refactor: http support tracing (#3083)

Updated the description to emphasize the open-source monitoring alert management aspect and added information about the MCP-Server.

README.md

@@ -31,7 +31,9 @@
 
 Nightingale is an open-source monitoring project that focuses on alerting. Similar to Grafana, Nightingale also connects with various existing data sources. However, while Grafana emphasizes visualization, Nightingale places greater emphasis on the alerting engine, as well as the processing and distribution of alarms.
 
-> The Nightingale project was initially developed and open-sourced by DiDi.inc. On May 11, 2022, it was donated to the Open Source Development Committee of the China Computer Federation (CCF ODC).
+> 💡 Nightingale has now officially launched the [MCP-Server](https://github.com/n9e/n9e-mcp-server/). This MCP Server enables AI assistants to interact with the Nightingale API using natural language, facilitating alert management, monitoring, and observability tasks.
+> 
+> The Nightingale project was initially developed and open-sourced by DiDi.inc. On May 11, 2022, it was donated to the Open Source Development Committee of the China Computer Federation (CCF ODTC).
 
 ![](https://n9e.github.io/img/global/arch-bg.png)
 

README_zh.md

@@ -3,7 +3,7 @@
     <img src="doc/img/Nightingale_L_V.png" alt="nightingale - cloud native monitoring" width="100" /></a>
 </p>
 <p align="center">
-  <b>开源告警管理专家</b>
+  <b>开源监控告警管理专家</b>
 </p>
 
 <p align="center">
@@ -33,7 +33,8 @@
 
 夜莺侧重于监控告警，类似于 Grafana 的数据源集成方式，夜莺也是对接多种既有的数据源，不过 Grafana 侧重于可视化，夜莺则是侧重于告警引擎、告警事件的处理和分发。
 
-> 夜莺监控项目，最初由滴滴开发和开源，并于 2022 年 5 月 11 日，捐赠予中国计算机学会开源发展技术委员会（CCF ODTC），为 CCF ODTC 成立后接受捐赠的第一个开源项目。
+> - 💡夜莺正式推出了 [MCP-Server](https://github.com/n9e/n9e-mcp-server/)，此 MCP Server 允许 AI 助手通过自然语言与夜莺 API 交互，实现告警管理、监控和可观测性任务。
+> - 夜莺监控项目，最初由滴滴开发和开源，并于 2022 年 5 月 11 日，捐赠予中国计算机学会开源发展技术委员会（CCF ODTC），为 CCF ODTC 成立后接受捐赠的第一个开源项目。
 
 ![](https://n9e.github.io/img/global/arch-bg.png)
 

alert/alert.go

@@ -79,7 +79,7 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 
 	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)
+	rt := router.New(config.HTTP, config.Alert, alertMuteCache, targetCache, busiGroupCache, alertStats, ctx, externalProcessors, config.Log.Dir)
 
 	if config.Ibex.Enable {
 		ibex.ServerStart(false, nil, redis, config.HTTP.APIForService.BasicAuth, config.Alert.Heartbeat, &config.CenterApi, r, nil, config.Ibex, config.HTTP.Port)

alert/dispatch/consume.go

@@ -8,7 +8,6 @@ import (
 	"time"
 
 	"github.com/ccfos/nightingale/v6/alert/aconf"
-	"github.com/ccfos/nightingale/v6/alert/common"
 	"github.com/ccfos/nightingale/v6/alert/queue"
 	"github.com/ccfos/nightingale/v6/memsto"
 	"github.com/ccfos/nightingale/v6/models"
@@ -99,12 +98,12 @@ func (e *Consumer) consumeOne(event *models.AlertCurEvent) {
 	e.dispatch.Astats.CounterAlertsTotal.WithLabelValues(event.Cluster, eventType, event.GroupName).Inc()
 
 	if err := event.ParseRule("rule_name"); err != nil {
-		logger.Warningf("ruleid:%d failed to parse rule name: %v", event.RuleId, err)
+		logger.Warningf("alert_eval_%d datasource_%d failed to parse rule name: %v", event.RuleId, event.DatasourceId, err)
 		event.RuleName = fmt.Sprintf("failed to parse rule name: %v", err)
 	}
 
 	if err := event.ParseRule("annotations"); err != nil {
-		logger.Warningf("ruleid:%d failed to parse annotations: %v", event.RuleId, err)
+		logger.Warningf("alert_eval_%d datasource_%d failed to parse annotations: %v", event.RuleId, event.DatasourceId, err)
 		event.Annotations = fmt.Sprintf("failed to parse annotations: %v", err)
 		event.AnnotationsJSON["error"] = event.Annotations
 	}
@@ -112,7 +111,7 @@ func (e *Consumer) consumeOne(event *models.AlertCurEvent) {
 	e.queryRecoveryVal(event)
 
 	if err := event.ParseRule("rule_note"); err != nil {
-		logger.Warningf("ruleid:%d failed to parse rule note: %v", event.RuleId, err)
+		logger.Warningf("alert_eval_%d datasource_%d failed to parse rule note: %v", event.RuleId, event.DatasourceId, err)
 		event.RuleNote = fmt.Sprintf("failed to parse rule note: %v", err)
 	}
 
@@ -131,7 +130,7 @@ func (e *Consumer) persist(event *models.AlertCurEvent) {
 		var err error
 		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)
+			logger.Errorf("event:%s persist err:%v", event.Hash, err)
 			e.dispatch.Astats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", event.DatasourceId), "persist_event", event.GroupName, fmt.Sprintf("%v", event.RuleId)).Inc()
 		}
 		return
@@ -139,7 +138,7 @@ 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)
+		logger.Errorf("event:%s persist err:%v", event.Hash, err)
 		e.dispatch.Astats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", event.DatasourceId), "persist_event", event.GroupName, fmt.Sprintf("%v", event.RuleId)).Inc()
 	}
 }
@@ -157,12 +156,12 @@ func (e *Consumer) queryRecoveryVal(event *models.AlertCurEvent) {
 
 	promql = strings.TrimSpace(promql)
 	if promql == "" {
-		logger.Warningf("rule_eval:%s promql is blank", getKey(event))
+		logger.Warningf("alert_eval_%d datasource_%d promql is blank", event.RuleId, event.DatasourceId)
 		return
 	}
 
 	if e.promClients.IsNil(event.DatasourceId) {
-		logger.Warningf("rule_eval:%s error reader client is nil", getKey(event))
+		logger.Warningf("alert_eval_%d datasource_%d error reader client is nil", event.RuleId, event.DatasourceId)
 		return
 	}
 
@@ -171,7 +170,7 @@ func (e *Consumer) queryRecoveryVal(event *models.AlertCurEvent) {
 	var warnings promsdk.Warnings
 	value, warnings, err := readerClient.Query(e.ctx.Ctx, promql, time.Now())
 	if err != nil {
-		logger.Errorf("rule_eval:%s promql:%s, error:%v", getKey(event), promql, err)
+		logger.Errorf("alert_eval_%d datasource_%d promql:%s, error:%v", event.RuleId, event.DatasourceId, promql, err)
 		event.AnnotationsJSON["recovery_promql_error"] = fmt.Sprintf("promql:%s error:%v", promql, err)
 
 		b, err := json.Marshal(event.AnnotationsJSON)
@@ -185,12 +184,12 @@ func (e *Consumer) queryRecoveryVal(event *models.AlertCurEvent) {
 	}
 
 	if len(warnings) > 0 {
-		logger.Errorf("rule_eval:%s promql:%s, warnings:%v", getKey(event), promql, warnings)
+		logger.Errorf("alert_eval_%d datasource_%d promql:%s, warnings:%v", event.RuleId, event.DatasourceId, promql, warnings)
 	}
 
 	anomalyPoints := models.ConvertAnomalyPoints(value)
 	if len(anomalyPoints) == 0 {
-		logger.Warningf("rule_eval:%s promql:%s, result is empty", getKey(event), promql)
+		logger.Warningf("alert_eval_%d datasource_%d promql:%s, result is empty", event.RuleId, event.DatasourceId, promql)
 		event.AnnotationsJSON["recovery_promql_error"] = fmt.Sprintf("promql:%s error:%s", promql, "result is empty")
 	} else {
 		event.AnnotationsJSON["recovery_value"] = fmt.Sprintf("%v", anomalyPoints[0].Value)
@@ -205,6 +204,3 @@ func (e *Consumer) queryRecoveryVal(event *models.AlertCurEvent) {
 	}
 }
 
-func getKey(event *models.AlertCurEvent) string {
-	return common.RuleKey(event.DatasourceId, event.RuleId)
-}

alert/dispatch/dispatch.go

@@ -171,7 +171,7 @@ func (e *Dispatch) HandleEventWithNotifyRule(eventOrigin *models.AlertCurEvent)
 			// 深拷贝新的 event，避免并发修改 event 冲突
 			eventCopy := eventOrigin.DeepCopy()
 
-			logger.Infof("notify rule ids: %v, event: %+v", notifyRuleId, eventCopy)
+			logger.Infof("notify rule ids: %v, event: %s", notifyRuleId, eventCopy.Hash)
 			notifyRule := e.notifyRuleCache.Get(notifyRuleId)
 			if notifyRule == nil {
 				continue
@@ -185,7 +185,7 @@ func (e *Dispatch) HandleEventWithNotifyRule(eventOrigin *models.AlertCurEvent)
 
 			eventCopy = HandleEventPipeline(notifyRule.PipelineConfigs, eventOrigin, eventCopy, e.eventProcessorCache, e.ctx, notifyRuleId, "notify_rule")
 			if ShouldSkipNotify(e.ctx, eventCopy, notifyRuleId) {
-				logger.Infof("notify_id: %d, event:%+v, should skip notify", notifyRuleId, eventCopy)
+				logger.Infof("notify_id: %d, event:%s, should skip notify", notifyRuleId, eventCopy.Hash)
 				continue
 			}
 
@@ -193,7 +193,7 @@ func (e *Dispatch) HandleEventWithNotifyRule(eventOrigin *models.AlertCurEvent)
 			for i := range notifyRule.NotifyConfigs {
 				err := NotifyRuleMatchCheck(&notifyRule.NotifyConfigs[i], eventCopy)
 				if err != nil {
-					logger.Errorf("notify_id: %d, event:%+v, channel_id:%d, template_id: %d, notify_config:%+v, err:%v", notifyRuleId, eventCopy, notifyRule.NotifyConfigs[i].ChannelID, notifyRule.NotifyConfigs[i].TemplateID, notifyRule.NotifyConfigs[i], err)
+					logger.Errorf("notify_id: %d, event:%s, channel_id:%d, template_id: %d, notify_config:%+v, err:%v", notifyRuleId, eventCopy.Hash, notifyRule.NotifyConfigs[i].ChannelID, notifyRule.NotifyConfigs[i].TemplateID, notifyRule.NotifyConfigs[i], err)
 					continue
 				}
 
@@ -201,12 +201,12 @@ func (e *Dispatch) HandleEventWithNotifyRule(eventOrigin *models.AlertCurEvent)
 				messageTemplate := e.messageTemplateCache.Get(notifyRule.NotifyConfigs[i].TemplateID)
 				if notifyChannel == nil {
 					sender.NotifyRecord(e.ctx, []*models.AlertCurEvent{eventCopy}, notifyRuleId, fmt.Sprintf("notify_channel_id:%d", notifyRule.NotifyConfigs[i].ChannelID), "", "", errors.New("notify_channel not found"))
-					logger.Warningf("notify_id: %d, event:%+v, channel_id:%d, template_id: %d, notify_channel not found", notifyRuleId, eventCopy, notifyRule.NotifyConfigs[i].ChannelID, notifyRule.NotifyConfigs[i].TemplateID)
+					logger.Warningf("notify_id: %d, event:%s, channel_id:%d, template_id: %d, notify_channel not found", notifyRuleId, eventCopy.Hash, notifyRule.NotifyConfigs[i].ChannelID, notifyRule.NotifyConfigs[i].TemplateID)
 					continue
 				}
 
 				if notifyChannel.RequestType != "flashduty" && notifyChannel.RequestType != "pagerduty" && messageTemplate == nil {
-					logger.Warningf("notify_id: %d, channel_name: %v, event:%+v, template_id: %d, message_template not found", notifyRuleId, notifyChannel.Ident, eventCopy, notifyRule.NotifyConfigs[i].TemplateID)
+					logger.Warningf("notify_id: %d, channel_name: %v, event:%s, template_id: %d, message_template not found", notifyRuleId, notifyChannel.Ident, eventCopy.Hash, notifyRule.NotifyConfigs[i].TemplateID)
 					sender.NotifyRecord(e.ctx, []*models.AlertCurEvent{eventCopy}, notifyRuleId, notifyChannel.Name, "", "", errors.New("message_template not found"))
 
 					continue
@@ -241,12 +241,12 @@ func HandleEventPipeline(pipelineConfigs []models.PipelineConfig, eventOrigin, e
 
 		eventPipeline := eventProcessorCache.Get(pipelineConfig.PipelineId)
 		if eventPipeline == nil {
-			logger.Warningf("processor_by_%s_id:%d pipeline_id:%d, event pipeline not found, event: %+v", from, id, pipelineConfig.PipelineId, event)
+			logger.Warningf("processor_by_%s_id:%d pipeline_id:%d, event pipeline not found, event: %s", from, id, pipelineConfig.PipelineId, event.Hash)
 			continue
 		}
 
 		if !PipelineApplicable(eventPipeline, event) {
-			logger.Debugf("processor_by_%s_id:%d pipeline_id:%d, event pipeline not applicable, event: %+v", from, id, pipelineConfig.PipelineId, event)
+			logger.Debugf("processor_by_%s_id:%d pipeline_id:%d, event pipeline not applicable, event: %s", from, id, pipelineConfig.PipelineId, event.Hash)
 			continue
 		}
 
@@ -263,7 +263,7 @@ func HandleEventPipeline(pipelineConfigs []models.PipelineConfig, eventOrigin, e
 		}
 
 		if resultEvent == nil {
-			logger.Infof("processor_by_%s_id:%d pipeline_id:%d, event dropped, event: %+v", from, id, pipelineConfig.PipelineId, eventOrigin)
+			logger.Infof("processor_by_%s_id:%d pipeline_id:%d, event dropped, event: %s", from, id, pipelineConfig.PipelineId, eventOrigin.Hash)
 			if from == "notify_rule" {
 				sender.NotifyRecord(ctx, []*models.AlertCurEvent{eventOrigin}, id, "", "", result.Message, fmt.Errorf("processor_by_%s_id:%d pipeline_id:%d, drop by pipeline", from, id, pipelineConfig.PipelineId))
 			}
@@ -301,7 +301,7 @@ func PipelineApplicable(pipeline *models.EventPipeline, event *models.AlertCurEv
 
 		tagFilters, err := models.ParseTagFilter(labelFiltersCopy)
 		if err != nil {
-			logger.Errorf("pipeline applicable failed to parse tag filter: %v event:%+v pipeline:%+v", err, event, pipeline)
+			logger.Errorf("pipeline applicable failed to parse tag filter: %v event:%s pipeline:%+v", err, event.Hash, pipeline)
 			return false
 		}
 		tagMatch = common.MatchTags(event.TagsMap, tagFilters)
@@ -315,7 +315,7 @@ func PipelineApplicable(pipeline *models.EventPipeline, event *models.AlertCurEv
 
 		tagFilters, err := models.ParseTagFilter(attrFiltersCopy)
 		if err != nil {
-			logger.Errorf("pipeline applicable failed to parse tag filter: %v event:%+v pipeline:%+v err:%v", tagFilters, event, pipeline, err)
+			logger.Errorf("pipeline applicable failed to parse tag filter: %v event:%s pipeline:%+v err:%v", tagFilters, event.Hash, pipeline, err)
 			return false
 		}
 
@@ -405,7 +405,7 @@ func NotifyRuleMatchCheck(notifyConfig *models.NotifyConfig, event *models.Alert
 
 		tagFilters, err := models.ParseTagFilter(labelKeysCopy)
 		if err != nil {
-			logger.Errorf("notify send failed to parse tag filter: %v event:%+v notify_config:%+v", err, event, notifyConfig)
+			logger.Errorf("notify send failed to parse tag filter: %v event:%s notify_config:%+v", err, event.Hash, notifyConfig)
 			return fmt.Errorf("failed to parse tag filter: %v", err)
 		}
 		tagMatch = common.MatchTags(event.TagsMap, tagFilters)
@@ -423,7 +423,7 @@ func NotifyRuleMatchCheck(notifyConfig *models.NotifyConfig, event *models.Alert
 
 		tagFilters, err := models.ParseTagFilter(attributesCopy)
 		if err != nil {
-			logger.Errorf("notify send failed to parse tag filter: %v event:%+v notify_config:%+v err:%v", tagFilters, event, notifyConfig, err)
+			logger.Errorf("notify send failed to parse tag filter: %v event:%s notify_config:%+v err:%v", tagFilters, event.Hash, notifyConfig, err)
 			return fmt.Errorf("failed to parse tag filter: %v", err)
 		}
 
@@ -434,7 +434,7 @@ func NotifyRuleMatchCheck(notifyConfig *models.NotifyConfig, event *models.Alert
 		return fmt.Errorf("event attributes not match attributes filter")
 	}
 
-	logger.Infof("notify send timeMatch:%v severityMatch:%v tagMatch:%v attributesMatch:%v event:%+v notify_config:%+v", timeMatch, severityMatch, tagMatch, attributesMatch, event, notifyConfig)
+	logger.Infof("notify send timeMatch:%v severityMatch:%v tagMatch:%v attributesMatch:%v event:%s notify_config:%+v", timeMatch, severityMatch, tagMatch, attributesMatch, event.Hash, notifyConfig)
 	return nil
 }
 
@@ -547,7 +547,7 @@ func SendNotifyRuleMessage(ctx *ctx.Context, userCache *memsto.UserCacheType, us
 			start := time.Now()
 			respBody, err := notifyChannel.SendFlashDuty(events, flashDutyChannelIDs[i], notifyChannelCache.GetHttpClient(notifyChannel.ID))
 			respBody = fmt.Sprintf("send_time: %s duration: %d ms %s", time.Now().Format("2006-01-02 15:04:05"), time.Since(start).Milliseconds(), respBody)
-			logger.Infof("duty_sender notify_id: %d, channel_name: %v, event:%+v, IntegrationUrl: %v dutychannel_id: %v, respBody: %v, err: %v", notifyRuleId, notifyChannel.Name, events[0], notifyChannel.RequestConfig.FlashDutyRequestConfig.IntegrationUrl, flashDutyChannelIDs[i], respBody, err)
+			logger.Infof("duty_sender notify_id: %d, channel_name: %v, event:%s, IntegrationUrl: %v dutychannel_id: %v, respBody: %v, err: %v", notifyRuleId, notifyChannel.Name, events[0].Hash, notifyChannel.RequestConfig.FlashDutyRequestConfig.IntegrationUrl, flashDutyChannelIDs[i], respBody, err)
 			sender.NotifyRecord(ctx, events, notifyRuleId, notifyChannel.Name, strconv.FormatInt(flashDutyChannelIDs[i], 10), respBody, err)
 		}
 
@@ -556,7 +556,7 @@ func SendNotifyRuleMessage(ctx *ctx.Context, userCache *memsto.UserCacheType, us
 			start := time.Now()
 			respBody, err := notifyChannel.SendPagerDuty(events, routingKey, siteInfo.SiteUrl, notifyChannelCache.GetHttpClient(notifyChannel.ID))
 			respBody = fmt.Sprintf("send_time: %s duration: %d ms %s", time.Now().Format("2006-01-02 15:04:05"), time.Since(start).Milliseconds(), respBody)
-			logger.Infof("pagerduty_sender notify_id: %d, channel_name: %v, event:%+v, respBody: %v, err: %v", notifyRuleId, notifyChannel.Name, events[0], respBody, err)
+			logger.Infof("pagerduty_sender notify_id: %d, channel_name: %v, event:%s, respBody: %v, err: %v", notifyRuleId, notifyChannel.Name, events[0].Hash, respBody, err)
 			sender.NotifyRecord(ctx, events, notifyRuleId, notifyChannel.Name, "", respBody, err)
 		}
 
@@ -587,10 +587,10 @@ func SendNotifyRuleMessage(ctx *ctx.Context, userCache *memsto.UserCacheType, us
 		start := time.Now()
 		target, res, err := notifyChannel.SendScript(events, tplContent, customParams, sendtos)
 		res = fmt.Sprintf("send_time: %s duration: %d ms %s", time.Now().Format("2006-01-02 15:04:05"), time.Since(start).Milliseconds(), res)
-		logger.Infof("script_sender notify_id: %d, channel_name: %v, event:%+v, tplContent:%s, customParams:%v, target:%s, res:%s, err:%v", notifyRuleId, notifyChannel.Name, events[0], tplContent, customParams, target, res, err)
+		logger.Infof("script_sender notify_id: %d, channel_name: %v, event:%s, tplContent:%s, customParams:%v, target:%s, res:%s, err:%v", notifyRuleId, notifyChannel.Name, events[0].Hash, tplContent, customParams, target, res, err)
 		sender.NotifyRecord(ctx, events, notifyRuleId, notifyChannel.Name, target, res, err)
 	default:
-		logger.Warningf("notify_id: %d, channel_name: %v, event:%+v send type not found", notifyRuleId, notifyChannel.Name, events[0])
+		logger.Warningf("notify_id: %d, channel_name: %v, event:%s send type not found", notifyRuleId, notifyChannel.Name, events[0].Hash)
 	}
 }
 
@@ -734,7 +734,7 @@ func (e *Dispatch) Send(rule *models.AlertRule, event *models.AlertCurEvent, not
 				event = msgCtx.Events[0]
 			}
 
-			logger.Debugf("send to channel:%s event:%+v users:%+v", channel, event, msgCtx.Users)
+			logger.Debugf("send to channel:%s event:%s users:%+v", channel, event.Hash, msgCtx.Users)
 			s.Send(msgCtx)
 		}
 	}

alert/dispatch/log.go

@@ -18,11 +18,11 @@ func LogEvent(event *models.AlertCurEvent, location string, err ...error) {
 	}
 
 	logger.Infof(
-		"event(%s %s) %s: rule_id=%d sub_id:%d notify_rule_ids:%v cluster:%s %v%s@%d last_eval_time:%d %s",
+		"alert_eval_%d event(%s %s) %s: sub_id:%d notify_rule_ids:%v cluster:%s %v%s@%d last_eval_time:%d %s",
+		event.RuleId,
 		event.Hash,
 		status,
 		location,
-		event.RuleId,
 		event.SubRuleId,
 		event.NotifyRuleIds,
 		event.Cluster,

alert/eval/alert_rule.go

@@ -101,17 +101,17 @@ func (s *Scheduler) syncAlertRules() {
 				}
 				ds := s.datasourceCache.GetById(dsId)
 				if ds == nil {
-					logger.Debugf("datasource %d not found", dsId)
+					logger.Debugf("alert_eval_%d datasource %d not found", rule.Id, dsId)
 					continue
 				}
 
 				if ds.PluginType != ruleType {
-					logger.Debugf("datasource %d category is %s not %s", dsId, ds.PluginType, ruleType)
+					logger.Debugf("alert_eval_%d datasource %d category is %s not %s", rule.Id, dsId, ds.PluginType, ruleType)
 					continue
 				}
 
 				if ds.Status != "enabled" {
-					logger.Debugf("datasource %d status is %s", dsId, ds.Status)
+					logger.Debugf("alert_eval_%d datasource %d status is %s", rule.Id, dsId, ds.Status)
 					continue
 				}
 				processor := process.NewProcessor(s.aconf.Heartbeat.EngineName, rule, dsId, s.alertRuleCache, s.targetCache, s.targetsOfAlertRuleCache, s.busiGroupCache, s.alertMuteCache, s.datasourceCache, s.ctx, s.stats)
@@ -134,12 +134,12 @@ func (s *Scheduler) syncAlertRules() {
 			for _, dsId := range dsIds {
 				ds := s.datasourceCache.GetById(dsId)
 				if ds == nil {
-					logger.Debugf("datasource %d not found", dsId)
+					logger.Debugf("alert_eval_%d datasource %d not found", rule.Id, dsId)
 					continue
 				}
 
 				if ds.Status != "enabled" {
-					logger.Debugf("datasource %d status is %s", dsId, ds.Status)
+					logger.Debugf("alert_eval_%d datasource %d status is %s", rule.Id, dsId, ds.Status)
 					continue
 				}
 				processor := process.NewProcessor(s.aconf.Heartbeat.EngineName, rule, dsId, s.alertRuleCache, s.targetCache, s.targetsOfAlertRuleCache, s.busiGroupCache, s.alertMuteCache, s.datasourceCache, s.ctx, s.stats)

alert/eval/eval.go

@@ -109,7 +109,7 @@ func NewAlertRuleWorker(rule *models.AlertRule, datasourceId int64, Processor *p
 	})
 
 	if err != nil {
-		logger.Errorf("alert rule %s add cron pattern error: %v", arw.Key(), err)
+		logger.Errorf("alert_eval_%d datasource_%d add cron pattern error: %v", arw.Rule.Id, arw.DatasourceId, err)
 	}
 
 	Processor.ScheduleEntry = arw.Scheduler.Entry(entryID)
@@ -152,9 +152,9 @@ func (arw *AlertRuleWorker) Eval() {
 
 	defer func() {
 		if len(message) == 0 {
-			logger.Infof("rule_eval:%s finished, duration:%v", arw.Key(), time.Since(begin))
+			logger.Infof("alert_eval_%d datasource_%d finished, duration:%v", arw.Rule.Id, arw.DatasourceId, time.Since(begin))
 		} else {
-			logger.Warningf("rule_eval:%s finished, duration:%v, message:%s", arw.Key(), time.Since(begin), message)
+			logger.Warningf("alert_eval_%d datasource_%d finished, duration:%v, message:%s", arw.Rule.Id, arw.DatasourceId, time.Since(begin), message)
 		}
 	}()
 
@@ -236,7 +236,7 @@ func (arw *AlertRuleWorker) Eval() {
 }
 
 func (arw *AlertRuleWorker) Stop() {
-	logger.Infof("rule_eval:%s stopped", arw.Key())
+	logger.Infof("alert_eval_%d datasource_%d stopped", arw.Rule.Id, arw.DatasourceId)
 	close(arw.Quit)
 	c := arw.Scheduler.Stop()
 	<-c.Done()
@@ -252,7 +252,7 @@ func (arw *AlertRuleWorker) GetPromAnomalyPoint(ruleConfig string) ([]models.Ano
 
 	var rule *models.PromRuleConfig
 	if err := json.Unmarshal([]byte(ruleConfig), &rule); err != nil {
-		logger.Errorf("rule_eval:%s rule_config:%s, error:%v", arw.Key(), ruleConfig, err)
+		logger.Errorf("alert_eval_%d datasource_%d rule_config:%s, error:%v", arw.Rule.Id, arw.DatasourceId, ruleConfig, err)
 		arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), GET_RULE_CONFIG, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 		arw.Processor.Stats.GaugeQuerySeriesCount.WithLabelValues(
 			fmt.Sprintf("%v", arw.Rule.Id),
@@ -263,7 +263,7 @@ func (arw *AlertRuleWorker) GetPromAnomalyPoint(ruleConfig string) ([]models.Ano
 	}
 
 	if rule == nil {
-		logger.Errorf("rule_eval:%s rule_config:%s, error:rule is nil", arw.Key(), ruleConfig)
+		logger.Errorf("alert_eval_%d datasource_%d rule_config:%s, error:rule is nil", arw.Rule.Id, arw.DatasourceId, ruleConfig)
 		arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), GET_RULE_CONFIG, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 		arw.Processor.Stats.GaugeQuerySeriesCount.WithLabelValues(
 			fmt.Sprintf("%v", arw.Rule.Id),
@@ -278,7 +278,7 @@ func (arw *AlertRuleWorker) GetPromAnomalyPoint(ruleConfig string) ([]models.Ano
 		readerClient := arw.PromClients.GetCli(arw.DatasourceId)
 
 		if readerClient == nil {
-			logger.Warningf("rule_eval:%s error reader client is nil", arw.Key())
+			logger.Warningf("alert_eval_%d datasource_%d error reader client is nil", arw.Rule.Id, arw.DatasourceId)
 			arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), GET_CLIENT, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 			arw.Processor.Stats.GaugeQuerySeriesCount.WithLabelValues(
 				fmt.Sprintf("%v", arw.Rule.Id),
@@ -314,13 +314,13 @@ func (arw *AlertRuleWorker) GetPromAnomalyPoint(ruleConfig string) ([]models.Ano
 			// 无变量
 			promql := strings.TrimSpace(query.PromQl)
 			if promql == "" {
-				logger.Warningf("rule_eval:%s promql is blank", arw.Key())
+				logger.Warningf("alert_eval_%d datasource_%d promql is blank", arw.Rule.Id, arw.DatasourceId)
 				arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), CHECK_QUERY, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 				continue
 			}
 
 			if arw.PromClients.IsNil(arw.DatasourceId) {
-				logger.Warningf("rule_eval:%s error reader client is nil", arw.Key())
+				logger.Warningf("alert_eval_%d datasource_%d error reader client is nil", arw.Rule.Id, arw.DatasourceId)
 				arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), GET_CLIENT, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 				continue
 			}
@@ -329,7 +329,7 @@ func (arw *AlertRuleWorker) GetPromAnomalyPoint(ruleConfig string) ([]models.Ano
 			arw.Processor.Stats.CounterQueryDataTotal.WithLabelValues(fmt.Sprintf("%d", arw.DatasourceId), fmt.Sprintf("%d", arw.Rule.Id)).Inc()
 			value, warnings, err := readerClient.Query(context.Background(), promql, time.Now())
 			if err != nil {
-				logger.Errorf("rule_eval:%s promql:%s, error:%v", arw.Key(), promql, err)
+				logger.Errorf("alert_eval_%d datasource_%d promql:%s, error:%v", arw.Rule.Id, arw.DatasourceId, promql, err)
 				arw.Processor.Stats.CounterQueryDataErrorTotal.WithLabelValues(fmt.Sprintf("%d", arw.DatasourceId)).Inc()
 				arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), QUERY_DATA, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 				arw.Processor.Stats.GaugeQuerySeriesCount.WithLabelValues(
@@ -341,12 +341,12 @@ func (arw *AlertRuleWorker) GetPromAnomalyPoint(ruleConfig string) ([]models.Ano
 			}
 
 			if len(warnings) > 0 {
-				logger.Errorf("rule_eval:%s promql:%s, warnings:%v", arw.Key(), promql, warnings)
+				logger.Errorf("alert_eval_%d datasource_%d promql:%s, warnings:%v", arw.Rule.Id, arw.DatasourceId, promql, warnings)
 				arw.Processor.Stats.CounterQueryDataErrorTotal.WithLabelValues(fmt.Sprintf("%d", arw.DatasourceId)).Inc()
 				arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), QUERY_DATA, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 			}
 
-			logger.Infof("rule_eval:%s query:%+v, value:%v", arw.Key(), query, value)
+			logger.Infof("alert_eval_%d datasource_%d query:%+v, value:%v", arw.Rule.Id, arw.DatasourceId, query, value)
 			points := models.ConvertAnomalyPoints(value)
 			arw.Processor.Stats.GaugeQuerySeriesCount.WithLabelValues(
 				fmt.Sprintf("%v", arw.Rule.Id),
@@ -440,14 +440,14 @@ func (arw *AlertRuleWorker) VarFillingAfterQuery(query models.PromQuery, readerC
 			arw.Processor.Stats.CounterQueryDataTotal.WithLabelValues(fmt.Sprintf("%d", arw.DatasourceId), fmt.Sprintf("%d", arw.Rule.Id)).Inc()
 			value, _, err := readerClient.Query(context.Background(), curQuery, time.Now())
 			if err != nil {
-				logger.Errorf("rule_eval:%s, promql:%s, error:%v", arw.Key(), curQuery, err)
+				logger.Errorf("alert_eval_%d datasource_%d promql:%s, error:%v", arw.Rule.Id, arw.DatasourceId, curQuery, err)
 				continue
 			}
 			seqVals := getSamples(value)
 			// 得到参数变量的所有组合
 			paramPermutation, err := arw.getParamPermutation(param, ParamKeys, varToLabel, query.PromQl, readerClient)
 			if err != nil {
-				logger.Errorf("rule_eval:%s, paramPermutation error:%v", arw.Key(), err)
+				logger.Errorf("alert_eval_%d datasource_%d paramPermutation error:%v", arw.Rule.Id, arw.DatasourceId, err)
 				continue
 			}
 			// 判断哪些参数值符合条件
@@ -580,14 +580,14 @@ func (arw *AlertRuleWorker) getParamPermutation(paramVal map[string]models.Param
 		case "host":
 			hostIdents, err := arw.getHostIdents(paramQuery)
 			if err != nil {
-				logger.Errorf("rule_eval:%s, fail to get host idents, error:%v", arw.Key(), err)
+				logger.Errorf("alert_eval_%d datasource_%d fail to get host idents, error:%v", arw.Rule.Id, arw.DatasourceId, err)
 				break
 			}
 			params = hostIdents
 		case "device":
 			deviceIdents, err := arw.getDeviceIdents(paramQuery)
 			if err != nil {
-				logger.Errorf("rule_eval:%s, fail to get device idents, error:%v", arw.Key(), err)
+				logger.Errorf("alert_eval_%d datasource_%d fail to get device idents, error:%v", arw.Rule.Id, arw.DatasourceId, err)
 				break
 			}
 			params = deviceIdents
@@ -596,12 +596,12 @@ func (arw *AlertRuleWorker) getParamPermutation(paramVal map[string]models.Param
 			var query []string
 			err := json.Unmarshal(q, &query)
 			if err != nil {
-				logger.Errorf("query:%s fail to unmarshalling into string slice, error:%v", paramQuery.Query, err)
+				logger.Errorf("alert_eval_%d datasource_%d query:%s fail to unmarshalling into string slice, error:%v", arw.Rule.Id, arw.DatasourceId, paramQuery.Query, err)
 			}
 			if len(query) == 0 {
 				paramsKeyAllLabel, err := getParamKeyAllLabel(varToLabel[paramKey], originPromql, readerClient, arw.DatasourceId, arw.Rule.Id, arw.Processor.Stats)
 				if err != nil {
-					logger.Errorf("rule_eval:%s, fail to getParamKeyAllLabel, error:%v query:%s", arw.Key(), err, paramQuery.Query)
+					logger.Errorf("alert_eval_%d datasource_%d fail to getParamKeyAllLabel, error:%v query:%s", arw.Rule.Id, arw.DatasourceId, err, paramQuery.Query)
 				}
 				params = paramsKeyAllLabel
 			} else {
@@ -615,7 +615,7 @@ func (arw *AlertRuleWorker) getParamPermutation(paramVal map[string]models.Param
 			return nil, fmt.Errorf("param key: %s, params is empty", paramKey)
 		}
 
-		logger.Infof("rule_eval:%s paramKey: %s, params: %v", arw.Key(), paramKey, params)
+		logger.Infof("alert_eval_%d datasource_%d paramKey: %s, params: %v", arw.Rule.Id, arw.DatasourceId, paramKey, params)
 		paramMap[paramKey] = params
 	}
 
@@ -766,7 +766,7 @@ func (arw *AlertRuleWorker) GetHostAnomalyPoint(ruleConfig string) ([]models.Ano
 
 	var rule *models.HostRuleConfig
 	if err := json.Unmarshal([]byte(ruleConfig), &rule); err != nil {
-		logger.Errorf("rule_eval:%s rule_config:%s, error:%v", arw.Key(), ruleConfig, err)
+		logger.Errorf("alert_eval_%d datasource_%d rule_config:%s, error:%v", arw.Rule.Id, arw.DatasourceId, ruleConfig, err)
 		arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), GET_RULE_CONFIG, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 		arw.Processor.Stats.GaugeQuerySeriesCount.WithLabelValues(
 			fmt.Sprintf("%v", arw.Rule.Id),
@@ -777,7 +777,7 @@ func (arw *AlertRuleWorker) GetHostAnomalyPoint(ruleConfig string) ([]models.Ano
 	}
 
 	if rule == nil {
-		logger.Errorf("rule_eval:%s rule_config:%s, error:rule is nil", arw.Key(), ruleConfig)
+		logger.Errorf("alert_eval_%d datasource_%d rule_config:%s, error:rule is nil", arw.Rule.Id, arw.DatasourceId, ruleConfig)
 		arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), GET_RULE_CONFIG, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 		arw.Processor.Stats.GaugeQuerySeriesCount.WithLabelValues(
 			fmt.Sprintf("%v", arw.Rule.Id),
@@ -800,7 +800,7 @@ func (arw *AlertRuleWorker) GetHostAnomalyPoint(ruleConfig string) ([]models.Ano
 				// 如果是中心节点, 将不再上报数据的主机 engineName 为空的机器，也加入到 targets 中
 				missEngineIdents, exists = arw.Processor.TargetsOfAlertRuleCache.Get("", arw.Rule.Id)
 				if !exists {
-					logger.Debugf("rule_eval:%s targets not found engineName:%s", arw.Key(), arw.Processor.EngineName)
+					logger.Debugf("alert_eval_%d datasource_%d targets not found engineName:%s", arw.Rule.Id, arw.DatasourceId, arw.Processor.EngineName)
 					arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), QUERY_DATA, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 				}
 			}
@@ -808,7 +808,7 @@ func (arw *AlertRuleWorker) GetHostAnomalyPoint(ruleConfig string) ([]models.Ano
 
 			engineIdents, exists = arw.Processor.TargetsOfAlertRuleCache.Get(arw.Processor.EngineName, arw.Rule.Id)
 			if !exists {
-				logger.Warningf("rule_eval:%s targets not found engineName:%s", arw.Key(), arw.Processor.EngineName)
+				logger.Warningf("alert_eval_%d datasource_%d targets not found engineName:%s", arw.Rule.Id, arw.DatasourceId, arw.Processor.EngineName)
 				arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), QUERY_DATA, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 			}
 			idents = append(idents, engineIdents...)
@@ -835,7 +835,7 @@ func (arw *AlertRuleWorker) GetHostAnomalyPoint(ruleConfig string) ([]models.Ano
 				"",
 			).Set(float64(len(missTargets)))
 
-			logger.Debugf("rule_eval:%s missTargets:%v", arw.Key(), missTargets)
+			logger.Debugf("alert_eval_%d datasource_%d missTargets:%v", arw.Rule.Id, arw.DatasourceId, missTargets)
 			targets := arw.Processor.TargetCache.Gets(missTargets)
 			for _, target := range targets {
 				m := make(map[string]string)
@@ -854,7 +854,7 @@ func (arw *AlertRuleWorker) GetHostAnomalyPoint(ruleConfig string) ([]models.Ano
 					fmt.Sprintf("%v", arw.Processor.DatasourceId()),
 					"",
 				).Set(0)
-				logger.Warningf("rule_eval:%s targets not found", arw.Key())
+				logger.Warningf("alert_eval_%d datasource_%d targets not found", arw.Rule.Id, arw.DatasourceId)
 				arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), QUERY_DATA, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 				continue
 			}
@@ -885,7 +885,7 @@ func (arw *AlertRuleWorker) GetHostAnomalyPoint(ruleConfig string) ([]models.Ano
 				}
 			}
 
-			logger.Debugf("rule_eval:%s offsetIdents:%v", arw.Key(), offsetIdents)
+			logger.Debugf("alert_eval_%d datasource_%d offsetIdents:%v", arw.Rule.Id, arw.DatasourceId, offsetIdents)
 			arw.Processor.Stats.GaugeQuerySeriesCount.WithLabelValues(
 				fmt.Sprintf("%v", arw.Rule.Id),
 				fmt.Sprintf("%v", arw.Processor.DatasourceId()),
@@ -912,7 +912,7 @@ func (arw *AlertRuleWorker) GetHostAnomalyPoint(ruleConfig string) ([]models.Ano
 					fmt.Sprintf("%v", arw.Processor.DatasourceId()),
 					"",
 				).Set(0)
-				logger.Warningf("rule_eval:%s targets not found", arw.Key())
+				logger.Warningf("alert_eval_%d datasource_%d targets not found", arw.Rule.Id, arw.DatasourceId)
 				arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), QUERY_DATA, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 				continue
 			}
@@ -924,7 +924,7 @@ func (arw *AlertRuleWorker) GetHostAnomalyPoint(ruleConfig string) ([]models.Ano
 					missTargets = append(missTargets, ident)
 				}
 			}
-			logger.Debugf("rule_eval:%s missTargets:%v", arw.Key(), missTargets)
+			logger.Debugf("alert_eval_%d datasource_%d missTargets:%v", arw.Rule.Id, arw.DatasourceId, missTargets)
 			arw.Processor.Stats.GaugeQuerySeriesCount.WithLabelValues(
 				fmt.Sprintf("%v", arw.Rule.Id),
 				fmt.Sprintf("%v", arw.Processor.DatasourceId()),
@@ -1120,7 +1120,7 @@ func ProcessJoins(ruleId int64, trigger models.Trigger, seriesTagIndexes map[str
 
 	// 有 join 条件，按条件依次合并
 	if len(seriesTagIndexes) < len(trigger.Joins)+1 {
-		logger.Errorf("rule_eval rid:%d queries' count: %d not match join condition's count: %d", ruleId, len(seriesTagIndexes), len(trigger.Joins))
+		logger.Errorf("alert_eval_%d queries' count: %d not match join condition's count: %d", ruleId, len(seriesTagIndexes), len(trigger.Joins))
 		return nil
 	}
 
@@ -1156,7 +1156,7 @@ func ProcessJoins(ruleId int64, trigger models.Trigger, seriesTagIndexes map[str
 			lastRehashed = exclude(curRehashed, lastRehashed)
 			last = flatten(lastRehashed)
 		default:
-			logger.Warningf("rule_eval rid:%d join type:%s not support", ruleId, trigger.Joins[i].JoinType)
+			logger.Warningf("alert_eval_%d join type:%s not support", ruleId, trigger.Joins[i].JoinType)
 		}
 	}
 	return last
@@ -1276,7 +1276,7 @@ func (arw *AlertRuleWorker) VarFillingBeforeQuery(query models.PromQuery, reader
 			// 得到参数变量的所有组合
 			paramPermutation, err := arw.getParamPermutation(param, ParamKeys, varToLabel, query.PromQl, readerClient)
 			if err != nil {
-				logger.Errorf("rule_eval:%s, paramPermutation error:%v", arw.Key(), err)
+				logger.Errorf("alert_eval_%d datasource_%d paramPermutation error:%v", arw.Rule.Id, arw.DatasourceId, err)
 				continue
 			}
 
@@ -1304,10 +1304,10 @@ func (arw *AlertRuleWorker) VarFillingBeforeQuery(query models.PromQuery, reader
 					arw.Processor.Stats.CounterQueryDataTotal.WithLabelValues(fmt.Sprintf("%d", arw.DatasourceId), fmt.Sprintf("%d", arw.Rule.Id)).Inc()
 					value, _, err := readerClient.Query(context.Background(), promql, time.Now())
 					if err != nil {
-						logger.Errorf("rule_eval:%s, promql:%s, error:%v", arw.Key(), promql, err)
+						logger.Errorf("alert_eval_%d datasource_%d promql:%s, error:%v", arw.Rule.Id, arw.DatasourceId, promql, err)
 						return
 					}
-					logger.Infof("rule_eval:%s, promql:%s, value:%+v", arw.Key(), promql, value)
+					logger.Infof("alert_eval_%d datasource_%d promql:%s, value:%+v", arw.Rule.Id, arw.DatasourceId, promql, value)
 
 					points := models.ConvertAnomalyPoints(value)
 					if len(points) == 0 {
@@ -1446,7 +1446,7 @@ func (arw *AlertRuleWorker) GetAnomalyPoint(rule *models.AlertRule, dsId int64)
 	recoverPoints := []models.AnomalyPoint{}
 	ruleConfig := strings.TrimSpace(rule.RuleConfig)
 	if ruleConfig == "" {
-		logger.Warningf("rule_eval:%d ruleConfig is blank", rule.Id)
+		logger.Warningf("alert_eval_%d datasource_%d ruleConfig is blank", rule.Id, dsId)
 		arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), GET_RULE_CONFIG, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 		arw.Processor.Stats.GaugeQuerySeriesCount.WithLabelValues(
 			fmt.Sprintf("%v", arw.Rule.Id),
@@ -1454,15 +1454,15 @@ func (arw *AlertRuleWorker) GetAnomalyPoint(rule *models.AlertRule, dsId int64)
 			"",
 		).Set(0)
 
-		return points, recoverPoints, fmt.Errorf("rule_eval:%d ruleConfig is blank", rule.Id)
+		return points, recoverPoints, fmt.Errorf("alert_eval_%d datasource_%d ruleConfig is blank", rule.Id, dsId)
 	}
 
 	var ruleQuery models.RuleQuery
 	err := json.Unmarshal([]byte(ruleConfig), &ruleQuery)
 	if err != nil {
-		logger.Warningf("rule_eval:%d promql parse error:%s", rule.Id, err.Error())
+		logger.Warningf("alert_eval_%d datasource_%d promql parse error:%s", rule.Id, dsId, err.Error())
 		arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), GET_RULE_CONFIG, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
-		return points, recoverPoints, fmt.Errorf("rule_eval:%d promql parse error:%s", rule.Id, err.Error())
+		return points, recoverPoints, fmt.Errorf("alert_eval_%d datasource_%d promql parse error:%s", rule.Id, dsId, err.Error())
 	}
 
 	arw.Inhibit = ruleQuery.Inhibit
@@ -1474,7 +1474,7 @@ func (arw *AlertRuleWorker) GetAnomalyPoint(rule *models.AlertRule, dsId int64)
 
 			plug, exists := dscache.DsCache.Get(rule.Cate, dsId)
 			if !exists {
-				logger.Warningf("rule_eval rid:%d datasource:%d not exists", rule.Id, dsId)
+				logger.Warningf("alert_eval_%d datasource_%d not exists", rule.Id, dsId)
 				arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), GET_CLIENT, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 
 				arw.Processor.Stats.GaugeQuerySeriesCount.WithLabelValues(
@@ -1483,11 +1483,11 @@ func (arw *AlertRuleWorker) GetAnomalyPoint(rule *models.AlertRule, dsId int64)
 					fmt.Sprintf("%v", i),
 				).Set(-2)
 
-				return points, recoverPoints, fmt.Errorf("rule_eval:%d datasource:%d not exists", rule.Id, dsId)
+				return points, recoverPoints, fmt.Errorf("alert_eval_%d datasource_%d not exists", rule.Id, dsId)
 			}
 
 			if err = ExecuteQueryTemplate(rule.Cate, query, nil); err != nil {
-				logger.Warningf("rule_eval rid:%d execute query template error: %v", rule.Id, err)
+				logger.Warningf("alert_eval_%d datasource_%d execute query template error: %v", rule.Id, dsId, err)
 				arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), EXEC_TEMPLATE, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 				arw.Processor.Stats.GaugeQuerySeriesCount.WithLabelValues(
 					fmt.Sprintf("%v", arw.Rule.Id),
@@ -1500,7 +1500,7 @@ func (arw *AlertRuleWorker) GetAnomalyPoint(rule *models.AlertRule, dsId int64)
 			series, err := plug.QueryData(ctx, query)
 			arw.Processor.Stats.CounterQueryDataTotal.WithLabelValues(fmt.Sprintf("%d", arw.DatasourceId), fmt.Sprintf("%d", rule.Id)).Inc()
 			if err != nil {
-				logger.Warningf("rule_eval rid:%d query data error: %v", rule.Id, err)
+				logger.Warningf("alert_eval_%d datasource_%d query data error: %v", rule.Id, dsId, err)
 				arw.Processor.Stats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", arw.Processor.DatasourceId()), GET_CLIENT, arw.Processor.BusiGroupCache.GetNameByBusiGroupId(arw.Rule.GroupId), fmt.Sprintf("%v", arw.Rule.Id)).Inc()
 				arw.Processor.Stats.GaugeQuerySeriesCount.WithLabelValues(
 					fmt.Sprintf("%v", arw.Rule.Id),
@@ -1508,7 +1508,7 @@ func (arw *AlertRuleWorker) GetAnomalyPoint(rule *models.AlertRule, dsId int64)
 					fmt.Sprintf("%v", i),
 				).Set(-1)
 
-				return points, recoverPoints, fmt.Errorf("rule_eval:%d query data error: %v", rule.Id, err)
+				return points, recoverPoints, fmt.Errorf("alert_eval_%d datasource_%d query data error: %v", rule.Id, dsId, err)
 			}
 
 			arw.Processor.Stats.GaugeQuerySeriesCount.WithLabelValues(
@@ -1518,7 +1518,7 @@ func (arw *AlertRuleWorker) GetAnomalyPoint(rule *models.AlertRule, dsId int64)
 			).Set(float64(len(series)))
 
 			//  此条日志很重要，是告警判断的现场值
-			logger.Infof("rule_eval rid:%d req:%+v resp:%v", rule.Id, query, series)
+			logger.Infof("alert_eval_%d datasource_%d req:%+v resp:%v", rule.Id, dsId, query, series)
 			for i := 0; i < len(series); i++ {
 				seriesHash := hash.GetHash(series[i].Metric, series[i].Ref)
 				tagHash := hash.GetTagHash(series[i].Metric)
@@ -1532,7 +1532,7 @@ func (arw *AlertRuleWorker) GetAnomalyPoint(rule *models.AlertRule, dsId int64)
 			}
 			ref, err := GetQueryRef(query)
 			if err != nil {
-				logger.Warningf("rule_eval rid:%d query:%+v get ref error:%s", rule.Id, query, err.Error())
+				logger.Warningf("alert_eval_%d datasource_%d query:%+v get ref error:%s", rule.Id, dsId, query, err.Error())
 				continue
 			}
 			seriesTagIndexes[ref] = seriesTagIndex
@@ -1542,7 +1542,7 @@ func (arw *AlertRuleWorker) GetAnomalyPoint(rule *models.AlertRule, dsId int64)
 		for _, query := range ruleQuery.Queries {
 			ref, unit, err := GetQueryRefAndUnit(query)
 			if err != nil {
-				logger.Warningf("rule_eval rid:%d query:%+v get ref and unit error:%s", rule.Id, query, err.Error())
+				logger.Warningf("alert_eval_%d datasource_%d query:%+v get ref and unit error:%s", rule.Id, dsId, query, err.Error())
 				continue
 			}
 			unitMap[ref] = unit
@@ -1565,12 +1565,12 @@ func (arw *AlertRuleWorker) GetAnomalyPoint(rule *models.AlertRule, dsId int64)
 					for _, seriesHash := range seriesHash {
 						series, exists := seriesStore[seriesHash]
 						if !exists {
-							logger.Warningf("rule_eval rid:%d series:%+v not found", rule.Id, series)
+							logger.Warningf("alert_eval_%d datasource_%d series:%+v not found", rule.Id, dsId, series)
 							continue
 						}
 						t, v, exists := series.Last()
 						if !exists {
-							logger.Warningf("rule_eval rid:%d series:%+v value not found", rule.Id, series)
+							logger.Warningf("alert_eval_%d datasource_%d series:%+v value not found", rule.Id, dsId, series)
 							continue
 						}
 
@@ -1601,12 +1601,12 @@ func (arw *AlertRuleWorker) GetAnomalyPoint(rule *models.AlertRule, dsId int64)
 						ts = int64(t)
 						sample = series
 						value = v
-						logger.Infof("rule_eval rid:%d origin series labels:%+v", rule.Id, series.Metric)
+						logger.Infof("alert_eval_%d datasource_%d origin series labels:%+v", rule.Id, dsId, series.Metric)
 					}
 
 					isTriggered := parser.CalcWithRid(trigger.Exp, m, rule.Id)
 					//  此条日志很重要，是告警判断的现场值
-					logger.Infof("rule_eval rid:%d trigger:%+v exp:%s res:%v m:%v", rule.Id, trigger, trigger.Exp, isTriggered, m)
+					logger.Infof("alert_eval_%d datasource_%d trigger:%+v exp:%s res:%v m:%v", rule.Id, dsId, trigger, trigger.Exp, isTriggered, m)
 
 					var values string
 					for k, v := range m {
@@ -1679,7 +1679,7 @@ func (arw *AlertRuleWorker) GetAnomalyPoint(rule *models.AlertRule, dsId int64)
 
 						// 检查是否超过 resolve_after 时间
 						if now-int64(lastTs) > int64(ruleQuery.NodataTrigger.ResolveAfter) {
-							logger.Infof("rule_eval rid:%d series:%+v resolve after %d seconds now:%d lastTs:%d", rule.Id, lastSeries, ruleQuery.NodataTrigger.ResolveAfter, now, int64(lastTs))
+							logger.Infof("alert_eval_%d datasource_%d series:%+v resolve after %d seconds now:%d lastTs:%d", rule.Id, dsId, lastSeries, ruleQuery.NodataTrigger.ResolveAfter, now, int64(lastTs))
 							delete(arw.LastSeriesStore, hash)
 							continue
 						}
@@ -1700,7 +1700,7 @@ func (arw *AlertRuleWorker) GetAnomalyPoint(rule *models.AlertRule, dsId int64)
 							TriggerType: models.TriggerTypeNodata,
 						}
 						points = append(points, point)
-						logger.Infof("rule_eval rid:%d nodata point:%+v", rule.Id, point)
+						logger.Infof("alert_eval_%d datasource_%d nodata point:%+v", rule.Id, dsId, point)
 					}
 				}
 

alert/mute/mute.go

@@ -41,8 +41,28 @@ func IsMuted(rule *models.AlertRule, event *models.AlertCurEvent, targetCache *m
 
 // TimeSpanMuteStrategy 根据规则配置的告警生效时间段过滤,如果产生的告警不在规则配置的告警生效时间段内,则不告警,即被mute
 // 时间范围，左闭右开，默认范围：00:00-24:00
+// 如果规则配置了时区，则在该时区下进行时间判断；如果时区为空，则使用系统时区
 func TimeSpanMuteStrategy(rule *models.AlertRule, event *models.AlertCurEvent) bool {
-	tm := time.Unix(event.TriggerTime, 0)
+	// 确定使用的时区
+	var targetLoc *time.Location
+	var err error
+
+	timezone := rule.TimeZone
+	if timezone == "" {
+		// 如果时区为空，使用系统时区（保持原有逻辑）
+		targetLoc = time.Local
+	} else {
+		// 加载规则配置的时区
+		targetLoc, err = time.LoadLocation(timezone)
+		if err != nil {
+			// 如果时区加载失败，记录错误并使用系统时区
+			logger.Warningf("Failed to load timezone %s for rule %d, using system timezone: %v", timezone, rule.Id, err)
+			targetLoc = time.Local
+		}
+	}
+
+	// 将触发时间转换到目标时区
+	tm := time.Unix(event.TriggerTime, 0).In(targetLoc)
 	triggerTime := tm.Format("15:04")
 	triggerWeek := strconv.Itoa(int(tm.Weekday()))
 
@@ -102,7 +122,7 @@ func IdentNotExistsMuteStrategy(rule *models.AlertRule, event *models.AlertCurEv
 	// 如果是target_up的告警,且ident已经不存在了,直接过滤掉
 	// 这里的判断有点太粗暴了,但是目前没有更好的办法
 	if !exists && strings.Contains(rule.PromQl, "target_up") {
-		logger.Debugf("[%s] mute: rule_eval:%d cluster:%s ident:%s", "IdentNotExistsMuteStrategy", rule.Id, event.Cluster, ident)
+		logger.Debugf("alert_eval_%d [IdentNotExistsMuteStrategy] mute: cluster:%s ident:%s", rule.Id, event.Cluster, ident)
 		return true
 	}
 	return false
@@ -124,7 +144,7 @@ func BgNotMatchMuteStrategy(rule *models.AlertRule, event *models.AlertCurEvent,
 	// 对于包含ident的告警事件，check一下ident所属bg和rule所属bg是否相同
 	// 如果告警规则选择了只在本BG生效，那其他BG的机器就不能因此规则产生告警
 	if exists && !target.MatchGroupId(rule.GroupId) {
-		logger.Debugf("[%s] mute: rule_eval:%d cluster:%s", "BgNotMatchMuteStrategy", rule.Id, event.Cluster)
+		logger.Debugf("alert_eval_%d [BgNotMatchMuteStrategy] mute: cluster:%s", rule.Id, event.Cluster)
 		return true
 	}
 	return false

alert/pipeline/processor/eventdrop/event_drop.go

@@ -55,7 +55,7 @@ func (c *EventDropConfig) Process(ctx *ctx.Context, wfCtx *models.WorkflowContex
 	logger.Infof("processor eventdrop result: %v", result)
 	if result == "true" {
 		wfCtx.Event = nil
-		logger.Infof("processor eventdrop drop event: %v", event)
+		logger.Infof("processor eventdrop drop event: %s", event.Hash)
 		return wfCtx, "drop event success", nil
 	}
 

alert/process/process.go

@@ -131,7 +131,7 @@ func (p *Processor) Handle(anomalyPoints []models.AnomalyPoint, from string, inh
 	p.inhibit = inhibit
 	cachedRule := p.alertRuleCache.Get(p.rule.Id)
 	if cachedRule == nil {
-		logger.Warningf("process handle error: rule not found %+v rule_id:%d maybe rule has been deleted", anomalyPoints, p.rule.Id)
+		logger.Warningf("alert_eval_%d datasource_%d handle error: rule not found, maybe rule has been deleted, anomalyPoints:%+v", p.rule.Id, p.datasourceId, anomalyPoints)
 		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
 	}
@@ -156,14 +156,14 @@ func (p *Processor) Handle(anomalyPoints []models.AnomalyPoint, from string, inh
 		eventCopy := event.DeepCopy()
 		event = dispatch.HandleEventPipeline(cachedRule.PipelineConfigs, eventCopy, event, dispatch.EventProcessorCache, p.ctx, cachedRule.Id, "alert_rule")
 		if event == nil {
-			logger.Infof("rule_eval:%s is muted drop by pipeline event:%v", p.Key(), eventCopy)
+			logger.Infof("alert_eval_%d datasource_%d is muted drop by pipeline event:%s", p.rule.Id, p.datasourceId, eventCopy.Hash)
 			continue
 		}
 
 		// event mute
 		isMuted, detail, muteId := mute.IsMuted(cachedRule, event, p.TargetCache, p.alertMuteCache)
 		if isMuted {
-			logger.Infof("rule_eval:%s is muted, detail:%s event:%v", p.Key(), detail, event)
+			logger.Infof("alert_eval_%d datasource_%d is muted, detail:%s event:%s", p.rule.Id, p.datasourceId, detail, event.Hash)
 			p.Stats.CounterMuteTotal.WithLabelValues(
 				fmt.Sprintf("%v", event.GroupName),
 				fmt.Sprintf("%v", p.rule.Id),
@@ -174,7 +174,7 @@ func (p *Processor) Handle(anomalyPoints []models.AnomalyPoint, from string, inh
 		}
 
 		if dispatch.EventMuteHook(event) {
-			logger.Infof("rule_eval:%s is muted by hook event:%v", p.Key(), event)
+			logger.Infof("alert_eval_%d datasource_%d is muted by hook event:%s", p.rule.Id, p.datasourceId, event.Hash)
 			p.Stats.CounterMuteTotal.WithLabelValues(
 				fmt.Sprintf("%v", event.GroupName),
 				fmt.Sprintf("%v", p.rule.Id),
@@ -247,7 +247,7 @@ func (p *Processor) BuildEvent(anomalyPoint models.AnomalyPoint, from string, no
 
 	if err := json.Unmarshal([]byte(p.rule.Annotations), &event.AnnotationsJSON); err != nil {
 		event.AnnotationsJSON = make(map[string]string) // 解析失败时使用空 map
-		logger.Warningf("unmarshal annotations json failed: %v, rule: %d", err, p.rule.Id)
+		logger.Warningf("alert_eval_%d datasource_%d unmarshal annotations json failed: %v", p.rule.Id, p.datasourceId, err)
 	}
 
 	if event.TriggerValues != "" && strings.Count(event.TriggerValues, "$") > 1 {
@@ -272,7 +272,7 @@ func (p *Processor) BuildEvent(anomalyPoint models.AnomalyPoint, from string, no
 			pt.GroupNames = p.BusiGroupCache.GetNamesByBusiGroupIds(pt.GroupIds)
 			event.Target = pt
 		} else {
-			logger.Infof("fill event target error, ident: %s doesn't exist in cache.", event.TargetIdent)
+			logger.Infof("alert_eval_%d datasource_%d fill event target error, ident: %s doesn't exist in cache.", p.rule.Id, p.datasourceId, event.TargetIdent)
 		}
 	}
 
@@ -371,19 +371,19 @@ func (p *Processor) RecoverSingle(byRecover bool, hash string, now int64, value
 		lastPendingEvent, has := p.pendingsUseByRecover.Get(hash)
 		if !has {
 			// 说明没有产生过异常点，就不需要恢复了
-			logger.Debugf("rule_eval:%s event:%v do not has pending event, not recover", p.Key(), event)
+			logger.Debugf("alert_eval_%d datasource_%d event:%s do not has pending event, not recover", p.rule.Id, p.datasourceId, event.Hash)
 			return
 		}
 
 		if now-lastPendingEvent.LastEvalTime < cachedRule.RecoverDuration {
-			logger.Debugf("rule_eval:%s event:%v not recover", p.Key(), event)
+			logger.Debugf("alert_eval_%d datasource_%d event:%s not recover", p.rule.Id, p.datasourceId, event.Hash)
 			return
 		}
 	}
 
 	// 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)
+		logger.Debugf("alert_eval_%d datasource_%d event:%s not recover", p.rule.Id, p.datasourceId, event.Hash)
 		return
 	}
 
@@ -460,7 +460,7 @@ func (p *Processor) handleEvent(events []*models.AlertCurEvent) {
 func (p *Processor) inhibitEvent(events []*models.AlertCurEvent, highSeverity int) {
 	for _, event := range events {
 		if p.inhibit && event.Severity > highSeverity {
-			logger.Debugf("rule_eval:%s event:%+v inhibit highSeverity:%d", p.Key(), event, highSeverity)
+			logger.Debugf("alert_eval_%d datasource_%d event:%s inhibit highSeverity:%d", p.rule.Id, p.datasourceId, event.Hash, highSeverity)
 			continue
 		}
 		p.fireEvent(event)
@@ -476,7 +476,7 @@ func (p *Processor) fireEvent(event *models.AlertCurEvent) {
 
 	message := "unknown"
 	defer func() {
-		logger.Infof("rule_eval:%s event-hash-%s %s", p.Key(), event.Hash, message)
+		logger.Infof("alert_eval_%d datasource_%d event-hash-%s %s", p.rule.Id, p.datasourceId, event.Hash, message)
 	}()
 
 	if fired, has := p.fires.Get(event.Hash); has {
@@ -527,7 +527,7 @@ 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)
+		logger.Warningf("alert_eval_%d datasource_%d event_push_queue: queue is full, event:%s", p.rule.Id, p.datasourceId, e.Hash)
 		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()
 	}
 }
@@ -538,7 +538,7 @@ 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)
+		logger.Errorf("alert_eval_%d datasource_%d recover event from db failed, err:%s", p.rule.Id, p.datasourceId, err)
 		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

alert/router/router.go

@@ -22,10 +22,11 @@ type Router struct {
 	AlertStats         *astats.Stats
 	Ctx                *ctx.Context
 	ExternalProcessors *process.ExternalProcessorsType
+	LogDir             string
 }
 
 func New(httpConfig httpx.Config, alert aconf.Alert, amc *memsto.AlertMuteCacheType, tc *memsto.TargetCacheType, bgc *memsto.BusiGroupCacheType,
-	astats *astats.Stats, ctx *ctx.Context, externalProcessors *process.ExternalProcessorsType) *Router {
+	astats *astats.Stats, ctx *ctx.Context, externalProcessors *process.ExternalProcessorsType, logDir string) *Router {
 	return &Router{
 		HTTP:               httpConfig,
 		Alert:              alert,
@@ -35,6 +36,7 @@ func New(httpConfig httpx.Config, alert aconf.Alert, amc *memsto.AlertMuteCacheT
 		AlertStats:         astats,
 		Ctx:                ctx,
 		ExternalProcessors: externalProcessors,
+		LogDir:             logDir,
 	}
 }
 
@@ -50,6 +52,9 @@ func (rt *Router) Config(r *gin.Engine) {
 	service.POST("/event", rt.pushEventToQueue)
 	service.POST("/event-persist", rt.eventPersist)
 	service.POST("/make-event", rt.makeEvent)
+	service.GET("/event-detail/:hash", rt.eventDetail)
+	service.GET("/alert-eval-detail/:id", rt.alertEvalDetail)
+	service.GET("/trace-logs/:traceid", rt.traceLogs)
 }
 
 func Render(c *gin.Context, data, msg interface{}) {

alert/router/router_alert_eval_detail.go

@@ -0,0 +1,28 @@
+package router
+
+import (
+	"fmt"
+
+	"github.com/ccfos/nightingale/v6/pkg/loggrep"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
+
+	"github.com/gin-gonic/gin"
+)
+
+func (rt *Router) alertEvalDetail(c *gin.Context) {
+	id := ginx.UrlParamStr(c, "id")
+	if !loggrep.IsValidRuleID(id) {
+		ginx.Bomb(200, "invalid rule id format")
+	}
+
+	instance := fmt.Sprintf("%s:%d", rt.Alert.Heartbeat.IP, rt.HTTP.Port)
+
+	keyword := fmt.Sprintf("alert_eval_%s", id)
+	logs, err := loggrep.GrepLogDir(rt.LogDir, keyword)
+	ginx.Dangerous(err)
+
+	ginx.NewRender(c).Data(loggrep.EventDetailResp{
+		Logs:     logs,
+		Instance: instance,
+	}, nil)
+}

alert/router/router_event.go

@@ -13,9 +13,9 @@ import (
 	"github.com/ccfos/nightingale/v6/alert/queue"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/poster"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 )
 
@@ -75,7 +75,7 @@ func (rt *Router) pushEventToQueue(c *gin.Context) {
 
 	dispatch.LogEvent(event, "http_push_queue")
 	if !queue.EventQueue.PushFront(event) {
-		msg := fmt.Sprintf("event:%+v push_queue err: queue is full", event)
+		msg := fmt.Sprintf("event:%s push_queue err: queue is full", event.Hash)
 		ginx.Bomb(200, msg)
 		logger.Warningf(msg)
 	}
@@ -105,21 +105,21 @@ func (rt *Router) makeEvent(c *gin.Context) {
 	for i := 0; i < len(events); i++ {
 		node, err := naming.DatasourceHashRing.GetNode(strconv.FormatInt(events[i].DatasourceId, 10), fmt.Sprintf("%d", events[i].RuleId))
 		if err != nil {
-			logger.Warningf("event:%+v get node err:%v", events[i], err)
+			logger.Warningf("event(rule_id=%d ds_id=%d) get node err:%v", events[i].RuleId, events[i].DatasourceId, err)
 			ginx.Bomb(200, "event node not exists")
 		}
 
 		if node != rt.Alert.Heartbeat.Endpoint {
 			err := forwardEvent(events[i], node)
 			if err != nil {
-				logger.Warningf("event:%+v forward err:%v", events[i], err)
+				logger.Warningf("event(rule_id=%d ds_id=%d) forward err:%v", events[i].RuleId, events[i].DatasourceId, err)
 				ginx.Bomb(200, "event forward error")
 			}
 			continue
 		}
 
 		ruleWorker, exists := rt.ExternalProcessors.GetExternalAlertRule(events[i].DatasourceId, events[i].RuleId)
-		logger.Debugf("handle event:%+v exists:%v", events[i], exists)
+		logger.Debugf("handle event(rule_id=%d ds_id=%d) exists:%v", events[i].RuleId, events[i].DatasourceId, exists)
 		if !exists {
 			ginx.Bomb(200, "rule not exists")
 		}
@@ -143,6 +143,6 @@ func forwardEvent(event *eventForm, instance string) error {
 	if err != nil {
 		return err
 	}
-	logger.Infof("forward event: result=succ url=%s code=%d event:%v response=%s", ur, code, event, string(res))
+	logger.Infof("forward event: result=succ url=%s code=%d rule_id=%d response=%s", ur, code, event.RuleId, string(res))
 	return nil
 }

alert/router/router_event_detail.go

@@ -0,0 +1,27 @@
+package router
+
+import (
+	"fmt"
+
+	"github.com/ccfos/nightingale/v6/pkg/loggrep"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
+
+	"github.com/gin-gonic/gin"
+)
+
+func (rt *Router) eventDetail(c *gin.Context) {
+	hash := ginx.UrlParamStr(c, "hash")
+	if !loggrep.IsValidHash(hash) {
+		ginx.Bomb(200, "invalid hash format")
+	}
+
+	instance := fmt.Sprintf("%s:%d", rt.Alert.Heartbeat.IP, rt.HTTP.Port)
+
+	logs, err := loggrep.GrepLogDir(rt.LogDir, hash)
+	ginx.Dangerous(err)
+
+	ginx.NewRender(c).Data(loggrep.EventDetailResp{
+		Logs:     logs,
+		Instance: instance,
+	}, nil)
+}

alert/router/router_trace_logs.go

@@ -0,0 +1,28 @@
+package router
+
+import (
+	"fmt"
+
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
+	"github.com/ccfos/nightingale/v6/pkg/loggrep"
+
+	"github.com/gin-gonic/gin"
+)
+
+func (rt *Router) traceLogs(c *gin.Context) {
+	traceId := ginx.UrlParamStr(c, "traceid")
+	if !loggrep.IsValidTraceID(traceId) {
+		ginx.Bomb(200, "invalid trace id format")
+	}
+
+	instance := fmt.Sprintf("%s:%d", rt.Alert.Heartbeat.IP, rt.HTTP.Port)
+
+	keyword := "trace_id=" + traceId
+	logs, err := loggrep.GrepLatestLogFiles(rt.LogDir, keyword)
+	ginx.Dangerous(err)
+
+	ginx.NewRender(c).Data(loggrep.EventDetailResp{
+		Logs:     logs,
+		Instance: instance,
+	}, nil)
+}

alert/sender/callback.go

@@ -205,6 +205,6 @@ func PushCallbackEvent(ctx *ctx.Context, webhook *models.Webhook, event *models.
 
 	succ := queue.eventQueue.Push(event)
 	if !succ {
-		logger.Warningf("Write channel(%s) full, current channel size: %d event:%v", webhook.Url, queue.eventQueue.Len(), event)
+		logger.Warningf("Write channel(%s) full, current channel size: %d event:%s", webhook.Url, queue.eventQueue.Len(), event.Hash)
 	}
 }

alert/sender/ibex.go

@@ -30,14 +30,14 @@ type IbexCallBacker struct {
 
 func (c *IbexCallBacker) CallBack(ctx CallBackContext) {
 	if len(ctx.CallBackURL) == 0 || len(ctx.Events) == 0 {
-		logger.Warningf("event_callback_ibex: url or events is empty, url: %s, events: %+v", ctx.CallBackURL, ctx.Events)
+		logger.Warningf("event_callback_ibex: url or events is empty, url: %s", ctx.CallBackURL)
 		return
 	}
 
 	event := ctx.Events[0]
 
 	if event.IsRecovered {
-		logger.Infof("event_callback_ibex: event is recovered, event: %+v", event)
+		logger.Infof("event_callback_ibex: event is recovered, event: %s", event.Hash)
 		return
 	}
 
@@ -45,9 +45,9 @@ func (c *IbexCallBacker) CallBack(ctx CallBackContext) {
 }
 
 func (c *IbexCallBacker) handleIbex(ctx *ctx.Context, url string, event *models.AlertCurEvent) {
-	logger.Infof("event_callback_ibex: url: %s, event: %+v", url, event)
+	logger.Infof("event_callback_ibex: url: %s, event: %s", url, event.Hash)
 	if imodels.DB() == nil && ctx.IsCenter {
-		logger.Warningf("event_callback_ibex: db is nil, event: %+v", event)
+		logger.Warningf("event_callback_ibex: db is nil, event: %s", event.Hash)
 		return
 	}
 
@@ -66,7 +66,7 @@ func (c *IbexCallBacker) handleIbex(ctx *ctx.Context, url string, event *models.
 
 	id, err := strconv.ParseInt(idstr, 10, 64)
 	if err != nil {
-		logger.Errorf("event_callback_ibex: failed to parse url: %s event: %+v", url, event)
+		logger.Errorf("event_callback_ibex: failed to parse url: %s event: %s", url, event.Hash)
 		return
 	}
 
@@ -82,7 +82,7 @@ func (c *IbexCallBacker) handleIbex(ctx *ctx.Context, url string, event *models.
 	}
 
 	if host == "" {
-		logger.Errorf("event_callback_ibex: failed to get host, id: %d, event: %+v", id, event)
+		logger.Errorf("event_callback_ibex: failed to get host, id: %d, event: %s", id, event.Hash)
 		return
 	}
 
@@ -92,11 +92,11 @@ func (c *IbexCallBacker) handleIbex(ctx *ctx.Context, url string, event *models.
 func CallIbex(ctx *ctx.Context, id int64, host string,
 	taskTplCache *memsto.TaskTplCache, targetCache *memsto.TargetCacheType,
 	userCache *memsto.UserCacheType, event *models.AlertCurEvent, args string) (int64, error) {
-	logger.Infof("event_callback_ibex: id: %d, host: %s, args: %s, event: %+v", id, host, args, event)
+	logger.Infof("event_callback_ibex: id: %d, host: %s, args: %s, event: %s", id, host, args, event.Hash)
 
 	tpl := taskTplCache.Get(id)
 	if tpl == nil {
-		err := fmt.Errorf("event_callback_ibex: no such tpl(%d), event: %+v", id, event)
+		err := fmt.Errorf("event_callback_ibex: no such tpl(%d), event: %s", id, event.Hash)
 		logger.Errorf("%s", err)
 		return 0, err
 	}
@@ -104,13 +104,13 @@ func CallIbex(ctx *ctx.Context, id int64, host string,
 	// tpl.GroupId - host - account 三元组校验权限
 	can, err := CanDoIbex(tpl.UpdateBy, tpl, host, targetCache, userCache)
 	if err != nil {
-		err = fmt.Errorf("event_callback_ibex: check perm fail: %v, event: %+v", err, event)
+		err = fmt.Errorf("event_callback_ibex: check perm fail: %v, event: %s", err, event.Hash)
 		logger.Errorf("%s", err)
 		return 0, err
 	}
 
 	if !can {
-		err = fmt.Errorf("event_callback_ibex: user(%s) no permission, event: %+v", tpl.UpdateBy, event)
+		err = fmt.Errorf("event_callback_ibex: user(%s) no permission, event: %s", tpl.UpdateBy, event.Hash)
 		logger.Errorf("%s", err)
 		return 0, err
 	}
@@ -136,7 +136,7 @@ func CallIbex(ctx *ctx.Context, id int64, host string,
 
 	tags, err := json.Marshal(tagsMap)
 	if err != nil {
-		err = fmt.Errorf("event_callback_ibex: failed to marshal tags to json: %v, event: %+v", tagsMap, event)
+		err = fmt.Errorf("event_callback_ibex: failed to marshal tags to json: %v, event: %s", tagsMap, event.Hash)
 		logger.Errorf("%s", err)
 		return 0, err
 	}
@@ -164,7 +164,7 @@ func CallIbex(ctx *ctx.Context, id int64, host string,
 
 	id, err = TaskAdd(in, tpl.UpdateBy, ctx.IsCenter)
 	if err != nil {
-		err = fmt.Errorf("event_callback_ibex: call ibex fail: %v, event: %+v", err, event)
+		err = fmt.Errorf("event_callback_ibex: call ibex fail: %v, event: %s", err, event.Hash)
 		logger.Errorf("%s", err)
 		return 0, err
 	}
@@ -187,7 +187,7 @@ func CallIbex(ctx *ctx.Context, id int64, host string,
 	}
 
 	if err = record.Add(ctx); err != nil {
-		err = fmt.Errorf("event_callback_ibex: persist task_record fail: %v, event: %+v", err, event)
+		err = fmt.Errorf("event_callback_ibex: persist task_record fail: %v, event: %s", err, event.Hash)
 		logger.Errorf("%s", err)
 		return id, err
 	}

alert/sender/webhook.go

@@ -72,7 +72,7 @@ func sendWebhook(webhook *models.Webhook, event interface{}, stats *astats.Stats
 	}
 	bs, err := json.Marshal(event)
 	if err != nil {
-		logger.Errorf("%s alertingWebhook failed to marshal event:%+v err:%v", channel, event, err)
+		logger.Errorf("%s alertingWebhook failed to marshal event err:%v", channel, err)
 		return false, "", err
 	}
 
@@ -145,7 +145,7 @@ func SingleSendWebhooks(ctx *ctx.Context, webhooks map[string]*models.Webhook, e
 
 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)
+		logger.Infof("push event:%s to queue:%v", event.Hash, conf)
 		PushEvent(ctx, conf, event, stats)
 	}
 }
@@ -183,7 +183,7 @@ func PushEvent(ctx *ctx.Context, webhook *models.Webhook, event *models.AlertCur
 	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.eventQueue.Len(), event)
+		logger.Warningf("Write channel(%s) full, current channel size: %d event:%s", webhook.Url, queue.eventQueue.Len(), event.Hash)
 	}
 }
 

center/center.go

@@ -136,10 +136,10 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 	go cron.CleanNotifyRecord(ctx, config.Center.CleanNotifyRecordDay)
 	go cron.CleanPipelineExecution(ctx, config.Center.CleanPipelineExecutionDay)
 
-	alertrtRouter := alertrt.New(config.HTTP, config.Alert, alertMuteCache, targetCache, busiGroupCache, alertStats, ctx, externalProcessors)
+	alertrtRouter := alertrt.New(config.HTTP, config.Alert, alertMuteCache, targetCache, busiGroupCache, alertStats, ctx, externalProcessors, config.Log.Dir)
 	centerRouter := centerrt.New(config.HTTP, config.Center, config.Alert, config.Ibex,
 		cconf.Operations, dsCache, notifyConfigCache, promClients,
-		redis, sso, ctx, metas, idents, targetCache, userCache, userGroupCache, userTokenCache)
+		redis, sso, ctx, metas, idents, targetCache, userCache, userGroupCache, userTokenCache, config.Log.Dir)
 	pushgwRouter := pushgwrt.New(config.HTTP, config.Pushgw, config.Alert, targetCache, busiGroupCache, idents, metas, writers, ctx)
 
 	r := httpx.GinEngine(config.Global.RunMode, config.HTTP, configCvalCache.PrintBodyPaths, configCvalCache.PrintAccessLog)

center/router/router.go

@@ -24,11 +24,11 @@ import (
 	"github.com/ccfos/nightingale/v6/prom"
 	"github.com/ccfos/nightingale/v6/pushgw/idents"
 	"github.com/ccfos/nightingale/v6/storage"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 	"gorm.io/gorm"
 
 	"github.com/gin-gonic/gin"
 	"github.com/rakyll/statik/fs"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 	"github.com/toolkits/pkg/runner"
 )
@@ -51,6 +51,7 @@ type Router struct {
 	UserGroupCache    *memsto.UserGroupCacheType
 	UserTokenCache    *memsto.UserTokenCacheType
 	Ctx               *ctx.Context
+	LogDir            string
 
 	HeartbeatHook       HeartbeatHookFunc
 	TargetDeleteHook    models.TargetDeleteHookFunc
@@ -61,7 +62,7 @@ func New(httpConfig httpx.Config, center cconf.Center, alert aconf.Alert, ibex c
 	operations cconf.Operation, ds *memsto.DatasourceCacheType, ncc *memsto.NotifyConfigCacheType,
 	pc *prom.PromClientMap, redis storage.Redis,
 	sso *sso.SsoClient, ctx *ctx.Context, metaSet *metas.Set, idents *idents.Set,
-	tc *memsto.TargetCacheType, uc *memsto.UserCacheType, ugc *memsto.UserGroupCacheType, utc *memsto.UserTokenCacheType) *Router {
+	tc *memsto.TargetCacheType, uc *memsto.UserCacheType, ugc *memsto.UserGroupCacheType, utc *memsto.UserTokenCacheType, logDir string) *Router {
 	return &Router{
 		HTTP:                httpConfig,
 		Center:              center,
@@ -80,6 +81,7 @@ func New(httpConfig httpx.Config, center cconf.Center, alert aconf.Alert, ibex c
 		UserGroupCache:      ugc,
 		UserTokenCache:      utc,
 		Ctx:                 ctx,
+		LogDir:              logDir,
 		HeartbeatHook:       func(ident string) map[string]interface{} { return nil },
 		TargetDeleteHook:    func(tx *gorm.DB, idents []string) error { return nil },
 		AlertRuleModifyHook: func(ar *models.AlertRule) {},
@@ -368,6 +370,7 @@ func (rt *Router) Config(r *gin.Engine) {
 		// pages.GET("/alert-rules/builtin/alerts-cates", rt.auth(), rt.user(), rt.builtinAlertCateGets)
 		// pages.GET("/alert-rules/builtin/list", rt.auth(), rt.user(), rt.builtinAlertRules)
 		pages.GET("/alert-rules/callbacks", rt.auth(), rt.user(), rt.alertRuleCallbacks)
+		pages.GET("/timezones", rt.auth(), rt.user(), rt.timezonesGet)
 
 		pages.GET("/busi-groups/alert-rules", rt.auth(), rt.user(), rt.perm("/alert-rules"), rt.alertRuleGetsByGids)
 		pages.GET("/busi-group/:id/alert-rules", rt.auth(), rt.user(), rt.perm("/alert-rules"), rt.alertRuleGets)
@@ -416,6 +419,9 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.GET("/alert-cur-event/:eid", rt.alertCurEventGet)
 		pages.GET("/alert-his-event/:eid", rt.alertHisEventGet)
 		pages.GET("/event-notify-records/:eid", rt.notificationRecordList)
+		pages.GET("/event-detail/:hash", rt.eventDetailPage)
+		pages.GET("/alert-eval-detail/:id", rt.alertEvalDetailPage)
+		pages.GET("/trace-logs/:traceid", rt.traceLogsPage)
 
 		// card logic
 		pages.GET("/alert-cur-events/list", rt.auth(), rt.user(), rt.alertCurEventsList)

center/router/router_alert_aggr_view.go

@@ -4,9 +4,9 @@ import (
 	"net/http"
 
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 // no param

center/router/router_alert_cur_event.go

@@ -10,9 +10,9 @@ import (
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
 	"github.com/ccfos/nightingale/v6/pkg/strx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 )
 

center/router/router_alert_eval_detail.go

@@ -0,0 +1,168 @@
+package router
+
+import (
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"sort"
+	"strconv"
+	"strings"
+	"time"
+
+	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/loggrep"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
+
+	"github.com/gin-gonic/gin"
+)
+
+// alertEvalDetailPage renders an HTML log viewer page for alert rule evaluation logs.
+func (rt *Router) alertEvalDetailPage(c *gin.Context) {
+	id := ginx.UrlParamStr(c, "id")
+	if !loggrep.IsValidRuleID(id) {
+		c.String(http.StatusBadRequest, "invalid rule id format")
+		return
+	}
+
+	logs, instance, err := rt.getAlertEvalLogs(id)
+	if err != nil {
+		c.String(http.StatusInternalServerError, "Error: %v", err)
+		return
+	}
+
+	c.Header("Content-Type", "text/html; charset=utf-8")
+	err = loggrep.RenderAlertEvalHTML(c.Writer, loggrep.AlertEvalPageData{
+		RuleID:   id,
+		Instance: instance,
+		Logs:     logs,
+		Total:    len(logs),
+	})
+	if err != nil {
+		c.String(http.StatusInternalServerError, "render error: %v", err)
+	}
+}
+
+// alertEvalDetailJSON returns JSON for alert rule evaluation logs.
+func (rt *Router) alertEvalDetailJSON(c *gin.Context) {
+	id := ginx.UrlParamStr(c, "id")
+	if !loggrep.IsValidRuleID(id) {
+		ginx.Bomb(200, "invalid rule id format")
+	}
+
+	logs, instance, err := rt.getAlertEvalLogs(id)
+	ginx.Dangerous(err)
+
+	ginx.NewRender(c).Data(loggrep.EventDetailResp{
+		Logs:     logs,
+		Instance: instance,
+	}, nil)
+}
+
+// getAlertEvalLogs resolves the target instance(s) and retrieves alert eval logs.
+func (rt *Router) getAlertEvalLogs(id string) ([]string, string, error) {
+	ruleId, _ := strconv.ParseInt(id, 10, 64)
+	rule, err := models.AlertRuleGetById(rt.Ctx, ruleId)
+	if err != nil {
+		return nil, "", err
+	}
+	if rule == nil {
+		return nil, "", fmt.Errorf("no such alert rule")
+	}
+
+	instance := fmt.Sprintf("%s:%d", rt.Alert.Heartbeat.IP, rt.HTTP.Port)
+	keyword := fmt.Sprintf("alert_eval_%s", id)
+
+	// Get datasource IDs for this rule
+	dsIds := rt.DatasourceCache.GetIDsByDsCateAndQueries(rule.Cate, rule.DatasourceQueries)
+	if len(dsIds) == 0 {
+		// No datasources found (e.g. host rule), try local grep
+		logs, err := loggrep.GrepLogDir(rt.LogDir, keyword)
+		return logs, instance, err
+	}
+
+	// Find unique target nodes via hash ring, with DB fallback
+	nodeSet := make(map[string]struct{})
+	for _, dsId := range dsIds {
+		node, err := rt.getNodeForDatasource(dsId, id)
+		if err != nil {
+			continue
+		}
+		nodeSet[node] = struct{}{}
+	}
+
+	if len(nodeSet) == 0 {
+		// Hash ring not ready, grep locally
+		logs, err := loggrep.GrepLogDir(rt.LogDir, keyword)
+		return logs, instance, err
+	}
+
+	// Collect logs from all target nodes
+	var allLogs []string
+	var instances []string
+
+	for node := range nodeSet {
+		if node == instance {
+			logs, err := loggrep.GrepLogDir(rt.LogDir, keyword)
+			if err == nil {
+				allLogs = append(allLogs, logs...)
+				instances = append(instances, node)
+			}
+		} else {
+			logs, nodeAddr, err := rt.forwardAlertEvalDetail(node, id)
+			if err == nil {
+				allLogs = append(allLogs, logs...)
+				instances = append(instances, nodeAddr)
+			}
+		}
+	}
+
+	// Sort logs by timestamp descending
+	sort.Slice(allLogs, func(i, j int) bool {
+		return allLogs[i] > allLogs[j]
+	})
+
+	if len(allLogs) > loggrep.MaxLogLines {
+		allLogs = allLogs[:loggrep.MaxLogLines]
+	}
+
+	return allLogs, strings.Join(instances, ", "), nil
+}
+
+func (rt *Router) forwardAlertEvalDetail(node, id string) ([]string, string, error) {
+	url := fmt.Sprintf("http://%s/v1/n9e/alert-eval-detail/%s", node, id)
+	req, err := http.NewRequest("GET", url, nil)
+	if err != nil {
+		return nil, node, err
+	}
+
+	for user, pass := range rt.HTTP.APIForService.BasicAuth {
+		req.SetBasicAuth(user, pass)
+		break
+	}
+
+	client := &http.Client{Timeout: 15 * time.Second}
+	resp, err := client.Do(req)
+	if err != nil {
+		return nil, node, fmt.Errorf("forward to %s failed: %v", node, err)
+	}
+	defer resp.Body.Close()
+
+	body, err := io.ReadAll(io.LimitReader(resp.Body, 10*1024*1024)) // 10MB limit
+	if err != nil {
+		return nil, node, err
+	}
+
+	var result struct {
+		Dat loggrep.EventDetailResp `json:"dat"`
+		Err string                  `json:"err"`
+	}
+	if err := json.Unmarshal(body, &result); err != nil {
+		return nil, node, err
+	}
+	if result.Err != "" {
+		return nil, node, fmt.Errorf("%s", result.Err)
+	}
+
+	return result.Dat.Logs, result.Dat.Instance, nil
+}

center/router/router_alert_his_event.go

@@ -8,9 +8,9 @@ import (
 
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 	"golang.org/x/exp/slices"
 )

center/router/router_alert_rule.go

@@ -16,12 +16,12 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/strx"
 	"github.com/ccfos/nightingale/v6/pushgw/pconf"
 	"github.com/ccfos/nightingale/v6/pushgw/writer"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
 	"github.com/jinzhu/copier"
 	"github.com/pkg/errors"
 	"github.com/prometheus/prometheus/prompb"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/i18n"
 )
 
@@ -36,6 +36,7 @@ func (rt *Router) alertRuleGets(c *gin.Context) {
 		for i := 0; i < len(ars); i++ {
 			ars[i].FillNotifyGroups(rt.Ctx, cache)
 		}
+		models.FillUpdateByNicknames(rt.Ctx, ars)
 	}
 	ginx.NewRender(c).Data(ars, err)
 }
@@ -76,7 +77,6 @@ func (rt *Router) alertRuleGetsByGids(c *gin.Context) {
 	if err == nil {
 		cache := make(map[int64]*models.UserGroup)
 		rids := make([]int64, 0, len(ars))
-		names := make([]string, 0, len(ars))
 		for i := 0; i < len(ars); i++ {
 			ars[i].FillNotifyGroups(rt.Ctx, cache)
 
@@ -85,7 +85,6 @@ func (rt *Router) alertRuleGetsByGids(c *gin.Context) {
 			}
 
 			rids = append(rids, ars[i].Id)
-			names = append(names, ars[i].UpdateBy)
 		}
 
 		stime, etime := GetAlertCueEventTimeRange(c)
@@ -96,14 +95,7 @@ func (rt *Router) alertRuleGetsByGids(c *gin.Context) {
 			}
 		}
 
-		users := models.UserMapGet(rt.Ctx, "username in (?)", names)
-		if users != nil {
-			for i := 0; i < len(ars); i++ {
-				if user, exist := users[ars[i].UpdateBy]; exist {
-					ars[i].UpdateByNickname = user.Nickname
-				}
-			}
-		}
+		models.FillUpdateByNicknames(rt.Ctx, ars)
 	}
 	ginx.NewRender(c).Data(ars, err)
 }
@@ -135,6 +127,7 @@ func (rt *Router) alertRulesGetByService(c *gin.Context) {
 				ars[i].DatasourceIdsJson = rt.DatasourceCache.GetIDsByDsCateAndQueries(ars[i].Cate, ars[i].DatasourceQueries)
 			}
 		}
+		models.FillUpdateByNicknames(rt.Ctx, ars)
 	}
 	ginx.NewRender(c).Data(ars, err)
 }
@@ -889,3 +882,27 @@ func (rt *Router) batchAlertRuleClone(c *gin.Context) {
 
 	ginx.NewRender(c).Data(reterr, nil)
 }
+
+func (rt *Router) timezonesGet(c *gin.Context) {
+	// 返回常用时区列表（按时差去重，每个时差只保留一个代表性时区）
+	timezones := []string{
+		"UTC",
+		"Asia/Shanghai",       // UTC+8 (代表 Asia/Hong_Kong, Asia/Singapore 等)
+		"Asia/Tokyo",          // UTC+9 (代表 Asia/Seoul 等)
+		"Asia/Dubai",          // UTC+4
+		"Asia/Kolkata",        // UTC+5:30
+		"Asia/Bangkok",        // UTC+7 (代表 Asia/Jakarta 等)
+		"Europe/London",       // UTC+0 (代表 UTC)
+		"Europe/Paris",        // UTC+1 (代表 Europe/Berlin, Europe/Rome, Europe/Madrid 等)
+		"Europe/Moscow",       // UTC+3
+		"America/New_York",    // UTC-5 (代表 America/Toronto 等)
+		"America/Chicago",     // UTC-6 (代表 America/Mexico_City 等)
+		"America/Denver",      // UTC-7
+		"America/Los_Angeles", // UTC-8
+		"America/Sao_Paulo",   // UTC-3
+		"Australia/Sydney",    // UTC+10 (代表 Australia/Melbourne 等)
+		"Pacific/Auckland",    // UTC+12
+	}
+
+	ginx.NewRender(c).Data(timezones, nil)
+}

center/router/router_alert_subscribe.go

@@ -9,9 +9,9 @@ import (
 	"github.com/ccfos/nightingale/v6/alert/common"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/strx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/i18n"
 )
 
@@ -30,6 +30,7 @@ func (rt *Router) alertSubscribeGets(c *gin.Context) {
 		ginx.Dangerous(lst[i].FillDatasourceIds(rt.Ctx))
 		ginx.Dangerous(lst[i].DB2FE())
 	}
+	models.FillUpdateByNicknames(rt.Ctx, lst)
 
 	ginx.NewRender(c).Data(lst, err)
 }
@@ -66,6 +67,7 @@ func (rt *Router) alertSubscribeGetsByGids(c *gin.Context) {
 		ginx.Dangerous(lst[i].FillDatasourceIds(rt.Ctx))
 		ginx.Dangerous(lst[i].DB2FE())
 	}
+	models.FillUpdateByNicknames(rt.Ctx, lst)
 
 	ginx.NewRender(c).Data(lst, err)
 }

center/router/router_board.go

@@ -7,9 +7,9 @@ import (
 
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/strx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/i18n"
 )
 
@@ -260,6 +260,9 @@ func (rt *Router) boardGets(c *gin.Context) {
 	query := ginx.QueryStr(c, "query", "")
 
 	boards, err := models.BoardGetsByGroupId(rt.Ctx, bgid, query)
+	if err == nil {
+		models.FillUpdateByNicknames(rt.Ctx, boards)
+	}
 	ginx.NewRender(c).Data(boards, err)
 }
 
@@ -273,6 +276,9 @@ func (rt *Router) publicBoardGets(c *gin.Context) {
 	ginx.Dangerous(err)
 
 	boards, err := models.BoardGets(rt.Ctx, "", "public=1 and (public_cate in (?) or id in (?))", []int64{0, 1}, boardIds)
+	if err == nil {
+		models.FillUpdateByNicknames(rt.Ctx, boards)
+	}
 	ginx.NewRender(c).Data(boards, err)
 }
 
@@ -312,6 +318,7 @@ func (rt *Router) boardGetsByGids(c *gin.Context) {
 			boards[i].Bgids = ids
 		}
 	}
+	models.FillUpdateByNicknames(rt.Ctx, boards)
 
 	ginx.NewRender(c).Data(boards, err)
 }

center/router/router_builtin.go

@@ -8,10 +8,10 @@ import (
 	"strings"
 
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
 	"github.com/toolkits/pkg/file"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 	"github.com/toolkits/pkg/runner"
 )

center/router/router_builtin_component.go

@@ -5,9 +5,9 @@ import (
 
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"gorm.io/gorm"
 )
 

center/router/router_builtin_metric_filter.go

@@ -3,8 +3,8 @@ package router
 import (
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/prom"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 func (rt *Router) metricFilterGets(c *gin.Context) {
@@ -27,6 +27,8 @@ func (rt *Router) metricFilterGets(c *gin.Context) {
 		}
 	}
 
+	models.FillUpdateByNicknames(rt.Ctx, arr)
+
 	ginx.NewRender(c).Data(arr, err)
 }
 

center/router/router_builtin_metrics.go

@@ -7,9 +7,9 @@ import (
 
 	"github.com/ccfos/nightingale/v6/center/integration"
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/i18n"
 )
 

center/router/router_builtin_payload.go

@@ -9,8 +9,8 @@ import (
 	"github.com/BurntSushi/toml"
 	"github.com/ccfos/nightingale/v6/center/integration"
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/i18n"
 )
 

center/router/router_busi_group.go

@@ -5,9 +5,9 @@ import (
 
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/strx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 )
 
@@ -119,6 +119,9 @@ func (rt *Router) busiGroupGets(c *gin.Context) {
 	if len(lst) == 0 {
 		lst = []models.BusiGroup{}
 	}
+	if err == nil {
+		models.FillUpdateByNicknames(rt.Ctx, lst)
+	}
 
 	ginx.NewRender(c).Data(lst, err)
 }

center/router/router_captcha.go

@@ -5,9 +5,9 @@ import (
 	"time"
 
 	"github.com/ccfos/nightingale/v6/storage"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 	"github.com/gin-gonic/gin"
 	captcha "github.com/mojocn/base64Captcha"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 )
 

center/router/router_chart_share.go

@@ -5,9 +5,9 @@ import (
 
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/strx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 func (rt *Router) chartShareGets(c *gin.Context) {

center/router/router_config.go

@@ -4,9 +4,9 @@ import (
 	"encoding/json"
 
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 func (rt *Router) notifyChannelsGets(c *gin.Context) {

center/router/router_configs.go

@@ -4,9 +4,9 @@ import (
 	"time"
 
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 const EMBEDDEDDASHBOARD = "embedded-dashboards"
@@ -15,6 +15,9 @@ func (rt *Router) configsGet(c *gin.Context) {
 	prefix := ginx.QueryStr(c, "prefix", "")
 	limit := ginx.QueryInt(c, "limit", 10)
 	configs, err := models.ConfigsGets(rt.Ctx, prefix, limit, ginx.Offset(c, limit))
+	if err == nil {
+		models.FillUpdateByNicknames(rt.Ctx, configs)
+	}
 	ginx.NewRender(c).Data(configs, err)
 }
 

center/router/router_crypto.go

@@ -2,9 +2,9 @@ package router
 
 import (
 	"github.com/ccfos/nightingale/v6/pkg/secu"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 type confPropCrypto struct {

center/router/router_dash_annotation.go

@@ -7,9 +7,9 @@ import (
 
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 func checkAnnotationPermission(c *gin.Context, ctx *ctx.Context, dashboardId int64) {

center/router/router_datasource.go

@@ -15,8 +15,8 @@ import (
 	"github.com/ccfos/nightingale/v6/datasource/opensearch"
 	"github.com/ccfos/nightingale/v6/dskit/clickhouse"
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/i18n"
 	"github.com/toolkits/pkg/logger"
 )

center/router/router_datasource_db.go

@@ -6,10 +6,10 @@ import (
 	"github.com/ccfos/nightingale/v6/dscache"
 	"github.com/ccfos/nightingale/v6/dskit/types"
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
+	"github.com/ccfos/nightingale/v6/pkg/logx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
-	"github.com/toolkits/pkg/logger"
 )
 
 func (rt *Router) ShowDatabases(c *gin.Context) {
@@ -18,7 +18,7 @@ func (rt *Router) ShowDatabases(c *gin.Context) {
 
 	plug, exists := dscache.DsCache.Get(f.Cate, f.DatasourceId)
 	if !exists {
-		logger.Warningf("cluster:%d not exists", f.DatasourceId)
+		logx.Warningf(c.Request.Context(), "cluster:%d not exists", f.DatasourceId)
 		ginx.Bomb(200, "cluster not exists")
 	}
 
@@ -48,7 +48,7 @@ func (rt *Router) ShowTables(c *gin.Context) {
 
 	plug, exists := dscache.DsCache.Get(f.Cate, f.DatasourceId)
 	if !exists {
-		logger.Warningf("cluster:%d not exists", f.DatasourceId)
+		logx.Warningf(c.Request.Context(), "cluster:%d not exists", f.DatasourceId)
 		ginx.Bomb(200, "cluster not exists")
 	}
 
@@ -78,7 +78,7 @@ func (rt *Router) DescribeTable(c *gin.Context) {
 
 	plug, exists := dscache.DsCache.Get(f.Cate, f.DatasourceId)
 	if !exists {
-		logger.Warningf("cluster:%d not exists", f.DatasourceId)
+		logx.Warningf(c.Request.Context(), "cluster:%d not exists", f.DatasourceId)
 		ginx.Bomb(200, "cluster not exists")
 	}
 	// 只接受一个入参

center/router/router_embedded.go

@@ -5,14 +5,15 @@ import (
 
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 func (rt *Router) embeddedProductGets(c *gin.Context) {
 	products, err := models.EmbeddedProductGets(rt.Ctx)
 	ginx.Dangerous(err)
+	models.FillUpdateByNicknames(rt.Ctx, products)
 	// 获取当前用户可访问的Group ID 列表
 	me := c.MustGet("user").(*models.User)
 

center/router/router_es.go

@@ -3,10 +3,10 @@ package router
 import (
 	"github.com/ccfos/nightingale/v6/datasource/es"
 	"github.com/ccfos/nightingale/v6/dscache"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
+	"github.com/ccfos/nightingale/v6/pkg/logx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
-	"github.com/toolkits/pkg/logger"
 )
 
 type IndexReq struct {
@@ -34,7 +34,7 @@ func (rt *Router) QueryIndices(c *gin.Context) {
 
 	plug, exists := dscache.DsCache.Get(f.Cate, f.DatasourceId)
 	if !exists {
-		logger.Warningf("cluster:%d not exists", f.DatasourceId)
+		logx.Warningf(c.Request.Context(), "cluster:%d not exists", f.DatasourceId)
 		ginx.Bomb(200, "cluster not exists")
 	}
 
@@ -50,7 +50,7 @@ func (rt *Router) QueryFields(c *gin.Context) {
 
 	plug, exists := dscache.DsCache.Get(f.Cate, f.DatasourceId)
 	if !exists {
-		logger.Warningf("cluster:%d not exists", f.DatasourceId)
+		logx.Warningf(c.Request.Context(), "cluster:%d not exists", f.DatasourceId)
 		ginx.Bomb(200, "cluster not exists")
 	}
 
@@ -66,7 +66,7 @@ func (rt *Router) QueryESVariable(c *gin.Context) {
 
 	plug, exists := dscache.DsCache.Get(f.Cate, f.DatasourceId)
 	if !exists {
-		logger.Warningf("cluster:%d not exists", f.DatasourceId)
+		logx.Warningf(c.Request.Context(), "cluster:%d not exists", f.DatasourceId)
 		ginx.Bomb(200, "cluster not exists")
 	}
 

center/router/router_es_index_pattern.go

@@ -5,8 +5,8 @@ import (
 	"time"
 
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 // 创建 ES Index Pattern
@@ -69,6 +69,10 @@ func (rt *Router) esIndexPatternGetList(c *gin.Context) {
 		lst, err = models.EsIndexPatternGets(rt.Ctx, "")
 	}
 
+	if err == nil {
+		models.FillUpdateByNicknames(rt.Ctx, lst)
+	}
+
 	ginx.NewRender(c).Data(lst, err)
 }
 

center/router/router_event_detail.go

@@ -0,0 +1,149 @@
+package router
+
+import (
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"strconv"
+	"time"
+
+	"github.com/ccfos/nightingale/v6/alert/naming"
+	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/loggrep"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
+
+	"github.com/gin-gonic/gin"
+)
+
+// eventDetailPage renders an HTML log viewer page (for pages group).
+func (rt *Router) eventDetailPage(c *gin.Context) {
+	hash := ginx.UrlParamStr(c, "hash")
+	if !loggrep.IsValidHash(hash) {
+		c.String(http.StatusBadRequest, "invalid hash format")
+		return
+	}
+
+	logs, instance, err := rt.getEventLogs(hash)
+	if err != nil {
+		c.String(http.StatusInternalServerError, "Error: %v", err)
+		return
+	}
+
+	c.Header("Content-Type", "text/html; charset=utf-8")
+	err = loggrep.RenderHTML(c.Writer, loggrep.PageData{
+		Hash:     hash,
+		Instance: instance,
+		Logs:     logs,
+		Total:    len(logs),
+	})
+	if err != nil {
+		c.String(http.StatusInternalServerError, "render error: %v", err)
+	}
+}
+
+// eventDetailJSON returns JSON (for service group).
+func (rt *Router) eventDetailJSON(c *gin.Context) {
+	hash := ginx.UrlParamStr(c, "hash")
+	if !loggrep.IsValidHash(hash) {
+		ginx.Bomb(200, "invalid hash format")
+	}
+
+	logs, instance, err := rt.getEventLogs(hash)
+	ginx.Dangerous(err)
+
+	ginx.NewRender(c).Data(loggrep.EventDetailResp{
+		Logs:     logs,
+		Instance: instance,
+	}, nil)
+}
+
+// getNodeForDatasource returns the alert engine instance responsible for the given
+// datasource and primary key. It first checks the local hashring, and falls back
+// to querying the database for active instances if the hashring is empty
+// (e.g. when the datasource belongs to another engine cluster).
+func (rt *Router) getNodeForDatasource(datasourceId int64, pk string) (string, error) {
+	dsIdStr := strconv.FormatInt(datasourceId, 10)
+	node, err := naming.DatasourceHashRing.GetNode(dsIdStr, pk)
+	if err == nil {
+		return node, nil
+	}
+
+	// Hashring is empty for this datasource (likely belongs to another engine cluster).
+	// Query the DB for active instances.
+	servers, dbErr := models.AlertingEngineGetsInstances(rt.Ctx,
+		"datasource_id = ? and clock > ?",
+		datasourceId, time.Now().Unix()-30)
+	if dbErr != nil {
+		return "", dbErr
+	}
+	if len(servers) == 0 {
+		return "", fmt.Errorf("no active instances for datasource %d", datasourceId)
+	}
+
+	ring := naming.NewConsistentHashRing(int32(naming.NodeReplicas), servers)
+	return ring.Get(pk)
+}
+
+// getEventLogs resolves the target instance and retrieves logs.
+func (rt *Router) getEventLogs(hash string) ([]string, string, error) {
+	event, err := models.AlertHisEventGetByHash(rt.Ctx, hash)
+	if err != nil {
+		return nil, "", err
+	}
+	if event == nil {
+		return nil, "", fmt.Errorf("no such alert event")
+	}
+
+	ruleId := strconv.FormatInt(event.RuleId, 10)
+
+	instance := fmt.Sprintf("%s:%d", rt.Alert.Heartbeat.IP, rt.HTTP.Port)
+
+	node, err := rt.getNodeForDatasource(event.DatasourceId, ruleId)
+	if err != nil || node == instance {
+		// hashring not ready or target is self, handle locally
+		logs, err := loggrep.GrepLogDir(rt.LogDir, hash)
+		return logs, instance, err
+	}
+
+	// forward to the target alert instance
+	return rt.forwardEventDetail(node, hash)
+}
+
+func (rt *Router) forwardEventDetail(node, hash string) ([]string, string, error) {
+	url := fmt.Sprintf("http://%s/v1/n9e/event-detail/%s", node, hash)
+	req, err := http.NewRequest("GET", url, nil)
+	if err != nil {
+		return nil, node, err
+	}
+
+	for user, pass := range rt.HTTP.APIForService.BasicAuth {
+		req.SetBasicAuth(user, pass)
+		break
+	}
+
+	client := &http.Client{Timeout: 15 * time.Second}
+	resp, err := client.Do(req)
+	if err != nil {
+		return nil, node, fmt.Errorf("forward to %s failed: %v", node, err)
+	}
+	defer resp.Body.Close()
+
+	body, err := io.ReadAll(io.LimitReader(resp.Body, 10*1024*1024)) // 10MB limit
+	if err != nil {
+		return nil, node, err
+	}
+
+	var result struct {
+		Dat loggrep.EventDetailResp `json:"dat"`
+		Err string                  `json:"err"`
+	}
+	if err := json.Unmarshal(body, &result); err != nil {
+		return nil, node, err
+	}
+	if result.Err != "" {
+		return nil, node, fmt.Errorf("%s", result.Err)
+	}
+
+	return result.Dat.Logs, result.Dat.Instance, nil
+}

center/router/router_event_pipeline.go

@@ -8,10 +8,10 @@ import (
 
 	"github.com/ccfos/nightingale/v6/alert/pipeline/engine"
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
 	"github.com/google/uuid"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/i18n"
 	"github.com/toolkits/pkg/logger"
 )
@@ -35,6 +35,7 @@ func (rt *Router) eventPipelinesList(c *gin.Context) {
 		// 兼容处理：自动填充工作流字段
 		pipeline.FillWorkflowFields()
 	}
+	models.FillUpdateByNicknames(rt.Ctx, pipelines)
 
 	gids, err := models.MyGroupIdsMap(rt.Ctx, me.Id)
 	ginx.Dangerous(err)

center/router/router_funcs.go

@@ -7,9 +7,9 @@ import (
 
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 const defaultLimit = 300

center/router/router_heartbeat.go

@@ -15,9 +15,9 @@ import (
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
 	"github.com/ccfos/nightingale/v6/pushgw/idents"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 )
 

center/router/router_login.go

@@ -14,16 +14,16 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/dingtalk"
 	"github.com/ccfos/nightingale/v6/pkg/feishu"
 	"github.com/ccfos/nightingale/v6/pkg/ldapx"
+	"github.com/ccfos/nightingale/v6/pkg/logx"
 	"github.com/ccfos/nightingale/v6/pkg/oauth2x"
 	"github.com/ccfos/nightingale/v6/pkg/oidcx"
 	"github.com/ccfos/nightingale/v6/pkg/secu"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/dgrijalva/jwt-go"
 	"github.com/gin-gonic/gin"
 	"github.com/pelletier/go-toml/v2"
 	"github.com/pkg/errors"
-	"github.com/toolkits/pkg/ginx"
-	"github.com/toolkits/pkg/logger"
 	"gorm.io/gorm"
 )
 
@@ -37,7 +37,9 @@ type loginForm struct {
 func (rt *Router) loginPost(c *gin.Context) {
 	var f loginForm
 	ginx.BindJSON(c, &f)
-	logger.Infof("username:%s login from:%s", f.Username, c.ClientIP())
+
+	rctx := c.Request.Context()
+	logx.Infof(rctx, "username:%s login from:%s", f.Username, c.ClientIP())
 
 	if rt.HTTP.ShowCaptcha.Enable {
 		if !CaptchaVerify(f.Captchaid, f.Verifyvalue) {
@@ -50,23 +52,25 @@ func (rt *Router) loginPost(c *gin.Context) {
 	if rt.HTTP.RSA.OpenRSA {
 		decPassWord, err := secu.Decrypt(f.Password, rt.HTTP.RSA.RSAPrivateKey, rt.HTTP.RSA.RSAPassWord)
 		if err != nil {
-			logger.Errorf("RSA Decrypt failed: %v username: %s", err, f.Username)
+			logx.Errorf(rctx, "RSA Decrypt failed: %v username: %s", err, f.Username)
 			ginx.NewRender(c).Message(err)
 			return
 		}
 		authPassWord = decPassWord
 	}
 
+	reqCtx := rt.Ctx.WithContext(rctx)
+
 	var user *models.User
 	var err error
 	lc := rt.Sso.LDAP.Copy()
 	if lc.Enable {
-		user, err = ldapx.LdapLogin(rt.Ctx, f.Username, authPassWord, lc.DefaultRoles, lc.DefaultTeams, lc)
+		user, err = ldapx.LdapLogin(reqCtx, f.Username, authPassWord, lc.DefaultRoles, lc.DefaultTeams, lc)
 		if err != nil {
-			logger.Debugf("ldap login failed: %v username: %s", err, f.Username)
+			logx.Debugf(rctx, "ldap login failed: %v username: %s", err, f.Username)
 			var errLoginInN9e error
 			// to use n9e as the minimum guarantee for login
-			if user, errLoginInN9e = models.PassLogin(rt.Ctx, rt.Redis, f.Username, authPassWord); errLoginInN9e != nil {
+			if user, errLoginInN9e = models.PassLogin(reqCtx, rt.Redis, f.Username, authPassWord); errLoginInN9e != nil {
 				ginx.NewRender(c).Message("ldap login failed: %v; n9e login failed: %v", err, errLoginInN9e)
 				return
 			}
@@ -74,7 +78,7 @@ func (rt *Router) loginPost(c *gin.Context) {
 			user.RolesLst = strings.Fields(user.Roles)
 		}
 	} else {
-		user, err = models.PassLogin(rt.Ctx, rt.Redis, f.Username, authPassWord)
+		user, err = models.PassLogin(reqCtx, rt.Redis, f.Username, authPassWord)
 		ginx.Dangerous(err)
 	}
 
@@ -98,7 +102,8 @@ func (rt *Router) loginPost(c *gin.Context) {
 }
 
 func (rt *Router) logoutPost(c *gin.Context) {
-	logger.Infof("username:%s logout from:%s", c.GetString("username"), c.ClientIP())
+	rctx := c.Request.Context()
+	logx.Infof(rctx, "username:%s logout from:%s", c.GetString("username"), c.ClientIP())
 	metadata, err := rt.extractTokenMetadata(c.Request)
 	if err != nil {
 		ginx.NewRender(c, http.StatusBadRequest).Message("failed to parse jwt token")
@@ -117,7 +122,7 @@ func (rt *Router) logoutPost(c *gin.Context) {
 	// 获取用户的 id_token
 	idToken, err := rt.fetchIdToken(c.Request.Context(), user.Id)
 	if err != nil {
-		logger.Debugf("fetch id_token failed: %v, user_id: %d", err, user.Id)
+		logx.Debugf(rctx, "fetch id_token failed: %v, user_id: %d", err, user.Id)
 		idToken = "" // 如果获取失败，使用空字符串
 	}
 
@@ -220,7 +225,7 @@ func (rt *Router) refreshPost(c *gin.Context) {
 		// 注意：这里不会获取新的 id_token，只是延长 Redis 中现有 id_token 的 TTL
 		if idToken, err := rt.fetchIdToken(c.Request.Context(), userid); err == nil && idToken != "" {
 			if err := rt.saveIdToken(c.Request.Context(), userid, idToken); err != nil {
-				logger.Debugf("refresh id_token ttl failed: %v, user_id: %d", err, userid)
+				logx.Debugf(c.Request.Context(), "refresh id_token ttl failed: %v, user_id: %d", err, userid)
 			}
 		}
 
@@ -271,12 +276,13 @@ type CallbackOutput struct {
 }
 
 func (rt *Router) loginCallback(c *gin.Context) {
+	rctx := c.Request.Context()
 	code := ginx.QueryStr(c, "code", "")
 	state := ginx.QueryStr(c, "state", "")
 
-	ret, err := rt.Sso.OIDC.Callback(rt.Redis, c.Request.Context(), code, state)
+	ret, err := rt.Sso.OIDC.Callback(rt.Redis, rctx, code, state)
 	if err != nil {
-		logger.Errorf("sso_callback fail. code:%s, state:%s, get ret: %+v. error: %v", code, state, ret, err)
+		logx.Errorf(rctx, "sso_callback fail. code:%s, state:%s, get ret: %+v. error: %v", code, state, ret, err)
 		ginx.NewRender(c).Data(CallbackOutput{}, err)
 		return
 	}
@@ -299,7 +305,7 @@ func (rt *Router) loginCallback(c *gin.Context) {
 			for _, gid := range rt.Sso.OIDC.DefaultTeams {
 				err = models.UserGroupMemberAdd(rt.Ctx, gid, user.Id)
 				if err != nil {
-					logger.Errorf("user:%v UserGroupMemberAdd: %s", user, err)
+					logx.Errorf(rctx, "user:%v UserGroupMemberAdd: %s", user, err)
 				}
 			}
 		}
@@ -309,12 +315,12 @@ func (rt *Router) loginCallback(c *gin.Context) {
 	userIdentity := fmt.Sprintf("%d-%s", user.Id, user.Username)
 	ts, err := rt.createTokens(rt.HTTP.JWTAuth.SigningKey, userIdentity)
 	ginx.Dangerous(err)
-	ginx.Dangerous(rt.createAuth(c.Request.Context(), userIdentity, ts))
+	ginx.Dangerous(rt.createAuth(rctx, userIdentity, ts))
 
 	// 保存 id_token 到 Redis，用于登出时使用
 	if ret.IdToken != "" {
-		if err := rt.saveIdToken(c.Request.Context(), user.Id, ret.IdToken); err != nil {
-			logger.Errorf("save id_token failed: %v, user_id: %d", err, user.Id)
+		if err := rt.saveIdToken(rctx, user.Id, ret.IdToken); err != nil {
+			logx.Errorf(rctx, "save id_token failed: %v, user_id: %d", err, user.Id)
 		}
 	}
 
@@ -355,7 +361,7 @@ func (rt *Router) loginRedirectCas(c *gin.Context) {
 	}
 
 	if !rt.Sso.CAS.Enable {
-		logger.Error("cas is not enable")
+		logx.Errorf(c.Request.Context(), "cas is not enable")
 		ginx.NewRender(c).Data("", nil)
 		return
 	}
@@ -370,17 +376,18 @@ func (rt *Router) loginRedirectCas(c *gin.Context) {
 }
 
 func (rt *Router) loginCallbackCas(c *gin.Context) {
+	rctx := c.Request.Context()
 	ticket := ginx.QueryStr(c, "ticket", "")
 	state := ginx.QueryStr(c, "state", "")
-	ret, err := rt.Sso.CAS.ValidateServiceTicket(c.Request.Context(), ticket, state, rt.Redis)
+	ret, err := rt.Sso.CAS.ValidateServiceTicket(rctx, ticket, state, rt.Redis)
 	if err != nil {
-		logger.Errorf("ValidateServiceTicket: %s", err)
+		logx.Errorf(rctx, "ValidateServiceTicket: %s", err)
 		ginx.NewRender(c).Data("", err)
 		return
 	}
 	user, err := models.UserGet(rt.Ctx, "username=?", ret.Username)
 	if err != nil {
-		logger.Errorf("UserGet: %s", err)
+		logx.Errorf(rctx, "UserGet: %s", err)
 	}
 	ginx.Dangerous(err)
 	if user != nil {
@@ -399,10 +406,10 @@ func (rt *Router) loginCallbackCas(c *gin.Context) {
 	userIdentity := fmt.Sprintf("%d-%s", user.Id, user.Username)
 	ts, err := rt.createTokens(rt.HTTP.JWTAuth.SigningKey, userIdentity)
 	if err != nil {
-		logger.Errorf("createTokens: %s", err)
+		logx.Errorf(rctx, "createTokens: %s", err)
 	}
 	ginx.Dangerous(err)
-	ginx.Dangerous(rt.createAuth(c.Request.Context(), userIdentity, ts))
+	ginx.Dangerous(rt.createAuth(rctx, userIdentity, ts))
 
 	redirect := "/"
 	if ret.Redirect != "/login" {
@@ -475,12 +482,13 @@ func (rt *Router) loginRedirectDingTalk(c *gin.Context) {
 }
 
 func (rt *Router) loginCallbackDingTalk(c *gin.Context) {
+	rctx := c.Request.Context()
 	code := ginx.QueryStr(c, "code", "")
 	state := ginx.QueryStr(c, "state", "")
 
-	ret, err := rt.Sso.DingTalk.Callback(rt.Redis, c.Request.Context(), code, state)
+	ret, err := rt.Sso.DingTalk.Callback(rt.Redis, rctx, code, state)
 	if err != nil {
-		logger.Errorf("sso_callback DingTalk fail. code:%s, state:%s, get ret: %+v. error: %v", code, state, ret, err)
+		logx.Errorf(rctx, "sso_callback DingTalk fail. code:%s, state:%s, get ret: %+v. error: %v", code, state, ret, err)
 		ginx.NewRender(c).Data(CallbackOutput{}, err)
 		return
 	}
@@ -550,12 +558,13 @@ func (rt *Router) loginRedirectFeiShu(c *gin.Context) {
 }
 
 func (rt *Router) loginCallbackFeiShu(c *gin.Context) {
+	rctx := c.Request.Context()
 	code := ginx.QueryStr(c, "code", "")
 	state := ginx.QueryStr(c, "state", "")
 
-	ret, err := rt.Sso.FeiShu.Callback(rt.Redis, c.Request.Context(), code, state)
+	ret, err := rt.Sso.FeiShu.Callback(rt.Redis, rctx, code, state)
 	if err != nil {
-		logger.Errorf("sso_callback FeiShu fail. code:%s, state:%s, get ret: %+v. error: %v", code, state, ret, err)
+		logx.Errorf(rctx, "sso_callback FeiShu fail. code:%s, state:%s, get ret: %+v. error: %v", code, state, ret, err)
 		ginx.NewRender(c).Data(CallbackOutput{}, err)
 		return
 	}
@@ -571,12 +580,22 @@ func (rt *Router) loginCallbackFeiShu(c *gin.Context) {
 	} else {
 		user = new(models.User)
 		defaultRoles := []string{}
+		defaultUserGroups := []int64{}
 		if rt.Sso.FeiShu != nil && rt.Sso.FeiShu.FeiShuConfig != nil {
 			defaultRoles = rt.Sso.FeiShu.FeiShuConfig.DefaultRoles
+			defaultUserGroups = rt.Sso.FeiShu.FeiShuConfig.DefaultUserGroups
 		}
+
 		user.FullSsoFields(feishu.SsoTypeName, ret.Username, ret.Nickname, ret.Phone, ret.Email, defaultRoles)
-		// create user from feishu
 		ginx.Dangerous(user.Add(rt.Ctx))
+
+		if len(defaultUserGroups) > 0 {
+			err = user.AddToUserGroups(rt.Ctx, defaultUserGroups)
+			if err != nil {
+				logx.Errorf(rctx, "sso feishu add user group error %v %v", ret, err)
+			}
+		}
+
 	}
 
 	// set user login state
@@ -600,12 +619,13 @@ func (rt *Router) loginCallbackFeiShu(c *gin.Context) {
 }
 
 func (rt *Router) loginCallbackOAuth(c *gin.Context) {
+	rctx := c.Request.Context()
 	code := ginx.QueryStr(c, "code", "")
 	state := ginx.QueryStr(c, "state", "")
 
-	ret, err := rt.Sso.OAuth2.Callback(rt.Redis, c.Request.Context(), code, state)
+	ret, err := rt.Sso.OAuth2.Callback(rt.Redis, rctx, code, state)
 	if err != nil {
-		logger.Debugf("sso.callback() get ret %+v error %v", ret, err)
+		logx.Debugf(rctx, "sso.callback() get ret %+v error %v", ret, err)
 		ginx.NewRender(c).Data(CallbackOutput{}, err)
 		return
 	}

center/router/router_message_template.go

@@ -12,10 +12,10 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/slice"
 	"github.com/ccfos/nightingale/v6/pkg/strx"
 	"github.com/ccfos/nightingale/v6/pkg/tplx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
 	"github.com/google/uuid"
-	"github.com/toolkits/pkg/ginx"
 )
 
 func (rt *Router) messageTemplatesAdd(c *gin.Context) {
@@ -154,6 +154,7 @@ func (rt *Router) messageTemplatesGet(c *gin.Context) {
 
 	lst, err := models.MessageTemplatesGetBy(rt.Ctx, notifyChannelIdents)
 	ginx.Dangerous(err)
+	models.FillUpdateByNicknames(rt.Ctx, lst)
 
 	if me.IsAdmin() {
 		ginx.NewRender(c).Data(lst, nil)

center/router/router_metric_desc.go

@@ -2,9 +2,9 @@ package router
 
 import (
 	"github.com/ccfos/nightingale/v6/center/cconf"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 func (rt *Router) metricsDescGetFile(c *gin.Context) {

center/router/router_metric_view.go

@@ -4,9 +4,9 @@ import (
 	"net/http"
 
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 // no param

center/router/router_mute.go

@@ -9,9 +9,9 @@ import (
 	"github.com/ccfos/nightingale/v6/alert/mute"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/strx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/i18n"
 )
 
@@ -22,6 +22,9 @@ func (rt *Router) alertMuteGetsByBG(c *gin.Context) {
 	query := ginx.QueryStr(c, "query", "")
 	expired := ginx.QueryInt(c, "expired", -1)
 	lst, err := models.AlertMuteGets(rt.Ctx, prods, bgid, -1, expired, query)
+	if err == nil {
+		models.FillUpdateByNicknames(rt.Ctx, lst)
+	}
 
 	ginx.NewRender(c).Data(lst, err)
 }
@@ -47,6 +50,9 @@ func (rt *Router) alertMuteGetsByGids(c *gin.Context) {
 	}
 
 	lst, err := models.AlertMuteGetsByBGIds(rt.Ctx, gids)
+	if err == nil {
+		models.FillUpdateByNicknames(rt.Ctx, lst)
+	}
 
 	ginx.NewRender(c).Data(lst, err)
 }
@@ -58,6 +64,9 @@ func (rt *Router) alertMuteGets(c *gin.Context) {
 	disabled := ginx.QueryInt(c, "disabled", -1)
 	expired := ginx.QueryInt(c, "expired", -1)
 	lst, err := models.AlertMuteGets(rt.Ctx, prods, bgid, disabled, expired, query)
+	if err == nil {
+		models.FillUpdateByNicknames(rt.Ctx, lst)
+	}
 
 	ginx.NewRender(c).Data(lst, err)
 }

center/router/router_mw.go

@@ -11,11 +11,11 @@ import (
 
 	"github.com/ccfos/nightingale/v6/center/cstats"
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
 	"github.com/golang-jwt/jwt"
 	"github.com/google/uuid"
-	"github.com/toolkits/pkg/ginx"
 )
 
 const (

center/router/router_notification_record.go

@@ -6,9 +6,9 @@ import (
 	"github.com/ccfos/nightingale/v6/alert/sender"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 )
 

center/router/router_notify_channel.go

@@ -11,8 +11,8 @@ import (
 	"time"
 
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 func (rt *Router) notifyChannelsAdd(c *gin.Context) {
@@ -118,6 +118,9 @@ func (rt *Router) notifyChannelGetBy(c *gin.Context) {
 
 func (rt *Router) notifyChannelsGet(c *gin.Context) {
 	lst, err := models.NotifyChannelsGet(rt.Ctx, "", nil)
+	if err == nil {
+		models.FillUpdateByNicknames(rt.Ctx, lst)
+	}
 	ginx.NewRender(c).Data(lst, err)
 }
 

center/router/router_notify_config.go

@@ -10,10 +10,10 @@ import (
 	"github.com/ccfos/nightingale/v6/memsto"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/tplx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
 	"github.com/pelletier/go-toml/v2"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/str"
 )
 

center/router/router_notify_rule.go

@@ -10,9 +10,9 @@ import (
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
 	"github.com/ccfos/nightingale/v6/pkg/slice"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 )
 
@@ -118,6 +118,7 @@ func (rt *Router) notifyRulesGet(c *gin.Context) {
 
 	lst, err := models.NotifyRulesGet(rt.Ctx, "", nil)
 	ginx.Dangerous(err)
+	models.FillUpdateByNicknames(rt.Ctx, lst)
 	if me.IsAdmin() {
 		ginx.NewRender(c).Data(lst, nil)
 		return
@@ -221,7 +222,7 @@ func SendNotifyChannelMessage(ctx *ctx.Context, userCache *memsto.UserCacheType,
 				return "", fmt.Errorf("failed to send flashduty notify: %v", err)
 			}
 		}
-		logger.Infof("channel_name: %v, event:%+v, tplContent:%s, customParams:%v, respBody: %v, err: %v", notifyChannel.Name, events[0], tplContent, customParams, resp, err)
+		logger.Infof("channel_name: %v, event:%s, tplContent:%s, customParams:%v, respBody: %v, err: %v", notifyChannel.Name, events[0].Hash, tplContent, customParams, resp, err)
 		return resp, nil
 	case "pagerduty":
 		client, err := models.GetHTTPClient(notifyChannel)
@@ -235,7 +236,7 @@ func SendNotifyChannelMessage(ctx *ctx.Context, userCache *memsto.UserCacheType,
 				return "", fmt.Errorf("failed to send pagerduty notify: %v", err)
 			}
 		}
-		logger.Infof("channel_name: %v, event:%+v, tplContent:%s, customParams:%v, respBody: %v, err: %v", notifyChannel.Name, events[0], tplContent, customParams, resp, err)
+		logger.Infof("channel_name: %v, event:%s, tplContent:%s, customParams:%v, respBody: %v, err: %v", notifyChannel.Name, events[0].Hash, tplContent, customParams, resp, err)
 		return resp, nil
 	case "http":
 		client, err := models.GetHTTPClient(notifyChannel)
@@ -253,7 +254,7 @@ func SendNotifyChannelMessage(ctx *ctx.Context, userCache *memsto.UserCacheType,
 
 		if dispatch.NeedBatchContacts(notifyChannel.RequestConfig.HTTPRequestConfig) || len(sendtos) == 0 {
 			resp, err = notifyChannel.SendHTTP(events, tplContent, customParams, sendtos, client)
-			logger.Infof("channel_name: %v, event:%+v, sendtos:%+v, tplContent:%s, customParams:%v, respBody: %v, err: %v", notifyChannel.Name, events[0], sendtos, tplContent, customParams, resp, err)
+			logger.Infof("channel_name: %v, event:%s, sendtos:%+v, tplContent:%s, customParams:%v, respBody: %v, err: %v", notifyChannel.Name, events[0].Hash, sendtos, tplContent, customParams, resp, err)
 			if err != nil {
 				return "", fmt.Errorf("failed to send http notify: %v", err)
 			}
@@ -261,7 +262,7 @@ func SendNotifyChannelMessage(ctx *ctx.Context, userCache *memsto.UserCacheType,
 		} else {
 			for i := range sendtos {
 				resp, err = notifyChannel.SendHTTP(events, tplContent, customParams, []string{sendtos[i]}, client)
-				logger.Infof("channel_name: %v, event:%+v,  tplContent:%s, customParams:%v, sendto:%+v, respBody: %v, err: %v", notifyChannel.Name, events[0], tplContent, customParams, sendtos[i], resp, err)
+				logger.Infof("channel_name: %v, event:%s,  tplContent:%s, customParams:%v, sendto:%+v, respBody: %v, err: %v", notifyChannel.Name, events[0].Hash, tplContent, customParams, sendtos[i], resp, err)
 				if err != nil {
 					return "", fmt.Errorf("failed to send http notify: %v", err)
 				}
@@ -280,7 +281,7 @@ func SendNotifyChannelMessage(ctx *ctx.Context, userCache *memsto.UserCacheType,
 		return resp, nil
 	case "script":
 		resp, _, err := notifyChannel.SendScript(events, tplContent, customParams, sendtos)
-		logger.Infof("channel_name: %v, event:%+v, tplContent:%s, customParams:%v, respBody: %v, err: %v", notifyChannel.Name, events[0], tplContent, customParams, resp, err)
+		logger.Infof("channel_name: %v, event:%s, tplContent:%s, customParams:%v, respBody: %v, err: %v", notifyChannel.Name, events[0].Hash, tplContent, customParams, resp, err)
 		return resp, err
 	default:
 		logger.Errorf("unsupported request type: %v", notifyChannel.RequestType)

center/router/router_notify_tpl.go

@@ -11,9 +11,9 @@ import (
 	"github.com/ccfos/nightingale/v6/center/cconf"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/tplx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/str"
 )
 
@@ -25,11 +25,14 @@ func (rt *Router) notifyTplGets(c *gin.Context) {
 	m[models.EmailSubject] = struct{}{}
 
 	lst, err := models.NotifyTplGets(rt.Ctx)
+	ginx.Dangerous(err)
+
 	for i := 0; i < len(lst); i++ {
 		if _, exists := m[lst[i].Channel]; exists {
 			lst[i].BuiltIn = true
 		}
 	}
+	models.FillUpdateByNicknames(rt.Ctx, lst)
 
 	ginx.NewRender(c).Data(lst, err)
 }
@@ -200,6 +203,9 @@ func (rt *Router) messageTemplateGets(c *gin.Context) {
 	ident := ginx.QueryStr(c, "ident", "")
 
 	tpls, err := models.MessageTemplateGets(rt.Ctx, id, name, ident)
+	if err == nil {
+		models.FillUpdateByNicknames(rt.Ctx, tpls)
+	}
 
 	ginx.NewRender(c).Data(tpls, err)
 }

center/router/router_opensearch.go

@@ -3,9 +3,9 @@ package router
 import (
 	"github.com/ccfos/nightingale/v6/datasource/opensearch"
 	"github.com/ccfos/nightingale/v6/dscache"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 )
 

center/router/router_proxy.go

@@ -12,12 +12,13 @@ import (
 	"sync"
 	"time"
 
+	"github.com/ccfos/nightingale/v6/pkg/logx"
 	"github.com/ccfos/nightingale/v6/pkg/poster"
 	pkgprom "github.com/ccfos/nightingale/v6/pkg/prom"
 	"github.com/ccfos/nightingale/v6/prom"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 	"github.com/gin-gonic/gin"
 	"github.com/prometheus/common/model"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 	"github.com/toolkits/pkg/net/httplib"
 )
@@ -38,15 +39,16 @@ func (rt *Router) promBatchQueryRange(c *gin.Context) {
 	var f BatchQueryForm
 	ginx.Dangerous(c.BindJSON(&f))
 
-	lst, err := PromBatchQueryRange(rt.PromClients, f)
+	lst, err := PromBatchQueryRange(c.Request.Context(), rt.PromClients, f)
 	ginx.NewRender(c).Data(lst, err)
 }
 
-func PromBatchQueryRange(pc *prom.PromClientMap, f BatchQueryForm) ([]model.Value, error) {
+func PromBatchQueryRange(ctx context.Context, pc *prom.PromClientMap, f BatchQueryForm) ([]model.Value, error) {
 	var lst []model.Value
 
 	cli := pc.GetCli(f.DatasourceId)
 	if cli == nil {
+		logx.Warningf(ctx, "no such datasource id: %d", f.DatasourceId)
 		return lst, fmt.Errorf("no such datasource id: %d", f.DatasourceId)
 	}
 
@@ -57,8 +59,9 @@ func PromBatchQueryRange(pc *prom.PromClientMap, f BatchQueryForm) ([]model.Valu
 			Step:  time.Duration(item.Step) * time.Second,
 		}
 
-		resp, _, err := cli.QueryRange(context.Background(), item.Query, r)
+		resp, _, err := cli.QueryRange(ctx, item.Query, r)
 		if err != nil {
+			logx.Warningf(ctx, "query range error: query:%s err:%v", item.Query, err)
 			return lst, err
 		}
 
@@ -81,22 +84,23 @@ func (rt *Router) promBatchQueryInstant(c *gin.Context) {
 	var f BatchInstantForm
 	ginx.Dangerous(c.BindJSON(&f))
 
-	lst, err := PromBatchQueryInstant(rt.PromClients, f)
+	lst, err := PromBatchQueryInstant(c.Request.Context(), rt.PromClients, f)
 	ginx.NewRender(c).Data(lst, err)
 }
 
-func PromBatchQueryInstant(pc *prom.PromClientMap, f BatchInstantForm) ([]model.Value, error) {
+func PromBatchQueryInstant(ctx context.Context, pc *prom.PromClientMap, f BatchInstantForm) ([]model.Value, error) {
 	var lst []model.Value
 
 	cli := pc.GetCli(f.DatasourceId)
 	if cli == nil {
-		logger.Warningf("no such datasource id: %d", f.DatasourceId)
+		logx.Warningf(ctx, "no such datasource id: %d", f.DatasourceId)
 		return lst, fmt.Errorf("no such datasource id: %d", f.DatasourceId)
 	}
 
 	for _, item := range f.Queries {
-		resp, _, err := cli.Query(context.Background(), item.Query, time.Unix(item.Time, 0))
+		resp, _, err := cli.Query(ctx, item.Query, time.Unix(item.Time, 0))
 		if err != nil {
+			logx.Warningf(ctx, "query instant error: query:%s err:%v", item.Query, err)
 			return lst, err
 		}
 
@@ -189,7 +193,7 @@ func (rt *Router) dsProxy(c *gin.Context) {
 
 	modifyResponse := func(r *http.Response) error {
 		if r.StatusCode == http.StatusUnauthorized {
-			logger.Warningf("proxy path:%s unauthorized access ", c.Request.URL.Path)
+			logx.Warningf(c.Request.Context(), "proxy path:%s unauthorized access ", c.Request.URL.Path)
 			return fmt.Errorf("unauthorized access")
 		}
 

center/router/router_query.go

@@ -8,9 +8,9 @@ import (
 	"github.com/ccfos/nightingale/v6/alert/eval"
 	"github.com/ccfos/nightingale/v6/dscache"
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/logx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
-	"github.com/toolkits/pkg/logger"
 )
 
 type CheckDsPermFunc func(c *gin.Context, dsId int64, cate string, q interface{}) bool
@@ -47,6 +47,7 @@ func QueryLogBatchConcurrently(anonymousAccess bool, ctx *gin.Context, f QueryFr
 	var mu sync.Mutex
 	var wg sync.WaitGroup
 	var errs []error
+	rctx := ctx.Request.Context()
 
 	for _, q := range f.Queries {
 		if !anonymousAccess && !CheckDsPerm(ctx, q.Did, q.DsCate, q) {
@@ -55,14 +56,14 @@ func QueryLogBatchConcurrently(anonymousAccess bool, ctx *gin.Context, f QueryFr
 
 		plug, exists := dscache.DsCache.Get(q.DsCate, q.Did)
 		if !exists {
-			logger.Warningf("cluster:%d not exists query:%+v", q.Did, q)
+			logx.Warningf(rctx, "cluster:%d not exists query:%+v", q.Did, q)
 			return LogResp{}, fmt.Errorf("cluster not exists")
 		}
 
 		// 根据数据源类型对 Query 进行模板渲染处理
 		err := eval.ExecuteQueryTemplate(q.DsCate, q.Query, nil)
 		if err != nil {
-			logger.Warningf("query template execute error: %v", err)
+			logx.Warningf(rctx, "query template execute error: %v", err)
 			return LogResp{}, fmt.Errorf("query template execute error: %v", err)
 		}
 
@@ -70,12 +71,12 @@ func QueryLogBatchConcurrently(anonymousAccess bool, ctx *gin.Context, f QueryFr
 		go func(query Query) {
 			defer wg.Done()
 
-			data, total, err := plug.QueryLog(ctx.Request.Context(), query.Query)
+			data, total, err := plug.QueryLog(rctx, query.Query)
 			mu.Lock()
 			defer mu.Unlock()
 			if err != nil {
 				errMsg := fmt.Sprintf("query data error: %v query:%v\n ", err, query)
-				logger.Warningf(errMsg)
+				logx.Warningf(rctx, "%s", errMsg)
 				errs = append(errs, err)
 				return
 			}
@@ -121,6 +122,7 @@ func QueryDataConcurrently(anonymousAccess bool, ctx *gin.Context, f models.Quer
 	var mu sync.Mutex
 	var wg sync.WaitGroup
 	var errs []error
+	rctx := ctx.Request.Context()
 
 	for _, q := range f.Queries {
 		if !anonymousAccess && !CheckDsPerm(ctx, f.DatasourceId, f.Cate, q) {
@@ -129,7 +131,7 @@ func QueryDataConcurrently(anonymousAccess bool, ctx *gin.Context, f models.Quer
 
 		plug, exists := dscache.DsCache.Get(f.Cate, f.DatasourceId)
 		if !exists {
-			logger.Warningf("cluster:%d not exists", f.DatasourceId)
+			logx.Warningf(rctx, "cluster:%d not exists", f.DatasourceId)
 			return nil, fmt.Errorf("cluster not exists")
 		}
 
@@ -137,16 +139,16 @@ func QueryDataConcurrently(anonymousAccess bool, ctx *gin.Context, f models.Quer
 		go func(query interface{}) {
 			defer wg.Done()
 
-			data, err := plug.QueryData(ctx.Request.Context(), query)
+			data, err := plug.QueryData(rctx, query)
 			if err != nil {
-				logger.Warningf("query data error: req:%+v err:%v", query, err)
+				logx.Warningf(rctx, "query data error: req:%+v err:%v", query, err)
 				mu.Lock()
 				errs = append(errs, err)
 				mu.Unlock()
 				return
 			}
 
-			logger.Debugf("query data: req:%+v resp:%+v", query, data)
+			logx.Debugf(rctx, "query data: req:%+v resp:%+v", query, data)
 			mu.Lock()
 			resp = append(resp, data...)
 			mu.Unlock()
@@ -192,6 +194,7 @@ func QueryLogConcurrently(anonymousAccess bool, ctx *gin.Context, f models.Query
 	var mu sync.Mutex
 	var wg sync.WaitGroup
 	var errs []error
+	rctx := ctx.Request.Context()
 
 	for _, q := range f.Queries {
 		if !anonymousAccess && !CheckDsPerm(ctx, f.DatasourceId, f.Cate, q) {
@@ -200,7 +203,7 @@ func QueryLogConcurrently(anonymousAccess bool, ctx *gin.Context, f models.Query
 
 		plug, exists := dscache.DsCache.Get(f.Cate, f.DatasourceId)
 		if !exists {
-			logger.Warningf("cluster:%d not exists query:%+v", f.DatasourceId, f)
+			logx.Warningf(rctx, "cluster:%d not exists query:%+v", f.DatasourceId, f)
 			return LogResp{}, fmt.Errorf("cluster not exists")
 		}
 
@@ -208,11 +211,11 @@ func QueryLogConcurrently(anonymousAccess bool, ctx *gin.Context, f models.Query
 		go func(query interface{}) {
 			defer wg.Done()
 
-			data, total, err := plug.QueryLog(ctx.Request.Context(), query)
-			logger.Debugf("query log: req:%+v resp:%+v", query, data)
+			data, total, err := plug.QueryLog(rctx, query)
+			logx.Debugf(rctx, "query log: req:%+v resp:%+v", query, data)
 			if err != nil {
 				errMsg := fmt.Sprintf("query data error: %v query:%v\n ", err, query)
-				logger.Warningf(errMsg)
+				logx.Warningf(rctx, "%s", errMsg)
 				mu.Lock()
 				errs = append(errs, err)
 				mu.Unlock()
@@ -250,6 +253,7 @@ func (rt *Router) QueryLogV2(c *gin.Context) {
 func (rt *Router) QueryLog(c *gin.Context) {
 	var f models.QueryParam
 	ginx.BindJSON(c, &f)
+	rctx := c.Request.Context()
 
 	var resp []interface{}
 	for _, q := range f.Queries {
@@ -259,13 +263,13 @@ func (rt *Router) QueryLog(c *gin.Context) {
 
 		plug, exists := dscache.DsCache.Get("elasticsearch", f.DatasourceId)
 		if !exists {
-			logger.Warningf("cluster:%d not exists", f.DatasourceId)
+			logx.Warningf(rctx, "cluster:%d not exists", f.DatasourceId)
 			ginx.Bomb(200, "cluster not exists")
 		}
 
-		data, _, err := plug.QueryLog(c.Request.Context(), q)
+		data, _, err := plug.QueryLog(rctx, q)
 		if err != nil {
-			logger.Warningf("query data error: %v", err)
+			logx.Warningf(rctx, "query data error: %v", err)
 			ginx.Bomb(200, "err:%v", err)
 			continue
 		}

center/router/router_recording_rule.go

@@ -7,14 +7,17 @@ import (
 
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/strx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 func (rt *Router) recordingRuleGets(c *gin.Context) {
 	busiGroupId := ginx.UrlParamInt64(c, "id")
 	ars, err := models.RecordingRuleGets(rt.Ctx, busiGroupId)
+	if err == nil {
+		models.FillUpdateByNicknames(rt.Ctx, ars)
+	}
 	ginx.NewRender(c).Data(ars, err)
 }
 
@@ -39,6 +42,9 @@ func (rt *Router) recordingRuleGetsByGids(c *gin.Context) {
 	}
 
 	ars, err := models.RecordingRuleGetsByBGIds(rt.Ctx, gids)
+	if err == nil {
+		models.FillUpdateByNicknames(rt.Ctx, ars)
+	}
 	ginx.NewRender(c).Data(ars, err)
 }
 

center/router/router_role.go

@@ -6,9 +6,9 @@ import (
 
 	"github.com/ccfos/nightingale/v6/center/cconf"
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 func (rt *Router) rolesGets(c *gin.Context) {

center/router/router_role_operation.go

@@ -5,8 +5,8 @@ import (
 
 	"github.com/ccfos/nightingale/v6/center/cconf"
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/i18n"
 )
 

center/router/router_saved_view.go

@@ -5,9 +5,9 @@ import (
 
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/slice"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 func (rt *Router) savedViewGets(c *gin.Context) {
@@ -20,6 +20,7 @@ func (rt *Router) savedViewGets(c *gin.Context) {
 		ginx.NewRender(c).Data(nil, err)
 		return
 	}
+	models.FillUpdateByNicknames(rt.Ctx, lst)
 
 	userGids, err := models.MyGroupIds(rt.Ctx, me.Id)
 	if err != nil {

center/router/router_self.go

@@ -5,10 +5,10 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/flashduty"
 	"github.com/ccfos/nightingale/v6/pkg/ormx"
 	"github.com/ccfos/nightingale/v6/pkg/secu"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 	"github.com/google/uuid"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 )
 

center/router/router_server.go

@@ -4,9 +4,9 @@ import (
 	"time"
 
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 func (rt *Router) serversGet(c *gin.Context) {

center/router/router_source_token.go

@@ -5,10 +5,10 @@ import (
 	"time"
 
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 	"github.com/google/uuid"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 // sourceTokenAdd 生成新的源令牌

center/router/router_target.go

@@ -13,10 +13,10 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/strx"
 	"github.com/ccfos/nightingale/v6/pushgw/idents"
 	"github.com/ccfos/nightingale/v6/storage"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
 	"github.com/prometheus/common/model"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 )
 

center/router/router_task.go

@@ -7,9 +7,9 @@ import (
 	"github.com/ccfos/nightingale/v6/alert/sender"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/strx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/i18n"
 )
 

center/router/router_task_tpl.go

@@ -8,9 +8,9 @@ import (
 
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/strx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/i18n"
 	"github.com/toolkits/pkg/str"
 )
@@ -25,6 +25,7 @@ func (rt *Router) taskTplGets(c *gin.Context) {
 
 	list, err := models.TaskTplGets(rt.Ctx, []int64{groupId}, query, limit, ginx.Offset(c, limit))
 	ginx.Dangerous(err)
+	models.FillUpdateByNicknames(rt.Ctx, list)
 
 	ginx.NewRender(c).Data(gin.H{
 		"total": total,
@@ -60,6 +61,7 @@ func (rt *Router) taskTplGetsByGids(c *gin.Context) {
 
 	list, err := models.TaskTplGets(rt.Ctx, gids, query, limit, ginx.Offset(c, limit))
 	ginx.Dangerous(err)
+	models.FillUpdateByNicknames(rt.Ctx, list)
 
 	ginx.NewRender(c).Data(gin.H{
 		"total": total,

center/router/router_tdengine.go

@@ -8,8 +8,8 @@ import (
 	"github.com/ccfos/nightingale/v6/datasource/tdengine"
 	"github.com/ccfos/nightingale/v6/dscache"
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 type databasesQueryForm struct {

center/router/router_trace_logs.go

@@ -0,0 +1,136 @@
+package router
+
+import (
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"time"
+
+	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
+	"github.com/ccfos/nightingale/v6/pkg/loggrep"
+	"github.com/toolkits/pkg/logger"
+
+	"github.com/gin-gonic/gin"
+)
+
+// traceLogsPage renders an HTML log viewer page for trace logs.
+func (rt *Router) traceLogsPage(c *gin.Context) {
+	traceId := ginx.UrlParamStr(c, "traceid")
+	if !loggrep.IsValidTraceID(traceId) {
+		c.String(http.StatusBadRequest, "invalid trace id format")
+		return
+	}
+
+	logs, instance, err := rt.getTraceLogs(traceId)
+	if err != nil {
+		c.String(http.StatusInternalServerError, "Error: %v", err)
+		return
+	}
+
+	c.Header("Content-Type", "text/html; charset=utf-8")
+	err = loggrep.RenderTraceLogsHTML(c.Writer, loggrep.TraceLogsPageData{
+		TraceID:  traceId,
+		Instance: instance,
+		Logs:     logs,
+		Total:    len(logs),
+	})
+	if err != nil {
+		c.String(http.StatusInternalServerError, "render error: %v", err)
+	}
+}
+
+// traceLogsJSON returns JSON for trace logs.
+func (rt *Router) traceLogsJSON(c *gin.Context) {
+	traceId := ginx.UrlParamStr(c, "traceid")
+	if !loggrep.IsValidTraceID(traceId) {
+		ginx.Bomb(200, "invalid trace id format")
+	}
+
+	logs, instance, err := rt.getTraceLogs(traceId)
+	ginx.Dangerous(err)
+
+	ginx.NewRender(c).Data(loggrep.EventDetailResp{
+		Logs:     logs,
+		Instance: instance,
+	}, nil)
+}
+
+// getTraceLogs finds the same-engine instances and queries each one
+// until trace logs are found. Trace logs belong to a single instance.
+func (rt *Router) getTraceLogs(traceId string) ([]string, string, error) {
+	keyword := "trace_id=" + traceId
+	instance := fmt.Sprintf("%s:%d", rt.Alert.Heartbeat.IP, rt.HTTP.Port)
+	engineName := rt.Alert.Heartbeat.EngineName
+
+	// try local first
+	logs, err := loggrep.GrepLatestLogFiles(rt.LogDir, keyword)
+	if err == nil && len(logs) > 0 {
+		return logs, instance, nil
+	}
+
+	// find all instances with the same engineName
+	servers, err := models.AlertingEngineGetsInstances(rt.Ctx,
+		"engine_cluster = ? and clock > ?",
+		engineName, time.Now().Unix()-30)
+	if err != nil {
+		return nil, "", err
+	}
+
+	// loop through remote instances until we find logs
+	for _, node := range servers {
+		if node == instance {
+			continue // already tried local
+		}
+
+		logs, nodeAddr, err := rt.forwardTraceLogs(node, traceId)
+		if err != nil {
+			logger.Errorf("forwardTraceLogs failed: %v", err)
+			continue
+		}
+		if len(logs) > 0 {
+			return logs, nodeAddr, nil
+		}
+	}
+
+	return nil, instance, nil
+}
+
+func (rt *Router) forwardTraceLogs(node, traceId string) ([]string, string, error) {
+	url := fmt.Sprintf("http://%s/v1/n9e/trace-logs/%s", node, traceId)
+	req, err := http.NewRequest("GET", url, nil)
+	if err != nil {
+		return nil, node, err
+	}
+
+	for user, pass := range rt.HTTP.APIForService.BasicAuth {
+		req.SetBasicAuth(user, pass)
+		break
+	}
+
+	client := &http.Client{Timeout: 15 * time.Second}
+	resp, err := client.Do(req)
+	if err != nil {
+		return nil, node, fmt.Errorf("forward to %s failed: %v", node, err)
+	}
+	defer resp.Body.Close()
+
+	body, err := io.ReadAll(io.LimitReader(resp.Body, 10*1024*1024))
+	if err != nil {
+		return nil, node, err
+	}
+
+	var result struct {
+		Dat loggrep.EventDetailResp `json:"dat"`
+		Err string                  `json:"err"`
+	}
+	if err := json.Unmarshal(body, &result); err != nil {
+		return nil, node, err
+	}
+	if result.Err != "" {
+		return nil, node, fmt.Errorf("%s", result.Err)
+	}
+
+	return result.Dat.Logs, result.Dat.Instance, nil
+}

center/router/router_user.go

@@ -9,9 +9,9 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/flashduty"
 	"github.com/ccfos/nightingale/v6/pkg/ormx"
 	"github.com/ccfos/nightingale/v6/pkg/secu"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 	"gorm.io/gorm"
 )

center/router/router_user_group.go

@@ -7,9 +7,9 @@ import (
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/flashduty"
 	"github.com/ccfos/nightingale/v6/pkg/strx"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 )
 
@@ -27,6 +27,9 @@ func (rt *Router) userGroupGets(c *gin.Context) {
 
 	me := c.MustGet("user").(*models.User)
 	lst, err := me.UserGroups(rt.Ctx, limit, query)
+	if err == nil {
+		models.FillUpdateByNicknames(rt.Ctx, lst)
+	}
 
 	ginx.NewRender(c).Data(lst, err)
 }

center/router/router_user_variable_config.go

@@ -5,9 +5,9 @@ import (
 	"time"
 
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
 	"github.com/gin-gonic/gin"
-	"github.com/toolkits/pkg/ginx"
 )
 
 func (rt *Router) userVariableConfigGets(context *gin.Context) {

cmd/edge/edge.go

@@ -87,7 +87,7 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 		alert.Start(config.Alert, config.Pushgw, syncStats, alertStats, externalProcessors, targetCache, busiGroupCache, alertMuteCache,
 			alertRuleCache, notifyConfigCache, taskTplsCache, dsCache, ctx, promClients, userCache, userGroupCache, notifyRuleCache, notifyChannelCache, messageTemplateCache, configCvalCache)
 
-		alertrtRouter := alertrt.New(config.HTTP, config.Alert, alertMuteCache, targetCache, busiGroupCache, alertStats, ctx, externalProcessors)
+		alertrtRouter := alertrt.New(config.HTTP, config.Alert, alertMuteCache, targetCache, busiGroupCache, alertStats, ctx, externalProcessors, config.Log.Dir)
 
 		alertrtRouter.Config(r)
 

datasource/ck/clickhouse.go

@@ -12,6 +12,8 @@ import (
 
 	"github.com/mitchellh/mapstructure"
 	"github.com/toolkits/pkg/logger"
+
+	"github.com/ccfos/nightingale/v6/pkg/logx"
 )
 
 const (
@@ -178,14 +180,9 @@ func (c *Clickhouse) QueryData(ctx context.Context, query interface{}) ([]models
 
 	rows, err := c.QueryTimeseries(ctx, ckQueryParam)
 	if err != nil {
-		logger.Warningf("query:%+v get data err:%v", ckQueryParam, err)
+		logx.Warningf(ctx, "query:%+v get data err:%v", ckQueryParam, err)
 		return nil, err
 	}
-
-	if err != nil {
-		logger.Warningf("query:%+v get data err:%v", ckQueryParam, err)
-		return []models.DataResp{}, err
-	}
 	data := make([]models.DataResp, 0)
 	for i := range rows {
 		data = append(data, models.DataResp{
@@ -214,7 +211,7 @@ func (c *Clickhouse) QueryLog(ctx context.Context, query interface{}) ([]interfa
 
 	rows, err := c.Query(ctx, ckQueryParam)
 	if err != nil {
-		logger.Warningf("query:%+v get data err:%v", ckQueryParam, err)
+		logx.Warningf(ctx, "query:%+v get data err:%v", ckQueryParam, err)
 		return nil, 0, err
 	}
 

datasource/commons/eslike/eslike.go

@@ -17,6 +17,7 @@ import (
 
 	"github.com/ccfos/nightingale/v6/memsto"
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/logx"
 )
 
 type FixedField string
@@ -390,8 +391,8 @@ func QueryData(ctx context.Context, queryParam interface{}, cliTimeout int64, ve
 	now := time.Now().Unix()
 	var start, end int64
 	if param.End != 0 && param.Start != 0 {
-		end = param.End - param.End%param.Interval
-		start = param.Start - param.Start%param.Interval
+		end = param.End
+		start = param.Start
 	} else {
 		end = now
 		start = end - param.Interval
@@ -543,7 +544,7 @@ func QueryData(ctx context.Context, queryParam interface{}, cliTimeout int64, ve
 
 	source, _ := queryString.Source()
 	b, _ := json.Marshal(source)
-	logger.Debugf("query_data q:%+v indexArr:%+v tsAggr:%+v query_string:%s", param, indexArr, tsAggr, string(b))
+	logx.Debugf(ctx, "query_data q:%+v indexArr:%+v tsAggr:%+v query_string:%s", param, indexArr, tsAggr, string(b))
 
 	searchSource := elastic.NewSearchSource().
 		Query(queryString).
@@ -551,29 +552,29 @@ func QueryData(ctx context.Context, queryParam interface{}, cliTimeout int64, ve
 
 	searchSourceString, err := searchSource.Source()
 	if err != nil {
-		logger.Warningf("query_data searchSource:%s to string error:%v", searchSourceString, err)
+		logx.Warningf(ctx, "query_data searchSource:%s to string error:%v", searchSourceString, err)
 	}
 
 	jsonSearchSource, err := json.Marshal(searchSourceString)
 	if err != nil {
-		logger.Warningf("query_data searchSource:%s to json error:%v", searchSourceString, err)
+		logx.Warningf(ctx, "query_data searchSource:%s to json error:%v", searchSourceString, err)
 	}
 
 	result, err := search(ctx, indexArr, searchSource, param.Timeout, param.MaxShard)
 	if err != nil {
-		logger.Warningf("query_data searchSource:%s query_data error:%v", searchSourceString, err)
+		logx.Warningf(ctx, "query_data searchSource:%s query_data error:%v", searchSourceString, err)
 		return nil, err
 	}
 
 	// 检查是否有 shard failures，有部分数据时仅记录警告继续处理
-	if shardErr := checkShardFailures(result.Shards, "query_data", searchSourceString); shardErr != nil {
+	if shardErr := checkShardFailures(ctx, result.Shards, "query_data", searchSourceString); shardErr != nil {
 		if len(result.Aggregations["ts"]) == 0 {
 			return nil, shardErr
 		}
 		// 有部分数据，checkShardFailures 已记录警告，继续处理
 	}
 
-	logger.Debugf("query_data searchSource:%s resp:%s", string(jsonSearchSource), string(result.Aggregations["ts"]))
+	logx.Infof(ctx, "query_data searchSource:%s resp:%s", string(jsonSearchSource), string(result.Aggregations["ts"]))
 
 	js, err := simplejson.NewJson(result.Aggregations["ts"])
 	if err != nil {
@@ -611,7 +612,7 @@ func QueryData(ctx context.Context, queryParam interface{}, cliTimeout int64, ve
 }
 
 // checkShardFailures 检查 ES 查询结果中的 shard failures，返回格式化的错误信息
-func checkShardFailures(shards *elastic.ShardsInfo, logPrefix string, queryContext interface{}) error {
+func checkShardFailures(ctx context.Context, shards *elastic.ShardsInfo, logPrefix string, queryContext interface{}) error {
 	if shards == nil || shards.Failed == 0 || len(shards.Failures) == 0 {
 		return nil
 	}
@@ -638,7 +639,7 @@ func checkShardFailures(shards *elastic.ShardsInfo, logPrefix string, queryConte
 
 	if len(failureReasons) > 0 {
 		errMsg := fmt.Sprintf("elasticsearch shard failures (%d/%d failed): %s", shards.Failed, shards.Total, strings.Join(failureReasons, "; "))
-		logger.Warningf("%s query:%v %s", logPrefix, queryContext, errMsg)
+		logx.Warningf(ctx, "%s query:%v %s", logPrefix, queryContext, errMsg)
 		return fmt.Errorf("%s", errMsg)
 	}
 	return nil
@@ -723,12 +724,12 @@ func QueryLog(ctx context.Context, queryParam interface{}, timeout int64, versio
 	sourceBytes, _ := json.Marshal(source)
 	result, err := search(ctx, indexArr, source, param.Timeout, param.MaxShard)
 	if err != nil {
-		logger.Warningf("query_log source:%s error:%v", string(sourceBytes), err)
+		logx.Warningf(ctx, "query_log source:%s error:%v", string(sourceBytes), err)
 		return nil, 0, err
 	}
 
 	// 检查是否有 shard failures，有部分数据时仅记录警告继续处理
-	if shardErr := checkShardFailures(result.Shards, "query_log", string(sourceBytes)); shardErr != nil {
+	if shardErr := checkShardFailures(ctx, result.Shards, "query_log", string(sourceBytes)); shardErr != nil {
 		if len(result.Hits.Hits) == 0 {
 			return nil, 0, shardErr
 		}
@@ -737,17 +738,17 @@ func QueryLog(ctx context.Context, queryParam interface{}, timeout int64, versio
 
 	total := result.TotalHits()
 	var ret []interface{}
-	logger.Debugf("query_log source:%s len:%d total:%d", string(sourceBytes), len(result.Hits.Hits), total)
+	logx.Debugf(ctx, "query_log source:%s len:%d total:%d", string(sourceBytes), len(result.Hits.Hits), total)
 
 	resultBytes, _ := json.Marshal(result)
-	logger.Debugf("query_log source:%s result:%s", string(sourceBytes), string(resultBytes))
+	logx.Debugf(ctx, "query_log source:%s result:%s", string(sourceBytes), string(resultBytes))
 
 	if strings.HasPrefix(version, "6") {
 		for i := 0; i < len(result.Hits.Hits); i++ {
 			var x map[string]interface{}
 			err := json.Unmarshal(result.Hits.Hits[i].Source, &x)
 			if err != nil {
-				logger.Warningf("Unmarshal source error:%v", err)
+				logx.Warningf(ctx, "Unmarshal source error:%v", err)
 				continue
 			}
 

datasource/doris/doris.go

@@ -14,6 +14,8 @@ import (
 
 	"github.com/mitchellh/mapstructure"
 	"github.com/toolkits/pkg/logger"
+
+	"github.com/ccfos/nightingale/v6/pkg/logx"
 )
 
 const (
@@ -79,52 +81,19 @@ func (d *Doris) Equal(p datasource.Datasource) bool {
 		return false
 	}
 
-	// only compare first shard
-	if d.Addr != newest.Addr {
-		return false
-	}
-
-	if d.User != newest.User {
-		return false
-	}
-
-	if d.Password != newest.Password {
-		return false
-	}
-
-	if d.EnableWrite != newest.EnableWrite {
-		return false
-	}
-
-	if d.FeAddr != newest.FeAddr {
-		return false
-	}
-
-	if d.MaxQueryRows != newest.MaxQueryRows {
-		return false
-	}
-
-	if d.Timeout != newest.Timeout {
-		return false
-	}
-
-	if d.MaxIdleConns != newest.MaxIdleConns {
-		return false
-	}
-
-	if d.MaxOpenConns != newest.MaxOpenConns {
-		return false
-	}
-
-	if d.ConnMaxLifetime != newest.ConnMaxLifetime {
-		return false
-	}
-
-	if d.ClusterName != newest.ClusterName {
-		return false
-	}
-
-	return true
+	return d.Addr == newest.Addr &&
+		d.FeAddr == newest.FeAddr &&
+		d.User == newest.User &&
+		d.Password == newest.Password &&
+		d.EnableWrite == newest.EnableWrite &&
+		d.UserWrite == newest.UserWrite &&
+		d.PasswordWrite == newest.PasswordWrite &&
+		d.MaxQueryRows == newest.MaxQueryRows &&
+		d.Timeout == newest.Timeout &&
+		d.MaxIdleConns == newest.MaxIdleConns &&
+		d.MaxOpenConns == newest.MaxOpenConns &&
+		d.ConnMaxLifetime == newest.ConnMaxLifetime &&
+		d.ClusterName == newest.ClusterName
 }
 
 func (d *Doris) MakeLogQuery(ctx context.Context, query interface{}, eventTags []string, start, end int64) (interface{}, error) {
@@ -181,7 +150,7 @@ func (d *Doris) QueryData(ctx context.Context, query interface{}) ([]models.Data
 		}
 	}
 
-	items, err := d.QueryTimeseries(context.TODO(), &doris.QueryParam{
+	items, err := d.QueryTimeseries(ctx, &doris.QueryParam{
 		Database: dorisQueryParam.Database,
 		Sql:      dorisQueryParam.SQL,
 		Keys: types.Keys{
@@ -192,7 +161,7 @@ func (d *Doris) QueryData(ctx context.Context, query interface{}) ([]models.Data
 		},
 	})
 	if err != nil {
-		logger.Warningf("query:%+v get data err:%v", dorisQueryParam, err)
+		logx.Warningf(ctx, "query:%+v get data err:%v", dorisQueryParam, err)
 		return []models.DataResp{}, err
 	}
 	data := make([]models.DataResp, 0)
@@ -205,7 +174,7 @@ func (d *Doris) QueryData(ctx context.Context, query interface{}) ([]models.Data
 	}
 
 	// parse resp to time series data
-	logger.Infof("req:%+v keys:%+v \n data:%v", dorisQueryParam, dorisQueryParam.Keys, data)
+	logx.Infof(ctx, "req:%+v keys:%+v \n data:%v", dorisQueryParam, dorisQueryParam.Keys, data)
 
 	return data, nil
 }
@@ -241,7 +210,7 @@ func (d *Doris) QueryLog(ctx context.Context, query interface{}) ([]interface{},
 		Sql:      dorisQueryParam.SQL,
 	})
 	if err != nil {
-		logger.Warningf("query:%+v get data err:%v", dorisQueryParam, err)
+		logx.Warningf(ctx, "query:%+v get data err:%v", dorisQueryParam, err)
 		return []interface{}{}, 0, err
 	}
 	logs := make([]interface{}, 0)

datasource/es/es.go

@@ -19,7 +19,8 @@ import (
 
 	"github.com/mitchellh/mapstructure"
 	"github.com/olivere/elastic/v7"
-	"github.com/toolkits/pkg/logger"
+
+	"github.com/ccfos/nightingale/v6/pkg/logx"
 )
 
 const (
@@ -380,14 +381,14 @@ func (e *Elasticsearch) QueryMapData(ctx context.Context, query interface{}) ([]
 
 	var result []map[string]string
 	for _, item := range res {
-		logger.Debugf("query:%v item:%v", query, item)
+		logx.Debugf(ctx, "query:%v item:%v", query, item)
 		if itemMap, ok := item.(*elastic.SearchHit); ok {
 			mItem := make(map[string]string)
 			// 遍历 fields 字段的每个键值对
 			sourceMap := make(map[string]interface{})
 			err := json.Unmarshal(itemMap.Source, &sourceMap)
 			if err != nil {
-				logger.Warningf("unmarshal source%s error:%v", string(itemMap.Source), err)
+				logx.Warningf(ctx, "unmarshal source%s error:%v", string(itemMap.Source), err)
 				continue
 			}
 

datasource/mysql/mysql.go

@@ -15,6 +15,8 @@ import (
 
 	"github.com/mitchellh/mapstructure"
 	"github.com/toolkits/pkg/logger"
+
+	"github.com/ccfos/nightingale/v6/pkg/logx"
 )
 
 const (
@@ -165,7 +167,7 @@ func (m *MySQL) QueryData(ctx context.Context, query interface{}) ([]models.Data
 	})
 
 	if err != nil {
-		logger.Warningf("query:%+v get data err:%v", mysqlQueryParam, err)
+		logx.Warningf(ctx, "query:%+v get data err:%v", mysqlQueryParam, err)
 		return []models.DataResp{}, err
 	}
 	data := make([]models.DataResp, 0)
@@ -207,7 +209,7 @@ func (m *MySQL) QueryLog(ctx context.Context, query interface{}) ([]interface{},
 	})
 
 	if err != nil {
-		logger.Warningf("query:%+v get data err:%v", mysqlQueryParam, err)
+		logx.Warningf(ctx, "query:%+v get data err:%v", mysqlQueryParam, err)
 		return []interface{}{}, 0, err
 	}
 	logs := make([]interface{}, 0)

datasource/postgresql/postgresql.go

@@ -16,6 +16,8 @@ import (
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/mitchellh/mapstructure"
 	"github.com/toolkits/pkg/logger"
+
+	"github.com/ccfos/nightingale/v6/pkg/logx"
 )
 
 const (
@@ -197,7 +199,7 @@ func (p *PostgreSQL) QueryData(ctx context.Context, query interface{}) ([]models
 	})
 
 	if err != nil {
-		logger.Warningf("query:%+v get data err:%v", postgresqlQueryParam, err)
+		logx.Warningf(ctx, "query:%+v get data err:%v", postgresqlQueryParam, err)
 		return []models.DataResp{}, err
 	}
 	data := make([]models.DataResp, 0)
@@ -210,7 +212,7 @@ func (p *PostgreSQL) QueryData(ctx context.Context, query interface{}) ([]models
 	}
 
 	// parse resp to time series data
-	logger.Infof("req:%+v keys:%+v \n data:%v", postgresqlQueryParam, postgresqlQueryParam.Keys, data)
+	logx.Infof(ctx, "req:%+v keys:%+v \n data:%v", postgresqlQueryParam, postgresqlQueryParam.Keys, data)
 
 	return data, nil
 }
@@ -249,7 +251,7 @@ func (p *PostgreSQL) QueryLog(ctx context.Context, query interface{}) ([]interfa
 		Sql: postgresqlQueryParam.SQL,
 	})
 	if err != nil {
-		logger.Warningf("query:%+v get data err:%v", postgresqlQueryParam, err)
+		logx.Warningf(ctx, "query:%+v get data err:%v", postgresqlQueryParam, err)
 		return []interface{}{}, 0, err
 	}
 	logs := make([]interface{}, 0)

datasource/tdengine/tdengine.go

@@ -12,6 +12,8 @@ import (
 	"github.com/prometheus/common/model"
 	"github.com/toolkits/pkg/logger"
 
+	"github.com/ccfos/nightingale/v6/pkg/logx"
+
 	"github.com/ccfos/nightingale/v6/datasource"
 	td "github.com/ccfos/nightingale/v6/dskit/tdengine"
 	"github.com/ccfos/nightingale/v6/models"
@@ -118,7 +120,7 @@ func (td *TDengine) MakeTSQuery(ctx context.Context, query interface{}, eventTag
 }
 
 func (td *TDengine) QueryData(ctx context.Context, queryParam interface{}) ([]models.DataResp, error) {
-	return td.Query(queryParam, 0)
+	return td.Query(ctx, queryParam, 0)
 }
 
 func (td *TDengine) QueryLog(ctx context.Context, queryParam interface{}) ([]interface{}, int64, error) {
@@ -170,7 +172,7 @@ func (td *TDengine) QueryMapData(ctx context.Context, query interface{}) ([]map[
 	return nil, nil
 }
 
-func (td *TDengine) Query(query interface{}, delay ...int) ([]models.DataResp, error) {
+func (td *TDengine) Query(ctx context.Context, query interface{}, delay ...int) ([]models.DataResp, error) {
 	b, err := json.Marshal(query)
 	if err != nil {
 		return nil, err
@@ -212,7 +214,7 @@ func (td *TDengine) Query(query interface{}, delay ...int) ([]models.DataResp, e
 	if err != nil {
 		return nil, err
 	}
-	logger.Debugf("tdengine query:%s result: %+v", q.Query, data)
+	logx.Debugf(ctx, "tdengine query:%s result: %+v", q.Query, data)
 
 	return ConvertToTStData(data, q.Keys, q.Ref)
 }

docker/compose-postgres/initsql_for_postgres/a-n9e-for-Postgres.sql

@@ -321,6 +321,7 @@ CREATE TABLE alert_rule (
     create_by varchar(64) not null default '',
     update_at bigint not null default 0,
     update_by varchar(64) not null default '',
+    time_zone varchar(64) not null default '',
     PRIMARY KEY (id)
 ) ;
 CREATE INDEX alert_rule_group_id_idx ON alert_rule (group_id);

docker/initsql/a-n9e.sql

@@ -293,6 +293,7 @@ CREATE TABLE `alert_rule` (
     `update_at` bigint not null default 0,
     `update_by` varchar(64) not null default '',
     `cron_pattern` varchar(64),
+    `time_zone` varchar(64) not null default '',
     `datasource_queries` text,
     PRIMARY KEY (`id`),
     KEY (`group_id`),

docker/migratesql/migrate.sql

@@ -361,3 +361,6 @@ CREATE TABLE `user_view_favorite` (
 
 /* v9 2026-01-20 datasource weight */
 ALTER TABLE `datasource` ADD COLUMN `weight` int not null default 0 COMMENT 'weight for sorting';
+
+/* v9 2026-01-20 alert_rule time_zone support */
+ALTER TABLE `alert_rule` ADD COLUMN `time_zone` varchar(64) not null default '';

docker/sqlite.sql

@@ -253,6 +253,7 @@ CREATE TABLE `alert_rule` (
     `update_at` bigint not null default 0,
     `update_by` varchar(64) not null default '',
     `cron_pattern` varchar(64),
+    `time_zone` varchar(64) not null default '',
     `datasource_queries` text
 );
 CREATE INDEX `idx_alert_rule_group_id` ON `alert_rule` (`group_id` asc);

dskit/doris/doris.go

@@ -39,6 +39,9 @@ type Doris struct {
 	MaxQueryRows    int    `json:"doris.max_query_rows" mapstructure:"doris.max_query_rows"`
 	ClusterName     string `json:"doris.cluster_name" mapstructure:"doris.cluster_name"`
 	EnableWrite     bool   `json:"doris.enable_write" mapstructure:"doris.enable_write"`
+	// 写用户，用来区分读写用户，减少数据源
+	UserWrite     string `json:"doris.user_write" mapstructure:"doris.user_write"`
+	PasswordWrite string `json:"doris.password_write" mapstructure:"doris.password_write"`
 }
 
 // NewDorisWithSettings initializes a new Doris instance with the given settings
@@ -88,13 +91,13 @@ func (d *Doris) NewConn(ctx context.Context, database string) (*sql.DB, error) {
 
 	var keys []string
 	keys = append(keys, d.Addr)
-	keys = append(keys, d.Password, d.User)
+	keys = append(keys, d.User, d.Password)
 	if len(database) > 0 {
 		keys = append(keys, database)
 	}
-	cachedkey := strings.Join(keys, ":")
+	cachedKey := strings.Join(keys, ":")
 	// cache conn with database
-	conn, ok := pool.PoolClient.Load(cachedkey)
+	conn, ok := pool.PoolClient.Load(cachedKey)
 	if ok {
 		return conn.(*sql.DB), nil
 	}
@@ -102,7 +105,7 @@ func (d *Doris) NewConn(ctx context.Context, database string) (*sql.DB, error) {
 	var err error
 	defer func() {
 		if db != nil && err == nil {
-			pool.PoolClient.Store(cachedkey, db)
+			pool.PoolClient.Store(cachedKey, db)
 		}
 	}()
 
@@ -121,6 +124,79 @@ func (d *Doris) NewConn(ctx context.Context, database string) (*sql.DB, error) {
 	return db, nil
 }
 
+// NewWriteConn establishes a new connection to Doris for write operations
+// When EnableWrite is true and UserWrite is configured, it uses the write user credentials
+// Otherwise, it reuses the read connection from NewConn
+func (d *Doris) NewWriteConn(ctx context.Context, database string) (*sql.DB, error) {
+	// If write user is not configured, reuse the read connection
+	if !d.EnableWrite || len(d.UserWrite) == 0 {
+		return d.NewConn(ctx, database)
+	}
+
+	if len(d.Addr) == 0 {
+		return nil, errors.New("empty fe-node addr")
+	}
+
+	// Set default values similar to postgres implementation
+	if d.Timeout == 0 {
+		d.Timeout = 60000
+	}
+	if d.MaxIdleConns == 0 {
+		d.MaxIdleConns = 10
+	}
+	if d.MaxOpenConns == 0 {
+		d.MaxOpenConns = 100
+	}
+	if d.ConnMaxLifetime == 0 {
+		d.ConnMaxLifetime = 14400
+	}
+	if d.MaxQueryRows == 0 {
+		d.MaxQueryRows = 500
+	}
+
+	// Use write user credentials
+	user := d.UserWrite
+	password := d.PasswordWrite
+
+	var keys []string
+	keys = append(keys, d.Addr)
+	keys = append(keys, user, password)
+	if len(database) > 0 {
+		keys = append(keys, database)
+	}
+	cachedKey := strings.Join(keys, ":")
+	// cache conn with database
+	conn, ok := pool.PoolClient.Load(cachedKey)
+	if ok {
+		return conn.(*sql.DB), nil
+	}
+	var db *sql.DB
+	var err error
+	defer func() {
+		if db != nil && err == nil {
+			pool.PoolClient.Store(cachedKey, db)
+		}
+	}()
+
+	// Simplified connection logic for Doris using MySQL driver
+	dsn := fmt.Sprintf("%s:%s@tcp(%s)/%s?charset=utf8", user, password, d.Addr, database)
+	db, err = sql.Open("mysql", dsn)
+	if err != nil {
+		return nil, err
+	}
+
+	// Set connection pool configuration for write connections
+	// Use more conservative values since write operations are typically less frequent
+	writeMaxIdleConns := max(d.MaxIdleConns/5, 2)
+	writeMaxOpenConns := max(d.MaxOpenConns/10, 5)
+
+	db.SetMaxIdleConns(writeMaxIdleConns)
+	db.SetMaxOpenConns(writeMaxOpenConns)
+	db.SetConnMaxLifetime(time.Duration(d.ConnMaxLifetime) * time.Second)
+
+	return db, nil
+}
+
 // createTimeoutContext creates a context with timeout based on Doris configuration
 func (d *Doris) createTimeoutContext(ctx context.Context) (context.Context, context.CancelFunc) {
 	timeout := d.Timeout
@@ -472,7 +548,7 @@ func (d *Doris) ExecContext(ctx context.Context, database string, sql string) er
 	timeoutCtx, cancel := d.createTimeoutContext(ctx)
 	defer cancel()
 
-	db, err := d.NewConn(timeoutCtx, database)
+	db, err := d.NewWriteConn(timeoutCtx, database)
 	if err != nil {
 		return err
 	}

memsto/notify_channel_cache.go

@@ -140,7 +140,7 @@ func (ncc *NotifyChannelCacheType) addOrUpdateChannels(newChannels map[int64]*mo
 				logger.Infof("updating channel %d (new: %t)", chID, !exists)
 				ncc.stopChannelResources(chID)
 			} else {
-				logger.Infof("channel %d config not changed", chID)
+				logger.Debugf("channel %d config not changed", chID)
 				continue
 			}
 		}
@@ -284,8 +284,8 @@ func (ncc *NotifyChannelCacheType) processNotifyTask(task *NotifyTask) {
 			start := time.Now()
 			resp, err := task.NotifyChannel.SendHTTP(task.Events, task.TplContent, task.CustomParams, task.Sendtos, httpClient)
 			resp = fmt.Sprintf("send_time: %s duration: %d ms %s", time.Now().Format("2006-01-02 15:04:05"), time.Since(start).Milliseconds(), resp)
-			logger.Infof("http_sendernotify_id: %d, channel_name: %v, event:%+v, tplContent:%v, customParams:%v, userInfo:%+v, respBody: %v, err: %v",
-				task.NotifyRuleId, task.NotifyChannel.Name, task.Events[0], task.TplContent, task.CustomParams, task.Sendtos, resp, err)
+			logger.Infof("http_sendernotify_id: %d, channel_name: %v, event:%s, tplContent:%v, customParams:%v, userInfo:%+v, respBody: %v, err: %v",
+				task.NotifyRuleId, task.NotifyChannel.Name, task.Events[0].Hash, task.TplContent, task.CustomParams, task.Sendtos, resp, err)
 
 			// 调用通知记录回调函数
 			if ncc.notifyRecordFunc != nil {
@@ -296,8 +296,8 @@ func (ncc *NotifyChannelCacheType) processNotifyTask(task *NotifyTask) {
 				start := time.Now()
 				resp, err := task.NotifyChannel.SendHTTP(task.Events, task.TplContent, task.CustomParams, []string{task.Sendtos[i]}, httpClient)
 				resp = fmt.Sprintf("send_time: %s duration: %d ms %s", time.Now().Format("2006-01-02 15:04:05"), time.Since(start).Milliseconds(), resp)
-				logger.Infof("http_sender notify_id: %d, channel_name: %v, event:%+v, tplContent:%v, customParams:%v, userInfo:%+v, respBody: %v, err: %v",
-					task.NotifyRuleId, task.NotifyChannel.Name, task.Events[0], task.TplContent, task.CustomParams, task.Sendtos[i], resp, err)
+				logger.Infof("http_sender notify_id: %d, channel_name: %v, event:%s, tplContent:%v, customParams:%v, userInfo:%+v, respBody: %v, err: %v",
+					task.NotifyRuleId, task.NotifyChannel.Name, task.Events[0].Hash, task.TplContent, task.CustomParams, task.Sendtos[i], resp, err)
 
 				// 调用通知记录回调函数
 				if ncc.notifyRecordFunc != nil {

models/alert_cur_event.go

@@ -15,8 +15,8 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/poster"
 	"github.com/ccfos/nightingale/v6/pkg/tplx"
 	"github.com/ccfos/nightingale/v6/pkg/unit"
+	"github.com/ccfos/nightingale/v6/pkg/ginx"
 
-	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
 )
 

models/alert_his_event.go

@@ -251,6 +251,18 @@ func AlertHisEventGetById(ctx *ctx.Context, id int64) (*AlertHisEvent, error) {
 	return AlertHisEventGet(ctx, "id=?", id)
 }
 
+func AlertHisEventGetByHash(ctx *ctx.Context, hash string) (*AlertHisEvent, error) {
+	var lst []*AlertHisEvent
+	err := DB(ctx).Where("hash = ?", hash).Order("trigger_time desc").Limit(1).Find(&lst).Error
+	if err != nil {
+		return nil, err
+	}
+	if len(lst) == 0 {
+		return nil, nil
+	}
+	return lst[0], nil
+}
+
 func AlertHisEventBatchDelete(ctx *ctx.Context, timestamp int64, severities []int, limit int) (int64, error) {
 	db := DB(ctx).Where("last_eval_time < ?", timestamp)
 	if len(severities) > 0 {

models/alert_mute.go

@@ -192,6 +192,7 @@ type AlertMute struct {
 	Activated         int            `json:"activated" gorm:"-"` // 0: not activated, 1: activated
 	CreateBy          string         `json:"create_by"`
 	UpdateBy          string         `json:"update_by"`
+	UpdateByNickname  string         `json:"update_by_nickname" gorm:"-"`
 	CreateAt          int64          `json:"create_at"`
 	UpdateAt          int64          `json:"update_at"`
 	ITags             []TagFilter    `json:"-" gorm:"-"`     // inner tags

models/alert_rule.go

@@ -119,6 +119,7 @@ type AlertRule struct {
 	CurEventCount         int64                  `json:"cur_event_count" gorm:"-"`
 	UpdateByNickname      string                 `json:"update_by_nickname" gorm:"-"` // for fe
 	CronPattern           string                 `json:"cron_pattern"`
+	TimeZone              string                 `json:"time_zone" gorm:"default:''"` // timezone for alert rule, e.g. "Asia/Shanghai", "UTC", empty for default
 	NotifyRuleIds         []int64                `json:"notify_rule_ids" gorm:"serializer:json"`
 	PipelineConfigs       []PipelineConfig       `json:"pipeline_configs" gorm:"serializer:json"`
 	NotifyVersion         int                    `json:"notify_version"` // 0: old, 1: new
@@ -482,6 +483,13 @@ func (ar *AlertRule) Verify() error {
 		return errors.New("name is blank")
 	}
 
+	if ar.TimeZone != "" {
+		_, err := time.LoadLocation(ar.TimeZone)
+		if err != nil {
+			return fmt.Errorf("invalid timezone: %s", ar.TimeZone)
+		}
+	}
+
 	if str.Dangerous(ar.Name) {
 		return errors.New("Name has invalid characters")
 	}

models/alert_subscribe.go

@@ -45,6 +45,7 @@ type AlertSubscribe struct {
 	CreateAt          int64        `json:"create_at"`
 	UpdateBy          string       `json:"update_by"`
 	UpdateAt          int64        `json:"update_at"`
+	UpdateByNickname  string       `json:"update_by_nickname" gorm:"-"`
 	ITags             []TagFilter  `json:"-" gorm:"-"` // inner tags
 	BusiGroups        ormx.JSONArr `json:"busi_groups"`
 	IBusiGroups       []TagFilter  `json:"-" gorm:"-"` // inner busiGroups

models/board.go

@@ -19,22 +19,23 @@ const (
 )
 
 type Board struct {
-	Id         int64   `json:"id" gorm:"primaryKey"`
-	GroupId    int64   `json:"group_id"`
-	Name       string  `json:"name"`
-	Ident      string  `json:"ident"`
-	Tags       string  `json:"tags"`
-	Note       string  `json:"note"`
-	CreateAt   int64   `json:"create_at"`
-	CreateBy   string  `json:"create_by"`
-	UpdateAt   int64   `json:"update_at"`
-	UpdateBy   string  `json:"update_by"`
-	Configs    string  `json:"configs" gorm:"-"`
-	Public     int     `json:"public"`      // 0: false, 1: true
-	PublicCate int     `json:"public_cate"` // 0: anonymous, 1: login, 2: busi
-	Bgids      []int64 `json:"bgids" gorm:"-"`
-	BuiltIn    int     `json:"built_in"` // 0: false, 1: true
-	Hide       int     `json:"hide"`     // 0: false, 1: true
+	Id               int64   `json:"id" gorm:"primaryKey"`
+	GroupId          int64   `json:"group_id"`
+	Name             string  `json:"name"`
+	Ident            string  `json:"ident"`
+	Tags             string  `json:"tags"`
+	Note             string  `json:"note"`
+	CreateAt         int64   `json:"create_at"`
+	CreateBy         string  `json:"create_by"`
+	UpdateAt         int64   `json:"update_at"`
+	UpdateBy         string  `json:"update_by"`
+	UpdateByNickname string  `json:"update_by_nickname" gorm:"-"`
+	Configs          string  `json:"configs" gorm:"-"`
+	Public           int     `json:"public"`      // 0: false, 1: true
+	PublicCate       int     `json:"public_cate"` // 0: anonymous, 1: login, 2: busi
+	Bgids            []int64 `json:"bgids" gorm:"-"`
+	BuiltIn          int     `json:"built_in"` // 0: false, 1: true
+	Hide             int     `json:"hide"`     // 0: false, 1: true
 }
 
 func (b *Board) TableName() string {

models/builtin_metrics_filter.go

@@ -9,14 +9,15 @@ import (
 )
 
 type MetricFilter struct {
-	ID         int64       `json:"id" gorm:"primaryKey;type:bigint;autoIncrement;comment:'unique identifier'"`
-	Name       string      `json:"name" gorm:"type:varchar(191);not null;index:idx_metricfilter_name,sort:asc;comment:'name of metric filter'"`
-	Configs    string      `json:"configs" gorm:"type:varchar(4096);not null;comment:'configuration of metric filter'"`
-	GroupsPerm []GroupPerm `json:"groups_perm" gorm:"type:text;serializer:json;"`
-	CreateAt   int64       `json:"create_at" gorm:"type:bigint;not null;default:0;comment:'create time'"`
-	CreateBy   string      `json:"create_by" gorm:"type:varchar(191);not null;default:'';comment:'creator'"`
-	UpdateAt   int64       `json:"update_at" gorm:"type:bigint;not null;default:0;comment:'update time'"`
-	UpdateBy   string      `json:"update_by" gorm:"type:varchar(191);not null;default:'';comment:'updater'"`
+	ID               int64       `json:"id" gorm:"primaryKey;type:bigint;autoIncrement;comment:'unique identifier'"`
+	Name             string      `json:"name" gorm:"type:varchar(191);not null;index:idx_metricfilter_name,sort:asc;comment:'name of metric filter'"`
+	Configs          string      `json:"configs" gorm:"type:varchar(4096);not null;comment:'configuration of metric filter'"`
+	GroupsPerm       []GroupPerm `json:"groups_perm" gorm:"type:text;serializer:json;"`
+	CreateAt         int64       `json:"create_at" gorm:"type:bigint;not null;default:0;comment:'create time'"`
+	CreateBy         string      `json:"create_by" gorm:"type:varchar(191);not null;default:'';comment:'creator'"`
+	UpdateAt         int64       `json:"update_at" gorm:"type:bigint;not null;default:0;comment:'update time'"`
+	UpdateBy         string      `json:"update_by" gorm:"type:varchar(191);not null;default:'';comment:'updater'"`
+	UpdateByNickname string      `json:"update_by_nickname" gorm:"-"`
 }
 
 type GroupPerm struct {

models/busi_group.go

@@ -12,16 +12,17 @@ import (
 )
 
 type BusiGroup struct {
-	Id          int64                   `json:"id" gorm:"primaryKey"`
-	Name        string                  `json:"name"`
-	LabelEnable int                     `json:"label_enable"`
-	LabelValue  string                  `json:"label_value"`
-	CreateAt    int64                   `json:"create_at"`
-	CreateBy    string                  `json:"create_by"`
-	UpdateAt    int64                   `json:"update_at"`
-	UpdateBy    string                  `json:"update_by"`
-	UserGroups  []UserGroupWithPermFlag `json:"user_groups" gorm:"-"`
-	DB          *gorm.DB                `json:"-" gorm:"-"`
+	Id               int64                   `json:"id" gorm:"primaryKey"`
+	Name             string                  `json:"name"`
+	LabelEnable      int                     `json:"label_enable"`
+	LabelValue       string                  `json:"label_value"`
+	CreateAt         int64                   `json:"create_at"`
+	CreateBy         string                  `json:"create_by"`
+	UpdateAt         int64                   `json:"update_at"`
+	UpdateBy         string                  `json:"update_by"`
+	UpdateByNickname string                  `json:"update_by_nickname" gorm:"-"`
+	UserGroups       []UserGroupWithPermFlag `json:"user_groups" gorm:"-"`
+	DB               *gorm.DB                `json:"-" gorm:"-"`
 }
 
 func New(db *gorm.DB) *BusiGroup {