Merge pull request 'feat: add service monitor and error alter integration guideline' (#114) from icecheng/feature into master

Reviewed-on: https://gitea.freeleaps.mathmast.com/freeleaps/freeleaps-ops/pulls/114
This commit is contained in:
icecheng 2025-09-23 09:36:24 +00:00
commit e929102d0b
3 changed files with 75 additions and 16 deletions

View File

@ -1,32 +1,91 @@
# Prometheus Alter Rule Config
# 1. Prometheus Alert Rule Configuration
Add `prometheusrule.yaml` to `<helm-pkg>/templates`.
see
```
## 1.1. Add `prometheusrule.yaml` to `<helm-pkg>/templates`.
Example:
> Update metrics to your service name, see freeleaps-ops/freeleaps/helm-pkg/metrics
```yaml
{{- /*
Copyright Broadcom, Inc. All Rights Reserved.
SPDX-License-Identifier: APACHE-2.0
*/}}
{{- if and .Values.metrics.enabled .Values.metrics.prometheusRule.enabled }}
{{- if .Values.metrics.prometheusRule.enabled }}
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: {{ include "common.names.fullname" . }}
namespace: {{ default (include "common.names.namespace" .) .Values.metrics.prometheusRule.namespace | quote}}
labels: {{- include "common.labels.standard" ( dict "customLabels" .Values.commonLabels "context" $ ) | nindent 4 }}
{{- if .Values.metrics.prometheusRule.additionalLabels }}
{{- include "common.tplvalues.render" (dict "value" .Values.metrics.prometheusRule.additionalLabels "context" $) | nindent 4 }}
{{- end }}
{{- if .Values.commonAnnotations }}
annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }}
name: {{ .Values.metrics.prometheusRule.name }}
namespace: {{ .Values.metrics.prometheusRule.namespace | quote }}
{{- with .Values.metrics.prometheusRule.labels }}
labels:
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
groups:
{{- with .Values.metrics.prometheusRule.rules }}
- name: {{ template "common.names.name" $ }}
rules: {{- include "common.tplvalues.render" (dict "value" . "context" $) | nindent 8 }}
- name: {{ $.Values.metrics.prometheusRule.name }}
rules:
{{- range . }}
- alert: {{ .alert }}
expr: {{ .expr | quote }}
{{- if .for }}
for: {{ .for }}
{{- end }}
{{- if .labels }}
labels:
{{- toYaml .labels | nindent 12 }}
{{- end }}
{{- if .annotations }}
annotations:
{{- toYaml .annotations | nindent 12 }}
{{- end }}
{{- end }}
{{- end }}
{{- end }}
```
```
## 1.2. Add prometheusrule configuration to values.{alpha/prod}.yaml
Example:
> See freeleaps-ops/freeleaps/helm-pkg/metrics
```yaml
prometheusRule:
name: freepeals-metrics
enabled: true
namespace: "freeleaps-monitoring-system"
labels:
release: kube-prometheus-stack
rules:
- alert: FreeleapsMetricsServiceDown
expr: up{job="metrics-service"} == 0
for: 1m
labels:
severity: critical
service: metrics-service
annotations:
summary: "Freeleaps Metrics service is down (instance {{ $labels.instance }})"
description: "Freeleaps Metrics service has been down for more than 1 minutes."
runbook_url: "https://netorgft10898514.sharepoint.com/:w:/s/FreeleapsEngineeringTeam/EUlvzumTsPxCpPAzI3gm9OIB0DCLTjQzzYVL6VsHYZFjxg?e=0dxVr7"
- alert: FreeleapsMetricsServiceHighErrorRate
expr: rate(http_requests_total{job="metrics-service",status=~"5.."}[5m]) > 0.1
for: 5m
labels:
severity: warning
service: metrics-service
annotations:
summary: "High error rate in freeleaps metrics service (instance {{ $labels.instance }})"
description: "Freeleaps Metrics service error rate is {{ $value }} errors per second."
runbook_url: "https://netorgft10898514.sharepoint.com/:w:/s/FreeleapsEngineeringTeam/EUlvzumTsPxCpPAzI3gm9OIB0DCLTjQzzYVL6VsHYZFjxg?e=0dxVr7"
```
## 1.3. Verify Alert Rule Configuration is Effective
> Redirect to local
![alt text](asserts/image4.png)
> You can see the newly added rules indicating they are effective
![alt text](asserts/image5.png)

BIN
docs/asserts/image4.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 569 KiB

BIN
docs/asserts/image5.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 341 KiB