Feature middleware (#1476)

* fix:fix error values&logs

* modify: add logs

* feature:add redis io retry logic

* feature:add redis error alert rule

* test:for test alert

* fix:fix prometheus rules

* del:del test code

---------

Co-authored-by: lin.huang <lin.huang@apulis.com>

config/instance-down-rules.yml

@@ -8,4 +8,15 @@ groups:
           severity: critical
         annotations:
           summary: "Instance {{ $labels.instance }} down"
-          description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 1 minutes."
+          description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 1 minutes."
+
+  - name: database_insert_failure_alerts
+    rules:
+      - alert: DatabaseInsertFailed
+        expr: (increase(msg_insert_redis_failed_total[5m]) > 0) or (increase(msg_insert_mongo_failed_total[5m]) > 0)
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Increase in MsgInsertRedisFailedCounter or MsgInsertMongoFailedCounter detected"
+          description: "Either MsgInsertRedisFailedCounter or MsgInsertMongoFailedCounter has increased in the last 5 minutes, indicating failures in message insert operations to Redis or MongoDB,maybe the redis or mongodb is crash."