Feat metrics (#2429)

* feat: register and alert

* feat: grafana

config/alertmanager.yml

@@ -11,11 +11,20 @@ templates:
   - /etc/alertmanager/email.tmpl
 
 route:
-  group_by: ['alertname']
+  group_by: [ 'alertname' ]
   group_wait: 5s
   group_interval: 5s
   repeat_interval: 5m
   receiver: email
+  routes:
+    - matchers:
+        - alertname = "XXX"
+      group_by: [ 'instance' ]
+      group_wait: 5s
+      group_interval: 5s
+      repeat_interval: 5m
+      receiver: email
+
 receivers:
   - name: email
     email_configs:

config/instance-down-rules.yml

@@ -20,3 +20,25 @@ groups:
         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."
+
+  - name: registrations_few
+    rules:
+      - alert: RegistrationsFew
+        expr: increase(user_login_total[1h]) == 0
+        for: 1m
+        labels:
+          severity: info
+        annotations:
+          summary: "Too few registrations within the time frame"
+          description: "The number of registrations in the last hour is 0. There might be some issues."
+
+  - name: messages_few
+    rules:
+      - alert: MessagesFew
+        expr: (increase(single_chat_msg_process_success_total[1h])+increase(group_chat_msg_process_success_total[1h])) == 0
+        for: 1m
+        labels:
+          severity: info
+        annotations:
+          summary: "Too few messages within the time frame"
+          description: "The number of messages sent in the last hour is 0. There might be some issues."

internal/rpc/user/user.go

@@ -19,6 +19,7 @@ import (
 	"errors"
 	"github.com/openimsdk/open-im-server/v3/internal/rpc/friend"
 	"github.com/openimsdk/open-im-server/v3/pkg/common/config"
+	"github.com/openimsdk/open-im-server/v3/pkg/common/prommetrics"
 	"github.com/openimsdk/open-im-server/v3/pkg/common/storage/cache"
 	"github.com/openimsdk/open-im-server/v3/pkg/common/storage/cache/redis"
 	"github.com/openimsdk/open-im-server/v3/pkg/common/storage/database/mgo"
@@ -310,6 +311,8 @@ func (s *userServer) UserRegister(ctx context.Context, req *pbuser.UserRegisterR
 		return nil, err
 	}
 
+	prommetrics.UserRegisterCounter.Add(float64(len(users)))
+
 	s.webhookAfterUserRegister(ctx, &s.config.WebhooksConfig.AfterUserRegister, req)
 	return resp, nil
 }

pkg/common/prommetrics/grpc_user.go

@@ -0,0 +1,10 @@
+package prommetrics
+
+import "github.com/prometheus/client_golang/prometheus"
+
+var (
+	UserRegisterCounter = prometheus.NewCounter(prometheus.CounterOpts{
+		Name: "user_register_total",
+		Help: "The number of user login",
+	})
+)

pkg/common/prommetrics/rpc.go

@@ -52,6 +52,8 @@ func GetGrpcCusMetrics(registerName string, share *config.Share) []prometheus.Co
 		return []prometheus.Collector{MsgOfflinePushFailedCounter}
 	case share.RpcRegisterName.Auth:
 		return []prometheus.Collector{UserLoginCounter}
+	case share.RpcRegisterName.User:
+		return []prometheus.Collector{UserRegisterCounter}
 	default:
 		return nil
 	}