feat: new features merged

.env

@@ -5,6 +5,9 @@ ZOOKEEPER_IMAGE=bitnami/zookeeper:3.8
 KAFKA_IMAGE=bitnami/kafka:3.5.1
 MINIO_IMAGE=minio/minio:RELEASE.2024-01-11T07-46-16Z
 ETCD_IMAGE=quay.io/coreos/etcd:v3.5.13
+PROMETHEUS_IMAGE=prom/prometheus:v2.45.6
+ALERTMANAGER_IMAGE=prom/alertmanager:v0.27.0
+GRAFANA_IMAGE=grafana/grafana:11.0.1
 
 OPENIM_WEB_FRONT_IMAGE=openim/openim-web-front:release-v3.5.1
 OPENIM_ADMIN_FRONT_IMAGE=openim/openim-admin-front:release-v1.7

.gitignore

@@ -34,11 +34,7 @@ deployments/charts/generated-configs/
 ### OpenIM Config ###
 .env
 config/config.yaml
-config/alertmanager.yml
-config/prometheus.yml
-config/email.tmpl
 config/notification.yaml
-config/instance-down-rules.yml
 
 ### OpenIM deploy ###
 deployments/openim-server/charts

cmd/openim-api/main.go

@@ -25,5 +25,4 @@ func main() {
 	if err := cmd.NewApiCmd().Exec(); err != nil {
 		program.ExitWithError(err)
 	}
-
 }

config/alertmanager.yml

@@ -0,0 +1,25 @@
+global:
+  resolve_timeout: 5m
+  smtp_from: alert@openim.io
+  smtp_smarthost: smtp.163.com:465
+  smtp_auth_username: alert@openim.io
+  smtp_auth_password: YOURAUTHPASSWORD
+  smtp_require_tls: false
+  smtp_hello: xxx
+
+templates:
+  - /etc/alertmanager/email.tmpl
+
+route:
+  group_by: ['alertname']
+  group_wait: 5s
+  group_interval: 5s
+  repeat_interval: 5m
+  receiver: email
+receivers:
+  - name: email
+    email_configs:
+      - to: 'alert@example.com'
+        html: '{{ template "email.to.html" . }}'
+        headers: { Subject: "[OPENIM-SERVER]Alarm" }
+        send_resolved: true

config/email.tmpl

@@ -0,0 +1,16 @@
+{{ define "email.to.html" }}
+{{ range .Alerts }}
+<!-- Begin of OpenIM Alert -->
+<div style="border:1px solid #ccc; padding:10px; margin-bottom:10px;">
+    <h3>OpenIM Alert</h3>
+    <p><strong>Alert Program:</strong> Prometheus Alert</p>
+    <p><strong>Severity Level:</strong> {{ .Labels.severity }}</p>
+    <p><strong>Alert Type:</strong> {{ .Labels.alertname }}</p>
+    <p><strong>Affected Host:</strong> {{ .Labels.instance }}</p>
+    <p><strong>Affected Service:</strong> {{ .Labels.job }}</p>
+    <p><strong>Alert Subject:</strong> {{ .Annotations.summary }}</p>
+    <p><strong>Trigger Time:</strong> {{ .StartsAt.Format "2006-01-02 15:04:05" }}</p>
+</div>
+<!-- End of OpenIM Alert -->
+{{ end }}
+{{ end }}

config/instance-down-rules.yml

@@ -0,0 +1,22 @@
+groups:
+  - name: instance_down
+    rules:
+      - alert: InstanceDown
+        expr: up == 0
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Instance {{ $labels.instance }} down"
+          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."

config/openim-crontask.yml

@@ -1,2 +1,3 @@
-chatRecordsClearTime: "0 2 * * *"
+cronExecuteTime: "0 2 * * *"
 retainChatRecords: 365
+fileExpireTime: 90

config/prometheus.yml

@@ -0,0 +1,83 @@
+# my global config
+global:
+  scrape_interval:     15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
+  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
+  # scrape_timeout is set to the global default (10s).
+
+# Alertmanager configuration
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets: ['192.168.2.22:19093']
+
+# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
+rule_files:
+  - "instance-down-rules.yml"
+# - "first_rules.yml"
+# - "second_rules.yml"
+
+# A scrape configuration containing exactly one endpoint to scrape:
+# Here it's Prometheus itself.
+scrape_configs:
+  # The job name is added as a label "job='job_name'"" to any timeseries scraped from this config.
+  # Monitored information captured by prometheus
+
+  # prometheus fetches application services
+  - job_name: 'node_exporter'
+    static_configs:
+      - targets: [ '192.168.2.22:20114' ]
+  - job_name: 'openimserver-openim-api'
+    static_configs:
+      - targets: [ '192.168.2.22:20113' ]
+        labels:
+          namespace: 'default'
+  - job_name: 'openimserver-openim-msggateway'
+    static_configs:
+      - targets: [ '192.168.2.22:20112' ]
+        labels:
+          namespace: 'default'
+  - job_name: 'openimserver-openim-msgtransfer'
+    static_configs:
+      - targets: [ 192.168.2.22:20111, 192.168.2.22:20110, 192.168.2.22:20109, 192.168.2.22:20108 ]
+        labels:
+          namespace: 'default'
+  - job_name: 'openimserver-openim-push'
+    static_configs:
+      - targets: [ '192.168.2.22:20107' ]
+        labels:
+          namespace: 'default'
+  - job_name: 'openimserver-openim-rpc-auth'
+    static_configs:
+      - targets: [ '192.168.2.22:20106' ]
+        labels:
+          namespace: 'default'
+  - job_name: 'openimserver-openim-rpc-conversation'
+    static_configs:
+      - targets: [ '192.168.2.22:20105' ]
+        labels:
+          namespace: 'default'
+  - job_name: 'openimserver-openim-rpc-friend'
+    static_configs:
+      - targets: [ '192.168.2.22:20104' ]
+        labels:
+          namespace: 'default'
+  - job_name: 'openimserver-openim-rpc-group'
+    static_configs:
+      - targets: [ '192.168.2.22:20103' ]
+        labels:
+          namespace: 'default'
+  - job_name: 'openimserver-openim-rpc-msg'
+    static_configs:
+      - targets: [ '192.168.2.22:20102' ]
+        labels:
+          namespace: 'default'
+  - job_name: 'openimserver-openim-rpc-third'
+    static_configs:
+      - targets: [ '192.168.2.22:20101' ]
+        labels:
+          namespace: 'default'
+  - job_name: 'openimserver-openim-rpc-user'
+    static_configs:
+      - targets: [ '192.168.2.22:20100' ]
+        labels:
+          namespace: 'default'

docker-compose.yml

@@ -140,5 +140,50 @@ services:
     networks:
       - openim
 
+  prometheus:
+    image: ${PROMETHEUS_IMAGE}
+    container_name: prometheus
+    restart: always
+    volumes:
+      - ./config/prometheus.yml:/etc/prometheus/prometheus.yml
+      - ./config/instance-down-rules.yml:/etc/prometheus/instance-down-rules.yml
+      - ${DATA_DIR}/components/prometheus/data:/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+    ports:
+      - "19091:9090"
+    networks:
+      - openim
+
+  alertmanager:
+    image: ${ALERTMANAGER_IMAGE}
+    container_name: alertmanager
+    restart: always
+    volumes:
+      - ./config/alertmanager.yml:/etc/alertmanager/alertmanager.yml
+      - ./config/email.tmpl:/etc/alertmanager/email.tmpl
+    ports:
+      - "19093:9093"
+    networks:
+      - openim
+
+  grafana:
+    image: ${GRAFANA_IMAGE}
+    container_name: grafana
+    user: root
+    restart: always
+    environment:
+      - GF_SECURITY_ALLOW_EMBEDDING=true
+      - GF_SESSION_COOKIE_SAMESITE=none
+      - GF_SESSION_COOKIE_SECURE=true
+      - GF_AUTH_ANONYMOUS_ENABLED=true
+      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
+    ports:
+      - "13000:3000"
+    volumes:
+      - ${DATA_DIR:-./}/components/grafana:/var/lib/grafana
+    networks:
+      - openim
 
 

go.mod

@@ -13,7 +13,7 @@ require (
 	github.com/grpc-ecosystem/go-grpc-prometheus v1.2.0
 	github.com/mitchellh/mapstructure v1.5.0
 	github.com/openimsdk/protocol v0.0.69-alpha.30
-	github.com/openimsdk/tools v0.0.49-alpha.49
+	github.com/openimsdk/tools v0.0.49-alpha.50
 	github.com/pkg/errors v0.9.1 // indirect
 	github.com/prometheus/client_golang v1.18.0
 	github.com/stretchr/testify v1.9.0
@@ -194,5 +194,3 @@ require (
 	golang.org/x/crypto v0.21.0 // indirect
 	gopkg.in/ini.v1 v1.67.0 // indirect
 )
-
-//replace github.com/openimsdk/protocol => /Users/chao/Desktop/project/protocol

go.sum

@@ -313,8 +313,8 @@ github.com/openimsdk/gomake v0.0.14-alpha.5 h1:VY9c5x515lTfmdhhPjMvR3BBRrRquAUCF
 github.com/openimsdk/gomake v0.0.14-alpha.5/go.mod h1:PndCozNc2IsQIciyn9mvEblYWZwJmAI+06z94EY+csI=
 github.com/openimsdk/protocol v0.0.69-alpha.30 h1:OXzCIpDpIY/GI6h1SDYWN51OS9Xv/BcHaOwq8whPKqI=
 github.com/openimsdk/protocol v0.0.69-alpha.30/go.mod h1:OZQA9FR55lseYoN2Ql1XAHYKHJGu7OMNkUbuekrKCM8=
-github.com/openimsdk/tools v0.0.49-alpha.49 h1:bkVxlEDM9rJxo5a98mk2ETR0xbEv+5mjeVVVFQfARAQ=
-github.com/openimsdk/tools v0.0.49-alpha.49/go.mod h1:HtSRjPTL8PsuZ+PhR5noqzrYBF0sdwW3/O/sWVucWg8=
+github.com/openimsdk/tools v0.0.49-alpha.50 h1:7CaYLVtsBU5kyiTetUOuOkO5FFFmMvSzBEfh2tfCn90=
+github.com/openimsdk/tools v0.0.49-alpha.50/go.mod h1:HtSRjPTL8PsuZ+PhR5noqzrYBF0sdwW3/O/sWVucWg8=
 github.com/pelletier/go-toml/v2 v2.1.0 h1:FnwAJ4oYMvbT/34k9zzHuZNrhlz48GB3/s6at6/MHO4=
 github.com/pelletier/go-toml/v2 v2.1.0/go.mod h1:tJU2Z3ZkXwnxa4DPO899bsyIoywizdUvyaeZurnPPDc=
 github.com/pierrec/lz4/v4 v4.1.21 h1:yOVMLb6qSIDP67pl/5F7RepeKYu/VmTyEXvuMI5d9mQ=

internal/api/friend.go

@@ -58,7 +58,6 @@ func (o *FriendApi) GetFriendList(c *gin.Context) {
 
 func (o *FriendApi) GetDesignatedFriends(c *gin.Context) {
 	a2r.Call(relation.FriendClient.GetDesignatedFriends, o.Client, c)
-	//a2r.Call(relation.FriendClient.GetDesignatedFriends, o.Client, c, a2r.NewNilReplaceOption(relation.FriendClient.GetDesignatedFriends))
 }
 
 func (o *FriendApi) SetFriendRemark(c *gin.Context) {

internal/api/init.go

@@ -29,7 +29,6 @@ import (
 	"time"
 
 	kdisc "github.com/openimsdk/open-im-server/v3/pkg/common/discoveryregister"
-	ginprom "github.com/openimsdk/open-im-server/v3/pkg/common/ginprometheus"
 	"github.com/openimsdk/open-im-server/v3/pkg/common/prommetrics"
 	"github.com/openimsdk/tools/discovery"
 	"github.com/openimsdk/tools/errs"
@@ -72,10 +71,8 @@ func Start(ctx context.Context, index int, config *Config) error {
 				netDone <- struct{}{}
 				return
 			}
-			p := ginprom.NewPrometheus("app", prommetrics.GetGinCusMetrics("Api"))
-			p.SetListenAddress(fmt.Sprintf(":%d", prometheusPort))
-			if err = p.Use(router); err != nil && err != http.ErrServerClosed {
-				netErr = errs.WrapMsg(err, fmt.Sprintf("prometheus start err: %d", prometheusPort))
+			if err := prommetrics.ApiInit(prometheusPort); err != nil && err != http.ErrServerClosed {
+				netErr = errs.WrapMsg(err, fmt.Sprintf("api prometheus start err: %d", prometheusPort))
 				netDone <- struct{}{}
 			}
 		}()

internal/api/router.go

@@ -2,24 +2,39 @@ package api
 
 import (
 	"fmt"
-	"net/http"
-	"strings"
-
 	"github.com/gin-gonic/gin"
 	"github.com/gin-gonic/gin/binding"
 	"github.com/go-playground/validator/v10"
 	"google.golang.org/grpc"
 	"google.golang.org/grpc/credentials/insecure"
 
+	"github.com/openimsdk/open-im-server/v3/pkg/common/prommetrics"
 	"github.com/openimsdk/open-im-server/v3/pkg/common/servererrs"
 	"github.com/openimsdk/open-im-server/v3/pkg/rpcclient"
 	"github.com/openimsdk/protocol/constant"
 	"github.com/openimsdk/tools/apiresp"
 	"github.com/openimsdk/tools/discovery"
 	"github.com/openimsdk/tools/log"
 	"github.com/openimsdk/tools/mw"
+	"net/http"
+	"strings"
 )
 
+func prommetricsGin() gin.HandlerFunc {
+	return func(c *gin.Context) {
+		c.Next()
+		path := c.FullPath()
+		if c.Writer.Status() == http.StatusNotFound {
+			prommetrics.HttpCall("<404>", c.Request.Method, c.Writer.Status())
+		} else {
+			prommetrics.HttpCall(path, c.Request.Method, c.Writer.Status())
+		}
+		if resp := apiresp.GetGinApiResponse(c); resp != nil {
+			prommetrics.APICall(path, c.Request.Method, resp.ErrCode)
+		}
+	}
+}
+
 func newGinRouter(disCov discovery.SvcDiscoveryRegistry, config *Config) *gin.Engine {
 	disCov.AddOption(mw.GrpcClient(), grpc.WithTransportCredentials(insecure.NewCredentials()),
 		grpc.WithDefaultServiceConfig(fmt.Sprintf(`{"LoadBalancingPolicy": "%s"}`, "round_robin")))
@@ -38,7 +53,7 @@ func newGinRouter(disCov discovery.SvcDiscoveryRegistry, config *Config) *gin.En
 	authRpc := rpcclient.NewAuth(disCov, config.Share.RpcRegisterName.Auth)
 	thirdRpc := rpcclient.NewThird(disCov, config.Share.RpcRegisterName.Third, config.API.Prometheus.GrafanaURL)
 
-	r.Use(gin.Recovery(), mw.CorsHandler(), mw.GinParseOperationID(), GinParseToken(authRpc))
+	r.Use(prommetricsGin(), gin.Recovery(), mw.CorsHandler(), mw.GinParseOperationID(), GinParseToken(authRpc))
 	u := NewUserApi(*userRpc)
 	m := NewMessageApi(messageRpc, userRpc, config.Share.IMAdminUserID)
 	userRouterGroup := r.Group("/user")

internal/msggateway/client.go

@@ -75,6 +75,8 @@ type Client struct {
 	token          string
 	hbCtx          context.Context
 	hbCancel       context.CancelFunc
+	subLock        sync.Mutex
+	subUserIDs     map[string]struct{}
 }
 
 // ResetClient updates the client's state with new connection and context information.
@@ -216,6 +218,8 @@ func (c *Client) handleMessage(message []byte) error {
 		resp, messageErr = c.longConnServer.UserLogout(ctx, binaryReq)
 	case WsSetBackgroundStatus:
 		resp, messageErr = c.setAppBackgroundStatus(ctx, binaryReq)
+	case WsSubUserOnlineStatus:
+		resp, messageErr = c.longConnServer.SubUserOnlineStatus(ctx, c, binaryReq)
 	default:
 		return fmt.Errorf(
 			"ReqIdentifier failed,sendID:%s,msgIncr:%s,reqIdentifier:%d",

internal/msggateway/compressor_test.go

@@ -16,10 +16,10 @@ package msggateway
 
 import (
 	"crypto/rand"
+	"github.com/stretchr/testify/assert"
 	"sync"
 	"testing"
-
-	"github.com/stretchr/testify/assert"
+	"unsafe"
 )
 
 func mockRandom() []byte {
@@ -132,3 +132,8 @@ func BenchmarkDecompressWithSyncPool(b *testing.B) {
 		assert.Equal(b, nil, err)
 	}
 }
+
+func TestName(t *testing.T) {
+	t.Log(unsafe.Sizeof(Client{}))
+
+}

internal/msggateway/constant.go

@@ -43,6 +43,7 @@ const (
 	WSKickOnlineMsg       = 2002
 	WsLogoutMsg           = 2003
 	WsSetBackgroundStatus = 2004
+	WsSubUserOnlineStatus = 2005
 	WSDataError           = 3001
 )