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

update go-jsonnet for linter bugfix

Browse Source
This commit is contained in:
Haoyu Sun
2021-10-09 21:07:37 +02:00
parent 10c11d5019
commit 1e632d2ec8
17 changed files with 10070 additions and 3236 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
manifests/kube-prometheus-prometheusRule.yaml
View File

@@ -15,10 +15,12 @@ spec:
rules:
- alert: TargetDown
annotations:
description: '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service }} targets in {{ $labels.namespace }} namespace are down.'
description: '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service
}} targets in {{ $labels.namespace }} namespace are down.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/targetdown
summary: One or more targets are unreachable.
expr: 100 * (count(up == 0) BY (job, namespace, service) / count(up) BY (job, namespace, service)) > 10
expr: 100 * (count(up == 0) BY (job, namespace, service) / count(up) BY (job,
namespace, service)) > 10
for: 10m
labels:
severity: warning
@@ -31,7 +33,8 @@ spec:
mechanisms that send a notification when this alert is not firing. For example the
"DeadMansSnitch" integration in PagerDuty.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/watchdog
summary: An alert that should always be firing to certify that Alertmanager is working properly.
summary: An alert that should always be firing to certify that Alertmanager
is working properly.
expr: vector(1)
labels:
severity: none
@@ -39,7 +42,8 @@ spec:
rules:
- alert: NodeNetworkInterfaceFlapping
annotations:
description: Network interface "{{ $labels.device }}" changing its up status often on node-exporter {{ $labels.namespace }}/{{ $labels.pod }}
description: Network interface "{{ $labels.device }}" changing its up status
often on node-exporter {{ $labels.namespace }}/{{ $labels.pod }}
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/nodenetworkinterfaceflapping
summary: Network interface is often changing its status
expr: |
@@ -49,17 +53,21 @@ spec:
severity: warning
- name: kube-prometheus-node-recording.rules
rules:
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[3m])) BY (instance)
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[3m]))
BY (instance)
record: instance:node_cpu:rate:sum
- expr: sum(rate(node_network_receive_bytes_total[3m])) BY (instance)
record: instance:node_network_receive_bytes:rate:sum
- expr: sum(rate(node_network_transmit_bytes_total[3m])) BY (instance)
record: instance:node_network_transmit_bytes:rate:sum
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance)
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m]))
WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total)
BY (instance, cpu)) BY (instance)
record: instance:node_cpu:ratio
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m]))
record: cluster:node_cpu:sum_rate5m
- expr: cluster:node_cpu_seconds_total:rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu))
- expr: cluster:node_cpu_seconds_total:rate5m / count(sum(node_cpu_seconds_total)
BY (instance, cpu))
record: cluster:node_cpu:ratio
- name: kube-prometheus-general.rules
rules: