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

manifests: Regenerate files

Browse Source
This commit is contained in:
Lili Cosic
2020-04-03 12:00:49 +02:00
parent 5ee1229be8
commit 7992aa4e73
2 changed files with 1349 additions and 172 deletions
Download Patch File Download Diff File Expand all files Collapse all files

958
manifests/grafana-dashboardDefinitions.yaml
View File

File diff suppressed because it is too large Load Diff

563
manifests/prometheus-rules.yaml
View File

@@ -65,122 +65,361 @@ spec:
rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[1m])
)
record: instance:node_network_transmit_drop_excluding_lo:rate1m
- name: kube-apiserver-error
rules:
- expr: |
sum by (status_class) (
label_replace(
rate(apiserver_request_total{job="apiserver"}[5m]
), "status_class", "${1}xx", "code", "([0-9])..")
)
labels:
job: apiserver
record: status_class:apiserver_request_total:rate5m
- expr: |
sum by (status_class) (
label_replace(
rate(apiserver_request_total{job="apiserver"}[30m]
), "status_class", "${1}xx", "code", "([0-9])..")
)
labels:
job: apiserver
record: status_class:apiserver_request_total:rate30m
- expr: |
sum by (status_class) (
label_replace(
rate(apiserver_request_total{job="apiserver"}[1h]
), "status_class", "${1}xx", "code", "([0-9])..")
)
labels:
job: apiserver
record: status_class:apiserver_request_total:rate1h
- expr: |
sum by (status_class) (
label_replace(
rate(apiserver_request_total{job="apiserver"}[2h]
), "status_class", "${1}xx", "code", "([0-9])..")
)
labels:
job: apiserver
record: status_class:apiserver_request_total:rate2h
- expr: |
sum by (status_class) (
label_replace(
rate(apiserver_request_total{job="apiserver"}[6h]
), "status_class", "${1}xx", "code", "([0-9])..")
)
labels:
job: apiserver
record: status_class:apiserver_request_total:rate6h
- expr: |
sum by (status_class) (
label_replace(
rate(apiserver_request_total{job="apiserver"}[1d]
), "status_class", "${1}xx", "code", "([0-9])..")
)
labels:
job: apiserver
record: status_class:apiserver_request_total:rate1d
- expr: |
sum by (status_class) (
label_replace(
rate(apiserver_request_total{job="apiserver"}[3d]
), "status_class", "${1}xx", "code", "([0-9])..")
)
labels:
job: apiserver
record: status_class:apiserver_request_total:rate3d
- expr: |
sum(status_class:apiserver_request_total:rate5m{job="apiserver",status_class="5xx"})
/
sum(status_class:apiserver_request_total:rate5m{job="apiserver"})
labels:
job: apiserver
record: status_class_5xx:apiserver_request_total:ratio_rate5m
- expr: |
sum(status_class:apiserver_request_total:rate30m{job="apiserver",status_class="5xx"})
/
sum(status_class:apiserver_request_total:rate30m{job="apiserver"})
labels:
job: apiserver
record: status_class_5xx:apiserver_request_total:ratio_rate30m
- expr: |
sum(status_class:apiserver_request_total:rate1h{job="apiserver",status_class="5xx"})
/
sum(status_class:apiserver_request_total:rate1h{job="apiserver"})
labels:
job: apiserver
record: status_class_5xx:apiserver_request_total:ratio_rate1h
- expr: |
sum(status_class:apiserver_request_total:rate2h{job="apiserver",status_class="5xx"})
/
sum(status_class:apiserver_request_total:rate2h{job="apiserver"})
labels:
job: apiserver
record: status_class_5xx:apiserver_request_total:ratio_rate2h
- expr: |
sum(status_class:apiserver_request_total:rate6h{job="apiserver",status_class="5xx"})
/
sum(status_class:apiserver_request_total:rate6h{job="apiserver"})
labels:
job: apiserver
record: status_class_5xx:apiserver_request_total:ratio_rate6h
- expr: |
sum(status_class:apiserver_request_total:rate1d{job="apiserver",status_class="5xx"})
/
sum(status_class:apiserver_request_total:rate1d{job="apiserver"})
labels:
job: apiserver
record: status_class_5xx:apiserver_request_total:ratio_rate1d
- expr: |
sum(status_class:apiserver_request_total:rate3d{job="apiserver",status_class="5xx"})
/
sum(status_class:apiserver_request_total:rate3d{job="apiserver"})
labels:
job: apiserver
record: status_class_5xx:apiserver_request_total:ratio_rate3d
- 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: |
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) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[30d]))
labels:
verb: read
record: code:apiserver_request_total:increase30d
- expr: |
sum by (code) (increase(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30d]))
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:
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)
/
@@ -628,7 +867,7 @@ spec:
)
or
(
node_timex_offset_seconds < 0.05
node_timex_offset_seconds < -0.05
and
deriv(node_timex_offset_seconds[5m]) <= 0
)
@@ -791,7 +1030,7 @@ spec:
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetmisscheduled
expr: |
kube_daemonset_status_number_misscheduled{job="kube-state-metrics"} > 0
for: 10m
for: 15m
labels:
severity: warning
- alert: KubeCronJobRunning
@@ -865,11 +1104,11 @@ spec:
for: 5m
labels:
severity: warning
- alert: KubeMemOvercommit
- alert: KubeMemoryOvercommit
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-kubememovercommit
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryovercommit
expr: |
sum(namespace:kube_pod_container_resource_requests_memory_bytes:sum{})
/
@@ -881,10 +1120,10 @@ spec:
for: 5m
labels:
severity: warning
- alert: KubeCPUOvercommit
- alert: KubeCPUQuotaOvercommit
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-kubecpuovercommit
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuquotaovercommit
expr: |
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="cpu"})
/
@@ -893,10 +1132,10 @@ spec:
for: 5m
labels:
severity: warning
- alert: KubeMemOvercommit
- alert: KubeMemoryQuotaOvercommit
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-kubememovercommit
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryquotaovercommit
expr: |
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="memory"})
/
@@ -934,12 +1173,12 @@ spec:
severity: warning
- name: kubernetes-storage
rules:
- alert: KubePersistentVolumeUsageCritical
- 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-kubepersistentvolumeusagecritical
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"}
/
@@ -948,12 +1187,12 @@ spec:
for: 1m
labels:
severity: critical
- alert: KubePersistentVolumeFullInFourDays
- 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-kubepersistentvolumefullinfourdays
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"}
@@ -964,7 +1203,7 @@ spec:
predict_linear(kubelet_volume_stats_available_bytes{job="kubelet", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0
for: 1h
labels:
severity: critical
severity: warning
- alert: KubePersistentVolumeErrors
annotations:
message: The persistent volume {{ $labels.persistentvolume }} has status {{
@@ -1000,47 +1239,51 @@ spec:
for: 15m
labels:
severity: warning
- name: kube-apiserver-error-alerts
- name: kube-apiserver-slos
rules:
- alert: ErrorBudgetBurn
- alert: KubeAPIErrorBudgetBurn
annotations:
message: 'High requests error budget burn for job=apiserver (current value:
{{ $value }})'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-errorbudgetburn
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: |
(
status_class_5xx:apiserver_request_total:ratio_rate1h{job="apiserver"} > (14.4*0.010000)
and
status_class_5xx:apiserver_request_total:ratio_rate5m{job="apiserver"} > (14.4*0.010000)
)
or
(
status_class_5xx:apiserver_request_total:ratio_rate6h{job="apiserver"} > (6*0.010000)
and
status_class_5xx:apiserver_request_total:ratio_rate30m{job="apiserver"} > (6*0.010000)
)
sum(apiserver_request:burnrate1h) > (14.40 * 0.01000)
and
sum(apiserver_request:burnrate5m) > (14.40 * 0.01000)
for: 2m
labels:
job: apiserver
severity: critical
- alert: ErrorBudgetBurn
- alert: KubeAPIErrorBudgetBurn
annotations:
message: 'High requests error budget burn for job=apiserver (current value:
{{ $value }})'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-errorbudgetburn
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: |
(
status_class_5xx:apiserver_request_total:ratio_rate1d{job="apiserver"} > (3*0.010000)
and
status_class_5xx:apiserver_request_total:ratio_rate2h{job="apiserver"} > (3*0.010000)
)
or
(
status_class_5xx:apiserver_request_total:ratio_rate3d{job="apiserver"} > (0.010000)
and
status_class_5xx:apiserver_request_total:ratio_rate6h{job="apiserver"} > (0.010000)
)
sum(apiserver_request:burnrate6h) > (6.00 * 0.01000)
and
sum(apiserver_request:burnrate30m) > (6.00 * 0.01000)
for: 15m
labels:
severity: critical
- 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:
severity: warning
- 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:
job: apiserver
severity: warning
- name: kubernetes-system-apiserver
rules: