easylinux/kube-prometheus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs, manifests: Regenerate files

Browse Source
This commit is contained in:
Lili Cosic
2020-06-19 10:30:50 +02:00
parent c5ecc42244
commit beaba9f4da
11 changed files with 599 additions and 557 deletions
Download Patch File Download Diff File Expand all files Collapse all files

332
manifests/prometheus-rules.yaml
View File

@@ -74,7 +74,7 @@ spec:
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=~"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]))
)
@@ -95,7 +95,7 @@ spec:
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=~"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]))
)
@@ -116,7 +116,7 @@ spec:
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=~"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]))
)
@@ -137,7 +137,7 @@ spec:
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=~"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]))
)
@@ -158,7 +158,7 @@ spec:
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=~"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]))
)
@@ -179,7 +179,7 @@ spec:
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=~"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]))
)
@@ -200,7 +200,7 @@ spec:
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=~"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]))
)
@@ -326,81 +326,6 @@ spec:
labels:
verb: write
record: apiserver_request:burnrate6h
- 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.."})
)
/
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.."})
)
/
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.."})
)
/
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"}[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
- expr: |
sum by (code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m]))
labels:
@@ -443,6 +368,153 @@ spec:
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: k8s.rules
rules:
- expr: |
@@ -452,31 +524,31 @@ spec:
sum by (cluster, namespace, pod, container) (
rate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!="", container!="POD"}[5m])
) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (
1, max by(cluster, namespace, pod, node) (kube_pod_info)
1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
)
record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate
- expr: |
container_memory_working_set_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,
max by(namespace, pod, node) (kube_pod_info)
max by(namespace, pod, node) (kube_pod_info{node!=""})
)
record: node_namespace_pod_container:container_memory_working_set_bytes
- expr: |
container_memory_rss{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,
max by(namespace, pod, node) (kube_pod_info)
max by(namespace, pod, node) (kube_pod_info{node!=""})
)
record: node_namespace_pod_container:container_memory_rss
- expr: |
container_memory_cache{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,
max by(namespace, pod, node) (kube_pod_info)
max by(namespace, pod, node) (kube_pod_info{node!=""})
)
record: node_namespace_pod_container:container_memory_cache
- expr: |
container_memory_swap{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,
max by(namespace, pod, node) (kube_pod_info)
max by(namespace, pod, node) (kube_pod_info{node!=""})
)
record: node_namespace_pod_container:container_memory_swap
- expr: |
@@ -591,12 +663,12 @@ spec:
- name: node.rules
rules:
- expr: |
sum(min(kube_pod_info) by (cluster, node))
sum(min(kube_pod_info{node!=""}) by (cluster, node))
record: ':kube_pod_info_node_count:'
- expr: |
topk by(namespace, pod) (1,
max by (node, namespace, pod) (
label_replace(kube_pod_info{job="kube-state-metrics"}, "pod", "$1", "pod", "(.*)")
label_replace(kube_pod_info{job="kube-state-metrics",node!=""}, "pod", "$1", "pod", "(.*)")
))
record: 'node_namespace_pod:kube_pod_info:'
- expr: |
@@ -849,13 +921,22 @@ spec:
severity: warning
- alert: NodeHighNumberConntrackEntriesUsed
annotations:
description: '{{ $value | humanizePercentage }} of conntrack entries are used'
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
summary: Number of conntrack are getting close to the limit.
expr: |
(node_nf_conntrack_entries / node_nf_conntrack_entries_limit) > 0.75
labels:
severity: warning
- alert: NodeTextFileCollectorScrapeError
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.
expr: |
node_textfile_scrape_error{job="node-exporter"} == 1
labels:
severity: warning
- alert: NodeClockSkewDetected
annotations:
message: Clock on {{ $labels.instance }} is out of sync by more than 300s.
@@ -896,20 +977,26 @@ spec:
}}) is restarting {{ printf "%.2f" $value }} times / 5 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodcrashlooping
expr: |
rate(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[15m]) * 60 * 5 > 0
rate(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[5m]) * 60 * 5 > 0
for: 15m
labels:
severity: critical
severity: warning
- alert: KubePodNotReady
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
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) max by(namespace, pod, owner_kind) (kube_pod_owner{owner_kind!="Job"})) > 0
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: critical
severity: warning
- alert: KubeDeploymentGenerationMismatch
annotations:
message: Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment
@@ -922,7 +1009,7 @@ spec:
kube_deployment_metadata_generation{job="kube-state-metrics"}
for: 15m
labels:
severity: critical
severity: warning
- alert: KubeDeploymentReplicasMismatch
annotations:
message: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not
@@ -940,7 +1027,7 @@ spec:
)
for: 15m
labels:
severity: critical
severity: warning
- alert: KubeStatefulSetReplicasMismatch
annotations:
message: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has
@@ -958,7 +1045,7 @@ spec:
)
for: 15m
labels:
severity: critical
severity: warning
- alert: KubeStatefulSetGenerationMismatch
annotations:
message: StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset
@@ -971,27 +1058,33 @@ spec:
kube_statefulset_metadata_generation{job="kube-state-metrics"}
for: 15m
labels:
severity: critical
severity: warning
- alert: KubeStatefulSetUpdateNotRolledOut
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
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"}
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: critical
severity: warning
- alert: KubeDaemonSetRolloutStuck
annotations:
message: Only {{ $value | humanizePercentage }} of the desired Pods of DaemonSet
@@ -1003,7 +1096,7 @@ spec:
kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"} < 1.00
for: 15m
labels:
severity: critical
severity: warning
- alert: KubeContainerWaiting
annotations:
message: Pod {{ $labels.namespace }}/{{ $labels.pod }} container {{ $labels.container}}
@@ -1254,7 +1347,9 @@ spec:
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
@@ -1265,7 +1360,9 @@ spec:
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
@@ -1276,7 +1373,9 @@ spec:
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
@@ -1287,7 +1386,9 @@ spec:
sum(apiserver_request:burnrate6h) > (1.00 * 0.01000)
for: 3h
labels:
long: 3d
severity: warning
short: 6h
- name: kubernetes-system-apiserver
rules:
- alert: KubeAPILatencyHigh
@@ -1296,6 +1397,10 @@ spec:
{{ $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"}
>
@@ -1307,10 +1412,6 @@ spec:
)
) > on (verb) group_left()
1.2 * avg by (verb) (cluster:apiserver_request_duration_seconds:mean5m{job="apiserver"} >= 0)
and on (verb,resource)
cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job="apiserver",quantile="0.99"}
>
1
for: 5m
labels:
severity: warning
@@ -1391,8 +1492,7 @@ spec:
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"} == 1
for: 2m
(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