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

manifests: Regenerate

Browse Source
This commit is contained in:
Lili Cosic
2020-04-16 22:03:16 +02:00
parent fd67733729
commit 926337feac
9 changed files with 49 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
manifests/prometheus-rules.yaml
View File

@@ -389,12 +389,15 @@ spec:
verb: write
record: apiserver_request:availability30d
- expr: |
sum by (code) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[30d]))
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) (increase(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30d]))
sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~"POST|PUT|PATCH|DELETE"})
labels:
verb: write
record: code:apiserver_request_total:increase30d
@@ -1311,29 +1314,6 @@ spec:
for: 5m
labels:
severity: warning
- alert: KubeAPILatencyHigh
annotations:
message: The API server has a 99th percentile 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"} > 4
for: 10m
labels:
severity: critical
- 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) > 0.10
for: 10m
labels:
severity: critical
- alert: KubeAPIErrorsHigh
annotations:
message: API server is returning errors for {{ $value | humanizePercentage
@@ -1451,7 +1431,7 @@ spec:
on node {{ $labels.node }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletpodstartuplatencyhigh
expr: |
histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name > 60
histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"} > 60
for: 15m
labels:
severity: warning
@@ -1616,8 +1596,8 @@ spec:
- alert: PrometheusRemoteStorageFailures
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send
{{ printf "%.1f" $value }}% of the samples to {{ if $labels.queue }}{{ $labels.queue
}}{{ else }}{{ $labels.url }}{{ end }}.
{{ printf "%.1f" $value }}% of the samples to {{ $labels.remote_name}}:{{
$labels.url }}
summary: Prometheus fails to send samples to remote storage.
expr: |
(
@@ -1637,8 +1617,8 @@ spec:
- alert: PrometheusRemoteWriteBehind
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write
is {{ printf "%.1f" $value }}s behind for {{ if $labels.queue }}{{ $labels.queue
}}{{ else }}{{ $labels.url }}{{ end }}.
is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url
}}.
summary: Prometheus remote write is behind.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
@@ -1655,8 +1635,9 @@ spec:
- alert: PrometheusRemoteWriteDesiredShards
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write
desired shards calculation wants to run {{ $value }} shards, which is more
than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}`
desired shards calculation wants to run {{ $value }} shards for queue {{
$labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{
printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}`
$labels.instance | query | first | value }}.
summary: Prometheus remote write desired shards calculation wants to run more
than configured max shards.