| 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
|
|
29.329s ago
|
4.924ms |
| 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
|
|
29.324s ago
|
9.037ms |
| 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
|
|
29.315s ago
|
10.84ms |
| 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
|
|
29.305s ago
|
10.64ms |
| 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
|
|
29.294s ago
|
10.49ms |
| 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
|
|
29.284s ago
|
10.42ms |
| 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
|
|
29.273s ago
|
3.666ms |
| 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
|
|
29.27s ago
|
2.87ms |
| 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
|
|
29.267s ago
|
2.816ms |
| record: mixin_pod_workload
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
|
|
29.264s ago
|
3.797ms |
| record: mixin_pod_workload
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
|
|
29.261s ago
|
700us |
| record: mixin_pod_workload
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
|
|
29.26s ago
|
291.8us |
|
2m5.513s ago |
12.3s |
| 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])) + 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
|
|
2m5.513s ago
|
6.102s |
| 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])) + 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
|
|
1m59.411s ago
|
2.018s |
| 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
|
|
1m57.394s ago
|
2.222s |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"2..",job="apiserver",verb="LIST"}[30d]))
|
ok
|
|
1m55.171s ago
|
844ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"2..",job="apiserver",verb="GET"}[30d]))
|
ok
|
|
1m54.327s ago
|
231.8ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"2..",job="apiserver",verb="POST"}[30d]))
|
ok
|
|
1m54.096s ago
|
145.1ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"2..",job="apiserver",verb="PUT"}[30d]))
|
ok
|
|
1m53.951s ago
|
191ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"2..",job="apiserver",verb="PATCH"}[30d]))
|
ok
|
|
1m53.76s ago
|
123.5ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"2..",job="apiserver",verb="DELETE"}[30d]))
|
ok
|
|
1m53.636s ago
|
58.36ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"3..",job="apiserver",verb="LIST"}[30d]))
|
ok
|
|
1m53.578s ago
|
1.59ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"3..",job="apiserver",verb="GET"}[30d]))
|
ok
|
|
1m53.576s ago
|
15.65ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"3..",job="apiserver",verb="POST"}[30d]))
|
ok
|
|
1m53.561s ago
|
1.413ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"3..",job="apiserver",verb="PUT"}[30d]))
|
ok
|
|
1m53.56s ago
|
1.193ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"3..",job="apiserver",verb="PATCH"}[30d]))
|
ok
|
|
1m53.558s ago
|
1.118ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"3..",job="apiserver",verb="DELETE"}[30d]))
|
ok
|
|
1m53.557s ago
|
1.07ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"4..",job="apiserver",verb="LIST"}[30d]))
|
ok
|
|
1m53.556s ago
|
81.8ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"4..",job="apiserver",verb="GET"}[30d]))
|
ok
|
|
1m53.475s ago
|
64.48ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"4..",job="apiserver",verb="POST"}[30d]))
|
ok
|
|
1m53.41s ago
|
17.47ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"4..",job="apiserver",verb="PUT"}[30d]))
|
ok
|
|
1m53.393s ago
|
63.28ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"4..",job="apiserver",verb="PATCH"}[30d]))
|
ok
|
|
1m53.33s ago
|
16.99ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"4..",job="apiserver",verb="DELETE"}[30d]))
|
ok
|
|
1m53.313s ago
|
25.83ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"5..",job="apiserver",verb="LIST"}[30d]))
|
ok
|
|
1m53.287s ago
|
21.1ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"5..",job="apiserver",verb="GET"}[30d]))
|
ok
|
|
1m53.266s ago
|
22.08ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"5..",job="apiserver",verb="POST"}[30d]))
|
ok
|
|
1m53.244s ago
|
8.176ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"5..",job="apiserver",verb="PUT"}[30d]))
|
ok
|
|
1m53.236s ago
|
12.24ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"5..",job="apiserver",verb="PATCH"}[30d]))
|
ok
|
|
1m53.224s ago
|
4.921ms |
| record: code_verb:apiserver_request_total:increase30d
expr: sum by(code, verb) (increase(apiserver_request_total{code=~"5..",job="apiserver",verb="DELETE"}[30d]))
|
ok
|
|
1m53.219s ago
|
1.433ms |
| record: code:apiserver_request_total:increase30d
expr: sum by(code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"})
labels:
verb: read
|
ok
|
|
1m53.217s ago
|
247.8us |
| 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
|
|
1m53.217s ago
|
252.6us |
|
16.658s ago |
684.8us |
| 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])) + 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
|
|
23.545s ago
|
295.7ms |
| 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])) + 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
|
|
23.249s ago
|
18.19ms |
| 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])) + 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
|
|
23.231s ago
|
34.89ms |
| 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])) + 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
|
|
23.196s ago
|
16.47ms |
| 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])) + 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
|
|
23.18s ago
|
673.7ms |
| 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])) + 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
|
|
22.507s ago
|
9.312ms |
| 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])) + 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
|
|
22.497s ago
|
85.23ms |
| 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
|
|
22.412s ago
|
147.4ms |
| 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
|
|
22.265s ago
|
11.87ms |
| 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
|
|
22.253s ago
|
22.08ms |
| 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
|
|
22.231s ago
|
10.4ms |
| 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
|
|
22.222s ago
|
351.2ms |
| 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
|
|
21.871s ago
|
5.282ms |
| 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
|
|
21.866s ago
|
43.85ms |
| 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
|
|
21.822s ago
|
4.143ms |
| 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
|
|
21.818s ago
|
2.445ms |
| 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
|
|
21.816s ago
|
34.99ms |
| 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
|
|
21.781s ago
|
17.36ms |
| 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
|
|
21.764s ago
|
16.23ms |
| 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
|
|
21.747s ago
|
36.45ms |
| 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
|
|
21.711s ago
|
36.28ms |
| 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
|
|
21.675s ago
|
36.47ms |
|
28.549s ago |
1.164ms |
| Rule |
State |
Error |
Last Evaluation |
Evaluation Time |
| alert: KubePodCrashLooping
expr: rate(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[5m]) * 60 * 5 > 0
for: 15m
labels:
severity: warning
annotations:
message: 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
|
ok
|
|
14.458s ago
|
1.949ms |
| alert: KubePodNotReady
expr: sum by(namespace, pod) (max by(namespace, pod) (kube_pod_status_phase{job="kube-state-metrics",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:
message: 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
|
ok
|
|
14.456s ago
|
3.878ms |
| alert: KubeDeploymentGenerationMismatch
expr: kube_deployment_status_observed_generation{job="kube-state-metrics"} != kube_deployment_metadata_generation{job="kube-state-metrics"}
for: 15m
labels:
severity: warning
annotations:
message: 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
|
ok
|
|
14.452s ago
|
977.5us |
| alert: KubeDeploymentReplicasMismatch
expr: (kube_deployment_spec_replicas{job="kube-state-metrics"} != kube_deployment_status_replicas_available{job="kube-state-metrics"}) and (changes(kube_deployment_status_replicas_updated{job="kube-state-metrics"}[5m]) == 0)
for: 15m
labels:
severity: warning
annotations:
message: 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
|
ok
|
|
14.452s ago
|
1.496ms |
| alert: KubeStatefulSetReplicasMismatch
expr: (kube_statefulset_status_replicas_ready{job="kube-state-metrics"} != kube_statefulset_status_replicas{job="kube-state-metrics"}) and (changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics"}[5m]) == 0)
for: 15m
labels:
severity: warning
annotations:
message: 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
|
ok
|
|
14.45s ago
|
414.1us |
| alert: KubeStatefulSetGenerationMismatch
expr: kube_statefulset_status_observed_generation{job="kube-state-metrics"} != kube_statefulset_metadata_generation{job="kube-state-metrics"}
for: 15m
labels:
severity: warning
annotations:
message: 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
|
ok
|
|
14.45s ago
|
220.2us |
| alert: KubeStatefulSetUpdateNotRolledOut
expr: (max without(revision) (kube_statefulset_status_current_revision{job="kube-state-metrics"} unless kube_statefulset_status_update_revision{job="kube-state-metrics"}) * (kube_statefulset_replicas{job="kube-state-metrics"} != kube_statefulset_status_replicas_updated{job="kube-state-metrics"})) and (changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics"}[5m]) == 0)
for: 15m
labels:
severity: warning
annotations:
message: 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
|
ok
|
|
14.45s ago
|
635.6us |
| alert: KubeDaemonSetRolloutStuck
expr: kube_daemonset_status_number_ready{job="kube-state-metrics"} / kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"} < 1
for: 15m
labels:
severity: warning
annotations:
message: Only {{ $value | humanizePercentage }} of the desired Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are scheduled and ready.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetrolloutstuck
|
ok
|
|
14.449s ago
|
180.4us |
| alert: KubeContainerWaiting
expr: sum by(namespace, pod, container) (kube_pod_container_status_waiting_reason{job="kube-state-metrics"}) > 0
for: 1h
labels:
severity: warning
annotations:
message: 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
|
ok
|
|
14.449s ago
|
7.784ms |
| alert: KubeDaemonSetNotScheduled
expr: kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"} - kube_daemonset_status_current_number_scheduled{job="kube-state-metrics"} > 0
for: 10m
labels:
severity: warning
annotations:
message: '{{ $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
|
ok
|
|
14.442s ago
|
244.6us |
| alert: KubeDaemonSetMisScheduled
expr: kube_daemonset_status_number_misscheduled{job="kube-state-metrics"} > 0
for: 15m
labels:
severity: warning
annotations:
message: '{{ $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
|
ok
|
|
14.441s ago
|
727us |
| alert: KubeCronJobRunning
expr: time() - kube_cronjob_next_schedule_time{job="kube-state-metrics"} > 3600
for: 1h
labels:
severity: warning
annotations:
message: CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking more than 1h to complete.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecronjobrunning
|
ok
|
|
14.441s ago
|
119.4us |
| alert: KubeJobCompletion
expr: kube_job_spec_completions{job="kube-state-metrics"} - kube_job_status_succeeded{job="kube-state-metrics"} > 0
for: 1h
labels:
severity: warning
annotations:
message: Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than one hour to complete.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobcompletion
|
ok
|
|
14.441s ago
|
137.2us |
| alert: KubeJobFailed
expr: kube_job_failed{job="kube-state-metrics"} > 0
for: 15m
labels:
severity: warning
annotations:
message: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed
|
ok
|
|
14.441s ago
|
49.26us |
| alert: KubeHpaReplicasMismatch
expr: (kube_hpa_status_desired_replicas{job="kube-state-metrics"} != kube_hpa_status_current_replicas{job="kube-state-metrics"}) and changes(kube_hpa_status_current_replicas[15m]) == 0
for: 15m
labels:
severity: warning
annotations:
message: 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
|
ok
|
|
14.441s ago
|
112.6us |
| alert: KubeHpaMaxedOut
expr: kube_hpa_status_current_replicas{job="kube-state-metrics"} == kube_hpa_spec_max_replicas{job="kube-state-metrics"}
for: 15m
labels:
severity: warning
annotations:
message: 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
|
ok
|
|
14.441s ago
|
54.09us |
|
2.003s ago |
4.497ms |
| 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: warning
annotations:
message: 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
|
ok
|
|
2.003s ago
|
534us |
| 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:
message: 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
|
ok
|
|
2.002s ago
|
368.5us |
| 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:
message: Cluster has overcommitted CPU resource requests for Namespaces.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuquotaovercommit
|
ok
|
|
2.002s ago
|
138.3us |
| alert: KubeMemoryQuotaOvercommit
expr: sum(kube_resourcequota{job="kube-state-metrics",resource="memory",type="hard"}) / sum(kube_node_status_allocatable_memory_bytes{job="node-exporter"}) > 1.5
for: 5m
labels:
severity: warning
annotations:
message: Cluster has overcommitted memory resource requests for Namespaces.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryquotaovercommit
|
ok
|
|
2.002s ago
|
89.8us |
| alert: KubeQuotaExceeded
expr: kube_resourcequota{job="kube-state-metrics",type="used"} / ignoring(instance, job, type) (kube_resourcequota{job="kube-state-metrics",type="hard"} > 0) > 0.9
for: 15m
labels:
severity: warning
annotations:
message: 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
|
ok
|
|
2.002s ago
|
92.06us |
| 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: warning
annotations:
message: '{{ $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
|
ok
|
|
2.002s ago
|
3.257ms |
|
23.519s ago |
13.67ms |
| Rule |
State |
Error |
Last Evaluation |
Evaluation Time |
| alert: KubeAPILatencyHigh
expr: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job="apiserver",quantile="0.99"} > 1 and on(verb, resource) (cluster:apiserver_request_duration_seconds:mean5m{job="apiserver"} > on(verb) group_left() (avg by(verb) (cluster:apiserver_request_duration_seconds:mean5m{job="apiserver"} >= 0) + 2 * stddev by(verb) (cluster:apiserver_request_duration_seconds:mean5m{job="apiserver"} >= 0))) > on(verb) group_left() 1.2 * avg by(verb) (cluster:apiserver_request_duration_seconds:mean5m{job="apiserver"} >= 0)
for: 5m
labels:
severity: warning
annotations:
message: The API server has an abnormal latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh
|
ok
|
|
14.782s ago
|
8.223ms |
| alert: KubeAPIErrorsHigh
expr: sum by(resource, subresource, verb) (rate(apiserver_request_total{code=~"5..",job="apiserver"}[5m])) / sum by(resource, subresource, verb) (rate(apiserver_request_total{job="apiserver"}[5m])) > 0.05
for: 10m
labels:
severity: warning
annotations:
message: API server is returning errors for {{ $value | humanizePercentage }} of requests for {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh
|
ok
|
|
14.774s ago
|
8.374ms |
| alert: KubeClientCertificateExpiration
expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and on(job) histogram_quantile(0.01, sum by(job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 604800
labels:
severity: warning
annotations:
message: A client certificate used to authenticate to the apiserver is expiring in less than 7.0 days.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration
|
ok
|
|
14.766s ago
|
444.9us |
| alert: KubeClientCertificateExpiration
expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and on(job) histogram_quantile(0.01, sum by(job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400
labels:
severity: critical
annotations:
message: A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration
|
ok
|
|
14.766s ago
|
312.1us |
| alert: AggregatedAPIErrors
expr: sum by(name, namespace) (increase(aggregator_unavailable_apiservice_count[5m])) > 2
labels:
severity: warning
annotations:
message: An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. The number of errors have increased for it in the past five minutes. High values indicate that the availability of the service changes too often.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapierrors
|
ok
|
|
14.765s ago
|
72.11us |
| alert: AggregatedAPIDown
expr: sum by(name, namespace) (sum_over_time(aggregator_unavailable_apiservice[5m])) > 0
for: 5m
labels:
severity: warning
annotations:
message: An aggregated API {{ $labels.name }}/{{ $labels.namespace }} is down. It has not been available at least for the past five minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapidown
|
ok
|
|
14.765s ago
|
744.6us |
| alert: KubeAPIDown
expr: absent(up{job="apiserver"} == 1)
for: 15m
labels:
severity: critical
annotations:
message: KubeAPI has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapidown
|
ok
|
|
14.765s ago
|
85.8us |
|
5.15s ago |
622.9us |
| 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:
message: '{{ $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
|
ok
|
|
12.618s ago
|
300.9us |
| 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"}) == 1
labels:
severity: warning
annotations:
message: '{{ $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
|
ok
|
|
12.618s ago
|
137.3us |
| alert: KubeletTooManyPods
expr: max by(node) (max by(instance) (kubelet_running_pod_count{job="kubelet",metrics_path="/metrics"}) * on(instance) group_left(node) kubelet_node_name{job="kubelet",metrics_path="/metrics"}) / max by(node) (kube_node_status_capacity_pods{job="kube-state-metrics"} != 1) > 0.95
for: 15m
labels:
severity: warning
annotations:
message: 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
|
ok
|
|
12.618s ago
|
364.3us |
| alert: KubeNodeReadinessFlapping
expr: sum by(node) (changes(kube_node_status_condition{condition="Ready",status="true"}[15m])) > 2
for: 15m
labels:
severity: warning
annotations:
message: 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
|
ok
|
|
12.618s ago
|
223.1us |
| alert: KubeletPlegDurationHigh
expr: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile="0.99"} >= 10
for: 5m
labels:
severity: warning
annotations:
message: 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
|
ok
|
|
12.618s ago
|
150.6us |
| 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:
message: 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
|
ok
|
|
12.618s ago
|
3.759ms |
| alert: KubeletDown
expr: absent(up{job="kubelet",metrics_path="/metrics"} == 1)
for: 15m
labels:
severity: critical
annotations:
message: Kubelet has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletdown
|
ok
|
|
12.614s ago
|
191.4us |
|
16.623s ago |
366.9us |
| 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
|
|
3.081s ago
|
30.1ms |
| 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
|
|
3.051s ago
|
24.1ms |
| 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
|
|
3.028s ago
|
3.846ms |
| 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
|
|
3.024s ago
|
3.702ms |
| 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
|
|
3.02s ago
|
16.23ms |
| 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
|
|
3.004s ago
|
14.13ms |
| 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
|
|
2.99s ago
|
2.366ms |
| 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
|
|
2.988s ago
|
2.353ms |
| alert: NodeNetworkReceiveErrs
expr: increase(node_network_receive_errs_total[2m]) > 10
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
|
|
2.986s ago
|
1.813ms |
| alert: NodeNetworkTransmitErrs
expr: increase(node_network_transmit_errs_total[2m]) > 10
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
|
|
2.984s ago
|
1.874ms |
| 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
|
|
2.982s ago
|
297.7us |
| 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
|
|
2.982s ago
|
143.2us |
| 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
|
|
2.982s ago
|
697.2us |
| alert: NodeClockNotSynchronising
expr: min_over_time(node_timex_sync_status[5m]) == 0
for: 10m
labels:
severity: warning
annotations:
message: Clock on {{ $labels.instance }} is not synchronising. Ensure NTP is configured on this host.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodeclocknotsynchronising
summary: Clock not synchronising.
|
ok
|
|
2.981s ago
|
134.5us |
|
15.665s ago |
16.65ms |
| Rule |
State |
Error |
Last Evaluation |
Evaluation Time |
| alert: PrometheusBadConfig
expr: max_over_time(prometheus_config_last_reload_successful{job="prometheus-k8s",namespace="monitoring"}[5m]) == 0
for: 10m
labels:
severity: critical
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to reload its configuration.
summary: Failed Prometheus configuration reload.
|
ok
|
|
5.952s ago
|
239.5us |
| alert: PrometheusNotificationQueueRunningFull
expr: (predict_linear(prometheus_notifications_queue_length{job="prometheus-k8s",namespace="monitoring"}[5m], 60 * 30) > min_over_time(prometheus_notifications_queue_capacity{job="prometheus-k8s",namespace="monitoring"}[5m]))
for: 15m
labels:
severity: warning
annotations:
description: Alert notification queue of Prometheus {{$labels.namespace}}/{{$labels.pod}} is running full.
summary: Prometheus alert notification queue predicted to run full in less than 30m.
|
ok
|
|
5.952s ago
|
247.8us |
| alert: PrometheusErrorSendingAlertsToSomeAlertmanagers
expr: (rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m]) / rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring"}[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
|
|
5.952s ago
|
286.2us |
| alert: PrometheusErrorSendingAlertsToAnyAlertmanager
expr: min without(alertmanager) (rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m]) / rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring"}[5m])) * 100 > 3
for: 15m
labels:
severity: critical
annotations:
description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.'
summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager.
|
ok
|
|
5.952s ago
|
277.3us |
| alert: PrometheusNotConnectedToAlertmanagers
expr: max_over_time(prometheus_notifications_alertmanagers_discovered{job="prometheus-k8s",namespace="monitoring"}[5m]) < 1
for: 10m
labels:
severity: warning
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not connected to any Alertmanagers.
summary: Prometheus is not connected to any Alertmanagers.
|
ok
|
|
5.952s ago
|
123us |
| alert: PrometheusTSDBReloadsFailing
expr: increase(prometheus_tsdb_reloads_failures_total{job="prometheus-k8s",namespace="monitoring"}[3h]) > 0
for: 4h
labels:
severity: warning
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} reload failures over the last 3h.
summary: Prometheus has issues reloading blocks from disk.
|
ok
|
|
5.952s ago
|
260.9us |
| alert: PrometheusTSDBCompactionsFailing
expr: increase(prometheus_tsdb_compactions_failed_total{job="prometheus-k8s",namespace="monitoring"}[3h]) > 0
for: 4h
labels:
severity: warning
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} compaction failures over the last 3h.
summary: Prometheus has issues compacting blocks.
|
ok
|
|
5.952s ago
|
223.6us |
| alert: PrometheusNotIngestingSamples
expr: rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-k8s",namespace="monitoring"}[5m]) <= 0
for: 10m
labels:
severity: warning
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not ingesting samples.
summary: Prometheus is not ingesting samples.
|
ok
|
|
5.952s ago
|
130.5us |
| alert: PrometheusDuplicateTimestamps
expr: rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
for: 10m
labels:
severity: warning
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with different values but duplicated timestamp.
summary: Prometheus is dropping samples with duplicate timestamps.
|
ok
|
|
5.952s ago
|
112.5us |
| alert: PrometheusOutOfOrderTimestamps
expr: rate(prometheus_target_scrapes_sample_out_of_order_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
for: 10m
labels:
severity: warning
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with timestamps arriving out of order.
summary: Prometheus drops samples with out-of-order timestamps.
|
ok
|
|
5.952s ago
|
105.9us |
| alert: PrometheusRemoteStorageFailures
expr: (rate(prometheus_remote_storage_failed_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m]) / (rate(prometheus_remote_storage_failed_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m]) + rate(prometheus_remote_storage_succeeded_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m]))) * 100 > 1
for: 15m
labels:
severity: critical
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send {{ printf "%.1f" $value }}% of the samples to {{ $labels.remote_name}}:{{ $labels.url }}
summary: Prometheus fails to send samples to remote storage.
|
ok
|
|
5.952s ago
|
248.5us |
| alert: PrometheusRemoteWriteBehind
expr: (max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="prometheus-k8s",namespace="monitoring"}[5m]) - on(job, instance) group_right() max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="prometheus-k8s",namespace="monitoring"}[5m])) > 120
for: 15m
labels:
severity: critical
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url }}.
summary: Prometheus remote write is behind.
|
ok
|
|
5.951s ago
|
192.1us |
| alert: PrometheusRemoteWriteDesiredShards
expr: (max_over_time(prometheus_remote_storage_shards_desired{job="prometheus-k8s",namespace="monitoring"}[5m]) > max_over_time(prometheus_remote_storage_shards_max{job="prometheus-k8s",namespace="monitoring"}[5m]))
for: 15m
labels:
severity: warning
annotations:
description: Prometheus {{$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-k8s",namespace="monitoring"}` $labels.instance | query | first | value }}.
summary: Prometheus remote write desired shards calculation wants to run more than configured max shards.
|
ok
|
|
5.951s ago
|
138.9us |
| alert: PrometheusRuleFailures
expr: increase(prometheus_rule_evaluation_failures_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
for: 15m
labels:
severity: critical
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to evaluate {{ printf "%.0f" $value }} rules in the last 5m.
summary: Prometheus is failing rule evaluations.
|
ok
|
|
5.951s ago
|
438.7us |
| alert: PrometheusMissingRuleEvaluations
expr: increase(prometheus_rule_group_iterations_missed_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
for: 15m
labels:
severity: warning
annotations:
description: Prometheus {{$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
|
|
5.951s ago
|
136.5us |
|
1.243s ago |
394.5us |