StatefulSet"}, "workload", "$1", "owner_name", "(.*)"))
labels:
workload_type: statefulset
|
ok
|
|
6.071s ago
|
288.2us |
|
2m33.318s ago |
11.33s |
| Rule |
State |
Error |
Last Evaluation |
Evaluation Time |
| record: apiserver_request:availability30d
expr: 1 - ((sum(increase(apiserver_request_duration_seconds_count{verb=~"POST|PUT|PATCH|DELETE"}[30d])) - sum(increase(apiserver_request_duration_seconds_bucket{le="1",verb=~"POST|PUT|PATCH|DELETE"}[30d]))) + (sum(increase(apiserver_request_duration_seconds_count{verb=~"LIST|GET"}[30d])) - ((sum(increase(apiserver_request_duration_seconds_bucket{le="0.1",scope=~"resource|",verb=~"LIST|GET"}[30d])) or vector(0)) + sum(increase(apiserver_request_duration_seconds_bucket{le="0.5",scope="namespace",verb=~"LIST|GET"}[30d])) + sum(increase(apiserver_request_duration_seconds_bucket{le="5",scope="cluster",verb=~"LIST|GET"}[30d])))) + sum(code:apiserver_request_total:increase30d{code=~"5.."} or vector(0))) / sum(code:apiserver_request_total:increase30d)
labels:
verb: all
|
ok
|
|
2m33.318s ago
|
3.853s |
| record: apiserver_request:availability30d
expr: 1 - (sum(increase(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[30d])) - ((sum(increase(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.1",scope=~"resource|",verb=~"LIST|GET"}[30d])) or vector(0)) + sum(increase(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.5",scope="namespace",verb=~"LIST|GET"}[30d])) + sum(increase(apiserver_request_duration_seconds_bucket{job="apiserver",le="5",scope="cluster",verb=~"LIST|GET"}[30d]))) + sum(code:apiserver_request_total:increase30d{code=~"5..",verb="read"} or vector(0))) / sum(code:apiserver_request_total:increase30d{verb="read"})
labels:
verb: read
|
ok
|
|
2m29.466s ago
|
3.174s |
| record: apiserver_request:availability30d
expr: 1 - ((sum(increase(apiserver_request_duration_seconds_count{verb=~"POST|PUT|PATCH|DELETE"}[30d])) - sum(increase(apiserver_request_duration_seconds_bucket{le="1",verb=~"POST|PUT|PATCH|DELETE"}[30d]))) + sum(code:apiserver_request_total:increase30d{code=~"5..",verb="write"} or vector(0))) / sum(code:apiserver_request_total:increase30d{verb="write"})
labels:
verb: write
|
ok
|
|
2m26.291s ago
|
1.285s |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"2..",job="apiserver",verb="LIST"}[30d]))
|
ok
|
|
2m25.006s ago
|
1.285s |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"2..",job="apiserver",verb="GET"}[30d]))
|
ok
|
|
2m23.721s ago
|
535.3ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"2..",job="apiserver",verb="POST"}[30d]))
|
ok
|
|
2m23.186s ago
|
198.7ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"2..",job="apiserver",verb="PUT"}[30d]))
|
ok
|
|
2m22.987s ago
|
170.2ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"2..",job="apiserver",verb="PATCH"}[30d]))
|
ok
|
|
2m22.817s ago
|
185.2ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"2..",job="apiserver",verb="DELETE"}[30d]))
|
ok
|
|
2m22.631s ago
|
150.2ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"3..",job="apiserver",verb="LIST"}[30d]))
|
ok
|
|
2m22.481s ago
|
1.473ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"3..",job="apiserver",verb="GET"}[30d]))
|
ok
|
|
2m22.48s ago
|
892.6us |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"3..",job="apiserver",verb="POST"}[30d]))
|
ok
|
|
2m22.479s ago
|
656.4us |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"3..",job="apiserver",verb="PUT"}[30d]))
|
ok
|
|
2m22.478s ago
|
655.6us |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"3..",job="apiserver",verb="PATCH"}[30d]))
|
ok
|
|
2m22.478s ago
|
598.3us |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"3..",job="apiserver",verb="DELETE"}[30d]))
|
ok
|
|
2m22.477s ago
|
1.986ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"4..",job="apiserver",verb="LIST"}[30d]))
|
ok
|
|
2m22.475s ago
|
1.618ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"4..",job="apiserver",verb="GET"}[30d]))
|
ok
|
|
2m22.474s ago
|
158.7ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"4..",job="apiserver",verb="POST"}[30d]))
|
ok
|
|
2m22.315s ago
|
35.18ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"4..",job="apiserver",verb="PUT"}[30d]))
|
ok
|
|
2m22.28s ago
|
70.77ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"4..",job="apiserver",verb="PATCH"}[30d]))
|
ok
|
|
2m22.209s ago
|
46.69ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"4..",job="apiserver",verb="DELETE"}[30d]))
|
ok
|
|
2m22.163s ago
|
35.05ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"5..",job="apiserver",verb="LIST"}[30d]))
|
ok
|
|
2m22.128s ago
|
45.98ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"5..",job="apiserver",verb="GET"}[30d]))
|
ok
|
|
2m22.082s ago
|
40.87ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"5..",job="apiserver",verb="POST"}[30d]))
|
ok
|
|
2m22.041s ago
|
13.51ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"5..",job="apiserver",verb="PUT"}[30d]))
|
ok
|
|
2m22.027s ago
|
26.94ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"5..",job="apiserver",verb="PATCH"}[30d]))
|
ok
|
|
2m22.001s ago
|
5.042ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"5..",job="apiserver",verb="DELETE"}[30d]))
|
ok
|
|
2m21.996s ago
|
1.357ms |
| record: code:apiserver_request_total:increase30d
expr: sum by(code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"})
labels:
verb: read
|
ok
|
|
2m21.995s ago
|
337.5us |
| record: code:apiserver_request_total:increase30d
expr: sum by(code) (code_verb:apiserver_request_total:increase30d{verb=~"POST|PUT|PATCH|DELETE"})
labels:
verb: write
|
ok
|
|
2m21.994s ago
|
481.7us |
|
43.171s ago |
1.085ms |
| Rule |
State |
Error |
Last Evaluation |
Evaluation Time |
| record: apiserver_request:burnrate1d
expr: ((sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[1d])) - ((sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.1",scope=~"resource|",verb=~"LIST|GET"}[1d])) or vector(0)) + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.5",scope="namespace",verb=~"LIST|GET"}[1d])) + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="5",scope="cluster",verb=~"LIST|GET"}[1d])))) + sum(rate(apiserver_request_total{code=~"5..",job="apiserver",verb=~"LIST|GET"}[1d]))) / sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1d]))
labels:
verb: read
|
ok
|
|
43.371s ago
|
486.4ms |
| record: apiserver_request:burnrate1h
expr: ((sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[1h])) - ((sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.1",scope=~"resource|",verb=~"LIST|GET"}[1h])) or vector(0)) + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.5",scope="namespace",verb=~"LIST|GET"}[1h])) + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="5",scope="cluster",verb=~"LIST|GET"}[1h])))) + sum(rate(apiserver_request_total{code=~"5..",job="apiserver",verb=~"LIST|GET"}[1h]))) / sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1h]))
labels:
verb: read
|
ok
|
|
42.884s ago
|
33.26ms |
| record: apiserver_request:burnrate2h
expr: ((sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[2h])) - ((sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.1",scope=~"resource|",verb=~"LIST|GET"}[2h])) or vector(0)) + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.5",scope="namespace",verb=~"LIST|GET"}[2h])) + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="5",scope="cluster",verb=~"LIST|GET"}[2h])))) + sum(rate(apiserver_request_total{code=~"5..",job="apiserver",verb=~"LIST|GET"}[2h]))) / sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[2h]))
labels:
verb: read
|
ok
|
|
42.851s ago
|
45.16ms |
| record: apiserver_request:burnrate30m
expr: ((sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[30m])) - ((sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.1",scope=~"resource|",verb=~"LIST|GET"}[30m])) or vector(0)) + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.5",scope="namespace",verb=~"LIST|GET"}[30m])) + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="5",scope="cluster",verb=~"LIST|GET"}[30m])))) + sum(rate(apiserver_request_total{code=~"5..",job="apiserver",verb=~"LIST|GET"}[30m]))) / sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[30m]))
labels:
verb: read
|
ok
|
|
42.806s ago
|
25.75ms |
| record: apiserver_request:burnrate3d
expr: ((sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[3d])) - ((sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.1",scope=~"resource|",verb=~"LIST|GET"}[3d])) or vector(0)) + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.5",scope="namespace",verb=~"LIST|GET"}[3d])) + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="5",scope="cluster",verb=~"LIST|GET"}[3d])))) + sum(rate(apiserver_request_total{code=~"5..",job="apiserver",verb=~"LIST|GET"}[3d]))) / sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[3d]))
labels:
verb: read
|
ok
|
|
42.781s ago
|
1.353s |
| record: apiserver_request:burnrate5m
expr: ((sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[5m])) - ((sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.1",scope=~"resource|",verb=~"LIST|GET"}[5m])) or vector(0)) + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.5",scope="namespace",verb=~"LIST|GET"}[5m])) + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="5",scope="cluster",verb=~"LIST|GET"}[5m])))) + sum(rate(apiserver_request_total{code=~"5..",job="apiserver",verb=~"LIST|GET"}[5m]))) / sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m]))
labels:
verb: read
|
ok
|
|
41.428s ago
|
21.05ms |
| record: apiserver_request:burnrate6h
expr: ((sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[6h])) - ((sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.1",scope=~"resource|",verb=~"LIST|GET"}[6h])) or vector(0)) + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="0.5",scope="namespace",verb=~"LIST|GET"}[6h])) + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="5",scope="cluster",verb=~"LIST|GET"}[6h])))) + sum(rate(apiserver_request_total{code=~"5..",job="apiserver",verb=~"LIST|GET"}[6h]))) / sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[6h]))
labels:
verb: read
|
ok
|
|
41.407s ago
|
151.9ms |
| record: apiserver_request:burnrate1d
expr: ((sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d])) - sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="1",verb=~"POST|PUT|PATCH|DELETE"}[1d]))) + sum(rate(apiserver_request_total{code=~"5..",job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d]))) / sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d]))
labels:
verb: write
|
ok
|
|
41.255s ago
|
226.9ms |
| record: apiserver_request:burnrate1h
expr: ((sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h])) - sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="1",verb=~"POST|PUT|PATCH|DELETE"}[1h]))) + sum(rate(apiserver_request_total{code=~"5..",job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h]))) / sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h]))
labels:
verb: write
|
ok
|
|
41.029s ago
|
14.79ms |
| record: apiserver_request:burnrate2h
expr: ((sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h])) - sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="1",verb=~"POST|PUT|PATCH|DELETE"}[2h]))) + sum(rate(apiserver_request_total{code=~"5..",job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h]))) / sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h]))
labels:
verb: write
|
ok
|
|
41.014s ago
|
20.02ms |
| record: apiserver_request:burnrate30m
expr: ((sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m])) - sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="1",verb=~"POST|PUT|PATCH|DELETE"}[30m]))) + sum(rate(apiserver_request_total{code=~"5..",job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m]))) / sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m]))
labels:
verb: write
|
ok
|
|
40.994s ago
|
10.65ms |
| record: apiserver_request:burnrate3d
expr: ((sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d])) - sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="1",verb=~"POST|PUT|PATCH|DELETE"}[3d]))) + sum(rate(apiserver_request_total{code=~"5..",job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d]))) / sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d]))
labels:
verb: write
|
ok
|
|
40.984s ago
|
637.3ms |
| record: apiserver_request:burnrate5m
expr: ((sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m])) - sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="1",verb=~"POST|PUT|PATCH|DELETE"}[5m]))) + sum(rate(apiserver_request_total{code=~"5..",job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))) / sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
labels:
verb: write
|
ok
|
|
40.347s ago
|
10.38ms |
| record: apiserver_request:burnrate6h
expr: ((sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h])) - sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",le="1",verb=~"POST|PUT|PATCH|DELETE"}[6h]))) + sum(rate(apiserver_request_total{code=~"5..",job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h]))) / sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h]))
labels:
verb: write
|
ok
|
|
40.336s ago
|
73.15ms |
| record: code_resource:apiserver_request_total:rate5m
expr: sum by(code, resource) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m]))
labels:
verb: read
|
ok
|
|
40.263s ago
|
8.258ms |
| record: code_resource:apiserver_request_total:rate5m
expr: sum by(code, resource) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
labels:
verb: write
|
ok
|
|
40.255s ago
|
3.913ms |
| record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
expr: histogram_quantile(0.99, sum by(le, resource) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET"}[5m]))) > 0
labels:
quantile: "0.99"
verb: read
|
ok
|
|
40.251s ago
|
198.2ms |
| record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
expr: histogram_quantile(0.99, sum by(le, resource) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))) > 0
labels:
quantile: "0.99"
verb: write
|
ok
|
|
40.053s ago
|
104.4ms |
| record: cluster:apiserver_request_duration_seconds:mean5m
expr: sum without(instance, pod) (rate(apiserver_request_duration_seconds_sum{subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) / sum without(instance, pod) (rate(apiserver_request_duration_seconds_count{subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m]))
|
ok
|
|
39.949s ago
|
12.97ms |
| record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
expr: histogram_quantile(0.99, sum without(instance, pod) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])))
labels:
quantile: "0.99"
|
ok
|
|
39.936s ago
|
199.6ms |
| record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
expr: histogram_quantile(0.9, sum without(instance, pod) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])))
labels:
quantile: "0.9"
|
ok
|
|
39.737s ago
|
195.4ms |
| record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
expr: histogram_quantile(0.5, sum without(instance, pod) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])))
labels:
quantile: "0.5"
|
ok
|
|
39.542s ago
|
194.4ms |
|
1.051s ago |
2.692ms |
| Rule |
State |
Error |
Last Evaluation |
Evaluation Time |
| alert: KubePodCrashLooping
expr: rate(kube_pod_container_status_restarts_total{job="kube-state-metrics",namespace=~".*"}[5m]) * 60 * 5 > 0
for: 15m
labels:
severity: warning
annotations:
description: Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is restarting {{ printf "%.2f" $value }} times / 5 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodcrashlooping
summary: Pod is crash looping.
|
ok
|
|
2.197s ago
|
2.409ms |
| alert: KubePodNotReady
expr: sum by(namespace, pod) (max by(namespace, pod) (kube_pod_status_phase{job="kube-state-metrics",namespace=~".*",phase=~"Pending|Unknown"}) * on(namespace, pod) group_left(owner_kind) topk by(namespace, pod) (1, max by(namespace, pod, owner_kind) (kube_pod_owner{owner_kind!="Job"}))) > 0
for: 15m
labels:
severity: warning
annotations:
description: Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than 15 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready
summary: Pod has been in a non-ready state for more than 15 minutes.
|
ok
|
|
2.195s ago
|
4.987ms |
| alert: KubeDeploymentGenerationMismatch
expr: kube_deployment_status_observed_generation{job="kube-state-metrics",namespace=~".*"} != kube_deployment_metadata_generation{job="kube-state-metrics",namespace=~".*"}
for: 15m
labels:
severity: warning
annotations:
description: Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment }} does not match, this indicates that the Deployment has failed but has not been rolled back.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentgenerationmismatch
summary: Deployment generation mismatch due to possible roll-back
|
ok
|
|
2.19s ago
|
1.092ms |
| alert: KubeDeploymentReplicasMismatch
expr: (kube_deployment_spec_replicas{job="kube-state-metrics",namespace=~".*"} != kube_deployment_status_replicas_available{job="kube-state-metrics",namespace=~".*"}) and (changes(kube_deployment_status_replicas_updated{job="kube-state-metrics",namespace=~".*"}[5m]) == 0)
for: 15m
labels:
severity: warning
annotations:
description: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentreplicasmismatch
summary: Deployment has not matched the expected number of replicas.
|
ok
|
|
2.189s ago
|
1.641ms |
| alert: KubeStatefulSetReplicasMismatch
expr: (kube_statefulset_status_replicas_ready{job="kube-state-metrics",namespace=~".*"} != kube_statefulset_status_replicas{job="kube-state-metrics",namespace=~".*"}) and (changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics",namespace=~".*"}[5m]) == 0)
for: 15m
labels:
severity: warning
annotations:
description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetreplicasmismatch
summary: Deployment has not matched the expected number of replicas.
|
ok
|
|
2.188s ago
|
581.5us |
| alert: KubeStatefulSetGenerationMismatch
expr: kube_statefulset_status_observed_generation{job="kube-state-metrics",namespace=~".*"} != kube_statefulset_metadata_generation{job="kube-state-metrics",namespace=~".*"}
for: 15m
labels:
severity: warning
annotations:
description: StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset }} does not match, this indicates that the StatefulSet has failed but has not been rolled back.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetgenerationmismatch
summary: StatefulSet generation mismatch due to possible roll-back
|
ok
|
|
2.187s ago
|
1.58ms |
| alert: KubeStatefulSetUpdateNotRolledOut
expr: (max without(revision) (kube_statefulset_status_current_revision{job="kube-state-metrics",namespace=~".*"} unless kube_statefulset_status_update_revision{job="kube-state-metrics",namespace=~".*"}) * (kube_statefulset_replicas{job="kube-state-metrics",namespace=~".*"} != kube_statefulset_status_replicas_updated{job="kube-state-metrics",namespace=~".*"})) and (changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics",namespace=~".*"}[5m]) == 0)
for: 15m
labels:
severity: warning
annotations:
description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetupdatenotrolledout
summary: StatefulSet update has not been rolled out.
|
ok
|
|
2.186s ago
|
1.859ms |
| alert: KubeDaemonSetRolloutStuck
expr: ((kube_daemonset_status_current_number_scheduled{job="kube-state-metrics",namespace=~".*"} != kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics",namespace=~".*"}) or (kube_daemonset_status_number_misscheduled{job="kube-state-metrics",namespace=~".*"} != 0) or (kube_daemonset_updated_number_scheduled{job="kube-state-metrics",namespace=~".*"} != kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics",namespace=~".*"}) or (kube_daemonset_status_number_available{job="kube-state-metrics",namespace=~".*"} != kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics",namespace=~".*"})) and (changes(kube_daemonset_updated_number_scheduled{job="kube-state-metrics",namespace=~".*"}[5m]) == 0)
for: 15m
labels:
severity: warning
annotations:
description: DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} has not finished or progressed for at least 15 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetrolloutstuck
summary: DaemonSet rollout is stuck.
|
ok
|
|
2.184s ago
|
2.393ms |
| alert: KubeContainerWaiting
expr: sum by(namespace, pod, container) (kube_pod_container_status_waiting_reason{job="kube-state-metrics",namespace=~".*"}) > 0
for: 1h
labels:
severity: warning
annotations:
description: Pod {{ $labels.namespace }}/{{ $labels.pod }} container {{ $labels.container}} has been in waiting state for longer than 1 hour.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting
summary: Pod container waiting longer than 1 hour
|
ok
|
|
2.183s ago
|
16.23ms |
| alert: KubeDaemonSetNotScheduled
expr: kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics",namespace=~".*"} - kube_daemonset_status_current_number_scheduled{job="kube-state-metrics",namespace=~".*"} > 0
for: 10m
labels:
severity: warning
annotations:
description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetnotscheduled
summary: DaemonSet pods are not scheduled.
|
ok
|
|
2.167s ago
|
2.229ms |
| alert: KubeDaemonSetMisScheduled
expr: kube_daemonset_status_number_misscheduled{job="kube-state-metrics",namespace=~".*"} > 0
for: 15m
labels:
severity: warning
annotations:
description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetmisscheduled
summary: DaemonSet pods are misscheduled.
|
ok
|
|
2.164s ago
|
702.6us |
| alert: KubeJobCompletion
expr: kube_job_spec_completions{job="kube-state-metrics",namespace=~".*"} - kube_job_status_succeeded{job="kube-state-metrics",namespace=~".*"} > 0
for: 12h
labels:
severity: warning
annotations:
description: Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than 12 hours to complete.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobcompletion
summary: Job did not complete in time
|
ok
|
|
2.164s ago
|
5.069ms |
| alert: KubeJobFailed
expr: kube_job_failed{job="kube-state-metrics",namespace=~".*"} > 0
for: 15m
labels:
severity: warning
annotations:
description: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete. Removing failed job after investigation should clear this alert.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed
summary: Job failed to complete.
|
ok
|
|
2.159s ago
|
4.404ms |
| alert: KubeHpaReplicasMismatch
expr: (kube_hpa_status_desired_replicas{job="kube-state-metrics",namespace=~".*"} != kube_hpa_status_current_replicas{job="kube-state-metrics",namespace=~".*"}) and (kube_hpa_status_current_replicas{job="kube-state-metrics",namespace=~".*"} > kube_hpa_spec_min_replicas{job="kube-state-metrics",namespace=~".*"}) and (kube_hpa_status_current_replicas{job="kube-state-metrics",namespace=~".*"} < kube_hpa_spec_max_replicas{job="kube-state-metrics",namespace=~".*"}) and changes(kube_hpa_status_current_replicas[15m]) == 0
for: 15m
labels:
severity: warning
annotations:
description: HPA {{ $labels.namespace }}/{{ $labels.hpa }} has not matched the desired number of replicas for longer than 15 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpareplicasmismatch
summary: HPA has not matched descired number of replicas.
|
ok
|
|
2.155s ago
|
552.9us |
| alert: KubeHpaMaxedOut
expr: kube_hpa_status_current_replicas{job="kube-state-metrics",namespace=~".*"} == kube_hpa_spec_max_replicas{job="kube-state-metrics",namespace=~".*"}
for: 15m
labels:
severity: warning
annotations:
description: HPA {{ $labels.namespace }}/{{ $labels.hpa }} has been running at max replicas for longer than 15 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpamaxedout
summary: HPA is running at max replicas
|
ok
|
|
2.154s ago
|
163.8us |
|
50.932s ago |
4.978ms |
| Rule |
State |
Error |
Last Evaluation |
Evaluation Time |
| alert: KubeCPUOvercommit
expr: sum(namespace:kube_pod_container_resource_requests_cpu_cores:sum) / sum(kube_node_status_allocatable_cpu_cores) > (count(kube_node_status_allocatable_cpu_cores) - 1) / count(kube_node_status_allocatable_cpu_cores)
for: 5m
labels:
severity: info
annotations:
description: Cluster has overcommitted CPU resource requests for Pods and cannot tolerate node failure.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit
summary: Cluster has overcommitted CPU resource requests.
|
ok
|
|
50.932s ago
|
920us |
| alert: KubeMemoryOvercommit
expr: sum(namespace:kube_pod_container_resource_requests_memory_bytes:sum) / sum(kube_node_status_allocatable_memory_bytes) > (count(kube_node_status_allocatable_memory_bytes) - 1) / count(kube_node_status_allocatable_memory_bytes)
for: 5m
labels:
severity: warning
annotations:
description: Cluster has overcommitted memory resource requests for Pods and cannot tolerate node failure.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryovercommit
summary: Cluster has overcommitted memory resource requests.
|
ok
|
|
50.931s ago
|
575us |
| alert: KubeCPUQuotaOvercommit
expr: sum(kube_resourcequota{job="kube-state-metrics",resource="cpu",type="hard"}) / sum(kube_node_status_allocatable_cpu_cores) > 1.5
for: 5m
labels:
severity: warning
annotations:
description: Cluster has overcommitted CPU resource requests for Namespaces.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuquotaovercommit
summary: Cluster has overcommitted CPU resource requests.
|
ok
|
|
50.931s ago
|
284.3us |
| alert: KubeMemoryQuotaOvercommit
expr: sum(kube_resourcequota{job="kube-state-metrics",resource="memory",type="hard"}) / sum(kube_node_status_allocatable_memory_bytes{job="kube-state-metrics"}) > 1.5
for: 5m
labels:
severity: warning
annotations:
description: Cluster has overcommitted memory resource requests for Namespaces.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryquotaovercommit
summary: Cluster has overcommitted memory resource requests.
|
ok
|
|
50.93s ago
|
265.3us |
| alert: KubeQuotaAlmostFull
expr: kube_resourcequota{job="kube-state-metrics",type="used"} / ignoring(instance, job, type) (kube_resourcequota{job="kube-state-metrics",type="hard"} > 0) > 0.9 < 1
for: 15m
labels:
severity: info
annotations:
description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaalmostfull
summary: Namespace quota is going to be full.
|
ok
|
|
50.93s ago
|
202.6us |
| alert: KubeQuotaFullyUsed
expr: kube_resourcequota{job="kube-state-metrics",type="used"} / ignoring(instance, job, type) (kube_resourcequota{job="kube-state-metrics",type="hard"} > 0) == 1
for: 15m
labels:
severity: info
annotations:
description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotafullyused
summary: Namespace quota is fully used.
|
ok
|
|
50.93s ago
|
130.3us |
| alert: KubeQuotaExceeded
expr: kube_resourcequota{job="kube-state-metrics",type="used"} / ignoring(instance, job, type) (kube_resourcequota{job="kube-state-metrics",type="hard"} > 0) > 1
for: 15m
labels:
severity: warning
annotations:
description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaexceeded
summary: Namespace quota has exceeded the limits.
|
ok
|
|
50.93s ago
|
142.5us |
| alert: CPUThrottlingHigh
expr: sum by(container, pod, namespace) (increase(container_cpu_cfs_throttled_periods_total{container!=""}[5m])) / sum by(container, pod, namespace) (increase(container_cpu_cfs_periods_total[5m])) > (25 / 100)
for: 15m
labels:
severity: info
annotations:
description: '{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod }}.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh
summary: Processes experience elevated CPU throttling.
|
ok
|
|
50.93s ago
|
2.431ms |
|
55.373s ago |
2.448ms |
| Rule |
State |
Error |
Last Evaluation |
Evaluation Time |
| alert: KubeNodeNotReady
expr: kube_node_status_condition{condition="Ready",job="kube-state-metrics",status="true"} == 0
for: 15m
labels:
severity: warning
annotations:
description: '{{ $labels.node }} has been unready for more than 15 minutes.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodenotready
summary: Node is not ready.
|
ok
|
|
35.286s ago
|
2.953ms |
| alert: KubeNodeUnreachable
expr: (kube_node_spec_taint{effect="NoSchedule",job="kube-state-metrics",key="node.kubernetes.io/unreachable"} unless ignoring(key, value) kube_node_spec_taint{job="kube-state-metrics",key=~"ToBeDeletedByClusterAutoscaler|cloud.google.com/impending-node-termination|aws-node-termination-handler/spot-itn"}) == 1
for: 15m
labels:
severity: warning
annotations:
description: '{{ $labels.node }} is unreachable and some workloads may be rescheduled.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodeunreachable
summary: Node is unreachable.
|
ok
|
|
35.284s ago
|
411.9us |
| alert: KubeletTooManyPods
expr: count by(node) ((kube_pod_status_phase{job="kube-state-metrics",phase="Running"} == 1) * on(instance, pod, namespace, cluster) group_left(node) topk by(instance, pod, namespace, cluster) (1, kube_pod_info{job="kube-state-metrics"})) / max by(node) (kube_node_status_capacity_pods{job="kube-state-metrics"} != 1) > 0.95
for: 15m
labels:
severity: warning
annotations:
description: Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage }} of its Pod capacity.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubelettoomanypods
summary: Kubelet is running at capacity.
|
ok
|
|
35.283s ago
|
6.634ms |
| alert: KubeNodeReadinessFlapping
expr: sum by(node) (changes(kube_node_status_condition{condition="Ready",status="true"}[15m])) > 2
for: 15m
labels:
severity: warning
annotations:
description: The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodereadinessflapping
summary: Node readiness status is flapping.
|
ok
|
|
35.277s ago
|
396.4us |
| alert: KubeletPlegDurationHigh
expr: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile="0.99"} >= 10
for: 5m
labels:
severity: warning
annotations:
description: The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletplegdurationhigh
summary: Kubelet Pod Lifecycle Event Generator is taking too long to relist.
|
ok
|
|
35.277s ago
|
272.8us |
| alert: KubeletPodStartUpLatencyHigh
expr: histogram_quantile(0.99, sum by(instance, le) (rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet",metrics_path="/metrics"}[5m]))) * on(instance) group_left(node) kubelet_node_name{job="kubelet",metrics_path="/metrics"} > 60
for: 15m
labels:
severity: warning
annotations:
description: Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletpodstartuplatencyhigh
summary: Kubelet Pod startup latency is too high.
|
ok
|
|
35.277s ago
|
3.134ms |
| alert: KubeletClientCertificateExpiration
expr: kubelet_certificate_manager_client_ttl_seconds < 604800
labels:
severity: warning
annotations:
description: Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificateexpiration
summary: Kubelet client certificate is about to expire.
|
ok
|
|
35.273s ago
|
78.77us |
| alert: KubeletClientCertificateExpiration
expr: kubelet_certificate_manager_client_ttl_seconds < 86400
labels:
severity: critical
annotations:
description: Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificateexpiration
summary: Kubelet client certificate is about to expire.
|
ok
|
|
35.273s ago
|
135.2us |
| alert: KubeletServerCertificateExpiration
expr: kubelet_certificate_manager_server_ttl_seconds < 604800
labels:
severity: warning
annotations:
description: Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificateexpiration
summary: Kubelet server certificate is about to expire.
|
ok
|
|
35.273s ago
|
155.9us |
| alert: KubeletServerCertificateExpiration
expr: kubelet_certificate_manager_server_ttl_seconds < 86400
labels:
severity: critical
annotations:
description: Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificateexpiration
summary: Kubelet server certificate is about to expire.
|
ok
|
|
35.273s ago
|
191.3us |
| alert: KubeletClientCertificateRenewalErrors
expr: increase(kubelet_certificate_manager_client_expiration_renew_errors[5m]) > 0
for: 15m
labels:
severity: warning
annotations:
description: Kubelet on node {{ $labels.node }} has failed to renew its client certificate ({{ $value | humanize }} errors in the last 5 minutes).
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificaterenewalerrors
summary: Kubelet has failed to renew its client certificate.
|
ok
|
|
35.273s ago
|
227.2us |
| alert: KubeletServerCertificateRenewalErrors
expr: increase(kubelet_server_expiration_renew_errors[5m]) > 0
for: 15m
labels:
severity: warning
annotations:
description: Kubelet on node {{ $labels.node }} has failed to renew its server certificate ({{ $value | humanize }} errors in the last 5 minutes).
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificaterenewalerrors
summary: Kubelet has failed to renew its server certificate.
|
ok
|
|
35.273s ago
|
99.33us |
| alert: KubeletDown
expr: absent(up{job="kubelet",metrics_path="/metrics"} == 1)
for: 15m
labels:
severity: critical
annotations:
description: Kubelet has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletdown
summary: Target disappeared from Prometheus target discovery.
|
ok
|
|
35.273s ago
|
314.9us |
|
21.846s ago |
2.422ms |
| Rule |
State |
Error |
Last Evaluation |
Evaluation Time |
| alert: NodeFilesystemSpaceFillingUp
expr: (node_filesystem_avail_bytes{fstype!="",job="node-exporter"} / node_filesystem_size_bytes{fstype!="",job="node-exporter"} * 100 < 40 and predict_linear(node_filesystem_avail_bytes{fstype!="",job="node-exporter"}[6h], 24 * 60 * 60) < 0 and node_filesystem_readonly{fstype!="",job="node-exporter"} == 0)
for: 1h
labels:
severity: warning
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemspacefillingup
summary: Filesystem is predicted to run out of space within the next 24 hours.
|
ok
|
|
20.34s ago
|
7.746ms |
| alert: NodeFilesystemSpaceFillingUp
expr: (node_filesystem_avail_bytes{fstype!="",job="node-exporter"} / node_filesystem_size_bytes{fstype!="",job="node-exporter"} * 100 < 15 and predict_linear(node_filesystem_avail_bytes{fstype!="",job="node-exporter"}[6h], 4 * 60 * 60) < 0 and node_filesystem_readonly{fstype!="",job="node-exporter"} == 0)
for: 1h
labels:
severity: critical
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up fast.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemspacefillingup
summary: Filesystem is predicted to run out of space within the next 4 hours.
|
ok
|
|
20.332s ago
|
7.724ms |
| alert: NodeFilesystemAlmostOutOfSpace
expr: (node_filesystem_avail_bytes{fstype!="",job="node-exporter"} / node_filesystem_size_bytes{fstype!="",job="node-exporter"} * 100 < 5 and node_filesystem_readonly{fstype!="",job="node-exporter"} == 0)
for: 1h
labels:
severity: warning
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutofspace
summary: Filesystem has less than 5% space left.
|
ok
|
|
20.325s ago
|
1.73ms |
| alert: NodeFilesystemAlmostOutOfSpace
expr: (node_filesystem_avail_bytes{fstype!="",job="node-exporter"} / node_filesystem_size_bytes{fstype!="",job="node-exporter"} * 100 < 3 and node_filesystem_readonly{fstype!="",job="node-exporter"} == 0)
for: 1h
labels:
severity: critical
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutofspace
summary: Filesystem has less than 3% space left.
|
ok
|
|
20.323s ago
|
1.731ms |
| alert: NodeFilesystemFilesFillingUp
expr: (node_filesystem_files_free{fstype!="",job="node-exporter"} / node_filesystem_files{fstype!="",job="node-exporter"} * 100 < 40 and predict_linear(node_filesystem_files_free{fstype!="",job="node-exporter"}[6h], 24 * 60 * 60) < 0 and node_filesystem_readonly{fstype!="",job="node-exporter"} == 0)
for: 1h
labels:
severity: warning
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemfilesfillingup
summary: Filesystem is predicted to run out of inodes within the next 24 hours.
|
ok
|
|
20.322s ago
|
7.084ms |
| alert: NodeFilesystemFilesFillingUp
expr: (node_filesystem_files_free{fstype!="",job="node-exporter"} / node_filesystem_files{fstype!="",job="node-exporter"} * 100 < 20 and predict_linear(node_filesystem_files_free{fstype!="",job="node-exporter"}[6h], 4 * 60 * 60) < 0 and node_filesystem_readonly{fstype!="",job="node-exporter"} == 0)
for: 1h
labels:
severity: critical
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up fast.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemfilesfillingup
summary: Filesystem is predicted to run out of inodes within the next 4 hours.
|
ok
|
|
20.315s ago
|
6.862ms |
| alert: NodeFilesystemAlmostOutOfFiles
expr: (node_filesystem_files_free{fstype!="",job="node-exporter"} / node_filesystem_files{fstype!="",job="node-exporter"} * 100 < 5 and node_filesystem_readonly{fstype!="",job="node-exporter"} == 0)
for: 1h
labels:
severity: warning
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutoffiles
summary: Filesystem has less than 5% inodes left.
|
ok
|
|
20.308s ago
|
1.613ms |
| alert: NodeFilesystemAlmostOutOfFiles
expr: (node_filesystem_files_free{fstype!="",job="node-exporter"} / node_filesystem_files{fstype!="",job="node-exporter"} * 100 < 3 and node_filesystem_readonly{fstype!="",job="node-exporter"} == 0)
for: 1h
labels:
severity: critical
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutoffiles
summary: Filesystem has less than 3% inodes left.
|
ok
|
|
20.307s ago
|
1.67ms |
| alert: NodeNetworkReceiveErrs
expr: rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01
for: 1h
labels:
severity: warning
annotations:
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive errors in the last two minutes.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodenetworkreceiveerrs
summary: Network interface is reporting many receive errors.
|
ok
|
|
20.305s ago
|
2.134ms |
| alert: NodeNetworkTransmitErrs
expr: rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01
for: 1h
labels:
severity: warning
annotations:
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit errors in the last two minutes.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodenetworktransmiterrs
summary: Network interface is reporting many transmit errors.
|
ok
|
|
20.303s ago
|
2.092ms |
| alert: NodeHighNumberConntrackEntriesUsed
expr: (node_nf_conntrack_entries / node_nf_conntrack_entries_limit) > 0.75
labels:
severity: warning
annotations:
description: '{{ $value | humanizePercentage }} of conntrack entries are used.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodehighnumberconntrackentriesused
summary: Number of conntrack are getting close to the limit.
|
ok
|
|
20.301s ago
|
482.8us |
| alert: NodeTextFileCollectorScrapeError
expr: node_textfile_scrape_error{job="node-exporter"} == 1
labels:
severity: warning
annotations:
description: Node Exporter text file collector failed to scrape.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodetextfilecollectorscrapeerror
summary: Node Exporter text file collector failed to scrape.
|
ok
|
|
20.301s ago
|
219.7us |
| alert: NodeClockSkewDetected
expr: (node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0)
for: 10m
labels:
severity: warning
annotations:
message: Clock on {{ $labels.instance }} is out of sync by more than 300s. Ensure NTP is configured correctly on this host.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodeclockskewdetected
summary: Clock skew detected.
|
ok
|
|
20.301s ago
|
711us |
| alert: NodeClockNotSynchronising
expr: min_over_time(node_timex_sync_status[5m]) == 0 and node_timex_maxerror_seconds >= 16
for: 10m
labels:
severity: warning
annotations:
message: Clock on {{ $labels.instance }} is not synchronising. Ensure NTP is configured on this host.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodeclocknotsynchronising
summary: Clock not synchronising.
|
ok
|
|
20.3s ago
|
361.8us |
| alert: NodeRAIDDegraded
expr: node_md_disks_required - ignoring(state) (node_md_disks{state="active"}) > 0
for: 15m
labels:
severity: critical
annotations:
description: RAID array '{{ $labels.device }}' on {{ $labels.instance }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-noderaiddegraded
summary: RAID Array is degraded
|
ok
|
|
20.3s ago
|
144us |
| alert: NodeRAIDDiskFailure
expr: node_md_disks{state="fail"} > 0
labels:
severity: warning
annotations:
description: At least one device in RAID array on {{ $labels.instance }} failed. Array '{{ $labels.device }}' needs attention and possibly a disk swap.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-noderaiddiskfailure
summary: Failed device in RAID array
|
ok
|
|
20.3s ago
|
90.66us |
|
25.362s ago |
1.19ms |
| Rule |
State |
Error |
Last Evaluation |
Evaluation Time |
| alert: PrometheusOperatorListErrors
expr: (sum by(controller, namespace) (rate(prometheus_operator_list_operations_failed_total{job="prometheus-operator-kube-p-operator",namespace="default"}[10m])) / sum by(controller, namespace) (rate(prometheus_operator_list_operations_total{job="prometheus-operator-kube-p-operator",namespace="default"}[10m]))) > 0.4
for: 15m
labels:
severity: warning
annotations:
description: Errors while performing List operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatorlisterrors
summary: Errors while performing list operations in controller.
|
ok
|
|
41.161s ago
|
589.6us |
| alert: PrometheusOperatorWatchErrors
expr: (sum by(controller, namespace) (rate(prometheus_operator_watch_operations_failed_total{job="prometheus-operator-kube-p-operator",namespace="default"}[10m])) / sum by(controller, namespace) (rate(prometheus_operator_watch_operations_total{job="prometheus-operator-kube-p-operator",namespace="default"}[10m]))) > 0.4
for: 15m
labels:
severity: warning
annotations:
description: Errors while performing watch operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatorwatcherrors
summary: Errors while performing watch operations in controller.
|
ok
|
|
41.161s ago
|
236.2us |
| alert: PrometheusOperatorSyncFailed
expr: min_over_time(prometheus_operator_syncs{job="prometheus-operator-kube-p-operator",namespace="default",status="failed"}[5m]) > 0
for: 10m
labels:
severity: warning
annotations:
description: Controller {{ $labels.controller }} in {{ $labels.namespace }} namespace fails to reconcile {{ $value }} objects.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatorsyncfailed
summary: Last controller reconciliation failed
|
ok
|
|
41.161s ago
|
121.3us |
| alert: PrometheusOperatorReconcileErrors
expr: (sum by(controller, namespace) (rate(prometheus_operator_reconcile_errors_total{job="prometheus-operator-kube-p-operator",namespace="default"}[5m]))) / (sum by(controller, namespace) (rate(prometheus_operator_reconcile_operations_total{job="prometheus-operator-kube-p-operator",namespace="default"}[5m]))) > 0.1
for: 10m
labels:
severity: warning
annotations:
description: '{{ $value | humanizePercentage }} of reconciling operations failed for {{ $labels.controller }} controller in {{ $labels.namespace }} namespace.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatorreconcileerrors
summary: Errors while reconciling controller.
|
ok
|
|
41.161s ago
|
249.6us |
| alert: PrometheusOperatorNodeLookupErrors
expr: rate(prometheus_operator_node_address_lookup_errors_total{job="prometheus-operator-kube-p-operator",namespace="default"}[5m]) > 0.1
for: 10m
labels:
severity: warning
annotations:
description: Errors while reconciling Prometheus in {{ $labels.namespace }} Namespace.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatornodelookuperrors
summary: Errors while reconciling Prometheus.
|
ok
|
|
41.161s ago
|
88.15us |
| alert: PrometheusOperatorNotReady
expr: min by(namespace, controller) (max_over_time(prometheus_operator_ready{job="prometheus-operator-kube-p-operator",namespace="default"}[5m]) == 0)
for: 5m
labels:
severity: warning
annotations:
description: Prometheus operator in {{ $labels.namespace }} namespace isn't ready to reconcile {{ $labels.controller }} resources.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatornotready
summary: Prometheus operator not ready
|
ok
|
|
41.161s ago
|
181.3us |
| alert: PrometheusOperatorRejectedResources
expr: min_over_time(prometheus_operator_managed_resources{job="prometheus-operator-kube-p-operator",namespace="default",state="rejected"}[5m]) > 0
for: 5m
labels:
severity: warning
annotations:
description: Prometheus operator in {{ $labels.namespace }} namespace rejected {{ printf "%0.0f" $value }} {{ $labels.controller }}/{{ $labels.resource }} resources.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatorrejectedresources
summary: Resources rejected by Prometheus operator
|
ok
|
|
41.16s ago
|
375.2us |
|
19.995s ago |
3.378ms |
| Rule |
State |
Error |
Last Evaluation |
Evaluation Time |
| alert: PrometheusBadConfig
expr: max_over_time(prometheus_config_last_reload_successful{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]) == 0
for: 10m
labels:
severity: critical
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to reload its configuration.
summary: Failed Prometheus configuration reload.
|
ok
|
|
19.995s ago
|
280.9us |
| alert: PrometheusNotificationQueueRunningFull
expr: (predict_linear(prometheus_notifications_queue_length{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m], 60 * 30) > min_over_time(prometheus_notifications_queue_capacity{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]))
for: 15m
labels:
severity: warning
annotations:
description: Alert notification queue of Prometheus {{$labels.namespace}}/{{$labels.pod}} is running full.
summary: Prometheus alert notification queue predicted to run full in less than 30m.
|
ok
|
|
19.995s ago
|
253.9us |
| alert: PrometheusErrorSendingAlertsToSomeAlertmanagers
expr: (rate(prometheus_notifications_errors_total{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]) / rate(prometheus_notifications_sent_total{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m])) * 100 > 1
for: 15m
labels:
severity: warning
annotations:
description: '{{ printf "%.1f" $value }}% errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to Alertmanager {{$labels.alertmanager}}.'
summary: Prometheus has encountered more than 1% errors sending alerts to a specific Alertmanager.
|
ok
|
|
19.995s ago
|
287.7us |
| alert: PrometheusErrorSendingAlertsToAnyAlertmanager
expr: min without(alertmanager) (rate(prometheus_notifications_errors_total{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]) / rate(prometheus_notifications_sent_total{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m])) * 100 > 3
for: 15m
labels:
severity: critical
annotations:
description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.'
summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager.
|
ok
|
|
19.995s ago
|
265.4us |
| alert: PrometheusNotConnectedToAlertmanagers
expr: max_over_time(prometheus_notifications_alertmanagers_discovered{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]) < 1
for: 10m
labels:
severity: warning
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not connected to any Alertmanagers.
summary: Prometheus is not connected to any Alertmanagers.
|
ok
|
|
19.995s ago
|
133.6us |
| alert: PrometheusTSDBReloadsFailing
expr: increase(prometheus_tsdb_reloads_failures_total{job="prometheus-operator-kube-p-prometheus",namespace="default"}[3h]) > 0
for: 4h
labels:
severity: warning
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} reload failures over the last 3h.
summary: Prometheus has issues reloading blocks from disk.
|
ok
|
|
19.995s ago
|
281.7us |
| alert: PrometheusTSDBCompactionsFailing
expr: increase(prometheus_tsdb_compactions_failed_total{job="prometheus-operator-kube-p-prometheus",namespace="default"}[3h]) > 0
for: 4h
labels:
severity: warning
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} compaction failures over the last 3h.
summary: Prometheus has issues compacting blocks.
|
ok
|
|
19.995s ago
|
190.8us |
| alert: PrometheusNotIngestingSamples
expr: rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]) <= 0
for: 10m
labels:
severity: warning
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not ingesting samples.
summary: Prometheus is not ingesting samples.
|
ok
|
|
19.994s ago
|
100.1us |
| alert: PrometheusDuplicateTimestamps
expr: rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]) > 0
for: 10m
labels:
severity: warning
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with different values but duplicated timestamp.
summary: Prometheus is dropping samples with duplicate timestamps.
|
ok
|
|
19.994s ago
|
112.1us |
| alert: PrometheusOutOfOrderTimestamps
expr: rate(prometheus_target_scrapes_sample_out_of_order_total{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]) > 0
for: 10m
labels:
severity: warning
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with timestamps arriving out of order.
summary: Prometheus drops samples with out-of-order timestamps.
|
ok
|
|
19.994s ago
|
91.67us |
| alert: PrometheusRemoteStorageFailures
expr: (rate(prometheus_remote_storage_failed_samples_total{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]) / (rate(prometheus_remote_storage_failed_samples_total{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]) + rate(prometheus_remote_storage_succeeded_samples_total{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]))) * 100 > 1
for: 15m
labels:
severity: critical
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send {{ printf "%.1f" $value }}% of the samples to {{ $labels.remote_name}}:{{ $labels.url }}
summary: Prometheus fails to send samples to remote storage.
|
ok
|
|
19.994s ago
|
191.9us |
| alert: PrometheusRemoteWriteBehind
expr: (max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]) - on(job, instance) group_right() max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m])) > 120
for: 15m
labels:
severity: critical
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url }}.
summary: Prometheus remote write is behind.
|
ok
|
|
19.994s ago
|
175.5us |
| alert: PrometheusRemoteWriteDesiredShards
expr: (max_over_time(prometheus_remote_storage_shards_desired{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]) > max_over_time(prometheus_remote_storage_shards_max{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]))
for: 15m
labels:
severity: warning
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write desired shards calculation wants to run {{ $value }} shards for queue {{ $labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-operator-kube-p-prometheus",namespace="default"}` $labels.instance | query | first | value }}.
summary: Prometheus remote write desired shards calculation wants to run more than configured max shards.
|
ok
|
|
19.994s ago
|
137.2us |
| alert: PrometheusRuleFailures
expr: increase(prometheus_rule_evaluation_failures_total{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]) > 0
for: 15m
labels:
severity: critical
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to evaluate {{ printf "%.0f" $value }} rules in the last 5m.
summary: Prometheus is failing rule evaluations.
|
ok
|
|
19.994s ago
|
385.1us |
| alert: PrometheusMissingRuleEvaluations
expr: increase(prometheus_rule_group_iterations_missed_total{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]) > 0
for: 15m
labels:
severity: warning
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has missed {{ printf "%.0f" $value }} rule group evaluations in the last 5m.
summary: Prometheus is missing rule evaluations due to slow rule group evaluation.
|
ok
|
|
19.994s ago
|
333us |
| alert: PrometheusTargetLimitHit
expr: increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job="prometheus-operator-kube-p-prometheus",namespace="default"}[5m]) > 0
for: 15m
labels:
severity: warning
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped {{ printf "%.0f" $value }} targets because the number of targets exceeded the configured target_limit.
summary: Prometheus has dropped targets because some scrape configs have exceeded the targets limit.
|
ok
|
|
19.994s ago
|
134.1us |
|
51.998s ago |
623.7us |