322 lines
16 KiB
Plaintext
322 lines
16 KiB
Plaintext
---
|
|
# Source: kube-prometheus-stack/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-burnrate.rules.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-apiserver-burnrate.rules
|
|
namespace: kube-prometheus-stack
|
|
labels:
|
|
app: kube-prometheus-stack
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "79.11.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
chart: kube-prometheus-stack-79.11.0
|
|
release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kube-apiserver-burnrate.rules
|
|
rules:
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1d]))
|
|
-
|
|
(
|
|
(
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(\\.0)?"}[1d]))
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(\\.0)?"}[1d]))
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(\\.0)?"}[1d]))
|
|
)
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1d]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1d]))
|
|
labels:
|
|
verb: read
|
|
record: apiserver_request:burnrate1d
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1h]))
|
|
-
|
|
(
|
|
(
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(\\.0)?"}[1h]))
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(\\.0)?"}[1h]))
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(\\.0)?"}[1h]))
|
|
)
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1h]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1h]))
|
|
labels:
|
|
verb: read
|
|
record: apiserver_request:burnrate1h
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[2h]))
|
|
-
|
|
(
|
|
(
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(\\.0)?"}[2h]))
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(\\.0)?"}[2h]))
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(\\.0)?"}[2h]))
|
|
)
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[2h]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[2h]))
|
|
labels:
|
|
verb: read
|
|
record: apiserver_request:burnrate2h
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[30m]))
|
|
-
|
|
(
|
|
(
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(\\.0)?"}[30m]))
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(\\.0)?"}[30m]))
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(\\.0)?"}[30m]))
|
|
)
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[30m]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[30m]))
|
|
labels:
|
|
verb: read
|
|
record: apiserver_request:burnrate30m
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[3d]))
|
|
-
|
|
(
|
|
(
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(\\.0)?"}[3d]))
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(\\.0)?"}[3d]))
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(\\.0)?"}[3d]))
|
|
)
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[3d]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[3d]))
|
|
labels:
|
|
verb: read
|
|
record: apiserver_request:burnrate3d
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m]))
|
|
-
|
|
(
|
|
(
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(\\.0)?"}[5m]))
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(\\.0)?"}[5m]))
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(\\.0)?"}[5m]))
|
|
)
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[5m]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m]))
|
|
labels:
|
|
verb: read
|
|
record: apiserver_request:burnrate5m
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[6h]))
|
|
-
|
|
(
|
|
(
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(\\.0)?"}[6h]))
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(\\.0)?"}[6h]))
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(\\.0)?"}[6h]))
|
|
)
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[6h]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[6h]))
|
|
labels:
|
|
verb: read
|
|
record: apiserver_request:burnrate6h
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1d]))
|
|
-
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(\\.0)?"}[1d]))
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1d]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d]))
|
|
labels:
|
|
verb: write
|
|
record: apiserver_request:burnrate1d
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1h]))
|
|
-
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(\\.0)?"}[1h]))
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1h]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h]))
|
|
labels:
|
|
verb: write
|
|
record: apiserver_request:burnrate1h
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[2h]))
|
|
-
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(\\.0)?"}[2h]))
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[2h]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h]))
|
|
labels:
|
|
verb: write
|
|
record: apiserver_request:burnrate2h
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[30m]))
|
|
-
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(\\.0)?"}[30m]))
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[30m]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m]))
|
|
labels:
|
|
verb: write
|
|
record: apiserver_request:burnrate30m
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[3d]))
|
|
-
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(\\.0)?"}[3d]))
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[3d]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d]))
|
|
labels:
|
|
verb: write
|
|
record: apiserver_request:burnrate3d
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m]))
|
|
-
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(\\.0)?"}[5m]))
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[5m]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
|
|
labels:
|
|
verb: write
|
|
record: apiserver_request:burnrate5m
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[6h]))
|
|
-
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(\\.0)?"}[6h]))
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[6h]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h]))
|
|
labels:
|
|
verb: write
|
|
record: apiserver_request:burnrate6h
|