refactor: optimize webhook send

Co-authored-by: CRISPpp <78430796+CRISPpp@users.noreply.github.com>

.github/workflows/n9e.yml

@@ -5,7 +5,7 @@ on:
     tags:
       - 'v*'
 env:
-  GO_VERSION: 1.18
+  GO_VERSION: 1.23
 
 jobs:
   goreleaser:

.gitignore

@@ -9,6 +9,7 @@
 *.o
 *.a
 *.so
+*.db
 *.sw[po]
 *.tar.gz
 *.[568vq]

README.md

@@ -38,6 +38,7 @@
 - 👉 [文档中心](https://flashcat.cloud/docs/) | [下载中心](https://flashcat.cloud/download/nightingale/)
 - ❤️ [报告 Bug](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=&projects=&template=question.yml)
 - ℹ️ 为了提供更快速的访问体验，上述文档和下载站点托管于 [FlashcatCloud](https://flashcat.cloud)
+- 💡 前后端代码分离，前端代码仓库：[https://github.com/n9e/fe](https://github.com/n9e/fe)
 
 ## 功能特点
 
@@ -90,7 +91,7 @@
 - 推荐搜索关注夜莺公众号，第一时间获取社区动态：`夜莺监控Nightingale`
 - 日常问题交流：
   - QQ群：730841964
-  - [加入微信群](https://download.flashcat.cloud/ulric/20241008153952.png)，如果二维码过期了，可以联系我（我的微信：`picobyte`）拉群，备注： `夜莺互助群`
+  - [加入微信群](https://download.flashcat.cloud/ulric/20241022141621.png)，如果二维码过期了，可以联系我（我的微信：`picobyte`）拉群，备注： `夜莺互助群`
 
 ## 广受关注
 [![Stargazers over time](https://api.star-history.com/svg?repos=ccfos/nightingale&type=Date)](https://star-history.com/#ccfos/nightingale&Date)

alert/alert.go

@@ -62,15 +62,18 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 	userCache := memsto.NewUserCache(ctx, syncStats)
 	userGroupCache := memsto.NewUserGroupCache(ctx, syncStats)
 	taskTplsCache := memsto.NewTaskTplCache(ctx)
+	configCvalCache := memsto.NewCvalCache(ctx, syncStats)
 
 	promClients := prom.NewPromClient(ctx)
+	dispatch.InitRegisterQueryFunc(promClients)
 	tdengineClients := tdengine.NewTdengineClient(ctx, config.Alert.Heartbeat)
 
 	externalProcessors := process.NewExternalProcessors()
 
 	Start(config.Alert, config.Pushgw, syncStats, alertStats, externalProcessors, targetCache, busiGroupCache, alertMuteCache, alertRuleCache, notifyConfigCache, taskTplsCache, dsCache, ctx, promClients, tdengineClients, userCache, userGroupCache)
 
-	r := httpx.GinEngine(config.Global.RunMode, config.HTTP)
+	r := httpx.GinEngine(config.Global.RunMode, config.HTTP,
+		configCvalCache.PrintBodyPaths, configCvalCache.PrintAccessLog)
 	rt := router.New(config.HTTP, config.Alert, alertMuteCache, targetCache, busiGroupCache, alertStats, ctx, externalProcessors)
 
 	if config.Ibex.Enable {
@@ -100,7 +103,7 @@ func Start(alertc aconf.Alert, pushgwc pconf.Pushgw, syncStats *memsto.Stats, al
 	naming := naming.NewNaming(ctx, alertc.Heartbeat, alertStats)
 
 	writers := writer.NewWriters(pushgwc)
-	record.NewScheduler(alertc, recordingRuleCache, promClients, writers, alertStats)
+	record.NewScheduler(alertc, recordingRuleCache, promClients, writers, alertStats, datasourceCache)
 
 	eval.NewScheduler(alertc, externalProcessors, alertRuleCache, targetCache, targetsOfAlertRulesCache,
 		busiGroupCache, alertMuteCache, datasourceCache, promClients, tdendgineClients, naming, ctx, alertStats)

alert/astats/stats.go

@@ -38,7 +38,7 @@ func NewSyncStats() *Stats {
 		Subsystem: subsystem,
 		Name:      "rule_eval_error_total",
 		Help:      "Number of rule eval error.",
-	}, []string{"datasource", "stage"})
+	}, []string{"datasource", "stage", "busi_group", "rule_id"})
 
 	CounterQueryDataErrorTotal := prometheus.NewCounterVec(prometheus.CounterOpts{
 		Namespace: namespace,

alert/dispatch/consume.go

@@ -1,6 +1,7 @@
 package dispatch
 
 import (
+	"context"
 	"encoding/json"
 	"fmt"
 	"strings"
@@ -13,8 +14,10 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
 	"github.com/ccfos/nightingale/v6/pkg/poster"
 	promsdk "github.com/ccfos/nightingale/v6/pkg/prom"
+	"github.com/ccfos/nightingale/v6/pkg/tplx"
 	"github.com/ccfos/nightingale/v6/prom"
 
+	"github.com/prometheus/common/model"
 	"github.com/toolkits/pkg/concurrent/semaphore"
 	"github.com/toolkits/pkg/logger"
 )
@@ -27,6 +30,18 @@ type Consumer struct {
 	promClients *prom.PromClientMap
 }
 
+func InitRegisterQueryFunc(promClients *prom.PromClientMap) {
+	tplx.RegisterQueryFunc(func(datasourceID int64, promql string) model.Value {
+		if promClients.IsNil(datasourceID) {
+			return nil
+		}
+
+		readerClient := promClients.GetCli(datasourceID)
+		value, _, _ := readerClient.Query(context.Background(), promql, time.Now())
+		return value
+	})
+}
+
 // 创建一个 Consumer 实例
 func NewConsumer(alerting aconf.Alerting, ctx *ctx.Context, dispatch *Dispatch, promClients *prom.PromClientMap) *Consumer {
 	return &Consumer{
@@ -113,7 +128,7 @@ func (e *Consumer) persist(event *models.AlertCurEvent) {
 		event.Id, err = poster.PostByUrlsWithResp[int64](e.ctx, "/v1/n9e/event-persist", event)
 		if err != nil {
 			logger.Errorf("event:%+v persist err:%v", event, err)
-			e.dispatch.Astats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", event.DatasourceId), "persist_event").Inc()
+			e.dispatch.Astats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", event.DatasourceId), "persist_event", event.GroupName, fmt.Sprintf("%v", event.RuleId)).Inc()
 		}
 		return
 	}
@@ -121,7 +136,7 @@ func (e *Consumer) persist(event *models.AlertCurEvent) {
 	err := models.EventPersist(e.ctx, event)
 	if err != nil {
 		logger.Errorf("event%+v persist err:%v", event, err)
-		e.dispatch.Astats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", event.DatasourceId), "persist_event").Inc()
+		e.dispatch.Astats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", event.DatasourceId), "persist_event", event.GroupName, fmt.Sprintf("%v", event.RuleId)).Inc()
 	}
 }
 
@@ -169,7 +184,7 @@ func (e *Consumer) queryRecoveryVal(event *models.AlertCurEvent) {
 		logger.Errorf("rule_eval:%s promql:%s, warnings:%v", getKey(event), promql, warnings)
 	}
 
-	anomalyPoints := common.ConvertAnomalyPoints(value)
+	anomalyPoints := models.ConvertAnomalyPoints(value)
 	if len(anomalyPoints) == 0 {
 		logger.Warningf("rule_eval:%s promql:%s, result is empty", getKey(event), promql)
 		event.AnnotationsJSON["recovery_promql_error"] = fmt.Sprintf("promql:%s error:%s", promql, "result is empty")

alert/dispatch/dispatch.go

@@ -139,6 +139,12 @@ func (e *Dispatch) HandleEventNotify(event *models.AlertCurEvent, isSubscribe bo
 	if rule == nil {
 		return
 	}
+
+	if e.blockEventNotify(rule, event) {
+		logger.Infof("block event notify: rule_id:%d event:%+v", rule.Id, event)
+		return
+	}
+
 	fillUsers(event, e.userCache, e.userGroupCache)
 
 	var (
@@ -175,6 +181,25 @@ func (e *Dispatch) HandleEventNotify(event *models.AlertCurEvent, isSubscribe bo
 	}
 }
 
+func (e *Dispatch) blockEventNotify(rule *models.AlertRule, event *models.AlertCurEvent) bool {
+	ruleType := rule.GetRuleType()
+
+	// 若为机器则先看机器是否删除
+	if ruleType == models.HOST {
+		host, ok := e.targetCache.Get(event.TagsMap["ident"])
+		if !ok || host == nil {
+			return true
+		}
+	}
+
+	// 恢复通知，检测规则配置是否改变
+	// if event.IsRecovered && event.RuleHash != rule.Hash() {
+	// 	return true
+	// }
+
+	return false
+}
+
 func (e *Dispatch) handleSubs(event *models.AlertCurEvent) {
 	// handle alert subscribes
 	subscribes := make([]*models.AlertSubscribe, 0)
@@ -266,10 +291,12 @@ func (e *Dispatch) Send(rule *models.AlertRule, event *models.AlertCurEvent, not
 	e.SendCallbacks(rule, notifyTarget, event)
 
 	// handle global webhooks
-	if e.alerting.WebhookBatchSend {
-		sender.BatchSendWebhooks(e.ctx, notifyTarget.ToWebhookList(), event, e.Astats)
-	} else {
-		sender.SingleSendWebhooks(e.ctx, notifyTarget.ToWebhookList(), event, e.Astats)
+	if !event.OverrideGlobalWebhook() {
+		if e.alerting.WebhookBatchSend {
+			sender.BatchSendWebhooks(e.ctx, notifyTarget.ToWebhookMap(), event, e.Astats)
+		} else {
+			sender.SingleSendWebhooks(e.ctx, notifyTarget.ToWebhookMap(), event, e.Astats)
+		}
 	}
 
 	// handle plugin call
@@ -283,10 +310,10 @@ func (e *Dispatch) Send(rule *models.AlertRule, event *models.AlertCurEvent, not
 }
 
 func (e *Dispatch) SendCallbacks(rule *models.AlertRule, notifyTarget *NotifyTarget, event *models.AlertCurEvent) {
-
 	uids := notifyTarget.ToUidList()
 	urls := notifyTarget.ToCallbackList()
 	whMap := notifyTarget.ToWebhookMap()
+	ogw := event.OverrideGlobalWebhook()
 	for _, urlStr := range urls {
 		if len(urlStr) == 0 {
 			continue
@@ -294,7 +321,7 @@ func (e *Dispatch) SendCallbacks(rule *models.AlertRule, notifyTarget *NotifyTar
 
 		cbCtx := sender.BuildCallBackContext(e.ctx, urlStr, rule, []*models.AlertCurEvent{event}, uids, e.userCache, e.alerting.WebhookBatchSend, e.Astats)
 
-		if wh, ok := whMap[cbCtx.CallBackURL]; ok && wh.Enable {
+		if wh, ok := whMap[cbCtx.CallBackURL]; !ogw && ok && wh.Enable {
 			logger.Debugf("SendCallbacks: webhook[%s] is in global conf.", cbCtx.CallBackURL)
 			continue
 		}

alert/dispatch/notify_target.go

@@ -76,52 +76,8 @@ func (s *NotifyTarget) ToCallbackList() []string {
 	return callbacks
 }
 
-func (s *NotifyTarget) ToWebhookList() []*models.Webhook {
-	webhooks := make([]*models.Webhook, 0, len(s.webhooks))
-	for _, wh := range s.webhooks {
-		if wh.Batch == 0 {
-			wh.Batch = 1000
-		}
-
-		if wh.Timeout == 0 {
-			wh.Timeout = 10
-		}
-
-		if wh.RetryCount == 0 {
-			wh.RetryCount = 10
-		}
-
-		if wh.RetryInterval == 0 {
-			wh.RetryInterval = 10
-		}
-
-		webhooks = append(webhooks, wh)
-	}
-	return webhooks
-}
-
 func (s *NotifyTarget) ToWebhookMap() map[string]*models.Webhook {
-	webhookMap := make(map[string]*models.Webhook, len(s.webhooks))
-	for _, wh := range s.webhooks {
-		if wh.Batch == 0 {
-			wh.Batch = 1000
-		}
-
-		if wh.Timeout == 0 {
-			wh.Timeout = 10
-		}
-
-		if wh.RetryCount == 0 {
-			wh.RetryCount = 10
-		}
-
-		if wh.RetryInterval == 0 {
-			wh.RetryInterval = 10
-		}
-
-		webhookMap[wh.Url] = wh
-	}
-	return webhookMap
+	return s.webhooks
 }
 
 func (s *NotifyTarget) ToUidList() []int64 {

alert/eval/alert_rule.go

@@ -96,8 +96,7 @@ func (s *Scheduler) syncAlertRules() {
 
 		ruleType := rule.GetRuleType()
 		if rule.IsPrometheusRule() || rule.IsLokiRule() || rule.IsTdengineRule() {
-			datasourceIds := s.promClients.Hit(rule.DatasourceIdsJson)
-			datasourceIds = append(datasourceIds, s.tdengineClients.Hit(rule.DatasourceIdsJson)...)
+			datasourceIds := s.datasourceCache.GetIDsByDsCateAndQueries(rule.Cate, rule.DatasourceQueries)
 			for _, dsId := range datasourceIds {
 				if !naming.DatasourceHashRing.IsHit(strconv.FormatInt(dsId, 10), fmt.Sprintf("%d", rule.Id), s.aconf.Heartbeat.Endpoint) {
 					continue
@@ -133,7 +132,8 @@ func (s *Scheduler) syncAlertRules() {
 		} else {
 			// 如果 rule 不是通过 prometheus engine 来告警的，则创建为 externalRule
 			// if rule is not processed by prometheus engine, create it as externalRule
-			for _, dsId := range rule.DatasourceIdsJson {
+			dsIds := s.datasourceCache.GetIDsByDsCateAndQueries(rule.Cate, rule.DatasourceQueries)
+			for _, dsId := range dsIds {
 				ds := s.datasourceCache.GetById(dsId)
 				if ds == nil {
 					logger.Debugf("datasource %d not found", dsId)

alert/eval/eval_test.go

@@ -269,3 +269,190 @@ func allValueDeepEqual(got, want map[uint64][]uint64) bool {
 	}
 	return true
 }
+
+// allValueDeepEqualOmitOrder 判断两个字符串切片是否相等，不考虑顺序
+func allValueDeepEqualOmitOrder(got, want []string) bool {
+	if len(got) != len(want) {
+		return false
+	}
+	slices.Sort(got)
+	slices.Sort(want)
+	for i := range got {
+		if got[i] != want[i] {
+			return false
+		}
+	}
+	return true
+}
+
+func Test_removeVal(t *testing.T) {
+	type args struct {
+		promql string
+	}
+	tests := []struct {
+		name string
+		args args
+		want string
+	}{
+		// TODO: Add test cases.
+		{
+			name: "removeVal1",
+			args: args{
+				promql: "mem{test1=\"$test1\",test2=\"$test2\",test3=\"$test3\"} > $val",
+			},
+			want: "mem{} > $val",
+		},
+		{
+			name: "removeVal2",
+			args: args{
+				promql: "mem{test1=\"test1\",test2=\"$test2\",test3=\"$test3\"} > $val",
+			},
+			want: "mem{test1=\"test1\"} > $val",
+		},
+		{
+			name: "removeVal3",
+			args: args{
+				promql: "mem{test1=\"$test1\",test2=\"test2\",test3=\"$test3\"} > $val",
+			},
+			want: "mem{test2=\"test2\"} > $val",
+		},
+		{
+			name: "removeVal4",
+			args: args{
+				promql: "mem{test1=\"$test1\",test2=\"$test2\",test3=\"test3\"} > $val",
+			},
+			want: "mem{test3=\"test3\"} > $val",
+		},
+		{
+			name: "removeVal5",
+			args: args{
+				promql: "mem{test1=\"$test1\",test2=\"test2\",test3=\"test3\"} > $val",
+			},
+			want: "mem{test2=\"test2\",test3=\"test3\"} > $val",
+		},
+		{
+			name: "removeVal6",
+			args: args{
+				promql: "mem{test1=\"test1\",test2=\"$test2\",test3=\"test3\"} > $val",
+			},
+			want: "mem{test1=\"test1\",test3=\"test3\"} > $val",
+		},
+		{
+			name: "removeVal7",
+			args: args{
+				promql: "mem{test1=\"test1\",test2=\"test2\",test3='$test3'} > $val",
+			},
+			want: "mem{test1=\"test1\",test2=\"test2\"} > $val",
+		},
+		{
+			name: "removeVal8",
+			args: args{
+				promql: "mem{test1=\"test1\",test2=\"test2\",test3=\"test3\"} > $val",
+			},
+			want: "mem{test1=\"test1\",test2=\"test2\",test3=\"test3\"} > $val",
+		},
+		{
+			name: "removeVal9",
+			args: args{
+				promql: "mem{test1=\"$test1\",test2=\"test2\"} > $val1 and mem{test3=\"test3\",test4=\"test4\"} > $val2",
+			},
+			want: "mem{test2=\"test2\"} > $val1 and mem{test3=\"test3\",test4=\"test4\"} > $val2",
+		},
+		{
+			name: "removeVal10",
+			args: args{
+				promql: "mem{test1=\"test1\",test2='$test2'} > $val1 and mem{test3=\"test3\",test4=\"test4\"} > $val2",
+			},
+			want: "mem{test1=\"test1\"} > $val1 and mem{test3=\"test3\",test4=\"test4\"} > $val2",
+		},
+		{
+			name: "removeVal11",
+			args: args{
+				promql: "mem{test1='test1',test2=\"test2\"} > $val1 and mem{test3=\"$test3\",test4=\"test4\"} > $val2",
+			},
+			want: "mem{test1='test1',test2=\"test2\"} > $val1 and mem{test4=\"test4\"} > $val2",
+		},
+		{
+			name: "removeVal12",
+			args: args{
+				promql: "mem{test1=\"test1\",test2=\"test2\"} > $val1 and mem{test3=\"test3\",test4=\"$test4\"} > $val2",
+			},
+			want: "mem{test1=\"test1\",test2=\"test2\"} > $val1 and mem{test3=\"test3\"} > $val2",
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := removeVal(tt.args.promql); got != tt.want {
+				t.Errorf("removeVal() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestExtractVarMapping(t *testing.T) {
+	tests := []struct {
+		name   string
+		promql string
+		want   map[string]string
+	}{
+		{
+			name:   "单个花括号单个变量",
+			promql: `mem_used_percent{host="$my_host"} > $val`,
+			want:   map[string]string{"my_host": "host"},
+		},
+		{
+			name:   "单个花括号多个变量",
+			promql: `mem_used_percent{host="$my_host",region="$region",env="prod"} > $val`,
+			want:   map[string]string{"my_host": "host", "region": "region"},
+		},
+		{
+			name:   "多个花括号多个变量",
+			promql: `sum(rate(mem_used_percent{host="$my_host"})) by (instance) + avg(node_load1{region="$region"}) > $val`,
+			want:   map[string]string{"my_host": "host", "region": "region"},
+		},
+		{
+			name:   "相同变量出现多次",
+			promql: `sum(rate(mem_used_percent{host="$my_host"})) + avg(node_load1{host="$my_host"}) > $val`,
+			want:   map[string]string{"my_host": "host"},
+		},
+		{
+			name:   "没有变量",
+			promql: `mem_used_percent{host="localhost",region="cn"} > 80`,
+			want:   map[string]string{},
+		},
+		{
+			name:   "没有花括号",
+			promql: `80 > $val`,
+			want:   map[string]string{},
+		},
+		{
+			name:   "格式不规范的标签",
+			promql: `mem_used_percent{host=$my_host,region = $region} > $val`,
+			want:   map[string]string{"my_host": "host", "region": "region"},
+		},
+		{
+			name:   "空花括号",
+			promql: `mem_used_percent{} > $val`,
+			want:   map[string]string{},
+		},
+		{
+			name:   "不完整的花括号",
+			promql: `mem_used_percent{host="$my_host"`,
+			want:   map[string]string{},
+		},
+		{
+			name:   "复杂表达式",
+			promql: `sum(rate(http_requests_total{handler="$handler",code="$code"}[5m])) by (handler) / sum(rate(http_requests_total{handler="$handler"}[5m])) by (handler) * 100 > $threshold`,
+			want:   map[string]string{"handler": "handler", "code": "code"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := ExtractVarMapping(tt.promql)
+			if !reflect.DeepEqual(got, tt.want) {
+				t.Errorf("ExtractVarMapping() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}

alert/process/process.go

@@ -21,6 +21,7 @@ import (
 	"github.com/ccfos/nightingale/v6/pushgw/writer"
 
 	"github.com/prometheus/prometheus/prompb"
+	"github.com/robfig/cron/v3"
 	"github.com/toolkits/pkg/logger"
 	"github.com/toolkits/pkg/str"
 )
@@ -78,6 +79,9 @@ type Processor struct {
 	HandleFireEventHook    HandleEventFunc
 	HandleRecoverEventHook HandleEventFunc
 	EventMuteHook          EventMuteHookFunc
+
+	ScheduleEntry    cron.Entry
+	PromEvalInterval int
 }
 
 func (p *Processor) Key() string {
@@ -89,9 +93,9 @@ func (p *Processor) DatasourceId() int64 {
 }
 
 func (p *Processor) Hash() string {
-	return str.MD5(fmt.Sprintf("%d_%d_%s_%d",
+	return str.MD5(fmt.Sprintf("%d_%s_%s_%d",
 		p.rule.Id,
-		p.rule.PromEvalInterval,
+		p.rule.CronPattern,
 		p.rule.RuleConfig,
 		p.datasourceId,
 	))
@@ -126,7 +130,7 @@ func NewProcessor(engineName string, rule *models.AlertRule, datasourceId int64,
 	return p
 }
 
-func (p *Processor) Handle(anomalyPoints []common.AnomalyPoint, from string, inhibit bool) {
+func (p *Processor) Handle(anomalyPoints []models.AnomalyPoint, from string, inhibit bool) {
 	// 有可能rule的一些配置已经发生变化，比如告警接收人、callbacks等
 	// 这些信息的修改是不会引起worker restart的，但是确实会影响告警处理逻辑
 	// 所以，这里直接从memsto.AlertRuleCache中获取并覆盖
@@ -134,10 +138,13 @@ func (p *Processor) Handle(anomalyPoints []common.AnomalyPoint, from string, inh
 	cachedRule := p.alertRuleCache.Get(p.rule.Id)
 	if cachedRule == nil {
 		logger.Errorf("rule not found %+v", anomalyPoints)
-		p.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", p.DatasourceId()), "handle_event").Inc()
+		p.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", p.DatasourceId()), "handle_event", p.BusiGroupCache.GetNameByBusiGroupId(p.rule.GroupId), fmt.Sprintf("%v", p.rule.Id)).Inc()
 		return
 	}
 
+	// 在 rule 变化之前取到 ruleHash
+	ruleHash := p.rule.Hash()
+
 	p.rule = cachedRule
 	now := time.Now().Unix()
 	alertingKeys := map[string]struct{}{}
@@ -145,7 +152,7 @@ func (p *Processor) Handle(anomalyPoints []common.AnomalyPoint, from string, inh
 	// 根据 event 的 tag 将 events 分组，处理告警抑制的情况
 	eventsMap := make(map[string][]*models.AlertCurEvent)
 	for _, anomalyPoint := range anomalyPoints {
-		event := p.BuildEvent(anomalyPoint, from, now)
+		event := p.BuildEvent(anomalyPoint, from, now, ruleHash)
 		// 如果 event 被 mute 了,本质也是 fire 的状态,这里无论如何都添加到 alertingKeys 中,防止 fire 的事件自动恢复了
 		hash := event.Hash
 		alertingKeys[hash] = struct{}{}
@@ -170,10 +177,12 @@ func (p *Processor) Handle(anomalyPoints []common.AnomalyPoint, from string, inh
 		p.handleEvent(events)
 	}
 
-	p.HandleRecover(alertingKeys, now, inhibit)
+	if from == "inner" {
+		p.HandleRecover(alertingKeys, now, inhibit)
+	}
 }
 
-func (p *Processor) BuildEvent(anomalyPoint common.AnomalyPoint, from string, now int64) *models.AlertCurEvent {
+func (p *Processor) BuildEvent(anomalyPoint models.AnomalyPoint, from string, now int64, ruleHash string) *models.AlertCurEvent {
 	p.fillTags(anomalyPoint)
 	p.mayHandleIdent()
 	hash := Hash(p.rule.Id, p.datasourceId, anomalyPoint)
@@ -199,6 +208,7 @@ func (p *Processor) BuildEvent(anomalyPoint common.AnomalyPoint, from string, no
 	event.TargetNote = p.targetNote
 	event.TriggerValue = anomalyPoint.ReadableValue()
 	event.TriggerValues = anomalyPoint.Values
+	event.TriggerValuesJson = models.EventTriggerValues{ValuesWithUnit: anomalyPoint.ValuesUnit}
 	event.TagsJSON = p.tagsArr
 	event.Tags = strings.Join(p.tagsArr, ",,")
 	event.IsRecovered = false
@@ -211,9 +221,12 @@ func (p *Processor) BuildEvent(anomalyPoint common.AnomalyPoint, from string, no
 	event.Severity = anomalyPoint.Severity
 	event.ExtraConfig = p.rule.ExtraConfigJSON
 	event.PromQl = anomalyPoint.Query
+	event.RecoverConfig = anomalyPoint.RecoverConfig
+	event.RuleHash = ruleHash
 
 	if p.target != "" {
 		if pt, exist := p.TargetCache.Get(p.target); exist {
+			pt.GroupNames = p.BusiGroupCache.GetNamesByBusiGroupIds(pt.GroupIds)
 			event.Target = pt
 		} else {
 			logger.Infof("Target[ident: %s] doesn't exist in cache.", p.target)
@@ -290,7 +303,7 @@ func (p *Processor) HandleRecover(alertingKeys map[string]struct{}, now int64, i
 	}
 
 	hashArr := make([]string, 0, len(alertingKeys))
-	for hash := range p.fires.GetAll() {
+	for hash, _ := range p.fires.GetAll() {
 		if _, has := alertingKeys[hash]; has {
 			continue
 		}
@@ -309,7 +322,7 @@ func (p *Processor) HandleRecoverEvent(hashArr []string, now int64, inhibit bool
 
 	if !inhibit {
 		for _, hash := range hashArr {
-			p.RecoverSingle(hash, now, nil)
+			p.RecoverSingle(false, hash, now, nil)
 		}
 		return
 	}
@@ -337,11 +350,11 @@ func (p *Processor) HandleRecoverEvent(hashArr []string, now int64, inhibit bool
 	}
 
 	for _, event := range eventMap {
-		p.RecoverSingle(event.Hash, now, nil)
+		p.RecoverSingle(false, event.Hash, now, nil)
 	}
 }
 
-func (p *Processor) RecoverSingle(hash string, now int64, value *string, values ...string) {
+func (p *Processor) RecoverSingle(byRecover bool, hash string, now int64, value *string, values ...string) {
 	cachedRule := p.rule
 	if cachedRule == nil {
 		return
@@ -367,6 +380,12 @@ func (p *Processor) RecoverSingle(hash string, now int64, value *string, values
 		}
 	}
 
+	// 如果设置了恢复条件，则不能在此处恢复，必须依靠 recoverPoint 来恢复
+	if event.RecoverConfig.JudgeType != models.Origin && !byRecover {
+		logger.Debugf("rule_eval:%s event:%v not recover", p.Key(), event)
+		return
+	}
+
 	if value != nil {
 		event.TriggerValue = *value
 		if len(values) > 0 {
@@ -405,6 +424,7 @@ func (p *Processor) handleEvent(events []*models.AlertCurEvent) {
 			p.pendingsUseByRecover.Set(event.Hash, event)
 		}
 
+		event.PromEvalInterval = p.PromEvalInterval
 		if p.rule.PromForDuration == 0 {
 			fireEvents = append(fireEvents, event)
 			if severity > event.Severity {
@@ -499,7 +519,7 @@ func (p *Processor) pushEventToQueue(e *models.AlertCurEvent) {
 	dispatch.LogEvent(e, "push_queue")
 	if !queue.EventQueue.PushFront(e) {
 		logger.Warningf("event_push_queue: queue is full, event:%+v", e)
-		p.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", p.DatasourceId()), "push_event_queue").Inc()
+		p.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", p.DatasourceId()), "push_event_queue", p.BusiGroupCache.GetNameByBusiGroupId(p.rule.GroupId), fmt.Sprintf("%v", p.rule.Id)).Inc()
 	}
 }
 
@@ -510,7 +530,7 @@ func (p *Processor) RecoverAlertCurEventFromDb() {
 	curEvents, err := models.AlertCurEventGetByRuleIdAndDsId(p.ctx, p.rule.Id, p.datasourceId)
 	if err != nil {
 		logger.Errorf("recover event from db for rule:%s failed, err:%s", p.Key(), err)
-		p.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", p.DatasourceId()), "get_recover_event").Inc()
+		p.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", p.DatasourceId()), "get_recover_event", p.BusiGroupCache.GetNameByBusiGroupId(p.rule.GroupId), fmt.Sprintf("%v", p.rule.Id)).Inc()
 		p.fires = NewAlertCurEventMap(nil)
 		return
 	}
@@ -529,6 +549,7 @@ func (p *Processor) RecoverAlertCurEventFromDb() {
 		event.DB2Mem()
 		target, exists := p.TargetCache.Get(event.TargetIdent)
 		if exists {
+			target.GroupNames = p.BusiGroupCache.GetNamesByBusiGroupIds(target.GroupIds)
 			event.Target = target
 		}
 
@@ -543,7 +564,7 @@ func (p *Processor) RecoverAlertCurEventFromDb() {
 	p.pendingsUseByRecover = NewAlertCurEventMap(pendingsUseByRecoverMap)
 }
 
-func (p *Processor) fillTags(anomalyPoint common.AnomalyPoint) {
+func (p *Processor) fillTags(anomalyPoint models.AnomalyPoint) {
 	// handle series tags
 	tagsMap := make(map[string]string)
 	for label, value := range anomalyPoint.Labels {
@@ -633,10 +654,10 @@ func labelMapToArr(m map[string]string) []string {
 	return labelStrings
 }
 
-func Hash(ruleId, datasourceId int64, vector common.AnomalyPoint) string {
+func Hash(ruleId, datasourceId int64, vector models.AnomalyPoint) string {
 	return str.MD5(fmt.Sprintf("%d_%s_%d_%d_%s", ruleId, vector.Labels.String(), datasourceId, vector.Severity, vector.Query))
 }
 
-func TagHash(vector common.AnomalyPoint) string {
+func TagHash(vector models.AnomalyPoint) string {
 	return str.MD5(vector.Labels.String())
 }

alert/record/scheduler.go

@@ -26,9 +26,11 @@ type Scheduler struct {
 	writers     *writer.WritersType
 
 	stats *astats.Stats
+
+	datasourceCache *memsto.DatasourceCacheType
 }
 
-func NewScheduler(aconf aconf.Alert, rrc *memsto.RecordingRuleCacheType, promClients *prom.PromClientMap, writers *writer.WritersType, stats *astats.Stats) *Scheduler {
+func NewScheduler(aconf aconf.Alert, rrc *memsto.RecordingRuleCacheType, promClients *prom.PromClientMap, writers *writer.WritersType, stats *astats.Stats, datasourceCache *memsto.DatasourceCacheType) *Scheduler {
 	scheduler := &Scheduler{
 		aconf:       aconf,
 		recordRules: make(map[string]*RecordRuleContext),
@@ -39,6 +41,8 @@ func NewScheduler(aconf aconf.Alert, rrc *memsto.RecordingRuleCacheType, promCli
 		writers:     writers,
 
 		stats: stats,
+
+		datasourceCache: datasourceCache,
 	}
 
 	go scheduler.LoopSyncRules(context.Background())
@@ -67,7 +71,7 @@ func (s *Scheduler) syncRecordRules() {
 			continue
 		}
 
-		datasourceIds := s.promClients.Hit(rule.DatasourceIdsJson)
+		datasourceIds := s.datasourceCache.GetIDsByDsCateAndQueries("prometheus", rule.DatasourceQueries)
 		for _, dsId := range datasourceIds {
 			if !naming.DatasourceHashRing.IsHit(strconv.FormatInt(dsId, 10), fmt.Sprintf("%d", rule.Id), s.aconf.Heartbeat.Endpoint) {
 				continue

alert/router/router_event.go

@@ -6,7 +6,6 @@ import (
 	"strings"
 	"time"
 
-	"github.com/ccfos/nightingale/v6/alert/common"
 	"github.com/ccfos/nightingale/v6/alert/dispatch"
 	"github.com/ccfos/nightingale/v6/alert/mute"
 	"github.com/ccfos/nightingale/v6/alert/naming"
@@ -92,7 +91,7 @@ func (rt *Router) eventPersist(c *gin.Context) {
 
 type eventForm struct {
 	Alert         bool                  `json:"alert"`
-	AnomalyPoints []common.AnomalyPoint `json:"vectors"`
+	AnomalyPoints []models.AnomalyPoint `json:"vectors"`
 	RuleId        int64                 `json:"rule_id"`
 	DatasourceId  int64                 `json:"datasource_id"`
 	Inhibit       bool                  `json:"inhibit"`
@@ -129,7 +128,7 @@ func (rt *Router) makeEvent(c *gin.Context) {
 		} else {
 			for _, vector := range events[i].AnomalyPoints {
 				readableString := vector.ReadableValue()
-				go ruleWorker.RecoverSingle(process.Hash(events[i].RuleId, events[i].DatasourceId, vector), vector.Timestamp, &readableString)
+				go ruleWorker.RecoverSingle(false, process.Hash(events[i].RuleId, events[i].DatasourceId, vector), vector.Timestamp, &readableString)
 			}
 		}
 	}

alert/sender/callback.go

@@ -129,43 +129,39 @@ func (c *DefaultCallBacker) CallBack(ctx CallBackContext) {
 		return
 	}
 
-	ctx.Stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
-	resp, code, err := poster.PostJSON(ctx.CallBackURL, 5*time.Second, event, 3)
-	if err != nil {
-		logger.Errorf("event_callback_fail(rule_id=%d url=%s), event:%+v, resp: %s, err: %v, code: %d",
-			event.RuleId, ctx.CallBackURL, event, string(resp), err, code)
-		ctx.Stats.AlertNotifyErrorTotal.WithLabelValues("rule_callback").Inc()
-	} else {
-		logger.Infof("event_callback_succ(rule_id=%d url=%s), event:%+v, resp: %s, code: %d",
-			event.RuleId, ctx.CallBackURL, event, string(resp), code)
-	}
+	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, event, "callback", ctx.Stats, ctx.Events)
 }
 
 func doSendAndRecord(ctx *ctx.Context, url, token string, body interface{}, channel string,
-	stats *astats.Stats, event *models.AlertCurEvent) {
+	stats *astats.Stats, events []*models.AlertCurEvent) {
 	res, err := doSend(url, body, channel, stats)
-	NotifyRecord(ctx, event, channel, token, res, err)
+	NotifyRecord(ctx, events, channel, token, res, err)
 }
 
-func NotifyRecord(ctx *ctx.Context, evt *models.AlertCurEvent, channel, target, res string, err error) {
-	noti := models.NewNotificationRecord(evt, channel, target)
-	if err != nil {
-		noti.SetStatus(models.NotiStatusFailure)
-		noti.SetDetails(err.Error())
-	} else if res != "" {
-		noti.SetDetails(string(res))
+func NotifyRecord(ctx *ctx.Context, evts []*models.AlertCurEvent, channel, target, res string, err error) {
+	// 一个通知可能对应多个 event，都需要记录
+	notis := make([]*models.NotificaitonRecord, 0, len(evts))
+	for _, evt := range evts {
+		noti := models.NewNotificationRecord(evt, channel, target)
+		if err != nil {
+			noti.SetStatus(models.NotiStatusFailure)
+			noti.SetDetails(err.Error())
+		} else if res != "" {
+			noti.SetDetails(string(res))
+		}
+		notis = append(notis, noti)
 	}
 
 	if !ctx.IsCenter {
-		_, err := poster.PostByUrlsWithResp[int64](ctx, "/v1/n9e/notify-record", noti)
+		_, err := poster.PostByUrlsWithResp[[]int64](ctx, "/v1/n9e/notify-record", notis)
 		if err != nil {
-			logger.Errorf("add noti:%v failed, err: %v", noti, err)
+			logger.Errorf("add notis:%v failed, err: %v", notis, err)
 		}
 		return
 	}
 
-	if err := noti.Add(ctx); err != nil {
-		logger.Errorf("add noti:%v failed, err: %v", noti, err)
+	if err := models.DB(ctx).CreateInBatches(notis, 100).Error; err != nil {
+		logger.Errorf("add notis:%v failed, err: %v", notis, err)
 	}
 }
 
@@ -195,8 +191,8 @@ func PushCallbackEvent(ctx *ctx.Context, webhook *models.Webhook, event *models.
 
 	if queue == nil {
 		queue = &WebhookQueue{
-			list:    NewSafeListLimited(QueueMaxSize),
-			closeCh: make(chan struct{}),
+			eventQueue: NewSafeEventQueue(QueueMaxSize),
+			closeCh:    make(chan struct{}),
 		}
 
 		CallbackEventQueueLock.Lock()
@@ -206,8 +202,8 @@ func PushCallbackEvent(ctx *ctx.Context, webhook *models.Webhook, event *models.
 		StartConsumer(ctx, queue, webhook.Batch, webhook, stats)
 	}
 
-	succ := queue.list.PushFront(event)
+	succ := queue.eventQueue.Push(event)
 	if !succ {
-		logger.Warningf("Write channel(%s) full, current channel size: %d event:%v", webhook.Url, queue.list.Len(), event)
+		logger.Warningf("Write channel(%s) full, current channel size: %d event:%v", webhook.Url, queue.eventQueue.Len(), event)
 	}
 }

alert/sender/dingtalk.go

@@ -67,7 +67,7 @@ func (ds *DingtalkSender) Send(ctx MessageContext) {
 			}
 		}
 
-		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Dingtalk, ctx.Stats, ctx.Events[0])
+		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Dingtalk, ctx.Stats, ctx.Events)
 	}
 }
 
@@ -97,10 +97,7 @@ func (ds *DingtalkSender) CallBack(ctx CallBackContext) {
 		body.Markdown.Text = message
 	}
 
-	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body,
-		"callback", ctx.Stats, ctx.Events[0])
-
-	ctx.Stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
+	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback", ctx.Stats, ctx.Events)
 }
 
 // extract urls and ats from Users

alert/sender/email.go

@@ -25,8 +25,8 @@ type EmailSender struct {
 }
 
 type EmailContext struct {
-	event *models.AlertCurEvent
-	mail  *gomail.Message
+	events []*models.AlertCurEvent
+	mail   *gomail.Message
 }
 
 func (es *EmailSender) Send(ctx MessageContext) {
@@ -42,7 +42,7 @@ func (es *EmailSender) Send(ctx MessageContext) {
 		subject = ctx.Events[0].RuleName
 	}
 	content := BuildTplMessage(models.Email, es.contentTpl, ctx.Events)
-	es.WriteEmail(subject, content, tos, ctx.Events[0])
+	es.WriteEmail(subject, content, tos, ctx.Events)
 
 	ctx.Stats.AlertNotifyTotal.WithLabelValues(models.Email).Add(float64(len(tos)))
 }
@@ -79,8 +79,7 @@ func SendEmail(subject, content string, tos []string, stmp aconf.SMTPConfig) err
 	return nil
 }
 
-func (es *EmailSender) WriteEmail(subject, content string, tos []string,
-	event *models.AlertCurEvent) {
+func (es *EmailSender) WriteEmail(subject, content string, tos []string, events []*models.AlertCurEvent) {
 	m := gomail.NewMessage()
 
 	m.SetHeader("From", es.smtp.From)
@@ -88,7 +87,7 @@ func (es *EmailSender) WriteEmail(subject, content string, tos []string,
 	m.SetHeader("Subject", subject)
 	m.SetBody("text/html", content)
 
-	mailch <- &EmailContext{event, m}
+	mailch <- &EmailContext{events, m}
 }
 
 func dialSmtp(d *gomail.Dialer) gomail.SendCloser {
@@ -123,7 +122,7 @@ func InitEmailSender(ctx *ctx.Context, ncc *memsto.NotifyConfigCacheType) {
 	mailch = make(chan *EmailContext, 100000)
 	go updateSmtp(ctx, ncc)
 	smtpConfig = ncc.GetSMTP()
-	startEmailSender(ctx, smtpConfig)
+	go startEmailSender(ctx, smtpConfig)
 }
 
 func updateSmtp(ctx *ctx.Context, ncc *memsto.NotifyConfigCacheType) {
@@ -143,6 +142,7 @@ func startEmailSender(ctx *ctx.Context, smtp aconf.SMTPConfig) {
 	conf := smtp
 	if conf.Host == "" || conf.Port == 0 {
 		logger.Warning("SMTP configurations invalid")
+		<-mailQuit
 		return
 	}
 	logger.Infof("start email sender... conf.Host:%+v,conf.Port:%+v", conf.Host, conf.Port)
@@ -201,7 +201,11 @@ func startEmailSender(ctx *ctx.Context, smtp aconf.SMTPConfig) {
 			}
 
 			for _, to := range m.mail.GetHeader("To") {
-				NotifyRecord(ctx, m.event, models.Email, to, "", err)
+				msg := ""
+				if err == nil {
+					msg = "ok"
+				}
+				NotifyRecord(ctx, m.events, models.Email, to, msg, err)
 			}
 
 			size++

alert/sender/feishu.go

@@ -54,9 +54,7 @@ func (fs *FeishuSender) CallBack(ctx CallBackContext) {
 		},
 	}
 
-	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback",
-		ctx.Stats, ctx.Events[0])
-	ctx.Stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
+	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback", ctx.Stats, ctx.Events)
 }
 
 func (fs *FeishuSender) Send(ctx MessageContext) {
@@ -78,7 +76,7 @@ func (fs *FeishuSender) Send(ctx MessageContext) {
 				IsAtAll:   false,
 			}
 		}
-		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Feishu, ctx.Stats, ctx.Events[0])
+		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Feishu, ctx.Stats, ctx.Events)
 	}
 }
 

alert/sender/feishucard.go

@@ -135,8 +135,7 @@ func (fs *FeishuCardSender) CallBack(ctx CallBackContext) {
 	}
 	parsedURL.RawQuery = ""
 
-	doSendAndRecord(ctx.Ctx, parsedURL.String(), parsedURL.String(), body, "callback",
-		ctx.Stats, ctx.Events[0])
+	doSendAndRecord(ctx.Ctx, parsedURL.String(), parsedURL.String(), body, "callback", ctx.Stats, ctx.Events)
 }
 
 func (fs *FeishuCardSender) Send(ctx MessageContext) {
@@ -160,8 +159,7 @@ func (fs *FeishuCardSender) Send(ctx MessageContext) {
 	body.Card.Elements[0].Text.Content = message
 	body.Card.Elements[2].Elements[0].Content = SendTitle
 	for i, url := range urls {
-		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.FeishuCard,
-			ctx.Stats, ctx.Events[0])
+		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.FeishuCard, ctx.Stats, ctx.Events)
 	}
 }
 

alert/sender/ibex.go

@@ -118,6 +118,7 @@ func CallIbex(ctx *ctx.Context, id int64, host string,
 	// 附加告警级别  告警触发值标签
 	tagsMap["alert_severity"] = strconv.Itoa(event.Severity)
 	tagsMap["alert_trigger_value"] = event.TriggerValue
+	tagsMap["is_recovered"] = strconv.FormatBool(event.IsRecovered)
 
 	tags, err := json.Marshal(tagsMap)
 	if err != nil {
@@ -185,6 +186,11 @@ func canDoIbex(username string, tpl *models.TaskTpl, host string, targetCache *m
 }
 
 func TaskAdd(f models.TaskForm, authUser string, isCenter bool) (int64, error) {
+	if storage.Cache == nil {
+		logger.Warning("event_callback_ibex: redis cache is nil")
+		return 0, fmt.Errorf("redis cache is nil")
+	}
+
 	hosts := cleanHosts(f.Hosts)
 	if len(hosts) == 0 {
 		return 0, fmt.Errorf("arg(hosts) empty")

alert/sender/lark.go

@@ -27,30 +27,29 @@ func (lk *LarkSender) CallBack(ctx CallBackContext) {
 		},
 	}
 
-	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback",
-		ctx.Stats, ctx.Events[0])
-	ctx.Stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
+	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback", ctx.Stats, ctx.Events)
 }
 
 func (lk *LarkSender) Send(ctx MessageContext) {
 	if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
 		return
 	}
-	urls := lk.extract(ctx.Users)
+	urls, tokens := lk.extract(ctx.Users)
 	message := BuildTplMessage(models.Lark, lk.tpl, ctx.Events)
-	for _, url := range urls {
+	for i, url := range urls {
 		body := feishu{
 			Msgtype: "text",
 			Content: feishuContent{
 				Text: message,
 			},
 		}
-		doSend(url, body, models.Lark, ctx.Stats)
+		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Lark, ctx.Stats, ctx.Events)
 	}
 }
 
-func (lk *LarkSender) extract(users []*models.User) []string {
+func (lk *LarkSender) extract(users []*models.User) ([]string, []string) {
 	urls := make([]string, 0, len(users))
+	tokens := make([]string, 0, len(users))
 
 	for _, user := range users {
 		if token, has := user.ExtractToken(models.Lark); has {
@@ -59,7 +58,8 @@ func (lk *LarkSender) extract(users []*models.User) []string {
 				url = "https://open.larksuite.com/open-apis/bot/v2/hook/" + token
 			}
 			urls = append(urls, url)
+			tokens = append(tokens, token)
 		}
 	}
-	return urls
+	return urls, tokens
 }

alert/sender/larkcard.go

@@ -56,15 +56,14 @@ func (fs *LarkCardSender) CallBack(ctx CallBackContext) {
 	}
 	parsedURL.RawQuery = ""
 
-	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback",
-		ctx.Stats, ctx.Events[0])
+	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback", ctx.Stats, ctx.Events)
 }
 
 func (fs *LarkCardSender) Send(ctx MessageContext) {
 	if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
 		return
 	}
-	urls, _ := fs.extract(ctx.Users)
+	urls, tokens := fs.extract(ctx.Users)
 	message := BuildTplMessage(models.LarkCard, fs.tpl, ctx.Events)
 	color := "red"
 	lowerUnicode := strings.ToLower(message)
@@ -80,14 +79,14 @@ func (fs *LarkCardSender) Send(ctx MessageContext) {
 	body.Card.Header.Template = color
 	body.Card.Elements[0].Text.Content = message
 	body.Card.Elements[2].Elements[0].Content = SendTitle
-	for _, url := range urls {
-		doSend(url, body, models.LarkCard, ctx.Stats)
+	for i, url := range urls {
+		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.LarkCard, ctx.Stats, ctx.Events)
 	}
 }
 
 func (fs *LarkCardSender) extract(users []*models.User) ([]string, []string) {
 	urls := make([]string, 0, len(users))
-	ats := make([]string, 0)
+	tokens := make([]string, 0)
 	for i := range users {
 		if token, has := users[i].ExtractToken(models.Lark); has {
 			url := token
@@ -95,7 +94,8 @@ func (fs *LarkCardSender) extract(users []*models.User) ([]string, []string) {
 				url = "https://open.larksuite.com/open-apis/bot/v2/hook/" + strings.TrimSpace(token)
 			}
 			urls = append(urls, url)
+			tokens = append(tokens, token)
 		}
 	}
-	return urls, ats
+	return urls, tokens
 }

alert/sender/mm.go

@@ -43,7 +43,7 @@ func (ms *MmSender) Send(ctx MessageContext) {
 		Text:   message,
 		Tokens: urls,
 		Stats:  ctx.Stats,
-	}, ctx.Events[0])
+	}, ctx.Events, models.Mm)
 }
 
 func (ms *MmSender) CallBack(ctx CallBackContext) {
@@ -56,9 +56,7 @@ func (ms *MmSender) CallBack(ctx CallBackContext) {
 		Text:   message,
 		Tokens: []string{ctx.CallBackURL},
 		Stats:  ctx.Stats,
-	}, ctx.Events[0])
-
-	ctx.Stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
+	}, ctx.Events, "callback")
 }
 
 func (ms *MmSender) extract(users []*models.User) []string {
@@ -71,11 +69,12 @@ func (ms *MmSender) extract(users []*models.User) []string {
 	return tokens
 }
 
-func SendMM(ctx *ctx.Context, message MatterMostMessage, event *models.AlertCurEvent) {
+func SendMM(ctx *ctx.Context, message MatterMostMessage, events []*models.AlertCurEvent, channel string) {
 	for i := 0; i < len(message.Tokens); i++ {
 		u, err := url.Parse(message.Tokens[i])
 		if err != nil {
 			logger.Errorf("mm_sender: failed to parse error=%v", err)
+			NotifyRecord(ctx, events, channel, message.Tokens[i], "", err)
 			continue
 		}
 
@@ -104,7 +103,7 @@ func SendMM(ctx *ctx.Context, message MatterMostMessage, event *models.AlertCurE
 				Username: username,
 				Text:     txt + message.Text,
 			}
-			doSendAndRecord(ctx, ur, message.Tokens[i], body, models.Mm, message.Stats, event)
+			doSendAndRecord(ctx, ur, message.Tokens[i], body, channel, message.Stats, events)
 		}
 	}
 }

alert/sender/plugin.go

@@ -85,7 +85,7 @@ func alertingCallScript(ctx *ctx.Context, stdinBytes []byte, notifyScript models
 	}
 
 	err, isTimeout := sys.WrapTimeout(cmd, time.Duration(config.Timeout)*time.Second)
-	NotifyRecord(ctx, event, channel, cmd.String(), "", buildErr(err, isTimeout))
+	NotifyRecord(ctx, []*models.AlertCurEvent{event}, channel, cmd.String(), "", buildErr(err, isTimeout))
 
 	if isTimeout {
 		if err == nil {

alert/sender/telegram.go

@@ -1,6 +1,7 @@
 package sender
 
 import (
+	"errors"
 	"html/template"
 	"strings"
 
@@ -40,9 +41,7 @@ func (ts *TelegramSender) CallBack(ctx CallBackContext) {
 		Text:   message,
 		Tokens: []string{ctx.CallBackURL},
 		Stats:  ctx.Stats,
-	}, ctx.Events[0])
-
-	ctx.Stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
+	}, ctx.Events, "callback")
 }
 
 func (ts *TelegramSender) Send(ctx MessageContext) {
@@ -56,7 +55,7 @@ func (ts *TelegramSender) Send(ctx MessageContext) {
 		Text:   message,
 		Tokens: tokens,
 		Stats:  ctx.Stats,
-	}, ctx.Events[0])
+	}, ctx.Events, models.Telegram)
 }
 
 func (ts *TelegramSender) extract(users []*models.User) []string {
@@ -69,10 +68,11 @@ func (ts *TelegramSender) extract(users []*models.User) []string {
 	return tokens
 }
 
-func SendTelegram(ctx *ctx.Context, message TelegramMessage, event *models.AlertCurEvent) {
+func SendTelegram(ctx *ctx.Context, message TelegramMessage, events []*models.AlertCurEvent, channel string) {
 	for i := 0; i < len(message.Tokens); i++ {
 		if !strings.Contains(message.Tokens[i], "/") && !strings.HasPrefix(message.Tokens[i], "https://") {
 			logger.Errorf("telegram_sender: result=fail invalid token=%s", message.Tokens[i])
+			NotifyRecord(ctx, events, channel, message.Tokens[i], "", errors.New("invalid token"))
 			continue
 		}
 		var url string
@@ -93,6 +93,6 @@ func SendTelegram(ctx *ctx.Context, message TelegramMessage, event *models.Alert
 			Text:      message.Text,
 		}
 
-		doSendAndRecord(ctx, url, message.Tokens[i], body, models.Telegram, message.Stats, event)
+		doSendAndRecord(ctx, url, message.Tokens[i], body, channel, message.Stats, events)
 	}
 }

alert/sender/webhook.go

@@ -59,17 +59,21 @@ func sendWebhook(webhook *models.Webhook, event interface{}, stats *astats.Stats
 	if webhook != nil {
 		insecureSkipVerify = webhook.SkipVerify
 	}
-	client := http.Client{
-		Timeout: time.Duration(conf.Timeout) * time.Second,
-		Transport: &http.Transport{
-			TLSClientConfig: &tls.Config{InsecureSkipVerify: insecureSkipVerify},
-		},
+
+	if conf.Client == nil {
+		logger.Warningf("event_%s, event:%s, url: [%s], error: [%s]", channel, string(bs), conf.Url, "client is nil")
+		conf.Client = &http.Client{
+			Timeout: time.Duration(conf.Timeout) * time.Second,
+			Transport: &http.Transport{
+				TLSClientConfig: &tls.Config{InsecureSkipVerify: insecureSkipVerify},
+			},
+		}
 	}
 
 	stats.AlertNotifyTotal.WithLabelValues(channel).Inc()
 	var resp *http.Response
 	var body []byte
-	resp, err = client.Do(req)
+	resp, err = conf.Client.Do(req)
 
 	if err != nil {
 		stats.AlertNotifyErrorTotal.WithLabelValues(channel).Inc()
@@ -91,12 +95,12 @@ func sendWebhook(webhook *models.Webhook, event interface{}, stats *astats.Stats
 	return false, string(body), nil
 }
 
-func SingleSendWebhooks(ctx *ctx.Context, webhooks []*models.Webhook, event *models.AlertCurEvent, stats *astats.Stats) {
+func SingleSendWebhooks(ctx *ctx.Context, webhooks map[string]*models.Webhook, event *models.AlertCurEvent, stats *astats.Stats) {
 	for _, conf := range webhooks {
 		retryCount := 0
 		for retryCount < 3 {
 			needRetry, res, err := sendWebhook(conf, event, stats)
-			NotifyRecord(ctx, event, "webhook", conf.Url, res, err)
+			NotifyRecord(ctx, []*models.AlertCurEvent{event}, "webhook", conf.Url, res, err)
 			if !needRetry {
 				break
 			}
@@ -106,7 +110,7 @@ func SingleSendWebhooks(ctx *ctx.Context, webhooks []*models.Webhook, event *mod
 	}
 }
 
-func BatchSendWebhooks(ctx *ctx.Context, webhooks []*models.Webhook, event *models.AlertCurEvent, stats *astats.Stats) {
+func BatchSendWebhooks(ctx *ctx.Context, webhooks map[string]*models.Webhook, event *models.AlertCurEvent, stats *astats.Stats) {
 	for _, conf := range webhooks {
 		logger.Infof("push event:%+v to queue:%v", event, conf)
 		PushEvent(ctx, conf, event, stats)
@@ -121,8 +125,8 @@ var EventQueueLock sync.RWMutex
 const QueueMaxSize = 100000
 
 type WebhookQueue struct {
-	list    *SafeListLimited
-	closeCh chan struct{}
+	eventQueue *SafeEventQueue
+	closeCh    chan struct{}
 }
 
 func PushEvent(ctx *ctx.Context, webhook *models.Webhook, event *models.AlertCurEvent, stats *astats.Stats) {
@@ -132,8 +136,8 @@ func PushEvent(ctx *ctx.Context, webhook *models.Webhook, event *models.AlertCur
 
 	if queue == nil {
 		queue = &WebhookQueue{
-			list:    NewSafeListLimited(QueueMaxSize),
-			closeCh: make(chan struct{}),
+			eventQueue: NewSafeEventQueue(QueueMaxSize),
+			closeCh:    make(chan struct{}),
 		}
 
 		EventQueueLock.Lock()
@@ -143,10 +147,10 @@ func PushEvent(ctx *ctx.Context, webhook *models.Webhook, event *models.AlertCur
 		StartConsumer(ctx, queue, webhook.Batch, webhook, stats)
 	}
 
-	succ := queue.list.PushFront(event)
+	succ := queue.eventQueue.Push(event)
 	if !succ {
 		stats.AlertNotifyErrorTotal.WithLabelValues("push_event_queue").Inc()
-		logger.Warningf("Write channel(%s) full, current channel size: %d event:%v", webhook.Url, queue.list.Len(), event)
+		logger.Warningf("Write channel(%s) full, current channel size: %d event:%v", webhook.Url, queue.eventQueue.Len(), event)
 	}
 }
 
@@ -157,7 +161,7 @@ func StartConsumer(ctx *ctx.Context, queue *WebhookQueue, popSize int, webhook *
 			logger.Infof("event queue:%v closed", queue)
 			return
 		default:
-			events := queue.list.PopBack(popSize)
+			events := queue.eventQueue.PopN(popSize)
 			if len(events) == 0 {
 				time.Sleep(time.Millisecond * 400)
 				continue
@@ -166,7 +170,7 @@ func StartConsumer(ctx *ctx.Context, queue *WebhookQueue, popSize int, webhook *
 			retryCount := 0
 			for retryCount < webhook.RetryCount {
 				needRetry, res, err := sendWebhook(webhook, events, stats)
-				go RecordEvents(ctx, webhook, events, stats, res, err)
+				go NotifyRecord(ctx, events, "webhook", webhook.Url, res, err)
 				if !needRetry {
 					break
 				}
@@ -176,10 +180,3 @@ func StartConsumer(ctx *ctx.Context, queue *WebhookQueue, popSize int, webhook *
 		}
 	}
 }
-
-func RecordEvents(ctx *ctx.Context, webhook *models.Webhook, events []*models.AlertCurEvent, stats *astats.Stats, res string, err error) {
-	for _, event := range events {
-		time.Sleep(time.Millisecond * 10)
-		NotifyRecord(ctx, event, "webhook", webhook.Url, res, err)
-	}
-}

alert/sender/webhook_event_queue.go

@@ -0,0 +1,109 @@
+package sender
+
+import (
+	"container/list"
+	"sync"
+
+	"github.com/ccfos/nightingale/v6/models"
+)
+
+type SafeEventQueue struct {
+	lock        sync.RWMutex
+	maxSize     int
+	queueHigh   *list.List
+	queueMiddle *list.List
+	queueLow    *list.List
+}
+
+const (
+	High   = 1
+	Middle = 2
+	Low    = 3
+)
+
+func NewSafeEventQueue(maxSize int) *SafeEventQueue {
+	return &SafeEventQueue{
+		maxSize:     maxSize,
+		lock:        sync.RWMutex{},
+		queueHigh:   list.New(),
+		queueMiddle: list.New(),
+		queueLow:    list.New(),
+	}
+}
+
+func (spq *SafeEventQueue) Len() int {
+	spq.lock.RLock()
+	defer spq.lock.RUnlock()
+	return spq.queueHigh.Len() + spq.queueMiddle.Len() + spq.queueLow.Len()
+}
+
+// len 无锁读取长度，不要在本文件外调用
+func (spq *SafeEventQueue) len() int {
+	return spq.queueHigh.Len() + spq.queueMiddle.Len() + spq.queueLow.Len()
+}
+
+func (spq *SafeEventQueue) Push(event *models.AlertCurEvent) bool {
+	spq.lock.Lock()
+	defer spq.lock.Unlock()
+
+	for spq.len() > spq.maxSize {
+		return false
+	}
+
+	switch event.Severity {
+	case High:
+		spq.queueHigh.PushBack(event)
+	case Middle:
+		spq.queueMiddle.PushBack(event)
+	case Low:
+		spq.queueLow.PushBack(event)
+	default:
+		return false
+	}
+
+	return true
+}
+
+// pop 无锁弹出事件，不要在本文件外调用
+func (spq *SafeEventQueue) pop() *models.AlertCurEvent {
+	if spq.len() == 0 {
+		return nil
+	}
+
+	var elem interface{}
+
+	if spq.queueHigh.Len() > 0 {
+		elem = spq.queueHigh.Remove(spq.queueHigh.Front())
+	} else if spq.queueMiddle.Len() > 0 {
+		elem = spq.queueMiddle.Remove(spq.queueMiddle.Front())
+	} else {
+		elem = spq.queueLow.Remove(spq.queueLow.Front())
+	}
+	event, ok := elem.(*models.AlertCurEvent)
+	if !ok {
+		return nil
+	}
+	return event
+}
+
+func (spq *SafeEventQueue) Pop() *models.AlertCurEvent {
+	spq.lock.Lock()
+	defer spq.lock.Unlock()
+	return spq.pop()
+}
+
+func (spq *SafeEventQueue) PopN(n int) []*models.AlertCurEvent {
+	spq.lock.Lock()
+	defer spq.lock.Unlock()
+
+	events := make([]*models.AlertCurEvent, 0, n)
+	count := 0
+	for count < n && spq.len() > 0 {
+		event := spq.pop()
+		if event != nil {
+			events = append(events, event)
+		}
+		count++
+	}
+	return events
+}

alert/sender/webhook_event_queue_test.go

@@ -0,0 +1,157 @@
+package sender
+
+import (
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/ccfos/nightingale/v6/models"
+	"github.com/stretchr/testify/assert"
+)
+
+func TestSafePriorityQueue_ConcurrentPushPop(t *testing.T) {
+	spq := NewSafeEventQueue(100000)
+
+	var wg sync.WaitGroup
+	numGoroutines := 100
+	numEvents := 1000
+
+	// 并发 Push
+	wg.Add(numGoroutines)
+	for i := 0; i < numGoroutines; i++ {
+		go func(goroutineID int) {
+			defer wg.Done()
+			for j := 0; j < numEvents; j++ {
+				event := &models.AlertCurEvent{
+					Severity:    goroutineID%3 + 1,
+					TriggerTime: time.Now().UnixNano(),
+				}
+				spq.Push(event)
+			}
+		}(i)
+	}
+	wg.Wait()
+
+	// 检查队列长度是否正确
+	expectedLen := numGoroutines * numEvents
+	assert.Equal(t, expectedLen, spq.Len(), "Queue length mismatch after concurrent pushes")
+
+	// 并发 Pop
+	wg.Add(numGoroutines)
+	for i := 0; i < numGoroutines; i++ {
+		go func() {
+			defer wg.Done()
+			for {
+				event := spq.Pop()
+				if event == nil {
+					return
+				}
+			}
+		}()
+	}
+	wg.Wait()
+
+	// 最终队列应该为空
+	assert.Equal(t, 0, spq.Len(), "Queue should be empty after concurrent pops")
+}
+
+func TestSafePriorityQueue_ConcurrentPopMax(t *testing.T) {
+	spq := NewSafeEventQueue(100000)
+
+	// 添加初始数据
+	for i := 0; i < 1000; i++ {
+		spq.Push(&models.AlertCurEvent{
+			Severity:    i%3 + 1,
+			TriggerTime: time.Now().UnixNano(),
+		})
+	}
+
+	var wg sync.WaitGroup
+	numGoroutines := 10
+	popMax := 100
+
+	// 并发 PopN
+	wg.Add(numGoroutines)
+	for i := 0; i < numGoroutines; i++ {
+		go func() {
+			defer wg.Done()
+			events := spq.PopN(popMax)
+			assert.LessOrEqual(t, len(events), popMax, "PopN exceeded maximum")
+		}()
+	}
+	wg.Wait()
+
+	// 检查队列长度是否正确
+	expectedRemaining := 1000 - (numGoroutines * popMax)
+	if expectedRemaining < 0 {
+		expectedRemaining = 0
+	}
+	assert.Equal(t, expectedRemaining, spq.Len(), "Queue length mismatch after concurrent PopN")
+}
+
+func TestSafePriorityQueue_ConcurrentPushPopWithDifferentSeverities(t *testing.T) {
+	spq := NewSafeEventQueue(100000)
+
+	var wg sync.WaitGroup
+	numGoroutines := 50
+	numEvents := 500
+
+	// 并发 Push 不同优先级的事件
+	wg.Add(numGoroutines)
+	for i := 0; i < numGoroutines; i++ {
+		go func(goroutineID int) {
+			defer wg.Done()
+			for j := 0; j < numEvents; j++ {
+				event := &models.AlertCurEvent{
+					Severity:    goroutineID%3 + 1, // 模拟不同的 Severity
+					TriggerTime: time.Now().UnixNano(),
+				}
+				spq.Push(event)
+			}
+		}(i)
+	}
+	wg.Wait()
+
+	// 检查队列长度是否正确
+	expectedLen := numGoroutines * numEvents
+	assert.Equal(t, expectedLen, spq.Len(), "Queue length mismatch after concurrent pushes")
+
+	// 检查事件的顺序是否按照优先级排列
+	var lastEvent *models.AlertCurEvent
+	for spq.Len() > 0 {
+		event := spq.Pop()
+		if lastEvent != nil {
+			assert.LessOrEqual(t, lastEvent.Severity, event.Severity, "Events are not in correct priority order")
+		}
+		lastEvent = event
+	}
+}
+
+func TestSafePriorityQueue_ExceedMaxSize(t *testing.T) {
+	spq := NewSafeEventQueue(5)
+
+	// 插入超过最大容量的事件
+	for i := 0; i < 10; i++ {
+		spq.Push(&models.AlertCurEvent{
+			Severity:    i % 3,
+			TriggerTime: int64(i),
+		})
+	}
+
+	// 验证队列的长度是否不超过 maxSize
+	assert.LessOrEqual(t, spq.Len(), spq.maxSize)
+
+	// 验证队列中剩余事件的内容
+	expectedEvents := 5
+	if spq.Len() < 5 {
+		expectedEvents = spq.Len()
+	}
+
+	// 检查最后存入的事件是否是按优先级排序
+	for i := 0; i < expectedEvents; i++ {
+		event := spq.Pop()
+		if event != nil {
+			assert.LessOrEqual(t, event.Severity, 2)
+		}
+	}
+}

alert/sender/wecom.go

@@ -37,9 +37,7 @@ func (ws *WecomSender) CallBack(ctx CallBackContext) {
 		},
 	}
 
-	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback",
-		ctx.Stats, ctx.Events[0])
-	ctx.Stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
+	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback", ctx.Stats, ctx.Events)
 }
 
 func (ws *WecomSender) Send(ctx MessageContext) {
@@ -55,7 +53,7 @@ func (ws *WecomSender) Send(ctx MessageContext) {
 				Content: message,
 			},
 		}
-		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Wecom, ctx.Stats, ctx.Events[0])
+		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Wecom, ctx.Stats, ctx.Events)
 	}
 }
 

center/center.go

@@ -6,6 +6,7 @@ import (
 
 	"github.com/ccfos/nightingale/v6/alert"
 	"github.com/ccfos/nightingale/v6/alert/astats"
+	"github.com/ccfos/nightingale/v6/alert/dispatch"
 	"github.com/ccfos/nightingale/v6/alert/process"
 	alertrt "github.com/ccfos/nightingale/v6/alert/router"
 	"github.com/ccfos/nightingale/v6/center/cconf"
@@ -48,6 +49,10 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 
 	cconf.MergeOperationConf()
 
+	if config.Alert.Heartbeat.EngineName == "" {
+		config.Alert.Heartbeat.EngineName = "default"
+	}
+
 	logxClean, err := logx.Init(config.Log)
 	if err != nil {
 		return nil, err
@@ -63,7 +68,7 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 	}
 	ctx := ctx.NewContext(context.Background(), db, true)
 	migrate.Migrate(db)
-	models.InitRoot(ctx)
+	isRootInit := models.InitRoot(ctx)
 
 	config.HTTP.JWTAuth.SigningKey = models.InitJWTSigningKey(ctx)
 
@@ -95,9 +100,13 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 	userCache := memsto.NewUserCache(ctx, syncStats)
 	userGroupCache := memsto.NewUserGroupCache(ctx, syncStats)
 	taskTplCache := memsto.NewTaskTplCache(ctx)
+	configCvalCache := memsto.NewCvalCache(ctx, syncStats)
 
 	sso := sso.Init(config.Center, ctx, configCache)
 	promClients := prom.NewPromClient(ctx)
+
+	dispatch.InitRegisterQueryFunc(promClients)
+
 	tdengineClients := tdengine.NewTdengineClient(ctx, config.Alert.Heartbeat)
 
 	externalProcessors := process.NewExternalProcessors()
@@ -115,9 +124,13 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 		redis, sso, ctx, metas, idents, targetCache, userCache, userGroupCache)
 	pushgwRouter := pushgwrt.New(config.HTTP, config.Pushgw, config.Alert, targetCache, busiGroupCache, idents, metas, writers, ctx)
 
-	go models.MigrateBg(ctx, pushgwRouter.Pushgw.BusiGroupLabelKey)
+	go func() {
+		if config.Center.MigrateBusiGroupLabel || models.CanMigrateBg(ctx) {
+			models.MigrateBg(ctx, pushgwRouter.Pushgw.BusiGroupLabelKey)
+		}
+	}()
 
-	r := httpx.GinEngine(config.Global.RunMode, config.HTTP)
+	r := httpx.GinEngine(config.Global.RunMode, config.HTTP, configCvalCache.PrintBodyPaths, configCvalCache.PrintAccessLog)
 
 	centerRouter.Config(r)
 	alertrtRouter.Config(r)
@@ -131,6 +144,11 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 
 	httpClean := httpx.Init(config.HTTP, r)
 
+	fmt.Printf("please view n9e at  http://%v:%v\n", config.Alert.Heartbeat.IP, config.HTTP.Port)
+	if isRootInit {
+		fmt.Println("username/password: root/root.2020")
+	}
+
 	return func() {
 		logxClean()
 		httpClean()

center/integration/init.go

@@ -113,6 +113,12 @@ func Init(ctx *ctx.Context, builtinIntegrationsDir string) {
 			logger.Warning("delete builtin metrics fail ", err)
 		}
 
+		// 删除 uuid%1000 不为 0 uuid > 1000000000000000000 且 type 为 dashboard 的记录
+		err = models.DB(ctx).Exec("delete from builtin_payloads where uuid%1000 != 0 and uuid > 1000000000000000000 and type = 'dashboard' and updated_by = 'system'").Error
+		if err != nil {
+			logger.Warning("delete builtin payloads fail ", err)
+		}
+
 		// alerts
 		files, err = file.FilesUnder(componentDir + "/alerts")
 		if err == nil && len(files) > 0 {
@@ -218,7 +224,8 @@ func Init(ctx *ctx.Context, builtinIntegrationsDir string) {
 				}
 
 				if dashboard.UUID == 0 {
-					dashboard.UUID = time.Now().UnixNano()
+					time.Sleep(time.Microsecond)
+					dashboard.UUID = time.Now().UnixMicro()
 					// 补全文件中的 uuid
 					bs, err = json.MarshalIndent(dashboard, "", "    ")
 					if err != nil {

center/router/router.go

@@ -184,6 +184,7 @@ func (rt *Router) Config(r *gin.Engine) {
 			pages.POST("/query-range-batch", rt.promBatchQueryRange)
 			pages.POST("/query-instant-batch", rt.promBatchQueryInstant)
 			pages.GET("/datasource/brief", rt.datasourceBriefs)
+			pages.POST("/datasource/query", rt.datasourceQuery)
 
 			pages.POST("/ds-query", rt.QueryData)
 			pages.POST("/logs-query", rt.QueryLog)
@@ -197,6 +198,7 @@ func (rt *Router) Config(r *gin.Engine) {
 			pages.POST("/query-range-batch", rt.auth(), rt.promBatchQueryRange)
 			pages.POST("/query-instant-batch", rt.auth(), rt.promBatchQueryInstant)
 			pages.GET("/datasource/brief", rt.auth(), rt.user(), rt.datasourceBriefs)
+			pages.POST("/datasource/query", rt.auth(), rt.user(), rt.datasourceQuery)
 
 			pages.POST("/ds-query", rt.auth(), rt.QueryData)
 			pages.POST("/logs-query", rt.auth(), rt.QueryLog)
@@ -278,6 +280,7 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.DELETE("/busi-group/:id/members", rt.auth(), rt.user(), rt.perm("/busi-groups/put"), rt.bgrw(), rt.busiGroupMemberDel)
 		pages.DELETE("/busi-group/:id", rt.auth(), rt.user(), rt.perm("/busi-groups/del"), rt.bgrw(), rt.busiGroupDel)
 		pages.GET("/busi-group/:id/perm/:perm", rt.auth(), rt.user(), rt.checkBusiGroupPerm)
+		pages.GET("/busi-groups/tags", rt.auth(), rt.user(), rt.busiGroupsGetTags)
 
 		pages.GET("/targets", rt.auth(), rt.user(), rt.targetGets)
 		pages.GET("/target/extra-meta", rt.auth(), rt.user(), rt.targetExtendInfoByIdent)
@@ -552,6 +555,7 @@ func (rt *Router) Config(r *gin.Engine) {
 			service.GET("/config/:id", rt.configGet)
 			service.GET("/configs", rt.configsGet)
 			service.GET("/config", rt.configGetByKey)
+			service.GET("/all-configs", rt.configGetAll)
 			service.PUT("/configs", rt.configsPut)
 			service.POST("/configs", rt.configsPost)
 			service.DELETE("/configs", rt.configsDel)

center/router/router_alert_rule.go

@@ -77,6 +77,11 @@ func (rt *Router) alertRuleGetsByGids(c *gin.Context) {
 		for i := 0; i < len(ars); i++ {
 			ars[i].FillNotifyGroups(rt.Ctx, cache)
 			ars[i].FillSeverities()
+
+			if len(ars[i].DatasourceQueries) != 0 {
+				ars[i].DatasourceIdsJson = rt.DatasourceCache.GetIDsByDsCateAndQueries(ars[i].Cate, ars[i].DatasourceQueries)
+			}
+
 			rids = append(rids, ars[i].Id)
 			names = append(names, ars[i].UpdateBy)
 		}
@@ -123,6 +128,10 @@ func (rt *Router) alertRulesGetByService(c *gin.Context) {
 		cache := make(map[int64]*models.UserGroup)
 		for i := 0; i < len(ars); i++ {
 			ars[i].FillNotifyGroups(rt.Ctx, cache)
+
+			if len(ars[i].DatasourceQueries) != 0 {
+				ars[i].DatasourceIdsJson = rt.DatasourceCache.GetIDsByDsCateAndQueries(ars[i].Cate, ars[i].DatasourceQueries)
+			}
 		}
 	}
 	ginx.NewRender(c).Data(ars, err)
@@ -157,6 +166,14 @@ func (rt *Router) alertRuleAddByImport(c *gin.Context) {
 		ginx.Bomb(http.StatusBadRequest, "input json is empty")
 	}
 
+	for i := range lst {
+		if len(lst[i].DatasourceQueries) == 0 {
+			lst[i].DatasourceQueries = []models.DatasourceQuery{
+				models.DataSourceQueryAll,
+			}
+		}
+	}
+
 	bgid := ginx.UrlParamInt64(c, "id")
 	reterr := rt.alertRuleAdd(lst, username, bgid, c.GetHeader("X-Language"))
 
@@ -164,9 +181,9 @@ func (rt *Router) alertRuleAddByImport(c *gin.Context) {
 }
 
 type promRuleForm struct {
-	Payload       string  `json:"payload" binding:"required"`
-	DatasourceIds []int64 `json:"datasource_ids" binding:"required"`
-	Disabled      int     `json:"disabled" binding:"gte=0,lte=1"`
+	Payload           string                   `json:"payload" binding:"required"`
+	DatasourceQueries []models.DatasourceQuery `json:"datasource_queries" binding:"required"`
+	Disabled          int                      `json:"disabled" binding:"gte=0,lte=1"`
 }
 
 func (rt *Router) alertRuleAddByImportPromRule(c *gin.Context) {
@@ -185,7 +202,7 @@ func (rt *Router) alertRuleAddByImportPromRule(c *gin.Context) {
 		ginx.Bomb(http.StatusBadRequest, "input yaml is empty")
 	}
 
-	lst := models.DealPromGroup(pr.Groups, f.DatasourceIds, f.Disabled)
+	lst := models.DealPromGroup(pr.Groups, f.DatasourceQueries, f.Disabled)
 	username := c.MustGet("username").(string)
 	bgid := ginx.UrlParamInt64(c, "id")
 	ginx.NewRender(c).Data(rt.alertRuleAdd(lst, username, bgid, c.GetHeader("X-Language")), nil)
@@ -398,6 +415,16 @@ func (rt *Router) alertRulePutFields(c *gin.Context) {
 			}
 		}
 
+		if f.Action == "datasource_change" {
+			// 修改数据源
+			if datasourceQueries, has := f.Fields["datasource_queries"]; has {
+				bytes, err := json.Marshal(datasourceQueries)
+				ginx.Dangerous(err)
+				ginx.Dangerous(ar.UpdateFieldsMap(rt.Ctx, map[string]interface{}{"datasource_queries": bytes}))
+				continue
+			}
+		}
+
 		for k, v := range f.Fields {
 			ginx.Dangerous(ar.UpdateColumn(rt.Ctx, k, v))
 		}
@@ -417,6 +444,10 @@ func (rt *Router) alertRuleGet(c *gin.Context) {
 		return
 	}
 
+	if len(ar.DatasourceQueries) != 0 {
+		ar.DatasourceIdsJson = rt.DatasourceCache.GetIDsByDsCateAndQueries(ar.Cate, ar.DatasourceQueries)
+	}
+
 	err = ar.FillNotifyGroups(rt.Ctx, make(map[int64]*models.UserGroup))
 	ginx.Dangerous(err)
 
@@ -623,7 +654,7 @@ func (rt *Router) cloneToMachine(c *gin.Context) {
 			newRule.CreateAt = now
 			newRule.RuleConfig = alertRules[i].RuleConfig
 
-			exist, err := models.AlertRuleExists(rt.Ctx, 0, newRule.GroupId, newRule.DatasourceIdsJson, newRule.Name)
+			exist, err := models.AlertRuleExists(rt.Ctx, 0, newRule.GroupId, newRule.Name)
 			if err != nil {
 				errMsg[f.IdentList[j]] = err.Error()
 				continue

center/router/router_builtin_payload.go

@@ -43,7 +43,7 @@ func (rt *Router) builtinPayloadsAdd(c *gin.Context) {
 
 				for _, rule := range alertRules {
 					if rule.UUID == 0 {
-						rule.UUID = time.Now().UnixNano()
+						rule.UUID = time.Now().UnixMicro()
 					}
 
 					contentBytes, err := json.Marshal(rule)
@@ -78,7 +78,13 @@ func (rt *Router) builtinPayloadsAdd(c *gin.Context) {
 			}
 
 			if alertRule.UUID == 0 {
-				alertRule.UUID = time.Now().UnixNano()
+				alertRule.UUID = time.Now().UnixMicro()
+			}
+
+			contentBytes, err := json.Marshal(alertRule)
+			if err != nil {
+				reterr[alertRule.Name] = err.Error()
+				continue
 			}
 
 			bp := models.BuiltinPayload{
@@ -88,7 +94,7 @@ func (rt *Router) builtinPayloadsAdd(c *gin.Context) {
 				Name:        alertRule.Name,
 				Tags:        alertRule.AppendTags,
 				UUID:        alertRule.UUID,
-				Content:     lst[i].Content,
+				Content:     string(contentBytes),
 				CreatedBy:   username,
 				UpdatedBy:   username,
 			}
@@ -106,7 +112,7 @@ func (rt *Router) builtinPayloadsAdd(c *gin.Context) {
 
 				for _, dashboard := range dashboards {
 					if dashboard.UUID == 0 {
-						dashboard.UUID = time.Now().UnixNano()
+						dashboard.UUID = time.Now().UnixMicro()
 					}
 
 					contentBytes, err := json.Marshal(dashboard)
@@ -141,7 +147,13 @@ func (rt *Router) builtinPayloadsAdd(c *gin.Context) {
 			}
 
 			if dashboard.UUID == 0 {
-				dashboard.UUID = time.Now().UnixNano()
+				dashboard.UUID = time.Now().UnixMicro()
+			}
+
+			contentBytes, err := json.Marshal(dashboard)
+			if err != nil {
+				reterr[dashboard.Name] = err.Error()
+				continue
 			}
 
 			bp := models.BuiltinPayload{
@@ -151,7 +163,7 @@ func (rt *Router) builtinPayloadsAdd(c *gin.Context) {
 				Name:        dashboard.Name,
 				Tags:        dashboard.Tags,
 				UUID:        dashboard.UUID,
-				Content:     lst[i].Content,
+				Content:     string(contentBytes),
 				CreatedBy:   username,
 				UpdatedBy:   username,
 			}

center/router/router_busi_group.go

@@ -140,3 +140,12 @@ func (rt *Router) busiGroupGet(c *gin.Context) {
 	ginx.Dangerous(bg.FillUserGroups(rt.Ctx))
 	ginx.NewRender(c).Data(bg, nil)
 }
+
+func (rt *Router) busiGroupsGetTags(c *gin.Context) {
+	bgids := str.IdsInt64(ginx.QueryStr(c, "gids", ""), ",")
+	targetIdents, err := models.TargetIndentsGetByBgids(rt.Ctx, bgids)
+	ginx.Dangerous(err)
+	tags, err := models.TargetGetTags(rt.Ctx, targetIdents, true, "busigroup")
+	ginx.Dangerous(err)
+	ginx.NewRender(c).Data(tags, nil)
+}

center/router/router_configs.go

@@ -24,6 +24,11 @@ func (rt *Router) configGet(c *gin.Context) {
 	ginx.NewRender(c).Data(configs, err)
 }
 
+func (rt *Router) configGetAll(c *gin.Context) {
+	config, err := models.ConfigsGetAll(rt.Ctx)
+	ginx.NewRender(c).Data(config, err)
+}
+
 func (rt *Router) configGetByKey(c *gin.Context) {
 	config, err := models.ConfigsGet(rt.Ctx, ginx.QueryStr(c, "key"))
 	ginx.NewRender(c).Data(config, err)

center/router/router_datasource.go

@@ -122,12 +122,14 @@ func (rt *Router) datasourceUpsert(c *gin.Context) {
 }
 
 func DatasourceCheck(ds models.Datasource) error {
-	if ds.HTTPJson.Url == "" {
-		return fmt.Errorf("url is empty")
-	}
+	if ds.PluginType != models.ELASTICSEARCH {
+		if ds.HTTPJson.Url == "" {
+			return fmt.Errorf("url is empty")
+		}
 
-	if !strings.HasPrefix(ds.HTTPJson.Url, "http") {
-		return fmt.Errorf("url must start with http or https")
+		if !strings.HasPrefix(ds.HTTPJson.Url, "http") {
+			return fmt.Errorf("url must start with http or https")
+		}
 	}
 
 	client := &http.Client{
@@ -138,11 +140,11 @@ func DatasourceCheck(ds models.Datasource) error {
 		},
 	}
 
-	fullURL := ds.HTTPJson.Url
-	req, err := http.NewRequest("GET", fullURL, nil)
+	var fullURL string
+	req, err := ds.HTTPJson.NewReq(&fullURL)
 	if err != nil {
 		logger.Errorf("Error creating request: %v", err)
-		return fmt.Errorf("request url:%s failed", fullURL)
+		return fmt.Errorf("request urls:%v failed", ds.HTTPJson.GetUrls())
 	}
 
 	if ds.PluginType == models.PROMETHEUS {
@@ -249,3 +251,37 @@ func (rt *Router) getDatasourceIds(c *gin.Context) {
 
 	ginx.NewRender(c).Data(datasourceIds, err)
 }
+
+type datasourceQueryForm struct {
+	Cate              string                   `json:"datasource_cate"`
+	DatasourceQueries []models.DatasourceQuery `json:"datasource_queries"`
+}
+
+type datasourceQueryResp struct {
+	ID   int64  `json:"id"`
+	Name string `json:"name"`
+}
+
+func (rt *Router) datasourceQuery(c *gin.Context) {
+	var dsf datasourceQueryForm
+	ginx.BindJSON(c, &dsf)
+	datasources, err := models.GetDatasourcesGetsByTypes(rt.Ctx, []string{dsf.Cate})
+	ginx.Dangerous(err)
+
+	nameToID := make(map[string]int64)
+	IDToName := make(map[int64]string)
+	for _, ds := range datasources {
+		nameToID[ds.Name] = ds.Id
+		IDToName[ds.Id] = ds.Name
+	}
+
+	ids := models.GetDatasourceIDsByDatasourceQueries(dsf.DatasourceQueries, IDToName, nameToID)
+	var req []datasourceQueryResp
+	for _, id := range ids {
+		req = append(req, datasourceQueryResp{
+			ID:   id,
+			Name: IDToName[id],
+		})
+	}
+	ginx.NewRender(c).Data(req, err)
+}

center/router/router_funcs.go

@@ -45,6 +45,10 @@ func (rt *Router) statistic(c *gin.Context) {
 		statistics, err = models.ConfigsUserVariableStatistics(rt.Ctx)
 		ginx.NewRender(c).Data(statistics, err)
 		return
+	case "cval":
+		statistics, err = models.ConfigCvalStatistics(rt.Ctx)
+		ginx.NewRender(c).Data(statistics, err)
+		return
 	default:
 		ginx.Bomb(http.StatusBadRequest, "invalid name")
 	}

center/router/router_heartbeat.go

@@ -100,7 +100,7 @@ func HandleHeartbeat(c *gin.Context, ctx *ctx.Context, engineName string, metaSe
 				groupIds = append(groupIds, groupId)
 			}
 
-			err := models.TargetOverrideBgids(ctx, []string{target.Ident}, groupIds)
+			err := models.TargetOverrideBgids(ctx, []string{target.Ident}, groupIds, nil)
 			if err != nil {
 				logger.Warningf("update target:%s group ids failed, err: %v", target.Ident, err)
 			}
@@ -113,7 +113,7 @@ func HandleHeartbeat(c *gin.Context, ctx *ctx.Context, engineName string, metaSe
 				}
 
 				if !target.MatchGroupId(groupId) {
-					err := models.TargetBindBgids(ctx, []string{target.Ident}, []int64{groupId})
+					err := models.TargetBindBgids(ctx, []string{target.Ident}, []int64{groupId}, nil)
 					if err != nil {
 						logger.Warningf("update target:%s group ids failed, err: %v", target.Ident, err)
 					}

center/router/router_mute.go

@@ -50,7 +50,8 @@ func (rt *Router) alertMuteGets(c *gin.Context) {
 	prods := strings.Fields(ginx.QueryStr(c, "prods", ""))
 	bgid := ginx.QueryInt64(c, "bgid", -1)
 	query := ginx.QueryStr(c, "query", "")
-	lst, err := models.AlertMuteGets(rt.Ctx, prods, bgid, query)
+	disabled := ginx.QueryInt(c, "disabled", -1)
+	lst, err := models.AlertMuteGets(rt.Ctx, prods, bgid, disabled, query)
 
 	ginx.NewRender(c).Data(lst, err)
 }

center/router/router_notification_record.go

@@ -35,11 +35,18 @@ type Record struct {
 
 // notificationRecordAdd
 func (rt *Router) notificationRecordAdd(c *gin.Context) {
-	var req models.NotificaitonRecord
+	var req []*models.NotificaitonRecord
 	ginx.BindJSON(c, &req)
-	err := req.Add(rt.Ctx)
+	err := models.DB(rt.Ctx).CreateInBatches(req, 100).Error
+	var ids []int64
+	if err == nil {
+		ids = make([]int64, len(req))
+		for i, noti := range req {
+			ids[i] = noti.Id
+		}
+	}
 
-	ginx.NewRender(c).Data(req.Id, err)
+	ginx.NewRender(c).Data(ids, err)
 }
 
 func (rt *Router) notificationRecordList(c *gin.Context) {

center/router/router_notify_tpl.go

@@ -161,7 +161,11 @@ func (rt *Router) notifyTplPreview(c *gin.Context) {
 func (rt *Router) notifyTplAdd(c *gin.Context) {
 	var f models.NotifyTpl
 	ginx.BindJSON(c, &f)
-	f.Channel = strings.TrimSpace(f.Channel)
+
+        user := c.MustGet("user").(*models.User)
+        f.CreateBy = user.Username
+	
+        f.Channel = strings.TrimSpace(f.Channel)
 	ginx.Dangerous(templateValidate(f))
 
 	count, err := models.Count(models.DB(rt.Ctx).Model(&models.NotifyTpl{}).Where("channel = ? or name = ?", f.Channel, f.Name))
@@ -169,6 +173,8 @@ func (rt *Router) notifyTplAdd(c *gin.Context) {
 	if count != 0 {
 		ginx.Bomb(200, "Refuse to create duplicate channel(unique)")
 	}
+
+        f.CreateAt = time.Now().Unix()
 	ginx.NewRender(c).Message(f.Create(rt.Ctx))
 }
 

center/router/router_proxy.go

@@ -7,7 +7,6 @@ import (
 	"net"
 	"net/http"
 	"net/http/httputil"
-	"net/url"
 	"strings"
 	"sync"
 	"time"
@@ -112,9 +111,9 @@ func (rt *Router) dsProxy(c *gin.Context) {
 		return
 	}
 
-	target, err := url.Parse(ds.HTTPJson.Url)
+	target, err := ds.HTTPJson.ParseUrl()
 	if err != nil {
-		c.String(http.StatusInternalServerError, "invalid  url: %s", ds.HTTPJson.Url)
+		c.String(http.StatusInternalServerError, "invalid urls: %s", ds.HTTPJson.GetUrls())
 		return
 	}
 

center/router/router_recording_rule.go

@@ -3,8 +3,6 @@ package router
 import (
 	"encoding/json"
 	"net/http"
-	"strconv"
-	"strings"
 	"time"
 
 	"github.com/ccfos/nightingale/v6/models"
@@ -74,6 +72,14 @@ func (rt *Router) recordingRuleAddByFE(c *gin.Context) {
 		ginx.Bomb(http.StatusBadRequest, "input json is empty")
 	}
 
+	for i := range lst {
+		if len(lst[i].DatasourceQueries) == 0 {
+			lst[i].DatasourceQueries = []models.DatasourceQuery{
+				models.DataSourceQueryAll,
+			}
+		}
+	}
+
 	bgid := ginx.UrlParamInt64(c, "id")
 	reterr := make(map[string]string)
 	for i := 0; i < count; i++ {
@@ -137,23 +143,10 @@ func (rt *Router) recordingRulePutFields(c *gin.Context) {
 	f.Fields["update_by"] = c.MustGet("username").(string)
 	f.Fields["update_at"] = time.Now().Unix()
 
-	if _, ok := f.Fields["datasource_ids"]; ok {
-		// datasource_ids = "1 2 3"
-		idsStr := strings.Fields(f.Fields["datasource_ids"].(string))
-		ids := make([]int64, 0)
-		for _, idStr := range idsStr {
-			id, err := strconv.ParseInt(idStr, 10, 64)
-			if err != nil {
-				ginx.Bomb(http.StatusBadRequest, "datasource_ids error")
-			}
-			ids = append(ids, id)
-		}
-
-		bs, err := json.Marshal(ids)
-		if err != nil {
-			ginx.Bomb(http.StatusBadRequest, "datasource_ids error")
-		}
-		f.Fields["datasource_ids"] = string(bs)
+	if datasourceQueries, ok := f.Fields["datasource_queries"]; ok {
+		bytes, err := json.Marshal(datasourceQueries)
+		ginx.Dangerous(err)
+		f.Fields["datasource_queries"] = string(bytes)
 	}
 
 	for i := 0; i < len(f.Ids); i++ {

center/router/router_target.go

@@ -169,7 +169,7 @@ func (rt *Router) targetGetTags(c *gin.Context) {
 	idents := ginx.QueryStr(c, "idents", "")
 	idents = strings.ReplaceAll(idents, ",", " ")
 	ignoreHostTag := ginx.QueryBool(c, "ignore_host_tag", false)
-	lst, err := models.TargetGetTags(rt.Ctx, strings.Fields(idents), ignoreHostTag)
+	lst, err := models.TargetGetTags(rt.Ctx, strings.Fields(idents), ignoreHostTag, "")
 	ginx.NewRender(c).Data(lst, err)
 }
 
@@ -397,6 +397,7 @@ type targetBgidsForm struct {
 	Idents  []string `json:"idents" binding:"required_without=HostIps"`
 	HostIps []string `json:"host_ips" binding:"required_without=Idents"`
 	Bgids   []int64  `json:"bgids"`
+	Tags    []string `json:"tags"`
 	Action  string   `json:"action"` // add del reset
 }
 
@@ -452,11 +453,11 @@ func (rt *Router) targetBindBgids(c *gin.Context) {
 
 	switch f.Action {
 	case "add":
-		ginx.NewRender(c).Data(failedResults, models.TargetBindBgids(rt.Ctx, f.Idents, f.Bgids))
+		ginx.NewRender(c).Data(failedResults, models.TargetBindBgids(rt.Ctx, f.Idents, f.Bgids, f.Tags))
 	case "del":
 		ginx.NewRender(c).Data(failedResults, models.TargetUnbindBgids(rt.Ctx, f.Idents, f.Bgids))
 	case "reset":
-		ginx.NewRender(c).Data(failedResults, models.TargetOverrideBgids(rt.Ctx, f.Idents, f.Bgids))
+		ginx.NewRender(c).Data(failedResults, models.TargetOverrideBgids(rt.Ctx, f.Idents, f.Bgids, f.Tags))
 	default:
 		ginx.Bomb(http.StatusBadRequest, "invalid action")
 	}
@@ -478,7 +479,7 @@ func (rt *Router) targetUpdateBgidByService(c *gin.Context) {
 		ginx.Bomb(http.StatusBadRequest, err.Error())
 	}
 
-	ginx.NewRender(c).Data(failedResults, models.TargetOverrideBgids(rt.Ctx, f.Idents, []int64{f.Bgid}))
+	ginx.NewRender(c).Data(failedResults, models.TargetOverrideBgids(rt.Ctx, f.Idents, []int64{f.Bgid}, nil))
 }
 
 type identsForm struct {

cli/upgrade/config.go

@@ -33,7 +33,7 @@ type ClusterOptions struct {
 	MaxIdleConnsPerHost int
 }
 
-func Parse(fpath string, configPtr interface{}) error {
+func Parse(fpath string, configPtr *Config) error {
 	var (
 		tBuf []byte
 	)

cmd/edge/edge.go

@@ -7,6 +7,7 @@ import (
 
 	"github.com/ccfos/nightingale/v6/alert"
 	"github.com/ccfos/nightingale/v6/alert/astats"
+	"github.com/ccfos/nightingale/v6/alert/dispatch"
 	"github.com/ccfos/nightingale/v6/alert/process"
 	alertrt "github.com/ccfos/nightingale/v6/alert/router"
 	"github.com/ccfos/nightingale/v6/center/metas"
@@ -52,11 +53,13 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 
 	targetCache := memsto.NewTargetCache(ctx, syncStats, redis)
 	busiGroupCache := memsto.NewBusiGroupCache(ctx, syncStats)
+	configCvalCache := memsto.NewCvalCache(ctx, syncStats)
 	idents := idents.New(ctx, redis)
 	metas := metas.New(redis)
 	writers := writer.NewWriters(config.Pushgw)
 	pushgwRouter := pushgwrt.New(config.HTTP, config.Pushgw, config.Alert, targetCache, busiGroupCache, idents, metas, writers, ctx)
-	r := httpx.GinEngine(config.Global.RunMode, config.HTTP)
+	r := httpx.GinEngine(config.Global.RunMode, config.HTTP, configCvalCache.PrintBodyPaths, configCvalCache.PrintAccessLog)
+
 	pushgwRouter.Config(r)
 
 	if !config.Alert.Disable {
@@ -71,6 +74,9 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 		taskTplsCache := memsto.NewTaskTplCache(ctx)
 
 		promClients := prom.NewPromClient(ctx)
+
+		dispatch.InitRegisterQueryFunc(promClients)
+
 		tdengineClients := tdengine.NewTdengineClient(ctx, config.Alert.Heartbeat)
 		externalProcessors := process.NewExternalProcessors()
 

docker/compose-bridge/docker-compose.yaml

@@ -1,5 +1,3 @@
-version: "3.7"
-
 networks:
   nightingale:
     driver: bridge

docker/compose-bridge/etc-categraf/config.toml

@@ -19,8 +19,8 @@ precision = "ms"
 # global collect interval
 interval = 15
 
-[global.labels]
-source="categraf"
+# [global.labels]
+# source="categraf"
 # region = "shanghai"
 # env = "localhost"
 

docker/compose-bridge/etc-categraf/input.mysql/mysql.toml

@@ -0,0 +1,42 @@
+[[instances]]
+address = "mysql:3306"
+username = "root"
+password = "1234"
+
+# # set tls=custom to enable tls
+# parameters = "tls=false"
+
+# extra_status_metrics = true
+# extra_innodb_metrics = false
+# gather_processlist_processes_by_state = false
+# gather_processlist_processes_by_user = false
+# gather_schema_size = true
+# gather_table_size = false
+# gather_system_table_size = false
+# gather_slave_status = true
+
+# # timeout
+# timeout_seconds = 3
+
+# # interval = global.interval * interval_times
+# interval_times = 1
+
+# important! use global unique string to specify instance
+labels = { instance="docker-compose-mysql" }
+
+## Optional TLS Config
+# use_tls = false
+# tls_min_version = "1.2"
+# tls_ca = "/etc/categraf/ca.pem"
+# tls_cert = "/etc/categraf/cert.pem"
+# tls_key = "/etc/categraf/key.pem"
+## Use TLS but skip chain & host verification
+# insecure_skip_verify = true
+
+#[[instances.queries]]
+# mesurement = "lock_wait"
+# metric_fields = [ "total" ]
+# timeout = "3s"
+# request = '''
+#SELECT count(*) as total FROM information_schema.innodb_trx WHERE trx_state='LOCK WAIT'
+#'''

docker/compose-bridge/etc-categraf/input.redis/redis.toml

@@ -0,0 +1,37 @@
+[[instances]]
+address = "redis:6379"
+username = ""
+password = ""
+# pool_size = 2
+
+## 是否开启slowlog 收集
+# gather_slowlog = true
+## 最多收集少条slowlog
+# slowlog_max_len = 100
+## 收集距离现在多少秒以内的slowlog
+## 注意插件的采集周期,该参数不要小于采集周期，否则会有slowlog查不到
+# slowlog_time_window=30
+
+# 指标
+# redis_slow_log{ident=dev-01 client_addr=127.0.0.1:56364 client_name= cmd="info ALL" log_id=983} 74 (单位微秒)
+
+# # Optional. Specify redis commands to retrieve values
+# commands = [
+#     {command = ["get", "sample-key1"], metric = "custom_metric_name1"},
+#     {command = ["get", "sample-key2"], metric = "custom_metric_name2"}
+# ]
+
+# # interval = global.interval * interval_times
+# interval_times = 1
+
+# important! use global unique string to specify instance
+labels = { instance="docker-compose-redis" }
+
+## Optional TLS Config
+# use_tls = false
+# tls_min_version = "1.2"
+# tls_ca = "/etc/categraf/ca.pem"
+# tls_cert = "/etc/categraf/cert.pem"
+# tls_key = "/etc/categraf/key.pem"
+## Use TLS but skip chain & host verification
+# insecure_skip_verify = true

docker/compose-host-network/docker-compose.yaml

@@ -25,7 +25,7 @@ services:
     network_mode: host
 
   prometheus:
-    image: prom/prometheus
+    image: prom/prometheus:v2.55.1
     container_name: prometheus
     hostname: prometheus
     restart: always

docker/initsql/c-init.sql

@@ -1,3 +1,10 @@
-GRANT ALL ON *.* TO 'root'@'127.0.0.1' IDENTIFIED BY '1234';
-GRANT ALL ON *.* TO 'root'@'localhost' IDENTIFIED BY '1234';
-GRANT ALL ON *.* TO 'root'@'%' IDENTIFIED BY '1234';
+CREATE USER IF NOT EXISTS 'root'@'127.0.0.1' IDENTIFIED BY '1234';
+GRANT ALL PRIVILEGES ON *.* TO 'root'@'127.0.0.1' WITH GRANT OPTION;
+
+CREATE USER IF NOT EXISTS 'root'@'localhost' IDENTIFIED BY '1234';
+GRANT ALL PRIVILEGES ON *.* TO 'root'@'localhost' WITH GRANT OPTION;
+
+CREATE USER IF NOT EXISTS 'root'@'%' IDENTIFIED BY '1234';
+GRANT ALL PRIVILEGES ON *.* TO 'root'@'%' WITH GRANT OPTION;
+
+FLUSH PRIVILEGES;

docker/migratesql/migrate.sql

@@ -116,4 +116,8 @@ CREATE TABLE `target_busi_group` (
   `update_at` bigint NOT NULL,
   PRIMARY KEY (`id`),
   UNIQUE KEY `idx_target_group` (`target_ident`,`group_id`)
-) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
+
+/* v7.7.2 2024-12-02 */
+ALTER TABLE alert_subscribe MODIFY COLUMN rule_ids varchar(1024);
+ALTER TABLE alert_subscribe MODIFY COLUMN busi_groups varchar(4096);

etc/config.toml

@@ -73,14 +73,14 @@ DefaultRoles = ["Standard"]
 OpenRSA = false
 
 [DB]
+# mysql postgres sqlite
+DBType = "sqlite"
 # postgres: host=%s port=%s user=%s dbname=%s password=%s sslmode=%s
 # postgres: DSN="host=127.0.0.1 port=5432 user=root dbname=n9e_v6 password=1234 sslmode=disable"
 # sqlite: DSN="/path/to/filename.db"
-DSN = "root:1234@tcp(127.0.0.1:3306)/n9e_v6?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"
+DSN = "n9e.db"
 # enable debug mode or not
 Debug = false
-# mysql postgres sqlite
-DBType = "mysql"
 # unit: s
 MaxLifetime = 7200
 # max open connections
@@ -98,8 +98,8 @@ Address = "127.0.0.1:6379"
 # DB = 0
 # UseTLS = false
 # TLSMinVersion = "1.2"
-# standalone cluster sentinel
-RedisType = "standalone"
+# standalone cluster sentinel miniredis
+RedisType = "miniredis"
 # Mastername for sentinel type
 # MasterName = "mymaster"
 # SentinelUsername = ""
@@ -138,6 +138,9 @@ ForceUseServerTS = true
 # [Pushgw.WriterOpt]
 # QueueMaxSize = 1000000
 # QueuePopSize = 1000
+# AllQueueMaxSize = 1000000
+# fresh time, unit ms
+# AllQueueMaxSizeInterval = 200
 
 [[Pushgw.Writers]] 
 # Url = "http://127.0.0.1:8480/insert/0/prometheus/api/v1/write"

go.mod

@@ -1,6 +1,6 @@
 module github.com/ccfos/nightingale/v6
 
-go 1.18
+go 1.22
 
 require (
 	github.com/BurntSushi/toml v0.3.1
@@ -32,8 +32,9 @@ require (
 	github.com/rakyll/statik v0.1.7
 	github.com/redis/go-redis/v9 v9.0.2
 	github.com/spaolacci/murmur3 v1.1.0
+	github.com/stretchr/testify v1.8.4
 	github.com/tidwall/gjson v1.14.0
-	github.com/toolkits/pkg v1.3.6
+	github.com/toolkits/pkg v1.3.8
 	golang.org/x/exp v0.0.0-20230713183714-613f0c0eb8a1
 	golang.org/x/oauth2 v0.10.0
 	gopkg.in/gomail.v2 v2.0.0-20160411212932-81ebce5c23df
@@ -44,8 +45,15 @@ require (
 	gorm.io/gorm v1.25.7-0.20240204074919-46816ad31dde
 )
 
+require (
+	github.com/alicebob/gopher-json v0.0.0-20200520072559-a9ecdc9d1d3a // indirect
+	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
+	github.com/yuin/gopher-lua v1.1.1 // indirect
+)
+
 require (
 	github.com/Azure/go-ntlmssp v0.0.0-20220621081337-cb9428e4ac1e // indirect
+	github.com/alicebob/miniredis/v2 v2.33.0
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/bytedance/sonic v1.9.1 // indirect
 	github.com/cespare/xxhash/v2 v2.2.0 // indirect
@@ -87,7 +95,7 @@ require (
 	github.com/prometheus/client_model v0.4.0 // indirect
 	github.com/prometheus/procfs v0.11.0 // indirect
 	github.com/robfig/cron/v3 v3.0.1
-	github.com/tidwall/match v1.1.1 // indirect
+	github.com/tidwall/match v1.1.1
 	github.com/tidwall/pretty v1.2.0 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
 	github.com/ugorji/go/codec v1.2.11 // indirect
@@ -97,7 +105,7 @@ require (
 	golang.org/x/crypto v0.21.0 // indirect
 	golang.org/x/image v0.18.0 // indirect
 	golang.org/x/net v0.23.0 // indirect
-	golang.org/x/sys v0.18.0 // indirect
+	golang.org/x/sys v0.21.0 // indirect
 	golang.org/x/text v0.16.0 // indirect
 	google.golang.org/appengine v1.6.7 // indirect
 	google.golang.org/protobuf v1.33.0 // indirect

go.sum

@@ -1,20 +1,32 @@
 github.com/Azure/azure-sdk-for-go v65.0.0+incompatible h1:HzKLt3kIwMm4KeJYTdx9EbjRYTySD/t8i1Ee/W5EGXw=
 github.com/Azure/azure-sdk-for-go/sdk/azcore v1.7.0 h1:8q4SaHjFsClSvuVne0ID/5Ka8u3fcIHyqkLjcFpNRHQ=
+github.com/Azure/azure-sdk-for-go/sdk/azcore v1.7.0/go.mod h1:bjGvMhVMb+EEm3VRNQawDMUyMMjo+S5ewNjflkep/0Q=
 github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.3.0 h1:vcYCAze6p19qBW7MhZybIsqD8sMV8js0NyQM8JDnVtg=
+github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.3.0/go.mod h1:OQeznEEkTZ9OrhHJoDD8ZDq51FHgXjqtP9z6bEwBq9U=
 github.com/Azure/azure-sdk-for-go/sdk/internal v1.3.0 h1:sXr+ck84g/ZlZUOZiNELInmMgOsuGwdjjVkEIde0OtY=
+github.com/Azure/azure-sdk-for-go/sdk/internal v1.3.0/go.mod h1:okt5dMMTOFjX/aovMlrjvvXoPMBVSPzk9185BT0+eZM=
 github.com/Azure/go-ntlmssp v0.0.0-20220621081337-cb9428e4ac1e h1:NeAW1fUYUEWhft7pkxDf6WoUvEZJ/uOKsvtpjLnn8MU=
 github.com/Azure/go-ntlmssp v0.0.0-20220621081337-cb9428e4ac1e/go.mod h1:chxPXzSsl7ZWRAuOIE23GDNzjWuZquvFlgA8xmpunjU=
 github.com/AzureAD/microsoft-authentication-library-for-go v1.0.0 h1:OBhqkivkhkMqLPymWEppkm7vgPQY2XsHoEkaMQ0AdZY=
+github.com/AzureAD/microsoft-authentication-library-for-go v1.0.0/go.mod h1:kgDmCTgBzIEPFElEF+FK0SdjAor06dRq2Go927dnQ6o=
 github.com/BurntSushi/toml v0.3.1 h1:WXkYYl6Yr3qBf1K79EBnL4mak0OimBfB0XUf9Vl28OQ=
 github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
 github.com/Masterminds/semver/v3 v3.1.1 h1:hLg3sBzpNErnxhQtUy/mmLR2I9foDujNK030IGemrRc=
 github.com/Masterminds/semver/v3 v3.1.1/go.mod h1:VPu/7SZ7ePZ3QOrcuXROw5FAcLl4a0cBrbBpGY/8hQs=
 github.com/alecthomas/units v0.0.0-20211218093645-b94a6e3cc137 h1:s6gZFSlWYmbqAuRjVTiNNhvNRfY2Wxp9nhfyel4rklc=
+github.com/alecthomas/units v0.0.0-20211218093645-b94a6e3cc137/go.mod h1:OMCwj8VM1Kc9e19TLln2VL61YJF0x1XFtfdL4JdbSyE=
+github.com/alicebob/gopher-json v0.0.0-20200520072559-a9ecdc9d1d3a h1:HbKu58rmZpUGpz5+4FfNmIU+FmZg2P3Xaj2v2bfNWmk=
+github.com/alicebob/gopher-json v0.0.0-20200520072559-a9ecdc9d1d3a/go.mod h1:SGnFV6hVsYE877CKEZ6tDNTjaSXYUk6QqoIK6PrAtcc=
+github.com/alicebob/miniredis/v2 v2.33.0 h1:uvTF0EDeu9RLnUEG27Db5I68ESoIxTiXbNUiji6lZrA=
+github.com/alicebob/miniredis/v2 v2.33.0/go.mod h1:MhP4a3EU7aENRi9aO+tHfTBZicLqQevyi/DJpoj6mi0=
 github.com/aws/aws-sdk-go v1.44.302 h1:ST3ko6GrJKn3Xi+nAvxjG3uk/V1pW8KC52WLeIxqqNk=
+github.com/aws/aws-sdk-go v1.44.302/go.mod h1:aVsgQcEevwlmQ7qHE9I3h+dtQgpqhFB+i8Phjh7fkwI=
 github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
 github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
 github.com/bsm/ginkgo/v2 v2.5.0 h1:aOAnND1T40wEdAtkGSkvSICWeQ8L3UASX7YVCqQx+eQ=
+github.com/bsm/ginkgo/v2 v2.5.0/go.mod h1:AiKlXPm7ItEHNc/2+OkrNG4E0ITzojb9/xWzvQ9XZ9w=
 github.com/bsm/gomega v1.20.0 h1:JhAwLmtRzXFTx2AkALSLa8ijZafntmhSoU63Ok18Uq8=
+github.com/bsm/gomega v1.20.0/go.mod h1:JifAceMQ4crZIWYUKrlGcmbN3bqHogVTADMD2ATsbwk=
 github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=
 github.com/bytedance/sonic v1.9.1 h1:6iJ6NqdoxCDr6mbY8h18oSO+cShGSMRGCEo7F2h0x8s=
 github.com/bytedance/sonic v1.9.1/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZXU064P/U=
@@ -94,6 +106,7 @@ github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69
 github.com/golang-jwt/jwt v3.2.2+incompatible h1:IfV12K8xAKAnZqdXVzCZ+TOjboZ2keLg81eXfW3O+oY=
 github.com/golang-jwt/jwt v3.2.2+incompatible/go.mod h1:8pz2t5EyA70fFQQSrl6XZXzqecmYZeUEB8OUGHkxJ+I=
 github.com/golang-jwt/jwt/v4 v4.5.0 h1:7cYmW1XlMY7h7ii7UhUyChSgS5wUJEnm9uZVTGqOWzg=
+github.com/golang-jwt/jwt/v4 v4.5.0/go.mod h1:m21LjoU+eqJr34lmDMbreY2eSTRJ1cv77w39/MY0Ch0=
 github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0 h1:DACJavvAHhabrF08vX0COfcOBJRhZ8lUbR+ZWIs0Y5g=
 github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0/go.mod h1:E/TSTwGwJL78qG/PmXZO1EjYhfJinVAhrmmHX6Z8B9k=
 github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
@@ -105,6 +118,7 @@ github.com/golang/snappy v0.0.4 h1:yAGX7huGHXlcLOEtBnF4w7FQwA26wojNCwOYAEhLjQM=
 github.com/golang/snappy v0.0.4/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38=
+github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/renameio v0.1.0/go.mod h1:KWCgfxg9yswjAJkECMjeO8J8rahYeXnNhOm40UhjYkI=
 github.com/google/uuid v1.3.0 h1:t6JiXgmwXMjEs8VusXIJk2BXHsn+wx8BZdTaoZ5fu7I=
@@ -168,14 +182,17 @@ github.com/jinzhu/now v1.1.4/go.mod h1:d3SSVoowX0Lcu0IBviAWJpolVfI5UJVZZ7cO71lE/
 github.com/jinzhu/now v1.1.5 h1:/o9tlHleP7gOFmsnYNz3RGnqzefHA47wQpKrrdTIwXQ=
 github.com/jinzhu/now v1.1.5/go.mod h1:d3SSVoowX0Lcu0IBviAWJpolVfI5UJVZZ7cO71lE/z8=
 github.com/jmespath/go-jmespath v0.4.0 h1:BEgLn5cpjn8UN1mAw4NjwDrS35OdebyEtFe+9YPoQUg=
+github.com/jmespath/go-jmespath v0.4.0/go.mod h1:T8mJZnbsbmF+m6zOOFylbeCJqk5+pHWvzYPziyZiYoo=
 github.com/josharian/intern v1.0.0 h1:vlS4z54oSdjm0bgjRigI+G1HpF+tI+9rE5LLzOg8HmY=
 github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=
 github.com/jpillora/backoff v1.0.0 h1:uvFg412JmmHBHw7iwprIxkPMI+sGQ4kzOWsMeHnm2EA=
+github.com/jpillora/backoff v1.0.0/go.mod h1:J/6gKK9jxlEcS3zixgDgUAsiuZ7yrSoa/FX5e0EB2j4=
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
 github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8=
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
 github.com/klauspost/compress v1.16.7 h1:2mk3MPGNzKyxErAw8YaohYh69+pa4sIQSC0fPGCFR9I=
+github.com/klauspost/compress v1.16.7/go.mod h1:ntbaceVETuRiXiv4DpjP66DpAtAGkEQskQzEyD//IeE=
 github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
 github.com/klauspost/cpuid/v2 v2.2.4 h1:acbojRNwl3o09bUq+yDCtZFc1aiwaAAxtcn8YkZXnvk=
 github.com/klauspost/cpuid/v2 v2.2.4/go.mod h1:RVVoqg1df56z8g3pUjL/3lE5UfnlrJX8tyFgg4nqhuY=
@@ -187,12 +204,14 @@ github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORN
 github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
 github.com/kr/pretty v0.3.0/go.mod h1:640gp4NfQd8pI5XOwp5fnNeVWj67G7CFk/SaSQn7NBk=
 github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
+github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
 github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
 github.com/kr/pty v1.1.8/go.mod h1:O1sed60cT9XZ5uDucP5qwvh+TE3NnUj51EiZO/lmSfw=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
+github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
 github.com/leodido/go-urn v1.2.1/go.mod h1:zt4jvISO2HfUBqxjfIshjdMTYS56ZS/qv49ictyFfxY=
 github.com/leodido/go-urn v1.2.4 h1:XlAE/cm/ms7TE/VMVoduSpNBoyc2dOxHs5MZSwAN63Q=
 github.com/leodido/go-urn v1.2.4/go.mod h1:7ZrI8mTSeBSHl/UaRyKQW1qZeMgak41ANeCNaVckg+4=
@@ -223,20 +242,25 @@ github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjY
 github.com/mojocn/base64Captcha v1.3.6 h1:gZEKu1nsKpttuIAQgWHO+4Mhhls8cAKyiV2Ew03H+Tw=
 github.com/mojocn/base64Captcha v1.3.6/go.mod h1:i5CtHvm+oMbj1UzEPXaA8IH/xHFZ3DGY3Wh3dBpZ28E=
 github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f h1:KUppIJq7/+SVif2QVs3tOP0zanoHgBEVAwHxUSIzRqU=
+github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
 github.com/oklog/ulid v1.3.1 h1:EGfNDEx6MqHz8B3uNV6QAib1UR2Lm97sHi3ocA6ESJ4=
+github.com/oklog/ulid v1.3.1/go.mod h1:CirwcVhetQ6Lv90oh/F+FBtV6XMibvdAFo93nm5qn4U=
 github.com/pelletier/go-toml/v2 v2.0.1/go.mod h1:r9LEWfGN8R5k0VXJ+0BkIe7MYkRdwZOjgMj2KwnJFUo=
 github.com/pelletier/go-toml/v2 v2.0.8 h1:0ctb6s9mE31h0/lhu+J6OPmVeDxJn+kYnJc2jZR9tGQ=
 github.com/pelletier/go-toml/v2 v2.0.8/go.mod h1:vuYfssBdrU2XDZ9bYydBu6t+6a6PYNcZljzZR9VXg+4=
 github.com/pkg/browser v0.0.0-20210911075715-681adbf594b8 h1:KoWmjvw+nsYOo29YJK9vDA65RGE3NrOnUtO7a+RF9HU=
+github.com/pkg/browser v0.0.0-20210911075715-681adbf594b8/go.mod h1:HKlIX3XHQyzLZPlr7++PzdhaXEj94dEiJgZDTsxEqUI=
 github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
 github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
+github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/pquerna/cachecontrol v0.1.0 h1:yJMy84ti9h/+OEWa752kBTKv4XC30OtVVHYv/8cTqKc=
 github.com/pquerna/cachecontrol v0.1.0/go.mod h1:NrUG3Z7Rdu85UNR3vm7SOsl1nFIeSiQnrHV5K9mBcUI=
 github.com/prashantv/gostub v1.1.0 h1:BTyx3RfQjRHnUWaGF9oQos79AlQ5k8WNktv7VGvVH4g=
+github.com/prashantv/gostub v1.1.0/go.mod h1:A5zLQHz7ieHGG7is6LLXLz7I8+3LZzsrV0P1IAHhP5U=
 github.com/prometheus/client_golang v1.16.0 h1:yk/hx9hDbrGHovbci4BY+pRMfSuuat626eFsHb7tmT8=
 github.com/prometheus/client_golang v1.16.0/go.mod h1:Zsulrv/L9oM40tJ7T815tM89lFEugiJ9HzIqaAx4LKc=
 github.com/prometheus/client_model v0.4.0 h1:5lQXD3cAg1OXBf4Wq03gTrXHeaV0TQvGfUooCfx1yqY=
@@ -244,6 +268,7 @@ github.com/prometheus/client_model v0.4.0/go.mod h1:oMQmHW1/JoDwqLtg57MGgP/Fb1CJ
 github.com/prometheus/common v0.44.0 h1:+5BrQJwiBB9xsMygAB3TNvpQKOwlkc25LbISbrdOOfY=
 github.com/prometheus/common v0.44.0/go.mod h1:ofAIvZbQ1e/nugmZGz4/qCb9Ap1VoSTIO7x0VV9VvuY=
 github.com/prometheus/common/sigv4 v0.1.0 h1:qoVebwtwwEhS85Czm2dSROY5fTo2PAPEVdDeppTwGX4=
+github.com/prometheus/common/sigv4 v0.1.0/go.mod h1:2Jkxxk9yYvCkE5G1sQT7GuEXm57JrvHu9k5YwTjsNtI=
 github.com/prometheus/procfs v0.11.0 h1:5EAgkfkMl659uZPbe9AS2N68a7Cc1TJbPEuGzFuRbyk=
 github.com/prometheus/procfs v0.11.0/go.mod h1:nwNm2aOCAYw8uTR/9bWRREkZFxAUcWzPHWJq+XBB/FM=
 github.com/prometheus/prometheus v0.47.1 h1:bd2LiZyxzHn9Oo2Ei4eK2D86vz/L/OiqR1qYo0XmMBo=
@@ -259,6 +284,7 @@ github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFR
 github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc=
 github.com/rogpeppe/go-internal v1.8.0/go.mod h1:WmiCO8CzOY8rg0OYDC4/i/2WRWAB6poM+XZ2dLUbcbE=
 github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
+github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog=
 github.com/rs/xid v1.2.1/go.mod h1:+uKXf+4Djp6Md1KODXJxgGQPKngRmWyn10oCKFzNHOQ=
 github.com/rs/zerolog v1.13.0/go.mod h1:YbFCdg8HfsridGWAh22vktObvhZbQsZXe4/zB0OKkWU=
 github.com/rs/zerolog v1.15.0/go.mod h1:xYTKnLHcpfU2225ny5qZjxnj9NvkumZYjJHlAThCjNc=
@@ -288,14 +314,15 @@ github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o
 github.com/stretchr/testify v1.8.2/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
 github.com/stretchr/testify v1.8.3/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
+github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 github.com/tidwall/gjson v1.14.0 h1:6aeJ0bzojgWLa82gDQHcx3S0Lr/O51I9bJ5nv6JFx5w=
 github.com/tidwall/gjson v1.14.0/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
 github.com/tidwall/match v1.1.1 h1:+Ho715JplO36QYgwN9PGYNhgZvoUSc9X2c80KVTi+GA=
 github.com/tidwall/match v1.1.1/go.mod h1:eRSPERbgtNPcGhD8UCthc6PmLEQXEWd3PRB5JTxsfmM=
 github.com/tidwall/pretty v1.2.0 h1:RWIZEg2iJ8/g6fDDYzMpobmaoGh5OLl4AXtGUGPcqCs=
 github.com/tidwall/pretty v1.2.0/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=
-github.com/toolkits/pkg v1.3.6 h1:47e1amsY6mJmcnF3Y2lIpkJXfoYY2RmgI09PtwdAEMU=
-github.com/toolkits/pkg v1.3.6/go.mod h1:M9ecwFGW1vxCTUFM9sr2ZjXSKb04N+1sTQ6SA3RNAIU=
+github.com/toolkits/pkg v1.3.8 h1:2yamC20c5mHRtbcGiLY99Lm/2mVitFn6onE8KKvMT1o=
+github.com/toolkits/pkg v1.3.8/go.mod h1:M9ecwFGW1vxCTUFM9sr2ZjXSKb04N+1sTQ6SA3RNAIU=
 github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS4MhqMhdFk5YI=
 github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08=
 github.com/ugorji/go v1.2.7/go.mod h1:nF9osbDWLy6bDVv/Rtoh6QgnvNDpmCalQV5urGCCS6M=
@@ -305,6 +332,8 @@ github.com/ugorji/go/codec v1.2.11/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZ
 github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
+github.com/yuin/gopher-lua v1.1.1 h1:kYKnWBjvbNP4XLT3+bPEwAXJx262OhaHDWDVOPjL46M=
+github.com/yuin/gopher-lua v1.1.1/go.mod h1:GBR0iDaNXjAgGg9zfCvksxSRnQx76gclCIb7kdAd1Pw=
 github.com/zenazn/goji v0.9.0/go.mod h1:7S9M489iMyHBNxwZnk9/EHS098H4/F6TATF2mIxtB1Q=
 go.uber.org/atomic v1.3.2/go.mod h1:gD2HeocX3+yG+ygLZcrzQJaqmWj9AIm7n08wl/qW/PE=
 go.uber.org/atomic v1.4.0/go.mod h1:gD2HeocX3+yG+ygLZcrzQJaqmWj9AIm7n08wl/qW/PE=
@@ -316,6 +345,7 @@ go.uber.org/automaxprocs v1.4.0/go.mod h1:/mTEdr7LvHhs0v7mjdxDreTz1OG5zdZGqgOnhW
 go.uber.org/automaxprocs v1.5.2 h1:2LxUOGiR3O6tw8ui5sZa2LAaHnsviZdVOUZw4fvbnME=
 go.uber.org/automaxprocs v1.5.2/go.mod h1:eRbA25aqJrxAbsLO0xy5jVwPt7FQnRgjW+efnwa1WM0=
 go.uber.org/goleak v1.2.1 h1:NBol2c7O1ZokfZ0LEU9K6Whx/KnwvepVetCUhtKja4A=
+go.uber.org/goleak v1.2.1/go.mod h1:qlT2yGI9QafXHhZZLxlSuNsMw3FFLxBr+tBRlmO1xH4=
 go.uber.org/multierr v1.1.0/go.mod h1:wR5kodmAFQ0UK8QlbwjlSNy0Z68gJhDJUG5sjR94q/0=
 go.uber.org/multierr v1.3.0/go.mod h1:VgVr7evmIr6uPjLBxg28wmKNXyqE9akIJ5XnfpiKl+4=
 go.uber.org/multierr v1.5.0/go.mod h1:FeouvMocqHpRaaGuG9EjoKcStLC43Zu/fmqdUMPcKYU=
@@ -378,6 +408,7 @@ golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJ
 golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.7.0 h1:YsImfSBoP9QPYL0xyKJPq0gcaJdG3rInoqxTWbfQu9M=
+golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190222072716-a9d3bda3a223/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
@@ -400,8 +431,8 @@ golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.18.0 h1:DBdB3niSjOA/O0blCZBqDefyWNYveAYMNF1Wum0DYQ4=
-golang.org/x/sys v0.18.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.21.0 h1:rF+pYz3DAGSQAxAu1CbC7catZg4ebC4UIeIhKxBZvws=
+golang.org/x/sys v0.21.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201117132131-f5c789dd3221/go.mod h1:Nr5EML6q2oocZ2LXRh80K7BxOlk5/8JxuGnuhpl+muw=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=

integrations/AppDynamics/markdown/README.md

@@ -1,6 +1,6 @@
-## Appdynamics
+## AppDynamics
 
-Appdynamics 采集插件， 采集 Appdynamics 数据
+AppDynamics 采集插件， 采集 AppDynamics 数据
 
 ## Configuration
 

integrations/AutoMQ/dashboards/cluster_overview.json

@@ -584,7 +584,7 @@
                     "links": [
                         {
                             "title": "下钻",
-                            "url": "/dashboards/automq-group-metrics?TSDB=${DS_PROMETHEUS}\u0026cluster_id=${cluster_id}\u0026group_id=${__field.labels.consumer_group}\u0026partition=all\u0026topic=${__field.labels.topic}"
+                            "url": "/built-in-components/dashboard/detail?__uuid__=1717556327172992000&TSDB=${DS_PROMETHEUS}\u0026cluster_id=${cluster_id}\u0026group_id=${__field.labels.consumer_group}\u0026partition=all\u0026topic=${__field.labels.topic}"
                         }
                     ],
                     "showHeader": true
@@ -669,7 +669,7 @@
                     "links": [
                         {
                             "title": "下钻",
-                            "url": "/dashboards/automq-topic-metrics?TSDB=${DS_PROMETHEUS}\u0026cluster_id=${cluster_id}\u0026topic=${__field.labels.topic}"
+                            "url": "/built-in-components/dashboard/detail?__uuid__=1717556327174664000&TSDB=${DS_PROMETHEUS}\u0026cluster_id=${cluster_id}\u0026topic=${__field.labels.topic}"
                         }
                     ],
                     "showHeader": true
@@ -781,7 +781,7 @@
                     "links": [
                         {
                             "title": "下钻",
-                            "url": "/dashboards/automq-broker-metrics?DS_PROMETHEUS=${DS_PROMETHEUS}\u0026cluster_id=${cluster_id}\u0026node_id=${__field.labels.instance}"
+                            "url": "/built-in-components/dashboard/detail?__uuid__=1717556327159415000&DS_PROMETHEUS=${DS_PROMETHEUS}\u0026cluster_id=${cluster_id}\u0026node_id=${__field.labels.instance}"
                         }
                     ],
                     "showHeader": true

integrations/Bind/collect/bind/bind.toml

@@ -0,0 +1,8 @@
+[[instances]]
+urls = [
+    # "http://localhost:8053/xml/v3",
+]
+gather_memory_contexts = true
+gather_views = true
+timeout = "5s"
+# labels={app="bind"}

integrations/Bind/markdown/README.md

@@ -0,0 +1,13 @@
+forked from [telegraf/snmp](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/bind)
+
+配置示例
+```
+[[instances]]
+urls = [
+ #"http://localhost:8053/xml/v3",
+]
+
+timeout = "5s"
+gather_memory_contexts = true
+gather_views = true
+```

integrations/Canal/markdown/README.md

@@ -0,0 +1,3 @@
+## canal
+
+canal 默认提供了 prometheus 格式指标的接口 [Prometheus-QuickStart](https://github.com/alibaba/canal/wiki/Prometheus-QuickStart) ，所以可以直接通过[ prometheus 插件](https://flashcat.cloud/docs/content/flashcat-monitor/categraf/plugin/prometheus)采集。

integrations/Doris/collect/prometheus/collect_doris_examples.toml

@@ -0,0 +1,22 @@
+# doris_fe
+[[instances]]
+# 配置 fe metrics 服务地址
+urls = [
+     "http://127.0.0.1:8030/metrics"
+]
+
+url_label_key = "instance"
+url_label_value = "{{.Host}}"
+# 指定 fe 服务 group 和 job 标签，这里是仪表盘变量调用，可根据实际需求修改。
+labels = { group = "fe",job = "doris_cluster01"}
+
+# doris_be
+[[instances]]
+# 配置 be metrics 服务地址
+urls = [
+     "http://127.0.0.1:8040/metrics"
+]
+url_label_key = "instance"
+url_label_value = "{{.Host}}"
+# 指定 be 服务 group 和 job 标签，这里是仪表盘变量调用，可根据实际需求修改。
+labels = { group = "be",job = "doris_cluster01"}

integrations/Doris/icon/doris.svg

@@ -0,0 +1,26 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!-- Generator: Adobe Illustrator 27.6.1, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
+<svg version="1.1" id="图层_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
+	 viewBox="0 0 30 30" style="enable-background:new 0 0 30 30;" xml:space="preserve">
+<style type="text/css">
+	.st0{fill:#00A5CA;}
+	.st1{fill:#3ACA9B;}
+	.st2{fill:#405AAD;}
+</style>
+<g>
+	<g>
+		<g>
+			<path class="st0" d="M17.4,4.6l-3.3-3.3c-0.4-0.4-0.9-0.8-1.5-1C12.1,0.1,11.5,0,11,0C9.9,0,8.8,0.4,8,1.2C7.6,1.6,7.3,2,7.1,2.6
+				c-0.3,0.5-0.4,1-0.4,1.6S6.8,5.3,7,5.9c0.2,0.5,0.5,1,0.9,1.4l5.9,5.9c0.1,0.1,0.3,0.2,0.5,0.2s0.3-0.1,0.5-0.2l2.6-2.6
+				C17.6,10.5,20.2,7.4,17.4,4.6z"/>
+			<path class="st1" d="M22.8,9.8c-0.6-0.6-1.3-1.2-1.9-1.9l0,0c0,0.1,0,0.1,0,0.2c-0.2,1.4-0.9,2.7-2,3.7
+				c-3.4,3.4-6.9,6.9-10.3,10.3l-0.5,0.5c-0.7,0.6-1.2,1.5-1.3,2.4c-0.1,0.7,0,1.3,0.2,2c0.2,0.6,0.5,1.2,1,1.7
+				c0.4,0.4,0.9,0.8,1.4,1c0.5,0.2,1.1,0.3,1.7,0.3c1.3,0,2-0.2,3-1.1c3.9-3.8,7.8-7.7,10.8-10.6c1.4-1.4,1.7-3.7,0.7-5.2
+				C24.8,11.8,23.8,10.8,22.8,9.8z"/>
+			<path class="st2" d="M3.8,7.8v14.5c0,0.2,0,0.3,0.1,0.4C4,22.8,4.1,22.9,4.3,23c0.1,0,0.3,0,0.5,0c0.2,0,0.3-0.1,0.4-0.2l7.3-7.3
+				c0.1-0.1,0.2-0.3,0.2-0.5s-0.1-0.4-0.2-0.5L5.2,7.2C5.1,7.1,5,7.1,4.9,7C4.8,7,4.7,7,4.6,7C4.4,7,4.2,7.1,4,7.2
+				C3.9,7.4,3.8,7.6,3.8,7.8z"/>
+		</g>
+	</g>
+</g>
+</svg>

integrations/Doris/markdown/README.md

@@ -0,0 +1,39 @@
+# Doris
+
+Doris 的进程都会暴露 `/metrics` 接口，通过这个接口暴露 Prometheus 协议的监控数据。
+
+## 采集配置
+
+categraf 的 `conf/input.prometheus/prometheus.toml`。因为 Doris 是暴露的 Prometheus 协议的监控数据，所以使用 categraf 的 prometheus 插件即可采集。
+
+```toml
+# doris_fe
+[[instances]]
+urls = [
+     "http://127.0.0.1:8030/metrics"
+]
+
+url_label_key = "instance"
+url_label_value = "{{.Host}}"
+
+labels = { group = "fe",job = "doris_cluster01"}
+
+# doris_be
+[[instances]]
+urls = [
+     "http://127.0.0.1:8040/metrics"
+]
+url_label_key = "instance"
+url_label_value = "{{.Host}}"
+labels = { group = "be",job = "doris_cluster01"}
+```
+
+## 告警规则
+
+夜莺内置了 Doris 的告警规则，克隆到自己的业务组下即可使用。
+
+## 仪表盘
+
+夜莺内置了 Doris 的仪表盘，克隆到自己的业务组下即可使用。
+
+

integrations/IPMI/dashboards/IPMI_by_prometheus.json

@@ -459,5 +459,5 @@
             }
         ]
     },
-    "uuid": 1727587308068775200
+    "uuid": 1727587308068775000
 }

integrations/Kubernetes/dashboards/DeploymentContainer.json

@@ -1702,5 +1702,5 @@
         ],
         "version": "3.0.0"
     },
-    "uuid": 1727335102129685800
+    "uuid": 1727335102129685000
 }

integrations/Ldap/collect/ldap/ldap.toml

@@ -0,0 +1,37 @@
+# # collect interval
+# interval = 15
+
+[[instances]]
+# # append some labels for series
+# labels = { region="cloud", product="n9e" }
+
+# # interval = global.interval * interval_times
+# interval_times = 1
+
+## Server to monitor
+## The scheme determines the mode to use for connection with
+##    ldap://...      -- unencrypted (non-TLS) connection
+##    ldaps://...     -- TLS connection
+##    starttls://...  --  StartTLS connection
+## If no port is given, the default ports, 389 for ldap and starttls and
+## 636 for ldaps, are used.
+#server = "ldap://localhost"
+
+## Server dialect, can be "openldap" or "389ds"
+# dialect = "openldap"
+
+# DN and password to bind with
+## If bind_dn is empty an anonymous bind is performed.
+bind_dn = ""
+bind_password = ""
+
+## Reverse the field names constructed from the monitoring DN
+# reverse_field_names = false
+
+## Optional TLS Config
+# use_tls = false
+# tls_ca = "/etc/categraf/ca.pem"
+# tls_cert = "/etc/categraf/cert.pem"
+# tls_key = "/etc/categraf/key.pem"
+## Use TLS but skip chain & host verification
+# insecure_skip_verify = false

integrations/Ldap/markdown/README.md

@@ -0,0 +1,113 @@
+# LDAP Input Plugin
+
+This plugin gathers metrics from LDAP servers' monitoring (`cn=Monitor`)
+backend. Currently this plugin supports [OpenLDAP](https://www.openldap.org/)
+and [389ds](https://www.port389.org/) servers.
+
+To use this plugin you must enable the monitoring backend/plugin of your LDAP
+server. See
+[OpenLDAP](https://www.openldap.org/devel/admin/monitoringslapd.html) or 389ds
+documentation for details.
+
+## Metrics
+
+Depending on the server dialect, different metrics are produced. The metrics
+are usually named according to the selected dialect.
+
+### Tags
+
+- server -- Server name or IP
+- port   -- Port used for connecting
+
+## Example Output
+
+Using the `openldap` dialect
+
+```text
+openldap_modify_operations_completed agent_hostname=zy-fat port=389 server=localhost 0
+openldap_referrals_statistics agent_hostname=zy-fat port=389 server=localhost 0
+openldap_unbind_operations_initiated agent_hostname=zy-fat port=389 server=localhost 0
+openldap_delete_operations_completed agent_hostname=zy-fat port=389 server=localhost 0
+openldap_extended_operations_completed agent_hostname=zy-fat port=389 server=localhost 0
+openldap_pdu_statistics agent_hostname=zy-fat port=389 server=localhost 42
+openldap_starting_threads agent_hostname=zy-fat port=389 server=localhost 0
+openldap_active_threads agent_hostname=zy-fat port=389 server=localhost 1
+openldap_uptime_time agent_hostname=zy-fat port=389 server=localhost 102
+openldap_bytes_statistics agent_hostname=zy-fat port=389 server=localhost 3176
+openldap_compare_operations_completed agent_hostname=zy-fat port=389 server=localhost 0
+openldap_bind_operations_completed agent_hostname=zy-fat port=389 server=localhost 1
+openldap_total_connections agent_hostname=zy-fat port=389 server=localhost 1002
+openldap_search_operations_completed agent_hostname=zy-fat port=389 server=localhost 1
+openldap_abandon_operations_initiated agent_hostname=zy-fat port=389 server=localhost 0
+openldap_add_operations_initiated agent_hostname=zy-fat port=389 server=localhost 0
+openldap_open_threads agent_hostname=zy-fat port=389 server=localhost 1
+openldap_add_operations_completed agent_hostname=zy-fat port=389 server=localhost 0
+openldap_operations_initiated agent_hostname=zy-fat port=389 server=localhost 3
+openldap_write_waiters agent_hostname=zy-fat port=389 server=localhost 0
+openldap_entries_statistics agent_hostname=zy-fat port=389 server=localhost 41
+openldap_modrdn_operations_completed agent_hostname=zy-fat port=389 server=localhost 0
+openldap_pending_threads agent_hostname=zy-fat port=389 server=localhost 0
+openldap_max_pending_threads agent_hostname=zy-fat port=389 server=localhost 0
+openldap_bind_operations_initiated agent_hostname=zy-fat port=389 server=localhost 1
+openldap_max_file_descriptors_connections agent_hostname=zy-fat port=389 server=localhost 1024
+openldap_compare_operations_initiated agent_hostname=zy-fat port=389 server=localhost 0
+openldap_search_operations_initiated agent_hostname=zy-fat port=389 server=localhost 2
+openldap_modrdn_operations_initiated agent_hostname=zy-fat port=389 server=localhost 0
+openldap_read_waiters agent_hostname=zy-fat port=389 server=localhost 1
+openldap_backload_threads agent_hostname=zy-fat port=389 server=localhost 1
+openldap_current_connections agent_hostname=zy-fat port=389 server=localhost 1
+openldap_unbind_operations_completed agent_hostname=zy-fat port=389 server=localhost 0
+openldap_delete_operations_initiated agent_hostname=zy-fat port=389 server=localhost 0
+openldap_extended_operations_initiated agent_hostname=zy-fat port=389 server=localhost 0
+openldap_modify_operations_initiated agent_hostname=zy-fat port=389 server=localhost 0
+openldap_max_threads agent_hostname=zy-fat port=389 server=localhost 16
+openldap_abandon_operations_completed agent_hostname=zy-fat port=389 server=localhost 0
+openldap_operations_completed agent_hostname=zy-fat port=389 server=localhost 2
+openldap_database_2_databases agent_hostname=zy-fat port=389 server=localhost 0
+```
+
+Using the `389ds` dialect
+
+```text
+389ds_current_connections_at_max_threads agent_hostname=zy-fat port=389 server=localhost 0
+389ds_connections_max_threads agent_hostname=zy-fat port=389 server=localhost 0
+389ds_add_operations agent_hostname=zy-fat port=389 server=localhost 0
+389ds_dtablesize agent_hostname=zy-fat port=389 server=localhost 63936
+389ds_strongauth_binds agent_hostname=zy-fat port=389 server=localhost 13
+389ds_modrdn_operations agent_hostname=zy-fat port=389 server=localhost 0
+389ds_maxthreads_per_conn_hits agent_hostname=zy-fat port=389 server=localhost 0
+389ds_current_connections agent_hostname=zy-fat port=389 server=localhost 2
+389ds_security_errors agent_hostname=zy-fat port=389 server=localhost 0
+389ds_entries_sent agent_hostname=zy-fat port=389 server=localhost 13
+389ds_cache_entries agent_hostname=zy-fat port=389 server=localhost 0
+389ds_backends agent_hostname=zy-fat port=389 server=localhost 0
+389ds_threads agent_hostname=zy-fat port=389 server=localhost 17
+389ds_connections agent_hostname=zy-fat port=389 server=localhost 2
+389ds_read_operations agent_hostname=zy-fat port=389 server=localhost 0
+389ds_entries_returned agent_hostname=zy-fat port=389 server=localhost 13
+389ds_unauth_binds agent_hostname=zy-fat port=389 server=localhost 0
+389ds_search_operations agent_hostname=zy-fat port=389 server=localhost 14
+389ds_simpleauth_binds agent_hostname=zy-fat port=389 server=localhost 0
+389ds_operations_completed agent_hostname=zy-fat port=389 server=localhost 51
+389ds_connections_in_max_threads agent_hostname=zy-fat port=389 server=localhost 0
+389ds_modify_operations agent_hostname=zy-fat port=389 server=localhost 0
+389ds_wholesubtree_search_operations agent_hostname=zy-fat port=389 server=localhost 1
+389ds_read_waiters agent_hostname=zy-fat port=389 server=localhost 0
+389ds_compare_operations agent_hostname=zy-fat port=389 server=localhost 0
+389ds_errors agent_hostname=zy-fat port=389 server=localhost 13
+389ds_in_operations agent_hostname=zy-fat port=389 server=localhost 52
+389ds_total_connections agent_hostname=zy-fat port=389 server=localhost 15
+389ds_cache_hits agent_hostname=zy-fat port=389 server=localhost 0
+389ds_list_operations agent_hostname=zy-fat port=389 server=localhost 0
+389ds_referrals_returned agent_hostname=zy-fat port=389 server=localhost 0
+389ds_copy_entries agent_hostname=zy-fat port=389 server=localhost 0
+389ds_operations_initiated agent_hostname=zy-fat port=389 server=localhost 52
+389ds_chainings agent_hostname=zy-fat port=389 server=localhost 0
+389ds_bind_security_errors agent_hostname=zy-fat port=389 server=localhost 0
+389ds_onelevel_search_operations agent_hostname=zy-fat port=389 server=localhost 0
+389ds_bytes_sent agent_hostname=zy-fat port=389 server=localhost 1702
+389ds_bytes_received agent_hostname=zy-fat port=389 server=localhost 0
+389ds_referrals agent_hostname=zy-fat port=389 server=localhost 0
+389ds_delete_operations agent_hostname=zy-fat port=389 server=localhost 0
+389ds_anonymous_binds agent_hostname=zy-fat port=389 server=localhost 0
+```

integrations/Linux/dashboards/host_table_view_demo.json

@@ -1,13 +1,6 @@
 {
-    "id": 0,
-    "group_id": 0,
     "name": "机器台账表格视图",
-    "ident": "",
     "tags": "",
-    "create_at": 0,
-    "create_by": "",
-    "update_at": 0,
-    "update_by": "",
     "configs": {
         "links": [
             {
@@ -28,7 +21,7 @@
                     "colorRange": [
                         "thresholds"
                     ],
-                    "detailUrl": "/dashboards-built-in/detail?__built-in-cate=Linux\u0026__built-in-name=Linux%20Host%20by%20Categraf%20v2\u0026ident=${__field.labels.ident}",
+                    "detailUrl": "/built-in-components/dashboard/detail?__uuid__=1717556327744505000&ident=${__field.labels.ident}",
                     "textMode": "valueAndName",
                     "valueField": "Value"
                 },
@@ -98,7 +91,7 @@
                     "colorRange": [
                         "thresholds"
                     ],
-                    "detailUrl": "/dashboards-built-in/detail?__built-in-cate=Linux\u0026__built-in-name=Linux%20Host%20by%20Categraf%20v2\u0026ident=${__field.labels.ident}",
+                    "detailUrl": "/built-in-components/dashboard/detail?__uuid__=1717556327744505000&ident=${__field.labels.ident}",
                     "textMode": "valueAndName",
                     "valueField": "Value"
                 },
@@ -171,13 +164,16 @@
                     "linkMode": "appendLinkColumn",
                     "links": [
                         {
+                            "targetBlank": true,
                             "title": "详情",
-                            "url": "/dashboards-built-in/detail?__built-in-cate=Linux\u0026__built-in-name=Linux%20Host%20by%20Categraf%20v2\u0026ident=${__field.labels.ident}"
+                            "url": "/built-in-components/dashboard/detail?__uuid__=1717556327744505000&ident=${__field.labels.ident}"
                         }
                     ],
+                    "nowrap": false,
                     "showHeader": true,
                     "sortColumn": "ident",
-                    "sortOrder": "ascend"
+                    "sortOrder": "ascend",
+                    "tableLayout": "fixed"
                 },
                 "datasourceCate": "prometheus",
                 "datasourceValue": "${prom}",
@@ -385,10 +381,5 @@
         ],
         "version": "3.0.0"
     },
-    "public": 0,
-    "public_cate": 0,
-    "bgids": null,
-    "built_in": 0,
-    "hide": 0,
     "uuid": 1717556327742611000
 }

integrations/MongoDB/dashboards/mongo_by_exporter.json

@@ -1,13 +1,7 @@
 {
-    "id": 0,
-    "group_id": 0,
     "name": "MongoDB Overview by exporter",
-    "ident": "",
     "tags": "Prometheus MongoDB",
-    "create_at": 0,
-    "create_by": "",
-    "update_at": 0,
-    "update_by": "",
+    "ident": "",
     "configs": {
         "panels": [
             {
@@ -150,21 +144,7 @@
                 "version": "2.0.0"
             },
             {
-                "custom": {
-                    "drawStyle": "lines",
-                    "fillOpacity": 0.3,
-                    "gradientMode": "opacity",
-                    "lineInterpolation": "smooth",
-                    "lineWidth": 2,
-                    "scaleDistribution": {
-                        "type": "linear"
-                    },
-                    "spanNulls": false,
-                    "stack": "off"
-                },
-                "datasourceCate": "prometheus",
-                "datasourceValue": "${prom}",
-                "description": "Memory usage (MiB)",
+                "type": "timeseries",
                 "id": "8446dded-9e11-4ee9-bdad-769b193ddf3e",
                 "layout": {
                     "h": 7,
@@ -174,10 +154,37 @@
                     "x": 12,
                     "y": 1
                 },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "targets": [
+                    {
+                        "expr": "mongodb_ss_mem_resident{instance='$instance'} * 1024 * 1024",
+                        "legend": "{{type}}",
+                        "refId": "A",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
                 "name": "Memory",
+                "description": "Memory usage (MiB)",
+                "maxPerRow": 4,
                 "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "desc"
+                    },
                     "legend": {
-                        "displayMode": "hidden"
+                        "displayMode": "hidden",
+                        "heightInPercentage": 30,
+                        "placement": "bottom",
+                        "behaviour": "showItem",
+                        "selectMode": "single"
                     },
                     "standardOptions": {
                         "util": "bytesIEC"
@@ -186,25 +193,36 @@
                         "steps": [
                             {
                                 "color": "#634CD9",
-                                "type": "base",
-                                "value": null
+                                "value": null,
+                                "type": "base"
                             }
                         ]
-                    },
-                    "tooltip": {
-                        "mode": "all",
-                        "sort": "desc"
                     }
                 },
-                "targets": [
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "spanNulls": false,
+                    "lineWidth": 2,
+                    "fillOpacity": 0.3,
+                    "gradientMode": "opacity",
+                    "stack": "off",
+                    "scaleDistribution": {
+                        "type": "linear"
+                    },
+                    "showPoints": "none",
+                    "pointSize": 5
+                },
+                "overrides": [
                     {
-                        "expr": "mongodb_ss_mem_resident{cluster='$cluster'} * 1024 * 1024",
-                        "legend": "{{type}}",
-                        "refId": "A"
+                        "matcher": {
+                            "id": "byFrameRefID"
+                        },
+                        "properties": {
+                            "rightYAxisDisplay": "off"
+                        }
                     }
-                ],
-                "type": "timeseries",
-                "version": "2.0.0"
+                ]
             },
             {
                 "custom": {
@@ -571,21 +589,7 @@
                 "version": "2.0.0"
             },
             {
-                "custom": {
-                    "drawStyle": "lines",
-                    "fillOpacity": 0.3,
-                    "gradientMode": "opacity",
-                    "lineInterpolation": "smooth",
-                    "lineWidth": 2,
-                    "scaleDistribution": {
-                        "type": "linear"
-                    },
-                    "spanNulls": false,
-                    "stack": "off"
-                },
-                "datasourceCate": "prometheus",
-                "datasourceValue": "${prom}",
-                "description": "Number of document operations When used in combination with 'Command Operations', this graph can help identify write amplification. For example, when one insert or update command actually inserts or updates hundreds, thousands, or even millions of documents.",
+                "type": "timeseries",
                 "id": "7030d97a-d69f-4916-a415-ec57503ab1ed",
                 "layout": {
                     "h": 7,
@@ -595,52 +599,76 @@
                     "x": 12,
                     "y": 16
                 },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "targets": [
+                    {
+                        "expr": "rate(mongodb_ss_metrics_document{instance=\"$instance\"}[5m])",
+                        "legend": "",
+                        "refId": "A",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
                 "name": "Document Operations",
+                "description": "Number of document operations When used in combination with 'Command Operations', this graph can help identify write amplification. For example, when one insert or update command actually inserts or updates hundreds, thousands, or even millions of documents.",
+                "maxPerRow": 4,
                 "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
                     "legend": {
-                        "displayMode": "hidden"
+                        "displayMode": "hidden",
+                        "heightInPercentage": 30,
+                        "placement": "bottom",
+                        "behaviour": "showItem",
+                        "selectMode": "single"
                     },
                     "standardOptions": {},
                     "thresholds": {
                         "steps": [
                             {
                                 "color": "#634CD9",
-                                "type": "base",
-                                "value": null
+                                "value": null,
+                                "type": "base"
                             }
                         ]
-                    },
-                    "tooltip": {
-                        "mode": "all",
-                        "sort": "none"
                     }
                 },
-                "targets": [
-                    {
-                        "expr": "rate(mongodb_ss_metric_document{instance=\"$instance\"}[5m])",
-                        "legend": "",
-                        "refId": "A"
-                    }
-                ],
-                "type": "timeseries",
-                "version": "2.0.0"
-            },
-            {
                 "custom": {
                     "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "spanNulls": false,
+                    "lineWidth": 2,
                     "fillOpacity": 0.3,
                     "gradientMode": "opacity",
-                    "lineInterpolation": "smooth",
-                    "lineWidth": 2,
+                    "stack": "off",
                     "scaleDistribution": {
                         "type": "linear"
                     },
-                    "spanNulls": false,
-                    "stack": "off"
+                    "showPoints": "none",
+                    "pointSize": 5
                 },
-                "datasourceCate": "prometheus",
-                "datasourceValue": "${prom}",
-                "description": "Operation detail processing time (milliseconds)",
+                "overrides": [
+                    {
+                        "matcher": {
+                            "id": "byFrameRefID"
+                        },
+                        "properties": {
+                            "rightYAxisDisplay": "off"
+                        }
+                    }
+                ]
+            },
+            {
+                "type": "timeseries",
                 "id": "1c3b73d5-c25c-449f-995d-26acc9c621e1",
                 "layout": {
                     "h": 7,
@@ -650,10 +678,37 @@
                     "x": 0,
                     "y": 23
                 },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "targets": [
+                    {
+                        "expr": "rate(mongodb_ss_opLatencies_latency{instance='$instance'}[5m]) / rate(mongodb_ss_opLatencies_latency{instance='$instance'}[5m]) / 1000",
+                        "legend": "{{op_type}}",
+                        "refId": "A",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
                 "name": "Response Time",
+                "description": "Operation detail processing time (milliseconds)",
+                "maxPerRow": 4,
                 "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
                     "legend": {
-                        "displayMode": "hidden"
+                        "displayMode": "hidden",
+                        "heightInPercentage": 30,
+                        "placement": "bottom",
+                        "behaviour": "showItem",
+                        "selectMode": "single"
                     },
                     "standardOptions": {
                         "util": "milliseconds"
@@ -662,25 +717,36 @@
                         "steps": [
                             {
                                 "color": "#634CD9",
-                                "type": "base",
-                                "value": null
+                                "value": null,
+                                "type": "base"
                             }
                         ]
-                    },
-                    "tooltip": {
-                        "mode": "all",
-                        "sort": "none"
                     }
                 },
-                "targets": [
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "spanNulls": false,
+                    "lineWidth": 2,
+                    "fillOpacity": 0.3,
+                    "gradientMode": "opacity",
+                    "stack": "off",
+                    "scaleDistribution": {
+                        "type": "linear"
+                    },
+                    "showPoints": "none",
+                    "pointSize": 5
+                },
+                "overrides": [
                     {
-                        "expr": "rate(mongodb_ss_opLatencies_latency{cluster='$cluster'}[5m]) / rate(mongodb_ss_opLatencies_latency{cluster='$cluster'}[5m]) / 1000",
-                        "legend": "{{op_type}}",
-                        "refId": "A"
+                        "matcher": {
+                            "id": "byFrameRefID"
+                        },
+                        "properties": {
+                            "rightYAxisDisplay": "off"
+                        }
                     }
-                ],
-                "type": "timeseries",
-                "version": "2.0.0"
+                ]
             },
             {
                 "custom": {
@@ -815,21 +881,7 @@
                 "type": "row"
             },
             {
-                "custom": {
-                    "drawStyle": "lines",
-                    "fillOpacity": 0.3,
-                    "gradientMode": "opacity",
-                    "lineInterpolation": "smooth",
-                    "lineWidth": 2,
-                    "scaleDistribution": {
-                        "type": "linear"
-                    },
-                    "spanNulls": false,
-                    "stack": "off"
-                },
-                "datasourceCate": "prometheus",
-                "datasourceValue": "${prom}",
-                "description": "cache size (byte)",
+                "type": "timeseries",
                 "id": "bb0ae571-43a1-430b-8f63-256f6f1ebee6",
                 "layout": {
                     "h": 7,
@@ -839,10 +891,55 @@
                     "x": 0,
                     "y": 31
                 },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "targets": [
+                    {
+                        "expr": "mongodb_ss_wt_cache_bytes_currently_in_the_cache{instance='$instance'}",
+                        "legend": "total",
+                        "refId": "A",
+                        "maxDataPoints": 240
+                    },
+                    {
+                        "expr": "mongodb_ss_wt_cache_tracked_dirty_bytes_in_the_cache{cluster='$cluster'}",
+                        "legend": "dirty",
+                        "refId": "B",
+                        "maxDataPoints": 240
+                    },
+                    {
+                        "expr": "mongodb_ss_wt_cache_tracked_bytes_belonging_to_internal_pages_in_the_cache{cluster='$cluster'}",
+                        "legend": "internal_pages",
+                        "refId": "C",
+                        "maxDataPoints": 240
+                    },
+                    {
+                        "expr": "mongodb_ss_wt_cache_tracked_bytes_belonging_to_leaf_pages_in_the_cache{cluster='$cluster'}",
+                        "legend": "leaf_pages",
+                        "refId": "D",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
                 "name": "Cache Size",
+                "description": "cache size (byte)",
+                "maxPerRow": 4,
                 "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
                     "legend": {
-                        "displayMode": "hidden"
+                        "displayMode": "hidden",
+                        "heightInPercentage": 30,
+                        "placement": "bottom",
+                        "behaviour": "showItem",
+                        "selectMode": "single"
                     },
                     "standardOptions": {
                         "util": "bytesIEC"
@@ -851,57 +948,39 @@
                         "steps": [
                             {
                                 "color": "#634CD9",
-                                "type": "base",
-                                "value": null
+                                "value": null,
+                                "type": "base"
                             }
                         ]
-                    },
-                    "tooltip": {
-                        "mode": "all",
-                        "sort": "none"
                     }
                 },
-                "targets": [
-                    {
-                        "expr": "mongodb_ss_wt_cache_bytes_currently_in_the_cache{cluster='$cluster'}",
-                        "legend": "total",
-                        "refId": "A"
-                    },
-                    {
-                        "expr": "mongodb_ss_wt_cache_tracked_dirty_bytes_in_the_cache{cluster='$cluster'}",
-                        "legend": "dirty",
-                        "refId": "B"
-                    },
-                    {
-                        "expr": "mongodb_ss_wt_cache_tracked_bytes_belonging_to_internal_pages_in_the_cache{cluster='$cluster'}",
-                        "legend": "internal_pages",
-                        "refId": "C"
-                    },
-                    {
-                        "expr": "mongodb_ss_wt_cache_tracked_bytes_belonging_to_leaf_pages_in_the_cache{cluster='$cluster'}",
-                        "legend": "leaf_pages",
-                        "refId": "D"
-                    }
-                ],
-                "type": "timeseries",
-                "version": "2.0.0"
-            },
-            {
                 "custom": {
                     "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "spanNulls": false,
+                    "lineWidth": 2,
                     "fillOpacity": 0.3,
                     "gradientMode": "opacity",
-                    "lineInterpolation": "smooth",
-                    "lineWidth": 2,
+                    "stack": "off",
                     "scaleDistribution": {
                         "type": "linear"
                     },
-                    "spanNulls": false,
-                    "stack": "off"
+                    "showPoints": "none",
+                    "pointSize": 5
                 },
-                "datasourceCate": "prometheus",
-                "datasourceValue": "${prom}",
-                "description": "size of cached data written or read (in bytes)",
+                "overrides": [
+                    {
+                        "matcher": {
+                            "id": "byFrameRefID"
+                        },
+                        "properties": {
+                            "rightYAxisDisplay": "off"
+                        }
+                    }
+                ]
+            },
+            {
+                "type": "timeseries",
                 "id": "f1ffd169-2a1a-42bc-9647-0e6621be0fef",
                 "layout": {
                     "h": 7,
@@ -911,10 +990,43 @@
                     "x": 6,
                     "y": 31
                 },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "targets": [
+                    {
+                        "expr": "rate(mongodb_ss_wt_cache_bytes_read_into_cache{instance='$instance'}[5m])",
+                        "legend": "read",
+                        "refId": "A",
+                        "maxDataPoints": 240
+                    },
+                    {
+                        "expr": "rate(mongodb_ss_wt_cache_bytes_written_from_cache{cluster='$cluster'}[5m])",
+                        "legend": "written",
+                        "refId": "B",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
                 "name": "Cache I/O",
+                "description": "size of cached data written or read (in bytes)",
+                "maxPerRow": 4,
                 "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
                     "legend": {
-                        "displayMode": "hidden"
+                        "displayMode": "hidden",
+                        "heightInPercentage": 30,
+                        "placement": "bottom",
+                        "behaviour": "showItem",
+                        "selectMode": "single"
                     },
                     "standardOptions": {
                         "util": "bytesSI"
@@ -923,47 +1035,39 @@
                         "steps": [
                             {
                                 "color": "#634CD9",
-                                "type": "base",
-                                "value": null
+                                "value": null,
+                                "type": "base"
                             }
                         ]
-                    },
-                    "tooltip": {
-                        "mode": "all",
-                        "sort": "none"
                     }
                 },
-                "targets": [
-                    {
-                        "expr": "rate(mongodb_ss_wt_cache_bytes_read_into_cache{cluster='$cluster'}[5m])",
-                        "legend": "read",
-                        "refId": "A"
-                    },
-                    {
-                        "expr": "rate(mongodb_ss_wt_cache_bytes_written_from_cache{cluster='$cluster'}[5m])",
-                        "legend": "written",
-                        "refId": "B"
-                    }
-                ],
-                "type": "timeseries",
-                "version": "2.0.0"
-            },
-            {
                 "custom": {
                     "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "spanNulls": false,
+                    "lineWidth": 2,
                     "fillOpacity": 0.3,
                     "gradientMode": "opacity",
-                    "lineInterpolation": "smooth",
-                    "lineWidth": 2,
+                    "stack": "off",
                     "scaleDistribution": {
                         "type": "linear"
                     },
-                    "spanNulls": false,
-                    "stack": "off"
+                    "showPoints": "none",
+                    "pointSize": 5
                 },
-                "datasourceCate": "prometheus",
-                "datasourceValue": "${prom}",
-                "description": "",
+                "overrides": [
+                    {
+                        "matcher": {
+                            "id": "byFrameRefID"
+                        },
+                        "properties": {
+                            "rightYAxisDisplay": "off"
+                        }
+                    }
+                ]
+            },
+            {
+                "type": "timeseries",
                 "id": "43ee140d-ae6d-474a-9892-fa4743d7f97e",
                 "layout": {
                     "h": 7,
@@ -973,10 +1077,37 @@
                     "x": 12,
                     "y": 31
                 },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "targets": [
+                    {
+                        "expr": "100 * sum(mongodb_ss_wt_cache_tracked_dirty_pages_in_the_cache{instance='$instance'}) / sum(mongodb_ss_wt_cache_pages_currently_held_in_the_cache{instance='$instance'})",
+                        "legend": "dirty rate",
+                        "refId": "A",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
                 "name": "Cache Dirty Pages Rate",
+                "description": "",
+                "maxPerRow": 4,
                 "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
                     "legend": {
-                        "displayMode": "hidden"
+                        "displayMode": "hidden",
+                        "heightInPercentage": 30,
+                        "placement": "bottom",
+                        "behaviour": "showItem",
+                        "selectMode": "single"
                     },
                     "standardOptions": {
                         "util": "percent"
@@ -985,42 +1116,39 @@
                         "steps": [
                             {
                                 "color": "#634CD9",
-                                "type": "base",
-                                "value": null
+                                "value": null,
+                                "type": "base"
                             }
                         ]
-                    },
-                    "tooltip": {
-                        "mode": "all",
-                        "sort": "none"
                     }
                 },
-                "targets": [
-                    {
-                        "expr": "100 * sum(mongodb_ss_wt_cache_tracked_dirty_pages_in_the_cache{cluster='$cluster'}) / sum(mongodb_ss_wt_cache_pages_currently_held_in_the_cache{cluster='$cluster'})",
-                        "legend": "dirty rate",
-                        "refId": "A"
-                    }
-                ],
-                "type": "timeseries",
-                "version": "2.0.0"
-            },
-            {
                 "custom": {
                     "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "spanNulls": false,
+                    "lineWidth": 2,
                     "fillOpacity": 0.3,
                     "gradientMode": "opacity",
-                    "lineInterpolation": "smooth",
-                    "lineWidth": 2,
+                    "stack": "off",
                     "scaleDistribution": {
                         "type": "linear"
                     },
-                    "spanNulls": false,
-                    "stack": "off"
+                    "showPoints": "none",
+                    "pointSize": 5
                 },
-                "datasourceCate": "prometheus",
-                "datasourceValue": "${prom}",
-                "description": "",
+                "overrides": [
+                    {
+                        "matcher": {
+                            "id": "byFrameRefID"
+                        },
+                        "properties": {
+                            "rightYAxisDisplay": "off"
+                        }
+                    }
+                ]
+            },
+            {
+                "type": "timeseries",
                 "id": "1a22c31a-859a-400c-af2a-ae83c308d0f2",
                 "layout": {
                     "h": 7,
@@ -1030,35 +1158,73 @@
                     "x": 18,
                     "y": 31
                 },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "targets": [
+                    {
+                        "expr": "rate(mongodb_mongod_wiredtiger_cache_evicted_total{instance='$instance'}[5m])",
+                        "legend": "evicted pages",
+                        "refId": "A",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
                 "name": "Cache Evicted Pages",
+                "description": "",
+                "maxPerRow": 4,
                 "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
                     "legend": {
-                        "displayMode": "hidden"
+                        "displayMode": "hidden",
+                        "heightInPercentage": 30,
+                        "placement": "bottom",
+                        "behaviour": "showItem",
+                        "selectMode": "single"
                     },
                     "standardOptions": {},
                     "thresholds": {
                         "steps": [
                             {
                                 "color": "#634CD9",
-                                "type": "base",
-                                "value": null
+                                "value": null,
+                                "type": "base"
                             }
                         ]
-                    },
-                    "tooltip": {
-                        "mode": "all",
-                        "sort": "none"
                     }
                 },
-                "targets": [
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "spanNulls": false,
+                    "lineWidth": 2,
+                    "fillOpacity": 0.3,
+                    "gradientMode": "opacity",
+                    "stack": "off",
+                    "scaleDistribution": {
+                        "type": "linear"
+                    },
+                    "showPoints": "none",
+                    "pointSize": 5
+                },
+                "overrides": [
                     {
-                        "expr": "rate(mongodb_mongod_wiredtiger_cache_evicted_total{cluster='$cluster'}[5m])",
-                        "legend": "evicted pages",
-                        "refId": "A"
+                        "matcher": {
+                            "id": "byFrameRefID"
+                        },
+                        "properties": {
+                            "rightYAxisDisplay": "off"
+                        }
                     }
-                ],
-                "type": "timeseries",
-                "version": "2.0.0"
+                ]
             },
             {
                 "collapsed": true,
@@ -1204,10 +1370,5 @@
         ],
         "version": "3.0.0"
     },
-    "public": 0,
-    "public_cate": 0,
-    "bgids": null,
-    "built_in": 0,
-    "hide": 0,
     "uuid": 1717556328065329000
-}
+}

integrations/MySQL/dashboards/MySQL仪表盘-远端.json

@@ -1,5 +1,5 @@
 {
-    "name": "MySQL 仪表盘（远端）",
+    "name": "MySQL 仪表盘（使用 instance 筛选，需要采集时自行打上 instance 标签）",
     "tags": "",
     "ident": "",
     "configs": {
@@ -1802,5 +1802,5 @@
         ],
         "version": "3.0.0"
     },
-    "uuid": 1717556328087994322
+    "uuid": 1717556328087995000
 }

integrations/MySQL/dashboards/MySQL仪表盘.json

@@ -1,5 +1,5 @@
 {
-    "name": "MySQL 仪表盘",
+    "name": "MySQL 仪表盘，适用于 Categraf 采集本机 MySQL 的场景",
     "tags": "",
     "ident": "",
     "configs": {
@@ -1798,5 +1798,5 @@
         ],
         "version": "3.0.0"
     },
-    "uuid": 1717556328087994321
+    "uuid": 1717556328087994000
 }

integrations/Oracle/collect/oracle/oracle.toml

@@ -139,3 +139,11 @@ timeout = "3s"
 request = '''
 select METRIC_NAME,VALUE from v$sysmetric where group_id=2
 '''
+
+[[metrics]]
+mesurement = "applylag"
+metric_fields = [ "value" ]
+timeout = "3s"
+request = '''
+SELECT TO_NUMBER(EXTRACT(SECOND FROM TO_DSINTERVAL (value))) as value FROM v$dataguard_stats WHERE name = 'apply lag'
+'''

integrations/Redis/dashboards/FilterByAddress.json

@@ -0,0 +1,925 @@
+{
+    "name": "Redis by address",
+    "tags": "Redis Categraf",
+    "configs": {
+        "panels": [
+            {
+                "collapsed": true,
+                "id": "2ecb82c6-4d1a-41b5-8cdc-0284db16bd54",
+                "layout": {
+                    "h": 1,
+                    "i": "2ecb82c6-4d1a-41b5-8cdc-0284db16bd54",
+                    "isResizable": false,
+                    "w": 24,
+                    "x": 0,
+                    "y": 0
+                },
+                "name": "Basic Info",
+                "type": "row"
+            },
+            {
+                "custom": {
+                    "alignItems": "center",
+                    "bgColor": "rgba(0, 0, 0, 0)",
+                    "content": "<img src=\"https://download.flashcat.cloud/ulric/redis.png\" width=128 />",
+                    "justifyContent": "center",
+                    "textColor": "#000000",
+                    "textDarkColor": "#FFFFFF",
+                    "textSize": 12
+                },
+                "id": "b5acc352-a2bd-4afc-b6cd-d6db0905f807",
+                "layout": {
+                    "h": 3,
+                    "i": "b5acc352-a2bd-4afc-b6cd-d6db0905f807",
+                    "isResizable": true,
+                    "w": 4,
+                    "x": 0,
+                    "y": 1
+                },
+                "maxPerRow": 4,
+                "name": "",
+                "type": "text",
+                "version": "3.0.0"
+            },
+            {
+                "custom": {
+                    "calc": "lastNotNull",
+                    "colSpan": 0,
+                    "colorMode": "background",
+                    "graphMode": "none",
+                    "orientation": "vertical",
+                    "textMode": "valueAndName",
+                    "textSize": {},
+                    "valueField": "Value"
+                },
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "id": "5eb6fbcf-4260-40d0-ad6a-540e54a1f922",
+                "layout": {
+                    "h": 3,
+                    "i": "2a02e1d4-2ed3-4bd2-9fa0-69bb10f13888",
+                    "isResizable": true,
+                    "w": 5,
+                    "x": 4,
+                    "y": 1
+                },
+                "maxPerRow": 4,
+                "name": "Redis Uptime",
+                "options": {
+                    "standardOptions": {
+                        "decimals": 2,
+                        "util": "seconds"
+                    },
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "rgba(63, 196, 83, 1)",
+                                "type": "base",
+                                "value": null
+                            }
+                        ]
+                    },
+                    "valueMappings": [
+                        {
+                            "match": {
+                                "to": 600
+                            },
+                            "result": {
+                                "color": "rgba(255, 101, 107, 1)"
+                            },
+                            "type": "range"
+                        },
+                        {
+                            "match": {
+                                "from": 600
+                            },
+                            "result": {
+                                "color": "rgba(63, 196, 83, 1)"
+                            },
+                            "type": "range"
+                        }
+                    ]
+                },
+                "targets": [
+                    {
+                        "expr": "redis_uptime_in_seconds{address=~\"$address\"}",
+                        "legend": "{{address}}",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "type": "stat",
+                "version": "3.0.0"
+            },
+            {
+                "custom": {
+                    "calc": "lastNotNull",
+                    "colSpan": 0,
+                    "colorMode": "background",
+                    "graphMode": "none",
+                    "orientation": "vertical",
+                    "textMode": "valueAndName",
+                    "textSize": {},
+                    "valueField": "Value"
+                },
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "id": "8ccada5e-02f3-4efc-9b36-2a367612e4cb",
+                "layout": {
+                    "h": 3,
+                    "i": "8ccada5e-02f3-4efc-9b36-2a367612e4cb",
+                    "isResizable": true,
+                    "w": 5,
+                    "x": 9,
+                    "y": 1
+                },
+                "maxPerRow": 4,
+                "name": "Connected Clients",
+                "options": {
+                    "standardOptions": {},
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#6C53B1",
+                                "type": "base",
+                                "value": null
+                            }
+                        ]
+                    },
+                    "valueMappings": [
+                        {
+                            "match": {
+                                "to": 500
+                            },
+                            "result": {
+                                "color": "rgba(63, 196, 83, 1)"
+                            },
+                            "type": "range"
+                        },
+                        {
+                            "match": {
+                                "from": 500
+                            },
+                            "result": {
+                                "color": "rgba(255, 101, 107, 1)"
+                            },
+                            "type": "range"
+                        }
+                    ]
+                },
+                "targets": [
+                    {
+                        "expr": "redis_connected_clients{address=~\"$address\"}",
+                        "legend": "{{address}}",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "type": "stat",
+                "version": "3.0.0"
+            },
+            {
+                "custom": {
+                    "calc": "lastNotNull",
+                    "colSpan": 0,
+                    "colorMode": "background",
+                    "graphMode": "none",
+                    "orientation": "vertical",
+                    "textMode": "valueAndName",
+                    "textSize": {},
+                    "valueField": "Value"
+                },
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "id": "716dc7e7-c9ec-4195-93f6-db1c572ae8b0",
+                "layout": {
+                    "h": 3,
+                    "i": "716dc7e7-c9ec-4195-93f6-db1c572ae8b0",
+                    "isResizable": true,
+                    "w": 5,
+                    "x": 14,
+                    "y": 1
+                },
+                "maxPerRow": 4,
+                "name": "Memory Used",
+                "options": {
+                    "standardOptions": {
+                        "decimals": 1,
+                        "util": "bytesIEC"
+                    },
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#6C53B1",
+                                "type": "base",
+                                "value": null
+                            }
+                        ]
+                    },
+                    "valueMappings": [
+                        {
+                            "match": {
+                                "to": 128000000
+                            },
+                            "result": {
+                                "color": "#079e05"
+                            },
+                            "type": "range"
+                        },
+                        {
+                            "match": {
+                                "from": 128000000
+                            },
+                            "result": {
+                                "color": "#f10909"
+                            },
+                            "type": "range"
+                        }
+                    ]
+                },
+                "targets": [
+                    {
+                        "expr": "redis_used_memory{address=~\"$address\"}",
+                        "legend": "{{address}}",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "type": "stat",
+                "version": "3.0.0"
+            },
+            {
+                "custom": {
+                    "calc": "lastNotNull",
+                    "colSpan": 0,
+                    "colorMode": "background",
+                    "graphMode": "none",
+                    "orientation": "vertical",
+                    "textMode": "valueAndName",
+                    "textSize": {},
+                    "valueField": "Value"
+                },
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "id": "c6948161-db07-42df-beb1-765ee9c071a9",
+                "layout": {
+                    "h": 3,
+                    "i": "c6948161-db07-42df-beb1-765ee9c071a9",
+                    "isResizable": true,
+                    "w": 5,
+                    "x": 19,
+                    "y": 1
+                },
+                "maxPerRow": 4,
+                "name": "Max Memory Limit",
+                "options": {
+                    "standardOptions": {
+                        "decimals": 1,
+                        "util": "bytesIEC"
+                    },
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "rgba(63, 196, 83, 1)",
+                                "type": "base",
+                                "value": null
+                            }
+                        ]
+                    }
+                },
+                "targets": [
+                    {
+                        "expr": "redis_maxmemory{address=~\"$address\"}",
+                        "legend": "{{address}}",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "type": "stat",
+                "version": "3.0.0"
+            },
+            {
+                "collapsed": true,
+                "id": "bd54cf4f-1abb-4945-8aab-f89aec16daef",
+                "layout": {
+                    "h": 1,
+                    "i": "bd54cf4f-1abb-4945-8aab-f89aec16daef",
+                    "isResizable": false,
+                    "w": 24,
+                    "x": 0,
+                    "y": 4
+                },
+                "name": "Commands",
+                "type": "row"
+            },
+            {
+                "custom": {
+                    "drawStyle": "lines",
+                    "fillOpacity": 0.3,
+                    "gradientMode": "opacity",
+                    "lineInterpolation": "smooth",
+                    "lineWidth": 2,
+                    "scaleDistribution": {
+                        "type": "linear"
+                    },
+                    "spanNulls": false,
+                    "stack": "off"
+                },
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "id": "3d5f8c4e-0ddf-4d68-9f6d-2cc57d864a8e",
+                "layout": {
+                    "h": 5,
+                    "i": "3d5f8c4e-0ddf-4d68-9f6d-2cc57d864a8e",
+                    "isResizable": true,
+                    "w": 8,
+                    "x": 0,
+                    "y": 5
+                },
+                "maxPerRow": 4,
+                "name": "Commands Executed / sec",
+                "options": {
+                    "legend": {
+                        "behaviour": "showItem",
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {
+                        "decimals": 2
+                    },
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#6C53B1",
+                                "type": "base",
+                                "value": null
+                            }
+                        ]
+                    },
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    }
+                },
+                "overrides": [
+                    {
+                        "matcher": {
+                            "id": "byFrameRefID"
+                        },
+                        "properties": {
+                            "rightYAxisDisplay": "off"
+                        }
+                    }
+                ],
+                "targets": [
+                    {
+                        "expr": "rate(redis_total_commands_processed{address=~\"$address\"}[5m])",
+                        "legend": "{{address}}",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "type": "timeseries",
+                "version": "3.0.0"
+            },
+            {
+                "custom": {
+                    "drawStyle": "lines",
+                    "fillOpacity": 0.3,
+                    "gradientMode": "opacity",
+                    "lineInterpolation": "smooth",
+                    "lineWidth": 2,
+                    "scaleDistribution": {
+                        "type": "linear"
+                    },
+                    "spanNulls": false,
+                    "stack": "noraml"
+                },
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "id": "344a874d-c34d-4d2d-9bb4-46e0912cd9f5",
+                "layout": {
+                    "h": 5,
+                    "i": "344a874d-c34d-4d2d-9bb4-46e0912cd9f5",
+                    "isResizable": true,
+                    "w": 8,
+                    "x": 8,
+                    "y": 5
+                },
+                "maxPerRow": 4,
+                "name": "Hits / Misses per Sec",
+                "options": {
+                    "legend": {
+                        "behaviour": "showItem",
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {
+                        "decimals": 2
+                    },
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#6C53B1",
+                                "type": "base",
+                                "value": null
+                            }
+                        ]
+                    },
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    }
+                },
+                "overrides": [
+                    {
+                        "matcher": {
+                            "id": "byFrameRefID"
+                        },
+                        "properties": {
+                            "rightYAxisDisplay": "off"
+                        }
+                    }
+                ],
+                "targets": [
+                    {
+                        "expr": "irate(redis_keyspace_hits{address=~\"$address\"}[5m])",
+                        "legend": "{{address}} hits",
+                        "maxDataPoints": 240
+                    },
+                    {
+                        "expr": "irate(redis_keyspace_misses{address=~\"$address\"}[5m])",
+                        "legend": "{{address}} misses",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "type": "timeseries",
+                "version": "3.0.0"
+            },
+            {
+                "custom": {
+                    "drawStyle": "lines",
+                    "fillOpacity": 0.3,
+                    "gradientMode": "opacity",
+                    "lineInterpolation": "smooth",
+                    "lineWidth": 2,
+                    "scaleDistribution": {
+                        "type": "linear"
+                    },
+                    "spanNulls": false,
+                    "stack": "off"
+                },
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "id": "3c83cd35-585c-4070-a210-1f17345f13f4",
+                "layout": {
+                    "h": 5,
+                    "i": "3c83cd35-585c-4070-a210-1f17345f13f4",
+                    "isResizable": true,
+                    "w": 8,
+                    "x": 16,
+                    "y": 5
+                },
+                "maxPerRow": 4,
+                "name": "Top Commands",
+                "options": {
+                    "legend": {
+                        "behaviour": "showItem",
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {
+                        "decimals": 2
+                    },
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#6C53B1",
+                                "type": "base",
+                                "value": null
+                            }
+                        ]
+                    },
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "desc"
+                    }
+                },
+                "overrides": [
+                    {
+                        "matcher": {
+                            "id": "byFrameRefID"
+                        },
+                        "properties": {
+                            "rightYAxisDisplay": "off"
+                        }
+                    }
+                ],
+                "targets": [
+                    {
+                        "expr": "topk(5, irate(redis_cmdstat_calls{address=~\"$address\"}[1m]))",
+                        "legend": "{{address}} {{command}}",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "type": "timeseries",
+                "version": "3.0.0"
+            },
+            {
+                "collapsed": true,
+                "id": "1ea61073-a46d-4d7c-b072-fcdcbc5ac084",
+                "layout": {
+                    "h": 1,
+                    "i": "1ea61073-a46d-4d7c-b072-fcdcbc5ac084",
+                    "isResizable": false,
+                    "w": 24,
+                    "x": 0,
+                    "y": 10
+                },
+                "name": "Keys",
+                "type": "row"
+            },
+            {
+                "custom": {
+                    "drawStyle": "lines",
+                    "fillOpacity": 0.3,
+                    "gradientMode": "opacity",
+                    "lineInterpolation": "smooth",
+                    "lineWidth": 2,
+                    "scaleDistribution": {
+                        "type": "linear"
+                    },
+                    "spanNulls": false,
+                    "stack": "off"
+                },
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "id": "b2b4451c-4f8a-438a-8c48-69c95c68361e",
+                "layout": {
+                    "h": 5,
+                    "i": "b2b4451c-4f8a-438a-8c48-69c95c68361e",
+                    "isResizable": true,
+                    "w": 8,
+                    "x": 0,
+                    "y": 11
+                },
+                "maxPerRow": 4,
+                "name": "Total Items per DB",
+                "options": {
+                    "legend": {
+                        "behaviour": "showItem",
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {
+                        "decimals": 2
+                    },
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#6C53B1",
+                                "type": "base",
+                                "value": null
+                            }
+                        ]
+                    },
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "desc"
+                    }
+                },
+                "overrides": [
+                    {
+                        "matcher": {
+                            "id": "byFrameRefID"
+                        },
+                        "properties": {
+                            "rightYAxisDisplay": "off"
+                        }
+                    }
+                ],
+                "targets": [
+                    {
+                        "expr": "sum(redis_keyspace_keys{address=~\"$address\"}) by (address, db)",
+                        "legend": "{{address}} {{db}}",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "type": "timeseries",
+                "version": "3.0.0"
+            },
+            {
+                "custom": {
+                    "drawStyle": "lines",
+                    "fillOpacity": 0.3,
+                    "gradientMode": "opacity",
+                    "lineInterpolation": "smooth",
+                    "lineWidth": 2,
+                    "scaleDistribution": {
+                        "type": "linear"
+                    },
+                    "spanNulls": false,
+                    "stack": "off"
+                },
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "id": "894b9beb-e764-441c-ae04-13e5dbbb901d",
+                "layout": {
+                    "h": 5,
+                    "i": "894b9beb-e764-441c-ae04-13e5dbbb901d",
+                    "isResizable": true,
+                    "w": 8,
+                    "x": 8,
+                    "y": 11
+                },
+                "maxPerRow": 4,
+                "name": "Expired / Evicted",
+                "options": {
+                    "legend": {
+                        "behaviour": "showItem",
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {
+                        "decimals": 2
+                    },
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#6C53B1",
+                                "type": "base",
+                                "value": null
+                            }
+                        ]
+                    },
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "desc"
+                    }
+                },
+                "overrides": [
+                    {
+                        "matcher": {
+                            "id": "byFrameRefID"
+                        },
+                        "properties": {
+                            "rightYAxisDisplay": "off"
+                        }
+                    }
+                ],
+                "targets": [
+                    {
+                        "expr": "sum(rate(redis_expired_keys{address=~\"$address\"}[5m])) by (address)",
+                        "legend": "{{address}} expired",
+                        "maxDataPoints": 240
+                    },
+                    {
+                        "expr": "sum(rate(redis_evicted_keys{address=~\"$address\"}[5m])) by (address)",
+                        "legend": "{{address}} evicted",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "type": "timeseries",
+                "version": "3.0.0"
+            },
+            {
+                "custom": {
+                    "drawStyle": "lines",
+                    "fillOpacity": 0.3,
+                    "gradientMode": "opacity",
+                    "lineInterpolation": "smooth",
+                    "lineWidth": 2,
+                    "scaleDistribution": {
+                        "type": "linear"
+                    },
+                    "spanNulls": false,
+                    "stack": "noraml"
+                },
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "id": "f721a641-28c7-4e82-a37c-ec17704a0c57",
+                "layout": {
+                    "h": 5,
+                    "i": "f721a641-28c7-4e82-a37c-ec17704a0c57",
+                    "isResizable": true,
+                    "w": 8,
+                    "x": 16,
+                    "y": 11
+                },
+                "maxPerRow": 4,
+                "name": "Expiring vs Not-Expiring Keys",
+                "options": {
+                    "legend": {
+                        "behaviour": "showItem",
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {
+                        "decimals": 2
+                    },
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#6C53B1",
+                                "type": "base",
+                                "value": null
+                            }
+                        ]
+                    },
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    }
+                },
+                "overrides": [
+                    {
+                        "matcher": {
+                            "id": "byFrameRefID"
+                        },
+                        "properties": {
+                            "rightYAxisDisplay": "off"
+                        }
+                    }
+                ],
+                "targets": [
+                    {
+                        "expr": "sum(redis_keyspace_keys{address=~\"$address\"}) - sum(redis_keyspace_expires{address=~\"$address\"}) ",
+                        "legend": "{{address}} not expiring",
+                        "maxDataPoints": 240
+                    },
+                    {
+                        "expr": "sum(redis_keyspace_expires{address=~\"$address\"}) ",
+                        "legend": "{{address}} expiring",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "type": "timeseries",
+                "version": "3.0.0"
+            },
+            {
+                "collapsed": true,
+                "id": "60ff41ed-9d41-40ee-a13b-c968f3ca49d0",
+                "layout": {
+                    "h": 1,
+                    "i": "60ff41ed-9d41-40ee-a13b-c968f3ca49d0",
+                    "isResizable": false,
+                    "w": 24,
+                    "x": 0,
+                    "y": 16
+                },
+                "name": "Network",
+                "type": "row"
+            },
+            {
+                "custom": {
+                    "drawStyle": "lines",
+                    "fillOpacity": 0.3,
+                    "gradientMode": "opacity",
+                    "lineInterpolation": "smooth",
+                    "lineWidth": 2,
+                    "scaleDistribution": {
+                        "type": "linear"
+                    },
+                    "spanNulls": false,
+                    "stack": "off"
+                },
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "id": "1841950c-e867-4a62-b846-78754dc0e34d",
+                "layout": {
+                    "h": 7,
+                    "i": "1841950c-e867-4a62-b846-78754dc0e34d",
+                    "isResizable": true,
+                    "w": 24,
+                    "x": 0,
+                    "y": 17
+                },
+                "maxPerRow": 4,
+                "name": "Network I/O",
+                "options": {
+                    "legend": {
+                        "behaviour": "showItem",
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {
+                        "decimals": 2,
+                        "util": "bytesIEC"
+                    },
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#6C53B1",
+                                "type": "base",
+                                "value": null
+                            }
+                        ]
+                    },
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "desc"
+                    }
+                },
+                "overrides": [
+                    {
+                        "matcher": {
+                            "id": "byFrameRefID"
+                        },
+                        "properties": {
+                            "rightYAxisDisplay": "off"
+                        }
+                    }
+                ],
+                "targets": [
+                    {
+                        "expr": "sum(rate(redis_total_net_input_bytes{address=~\"$address\"}[5m]))",
+                        "legend": "input",
+                        "maxDataPoints": 240
+                    },
+                    {
+                        "expr": "sum(rate(redis_total_net_output_bytes{address=~\"$address\"}[5m]))",
+                        "legend": "output",
+                        "maxDataPoints": 240
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "type": "timeseries",
+                "version": "3.0.0"
+            }
+        ],
+        "var": [
+            {
+                "definition": "prometheus",
+                "name": "prom",
+                "type": "datasource"
+            },
+            {
+                "allOption": true,
+                "datasource": {
+                    "cate": "prometheus",
+                    "value": "${prom}"
+                },
+                "definition": "label_values(redis_uptime_in_seconds,address)",
+                "hide": false,
+                "multi": true,
+                "name": "address",
+                "type": "query"
+            }
+        ],
+        "version": "3.0.0"
+    },
+    "uuid": 1732008163114399
+}

integrations/Redis/dashboards/redis_by_categraf.json

@@ -1,6 +1,6 @@
 {
-    "name": "Redis Overview - categraf",
-    "tags": "Redis Prometheus",
+    "name": "Redis by instance",
+    "tags": "Redis Categraf",
     "ident": "",
     "configs": {
         "panels": [

memsto/busi_group_cache.go

@@ -60,6 +60,18 @@ func (c *BusiGroupCacheType) GetByBusiGroupId(id int64) *models.BusiGroup {
 	return c.ugs[id]
 }
 
+func (c *BusiGroupCacheType) GetNamesByBusiGroupIds(ids []int64) []string {
+	c.RLock()
+	defer c.RUnlock()
+	names := make([]string, 0, len(ids))
+	for _, id := range ids {
+		if ug, exists := c.ugs[id]; exists {
+			names = append(names, ug.Name)
+		}
+	}
+	return names
+}
+
 func (c *BusiGroupCacheType) SyncBusiGroups() {
 	err := c.syncBusiGroups()
 	if err != nil {
@@ -112,3 +124,14 @@ func (c *BusiGroupCacheType) syncBusiGroups() error {
 
 	return nil
 }
+
+func (c *BusiGroupCacheType) GetNameByBusiGroupId(id int64) string {
+	c.RLock()
+	defer c.RUnlock()
+
+	busiGroup := c.ugs[id]
+	if busiGroup == nil {
+		return ""
+	}
+	return busiGroup.Name
+}

memsto/config_cval_cache.go

@@ -0,0 +1,150 @@
+package memsto
+
+import (
+	"encoding/json"
+	"log"
+	"sync"
+	"time"
+
+	"github.com/ccfos/nightingale/v6/dumper"
+	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ctx"
+
+	"github.com/pkg/errors"
+	"github.com/toolkits/pkg/logger"
+)
+
+type CvalCache struct {
+	statTotal       int64
+	statLastUpdated int64
+	ctx             *ctx.Context
+	stats           *Stats
+
+	mu    sync.RWMutex
+	cvals map[string]string
+}
+
+func NewCvalCache(ctx *ctx.Context, stats *Stats) *CvalCache {
+	cvalCache := &CvalCache{
+		statTotal:       -1,
+		statLastUpdated: -1,
+		ctx:             ctx,
+		stats:           stats,
+		cvals:           make(map[string]string),
+	}
+	cvalCache.initSyncConfigs()
+	return cvalCache
+}
+
+func (c *CvalCache) initSyncConfigs() {
+	err := c.syncConfigs()
+	if err != nil {
+		log.Fatalln("failed to sync configs:", err)
+	}
+
+	go c.loopSyncConfigs()
+}
+
+func (c *CvalCache) loopSyncConfigs() {
+	duration := time.Duration(9000) * time.Millisecond
+	for {
+		time.Sleep(duration)
+		if err := c.syncConfigs(); err != nil {
+			logger.Warning("failed to sync configs:", err)
+		}
+	}
+}
+
+func (c *CvalCache) syncConfigs() error {
+	start := time.Now()
+
+	stat, err := models.ConfigCvalStatistics(c.ctx)
+	if err != nil {
+		dumper.PutSyncRecord("cvals", start.Unix(), -1, -1, "failed to query statistics: "+err.Error())
+		return errors.WithMessage(err, "failed to call ConfigCvalStatistics")
+	}
+
+	if !c.statChanged(stat.Total, stat.LastUpdated) {
+		c.stats.GaugeCronDuration.WithLabelValues("sync_cvals").Set(0)
+		c.stats.GaugeSyncNumber.WithLabelValues("sync_cvals").Set(0)
+		dumper.PutSyncRecord("cvals", start.Unix(), -1, -1, "not changed")
+		return nil
+	}
+
+	cvals, err := models.ConfigsGetAll(c.ctx)
+	if err != nil {
+		dumper.PutSyncRecord("cvals", start.Unix(), -1, -1, "failed to query records: "+err.Error())
+		return errors.WithMessage(err, "failed to call ConfigsGet")
+	}
+
+	c.Set(cvals, stat.Total, stat.LastUpdated)
+
+	ms := time.Since(start).Milliseconds()
+	c.stats.GaugeCronDuration.WithLabelValues("sync_cvals").Set(float64(ms))
+	c.stats.GaugeSyncNumber.WithLabelValues("sync_cvals").Set(float64(len(c.cvals)))
+
+	logger.Infof("timer: sync cvals done, cost: %dms", ms)
+	dumper.PutSyncRecord("cvals", start.Unix(), ms, len(c.cvals), "success")
+
+	return nil
+}
+
+func (c *CvalCache) statChanged(total int64, updated int64) bool {
+	if c.statTotal == total && c.statLastUpdated == updated {
+		return false
+	}
+	return true
+}
+
+func (c *CvalCache) Set(cvals []*models.Configs, total int64, updated int64) {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+	c.statTotal = total
+	c.statLastUpdated = updated
+	for _, cfg := range cvals {
+		c.cvals[cfg.Ckey] = cfg.Cval
+	}
+}
+
+func (c *CvalCache) Get(ckey string) string {
+	c.mu.RLock()
+	defer c.mu.RUnlock()
+	return c.cvals[ckey]
+}
+
+func (c *CvalCache) GetLastUpdateTime() int64 {
+	c.mu.RLock()
+	defer c.mu.RUnlock()
+	return c.statLastUpdated
+}
+
+type SiteInfo struct {
+	PrintBodyPaths []string `json:"print_body_paths"`
+	PrintAccessLog bool     `json:"print_access_log"`
+}
+
+func (c *CvalCache) GetSiteInfo() *SiteInfo {
+	c.mu.RLock()
+	defer c.mu.RUnlock()
+
+	si := SiteInfo{}
+	if siteInfoStr := c.Get("site_info"); siteInfoStr != "" {
+		if err := json.Unmarshal([]byte(siteInfoStr), &si); err != nil {
+			logger.Errorf("Failed to unmarshal site info: %v", err)
+		}
+	}
+	return &si
+}
+
+func (c *CvalCache) PrintBodyPaths() map[string]struct{} {
+	printBodyPaths := c.GetSiteInfo().PrintBodyPaths
+	pbp := make(map[string]struct{}, len(printBodyPaths))
+	for _, p := range printBodyPaths {
+		pbp[p] = struct{}{}
+	}
+	return pbp
+}
+
+func (c *CvalCache) PrintAccessLog() bool {
+	return c.GetSiteInfo().PrintAccessLog
+}

memsto/datasource_cache.go

@@ -23,7 +23,9 @@ type DatasourceCacheType struct {
 	DatasourceFilter    func([]*models.Datasource, *models.User) []*models.Datasource
 
 	sync.RWMutex
-	ds map[int64]*models.Datasource // key: id
+	ds          map[int64]*models.Datasource            // key: id value: datasource
+	CateToIDs   map[string]map[int64]*models.Datasource // key1: cate key2: id value: datasource
+	CateToNames map[string]map[string]int64             // key1: cate key2: name value: id
 }
 
 func NewDatasourceCache(ctx *ctx.Context, stats *Stats) *DatasourceCacheType {
@@ -33,6 +35,8 @@ func NewDatasourceCache(ctx *ctx.Context, stats *Stats) *DatasourceCacheType {
 		ctx:                 ctx,
 		stats:               stats,
 		ds:                  make(map[int64]*models.Datasource),
+		CateToIDs:           make(map[string]map[int64]*models.Datasource),
+		CateToNames:         make(map[string]map[string]int64),
 		DatasourceCheckHook: func(ctx *gin.Context) bool { return false },
 		DatasourceFilter:    func(ds []*models.Datasource, user *models.User) []*models.Datasource { return ds },
 	}
@@ -40,6 +44,12 @@ func NewDatasourceCache(ctx *ctx.Context, stats *Stats) *DatasourceCacheType {
 	return ds
 }
 
+func (d *DatasourceCacheType) GetIDsByDsCateAndQueries(cate string, datasourceQueries []models.DatasourceQuery) []int64 {
+	d.Lock()
+	defer d.Unlock()
+	return models.GetDatasourceIDsByDatasourceQueries(datasourceQueries, d.CateToIDs[cate], d.CateToNames[cate])
+}
+
 func (d *DatasourceCacheType) StatChanged(total, lastUpdated int64) bool {
 	if d.statTotal == total && d.statLastUpdated == lastUpdated {
 		return false
@@ -49,8 +59,22 @@ func (d *DatasourceCacheType) StatChanged(total, lastUpdated int64) bool {
 }
 
 func (d *DatasourceCacheType) Set(ds map[int64]*models.Datasource, total, lastUpdated int64) {
+	cateToDs := make(map[string]map[int64]*models.Datasource)
+	cateToNames := make(map[string]map[string]int64)
+	for _, datasource := range ds {
+		if _, exists := cateToDs[datasource.PluginType]; !exists {
+			cateToDs[datasource.PluginType] = make(map[int64]*models.Datasource)
+		}
+		cateToDs[datasource.PluginType][datasource.Id] = datasource
+		if _, exists := cateToNames[datasource.PluginType]; !exists {
+			cateToNames[datasource.PluginType] = make(map[string]int64)
+		}
+		cateToNames[datasource.PluginType][datasource.Name] = datasource.Id
+	}
 	d.Lock()
+	d.CateToIDs = cateToDs
 	d.ds = ds
+	d.CateToNames = cateToNames
 	d.Unlock()
 
 	// only one goroutine used, so no need lock
@@ -99,20 +123,20 @@ func (d *DatasourceCacheType) syncDatasources() error {
 		return nil
 	}
 
-	m, err := models.DatasourceGetMap(d.ctx)
+	ds, err := models.DatasourceGetMap(d.ctx)
 	if err != nil {
 		dumper.PutSyncRecord("datasources", start.Unix(), -1, -1, "failed to query records: "+err.Error())
 		return errors.WithMessage(err, "failed to call DatasourceGetMap")
 	}
 
-	d.Set(m, stat.Total, stat.LastUpdated)
+	d.Set(ds, stat.Total, stat.LastUpdated)
 
 	ms := time.Since(start).Milliseconds()
 	d.stats.GaugeCronDuration.WithLabelValues("sync_datasources").Set(float64(ms))
-	d.stats.GaugeSyncNumber.WithLabelValues("sync_datasources").Set(float64(len(m)))
+	d.stats.GaugeSyncNumber.WithLabelValues("sync_datasources").Set(float64(len(ds)))
 
-	logger.Infof("timer: sync datasources done, cost: %dms, number: %d", ms, len(m))
-	dumper.PutSyncRecord("datasources", start.Unix(), ms, len(m), "success")
+	logger.Infof("timer: sync datasources done, cost: %dms, number: %d", ms, len(ds))
+	dumper.PutSyncRecord("datasources", start.Unix(), ms, len(ds), "success")
 
 	return nil
 }

memsto/notify_config.go

@@ -1,7 +1,9 @@
 package memsto
 
 import (
+	"crypto/tls"
 	"encoding/json"
+	"net/http"
 	"strings"
 	"sync"
 	"time"
@@ -19,7 +21,7 @@ import (
 type NotifyConfigCacheType struct {
 	ctx         *ctx.Context
 	ConfigCache *ConfigCache
-	webhooks    []*models.Webhook
+	webhooks    map[string]*models.Webhook
 	smtp        aconf.SMTPConfig
 	script      models.NotifyScript
 
@@ -47,6 +49,7 @@ func NewNotifyConfigCache(ctx *ctx.Context, configCache *ConfigCache) *NotifyCon
 	w := &NotifyConfigCacheType{
 		ctx:         ctx,
 		ConfigCache: configCache,
+		webhooks:    make(map[string]*models.Webhook),
 	}
 	w.SyncNotifyConfigs()
 	return w
@@ -85,11 +88,55 @@ func (w *NotifyConfigCacheType) syncNotifyConfigs() error {
 	}
 
 	if strings.TrimSpace(cval) != "" {
-		err = json.Unmarshal([]byte(cval), &w.webhooks)
+		var webhooks []*models.Webhook
+		err = json.Unmarshal([]byte(cval), &webhooks)
 		if err != nil {
 			dumper.PutSyncRecord("webhooks", start.Unix(), -1, -1, "failed to unmarshal configs.webhook: "+err.Error())
 			logger.Errorf("failed to unmarshal webhooks:%s error:%v", cval, err)
 		}
+
+		newWebhooks := make(map[string]*models.Webhook, len(webhooks))
+		for i := 0; i < len(webhooks); i++ {
+			if webhooks[i].Batch == 0 {
+				webhooks[i].Batch = 1000
+			}
+
+			if webhooks[i].Timeout == 0 {
+				webhooks[i].Timeout = 10
+			}
+
+			if webhooks[i].RetryCount == 0 {
+				webhooks[i].RetryCount = 10
+			}
+
+			if webhooks[i].RetryInterval == 0 {
+				webhooks[i].RetryInterval = 10
+			}
+
+			if webhooks[i].Client == nil {
+				webhooks[i].Client = &http.Client{
+					Timeout: time.Second * time.Duration(webhooks[i].Timeout),
+					Transport: &http.Transport{
+						TLSClientConfig: &tls.Config{InsecureSkipVerify: webhooks[i].SkipVerify},
+					},
+				}
+			}
+			newWebhooks[webhooks[i].Url] = webhooks[i]
+		}
+
+		for url, wh := range newWebhooks {
+			if oldWh, has := w.webhooks[url]; has && oldWh.Hash() != wh.Hash() {
+				w.webhooks[url] = wh
+			} else {
+				w.webhooks[url] = wh
+			}
+		}
+
+		for url := range w.webhooks {
+			if _, has := newWebhooks[url]; !has {
+				delete(w.webhooks, url)
+			}
+		}
 	}
 
 	dumper.PutSyncRecord("webhooks", start.Unix(), time.Since(start).Milliseconds(), len(w.webhooks), "success, webhooks:\n"+cval)
@@ -133,7 +180,7 @@ func (w *NotifyConfigCacheType) syncNotifyConfigs() error {
 	return nil
 }
 
-func (w *NotifyConfigCacheType) GetWebhooks() []*models.Webhook {
+func (w *NotifyConfigCacheType) GetWebhooks() map[string]*models.Webhook {
 	w.RWMutex.RLock()
 	defer w.RWMutex.RUnlock()
 	return w.webhooks

models/alert_cur_event.go

@@ -12,62 +12,71 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
 	"github.com/ccfos/nightingale/v6/pkg/poster"
 	"github.com/ccfos/nightingale/v6/pkg/tplx"
+	"github.com/ccfos/nightingale/v6/pkg/unit"
 
 	"github.com/toolkits/pkg/logger"
 )
 
 type AlertCurEvent struct {
-	Id                 int64             `json:"id" gorm:"primaryKey"`
-	Cate               string            `json:"cate"`
-	Cluster            string            `json:"cluster"`
-	DatasourceId       int64             `json:"datasource_id"`
-	GroupId            int64             `json:"group_id"`   // busi group id
-	GroupName          string            `json:"group_name"` // busi group name
-	Hash               string            `json:"hash"`       // rule_id + vector_key
-	RuleId             int64             `json:"rule_id"`
-	RuleName           string            `json:"rule_name"`
-	RuleNote           string            `json:"rule_note"`
-	RuleProd           string            `json:"rule_prod"`
-	RuleAlgo           string            `json:"rule_algo"`
-	Severity           int               `json:"severity"`
-	PromForDuration    int               `json:"prom_for_duration"`
-	PromQl             string            `json:"prom_ql"`
-	RuleConfig         string            `json:"-" gorm:"rule_config"` // rule config
-	RuleConfigJson     interface{}       `json:"rule_config" gorm:"-"` // rule config for fe
-	PromEvalInterval   int               `json:"prom_eval_interval"`
-	Callbacks          string            `json:"-"`                  // for db
-	CallbacksJSON      []string          `json:"callbacks" gorm:"-"` // for fe
-	RunbookUrl         string            `json:"runbook_url"`
-	NotifyRecovered    int               `json:"notify_recovered"`
-	NotifyChannels     string            `json:"-"`                          // for db
-	NotifyChannelsJSON []string          `json:"notify_channels" gorm:"-"`   // for fe
-	NotifyGroups       string            `json:"-"`                          // for db
-	NotifyGroupsJSON   []string          `json:"notify_groups" gorm:"-"`     // for fe
-	NotifyGroupsObj    []*UserGroup      `json:"notify_groups_obj" gorm:"-"` // for fe
-	TargetIdent        string            `json:"target_ident"`
-	TargetNote         string            `json:"target_note"`
-	TriggerTime        int64             `json:"trigger_time"`
-	TriggerValue       string            `json:"trigger_value"`
-	TriggerValues      string            `json:"trigger_values" gorm:"-"`
-	Tags               string            `json:"-"`                         // for db
-	TagsJSON           []string          `json:"tags" gorm:"-"`             // for fe
-	TagsMap            map[string]string `json:"tags_map" gorm:"-"`         // for internal usage
-	OriginalTags       string            `json:"-"`                         // for db
-	OriginalTagsJSON   []string          `json:"original_tags" gorm:"-"`    // for fe
-	Annotations        string            `json:"-"`                         //
-	AnnotationsJSON    map[string]string `json:"annotations" gorm:"-"`      // for fe
-	IsRecovered        bool              `json:"is_recovered" gorm:"-"`     // for notify.py
-	NotifyUsersObj     []*User           `json:"notify_users_obj" gorm:"-"` // for notify.py
-	LastEvalTime       int64             `json:"last_eval_time" gorm:"-"`   // for notify.py 上次计算的时间
-	LastSentTime       int64             `json:"last_sent_time" gorm:"-"`   // 上次发送时间
-	NotifyCurNumber    int               `json:"notify_cur_number"`         // notify: current number
-	FirstTriggerTime   int64             `json:"first_trigger_time"`        // 连续告警的首次告警时间
-	ExtraConfig        interface{}       `json:"extra_config" gorm:"-"`
-	Status             int               `json:"status" gorm:"-"`
-	Claimant           string            `json:"claimant" gorm:"-"`
-	SubRuleId          int64             `json:"sub_rule_id" gorm:"-"`
-	ExtraInfo          []string          `json:"extra_info" gorm:"-"`
-	Target             *Target           `json:"target" gorm:"-"`
+	Id                 int64               `json:"id" gorm:"primaryKey"`
+	Cate               string              `json:"cate"`
+	Cluster            string              `json:"cluster"`
+	DatasourceId       int64               `json:"datasource_id"`
+	GroupId            int64               `json:"group_id"`   // busi group id
+	GroupName          string              `json:"group_name"` // busi group name
+	Hash               string              `json:"hash"`       // rule_id + vector_key
+	RuleId             int64               `json:"rule_id"`
+	RuleName           string              `json:"rule_name"`
+	RuleNote           string              `json:"rule_note"`
+	RuleProd           string              `json:"rule_prod"`
+	RuleAlgo           string              `json:"rule_algo"`
+	Severity           int                 `json:"severity"`
+	PromForDuration    int                 `json:"prom_for_duration"`
+	PromQl             string              `json:"prom_ql"`
+	RuleConfig         string              `json:"-" gorm:"rule_config"` // rule config
+	RuleConfigJson     interface{}         `json:"rule_config" gorm:"-"` // rule config for fe
+	PromEvalInterval   int                 `json:"prom_eval_interval"`
+	Callbacks          string              `json:"-"`                  // for db
+	CallbacksJSON      []string            `json:"callbacks" gorm:"-"` // for fe
+	RunbookUrl         string              `json:"runbook_url"`
+	NotifyRecovered    int                 `json:"notify_recovered"`
+	NotifyChannels     string              `json:"-"`                          // for db
+	NotifyChannelsJSON []string            `json:"notify_channels" gorm:"-"`   // for fe
+	NotifyGroups       string              `json:"-"`                          // for db
+	NotifyGroupsJSON   []string            `json:"notify_groups" gorm:"-"`     // for fe
+	NotifyGroupsObj    []*UserGroup        `json:"notify_groups_obj" gorm:"-"` // for fe
+	TargetIdent        string              `json:"target_ident"`
+	TargetNote         string              `json:"target_note"`
+	TriggerTime        int64               `json:"trigger_time"`
+	TriggerValue       string              `json:"trigger_value"`
+	TriggerValues      string              `json:"trigger_values" gorm:"-"`
+	TriggerValuesJson  EventTriggerValues  `json:"trigger_values_json" gorm:"-"`
+	Tags               string              `json:"-"`                         // for db
+	TagsJSON           []string            `json:"tags" gorm:"-"`             // for fe
+	TagsMap            map[string]string   `json:"tags_map" gorm:"-"`         // for internal usage
+	OriginalTags       string              `json:"-"`                         // for db
+	OriginalTagsJSON   []string            `json:"original_tags" gorm:"-"`    // for fe
+	Annotations        string              `json:"-"`                         //
+	AnnotationsJSON    map[string]string   `json:"annotations" gorm:"-"`      // for fe
+	IsRecovered        bool                `json:"is_recovered" gorm:"-"`     // for notify.py
+	NotifyUsersObj     []*User             `json:"notify_users_obj" gorm:"-"` // for notify.py
+	LastEvalTime       int64               `json:"last_eval_time" gorm:"-"`   // for notify.py 上次计算的时间
+	LastSentTime       int64               `json:"last_sent_time" gorm:"-"`   // 上次发送时间
+	NotifyCurNumber    int                 `json:"notify_cur_number"`         // notify: current number
+	FirstTriggerTime   int64               `json:"first_trigger_time"`        // 连续告警的首次告警时间
+	ExtraConfig        interface{}         `json:"extra_config" gorm:"-"`
+	Status             int                 `json:"status" gorm:"-"`
+	Claimant           string              `json:"claimant" gorm:"-"`
+	SubRuleId          int64               `json:"sub_rule_id" gorm:"-"`
+	ExtraInfo          []string            `json:"extra_info" gorm:"-"`
+	Target             *Target             `json:"target" gorm:"-"`
+	RecoverConfig      RecoverConfig       `json:"recover_config" gorm:"-"`
+	RuleHash           string              `json:"rule_hash" gorm:"-"`
+	ExtraInfoMap       []map[string]string `json:"extra_info_map" gorm:"-"`
+}
+
+type EventTriggerValues struct {
+	ValuesWithUnit map[string]unit.FormattedValue `json:"values_with_unit"`
 }
 
 func (e *AlertCurEvent) TableName() string {
@@ -106,8 +115,18 @@ func (e *AlertCurEvent) ParseRule(field string) error {
 				"{{$value := .TriggerValue}}",
 			}
 
+			templateFuncMapCopy := tplx.NewTemplateFuncMap()
+			templateFuncMapCopy["query"] = func(promql string, param ...int64) []AnomalyPoint {
+				datasourceId := e.DatasourceId
+				if len(param) > 0 {
+					datasourceId = param[0]
+				}
+				value := tplx.Query(datasourceId, promql)
+				return ConvertAnomalyPoints(value)
+			}
+
 			text := strings.Join(append(defs, f), "")
-			t, err := template.New(fmt.Sprint(e.RuleId)).Funcs(template.FuncMap(tplx.TemplateFuncMap)).Parse(text)
+			t, err := template.New(fmt.Sprint(e.RuleId)).Funcs(templateFuncMapCopy).Parse(text)
 			if err != nil {
 				e.AnnotationsJSON[k] = fmt.Sprintf("failed to parse annotations: %v", err)
 				continue
@@ -356,6 +375,15 @@ func (e *AlertCurEvent) DB2Mem() {
 	}
 }
 
+func (e *AlertCurEvent) OverrideGlobalWebhook() bool {
+	var rc RuleConfig
+	if err := json.Unmarshal([]byte(e.RuleConfig), &rc); err != nil {
+		logger.Warningf("failed to unmarshal rule config: %v", err)
+		return false
+	}
+	return rc.OverrideGlobalWebhook
+}
+
 func FillRuleConfigTplName(ctx *ctx.Context, ruleConfig string) (interface{}, bool) {
 	var config RuleConfig
 	err := json.Unmarshal([]byte(ruleConfig), &config)

models/alert_mute.go

@@ -108,7 +108,7 @@ func AlertMuteGet(ctx *ctx.Context, where string, args ...interface{}) (*AlertMu
 	return lst[0], err
 }
 
-func AlertMuteGets(ctx *ctx.Context, prods []string, bgid int64, query string) (lst []AlertMute, err error) {
+func AlertMuteGets(ctx *ctx.Context, prods []string, bgid int64, disabled int, query string) (lst []AlertMute, err error) {
 	session := DB(ctx)
 
 	if bgid != -1 {
@@ -119,6 +119,14 @@ func AlertMuteGets(ctx *ctx.Context, prods []string, bgid int64, query string) (
 		session = session.Where("prod in (?)", prods)
 	}
 
+	if disabled != -1 {
+		if disabled == 0 {
+			session = session.Where("disabled = 0")
+		} else {
+			session = session.Where("disabled = 1")
+		}
+	}
+
 	if query != "" {
 		arr := strings.Fields(query)
 		for i := 0; i < len(arr); i++ {
@@ -287,16 +295,9 @@ func AlertMuteStatistics(ctx *ctx.Context) (*Statistics, error) {
 		return s, err
 	}
 
-	// clean expired first
-	buf := int64(30)
-	err := DB(ctx).Where("etime < ? and mute_time_type = 0", time.Now().Unix()-buf).Delete(new(AlertMute)).Error
-	if err != nil {
-		return nil, err
-	}
-
 	session := DB(ctx).Model(&AlertMute{}).Select("count(*) as total", "max(update_at) as last_updated")
 
-	err = session.Find(&stats).Error
+	err := session.Find(&stats).Error
 	if err != nil {
 		return nil, err
 	}
@@ -308,7 +309,7 @@ func AlertMuteGetsAll(ctx *ctx.Context) ([]*AlertMute, error) {
 	// get my cluster's mutes
 	var lst []*AlertMute
 	if !ctx.IsCenter {
-		lst, err := poster.GetByUrls[[]*AlertMute](ctx, "/v1/n9e/alert-mutes")
+		lst, err := poster.GetByUrls[[]*AlertMute](ctx, "/v1/n9e/alert-mutes?disabled=0")
 		if err != nil {
 			return nil, err
 		}
@@ -318,7 +319,7 @@ func AlertMuteGetsAll(ctx *ctx.Context) ([]*AlertMute, error) {
 		return lst, err
 	}
 
-	session := DB(ctx).Model(&AlertMute{})
+	session := DB(ctx).Model(&AlertMute{}).Where("disabled = 0")
 
 	err := session.Find(&lst).Error
 	if err != nil {

models/alert_rule.go

@@ -13,6 +13,7 @@ import (
 
 	"github.com/jinzhu/copier"
 	"github.com/pkg/errors"
+	"github.com/tidwall/match"
 	"github.com/toolkits/pkg/logger"
 	"github.com/toolkits/pkg/str"
 )
@@ -23,8 +24,9 @@ const (
 	HOST   = "host"
 	LOKI   = "loki"
 
-	PROMETHEUS = "prometheus"
-	TDENGINE   = "tdengine"
+	PROMETHEUS    = "prometheus"
+	TDENGINE      = "tdengine"
+	ELASTICSEARCH = "elasticsearch"
 )
 
 const (
@@ -44,55 +46,56 @@ const (
 
 type AlertRule struct {
 	Id                    int64                  `json:"id" gorm:"primaryKey"`
-	GroupId               int64                  `json:"group_id"`                      // busi group id
-	Cate                  string                 `json:"cate"`                          // alert rule cate (prometheus|elasticsearch)
-	DatasourceIds         string                 `json:"-" gorm:"datasource_ids"`       // datasource ids
-	DatasourceIdsJson     []int64                `json:"datasource_ids" gorm:"-"`       // for fe
-	Cluster               string                 `json:"cluster"`                       // take effect by clusters, seperated by space
-	Name                  string                 `json:"name"`                          // rule name
-	Note                  string                 `json:"note"`                          // will sent in notify
-	Prod                  string                 `json:"prod"`                          // product empty means n9e
-	Algorithm             string                 `json:"algorithm"`                     // algorithm (''|holtwinters), empty means threshold
-	AlgoParams            string                 `json:"-" gorm:"algo_params"`          // params algorithm need
-	AlgoParamsJson        interface{}            `json:"algo_params" gorm:"-"`          // for fe
-	Delay                 int                    `json:"delay"`                         // Time (in seconds) to delay evaluation
-	Severity              int                    `json:"severity"`                      // 1: Emergency 2: Warning 3: Notice
-	Severities            []int                  `json:"severities" gorm:"-"`           // 1: Emergency 2: Warning 3: Notice
-	Disabled              int                    `json:"disabled"`                      // 0: enabled, 1: disabled
-	PromForDuration       int                    `json:"prom_for_duration"`             // prometheus for, unit:s
-	PromQl                string                 `json:"prom_ql"`                       // just one ql
-	RuleConfig            string                 `json:"-" gorm:"rule_config"`          // rule config
-	RuleConfigJson        interface{}            `json:"rule_config" gorm:"-"`          // rule config for fe
-	EventRelabelConfig    []*pconf.RelabelConfig `json:"event_relabel_config" gorm:"-"` // event relabel config
-	PromEvalInterval      int                    `json:"prom_eval_interval"`            // unit:s
-	EnableStime           string                 `json:"-"`                             // split by space: "00:00 10:00 12:00"
-	EnableStimeJSON       string                 `json:"enable_stime" gorm:"-"`         // for fe
-	EnableStimesJSON      []string               `json:"enable_stimes" gorm:"-"`        // for fe
-	EnableEtime           string                 `json:"-"`                             // split by space: "00:00 10:00 12:00"
-	EnableEtimeJSON       string                 `json:"enable_etime" gorm:"-"`         // for fe
-	EnableEtimesJSON      []string               `json:"enable_etimes" gorm:"-"`        // for fe
-	EnableDaysOfWeek      string                 `json:"-"`                             // eg: "0 1 2 3 4 5 6 ; 0 1 2"
-	EnableDaysOfWeekJSON  []string               `json:"enable_days_of_week" gorm:"-"`  // for fe
-	EnableDaysOfWeeksJSON [][]string             `json:"enable_days_of_weeks" gorm:"-"` // for fe
-	EnableInBG            int                    `json:"enable_in_bg"`                  // 0: global 1: enable one busi-group
-	NotifyRecovered       int                    `json:"notify_recovered"`              // whether notify when recovery
-	NotifyChannels        string                 `json:"-"`                             // split by space: sms voice email dingtalk wecom
-	NotifyChannelsJSON    []string               `json:"notify_channels" gorm:"-"`      // for fe
-	NotifyGroups          string                 `json:"-"`                             // split by space: 233 43
-	NotifyGroupsObj       []UserGroup            `json:"notify_groups_obj" gorm:"-"`    // for fe
-	NotifyGroupsJSON      []string               `json:"notify_groups" gorm:"-"`        // for fe
-	NotifyRepeatStep      int                    `json:"notify_repeat_step"`            // notify repeat interval, unit: min
-	NotifyMaxNumber       int                    `json:"notify_max_number"`             // notify: max number
-	RecoverDuration       int64                  `json:"recover_duration"`              // unit: s
-	Callbacks             string                 `json:"-"`                             // split by space: http://a.com/api/x http://a.com/api/y'
-	CallbacksJSON         []string               `json:"callbacks" gorm:"-"`            // for fe
-	RunbookUrl            string                 `json:"runbook_url"`                   // sop url
-	AppendTags            string                 `json:"-"`                             // split by space: service=n9e mod=api
-	AppendTagsJSON        []string               `json:"append_tags" gorm:"-"`          // for fe
-	Annotations           string                 `json:"-"`                             //
-	AnnotationsJSON       map[string]string      `json:"annotations" gorm:"-"`          // for fe
-	ExtraConfig           string                 `json:"-" gorm:"extra_config"`         // extra config
-	ExtraConfigJSON       interface{}            `json:"extra_config" gorm:"-"`         // for fe
+	GroupId               int64                  `json:"group_id"` // busi group id
+	Cate                  string                 `json:"cate"`     // alert rule cate (prometheus|elasticsearch)
+	DatasourceIds         string                 `json:"-" gorm:"datasource_ids"`
+	DatasourceIdsJson     []int64                `json:"datasource_ids,omitempty" gorm:"-"`                                      // alert rule list page use this field
+	DatasourceQueries     []DatasourceQuery      `json:"datasource_queries" gorm:"datasource_queries;type:text;serializer:json"` // datasource queries
+	Cluster               string                 `json:"cluster"`                                                                // take effect by clusters, seperated by space
+	Name                  string                 `json:"name"`                                                                   // rule name
+	Note                  string                 `json:"note"`                                                                   // will sent in notify
+	Prod                  string                 `json:"prod"`                                                                   // product empty means n9e
+	Algorithm             string                 `json:"algorithm"`                                                              // algorithm (''|holtwinters), empty means threshold
+	AlgoParams            string                 `json:"-" gorm:"algo_params"`                                                   // params algorithm need
+	AlgoParamsJson        interface{}            `json:"algo_params" gorm:"-"`                                                   // for fe
+	Delay                 int                    `json:"delay"`                                                                  // Time (in seconds) to delay evaluation
+	Severity              int                    `json:"severity"`                                                               // 1: Emergency 2: Warning 3: Notice
+	Severities            []int                  `json:"severities" gorm:"-"`                                                    // 1: Emergency 2: Warning 3: Notice
+	Disabled              int                    `json:"disabled"`                                                               // 0: enabled, 1: disabled
+	PromForDuration       int                    `json:"prom_for_duration"`                                                      // prometheus for, unit:s
+	PromQl                string                 `json:"prom_ql"`                                                                // just one ql
+	RuleConfig            string                 `json:"-" gorm:"rule_config"`                                                   // rule config
+	RuleConfigJson        interface{}            `json:"rule_config" gorm:"-"`                                                   // rule config for fe
+	EventRelabelConfig    []*pconf.RelabelConfig `json:"event_relabel_config" gorm:"-"`                                          // event relabel config
+	PromEvalInterval      int                    `json:"prom_eval_interval"`                                                     // unit:s
+	EnableStime           string                 `json:"-"`                                                                      // split by space: "00:00 10:00 12:00"
+	EnableStimeJSON       string                 `json:"enable_stime" gorm:"-"`                                                  // for fe
+	EnableStimesJSON      []string               `json:"enable_stimes" gorm:"-"`                                                 // for fe
+	EnableEtime           string                 `json:"-"`                                                                      // split by space: "00:00 10:00 12:00"
+	EnableEtimeJSON       string                 `json:"enable_etime" gorm:"-"`                                                  // for fe
+	EnableEtimesJSON      []string               `json:"enable_etimes" gorm:"-"`                                                 // for fe
+	EnableDaysOfWeek      string                 `json:"-"`                                                                      // eg: "0 1 2 3 4 5 6 ; 0 1 2"
+	EnableDaysOfWeekJSON  []string               `json:"enable_days_of_week" gorm:"-"`                                           // for fe
+	EnableDaysOfWeeksJSON [][]string             `json:"enable_days_of_weeks" gorm:"-"`                                          // for fe
+	EnableInBG            int                    `json:"enable_in_bg"`                                                           // 0: global 1: enable one busi-group
+	NotifyRecovered       int                    `json:"notify_recovered"`                                                       // whether notify when recovery
+	NotifyChannels        string                 `json:"-"`                                                                      // split by space: sms voice email dingtalk wecom
+	NotifyChannelsJSON    []string               `json:"notify_channels" gorm:"-"`                                               // for fe
+	NotifyGroups          string                 `json:"-"`                                                                      // split by space: 233 43
+	NotifyGroupsObj       []UserGroup            `json:"notify_groups_obj" gorm:"-"`                                             // for fe
+	NotifyGroupsJSON      []string               `json:"notify_groups" gorm:"-"`                                                 // for fe
+	NotifyRepeatStep      int                    `json:"notify_repeat_step"`                                                     // notify repeat interval, unit: min
+	NotifyMaxNumber       int                    `json:"notify_max_number"`                                                      // notify: max number
+	RecoverDuration       int64                  `json:"recover_duration"`                                                       // unit: s
+	Callbacks             string                 `json:"-"`                                                                      // split by space: http://a.com/api/x http://a.com/api/y'
+	CallbacksJSON         []string               `json:"callbacks" gorm:"-"`                                                     // for fe
+	RunbookUrl            string                 `json:"runbook_url"`                                                            // sop url
+	AppendTags            string                 `json:"-"`                                                                      // split by space: service=n9e mod=api
+	AppendTagsJSON        []string               `json:"append_tags" gorm:"-"`                                                   // for fe
+	Annotations           string                 `json:"-"`                                                                      //
+	AnnotationsJSON       map[string]string      `json:"annotations" gorm:"-"`                                                   // for fe
+	ExtraConfig           string                 `json:"-" gorm:"extra_config"`                                                  // extra config
+	ExtraConfigJSON       interface{}            `json:"extra_config" gorm:"-"`                                                  // for fe
 	CreateAt              int64                  `json:"create_at"`
 	CreateBy              string                 `json:"create_by"`
 	UpdateAt              int64                  `json:"update_at"`
@@ -100,6 +103,29 @@ type AlertRule struct {
 	UUID                  int64                  `json:"uuid" gorm:"-"` // tpl identifier
 	CurEventCount         int64                  `json:"cur_event_count" gorm:"-"`
 	UpdateByNickname      string                 `json:"update_by_nickname" gorm:"-"` // for fe
+	CronPattern           string                 `json:"cron_pattern"`
+}
+
+type ChildVarConfig struct {
+	ParamVal        []map[string]ParamQuery `json:"param_val"`
+	ChildVarConfigs *ChildVarConfig         `json:"child_var_configs"`
+}
+
+type ParamQuery struct {
+	ParamType string      `json:"param_type"` // host、device、enum、threshold 三种类型
+	Query     interface{} `json:"query"`
+}
+
+type VarConfig struct {
+	ParamVal        []ParamQueryForFirst `json:"param_val"`
+	ChildVarConfigs *ChildVarConfig      `json:"child_var_configs"`
+}
+
+// ParamQueryForFirst 同 ParamQuery，仅在第一层出现
+type ParamQueryForFirst struct {
+	Name      string      `json:"name"`
+	ParamType string      `json:"param_type"`
+	Query     interface{} `json:"query"`
 }
 
 type Tpl struct {
@@ -109,15 +135,16 @@ type Tpl struct {
 }
 
 type RuleConfig struct {
-	Version            string                 `json:"version,omitempty"`
-	EventRelabelConfig []*pconf.RelabelConfig `json:"event_relabel_config,omitempty"`
-	TaskTpls           []*Tpl                 `json:"task_tpls,omitempty"`
-	Queries            interface{}            `json:"queries,omitempty"`
-	Triggers           []Trigger              `json:"triggers,omitempty"`
-	Inhibit            bool                   `json:"inhibit,omitempty"`
-	PromQl             string                 `json:"prom_ql,omitempty"`
-	Severity           int                    `json:"severity,omitempty"`
-	AlgoParams         interface{}            `json:"algo_params,omitempty"`
+	Version               string                 `json:"version,omitempty"`
+	EventRelabelConfig    []*pconf.RelabelConfig `json:"event_relabel_config,omitempty"`
+	TaskTpls              []*Tpl                 `json:"task_tpls,omitempty"`
+	Queries               interface{}            `json:"queries,omitempty"`
+	Triggers              []Trigger              `json:"triggers,omitempty"`
+	Inhibit               bool                   `json:"inhibit,omitempty"`
+	PromQl                string                 `json:"prom_ql,omitempty"`
+	Severity              int                    `json:"severity,omitempty"`
+	AlgoParams            interface{}            `json:"algo_params,omitempty"`
+	OverrideGlobalWebhook bool                   `json:"override_global_webhook,omitempty"`
 }
 
 type PromRuleConfig struct {
@@ -128,6 +155,19 @@ type PromRuleConfig struct {
 	AlgoParams interface{} `json:"algo_params"`
 }
 
+type RecoverJudge int
+
+const (
+	Origin             RecoverJudge = 0
+	RecoverWithoutData RecoverJudge = 1
+	RecoverOnCondition RecoverJudge = 2
+)
+
+type RecoverConfig struct {
+	JudgeType  RecoverJudge `json:"judge_type"`
+	RecoverExp string       `json:"recover_exp"`
+}
+
 type HostRuleConfig struct {
 	Queries  []HostQuery   `json:"queries"`
 	Triggers []HostTrigger `json:"triggers"`
@@ -135,8 +175,12 @@ type HostRuleConfig struct {
 }
 
 type PromQuery struct {
-	PromQl   string `json:"prom_ql"`
-	Severity int    `json:"severity"`
+	PromQl        string        `json:"prom_ql"`
+	Severity      int           `json:"severity"`
+	VarEnabled    bool          `json:"var_enabled"`
+	VarConfig     VarConfig     `json:"var_config"`
+	RecoverConfig RecoverConfig `json:"recover_config"`
+	Unit          string        `json:"unit"`
 }
 
 type HostTrigger struct {
@@ -159,17 +203,146 @@ type Trigger struct {
 	Exp         string      `json:"exp"`
 	Severity    int         `json:"severity"`
 
-	Type     string `json:"type,omitempty"`
-	Duration int    `json:"duration,omitempty"`
-	Percent  int    `json:"percent,omitempty"`
-	Joins    []Join `json:"joins"`
+	Type          string        `json:"type,omitempty"`
+	Duration      int           `json:"duration,omitempty"`
+	Percent       int           `json:"percent,omitempty"`
+	Joins         []Join        `json:"joins"`
+	JoinRef       string        `json:"join_ref"`
+	RecoverConfig RecoverConfig `json:"recover_config"`
 }
 
 type Join struct {
 	JoinType string   `json:"join_type"`
+	Ref      string   `json:"ref"`
 	On       []string `json:"on"`
 }
 
+var DataSourceQueryAll = DatasourceQuery{
+	MatchType: 2,
+	Op:        "in",
+	Values:    []interface{}{DatasourceIdAll},
+}
+
+type DatasourceQuery struct {
+	MatchType int           `json:"match_type"`
+	Op        string        `json:"op"`
+	Values    []interface{} `json:"values"`
+}
+
+// GetDatasourceIDsByDatasourceQueries 从 datasourceQueries 中获取 datasourceIDs
+// 查询分为精确\模糊匹配，逻辑有 in 与 not in
+// idMap 为当前 datasourceQueries 对应的数据源全集
+// nameMap 为所有 datasource 的 name 到 id 的映射，用于名称的模糊匹配
+func GetDatasourceIDsByDatasourceQueries[T any](datasourceQueries []DatasourceQuery, idMap map[int64]T, nameMap map[string]int64) []int64 {
+	if len(datasourceQueries) == 0 {
+		return nil
+	}
+
+	// 所有 query 取交集，初始集合为全集
+	curIDs := make(map[int64]struct{})
+	for id, _ := range idMap {
+		curIDs[id] = struct{}{}
+	}
+
+	for i := range datasourceQueries {
+		// 每次 query 都在 curIDs 的基础上得到 dsIDs
+		dsIDs := make(map[int64]struct{})
+		q := datasourceQueries[i]
+		if q.MatchType == 0 {
+			// 精确匹配转为 id 匹配
+			idValues := make([]int64, 0, len(q.Values))
+			for v := range q.Values {
+				var val int64
+				switch v := q.Values[v].(type) {
+				case int64:
+					val = v
+				case int:
+					val = int64(v)
+				case float64:
+					val = int64(v)
+				case float32:
+					val = int64(v)
+				case int8:
+					val = int64(v)
+				case int16:
+					val = int64(v)
+				case int32:
+					val = int64(v)
+				default:
+					continue
+				}
+				idValues = append(idValues, int64(val))
+			}
+
+			if q.Op == "in" {
+				if len(idValues) == 1 && idValues[0] == DatasourceIdAll {
+					for id := range curIDs {
+						dsIDs[id] = struct{}{}
+					}
+				} else {
+					for idx := range idValues {
+						if _, exist := curIDs[idValues[idx]]; exist {
+							dsIDs[idValues[idx]] = struct{}{}
+						}
+					}
+				}
+			} else if q.Op == "not in" {
+				for idx := range idValues {
+					delete(curIDs, idValues[idx])
+				}
+				dsIDs = curIDs
+			}
+		} else if q.MatchType == 1 {
+			// 模糊匹配使用 datasource name
+			if q.Op == "in" {
+				for dsName, dsID := range nameMap {
+					if _, exist := curIDs[dsID]; exist {
+						for idx := range q.Values {
+							if _, ok := q.Values[idx].(string); !ok {
+								continue
+							}
+
+							if match.Match(dsName, q.Values[idx].(string)) {
+								dsIDs[nameMap[dsName]] = struct{}{}
+							}
+						}
+					}
+				}
+			} else if q.Op == "not in" {
+				for dsName, _ := range nameMap {
+					for idx := range q.Values {
+						if _, ok := q.Values[idx].(string); !ok {
+							continue
+						}
+
+						if match.Match(dsName, q.Values[idx].(string)) {
+							delete(curIDs, nameMap[dsName])
+						}
+					}
+				}
+				dsIDs = curIDs
+			}
+		} else if q.MatchType == 2 {
+			// 全部数据源
+			for id := range curIDs {
+				dsIDs[id] = struct{}{}
+			}
+		}
+
+		curIDs = dsIDs
+		if len(curIDs) == 0 {
+			break
+		}
+	}
+
+	dsIds := make([]int64, 0, len(curIDs))
+	for c := range curIDs {
+		dsIds = append(dsIds, c)
+	}
+
+	return dsIds
+}
+
 func GetHostsQuery(queries []HostQuery) []map[string]interface{} {
 	var query []map[string]interface{}
 	for _, q := range queries {
@@ -199,12 +372,14 @@ func GetHostsQuery(queries []HostQuery) []map[string]interface{} {
 					blank += " "
 				}
 			} else {
-				blank := " "
+				var args []interface{}
+				var query []string
 				for _, tag := range lst {
-					m["tags not like ?"+blank] = "%" + tag + "%"
-					m["host_tags not like ?"+blank] = "%" + tag + "%"
-					blank += " "
+					query = append(query, "tags not like ?",
+						"(host_tags not like ? or host_tags is null)")
+					args = append(args, "%"+tag+"%", "%"+tag+"%")
 				}
+				m[strings.Join(query, " and ")] = args
 			}
 		case "hosts":
 			lst := []string{}
@@ -225,11 +400,13 @@ func GetHostsQuery(queries []HostQuery) []map[string]interface{} {
 					blank += " "
 				}
 			} else if q.Op == "!~" {
-				blank := " "
+				var args []interface{}
+				var query []string
 				for _, host := range lst {
-					m["ident not like ?"+blank] = strings.ReplaceAll(host, "*", "%")
-					blank += " "
+					query = append(query, "ident not like ?")
+					args = append(args, strings.ReplaceAll(host, "*", "%"))
 				}
+				m[strings.Join(query, " and ")] = args
 			}
 		}
 		query = append(query, m)
@@ -268,9 +445,9 @@ func (ar *AlertRule) Verify() error {
 		return fmt.Errorf("GroupId(%d) invalid", ar.GroupId)
 	}
 
-	if IsAllDatasource(ar.DatasourceIdsJson) {
-		ar.DatasourceIdsJson = []int64{0}
-	}
+	//if IsAllDatasource(ar.DatasourceIdsJson) {
+	//	ar.DatasourceIdsJson = []int64{0}
+	//}
 
 	if str.Dangerous(ar.Name) {
 		return errors.New("Name has invalid characters")
@@ -324,7 +501,7 @@ func (ar *AlertRule) Add(ctx *ctx.Context) error {
 		return err
 	}
 
-	exists, err := AlertRuleExists(ctx, 0, ar.GroupId, ar.DatasourceIdsJson, ar.Name)
+	exists, err := AlertRuleExists(ctx, 0, ar.GroupId, ar.Name)
 	if err != nil {
 		return err
 	}
@@ -342,7 +519,7 @@ func (ar *AlertRule) Add(ctx *ctx.Context) error {
 
 func (ar *AlertRule) Update(ctx *ctx.Context, arf AlertRule) error {
 	if ar.Name != arf.Name {
-		exists, err := AlertRuleExists(ctx, ar.Id, ar.GroupId, ar.DatasourceIdsJson, arf.Name)
+		exists, err := AlertRuleExists(ctx, ar.Id, ar.GroupId, arf.Name)
 		if err != nil {
 			return err
 		}
@@ -491,11 +668,30 @@ func (ar *AlertRule) UpdateFieldsMap(ctx *ctx.Context, fields map[string]interfa
 	return DB(ctx).Model(ar).Updates(fields).Error
 }
 
-// for v5 rule
-func (ar *AlertRule) FillDatasourceIds() error {
-	if ar.DatasourceIds != "" {
-		json.Unmarshal([]byte(ar.DatasourceIds), &ar.DatasourceIdsJson)
-		return nil
+func (ar *AlertRule) FillDatasourceQueries() error {
+	// 兼容旧逻辑，将 datasourceIds 转换为 datasourceQueries
+	if len(ar.DatasourceQueries) == 0 && len(ar.DatasourceIds) != 0 {
+		datasourceQueries := DatasourceQuery{
+			MatchType: 0,
+			Op:        "in",
+			Values:    make([]interface{}, 0),
+		}
+
+		var values []int
+		if ar.DatasourceIds != "" {
+			json.Unmarshal([]byte(ar.DatasourceIds), &values)
+
+		}
+
+		for i := range values {
+			if values[i] == 0 {
+				// 0 表示所有数据源
+				datasourceQueries.MatchType = 2
+				break
+			}
+			datasourceQueries.Values = append(datasourceQueries.Values, values[i])
+		}
+		ar.DatasourceQueries = []DatasourceQuery{datasourceQueries}
 	}
 	return nil
 }
@@ -614,14 +810,6 @@ func (ar *AlertRule) FE2DB() error {
 	}
 	ar.AlgoParams = string(algoParamsByte)
 
-	if len(ar.DatasourceIdsJson) > 0 {
-		idsByte, err := json.Marshal(ar.DatasourceIdsJson)
-		if err != nil {
-			return fmt.Errorf("marshal datasource_ids err:%v", err)
-		}
-		ar.DatasourceIds = string(idsByte)
-	}
-
 	if ar.RuleConfigJson == nil {
 		query := PromQuery{
 			PromQl:   ar.PromQl,
@@ -693,8 +881,17 @@ func (ar *AlertRule) DB2FE() error {
 	json.Unmarshal([]byte(ar.RuleConfig), &ruleConfig)
 	ar.EventRelabelConfig = ruleConfig.EventRelabelConfig
 
-	err := ar.FillDatasourceIds()
-	return err
+	// 兼容旧逻辑填充 cron_pattern
+	if ar.CronPattern == "" && ar.PromEvalInterval != 0 {
+		ar.CronPattern = fmt.Sprintf("@every %ds", ar.PromEvalInterval)
+	}
+
+	err := ar.FillDatasourceQueries()
+	if err != nil {
+		return err
+	}
+
+	return nil
 }
 
 func AlertRuleDels(ctx *ctx.Context, ids []int64, bgid ...int64) error {
@@ -708,7 +905,7 @@ func AlertRuleDels(ctx *ctx.Context, ids []int64, bgid ...int64) error {
 			return ret.Error
 		}
 
-		// 说明确实删掉了，把相关的活跃告警也删了，这些告警永远都不会恢复了，而且策略都没了，说明没人关心了
+		// 说明确实删掉了，把相关的活跃告警也删了，这些告警永远都不会恢复了，而且策略都没了，说明没<EFBFBD><EFBFBD><EFBFBD>关心了
 		if ret.RowsAffected > 0 {
 			DB(ctx).Where("rule_id = ?", ids[i]).Delete(new(AlertCurEvent))
 		}
@@ -717,7 +914,7 @@ func AlertRuleDels(ctx *ctx.Context, ids []int64, bgid ...int64) error {
 	return nil
 }
 
-func AlertRuleExists(ctx *ctx.Context, id, groupId int64, datasourceIds []int64, name string) (bool, error) {
+func AlertRuleExists(ctx *ctx.Context, id, groupId int64, name string) (bool, error) {
 	session := DB(ctx).Where("id <> ? and group_id = ? and name = ?", id, groupId, name)
 
 	var lst []AlertRule
@@ -729,15 +926,6 @@ func AlertRuleExists(ctx *ctx.Context, id, groupId int64, datasourceIds []int64,
 		return false, nil
 	}
 
-	// match cluster
-	for _, r := range lst {
-		r.FillDatasourceIds()
-		for _, id := range r.DatasourceIdsJson {
-			if MatchDatasource(datasourceIds, id) {
-				return true, nil
-			}
-		}
-	}
 	return false, nil
 }
 
@@ -957,7 +1145,6 @@ func (ar *AlertRule) UpdateEvent(event *AlertCurEvent) {
 	event.PromForDuration = ar.PromForDuration
 	event.RuleConfig = ar.RuleConfig
 	event.RuleConfigJson = ar.RuleConfigJson
-	event.PromEvalInterval = ar.PromEvalInterval
 	event.Callbacks = ar.Callbacks
 	event.CallbacksJSON = ar.CallbacksJSON
 	event.RunbookUrl = ar.RunbookUrl
@@ -1109,3 +1296,7 @@ func InsertAlertRule(ctx *ctx.Context, ars []*AlertRule) error {
 	}
 	return DB(ctx).Create(ars).Error
 }
+
+func (ar *AlertRule) Hash() string {
+	return str.MD5(fmt.Sprintf("%d_%s_%s", ar.Id, ar.DatasourceIds, ar.RuleConfig))
+}

models/alert_subscribe.go

@@ -114,6 +114,11 @@ func (s *AlertSubscribe) Verify() error {
 		return errors.New("severities is required")
 	}
 
+	if s.UserGroupIds != "" && s.NewChannels == "" {
+		// 如果指定了用户组，那么新告警的通知渠道必须指定，否则容易出现告警规则中没有指定通知渠道，导致订阅通知时，没有通知渠道
+		return errors.New("new_channels is required")
+	}
+
 	ugids := strings.Fields(s.UserGroupIds)
 	for i := 0; i < len(ugids); i++ {
 		if _, err := strconv.ParseInt(ugids[i], 10, 64); err != nil {

models/anomaly_point.go

@@ -1,22 +1,25 @@
-package common
+package models
 
 import (
 	"fmt"
 	"math"
 	"strings"
 
+	"github.com/ccfos/nightingale/v6/pkg/unit"
 	"github.com/prometheus/common/model"
 )
 
 type AnomalyPoint struct {
-	Key       string       `json:"key"`
-	Labels    model.Metric `json:"labels"`
-	Timestamp int64        `json:"timestamp"`
-	Value     float64      `json:"value"`
-	Severity  int          `json:"severity"`
-	Triggered bool         `json:"triggered"`
-	Query     string       `json:"query"`
-	Values    string       `json:"values"`
+	Key           string                         `json:"key"`
+	Labels        model.Metric                   `json:"labels"`
+	Timestamp     int64                          `json:"timestamp"`
+	Value         float64                        `json:"value"`
+	Severity      int                            `json:"severity"`
+	Triggered     bool                           `json:"triggered"`
+	Query         string                         `json:"query"`
+	Values        string                         `json:"values"`
+	ValuesUnit    map[string]unit.FormattedValue `json:"values_unit"`
+	RecoverConfig RecoverConfig                  `json:"recover_config"`
 }
 
 func NewAnomalyPoint(key string, labels map[string]string, ts int64, value float64, severity int) AnomalyPoint {

models/builtin_component.go

@@ -10,9 +10,20 @@ import (
 
 // BuiltinComponent represents a builtin component along with its metadata.
 type BuiltinComponent struct {
+	ID        uint64 `json:"id" gorm:"primaryKey;type:bigint;autoIncrement;comment:'unique identifier'"`
+	Ident     string `json:"ident" gorm:"type:varchar(191);not null;uniqueIndex:idx_ident,sort:asc"`
+	Logo      string `json:"logo" gorm:"type:mediumtext;comment:'logo of component'"`
+	Readme    string `json:"readme" gorm:"type:text;not null;comment:'readme of component'"`
+	CreatedAt int64  `json:"created_at" gorm:"type:bigint;not null;default:0;comment:'create time'"`
+	CreatedBy string `json:"created_by" gorm:"type:varchar(191);not null;default:'';comment:'creator'"`
+	UpdatedAt int64  `json:"updated_at" gorm:"type:bigint;not null;default:0;comment:'update time'"`
+	UpdatedBy string `json:"updated_by" gorm:"type:varchar(191);not null;default:'';comment:'updater'"`
+}
+
+type PostgresBuiltinComponent struct {
 	ID        uint64 `json:"id" gorm:"primaryKey;type:bigint;autoIncrement;comment:'unique identifier'"`
 	Ident     string `json:"ident" gorm:"type:varchar(191);not null;uniqueIndex:idx_ident,sort:asc;comment:'identifier of component'"`
-	Logo      string `json:"logo" gorm:"type:varchar(191);not null;comment:'logo of component'"`
+	Logo      string `json:"logo" gorm:"type:text;comment:'logo of component'"`
 	Readme    string `json:"readme" gorm:"type:text;not null;comment:'readme of component'"`
 	CreatedAt int64  `json:"created_at" gorm:"type:bigint;not null;default:0;comment:'create time'"`
 	CreatedBy string `json:"created_by" gorm:"type:varchar(191);not null;default:'';comment:'creator'"`

models/builtin_metrics.go

@@ -14,12 +14,12 @@ import (
 type BuiltinMetric struct {
 	ID         int64  `json:"id" gorm:"primaryKey;type:bigint;autoIncrement;comment:'unique identifier'"`
 	UUID       int64  `json:"uuid" gorm:"type:bigint;not null;default:0;comment:'uuid'"`
-	Collector  string `json:"collector" gorm:"type:varchar(191);not null;index:idx_collector,sort:asc;comment:'type of collector'"` // Type of collector (e.g., 'categraf', 'telegraf')
-	Typ        string `json:"typ" gorm:"type:varchar(191);not null;index:idx_typ,sort:asc;comment:'type of metric'"`                // Type of metric (e.g., 'host', 'mysql', 'redis')
-	Name       string `json:"name" gorm:"type:varchar(191);not null;index:idx_builtinmetric_name,sort:asc;comment:'name of metric'"`
+	Collector  string `json:"collector" gorm:"uniqueIndex:idx_collector_typ_name;type:varchar(191);not null;index:idx_collector,sort:asc;comment:'type of collector'"`
+	Typ        string `json:"typ" gorm:"uniqueIndex:idx_collector_typ_name;type:varchar(191);not null;index:idx_typ,sort:asc;comment:'type of metric'"`
+	Name       string `json:"name" gorm:"uniqueIndex:idx_collector_typ_name;type:varchar(191);not null;index:idx_builtinmetric_name,sort:asc;comment:'name of metric'"`
 	Unit       string `json:"unit" gorm:"type:varchar(191);not null;comment:'unit of metric'"`
 	Note       string `json:"note" gorm:"type:varchar(4096);not null;comment:'description of metric'"`
-	Lang       string `json:"lang" gorm:"type:varchar(191);not null;default:'zh';index:idx_lang,sort:asc;comment:'language'"`
+	Lang       string `json:"lang" gorm:"uniqueIndex:idx_collector_typ_name;type:varchar(191);not null;default:'zh';index:idx_lang,sort:asc;comment:'language'"`
 	Expression string `json:"expression" gorm:"type:varchar(4096);not null;comment:'expression of metric'"`
 	CreatedAt  int64  `json:"created_at" gorm:"type:bigint;not null;default:0;comment:'create time'"`
 	CreatedBy  string `json:"created_by" gorm:"type:varchar(191);not null;default:'';comment:'creator'"`

models/busi_group.go

@@ -115,68 +115,54 @@ func BusiGroupExists(ctx *ctx.Context, where string, args ...interface{}) (bool,
 	return num > 0, err
 }
 
+var entries = []struct {
+	entry        interface{}
+	errorMessage string
+}{
+	{
+		entry:        &AlertRule{},
+		errorMessage: "Some alert rules still in the BusiGroup",
+	},
+	{
+		entry:        &AlertMute{},
+		errorMessage: "Some alert mutes still in the BusiGroup",
+	},
+	{
+		entry:        &AlertSubscribe{},
+		errorMessage: "Some alert subscribes still in the BusiGroup",
+	},
+	{
+		entry:        &Target{},
+		errorMessage: "Some targets still in the BusiGroup",
+	},
+	{
+		entry:        &RecordingRule{},
+		errorMessage: "Some recording rules still in the BusiGroup",
+	},
+	{
+		entry:        &TaskTpl{},
+		errorMessage: "Some recovery scripts still in the BusiGroup",
+	},
+	{
+		entry:        &TaskRecord{},
+		errorMessage: "Some Task Record records still in the BusiGroup",
+	},
+	{
+		entry:        &TargetBusiGroup{},
+		errorMessage: "Some target busigroups still in the BusiGroup",
+	},
+}
+
 func (bg *BusiGroup) Del(ctx *ctx.Context) error {
-	has, err := Exists(DB(ctx).Model(&AlertMute{}).Where("group_id=?", bg.Id))
-	if err != nil {
-		return err
-	}
+	for _, e := range entries {
+		has, err := Exists(DB(ctx).Model(e.entry).Where("group_id=?", bg.Id))
+		if err != nil {
+			return err
+		}
 
-	if has {
-		return errors.New("Some alert mutes still in the BusiGroup")
-	}
-
-	has, err = Exists(DB(ctx).Model(&AlertSubscribe{}).Where("group_id=?", bg.Id))
-	if err != nil {
-		return err
-	}
-
-	if has {
-		return errors.New("Some alert subscribes still in the BusiGroup")
-	}
-
-	has, err = Exists(DB(ctx).Model(&TargetBusiGroup{}).Where("group_id=?", bg.Id))
-	if err != nil {
-		return err
-	}
-
-	if has {
-		return errors.New("Some targets still in the BusiGroup")
-	}
-
-	has, err = Exists(DB(ctx).Model(&Board{}).Where("group_id=?", bg.Id))
-	if err != nil {
-		return err
-	}
-
-	if has {
-		return errors.New("Some dashboards still in the BusiGroup")
-	}
-
-	has, err = Exists(DB(ctx).Model(&TaskTpl{}).Where("group_id=?", bg.Id))
-	if err != nil {
-		return err
-	}
-
-	if has {
-		return errors.New("Some recovery scripts still in the BusiGroup")
-	}
-
-	// hasCR, err := Exists(DB(ctx).Table("collect_rule").Where("group_id=?", bg.Id))
-	// if err != nil {
-	// 	return err
-	// }
-
-	// if hasCR {
-	// 	return errors.New("Some collect rules still in the BusiGroup")
-	// }
-
-	has, err = Exists(DB(ctx).Model(&AlertRule{}).Where("group_id=?", bg.Id))
-	if err != nil {
-		return err
-	}
-
-	if has {
-		return errors.New("Some alert rules still in the BusiGroup")
+		if has {
+			return errors.New(e.errorMessage)
+		}
 	}
 
 	return DB(ctx).Transaction(func(tx *gorm.DB) error {

models/configs.go

@@ -106,10 +106,8 @@ func InitRSAPassWord(ctx *ctx.Context) (string, error) {
 
 func ConfigsGet(ctx *ctx.Context, ckey string) (string, error) { //select built-in type configs
 	if !ctx.IsCenter {
-		if !ctx.IsCenter {
-			s, err := poster.GetByUrls[string](ctx, "/v1/n9e/config?key="+ckey)
-			return s, err
-		}
+		s, err := poster.GetByUrls[string](ctx, "/v1/n9e/config?key="+ckey)
+		return s, err
 	}
 
 	var lst []string
@@ -125,6 +123,22 @@ func ConfigsGet(ctx *ctx.Context, ckey string) (string, error) { //select built-
 	return "", nil
 }
 
+func ConfigsGetAll(ctx *ctx.Context) ([]*Configs, error) { // select built-in type configs
+	if !ctx.IsCenter {
+		lst, err := poster.GetByUrls[[]*Configs](ctx, "/v1/n9e/all-configs")
+		return lst, err
+	}
+
+	var lst []*Configs
+	err := DB(ctx).Model(&Configs{}).Select("ckey, cval").
+		Where("ckey!='' and external=? ", 0).Find(&lst).Error
+	if err != nil {
+		return nil, errors.WithMessage(err, "failed to query configs")
+	}
+
+	return lst, nil
+}
+
 func ConfigsSet(ctx *ctx.Context, ckey, cval string) error {
 	return ConfigsSetWithUname(ctx, ckey, cval, "default")
 }
@@ -355,3 +369,19 @@ func ConfigUserVariableGetDecryptMap(context *ctx.Context, privateKey []byte, pa
 
 	return ret, nil
 }
+
+func ConfigCvalStatistics(context *ctx.Context) (*Statistics, error) {
+	if !context.IsCenter {
+		return poster.GetByUrls[*Statistics](context, "/v1/n9e/statistic?name=cval")
+	}
+
+	session := DB(context).Model(&Configs{}).Select("count(*) as total",
+		"max(update_at) as last_updated").Where("ckey!='' and external=? ", 0) // built-in config
+
+	var stats []*Statistics
+	err := session.Find(&stats).Error
+	if err != nil {
+		return nil, err
+	}
+	return stats[0], nil
+}

models/datasource.go

@@ -2,7 +2,9 @@ package models
 
 import (
 	"encoding/json"
+	"math/rand"
 	"net/http"
+	"net/url"
 	"strings"
 	"time"
 
@@ -50,6 +52,7 @@ type HTTP struct {
 	TLS                 TLS               `json:"tls"`
 	MaxIdleConnsPerHost int               `json:"max_idle_conns_per_host"`
 	Url                 string            `json:"url"`
+	Urls                []string          `json:"urls"`
 	Headers             map[string]string `json:"headers"`
 }
 
@@ -68,6 +71,49 @@ func (h HTTP) IsLoki() bool {
 	return false
 }
 
+func (h HTTP) GetUrls() []string {
+	var urls []string
+	if len(h.Urls) == 0 {
+		urls = []string{h.Url}
+	} else {
+		// 复制切片以避免修改原始数据
+		urls = make([]string, len(h.Urls))
+		copy(urls, h.Urls)
+	}
+
+	// 使用 Fisher-Yates 洗牌算法随机打乱顺序
+	for i := len(urls) - 1; i > 0; i-- {
+		j := rand.Intn(i + 1)
+		urls[i], urls[j] = urls[j], urls[i]
+	}
+
+	return urls
+}
+
+func (h HTTP) NewReq(reqUrl *string) (req *http.Request, err error) {
+	urls := h.GetUrls()
+	for i := 0; i < len(urls); i++ {
+		if req, err = http.NewRequest("GET", urls[i], nil); err == nil {
+			*reqUrl = urls[i]
+			return
+		}
+	}
+	return
+}
+
+func (h HTTP) ParseUrl() (target *url.URL, err error) {
+	urls := h.GetUrls()
+	if len(urls) == 0 {
+		return nil, errors.New("no urls")
+	}
+
+	target, err = url.Parse(urls[0])
+	if err != nil {
+		return nil, err
+	}
+	return
+}
+
 type TLS struct {
 	SkipTlsVerify bool `json:"skip_tls_verify"`
 }
@@ -300,6 +346,10 @@ func (ds *Datasource) DB2FE() error {
 		ds.HTTPJson.MaxIdleConnsPerHost = 100
 	}
 
+	if ds.PluginType == ELASTICSEARCH && len(ds.HTTPJson.Urls) == 0 {
+		ds.HTTPJson.Urls = []string{ds.HTTPJson.Url}
+	}
+
 	if ds.Auth != "" {
 		err := json.Unmarshal([]byte(ds.Auth), &ds.AuthJson)
 		if err != nil {
@@ -336,12 +386,12 @@ func DatasourceGetMap(ctx *ctx.Context) (map[int64]*Datasource, error) {
 		}
 	}
 
-	ret := make(map[int64]*Datasource)
+	ds := make(map[int64]*Datasource)
 	for i := 0; i < len(lst); i++ {
-		ret[lst[i].Id] = lst[i]
+		ds[lst[i].Id] = lst[i]
 	}
 
-	return ret, nil
+	return ds, nil
 }
 
 func DatasourceStatistics(ctx *ctx.Context) (*Statistics, error) {

models/migrate/migrate.go

@@ -28,7 +28,7 @@ func MigrateIbexTables(db *gorm.DB) {
 		db = db.Set("gorm:table_options", tableOptions)
 	}
 
-	dts := []interface{}{&imodels.TaskMeta{}, &imodels.TaskScheduler{}, &imodels.TaskSchedulerHealth{}, &imodels.TaskHostDoing{}, &imodels.TaskAction{}}
+	dts := []interface{}{&imodels.TaskMeta{}, &imodels.TaskScheduler{}, &TaskHostDoing{}, &imodels.TaskAction{}}
 	for _, dt := range dts {
 		err := db.AutoMigrate(dt)
 		if err != nil {
@@ -38,13 +38,22 @@ func MigrateIbexTables(db *gorm.DB) {
 
 	for i := 0; i < 100; i++ {
 		tableName := fmt.Sprintf("task_host_%d", i)
-		err := db.Table(tableName).AutoMigrate(&imodels.TaskHost{})
-		if err != nil {
-			logger.Errorf("failed to migrate table:%s %v", tableName, err)
+		exists := db.Migrator().HasTable(tableName)
+		if exists {
+			continue
+		} else {
+			err := db.Table(tableName).AutoMigrate(&imodels.TaskHost{})
+			if err != nil {
+				logger.Errorf("failed to migrate table:%s %v", tableName, err)
+			}
 		}
 	}
 }
 
+func isPostgres(db *gorm.DB) bool {
+	dialect := db.Dialector.Name()
+	return dialect == "postgres"
+}
 func MigrateTables(db *gorm.DB) error {
 	var tableOptions string
 	switch db.Dialector.(type) {
@@ -54,13 +63,22 @@ func MigrateTables(db *gorm.DB) error {
 	if tableOptions != "" {
 		db = db.Set("gorm:table_options", tableOptions)
 	}
-
 	dts := []interface{}{&RecordingRule{}, &AlertRule{}, &AlertSubscribe{}, &AlertMute{},
 		&TaskRecord{}, &ChartShare{}, &Target{}, &Configs{}, &Datasource{}, &NotifyTpl{},
 		&Board{}, &BoardBusigroup{}, &Users{}, &SsoConfig{}, &models.BuiltinMetric{},
-		&models.MetricFilter{}, &models.BuiltinComponent{}, &models.NotificaitonRecord{},
+		&models.MetricFilter{}, &models.NotificaitonRecord{},
 		&models.TargetBusiGroup{}}
 
+	if isPostgres(db) {
+		dts = append(dts, &models.PostgresBuiltinComponent{})
+	} else {
+		dts = append(dts, &models.BuiltinComponent{})
+	}
+
+	if !db.Migrator().HasColumn(&imodels.TaskSchedulerHealth{}, "scheduler") {
+		dts = append(dts, &imodels.TaskSchedulerHealth{})
+	}
+
 	if !columnHasIndex(db, &AlertHisEvent{}, "original_tags") ||
 		!columnHasIndex(db, &AlertCurEvent{}, "original_tags") {
 		asyncDts := []interface{}{&AlertHisEvent{}, &AlertCurEvent{}}
@@ -74,7 +92,7 @@ func MigrateTables(db *gorm.DB) error {
 
 			for _, dt := range asyncDts {
 				if err := db.AutoMigrate(dt); err != nil {
-					logger.Errorf("failed to migrate table: %v", err)
+					logger.Errorf("failed to migrate table %+v err:%v", dt, err)
 				}
 			}
 		}()
@@ -170,14 +188,20 @@ func InsertPermPoints(db *gorm.DB) {
 	})
 
 	for _, op := range ops {
-		exists, err := models.Exists(db.Model(&models.RoleOperation{}).Where("operation = ? and role_name = ?", op.Operation, op.RoleName))
+		var count int64
+
+		err := db.Raw("SELECT COUNT(*) FROM role_operation WHERE operation = ? AND role_name = ?",
+			op.Operation, op.RoleName).Scan(&count).Error
+
 		if err != nil {
 			logger.Errorf("check role operation exists failed, %v", err)
 			continue
 		}
-		if exists {
+
+		if count > 0 {
 			continue
 		}
+
 		err = db.Create(&op).Error
 		if err != nil {
 			logger.Errorf("insert role operation failed, %v", err)
@@ -186,15 +210,17 @@ func InsertPermPoints(db *gorm.DB) {
 }
 
 type AlertRule struct {
-	ExtraConfig string `gorm:"type:text;column:extra_config"` // extra config
+	ExtraConfig       string                   `gorm:"type:text;column:extra_config"`
+	CronPattern       string                   `gorm:"type:varchar(64);column:cron_pattern"`
+	DatasourceQueries []models.DatasourceQuery `gorm:"datasource_queries;type:text;serializer:json"` // datasource queries
 }
 
 type AlertSubscribe struct {
 	ExtraConfig string       `gorm:"type:text;column:extra_config"` // extra config
 	Severities  string       `gorm:"column:severities;type:varchar(32);not null;default:''"`
-	BusiGroups  ormx.JSONArr `gorm:"column:busi_groups;type:varchar(4096);not null;default:'[]'"`
+	BusiGroups  ormx.JSONArr `gorm:"column:busi_groups;type:varchar(4096)"`
 	Note        string       `gorm:"column:note;type:varchar(1024);default:'';comment:note"`
-	RuleIds     []int64      `gorm:"column:rule_ids;type:varchar(1024);default:'';comment:rule_ids"`
+	RuleIds     []int64      `gorm:"column:rule_ids;type:varchar(1024)"`
 }
 
 type AlertMute struct {
@@ -203,9 +229,10 @@ type AlertMute struct {
 }
 
 type RecordingRule struct {
-	QueryConfigs  string `gorm:"type:text;not null;column:query_configs"` // query_configs
-	DatasourceIds string `gorm:"column:datasource_ids;type:varchar(255);default:'';comment:datasource ids"`
-	CronPattern   string `gorm:"column:cron_pattern;type:varchar(255);default:'';comment:cron pattern"`
+	QueryConfigs      string                   `gorm:"type:text;not null;column:query_configs"` // query_configs
+	DatasourceIds     string                   `gorm:"column:datasource_ids;type:varchar(255);default:'';comment:datasource ids"`
+	CronPattern       string                   `gorm:"column:cron_pattern;type:varchar(255);default:'';comment:cron pattern"`
+	DatasourceQueries []models.DatasourceQuery `json:"datasource_queries" gorm:"datasource_queries;type:text;serializer:json"` // datasource queries
 }
 
 type AlertingEngines struct {
@@ -280,3 +307,15 @@ type BuiltinPayloads struct {
 	UUID        int64 `json:"uuid" gorm:"type:bigint;not null;index:idx_uuid;comment:'uuid of payload'"`
 	ComponentID int64 `json:"component_id" gorm:"type:bigint;index:idx_component,sort:asc;not null;default:0;comment:'component_id of payload'"`
 }
+
+type TaskHostDoing struct {
+	Id             int64  `gorm:"column:id;index;primaryKey:false"`
+	Host           string `gorm:"column:host;size:128;not null;index"`
+	Clock          int64  `gorm:"column:clock;not null;default:0"`
+	Action         string `gorm:"column:action;size:16;not null"`
+	AlertTriggered bool   `gorm:"-"`
+}
+
+func (TaskHostDoing) TableName() string {
+	return "task_host_doing"
+}

models/migrate/migrate_test.go

@@ -0,0 +1,69 @@
+package migrate
+
+import (
+	"fmt"
+	"testing"
+
+	"github.com/ccfos/nightingale/v6/models"
+	"gorm.io/driver/mysql"
+	"gorm.io/gorm"
+	"gorm.io/gorm/schema"
+)
+
+func TestInsertPermPoints(t *testing.T) {
+	db, err := gorm.Open(mysql.Open("root:1234@tcp(127.0.0.1:3306)/n9e_v6?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"), &gorm.Config{NamingStrategy: schema.NamingStrategy{
+		SingularTable: true,
+	}})
+	if err != nil {
+		fmt.Printf("failed to connect database: %v", err)
+	}
+
+	var ops []models.RoleOperation
+	ops = append(ops, models.RoleOperation{
+		RoleName:  "Standard",
+		Operation: "/alert-mutes/put",
+	})
+
+	ops = append(ops, models.RoleOperation{
+		RoleName:  "Standard",
+		Operation: "/log/index-patterns",
+	})
+
+	ops = append(ops, models.RoleOperation{
+		RoleName:  "Standard",
+		Operation: "/help/variable-configs",
+	})
+
+	ops = append(ops, models.RoleOperation{
+		RoleName:  "Admin",
+		Operation: "/permissions",
+	})
+
+	ops = append(ops, models.RoleOperation{
+		RoleName:  "Standard",
+		Operation: "/ibex-settings",
+	})
+
+	db = db.Debug()
+	for _, op := range ops {
+		var count int64
+
+		err := db.Raw("SELECT COUNT(*) FROM role_operation WHERE operation = ? AND role_name = ?",
+			op.Operation, op.RoleName).Scan(&count).Error
+		fmt.Printf("count: %d\n", count)
+
+		if err != nil {
+			fmt.Printf("check role operation exists failed, %v", err)
+			continue
+		}
+
+		if count > 0 {
+			continue
+		}
+
+		err = db.Create(&op).Error
+		if err != nil {
+			fmt.Printf("insert role operation failed, %v", err)
+		}
+	}
+}