可观测平台-4.1: Web前端/后端/网关 告警配置参考

Copy code
groups:
- name: vuejs_frontend_performance_metrics
  rules:
  - record: vuejs_page_load_time
    expr: rate(page_load_time_seconds_sum{job="vuejs_frontend"}[5m]) / rate(page_load_time_seconds_count{job="vuejs_frontend"}[5m])

  - record: vuejs_fcp_time
    expr: rate(first_contentful_paint_seconds{job="vuejs_frontend"}[5m])

  - record: vuejs_fmp_time
    expr: rate(first_meaningful_paint_seconds{job="vuejs_frontend"}[5m])

  - record: vuejs_fid_time
    expr: rate(first_input_delay_seconds{job="vuejs_frontend"}[5m])

  - record: vuejs_cls_score
    expr: rate(cumulative_layout_shift_score{job="vuejs_frontend"}[5m])

groups:
- name: vuejs_frontend_alerts
  rules:
  - alert: HighPageLoadTime
    expr: vuejs_page_load_time > 3
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: "High page load time on Vue.js frontend"
      description: "Vue.js frontend is experiencing a high page load time."

  - alert: HighCLS
    expr: vuejs_cls_score > 0.1 # Adjust based on your UX requirements
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: "High Cumulative Layout Shift on Vue.js frontend"
      description: "Vue.js frontend is experiencing high cumulative layout shift, impacting user experience."

yamlCopy codegroups:
- name: nginx_metrics
  rules:
  - alert: HighRequestLatency
    expr: nginx_http_request_duration_seconds{job="nginx"} > 0.5
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: High request latency on Nginx
      description: "Nginx server {{ $labels.instance }} has a high request latency of more than 0.5 seconds."

  - alert: HighErrorRate
    expr: rate(nginx_http_requests_total{status=~"5.."}[2m]) / rate(nginx_http_requests_total[2m]) > 0.05
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: High error rate on Nginx
      description: "Nginx server {{ $labels.instance }} is experiencing a high error rate."

yamlCopy codegroups:
- name: nginx_alerts
  rules:
  - alert: NginxDown
    expr: up{job="nginx"} == 0
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "Nginx down"
      description: "Nginx server {{ $labels.instance }} is down."

  - alert: HighTraffic
    expr: sum(rate(nginx_http_requests_total[5m])) by (instance) > 1000
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: "High traffic on Nginx"
      description: "Nginx server {{ $labels.instance }} is experiencing high traffic."

groups:
- name: python_backend_metrics
  rules:
  - record: python_http_requests_duration_seconds
    expr: rate(python_http_requests_duration_seconds_sum{job="python_backend"}[5m]) / rate(python_http_requests_duration_seconds_count{job="python_backend"}[5m])

  - record: python_http_requests_total
    expr: sum(rate(http_requests_total{job="python_backend"}[5m])) by (method, endpoint)

  - record: python_memory_usage_bytes
    expr: process_resident_memory_bytes{job="python_backend"}

  - record: python_cpu_usage_percentage
    expr: rate(process_cpu_seconds_total{job="python_backend"}[5m])

groups:
- name: python_backend_alerts
  rules:
  - alert: HighResponseTime
    expr: python_http_requests_duration_seconds > 1
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: "High response time in Python backend"
      description: "Python backend service is experiencing a high response time."

  - alert: HighMemoryUsage
    expr: python_memory_usage_bytes > 500000000 # Adjust based on your environment
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "High memory usage in Python backend"
      description: "Python backend service is using high memory."

Copy code
groups:
- name: go_backend_metrics
  rules:
  - record: go_http_requests_duration_seconds
    expr: rate(go_http_requests_duration_seconds_sum{job="go_backend"}[5m]) / rate(go_http_requests_duration_seconds_count{job="go_backend"}[5m])

  - record: go_http_requests_total
    expr: sum(rate(http_requests_total{job="go_backend"}[5m])) by (method, handler)

  - record: go_memory_usage_bytes
    expr: go_memstats_alloc_bytes{job="go_backend"}

  - record: go_cpu_usage_percentage
    expr: rate(process_cpu_seconds_total{job="go_backend"}[5m])

  - record: go_goroutines
    expr: go_goroutines{job="go_backend"}

Copy code
groups:
- name: go_backend_alerts
  rules:
  - alert: HighResponseTime
    expr: go_http_requests_duration_seconds > 1
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: "High response time in Go backend"
      description: "Go backend service is experiencing a high response time."

  - alert: HighMemoryUsage
    expr: go_memory_usage_bytes > 500000000 # Adjust based on your environment
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "High memory usage in Go backend"
      description: "Go backend service is using high memory."

Copy code
groups:
- name: java_backend_metrics
  rules:
  - record: java_http_requests_duration_seconds
    expr: rate(java_http_requests_duration_seconds_sum{job="java_backend"}[5m]) / rate(java_http_requests_duration_seconds_count{job="java_backend"}[5m])

  - record: java_http_requests_total
    expr: sum(rate(http_requests_total{job="java_backend"}[5m])) by (method, uri)

  - record: java_jvm_memory_usage
    expr: jvm_memory_used_bytes{job="java_backend"}

  - record: java_gc_duration_seconds
    expr: rate(jvm_gc_pause_seconds_sum{job="java_backend"}[5m])