服务监控

prometheus/prometheus/alert.rules

@@ -21,12 +21,51 @@ groups:
       summary: "Instance {{ $labels.instance }} under high load"
       description: "{{ $labels.instance }} of job {{ $labels.job }} is under high load."
 
-  - alert: curlHttpStatus
-    expr:  probe_http_status_code{job="test"}>=400 and probe_success{job="test"}==0
+  - alert: AMS接口服务异常
+    expr:  probe_http_status_code{job="ams_api"}>=400 and probe_success{job="ams_api"}==0
+    for: 2m
+    annotations:
+      summary: '业务报警: 健康检查异常'
+      description: '{{$labels.instance}} 不可访问,请及时查看,当前状态码为{{$value}}'
+
+  - alert: JAVA平台服务异常
+    expr:  probe_http_status_code{job="java-platform"}>=400 and probe_success{job="java-platform"}==0
+    for: 2m
+    annotations:
+      summary: '业务报警: 健康检查异常'
+      description: '{{$labels.instance}} 不可访问,请及时查看,当前状态码为{{$value}}'
+
+  - alert: JAVA投票服务异常
+    expr:  probe_http_status_code{job="java-vote"}>=400 and probe_success{job="java-vote"}==0
+    for: 2m
+    annotations:
+      summary: '业务报警: 健康检查异常'
+      description: '{{$labels.instance}} 不可访问,请及时查看,当前状态码为{{$value}}'
+
+  - alert: JAVA互动服务异常
+    expr:  probe_http_status_code{job="java-widget"}>=400 and probe_success{job="java-widget"}==0
+    for: 2m
+    annotations:
+      summary: '业务报警: 健康检查异常'
+      description: '{{$labels.instance}} 不可访问,请及时查看,当前状态码为{{$value}}'
+
+  - alert: JAVA答题服务异常
+    expr:  probe_http_status_code{job="java-question"}>=400 and probe_success{job="java-question"}==0
+    for: 2m
+    annotations:
+      summary: '业务报警: 健康检查异常'
+      description: '{{$labels.instance}} 不可访问,请及时查看,当前状态码为{{$value}}'
+
+  - alert: JAVA网关服务异常
+    expr:  probe_http_status_code{job="java-gateway"}>=400 and probe_success{job="java-gateway"}==0
     for: 2m
-    labels:
-      docker: number
     annotations:
-      summary: '业务报警: 链接不可访问'
+      summary: '业务报警: 健康检查异常'
       description: '{{$labels.instance}} 不可访问,请及时查看,当前状态码为{{$value}}'
 
+  - alert: JAVA小程序服务异常
+    expr:  probe_http_status_code{job="java-applet"}>=400 and probe_success{job="java-applet"}==0
+    for: 2m
+    annotations:
+      summary: '业务报警: 健康检查异常'
+      description: '{{$labels.instance}} 不可访问,请及时查看,当前状态码为{{$value}}'