refactor linux dashboard

etc/script/notify/notify.go

@@ -7,13 +7,6 @@ import (
 	"github.com/tidwall/gjson"
 )
 
-// the caller can be called for alerting notify by complete this interface
-type inter interface {
-	Descript() string
-	Notify([]byte)
-	NotifyMaintainer([]byte)
-}
-
 // N9E complete
 type N9EPlugin struct {
 	Name        string
@@ -41,13 +34,13 @@ func (n *N9EPlugin) Notify(bs []byte) {
 func (n *N9EPlugin) NotifyMaintainer(bs []byte) {
 	fmt.Println("do something... begin")
 	result := string(bs)
-	fmt.Println("%T",result)
+	fmt.Println(result)
 	fmt.Println("do something... end")
 }
 
 // will be loaded for alertingCall , The first letter must be capitalized to be exported
 var N9eCaller = N9EPlugin{
-	Name:        "n9e",
-	Description: "演示告警通过动态链接库方式通知",
+	Name:        "N9EPlugin",
+	Description: "Notify by lib",
 	BuildAt:     time.Now().Local().Format("2006/01/02 15:04:05"),
 }

src/models/board.go

@@ -71,6 +71,20 @@ func (b *Board) Del() error {
 	})
 }
 
+func BoardGetByID(id int64) (*Board, error) {
+	var lst []*Board
+	err := DB().Where("id = ?", id).Find(&lst).Error
+	if err != nil {
+		return nil, err
+	}
+
+	if len(lst) == 0 {
+		return nil, nil
+	}
+
+	return lst[0], nil
+}
+
 // BoardGet for detail page
 func BoardGet(where string, args ...interface{}) (*Board, error) {
 	var lst []*Board

src/models/user.go

@@ -450,6 +450,21 @@ func (u *User) BusiGroups(limit int, query string, all ...bool) ([]BusiGroup, er
 	var lst []BusiGroup
 	if u.IsAdmin() || (len(all) > 0 && all[0]) {
 		err := session.Where("name like ?", "%"+query+"%").Find(&lst).Error
+		if err != nil {
+			return lst, err
+		}
+
+		if len(lst) == 0 && len(query) > 0 {
+			// 隐藏功能，一般人不告诉，哈哈。query可能是给的ident，所以上面的sql没有查到，当做ident来查一下试试
+			var t *Target
+			t, err = TargetGet("ident=?", query)
+			if err != nil {
+				return lst, err
+			}
+
+			err = DB().Order("name").Limit(limit).Where("id=?", t.GroupId).Find(&lst).Error
+		}
+
 		return lst, err
 	}
 
@@ -468,6 +483,22 @@ func (u *User) BusiGroups(limit int, query string, all ...bool) ([]BusiGroup, er
 	}
 
 	err = session.Where("id in ?", busiGroupIds).Where("name like ?", "%"+query+"%").Find(&lst).Error
+	if err != nil {
+		return nil, err
+	}
+
+	if len(lst) == 0 && len(query) > 0 {
+		var t *Target
+		t, err = TargetGet("ident=?", query)
+		if err != nil {
+			return lst, err
+		}
+
+		if slice.ContainsInt64(busiGroupIds, t.GroupId) {
+			err = DB().Order("name").Limit(limit).Where("id=?", t.GroupId).Find(&lst).Error
+		}
+	}
+
 	return lst, err
 }
 

src/notifier/notifier.go

@@ -0,0 +1,9 @@
+package notifier
+
+type Notifier interface {
+	Descript() string
+	Notify([]byte)
+	NotifyMaintainer([]byte)
+}
+
+var Instance Notifier

src/server/config/config.go

@@ -2,8 +2,11 @@ package config
 
 import (
 	"fmt"
+	"log"
 	"net"
 	"os"
+	"plugin"
+	"runtime"
 	"strings"
 	"sync"
 	"time"
@@ -11,6 +14,7 @@ import (
 	"github.com/gin-gonic/gin"
 	"github.com/koding/multiconfig"
 
+	"github.com/didi/nightingale/v5/src/notifier"
 	"github.com/didi/nightingale/v5/src/pkg/httpx"
 	"github.com/didi/nightingale/v5/src/pkg/logx"
 	"github.com/didi/nightingale/v5/src/pkg/ormx"
@@ -100,6 +104,33 @@ func MustLoad(fpaths ...string) {
 			}
 		}
 
+		if C.Alerting.CallPlugin.Enable {
+			if runtime.GOOS == "windows" {
+				fmt.Println("notify plugin on unsupported os:", runtime.GOOS)
+				os.Exit(1)
+			}
+
+			p, err := plugin.Open(C.Alerting.CallPlugin.PluginPath)
+			if err != nil {
+				fmt.Println("failed to load plugin:", err)
+				os.Exit(1)
+			}
+
+			caller, err := p.Lookup(C.Alerting.CallPlugin.Caller)
+			if err != nil {
+				fmt.Println("failed to lookup plugin Caller:", err)
+				os.Exit(1)
+			}
+
+			ins, ok := caller.(notifier.Notifier)
+			if !ok {
+				log.Println("notifier interface not implemented")
+				os.Exit(1)
+			}
+
+			notifier.Instance = ins
+		}
+
 		if C.WriterOpt.QueueMaxSize <= 0 {
 			C.WriterOpt.QueueMaxSize = 100000
 		}

src/server/engine/mute.go

@@ -6,7 +6,7 @@ import (
 )
 
 // 如果传入了clock这个可选参数，就表示使用这个clock表示的时间，否则就从event的字段中取TriggerTime
-func isMuted(event *models.AlertCurEvent, clock ...int64) bool {
+func IsMuted(event *models.AlertCurEvent, clock ...int64) bool {
 	mutes, has := memsto.AlertMuteCache.Gets(event.GroupId)
 	if !has || len(mutes) == 0 {
 		return false

src/server/engine/notify.go

@@ -9,8 +9,6 @@ import (
 	"net/http"
 	"os/exec"
 	"path"
-	"plugin"
-	"runtime"
 	"strings"
 	"time"
 
@@ -22,6 +20,7 @@ import (
 	"github.com/toolkits/pkg/slice"
 
 	"github.com/didi/nightingale/v5/src/models"
+	"github.com/didi/nightingale/v5/src/notifier"
 	"github.com/didi/nightingale/v5/src/pkg/sys"
 	"github.com/didi/nightingale/v5/src/pkg/tplx"
 	"github.com/didi/nightingale/v5/src/server/common/sender"
@@ -103,7 +102,6 @@ func alertingRedisPub(bs []byte) {
 
 func handleNotice(notice Notice, bs []byte) {
 	alertingCallScript(bs)
-
 	alertingCallPlugin(bs)
 
 	if len(config.C.Alerting.NotifyBuiltinChannels) == 0 {
@@ -398,12 +396,6 @@ func alertingCallScript(stdinBytes []byte) {
 	logger.Infof("event_notify: exec %s output: %s", fpath, buf.String())
 }
 
-type Notifier interface {
-	Descript() string
-	Notify([]byte)
-	NotifyMaintainer([]byte)
-}
-
 // call notify.so via golang plugin build
 // ig. etc/script/notify/notify.so
 func alertingCallPlugin(stdinBytes []byte) {
@@ -411,26 +403,8 @@ func alertingCallPlugin(stdinBytes []byte) {
 		return
 	}
 
-	if runtime.GOOS == "windows" {
-		logger.Errorf("call notify plugin on unsupported os: %s", runtime.GOOS)
-		return
-	}
-
-	p, err := plugin.Open(config.C.Alerting.CallPlugin.PluginPath)
-	if err != nil {
-		logger.Errorf("failed to open notify plugin: %v", err)
-		return
-	}
-	caller, err := p.Lookup(config.C.Alerting.CallPlugin.Caller)
-	if err != nil {
-		logger.Errorf("failed to load caller: %v", err)
-		return
-	}
-	notifier, ok := caller.(Notifier)
-	if !ok {
-		logger.Errorf("notifier interface not implemented): %v", err)
-		return
-	}
-	notifier.Notify(stdinBytes)
-	logger.Debugf("alertingCallPlugin done. %s", notifier.Descript())
+	logger.Debugf("alertingCallPlugin begin")
+	logger.Debugf("payload:", string(stdinBytes))
+	notifier.Instance.Notify(stdinBytes)
+	logger.Debugf("alertingCallPlugin done")
 }

src/server/engine/notify_maintainer.go

@@ -2,11 +2,10 @@ package engine
 
 import (
 	"encoding/json"
-	"plugin"
-	"runtime"
 	"time"
 
 	"github.com/didi/nightingale/v5/src/models"
+	"github.com/didi/nightingale/v5/src/notifier"
 	"github.com/didi/nightingale/v5/src/server/common/sender"
 	"github.com/didi/nightingale/v5/src/server/config"
 	"github.com/didi/nightingale/v5/src/server/memsto"
@@ -14,72 +13,59 @@ import (
 	"github.com/toolkits/pkg/logger"
 )
 
-type NoticeMaintainer struct {
-	NotifyUsersObj []*models.User `json:"notify_user_obj" gorm:"-"`
-	Title          string         `json:"title"`
-	Content        string         `json:"content"`
+type MaintainMessage struct {
+	Tos     []*models.User `json:"tos"`
+	Title   string         `json:"title"`
+	Content string         `json:"content"`
 }
 
-func noticeCallPlugin(stdinBytes []byte) {
+func notifyMaintainerWithPlugin(e error, title, triggerTime string, users []*models.User) {
 	if !config.C.Alerting.CallPlugin.Enable {
 		return
 	}
 
-	if runtime.GOOS == "windows" {
-		logger.Errorf("call notify plugin on unsupported os: %s", runtime.GOOS)
+	stdinBytes, err := json.Marshal(MaintainMessage{
+		Tos:     users,
+		Title:   title,
+		Content: "Title: " + title + "\nContent: " + e.Error() + "\nTime: " + triggerTime,
+	})
+
+	if err != nil {
+		logger.Error("failed to marshal MaintainMessage:", err)
 		return
 	}
 
-	p, err := plugin.Open(config.C.Alerting.CallPlugin.PluginPath)
-	if err != nil {
-		logger.Errorf("failed to open notify plugin: %v", err)
-		return
-	}
-	caller, err := p.Lookup(config.C.Alerting.CallPlugin.Caller)
-	if err != nil {
-		logger.Errorf("failed to load caller: %v", err)
-		return
-	}
-	notifier, ok := caller.(Notifier)
-	if !ok {
-		logger.Errorf("notifier interface not implemented): %v", err)
-		return
-	}
-	notifier.NotifyMaintainer(stdinBytes)
-	logger.Debugf("noticeCallPlugin done. %s", notifier.Descript())
+	notifier.Instance.NotifyMaintainer(stdinBytes)
+	logger.Debugf("notify maintainer with plugin done")
 }
 
 // notify to maintainer to handle the error
 func notifyToMaintainer(e error, title string) {
+	logger.Errorf("notifyToMaintainer, title:%s, error:%v", title, e)
 
-	logger.Errorf("notifyToMaintainer，title:%s, error:%v", title, e)
-
-	var noticeMaintainer NoticeMaintainer
-	maintainerUsers := memsto.UserCache.GetMaintainerUsers()
-	if len(maintainerUsers) == 0 {
+	users := memsto.UserCache.GetMaintainerUsers()
+	if len(users) == 0 {
 		return
 	}
-	triggerTime := time.Now().Format("2006/01/02 - 15:04:05")
-	noticeMaintainer.NotifyUsersObj = maintainerUsers
-	noticeMaintainer.Content = "【内部处理错误】当前标题: " + title + "\n【内部处理错误】当前异常: " + e.Error() + "\n【内部处理错误】发送时间: " + triggerTime
-	noticeMaintainer.Title = title
-	stdinBytes, err := json.Marshal(noticeMaintainer)
-	if err != nil {
-		logger.Errorf("notifyToMaintainer: failed to marshal noticeMaintainer: %v", err)
-	} else {
-		noticeCallPlugin(stdinBytes)
-	}
 
+	triggerTime := time.Now().Format("2006/01/02 - 15:04:05")
+
+	notifyMaintainerWithPlugin(e, title, triggerTime, users)
+	notifyMaintainerWithBuiltin(e, title, triggerTime, users)
+}
+
+func notifyMaintainerWithBuiltin(e error, title, triggerTime string, users []*models.User) {
 	if len(config.C.Alerting.NotifyBuiltinChannels) == 0 {
 		return
 	}
+
 	emailset := make(map[string]struct{})
 	phoneset := make(map[string]struct{})
 	wecomset := make(map[string]struct{})
 	dingtalkset := make(map[string]struct{})
 	feishuset := make(map[string]struct{})
 
-	for _, user := range maintainerUsers {
+	for _, user := range users {
 		if user.Email != "" {
 			emailset[user.Email] = struct{}{}
 		}
@@ -118,13 +104,13 @@ func notifyToMaintainer(e error, title string) {
 			if len(emailset) == 0 {
 				continue
 			}
-			content := "【内部处理错误】当前标题: " + title + "\n【内部处理错误】当前异常: " + e.Error() + "\n【内部处理错误】发送时间: " + triggerTime
+			content := "Title: " + title + "\nContent: " + e.Error() + "\nTime: " + triggerTime
 			sender.WriteEmail(title, content, StringSetKeys(emailset))
 		case "dingtalk":
 			if len(dingtalkset) == 0 {
 				continue
 			}
-			content := "**【内部处理错误】当前标题: **" + title + "\n**【内部处理错误】当前异常: **" + e.Error() + "\n**【内部处理错误】发送时间: **" + triggerTime
+			content := "**Title: **" + title + "\n**Content: **" + e.Error() + "\n**Time: **" + triggerTime
 			sender.SendDingtalk(sender.DingtalkMessage{
 				Title:     title,
 				Text:      content,
@@ -135,7 +121,7 @@ func notifyToMaintainer(e error, title string) {
 			if len(wecomset) == 0 {
 				continue
 			}
-			content := "**【内部处理错误】当前标题: **" + title + "\n**【内部处理错误】当前异常: **" + e.Error() + "\n**【内部处理错误】发送时间: **" + triggerTime
+			content := "**Title: **" + title + "\n**Content: **" + e.Error() + "\n**Time: **" + triggerTime
 			sender.SendWecom(sender.WecomMessage{
 				Text:   content,
 				Tokens: StringSetKeys(wecomset),
@@ -145,7 +131,7 @@ func notifyToMaintainer(e error, title string) {
 				continue
 			}
 
-			content := "【内部处理错误】当前标题: " + title + "\n【内部处理错误】当前异常: " + e.Error() + "\n【内部处理错误】发送时间: " + triggerTime
+			content := "Title: " + title + "\nContent: " + e.Error() + "\nTime: " + triggerTime
 			sender.SendFeishu(sender.FeishuMessage{
 				Text:      content,
 				AtMobiles: phones,

src/server/engine/worker.go

@@ -87,7 +87,7 @@ func (r RuleEval) Start() {
 			return
 		default:
 			r.Work()
-			logger.Debugf("rule executed，rule_id=%d", r.RuleID())
+			logger.Debugf("rule executed, rule_id=%d", r.RuleID())
 			interval := r.rule.PromEvalInterval
 			if interval <= 0 {
 				interval = 10
@@ -116,8 +116,7 @@ func (r RuleEval) Work() {
 		value, warnings, err = reader.Client.Query(context.Background(), promql, time.Now())
 		if err != nil {
 			logger.Errorf("rule_eval:%d promql:%s, error:%v", r.RuleID(), promql, err)
-			// 告警查询prometheus逻辑出错，发告警信息给管理员
-			notifyToMaintainer(err, "查询prometheus出错")
+			notifyToMaintainer(err, "failed to query prometheus")
 			return
 		}
 
@@ -190,7 +189,6 @@ func (ws *WorkersType) Build(rids []int64) {
 		elst, err := models.AlertCurEventGetByRule(rules[hash].Id)
 		if err != nil {
 			logger.Errorf("worker_build: AlertCurEventGetByRule failed: %v", err)
-			notifyToMaintainer(err, "AlertCurEventGetByRule Error，ruleID="+fmt.Sprint(rules[hash].Id))
 			continue
 		}
 
@@ -326,7 +324,7 @@ func (r RuleEval) judge(vectors []conv.Vector) {
 		}
 
 		// isMuted only need TriggerTime RuleName and TagsMap
-		if isMuted(event) {
+		if IsMuted(event) {
 			logger.Infof("event_muted: rule_id=%d %s", r.rule.Id, vectors[i].Key)
 			continue
 		}

src/server/router/router_event.go

@@ -36,6 +36,13 @@ func pushEventToQueue(c *gin.Context) {
 		event.TagsMap[arr[0]] = arr[1]
 	}
 
+	// isMuted only need TriggerTime RuleName and TagsMap
+	if engine.IsMuted(event) {
+		logger.Infof("event_muted: rule_id=%d %s", event.RuleId, event.Hash)
+		ginx.NewRender(c).Message(nil)
+		return
+	}
+
 	if err := event.ParseRuleNote(); err != nil {
 		event.RuleNote = fmt.Sprintf("failed to parse rule note: %v", err)
 	}

src/webapi/router/router.go

@@ -101,11 +101,9 @@ func configRoute(r *gin.Engine, version string) {
 
 		if config.C.AnonymousAccess.PromQuerier {
 			pages.Any("/prometheus/*url", prometheusProxy)
-
 			pages.POST("/query-range-batch", promBatchQueryRange)
 		} else {
 			pages.Any("/prometheus/*url", auth(), prometheusProxy)
-
 			pages.POST("/query-range-batch", auth(), promBatchQueryRange)
 		}
 
@@ -179,6 +177,7 @@ func configRoute(r *gin.Engine, version string) {
 		pages.POST("/busi-group/:id/board/:bid/clone", auth(), user(), perm("/dashboards/add"), bgrw(), boardClone)
 
 		pages.GET("/board/:bid", auth(), user(), boardGet)
+		pages.GET("/board/:bid/pure", boardPureGet)
 		pages.PUT("/board/:bid", auth(), user(), perm("/dashboards/put"), boardPut)
 		pages.PUT("/board/:bid/configs", auth(), user(), perm("/dashboards/put"), boardPutConfigs)
 		pages.DELETE("/boards", auth(), user(), perm("/dashboards/del"), boardDel)

src/webapi/router/router_board.go

@@ -51,6 +51,17 @@ func boardGet(c *gin.Context) {
 	ginx.NewRender(c).Data(board, nil)
 }
 
+func boardPureGet(c *gin.Context) {
+	board, err := models.BoardGetByID(ginx.UrlParamInt64(c, "bid"))
+	ginx.Dangerous(err)
+
+	if board == nil {
+		ginx.Bomb(http.StatusNotFound, "No such dashboard")
+	}
+
+	ginx.NewRender(c).Data(board, nil)
+}
+
 // bgrwCheck
 func boardDel(c *gin.Context) {
 	var f idsForm

src/webapi/router/router_mw.go

@@ -59,7 +59,7 @@ func proxyAuth() gin.HandlerFunc {
 	return func(c *gin.Context) {
 		user := handleProxyUser(c)
 		c.Set("userid", user.Id)
-		c.Set("username", user)
+		c.Set("username", user.Username)
 		c.Next()
 	}
 }

src/webapi/router/router_prometheus.go

@@ -32,21 +32,15 @@ type batchQueryForm struct {
 func promBatchQueryRange(c *gin.Context) {
 	xcluster := c.GetHeader("X-Cluster")
 	if xcluster == "" {
-		c.String(500, "X-Cluster is blank")
-		return
+		ginx.Bomb(http.StatusBadRequest, "header(X-Cluster) is blank")
 	}
 
 	var f batchQueryForm
-	err := c.BindJSON(&f)
-	if err != nil {
-		c.String(500, err.Error())
-		return
-	}
+	ginx.Dangerous(c.BindJSON(&f))
 
 	cluster, exist := prom.Clusters.Get(xcluster)
 	if !exist {
-		c.String(http.StatusBadRequest, "cluster(%s) not found", xcluster)
-		return
+		ginx.Bomb(http.StatusBadRequest, "cluster(%s) not found", xcluster)
 	}
 
 	var lst []model.Value
@@ -59,15 +53,12 @@ func promBatchQueryRange(c *gin.Context) {
 		}
 
 		resp, _, err := cluster.PromClient.QueryRange(context.Background(), item.Query, r)
-		if err != nil {
-			c.String(500, err.Error())
-			return
-		}
+		ginx.Dangerous(err)
 
 		lst = append(lst, resp)
 	}
 
-	c.JSON(200, lst)
+	ginx.NewRender(c).Data(lst, nil)
 }
 
 func prometheusProxy(c *gin.Context) {