This commit is contained in:
Nicolas 2025-09-22 16:54:13 +08:00
commit b3ef716dde
11 changed files with 1017 additions and 5 deletions

View File

@ -0,0 +1,72 @@
# 1. 服务提供Metrics接口
在`webapi/providers`目录下创建一个`metrics.py`文件用于提供Metrics接口。
内容如下
```
def register(app):
instrumentator = (
Instrumentator().instrument(
app,
metric_namespace="freeleaps-mertics",
metric_subsystem=app_settings.APP_NAME)
)
@app.on_event("startup")
async def startup():
instrumentator.expose(app, endpoint="/api/_/metrics", should_gzip=True)
logging.info("Metrics endpoint exposed at /api/_/metrics")
```
参考https://gitea.freeleaps.mathmast.com/freeleaps/freeleaps-service-hub/src/branch/master/apps/metrics的接入方式
# 2. 配置Metrics采集
## 2.1. 找到helm pkg目录
对于freeleaps内部服务而言,你需要在freeleaps-ops仓库下找到该服务部署的helm-package配置
> 比如metrics服务他的配置在`https://gitea.freeleaps.mathmast.com/freeleaps/freeleaps-ops/src/branch/master/freeleaps/helm-pkg/metrics`
对于freeleaps租户服务而言(通过one-click部署),你需要在对应服务仓库下找到`.freeleas/devops/helm-pkg`
> 比如magicleaps服务他的配置在`https://gitea.freeleaps.mathmast.com/products/magicleaps/src/branch/main/.freeleaps/devops/helm-pkg`
## 2.2. 新增新增servicemonitor配置
在templates文件夹下新增`servicemonitor.yaml`文件,内容如下,内容参考`https://gitea.freeleaps.mathmast.com/freeleaps/freeleaps-ops/src/branch/master/freeleaps/helm-pkg/notification/templates/notification/servicemonitor.yaml`
根据value.yaml中的配置更新必要内容比如第6行从notification修改为metrics
## 2.3. 修改value.{alpha|prod}.yaml
新增serviceMonitor配置参考`https://gitea.freeleaps.mathmast.com/freeleaps/freeleaps-ops/src/branch/master/freeleaps/helm-pkg/notification/values.prod.yaml`
```
- name: notification-service
type: ClusterIP
port: 8003
targetPort: 8003
serviceMonitor:
enabled: true # alpha环境设置为false
labels:
release: kube-prometheus-stack
namespace: freeleaps-monitoring-system
internal: 30s
scrapeTimeout: ''
```
# 3. 配置Grafanana Dashboard
## 2.1. 在helm-pkg下新增`dashboard.yaml`
内容参考`https://gitea.freeleaps.mathmast.com/freeleaps/freeleaps-ops/src/branch/master/freeleaps/helm-pkg/notification/templates/notification/dashboard.yaml`
## 2.2. 修改value.{alpha|prod}.yaml
```yaml
dashboard:
enabled: true # alphah环境设置为false
name: freeleaps-prod-metrics-dashboard
title: Freeleaps Metrics Dashboard (PROD/ALPHA)
metricsPrefix: freeleaps_metrics
```

View File

@ -18,7 +18,7 @@ authentication:
registry: docker.io
repository: null
name: authentication
tag: snapshot-6d72fef
tag: snapshot-7b7c9ca
imagePullPolicy: IfNotPresent
ports:
- name: http

View File

@ -18,7 +18,7 @@ centralStorage:
registry: docker.io
repository: null
name: central_storage
tag: snapshot-6d72fef
tag: 1.8.0
imagePullPolicy: IfNotPresent
ports:
- name: http

View File

@ -15,7 +15,7 @@ content:
registry: docker.io
repository: null
name: content
tag: snapshot-77d0a9c
tag: snapshot-74d9550
imagePullPolicy: IfNotPresent
ports:
- name: http

View File

@ -0,0 +1,865 @@
{{- if .Values.dashboard.enabled }}
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ .Values.dashboard.name }}
namespace: {{ .Values.dashboard.namespace }}
labels:
grafana_dashboard: "1"
data:
{{ .Values.dashboard.name }}.json: |
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "datasource",
"uid": "grafana"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": 36,
"links": [],
"panels": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 9,
"x": 0,
"y": 0
},
"id": 2,
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull",
"max",
"min"
],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "11.5.2",
"targets": [
{
"$$hashKey": "object:214",
"datasource": {
"type": "prometheus",
"uid": "e4584a9f-5364-4b3d-a851-7abbc5250820"
},
"editorMode": "code",
"expr": "increase({{ .Values.dashboard.metricsPrefix }}_http_requests_total[1m])",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{ `{{ method }} {{ handler }}` }}",
"range": true,
"refId": "A"
}
],
"title": "Total requests per minute",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "bars",
"fillOpacity": 100,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "short"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "4xx"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "red",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "HTTP 500"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#bf1b00",
"mode": "fixed"
}
}
]
}
]
},
"gridPos": {
"h": 7,
"w": 10,
"x": 9,
"y": 0
},
"id": 13,
"options": {
"legend": {
"calcs": [
"mean",
"max"
],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "11.5.2",
"targets": [
{
"$$hashKey": "object:140",
"datasource": {
"type": "prometheus",
"uid": "e4584a9f-5364-4b3d-a851-7abbc5250820"
},
"editorMode": "code",
"expr": "sum by (status) (rate({{ .Values.dashboard.metricsPrefix }}_http_requests_total[1m]))",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{ `{{ status }}` }}",
"range": true,
"refId": "A"
}
],
"title": "Request per minute",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "short"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "errors"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#c15c17",
"mode": "fixed"
}
}
]
}
]
},
"gridPos": {
"h": 7,
"w": 5,
"x": 19,
"y": 0
},
"id": 4,
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull",
"max"
],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "11.5.2",
"targets": [
{
"$$hashKey": "object:766",
"datasource": {
"type": "prometheus",
"uid": "e4584a9f-5364-4b3d-a851-7abbc5250820"
},
"editorMode": "code",
"expr": "sum(rate({{ .Values.dashboard.metricsPrefix }}_http_requests_total{status=\"5xx\"}[1m]))",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "errors",
"range": true,
"refId": "A"
}
],
"title": "Errors per second",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "smooth",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 9,
"x": 0,
"y": 7
},
"id": 6,
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull",
"max",
"min"
],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "11.5.2",
"targets": [
{
"$$hashKey": "object:146",
"datasource": {
"type": "prometheus",
"uid": "e4584a9f-5364-4b3d-a851-7abbc5250820"
},
"editorMode": "code",
"expr": "{{ .Values.dashboard.metricsPrefix }}_http_request_duration_seconds_sum{handler!=\"none\"} / {{ .Values.dashboard.metricsPrefix }}_http_request_duration_seconds_count",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{ `{{ handler }}` }}",
"range": true,
"refId": "A"
}
],
"title": "Average response time",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"max": 1,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percentunit"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "none"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "red",
"mode": "fixed"
}
}
]
}
]
},
"gridPos": {
"h": 8,
"w": 10,
"x": 9,
"y": 7
},
"id": 11,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "11.5.2",
"targets": [
{
"$$hashKey": "object:1079",
"datasource": {
"type": "prometheus",
"uid": "e4584a9f-5364-4b3d-a851-7abbc5250820"
},
"editorMode": "code",
"expr": "increase({{ .Values.dashboard.metricsPrefix }}_http_request_duration_seconds_bucket{le=\"0.1\"}[1m]) \n/ ignoring (le) increase({{ .Values.dashboard.metricsPrefix }}_http_request_duration_seconds_count[1m])",
"format": "time_series",
"instant": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{ `{{ handler }}` }}",
"refId": "A"
}
],
"title": "Requests under 100ms",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "line+area"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "transparent",
"value": null
},
{
"color": "red",
"value": 0
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 9,
"x": 0,
"y": 15
},
"id": 16,
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull",
"max",
"min"
],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "11.5.2",
"targets": [
{
"$$hashKey": "object:426",
"datasource": {
"type": "prometheus",
"uid": "e4584a9f-5364-4b3d-a851-7abbc5250820"
},
"editorMode": "code",
"expr": "histogram_quantile(0.9, rate({{ .Values.dashboard.metricsPrefix }}_http_request_duration_seconds_bucket{handler!=\"none\"}[1m]))",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{ `{{ handler }}` }}",
"range": true,
"refId": "A"
}
],
"title": "Request duration [s] - p90",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 25,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 10,
"x": 9,
"y": 15
},
"id": 15,
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull",
"max",
"min"
],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "11.5.2",
"targets": [
{
"$$hashKey": "object:426",
"datasource": {
"type": "prometheus",
"uid": "e4584a9f-5364-4b3d-a851-7abbc5250820"
},
"editorMode": "code",
"expr": "histogram_quantile(0.5, rate({{ .Values.dashboard.metricsPrefix }}_http_request_duration_seconds_bucket{handler!=\"none\"}[1m]))",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{ `{{ handler }}` }}",
"range": true,
"refId": "A"
}
],
"title": "Request duration [s] - p50",
"type": "timeseries"
}
],
"preload": false,
"refresh": "5s",
"schemaVersion": 40,
"tags": ["freeleaps"],
"templating": {
"list": []
},
"time": {
"from": "now-5m",
"to": "now"
},
"timepicker": {
"refresh_intervals": []
},
"timezone": "",
"title": "{{ .Values.dashboard.title }}",
"uid": "",
"version": 11,
"weekStart": ""
}
{{- end }}

View File

@ -0,0 +1,40 @@
{{ $namespace := .Release.Namespace }}
{{ $appVersion := .Chart.AppVersion | quote }}
{{ $releaseService := .Release.Service }}
{{ $releaseName := .Release.Name }}
{{- range $service := .Values.metrics.services }}
{{- if $service.serviceMonitor.enabled }}
---
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
name: {{ $service.name }}-monitor
namespace: {{ $service.serviceMonitor.namespace }}
labels:
app.kubernetes.io/version: {{ $appVersion }}
app.kubernetes.io/name: {{ $service.name }}-monitor
app.kubernetes.io/managed-by: {{ $releaseService }}
app.kubernetes.io/instance: {{ $releaseName }}
{{- if $service.serviceMonitor.labels }}
{{- toYaml $service.serviceMonitor.labels | nindent 4 }}
{{- end }}
spec:
endpoints:
- path: /api/_/metrics
targetPort: {{ $service.targetPort }}
{{- if $service.serviceMonitor.interval }}
interval: {{ $service.serviceMonitor.interval }}
{{- end }}
{{- if $service.serviceMonitor.scrapeTimeout }}
scrapeTimeout: {{ $service.serviceMonitor.scrapeTimeout }}
{{- end }}
namespaceSelector:
matchNames:
- {{ $namespace | quote }}
selector:
matchLabels:
app.kubernetes.io/name: {{ $service.name }}
app.kubernetes.io/instance: {{ $releaseName }}
{{- end }}
{{- end }}

View File

@ -4,6 +4,11 @@ global:
nodeSelector: {}
logIngest:
enabled: false
dashboard:
enabled: true
name: freeleaps-prod-metrics-dashboard
title: Freeleaps Metrics Dashboard (ALPHA)
metricsPrefix: freeleaps_metrics
metrics:
replicas: 1
image:
@ -50,6 +55,13 @@ metrics:
type: ClusterIP
port: 8009
targetPort: 8009
serviceMonitor:
enabled: true
labels:
release: kube-prometheus-stack
namespace: freeleaps-monitoring-system
internal: 30s
scrapeTimeout: ''
configs:
starrocksHost: freeleaps-starrocks-cluster-fe-service.freeleaps-data-platform.svc
starrocksPort: 9030

View File

@ -4,6 +4,11 @@ global:
nodeSelector: {}
logIngest:
enabled: false
dashboard:
enabled: false
name: freeleaps-prod-metrics-dashboard
title: Freeleaps Metrics Dashboard (PROD)
metricsPrefix: freeleaps_metrics
metrics:
replicas: 1
image:
@ -50,6 +55,13 @@ metrics:
type: ClusterIP
port: 8009
targetPort: 8009
serviceMonitor:
enabled: false
labels:
release: kube-prometheus-stack
namespace: freeleaps-monitoring-system
internal: 30s
scrapeTimeout: ''
configs:
starrocksHost: freeleaps-starrocks-cluster-fe-service.freeleaps-data-platform.svc
starrocksPort: 9030

View File

@ -4,6 +4,10 @@ global:
nodeSelector: {}
logIngest:
enabled: false
dashboard:
enabled: false
name: freeleaps-prod-metrics-dashboard
title: Freeleaps Metrics Dashboard
metrics:
replicas: 1
image:
@ -50,6 +54,13 @@ metrics:
type: ClusterIP
port: 8009
targetPort: 8009
serviceMonitor:
enabled: false
labels:
release: kube-prometheus-stack
namespace: freeleaps-monitoring-system
internal: 30s
scrapeTimeout: ''
configs:
starrocksHost: ""
starrocksPort: 8009

View File

@ -15,7 +15,7 @@ notification:
registry: docker.io
repository: null
name: notification
tag: snapshot-77d0a9c
tag: snapshot-74d9550
imagePullPolicy: IfNotPresent
ports:
- name: http

View File

@ -15,7 +15,7 @@ payment:
registry: docker.io
repository: null
name: payment
tag: snapshot-77d0a9c
tag: snapshot-74d9550
imagePullPolicy: IfNotPresent
ports:
- name: http