Skip to content

Instantly share code, notes, and snippets.

@yangchuansheng

yangchuansheng/prometheus-rules-system.yaml

Created August 5, 2020 09:17
Show Gist options
  • Save yangchuansheng/4310ae9f41513899dc5f0176cdf804b1 to your computer and use it in GitHub Desktop.
Save yangchuansheng/4310ae9f41513899dc5f0176cdf804b1 to your computer and use it in GitHub Desktop.
Download ZIP
prometheus-rules-system.yaml
Raw
prometheus-rules-system.yaml
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
labels:
prometheus: system
role: alert-rules
name: prometheus-system-rules
namespace: monitoring
spec:
groups:
- name: kube-apiserver.rules
rules:
- expr: |
(
(
# too slow
sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[1d]))
-
(
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[1d])) +
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[1d])) +
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[1d]))
)
)
+
# errors
sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1d]))
)
/
sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1d]))
labels:
verb: read
record: apiserver_request:burnrate1d
- expr: |
(
(
# too slow
sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[1h]))
-
(
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[1h])) +
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[1h])) +
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[1h]))
)
)
+
# errors
sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1h]))
)
/
sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1h]))
labels:
verb: read
record: apiserver_request:burnrate1h
- expr: |
(
(
# too slow
sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[2h]))
-
(
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[2h])) +
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[2h])) +
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[2h]))
)
)
+
# errors
sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[2h]))
)
/
sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[2h]))
labels:
verb: read
record: apiserver_request:burnrate2h
- expr: |
(
(
# too slow
sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[30m]))
-
(
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30m])) +
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[30m])) +
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[30m]))
)
)
+
# errors
sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[30m]))
)
/
sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[30m]))
labels:
verb: read
record: apiserver_request:burnrate30m
- expr: |
(
(
# too slow
sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[3d]))
-
(
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[3d])) +
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[3d])) +
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[3d]))
)
)
+
# errors
sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[3d]))
)
/
sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[3d]))
labels:
verb: read
record: apiserver_request:burnrate3d
- expr: |
(
(
# too slow
sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[5m]))
-
(
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[5m])) +
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[5m])) +
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[5m]))
)
)
+
# errors
sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[5m]))
)
/
sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m]))
labels:
verb: read
record: apiserver_request:burnrate5m
- expr: |
(
(
# too slow
sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[6h]))
-
(
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[6h])) +
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[6h])) +
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[6h]))
)
)
+
# errors
sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[6h]))
)
/
sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[6h]))
labels:
verb: read
record: apiserver_request:burnrate6h
- expr: |
(
(
# too slow
sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d]))
-
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[1d]))
)
+
sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1d]))
)
/
sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d]))
labels:
verb: write
record: apiserver_request:burnrate1d
- expr: |
(
(
# too slow
sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h]))
-
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[1h]))
)
+
sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1h]))
)
/
sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h]))
labels:
verb: write
record: apiserver_request:burnrate1h
- expr: |
(
(
# too slow
sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h]))
-
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[2h]))
)
+
sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[2h]))
)
/
sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h]))
labels:
verb: write
record: apiserver_request:burnrate2h
- expr: |
(
(
# too slow
sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m]))
-
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[30m]))
)
+
sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[30m]))
)
/
sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m]))
labels:
verb: write
record: apiserver_request:burnrate30m
- expr: |
(
(
# too slow
sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d]))
-
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[3d]))
)
+
sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[3d]))
)
/
sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d]))
labels:
verb: write
record: apiserver_request:burnrate3d
- expr: |
(
(
# too slow
sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
-
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[5m]))
)
+
sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[5m]))
)
/
sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
labels:
verb: write
record: apiserver_request:burnrate5m
- expr: |
(
(
# too slow
sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h]))
-
sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[6h]))
)
+
sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[6h]))
)
/
sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h]))
labels:
verb: write
record: apiserver_request:burnrate6h
- expr: |
sum by (code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m]))
labels:
verb: read
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
record: code_resource:apiserver_request_total:rate5m
- 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
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
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
- expr: |
sum(rate(apiserver_request_duration_seconds_sum{subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod)
/
sum(rate(apiserver_request_duration_seconds_count{subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod)
record: cluster:apiserver_request_duration_seconds:mean5m
- expr: |
histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod))
labels:
quantile: "0.99"
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod))
labels:
quantile: "0.9"
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod))
labels:
quantile: "0.5"
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
- interval: 3m
name: kube-apiserver-availability.rules
rules:
- expr: |
1 - (
(
# write too slow
sum(increase(apiserver_request_duration_seconds_count{verb=~"POST|PUT|PATCH|DELETE"}[30d]))
-
sum(increase(apiserver_request_duration_seconds_bucket{verb=~"POST|PUT|PATCH|DELETE",le="1"}[30d]))
) +
(
# read too slow
sum(increase(apiserver_request_duration_seconds_count{verb=~"LIST|GET"}[30d]))
-
(
sum(increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30d])) +
sum(increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope="namespace",le="0.5"}[30d])) +
sum(increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope="cluster",le="5"}[30d]))
)
) +
# errors
sum(code:apiserver_request_total:increase30d{code=~"5.."} or vector(0))
)
/
sum(code:apiserver_request_total:increase30d)
labels:
verb: all
record: apiserver_request:availability30d
- expr: |
1 - (
sum(increase(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[30d]))
-
(
# too slow
sum(increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30d])) +
sum(increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[30d])) +
sum(increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[30d]))
)
+
# errors
sum(code:apiserver_request_total:increase30d{verb="read",code=~"5.."} or vector(0))
)
/
sum(code:apiserver_request_total:increase30d{verb="read"})
labels:
verb: read
record: apiserver_request:availability30d
- expr: |
1 - (
(
# too slow
sum(increase(apiserver_request_duration_seconds_count{verb=~"POST|PUT|PATCH|DELETE"}[30d]))
-
sum(increase(apiserver_request_duration_seconds_bucket{verb=~"POST|PUT|PATCH|DELETE",le="1"}[30d]))
)
+
# errors
sum(code:apiserver_request_total:increase30d{verb="write",code=~"5.."} or vector(0))
)
/
sum(code:apiserver_request_total:increase30d{verb="write"})
labels:
verb: write
record: apiserver_request:availability30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"2.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"2.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"2.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"2.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"2.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"2.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"3.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"3.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"3.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"3.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"3.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"3.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"4.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"4.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"4.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"4.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"4.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"4.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"5.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"5.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"5.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"5.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"5.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"5.."}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"})
labels:
verb: read
record: code:apiserver_request_total:increase30d
- expr: |
sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~"POST|PUT|PATCH|DELETE"})
labels:
verb: write
record: code:apiserver_request_total:increase30d
- name: kube-scheduler.rules
rules:
- expr: |
histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
quantile: "0.99"
record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
quantile: "0.99"
record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
quantile: "0.99"
record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.9, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
quantile: "0.9"
record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.9, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
quantile: "0.9"
record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.9, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
quantile: "0.9"
record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.5, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
quantile: "0.5"
record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.5, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
quantile: "0.5"
record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.5, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
quantile: "0.5"
record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile
- name: kubelet.rules
rules:
- expr: |
histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
labels:
quantile: "0.99"
record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.9, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
labels:
quantile: "0.9"
record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.5, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
labels:
quantile: "0.5"
record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
- name: kubernetes-storage
rules:
- alert: KubePersistentVolumeFillingUp
annotations:
message: The PersistentVolume claimed by {{ $labels.persistentvolumeclaim
}} in Namespace {{ $labels.namespace }} is only {{ $value | humanizePercentage
}} free.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefillingup
expr: |
kubelet_volume_stats_available_bytes{job="kubelet", metrics_path="/metrics"}
/
kubelet_volume_stats_capacity_bytes{job="kubelet", metrics_path="/metrics"}
< 0.03
for: 1m
labels:
severity: critical
- alert: KubePersistentVolumeFillingUp
annotations:
message: Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim
}} in Namespace {{ $labels.namespace }} is expected to fill up within four
days. Currently {{ $value | humanizePercentage }} is available.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefillingup
expr: |
(
kubelet_volume_stats_available_bytes{job="kubelet", metrics_path="/metrics"}
/
kubelet_volume_stats_capacity_bytes{job="kubelet", metrics_path="/metrics"}
) < 0.15
and
predict_linear(kubelet_volume_stats_available_bytes{job="kubelet", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0
for: 1h
labels:
severity: warning
- alert: KubePersistentVolumeErrors
annotations:
message: The persistent volume {{ $labels.persistentvolume }} has status {{
$labels.phase }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeerrors
expr: |
kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"} > 0
for: 5m
labels:
severity: critical
- name: kubernetes-system
rules:
- alert: KubeVersionMismatch
annotations:
message: There are {{ $value }} different semantic versions of Kubernetes
components running.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeversionmismatch
expr: |
count(count by (gitVersion) (label_replace(kubernetes_build_info{job!~"kube-dns|coredns"},"gitVersion","$1","gitVersion","(v[0-9]*.[0-9]*.[0-9]*).*"))) > 1
for: 15m
labels:
severity: warning
- alert: KubeClientErrors
annotations:
message: Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance
}}' is experiencing {{ $value | humanizePercentage }} errors.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors
expr: |
(sum(rate(rest_client_requests_total{code=~"5.."}[5m])) by (instance, job)
/
sum(rate(rest_client_requests_total[5m])) by (instance, job))
> 0.01
for: 15m
labels:
severity: warning
- name: kube-apiserver-slos
rules:
- alert: KubeAPIErrorBudgetBurn
annotations:
message: The API server is burning too much error budget
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn
expr: |
sum(apiserver_request:burnrate1h) > (14.40 * 0.01000)
and
sum(apiserver_request:burnrate5m) > (14.40 * 0.01000)
for: 2m
labels:
long: 1h
severity: critical
short: 5m
- alert: KubeAPIErrorBudgetBurn
annotations:
message: The API server is burning too much error budget
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn
expr: |
sum(apiserver_request:burnrate6h) > (6.00 * 0.01000)
and
sum(apiserver_request:burnrate30m) > (6.00 * 0.01000)
for: 15m
labels:
long: 6h
severity: critical
short: 30m
- alert: KubeAPIErrorBudgetBurn
annotations:
message: The API server is burning too much error budget
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn
expr: |
sum(apiserver_request:burnrate1d) > (3.00 * 0.01000)
and
sum(apiserver_request:burnrate2h) > (3.00 * 0.01000)
for: 1h
labels:
long: 1d
severity: warning
short: 2h
- alert: KubeAPIErrorBudgetBurn
annotations:
message: The API server is burning too much error budget
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn
expr: |
sum(apiserver_request:burnrate3d) > (1.00 * 0.01000)
and
sum(apiserver_request:burnrate6h) > (1.00 * 0.01000)
for: 3h
labels:
long: 3d
severity: warning
short: 6h
- name: kubernetes-system-apiserver
rules:
- alert: KubeAPILatencyHigh
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
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
- alert: KubeAPIErrorsHigh
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
expr: |
sum(rate(apiserver_request_total{job="apiserver",code=~"5.."}[5m])) by (resource,subresource,verb)
/
sum(rate(apiserver_request_total{job="apiserver"}[5m])) by (resource,subresource,verb) > 0.05
for: 10m
labels:
severity: warning
- alert: KubeClientCertificateExpiration
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
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
- alert: KubeClientCertificateExpiration
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
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
- alert: AggregatedAPIErrors
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
expr: |
sum by(name, namespace)(increase(aggregator_unavailable_apiservice_count[5m])) > 2
labels:
severity: warning
- alert: AggregatedAPIDown
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
expr: |
sum by(name, namespace)(sum_over_time(aggregator_unavailable_apiservice[5m])) > 0
for: 5m
labels:
severity: warning
- alert: KubeAPIDown
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
expr: |
absent(up{job="apiserver"} == 1)
for: 15m
labels:
severity: critical
- name: kubernetes-system-kubelet
rules:
- alert: KubeNodeNotReady
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
expr: |
kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0
for: 15m
labels:
severity: warning
- alert: KubeNodeUnreachable
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
expr: |
(kube_node_spec_taint{job="kube-state-metrics",key="node.kubernetes.io/unreachable",effect="NoSchedule"} unless ignoring(key,value) kube_node_spec_taint{job="kube-state-metrics",key="ToBeDeletedByClusterAutoscaler"}) == 1
labels:
severity: warning
- alert: KubeletTooManyPods
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
expr: |
max(max(kubelet_running_pod_count{job="kubelet", metrics_path="/metrics"}) by(instance) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) by(node) / max(kube_node_status_capacity_pods{job="kube-state-metrics"} != 1) by(node) > 0.95
for: 15m
labels:
severity: warning
- alert: KubeNodeReadinessFlapping
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
expr: |
sum(changes(kube_node_status_condition{status="true",condition="Ready"}[15m])) by (node) > 2
for: 15m
labels:
severity: warning
- alert: KubeletPlegDurationHigh
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
expr: |
node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile="0.99"} >= 10
for: 5m
labels:
severity: warning
- alert: KubeletPodStartUpLatencyHigh
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
expr: |
histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"} > 60
for: 15m
labels:
severity: warning
- alert: KubeletDown
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
expr: |
absent(up{job="kubelet", metrics_path="/metrics"} == 1)
for: 15m
labels:
severity: critical
- name: kubernetes-system-scheduler
rules:
- alert: KubeSchedulerDown
annotations:
message: KubeScheduler has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeschedulerdown
expr: |
absent(up{job="kube-scheduler"} == 1)
for: 15m
labels:
severity: critical
- name: kubernetes-system-controller-manager
rules:
- alert: KubeControllerManagerDown
annotations:
message: KubeControllerManager has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontrollermanagerdown
expr: |
absent(up{job="kube-controller-manager"} == 1)
for: 15m
labels:
severity: critical
- name: general.rules
rules:
- alert: TargetDown
annotations:
message: '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service
}} targets in {{ $labels.namespace }} namespace are down.'
expr: 100 * (count(up == 0) BY (job, namespace, service) / count(up) BY (job,
namespace, service)) > 10
for: 10m
labels:
severity: warning
- alert: Watchdog
annotations:
message: |
This is an alert meant to ensure that the entire alerting pipeline is functional.
This alert is always firing, therefore it should always be firing in Alertmanager
and always fire against a receiver. There are integrations with various notification
mechanisms that send a notification when this alert is not firing. For example the
"DeadMansSnitch" integration in PagerDuty.
expr: vector(1)
labels:
severity: none
- name: CoreDNS
rules:
- alert: CorednsPanicCount
expr: increase(coredns_panic_count_total[10m]) > 0
for: 5m
labels:
severity: critical
annotations:
summary: "CoreDNS Panic Count (instance {{ $labels.instance }})"
description: "Number of CoreDNS panics encountered\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment