refactor: global webhook add env proxy (#2367)

Co-authored-by: Yening Qin <710leo@gmail.com>

.gitignore

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

alert/alert.go

@@ -65,6 +65,7 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 	configCvalCache := memsto.NewCvalCache(ctx, syncStats)
 
 	promClients := prom.NewPromClient(ctx)
+	dispatch.InitRegisterQueryFunc(promClients)
 	tdengineClients := tdengine.NewTdengineClient(ctx, config.Alert.Heartbeat)
 
 	externalProcessors := process.NewExternalProcessors()

alert/dispatch/consume.go

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

alert/dispatch/dispatch.go

@@ -193,9 +193,9 @@ func (e *Dispatch) blockEventNotify(rule *models.AlertRule, event *models.AlertC
 	}
 
 	// 恢复通知，检测规则配置是否改变
-	if event.IsRecovered && event.RuleHash != rule.Hash() {
-		return true
-	}
+	// if event.IsRecovered && event.RuleHash != rule.Hash() {
+	// 	return true
+	// }
 
 	return false
 }
@@ -293,9 +293,9 @@ func (e *Dispatch) Send(rule *models.AlertRule, event *models.AlertCurEvent, not
 	// handle global webhooks
 	if !event.OverrideGlobalWebhook() {
 		if e.alerting.WebhookBatchSend {
-			sender.BatchSendWebhooks(e.ctx, notifyTarget.ToWebhookList(), event, e.Astats)
+			sender.BatchSendWebhooks(e.ctx, notifyTarget.ToWebhookMap(), event, e.Astats)
 		} else {
-			sender.SingleSendWebhooks(e.ctx, notifyTarget.ToWebhookList(), event, e.Astats)
+			sender.SingleSendWebhooks(e.ctx, notifyTarget.ToWebhookMap(), event, e.Astats)
 		}
 	}
 

alert/dispatch/notify_target.go

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

alert/eval/eval_test.go

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

alert/process/process.go

@@ -21,6 +21,7 @@ import (
 	"github.com/ccfos/nightingale/v6/pushgw/writer"
 
 	"github.com/prometheus/prometheus/prompb"
+	"github.com/robfig/cron/v3"
 	"github.com/toolkits/pkg/logger"
 	"github.com/toolkits/pkg/str"
 )
@@ -78,6 +79,9 @@ type Processor struct {
 	HandleFireEventHook    HandleEventFunc
 	HandleRecoverEventHook HandleEventFunc
 	EventMuteHook          EventMuteHookFunc
+
+	ScheduleEntry    cron.Entry
+	PromEvalInterval int
 }
 
 func (p *Processor) Key() string {
@@ -89,9 +93,9 @@ func (p *Processor) DatasourceId() int64 {
 }
 
 func (p *Processor) Hash() string {
-	return str.MD5(fmt.Sprintf("%d_%d_%s_%d",
+	return str.MD5(fmt.Sprintf("%d_%s_%s_%d",
 		p.rule.Id,
-		p.rule.PromEvalInterval,
+		p.rule.CronPattern,
 		p.rule.RuleConfig,
 		p.datasourceId,
 	))
@@ -126,7 +130,7 @@ func NewProcessor(engineName string, rule *models.AlertRule, datasourceId int64,
 	return p
 }
 
-func (p *Processor) Handle(anomalyPoints []common.AnomalyPoint, from string, inhibit bool) {
+func (p *Processor) Handle(anomalyPoints []models.AnomalyPoint, from string, inhibit bool) {
 	// 有可能rule的一些配置已经发生变化，比如告警接收人、callbacks等
 	// 这些信息的修改是不会引起worker restart的，但是确实会影响告警处理逻辑
 	// 所以，这里直接从memsto.AlertRuleCache中获取并覆盖
@@ -178,7 +182,7 @@ func (p *Processor) Handle(anomalyPoints []common.AnomalyPoint, from string, inh
 	}
 }
 
-func (p *Processor) BuildEvent(anomalyPoint common.AnomalyPoint, from string, now int64, ruleHash string) *models.AlertCurEvent {
+func (p *Processor) BuildEvent(anomalyPoint models.AnomalyPoint, from string, now int64, ruleHash string) *models.AlertCurEvent {
 	p.fillTags(anomalyPoint)
 	p.mayHandleIdent()
 	hash := Hash(p.rule.Id, p.datasourceId, anomalyPoint)
@@ -420,6 +424,7 @@ func (p *Processor) handleEvent(events []*models.AlertCurEvent) {
 			p.pendingsUseByRecover.Set(event.Hash, event)
 		}
 
+		event.PromEvalInterval = p.PromEvalInterval
 		if p.rule.PromForDuration == 0 {
 			fireEvents = append(fireEvents, event)
 			if severity > event.Severity {
@@ -559,7 +564,7 @@ func (p *Processor) RecoverAlertCurEventFromDb() {
 	p.pendingsUseByRecover = NewAlertCurEventMap(pendingsUseByRecoverMap)
 }
 
-func (p *Processor) fillTags(anomalyPoint common.AnomalyPoint) {
+func (p *Processor) fillTags(anomalyPoint models.AnomalyPoint) {
 	// handle series tags
 	tagsMap := make(map[string]string)
 	for label, value := range anomalyPoint.Labels {
@@ -649,10 +654,10 @@ func labelMapToArr(m map[string]string) []string {
 	return labelStrings
 }
 
-func Hash(ruleId, datasourceId int64, vector common.AnomalyPoint) string {
+func Hash(ruleId, datasourceId int64, vector models.AnomalyPoint) string {
 	return str.MD5(fmt.Sprintf("%d_%s_%d_%d_%s", ruleId, vector.Labels.String(), datasourceId, vector.Severity, vector.Query))
 }
 
-func TagHash(vector common.AnomalyPoint) string {
+func TagHash(vector models.AnomalyPoint) string {
 	return str.MD5(vector.Labels.String())
 }

alert/router/router_event.go

@@ -6,7 +6,6 @@ import (
 	"strings"
 	"time"
 
-	"github.com/ccfos/nightingale/v6/alert/common"
 	"github.com/ccfos/nightingale/v6/alert/dispatch"
 	"github.com/ccfos/nightingale/v6/alert/mute"
 	"github.com/ccfos/nightingale/v6/alert/naming"
@@ -92,7 +91,7 @@ func (rt *Router) eventPersist(c *gin.Context) {
 
 type eventForm struct {
 	Alert         bool                  `json:"alert"`
-	AnomalyPoints []common.AnomalyPoint `json:"vectors"`
+	AnomalyPoints []models.AnomalyPoint `json:"vectors"`
 	RuleId        int64                 `json:"rule_id"`
 	DatasourceId  int64                 `json:"datasource_id"`
 	Inhibit       bool                  `json:"inhibit"`

alert/sender/callback.go

@@ -129,34 +129,39 @@ func (c *DefaultCallBacker) CallBack(ctx CallBackContext) {
 		return
 	}
 
-	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, event, "callback", ctx.Stats, event)
+	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, event, "callback", ctx.Stats, ctx.Events)
 }
 
 func doSendAndRecord(ctx *ctx.Context, url, token string, body interface{}, channel string,
-	stats *astats.Stats, event *models.AlertCurEvent) {
+	stats *astats.Stats, events []*models.AlertCurEvent) {
 	res, err := doSend(url, body, channel, stats)
-	NotifyRecord(ctx, event, channel, token, res, err)
+	NotifyRecord(ctx, events, channel, token, res, err)
 }
 
-func NotifyRecord(ctx *ctx.Context, evt *models.AlertCurEvent, channel, target, res string, err error) {
-	noti := models.NewNotificationRecord(evt, channel, target)
-	if err != nil {
-		noti.SetStatus(models.NotiStatusFailure)
-		noti.SetDetails(err.Error())
-	} else if res != "" {
-		noti.SetDetails(string(res))
+func NotifyRecord(ctx *ctx.Context, evts []*models.AlertCurEvent, channel, target, res string, err error) {
+	// 一个通知可能对应多个 event，都需要记录
+	notis := make([]*models.NotificaitonRecord, 0, len(evts))
+	for _, evt := range evts {
+		noti := models.NewNotificationRecord(evt, channel, target)
+		if err != nil {
+			noti.SetStatus(models.NotiStatusFailure)
+			noti.SetDetails(err.Error())
+		} else if res != "" {
+			noti.SetDetails(string(res))
+		}
+		notis = append(notis, noti)
 	}
 
 	if !ctx.IsCenter {
-		_, err := poster.PostByUrlsWithResp[int64](ctx, "/v1/n9e/notify-record", noti)
+		_, err := poster.PostByUrlsWithResp[[]int64](ctx, "/v1/n9e/notify-record", notis)
 		if err != nil {
-			logger.Errorf("add noti:%v failed, err: %v", noti, err)
+			logger.Errorf("add notis:%v failed, err: %v", notis, err)
 		}
 		return
 	}
 
-	if err := noti.Add(ctx); err != nil {
-		logger.Errorf("add noti:%v failed, err: %v", noti, err)
+	if err := models.DB(ctx).CreateInBatches(notis, 100).Error; err != nil {
+		logger.Errorf("add notis:%v failed, err: %v", notis, err)
 	}
 }
 

alert/sender/dingtalk.go

@@ -67,7 +67,7 @@ func (ds *DingtalkSender) Send(ctx MessageContext) {
 			}
 		}
 
-		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Dingtalk, ctx.Stats, ctx.Events[0])
+		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Dingtalk, ctx.Stats, ctx.Events)
 	}
 }
 
@@ -97,8 +97,7 @@ func (ds *DingtalkSender) CallBack(ctx CallBackContext) {
 		body.Markdown.Text = message
 	}
 
-	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body,
-		"callback", ctx.Stats, ctx.Events[0])
+	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback", ctx.Stats, ctx.Events)
 }
 
 // extract urls and ats from Users

alert/sender/email.go

@@ -25,8 +25,8 @@ type EmailSender struct {
 }
 
 type EmailContext struct {
-	event *models.AlertCurEvent
-	mail  *gomail.Message
+	events []*models.AlertCurEvent
+	mail   *gomail.Message
 }
 
 func (es *EmailSender) Send(ctx MessageContext) {
@@ -42,7 +42,7 @@ func (es *EmailSender) Send(ctx MessageContext) {
 		subject = ctx.Events[0].RuleName
 	}
 	content := BuildTplMessage(models.Email, es.contentTpl, ctx.Events)
-	es.WriteEmail(subject, content, tos, ctx.Events[0])
+	es.WriteEmail(subject, content, tos, ctx.Events)
 
 	ctx.Stats.AlertNotifyTotal.WithLabelValues(models.Email).Add(float64(len(tos)))
 }
@@ -79,8 +79,7 @@ func SendEmail(subject, content string, tos []string, stmp aconf.SMTPConfig) err
 	return nil
 }
 
-func (es *EmailSender) WriteEmail(subject, content string, tos []string,
-	event *models.AlertCurEvent) {
+func (es *EmailSender) WriteEmail(subject, content string, tos []string, events []*models.AlertCurEvent) {
 	m := gomail.NewMessage()
 
 	m.SetHeader("From", es.smtp.From)
@@ -88,7 +87,7 @@ func (es *EmailSender) WriteEmail(subject, content string, tos []string,
 	m.SetHeader("Subject", subject)
 	m.SetBody("text/html", content)
 
-	mailch <- &EmailContext{event, m}
+	mailch <- &EmailContext{events, m}
 }
 
 func dialSmtp(d *gomail.Dialer) gomail.SendCloser {
@@ -206,7 +205,7 @@ func startEmailSender(ctx *ctx.Context, smtp aconf.SMTPConfig) {
 				if err == nil {
 					msg = "ok"
 				}
-				NotifyRecord(ctx, m.event, models.Email, to, msg, err)
+				NotifyRecord(ctx, m.events, models.Email, to, msg, err)
 			}
 
 			size++

alert/sender/feishu.go

@@ -54,8 +54,7 @@ func (fs *FeishuSender) CallBack(ctx CallBackContext) {
 		},
 	}
 
-	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback",
-		ctx.Stats, ctx.Events[0])
+	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback", ctx.Stats, ctx.Events)
 }
 
 func (fs *FeishuSender) Send(ctx MessageContext) {
@@ -77,7 +76,7 @@ func (fs *FeishuSender) Send(ctx MessageContext) {
 				IsAtAll:   false,
 			}
 		}
-		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Feishu, ctx.Stats, ctx.Events[0])
+		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Feishu, ctx.Stats, ctx.Events)
 	}
 }
 

alert/sender/feishucard.go

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

alert/sender/lark.go

@@ -27,8 +27,7 @@ func (lk *LarkSender) CallBack(ctx CallBackContext) {
 		},
 	}
 
-	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback",
-		ctx.Stats, ctx.Events[0])
+	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback", ctx.Stats, ctx.Events)
 }
 
 func (lk *LarkSender) Send(ctx MessageContext) {
@@ -44,7 +43,7 @@ func (lk *LarkSender) Send(ctx MessageContext) {
 				Text: message,
 			},
 		}
-		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Lark, ctx.Stats, ctx.Events[0])
+		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Lark, ctx.Stats, ctx.Events)
 	}
 }
 

alert/sender/larkcard.go

@@ -56,8 +56,7 @@ func (fs *LarkCardSender) CallBack(ctx CallBackContext) {
 	}
 	parsedURL.RawQuery = ""
 
-	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback",
-		ctx.Stats, ctx.Events[0])
+	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback", ctx.Stats, ctx.Events)
 }
 
 func (fs *LarkCardSender) Send(ctx MessageContext) {
@@ -81,7 +80,7 @@ func (fs *LarkCardSender) Send(ctx MessageContext) {
 	body.Card.Elements[0].Text.Content = message
 	body.Card.Elements[2].Elements[0].Content = SendTitle
 	for i, url := range urls {
-		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.LarkCard, ctx.Stats, ctx.Events[0])
+		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.LarkCard, ctx.Stats, ctx.Events)
 	}
 }
 

alert/sender/mm.go

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

alert/sender/plugin.go

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

alert/sender/telegram.go

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

alert/sender/webhook.go

@@ -59,17 +59,21 @@ func sendWebhook(webhook *models.Webhook, event interface{}, stats *astats.Stats
 	if webhook != nil {
 		insecureSkipVerify = webhook.SkipVerify
 	}
-	client := http.Client{
-		Timeout: time.Duration(conf.Timeout) * time.Second,
-		Transport: &http.Transport{
-			TLSClientConfig: &tls.Config{InsecureSkipVerify: insecureSkipVerify},
-		},
+
+	if conf.Client == nil {
+		logger.Warningf("event_%s, event:%s, url: [%s], error: [%s]", channel, string(bs), conf.Url, "client is nil")
+		conf.Client = &http.Client{
+			Timeout: time.Duration(conf.Timeout) * time.Second,
+			Transport: &http.Transport{
+				TLSClientConfig: &tls.Config{InsecureSkipVerify: insecureSkipVerify},
+			},
+		}
 	}
 
 	stats.AlertNotifyTotal.WithLabelValues(channel).Inc()
 	var resp *http.Response
 	var body []byte
-	resp, err = client.Do(req)
+	resp, err = conf.Client.Do(req)
 
 	if err != nil {
 		stats.AlertNotifyErrorTotal.WithLabelValues(channel).Inc()
@@ -91,12 +95,12 @@ func sendWebhook(webhook *models.Webhook, event interface{}, stats *astats.Stats
 	return false, string(body), nil
 }
 
-func SingleSendWebhooks(ctx *ctx.Context, webhooks []*models.Webhook, event *models.AlertCurEvent, stats *astats.Stats) {
+func SingleSendWebhooks(ctx *ctx.Context, webhooks map[string]*models.Webhook, event *models.AlertCurEvent, stats *astats.Stats) {
 	for _, conf := range webhooks {
 		retryCount := 0
 		for retryCount < 3 {
 			needRetry, res, err := sendWebhook(conf, event, stats)
-			NotifyRecord(ctx, event, "webhook", conf.Url, res, err)
+			NotifyRecord(ctx, []*models.AlertCurEvent{event}, "webhook", conf.Url, res, err)
 			if !needRetry {
 				break
 			}
@@ -106,7 +110,7 @@ func SingleSendWebhooks(ctx *ctx.Context, webhooks []*models.Webhook, event *mod
 	}
 }
 
-func BatchSendWebhooks(ctx *ctx.Context, webhooks []*models.Webhook, event *models.AlertCurEvent, stats *astats.Stats) {
+func BatchSendWebhooks(ctx *ctx.Context, webhooks map[string]*models.Webhook, event *models.AlertCurEvent, stats *astats.Stats) {
 	for _, conf := range webhooks {
 		logger.Infof("push event:%+v to queue:%v", event, conf)
 		PushEvent(ctx, conf, event, stats)
@@ -166,7 +170,7 @@ func StartConsumer(ctx *ctx.Context, queue *WebhookQueue, popSize int, webhook *
 			retryCount := 0
 			for retryCount < webhook.RetryCount {
 				needRetry, res, err := sendWebhook(webhook, events, stats)
-				go RecordEvents(ctx, webhook, events, stats, res, err)
+				go NotifyRecord(ctx, events, "webhook", webhook.Url, res, err)
 				if !needRetry {
 					break
 				}
@@ -176,10 +180,3 @@ func StartConsumer(ctx *ctx.Context, queue *WebhookQueue, popSize int, webhook *
 		}
 	}
 }
-
-func RecordEvents(ctx *ctx.Context, webhook *models.Webhook, events []*models.AlertCurEvent, stats *astats.Stats, res string, err error) {
-	for _, event := range events {
-		time.Sleep(time.Millisecond * 10)
-		NotifyRecord(ctx, event, "webhook", webhook.Url, res, err)
-	}
-}

alert/sender/wecom.go

@@ -37,8 +37,7 @@ func (ws *WecomSender) CallBack(ctx CallBackContext) {
 		},
 	}
 
-	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback",
-		ctx.Stats, ctx.Events[0])
+	doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback", ctx.Stats, ctx.Events)
 }
 
 func (ws *WecomSender) Send(ctx MessageContext) {
@@ -54,7 +53,7 @@ func (ws *WecomSender) Send(ctx MessageContext) {
 				Content: message,
 			},
 		}
-		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Wecom, ctx.Stats, ctx.Events[0])
+		doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Wecom, ctx.Stats, ctx.Events)
 	}
 }
 

center/center.go

@@ -6,6 +6,7 @@ import (
 
 	"github.com/ccfos/nightingale/v6/alert"
 	"github.com/ccfos/nightingale/v6/alert/astats"
+	"github.com/ccfos/nightingale/v6/alert/dispatch"
 	"github.com/ccfos/nightingale/v6/alert/process"
 	alertrt "github.com/ccfos/nightingale/v6/alert/router"
 	"github.com/ccfos/nightingale/v6/center/cconf"
@@ -103,6 +104,9 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 
 	sso := sso.Init(config.Center, ctx, configCache)
 	promClients := prom.NewPromClient(ctx)
+
+	dispatch.InitRegisterQueryFunc(promClients)
+
 	tdengineClients := tdengine.NewTdengineClient(ctx, config.Alert.Heartbeat)
 
 	externalProcessors := process.NewExternalProcessors()

center/router/router.go

@@ -280,6 +280,7 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.DELETE("/busi-group/:id/members", rt.auth(), rt.user(), rt.perm("/busi-groups/put"), rt.bgrw(), rt.busiGroupMemberDel)
 		pages.DELETE("/busi-group/:id", rt.auth(), rt.user(), rt.perm("/busi-groups/del"), rt.bgrw(), rt.busiGroupDel)
 		pages.GET("/busi-group/:id/perm/:perm", rt.auth(), rt.user(), rt.checkBusiGroupPerm)
+		pages.GET("/busi-groups/tags", rt.auth(), rt.user(), rt.busiGroupsGetTags)
 
 		pages.GET("/targets", rt.auth(), rt.user(), rt.targetGets)
 		pages.GET("/target/extra-meta", rt.auth(), rt.user(), rt.targetExtendInfoByIdent)

center/router/router_busi_group.go

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

center/router/router_heartbeat.go

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

center/router/router_notification_record.go

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

center/router/router_target.go

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

cli/upgrade/config.go

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

cmd/edge/edge.go

@@ -7,6 +7,7 @@ import (
 
 	"github.com/ccfos/nightingale/v6/alert"
 	"github.com/ccfos/nightingale/v6/alert/astats"
+	"github.com/ccfos/nightingale/v6/alert/dispatch"
 	"github.com/ccfos/nightingale/v6/alert/process"
 	alertrt "github.com/ccfos/nightingale/v6/alert/router"
 	"github.com/ccfos/nightingale/v6/center/metas"
@@ -73,6 +74,9 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 		taskTplsCache := memsto.NewTaskTplCache(ctx)
 
 		promClients := prom.NewPromClient(ctx)
+
+		dispatch.InitRegisterQueryFunc(promClients)
+
 		tdengineClients := tdengine.NewTdengineClient(ctx, config.Alert.Heartbeat)
 		externalProcessors := process.NewExternalProcessors()
 

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

@@ -50,7 +50,7 @@ Enable = true
 # user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
 [HTTP.APIForService]
-Enable = true 
+Enable = false
 [HTTP.APIForService.BasicAuth]
 user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 

docker/compose-host-network-metric-log/etc-nightingale/config.toml

@@ -50,7 +50,7 @@ Enable = true
 # user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
 [HTTP.APIForService]
-Enable = true 
+Enable = false
 [HTTP.APIForService.BasicAuth]
 user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 

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

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

docker/compose-host-network/etc-nightingale/config.toml

@@ -50,7 +50,7 @@ Enable = true
 # user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
 [HTTP.APIForService]
-Enable = true 
+Enable = false
 [HTTP.APIForService.BasicAuth]
 user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 

docker/compose-postgres/n9eetc_pg/config.toml

@@ -50,7 +50,7 @@ Enable = true
 # user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
 [HTTP.APIForService]
-Enable = true 
+Enable = false
 [HTTP.APIForService.BasicAuth]
 user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 

docker/initsql/c-init.sql

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

docker/migratesql/migrate.sql

@@ -116,4 +116,12 @@ CREATE TABLE `target_busi_group` (
   `update_at` bigint NOT NULL,
   PRIMARY KEY (`id`),
   UNIQUE KEY `idx_target_group` (`target_ident`,`group_id`)
-) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
+
+/* v7.7.2 2024-12-02 */
+ALTER TABLE alert_subscribe MODIFY COLUMN rule_ids varchar(1024);
+ALTER TABLE alert_subscribe MODIFY COLUMN busi_groups varchar(4096);
+
+/* v8.0.0-beta.1 2024-12-13 */
+ALTER TABLE `alert_rule` ADD COLUMN `cron_pattern` VARCHAR(64);
+ALTER TABLE `builtin_components` MODIFY COLUMN `logo` mediumtext COMMENT '''logo of component''';

docker/sqlite.sql

@@ -17,6 +17,8 @@ CREATE TABLE `users` (
     `update_by` varchar(64) not null default ''
 );
 
+CREATE UNIQUE INDEX idx_users_username ON `users` (username);
+
 insert into `users`(id, username, nickname, password, roles, create_at, create_by, update_at, update_by) values(1, 'root', '超管', 'root.2020', 'Admin', strftime('%s', 'now'), 'system', strftime('%s', 'now'), 'system');
 
 CREATE TABLE `user_group` (
@@ -182,8 +184,9 @@ CREATE TABLE `board` (
     `create_by` varchar(64) not null default '',
     `update_at` bigint not null default 0,
     `update_by` varchar(64) not null default '',
-    unique (`group_id`, `name`)
+    `public_cate` bigint not null default 0
 );
+CREATE UNIQUE INDEX idx_board_group_id_name ON `board` (group_id, name);
 CREATE INDEX `idx_board_ident` ON `board` (`ident` asc);
 
 -- for dashboard new version
@@ -192,6 +195,15 @@ CREATE TABLE `board_payload` (
     `payload` mediumtext not null
 );
 
+CREATE TABLE `chart` (
+    `id` integer primary key autoincrement,
+    `group_id` integer not null,
+    `configs` text,
+    `weight` integer not null default 0
+);
+
+CREATE INDEX idx_chart_group_id ON `chart` (group_id);
+
 CREATE TABLE `chart_share` (
     `id` integer primary key autoincrement,
     `cluster` varchar(128) not null,
@@ -238,7 +250,9 @@ CREATE TABLE `alert_rule` (
     `create_at` bigint not null default 0,
     `create_by` varchar(64) not null default '',
     `update_at` bigint not null default 0,
-    `update_by` varchar(64) not null default ''
+    `update_by` varchar(64) not null default '',
+    `cron_pattern` varchar(64),
+    `datasource_queries` text
 );
 CREATE INDEX `idx_alert_rule_group_id` ON `alert_rule` (`group_id` asc);
 CREATE INDEX `idx_alert_rule_update_at` ON `alert_rule` (`update_at` asc);
@@ -308,11 +322,18 @@ CREATE TABLE `target` (
     `tags` varchar(512) not null default '',
     `host_ip` varchar(15) default '',
     `agent_version` varchar(255) default '',
+    `host_tags` text,
     `engine_name` varchar(255) default '',
+    `os` varchar(31) default '',
     `update_at` bigint not null default 0
 );
-CREATE INDEX `idx_target_group_id` ON `target` (`group_id` asc);
 
+CREATE INDEX `idx_target_group_id` ON `target` (`group_id` asc);
+CREATE UNIQUE INDEX idx_target_ident ON `target` (ident);
+CREATE INDEX idx_host_ip ON `target` (host_ip);
+CREATE INDEX idx_agent_version ON `target` (agent_version);
+CREATE INDEX idx_engine_name ON `target` (engine_name);
+CREATE INDEX idx_os ON `target` (os);
 
 CREATE TABLE `metric_view` (
     `id` integer primary key autoincrement,
@@ -337,12 +358,14 @@ CREATE TABLE `recording_rule` (
     `disabled` tinyint(1) not null default 0,
     `prom_ql` varchar(8192) not null,
     `prom_eval_interval` int not null,
+    `cron_pattern` varchar(255) default '',
     `append_tags` varchar(255) default '',
     `query_configs` text not null,
     `create_at` bigint default '0',
     `create_by` varchar(64) default '',
     `update_at` bigint default '0',
-    `update_by` varchar(64) default ''
+    `update_by` varchar(64) default '',
+    `datasource_queries` text
 );
 CREATE INDEX `idx_recording_rule_group_id` ON `recording_rule` (`group_id` asc);
 CREATE INDEX `idx_recording_rule_update_at` ON `recording_rule` (`update_at` asc);
@@ -430,6 +453,7 @@ CREATE TABLE `alert_his_event` (
     `trigger_value` varchar(2048) not null,
     `recover_time` bigint not null default 0,
     `last_eval_time` bigint not null default 0,
+    `original_tags` varchar(8192),
     `tags` varchar(1024) not null default '',
     `annotations` text not null,
     `rule_config` text not null
@@ -459,6 +483,8 @@ CREATE INDEX `idx_builtin_components_ident` ON `builtin_components` (`ident` asc
 
 CREATE TABLE `builtin_payloads` (
   `id` integer primary key autoincrement,
+  `component_id` integer not null default 0,
+  `uuid` integer not null,
   `type` varchar(191) not null,
   `component` varchar(191) not null,
   `cate` varchar(191) not null,
@@ -474,6 +500,20 @@ CREATE INDEX `idx_builtin_payloads_component` ON `builtin_payloads` (`component`
 CREATE INDEX `idx_builtin_payloads_name` ON `builtin_payloads` (`name` asc);
 CREATE INDEX `idx_builtin_payloads_cate` ON `builtin_payloads` (`cate` asc);
 CREATE INDEX `idx_builtin_payloads_type` ON `builtin_payloads` (`type` asc);
+CREATE INDEX idx_uuid ON `builtin_payloads` (uuid);
+
+
+CREATE TABLE `notification_record` (
+    `id` integer primary key autoincrement,
+    `event_id` integer not null,
+    `sub_id` integer,
+    `channel` varchar(255) not null,
+    `status` integer,
+    `target` varchar(1024) not null,
+    `details` varchar(2048) default '',
+    `created_at` integer not null
+);
+CREATE INDEX idx_evt ON notification_record (event_id);
 
 CREATE TABLE `task_tpl` (
     `id`        integer primary key autoincrement,
@@ -553,6 +593,8 @@ CREATE TABLE `datasource`
     `updated_by` varchar(64) not null default ''
 );
 
+CREATE UNIQUE INDEX idx_datasource_name ON datasource (name);
+
 CREATE TABLE `builtin_cate` (
     `id` integer primary key autoincrement,
     `name` varchar(191) not null,
@@ -570,6 +612,8 @@ CREATE TABLE `notify_tpl` (
     `update_by` varchar(64) not null default ''
 );
 
+CREATE UNIQUE INDEX idx_notify_tpl_channel ON notify_tpl (channel);
+
 CREATE TABLE `sso_config` (
     `id` integer primary key autoincrement,
     `name` varchar(191) not null unique,
@@ -577,6 +621,8 @@ CREATE TABLE `sso_config` (
     `update_at` bigint not null default 0
 );
 
+CREATE UNIQUE INDEX idx_sso_config_name ON sso_config (name);
+
 CREATE TABLE `es_index_pattern` (
     `id` integer primary key autoincrement,
     `datasource_id` bigint not null default 0,
@@ -591,6 +637,8 @@ CREATE TABLE `es_index_pattern` (
     unique (`datasource_id`, `name`)
 );
 
+CREATE UNIQUE INDEX idx_es_index_pattern_datasource_id_name ON es_index_pattern (datasource_id, name);
+
 CREATE TABLE `builtin_metrics` (
     `id` integer primary key autoincrement,
     `collector` varchar(191) NOT NULL,
@@ -603,13 +651,15 @@ CREATE TABLE `builtin_metrics` (
     `created_at` bigint NOT NULL DEFAULT 0,
     `created_by` varchar(191) NOT NULL DEFAULT '',
     `updated_at` bigint NOT NULL DEFAULT 0,
-    `updated_by` varchar(191) NOT NULL DEFAULT ''
+    `updated_by` varchar(191) NOT NULL DEFAULT '',
+    `uuid integer` not null default 0
 );
--- CREATE UNIQUE INDEX `idx_builtin_metrics_collector_typ_name` ON `builtin_metrics` (`lang`,`collector`, `typ`, `name` asc);
--- CREATE INDEX `idx_builtin_metrics_collector` ON `builtin_metrics` (`collector` asc);
--- CREATE INDEX `idx_builtin_metrics_typ` ON `builtin_metrics` (`typ` asc);
--- CREATE INDEX `idx_builtin_metrics_name` ON `builtin_metrics` (`name` asc);
--- CREATE INDEX `idx_builtin_metrics_lang` ON `builtin_metrics` (`lang` asc);
+
+CREATE UNIQUE INDEX idx_collector_typ_name ON builtin_metrics (lang, collector, typ, name);
+CREATE INDEX idx_collector ON builtin_metrics (collector);
+CREATE INDEX idx_typ ON builtin_metrics (typ);
+CREATE INDEX idx_builtinmetric_name ON builtin_metrics (name);
+CREATE INDEX idx_lang ON builtin_metrics (lang);
 
 
 CREATE TABLE `metric_filter` (
@@ -624,6 +674,14 @@ CREATE TABLE `metric_filter` (
 );
 CREATE INDEX `idx_metric_filter_name` ON `metric_filter` (`name` asc);
 
+CREATE TABLE `target_busi_group` (
+    `id` integer primary key autoincrement,
+    `target_ident` varchar(191) not null,
+    `group_id` integer not null,
+    `update_at` integer not null
+);
+
+CREATE UNIQUE INDEX idx_target_busi_group ON target_busi_group (target_ident, group_id);
 
 CREATE TABLE `task_meta`
 (

etc/config.toml

@@ -50,7 +50,7 @@ Enable = true
 # user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
 [HTTP.APIForService]
-Enable = true 
+Enable = false
 [HTTP.APIForService.BasicAuth]
 user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
@@ -73,14 +73,14 @@ DefaultRoles = ["Standard"]
 OpenRSA = false
 
 [DB]
+# mysql postgres sqlite
+DBType = "sqlite"
 # postgres: host=%s port=%s user=%s dbname=%s password=%s sslmode=%s
 # postgres: DSN="host=127.0.0.1 port=5432 user=root dbname=n9e_v6 password=1234 sslmode=disable"
-# sqlite: DSN="/path/to/filename.db"
-DSN = "root:1234@tcp(127.0.0.1:3306)/n9e_v6?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"
+# mysql: DSN="root:1234@tcp(localhost:3306)/n9e_v6?charset=utf8mb4&parseTime=True&loc=Local"
+DSN = "n9e.db"
 # enable debug mode or not
 Debug = false
-# mysql postgres sqlite
-DBType = "mysql"
 # unit: s
 MaxLifetime = 7200
 # max open connections
@@ -98,8 +98,8 @@ Address = "127.0.0.1:6379"
 # DB = 0
 # UseTLS = false
 # TLSMinVersion = "1.2"
-# standalone cluster sentinel
-RedisType = "standalone"
+# standalone cluster sentinel miniredis
+RedisType = "miniredis"
 # Mastername for sentinel type
 # MasterName = "mymaster"
 # SentinelUsername = ""
@@ -138,6 +138,9 @@ ForceUseServerTS = true
 # [Pushgw.WriterOpt]
 # QueueMaxSize = 1000000
 # QueuePopSize = 1000
+# AllQueueMaxSize = 1000000
+# fresh time, unit ms
+# AllQueueMaxSizeInterval = 200
 
 [[Pushgw.Writers]] 
 # Url = "http://127.0.0.1:8480/insert/0/prometheus/api/v1/write"

etc/edge/edge.toml

@@ -54,7 +54,7 @@ Enable = true
 # user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
 [HTTP.APIForService]
-Enable = true 
+Enable = false
 [HTTP.APIForService.BasicAuth]
 user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 

go.mod

@@ -11,6 +11,7 @@ require (
 	github.com/flashcatcloud/ibex v1.3.5
 	github.com/gin-contrib/pprof v1.4.0
 	github.com/gin-gonic/gin v1.9.1
+	github.com/glebarez/sqlite v1.11.0
 	github.com/go-ldap/ldap/v3 v3.4.4
 	github.com/gogo/protobuf v1.3.2
 	github.com/golang-jwt/jwt v3.2.2+incompatible
@@ -42,13 +43,25 @@ require (
 	gorm.io/driver/mysql v1.4.4
 	gorm.io/driver/postgres v1.4.5
 	gorm.io/driver/sqlite v1.5.5
-	gorm.io/gorm v1.25.7-0.20240204074919-46816ad31dde
+	gorm.io/gorm v1.25.7
 )
 
-require github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
+require (
+	github.com/alicebob/gopher-json v0.0.0-20200520072559-a9ecdc9d1d3a // indirect
+	github.com/dustin/go-humanize v1.0.1 // indirect
+	github.com/glebarez/go-sqlite v1.21.2 // indirect
+	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
+	github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
+	github.com/yuin/gopher-lua v1.1.1 // indirect
+	modernc.org/libc v1.22.5 // indirect
+	modernc.org/mathutil v1.5.0 // indirect
+	modernc.org/memory v1.5.0 // indirect
+	modernc.org/sqlite v1.23.1 // indirect
+)
 
 require (
 	github.com/Azure/go-ntlmssp v0.0.0-20220621081337-cb9428e4ac1e // indirect
+	github.com/alicebob/miniredis/v2 v2.33.0
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/bytedance/sonic v1.9.1 // indirect
 	github.com/cespare/xxhash/v2 v2.2.0 // indirect
@@ -97,11 +110,11 @@ require (
 	go.uber.org/atomic v1.11.0 // indirect
 	go.uber.org/automaxprocs v1.5.2 // indirect
 	golang.org/x/arch v0.3.0 // indirect
-	golang.org/x/crypto v0.21.0 // indirect
+	golang.org/x/crypto v0.31.0 // indirect
 	golang.org/x/image v0.18.0 // indirect
 	golang.org/x/net v0.23.0 // indirect
-	golang.org/x/sys v0.18.0 // indirect
-	golang.org/x/text v0.16.0 // indirect
+	golang.org/x/sys v0.28.0 // indirect
+	golang.org/x/text v0.21.0 // indirect
 	google.golang.org/appengine v1.6.7 // indirect
 	google.golang.org/protobuf v1.33.0 // indirect
 	gopkg.in/alexcesaro/quotedprintable.v3 v3.0.0-20150716171945-2caba252f4dc // indirect

go.sum

@@ -15,6 +15,10 @@ github.com/Masterminds/semver/v3 v3.1.1 h1:hLg3sBzpNErnxhQtUy/mmLR2I9foDujNK030I
 github.com/Masterminds/semver/v3 v3.1.1/go.mod h1:VPu/7SZ7ePZ3QOrcuXROw5FAcLl4a0cBrbBpGY/8hQs=
 github.com/alecthomas/units v0.0.0-20211218093645-b94a6e3cc137 h1:s6gZFSlWYmbqAuRjVTiNNhvNRfY2Wxp9nhfyel4rklc=
 github.com/alecthomas/units v0.0.0-20211218093645-b94a6e3cc137/go.mod h1:OMCwj8VM1Kc9e19TLln2VL61YJF0x1XFtfdL4JdbSyE=
+github.com/alicebob/gopher-json v0.0.0-20200520072559-a9ecdc9d1d3a h1:HbKu58rmZpUGpz5+4FfNmIU+FmZg2P3Xaj2v2bfNWmk=
+github.com/alicebob/gopher-json v0.0.0-20200520072559-a9ecdc9d1d3a/go.mod h1:SGnFV6hVsYE877CKEZ6tDNTjaSXYUk6QqoIK6PrAtcc=
+github.com/alicebob/miniredis/v2 v2.33.0 h1:uvTF0EDeu9RLnUEG27Db5I68ESoIxTiXbNUiji6lZrA=
+github.com/alicebob/miniredis/v2 v2.33.0/go.mod h1:MhP4a3EU7aENRi9aO+tHfTBZicLqQevyi/DJpoj6mi0=
 github.com/aws/aws-sdk-go v1.44.302 h1:ST3ko6GrJKn3Xi+nAvxjG3uk/V1pW8KC52WLeIxqqNk=
 github.com/aws/aws-sdk-go v1.44.302/go.mod h1:aVsgQcEevwlmQ7qHE9I3h+dtQgpqhFB+i8Phjh7fkwI=
 github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
@@ -49,6 +53,8 @@ github.com/dgrijalva/jwt-go v3.2.0+incompatible h1:7qlOGliEKZXTDg6OTjfoBKDXWrumC
 github.com/dgrijalva/jwt-go v3.2.0+incompatible/go.mod h1:E3ru+11k8xSBh+hMPgOLZmtrrCbhqsmaPHjLKYnJCaQ=
 github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f h1:lO4WD4F/rVNCu3HqELle0jiPLLBs70cWOduZpkS1E78=
 github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f/go.mod h1:cuUVRXasLTGF7a8hSLbxyZXjz+1KgoB3wDUb6vlszIc=
+github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
+github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
 github.com/expr-lang/expr v1.16.1 h1:Na8CUcMdyGbnNpShY7kzcHCU7WqxuL+hnxgHZ4vaz/A=
 github.com/expr-lang/expr v1.16.1/go.mod h1:uCkhfG+x7fcZ5A5sXHKuQ07jGZRl6J0FCAaf2k4PtVQ=
 github.com/fatih/camelcase v1.0.0 h1:hxNvNX/xYBp0ovncs8WyWZrOrpBNub/JfaMvbURyft8=
@@ -67,6 +73,10 @@ github.com/gin-contrib/sse v0.1.0/go.mod h1:RHrZQHXnP2xjPF+u1gW/2HnVO7nvIa9PG3Gm
 github.com/gin-gonic/gin v1.8.1/go.mod h1:ji8BvRH1azfM+SYow9zQ6SZMvR8qOMZHmsCuWR9tTTk=
 github.com/gin-gonic/gin v1.9.1 h1:4idEAncQnU5cB7BeOkPtxjfCSye0AAm1R0RVIqJ+Jmg=
 github.com/gin-gonic/gin v1.9.1/go.mod h1:hPrL7YrpYKXt5YId3A/Tnip5kqbEAP+KLuI3SUcPTeU=
+github.com/glebarez/go-sqlite v1.21.2 h1:3a6LFC4sKahUunAmynQKLZceZCOzUthkRkEAl9gAXWo=
+github.com/glebarez/go-sqlite v1.21.2/go.mod h1:sfxdZyhQjTM2Wry3gVYWaW072Ri1WMdWJi0k6+3382k=
+github.com/glebarez/sqlite v1.11.0 h1:wSG0irqzP6VurnMEpFGer5Li19RpIRi2qvQz++w0GMw=
+github.com/glebarez/sqlite v1.11.0/go.mod h1:h8/o8j5wiAsqSPoWELDUdJXhjAhsVliSn7bWZjOhrgQ=
 github.com/go-asn1-ber/asn1-ber v1.5.4 h1:vXT6d/FNDiELJnLb6hGNa309LMsrCoYFvpwHDF0+Y1A=
 github.com/go-asn1-ber/asn1-ber v1.5.4/go.mod h1:hEBeB/ic+5LoWskz+yKT7vGhhPYkProFKoKdwZRWMe0=
 github.com/go-kit/log v0.1.0/go.mod h1:zbhenjAZHb184qTLMA9ZjW7ThYL0H2mk7Q6pNt4vbaY=
@@ -116,6 +126,8 @@ github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/
 github.com/google/go-cmp v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38=
 github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
+github.com/google/pprof v0.0.0-20230705174524-200ffdc848b8 h1:n6vlPhxsA+BW/XsS5+uqi7GyzaLa5MH7qlSLBZtRdiA=
+github.com/google/pprof v0.0.0-20230705174524-200ffdc848b8/go.mod h1:Jh3hGz2jkYak8qXPD19ryItVnUgpgeqzdkY/D0EaeuA=
 github.com/google/renameio v0.1.0/go.mod h1:KWCgfxg9yswjAJkECMjeO8J8rahYeXnNhOm40UhjYkI=
 github.com/google/uuid v1.3.0 h1:t6JiXgmwXMjEs8VusXIJk2BXHsn+wx8BZdTaoZ5fu7I=
 github.com/google/uuid v1.3.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
@@ -273,6 +285,9 @@ github.com/rakyll/statik v0.1.7 h1:OF3QCZUuyPxuGEP7B4ypUa7sB/iHtqOTDYZXGM8KOdQ=
 github.com/rakyll/statik v0.1.7/go.mod h1:AlZONWzMtEnMs7W4e/1LURLiI49pIMmp6V9Unghqrcc=
 github.com/redis/go-redis/v9 v9.0.2 h1:BA426Zqe/7r56kCcvxYLWe1mkaz71LKF77GwgFzSxfE=
 github.com/redis/go-redis/v9 v9.0.2/go.mod h1:/xDTe9EF1LM61hek62Poq2nzQSGj0xSrEtEHbBQevps=
+github.com/remyoudompheng/bigfft v0.0.0-20200410134404-eec4a21b6bb0/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
+github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
+github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
 github.com/robfig/cron/v3 v3.0.1 h1:WdRxkvbJztn8LMz/QEvLN5sBU+xKpSqwwUO1Pjr4qDs=
 github.com/robfig/cron/v3 v3.0.1/go.mod h1:eQICP3HwyT7UooqI/z+Ov+PtYAWygg1TEWWzGIFLtro=
 github.com/robfig/go-cache v0.0.0-20130306151617-9fc39e0dbf62/go.mod h1:65XQgovT59RWatovFwnwocoUxiI/eENTnOY5GK3STuY=
@@ -328,6 +343,8 @@ github.com/ugorji/go/codec v1.2.11/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZ
 github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
+github.com/yuin/gopher-lua v1.1.1 h1:kYKnWBjvbNP4XLT3+bPEwAXJx262OhaHDWDVOPjL46M=
+github.com/yuin/gopher-lua v1.1.1/go.mod h1:GBR0iDaNXjAgGg9zfCvksxSRnQx76gclCIb7kdAd1Pw=
 github.com/zenazn/goji v0.9.0/go.mod h1:7S9M489iMyHBNxwZnk9/EHS098H4/F6TATF2mIxtB1Q=
 go.uber.org/atomic v1.3.2/go.mod h1:gD2HeocX3+yG+ygLZcrzQJaqmWj9AIm7n08wl/qW/PE=
 go.uber.org/atomic v1.4.0/go.mod h1:gD2HeocX3+yG+ygLZcrzQJaqmWj9AIm7n08wl/qW/PE=
@@ -364,8 +381,8 @@ golang.org/x/crypto v0.0.0-20220622213112-05595931fe9d/go.mod h1:IxCIyHEi3zRg3s0
 golang.org/x/crypto v0.0.0-20220722155217-630584e8d5aa/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
 golang.org/x/crypto v0.7.0/go.mod h1:pYwdfH91IfpZVANVyUOhSIPZaFoJGxTFbZhFTx+dXZU=
 golang.org/x/crypto v0.9.0/go.mod h1:yrmDGqONDYtNj3tH8X9dzUun2m2lzPa9ngI6/RUPGR0=
-golang.org/x/crypto v0.21.0 h1:X31++rzVUdKhX5sWmSOFZxx8UW/ldWx55cbf08iNAMA=
-golang.org/x/crypto v0.21.0/go.mod h1:0BP7YvVV9gBbVKyeTG0Gyn+gZm94bibOW5BjDEYAOMs=
+golang.org/x/crypto v0.31.0 h1:ihbySMvVjLAeSH1IbfcRTkD/iNscyz8rGzjF/E5hV6U=
+golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
 golang.org/x/exp v0.0.0-20230713183714-613f0c0eb8a1 h1:MGwJjxBy0HJshjDNfLsYO8xppfqWlA5ZT9OhtUUhTNw=
 golang.org/x/exp v0.0.0-20230713183714-613f0c0eb8a1/go.mod h1:FXUEEKJgO7OQYeo8N01OfiKP8RXMtf6e8aTskBGqWdc=
 golang.org/x/image v0.13.0/go.mod h1:6mmbMOeV28HuMTgA6OSRkdXKYw/t5W9Uwn2Yv1r3Yxk=
@@ -401,8 +418,8 @@ golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJ
 golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.7.0 h1:YsImfSBoP9QPYL0xyKJPq0gcaJdG3rInoqxTWbfQu9M=
-golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
+golang.org/x/sync v0.10.0 h1:3NQrjDixjgGwUOCaF8w2+VYHv0Ve/vGYSbdkTa98gmQ=
+golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190222072716-a9d3bda3a223/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
@@ -425,8 +442,8 @@ golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.18.0 h1:DBdB3niSjOA/O0blCZBqDefyWNYveAYMNF1Wum0DYQ4=
-golang.org/x/sys v0.18.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.28.0 h1:Fksou7UEQUWlKvIdsqzJmUmCX3cZuD2+P3XyyzwMhlA=
+golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201117132131-f5c789dd3221/go.mod h1:Nr5EML6q2oocZ2LXRh80K7BxOlk5/8JxuGnuhpl+muw=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
@@ -444,8 +461,8 @@ golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
 golang.org/x/text v0.8.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
 golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
 golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
-golang.org/x/text v0.16.0 h1:a94ExnEXNtEwYLGJSIUxnWoxoRz/ZcCsV63ROupILh4=
-golang.org/x/text v0.16.0/go.mod h1:GhwF1Be+LQoKShO3cGOHzqOgRrGaYc9AvblQOmPVHnI=
+golang.org/x/text v0.21.0 h1:zyQAAkrwaneQ066sspRyJaG9VNi/YJ1NfzcGB3hZ/qo=
+golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
 golang.org/x/tools v0.0.0-20190425163242-31fd60d6bfdc/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
@@ -500,7 +517,15 @@ gorm.io/driver/sqlite v1.5.5 h1:7MDMtUZhV065SilG62E0MquljeArQZNfJnjd9i9gx3E=
 gorm.io/driver/sqlite v1.5.5/go.mod h1:6NgQ7sQWAIFsPrJJl1lSNSu2TABh0ZZ/zm5fosATavE=
 gorm.io/gorm v1.23.8/go.mod h1:l2lP/RyAtc1ynaTjFksBde/O8v9oOGIApu2/xRitmZk=
 gorm.io/gorm v1.24.1-0.20221019064659-5dd2bb482755/go.mod h1:DVrVomtaYTbqs7gB/x2uVvqnXzv0nqjB396B8cG4dBA=
-gorm.io/gorm v1.25.7-0.20240204074919-46816ad31dde h1:9DShaph9qhkIYw7QF91I/ynrr4cOO2PZra2PFD7Mfeg=
-gorm.io/gorm v1.25.7-0.20240204074919-46816ad31dde/go.mod h1:hbnx/Oo0ChWMn1BIhpy1oYozzpM15i4YPuHDmfYtwg8=
+gorm.io/gorm v1.25.7 h1:VsD6acwRjz2zFxGO50gPO6AkNs7KKnvfzUjHQhZDz/A=
+gorm.io/gorm v1.25.7/go.mod h1:hbnx/Oo0ChWMn1BIhpy1oYozzpM15i4YPuHDmfYtwg8=
 honnef.co/go/tools v0.0.1-2019.2.3/go.mod h1:a3bituU0lyd329TUQxRnasdCoJDkEUEAqEt0JzvZhAg=
+modernc.org/libc v1.22.5 h1:91BNch/e5B0uPbJFgqbxXuOnxBQjlS//icfQEGmvyjE=
+modernc.org/libc v1.22.5/go.mod h1:jj+Z7dTNX8fBScMVNRAYZ/jF91K8fdT2hYMThc3YjBY=
+modernc.org/mathutil v1.5.0 h1:rV0Ko/6SfM+8G+yKiyI830l3Wuz1zRutdslNoQ0kfiQ=
+modernc.org/mathutil v1.5.0/go.mod h1:mZW8CKdRPY1v87qxC/wUdX5O1qDzXMP5TH3wjfpga6E=
+modernc.org/memory v1.5.0 h1:N+/8c5rE6EqugZwHii4IFsaJ7MUhoWX07J5tC/iI5Ds=
+modernc.org/memory v1.5.0/go.mod h1:PkUhL0Mugw21sHPeskwZW4D6VscE/GQJOnIpCnW6pSU=
+modernc.org/sqlite v1.23.1 h1:nrSBg4aRQQwq59JpvGEQ15tNxoO5pX/kUjcRNwSAGQM=
+modernc.org/sqlite v1.23.1/go.mod h1:OrDj17Mggn6MhE+iPbBNf7RGKODDE9NFT0f3EwDzJqk=
 rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=

integrations/MongoDB/dashboards/mongo_by_exporter.json

@@ -1,5 +1,5 @@
 {
-    "name": "MongoDB by instance",
+    "name": "MongoDB Overview by exporter",
     "tags": "Prometheus MongoDB",
     "ident": "",
     "configs": {
@@ -9,11 +9,11 @@
                 "id": "939298f2-b21f-4e2f-9142-c10946cc4032",
                 "layout": {
                     "h": 1,
+                    "i": "939298f2-b21f-4e2f-9142-c10946cc4032",
+                    "isResizable": false,
                     "w": 24,
                     "x": 0,
-                    "y": 0,
-                    "i": "939298f2-b21f-4e2f-9142-c10946cc4032",
-                    "isResizable": false
+                    "y": 0
                 },
                 "name": "Basic Info",
                 "type": "row"
@@ -32,12 +32,12 @@
                 "description": "instance count",
                 "id": "91970d24-3f04-4424-a1ed-73e7d28f5706",
                 "layout": {
-                    "h": 4,
+                    "h": 7,
+                    "i": "91970d24-3f04-4424-a1ed-73e7d28f5706",
+                    "isResizable": true,
                     "w": 6,
                     "x": 0,
-                    "y": 1,
-                    "i": "91970d24-3f04-4424-a1ed-73e7d28f5706",
-                    "isResizable": true
+                    "y": 1
                 },
                 "name": "Up",
                 "options": {
@@ -77,54 +77,39 @@
                 "version": "2.0.0"
             },
             {
-                "type": "stat",
-                "id": "c7b52e8e-b417-4c61-a15e-e2f186fccd67",
-                "layout": {
-                    "h": 4,
-                    "w": 6,
-                    "x": 6,
-                    "y": 1,
-                    "i": "c7b52e8e-b417-4c61-a15e-e2f186fccd67",
-                    "isResizable": true
-                },
-                "version": "3.0.0",
-                "datasourceCate": "prometheus",
-                "datasourceValue": "${prom}",
-                "targets": [
-                    {
-                        "expr": "mongodb_ss_uptime{instance=\"$instance\"}",
-                        "refId": "A",
-                        "maxDataPoints": 240
-                    }
-                ],
-                "transformations": [
-                    {
-                        "id": "organize",
-                        "options": {}
-                    }
-                ],
-                "name": "Uptime",
-                "description": "Uptime",
-                "maxPerRow": 4,
                 "custom": {
-                    "textMode": "value",
-                    "graphMode": "none",
-                    "colorMode": "value",
                     "calc": "lastNotNull",
-                    "valueField": "Value",
                     "colSpan": 1,
+                    "colorMode": "value",
+                    "textMode": "value",
                     "textSize": {
                         "title": null
                     },
-                    "orientation": "auto"
+                    "valueField": "Value"
                 },
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "description": "Uptime",
+                "id": "c7b52e8e-b417-4c61-a15e-e2f186fccd67",
+                "layout": {
+                    "h": 7,
+                    "i": "c7b52e8e-b417-4c61-a15e-e2f186fccd67",
+                    "isResizable": true,
+                    "w": 6,
+                    "x": 6,
+                    "y": 1
+                },
+                "name": "Uptime",
                 "options": {
+                    "standardOptions": {
+                        "util": "humantimeSeconds"
+                    },
                     "thresholds": {
                         "steps": [
                             {
                                 "color": "#634CD9",
-                                "value": null,
-                                "type": "base"
+                                "type": "base",
+                                "value": null
                             }
                         ]
                     },
@@ -147,51 +132,34 @@
                             },
                             "type": "range"
                         }
-                    ],
-                    "standardOptions": {
-                        "util": "seconds",
-                        "decimals": 2
-                    }
+                    ]
                 },
-                "overrides": [
+                "targets": [
                     {
-                        "matcher": {
-                            "id": "byFrameRefID"
-                        },
-                        "properties": {
-                            "thresholds": {
-                                "steps": [
-                                    {
-                                        "color": "#6C53B1",
-                                        "value": null,
-                                        "type": "base"
-                                    }
-                                ]
-                            },
-                            "standardOptions": {
-                                "decimals": 0
-                            }
-                        }
+                        "expr": "mongodb_ss_uptime{instance=\"$instance\"}",
+                        "refId": "A"
                     }
-                ]
+                ],
+                "type": "stat",
+                "version": "2.0.0"
             },
             {
                 "type": "timeseries",
                 "id": "8446dded-9e11-4ee9-bdad-769b193ddf3e",
                 "layout": {
-                    "h": 4,
+                    "h": 7,
+                    "i": "8446dded-9e11-4ee9-bdad-769b193ddf3e",
+                    "isResizable": true,
                     "w": 6,
                     "x": 12,
-                    "y": 1,
-                    "i": "8446dded-9e11-4ee9-bdad-769b193ddf3e",
-                    "isResizable": true
+                    "y": 1
                 },
                 "version": "3.0.0",
                 "datasourceCate": "prometheus",
                 "datasourceValue": "${prom}",
                 "targets": [
                     {
-                        "expr": "mongodb_ss_mem_resident * 1024 * 1024",
+                        "expr": "mongodb_ss_mem_resident{instance='$instance'} * 1024 * 1024",
                         "legend": "{{type}}",
                         "refId": "A",
                         "maxDataPoints": 240
@@ -219,8 +187,7 @@
                         "selectMode": "single"
                     },
                     "standardOptions": {
-                        "util": "bytesIEC",
-                        "decimals": 2
+                        "util": "bytesIEC"
                     },
                     "thresholds": {
                         "steps": [
@@ -275,12 +242,12 @@
                 "description": "Page faults indicate that requests are processed from disk either because an index is missing or there is not enough memory for the data set. Consider increasing memory or sharding out.",
                 "id": "3eda28e7-2480-4ddc-b346-89ced1c33034",
                 "layout": {
-                    "h": 4,
+                    "h": 7,
+                    "i": "3eda28e7-2480-4ddc-b346-89ced1c33034",
+                    "isResizable": true,
                     "w": 6,
                     "x": 18,
-                    "y": 1,
-                    "i": "3eda28e7-2480-4ddc-b346-89ced1c33034",
-                    "isResizable": true
+                    "y": 1
                 },
                 "name": "Page Faults",
                 "options": {
@@ -333,12 +300,12 @@
                 "description": "Network traffic (bytes)",
                 "id": "528d0485-f947-470d-95f3-59eae157ebb6",
                 "layout": {
-                    "h": 4,
+                    "h": 7,
+                    "i": "528d0485-f947-470d-95f3-59eae157ebb6",
+                    "isResizable": true,
                     "w": 6,
                     "x": 0,
-                    "y": 5,
-                    "i": "528d0485-f947-470d-95f3-59eae157ebb6",
-                    "isResizable": true
+                    "y": 8
                 },
                 "name": "Network I/O",
                 "options": {
@@ -395,12 +362,12 @@
                 "description": "Number of connections Keep in mind the hard limit on the maximum number of connections set by your distribution.",
                 "id": "067e97c3-4e57-447f-a9dc-a49627b6ce18",
                 "layout": {
-                    "h": 4,
+                    "h": 7,
+                    "i": "067e97c3-4e57-447f-a9dc-a49627b6ce18",
+                    "isResizable": true,
                     "w": 6,
                     "x": 6,
-                    "y": 5,
-                    "i": "067e97c3-4e57-447f-a9dc-a49627b6ce18",
-                    "isResizable": true
+                    "y": 8
                 },
                 "name": "Connections",
                 "options": {
@@ -450,12 +417,12 @@
                 "description": "Number of assertion errors, Asserts are not important by themselves, but you can correlate spikes with other graphs.",
                 "id": "9e9b7356-cf0e-4e5f-95f5-00258c576bf4",
                 "layout": {
-                    "h": 4,
+                    "h": 7,
+                    "i": "9e9b7356-cf0e-4e5f-95f5-00258c576bf4",
+                    "isResizable": true,
                     "w": 6,
                     "x": 12,
-                    "y": 5,
-                    "i": "9e9b7356-cf0e-4e5f-95f5-00258c576bf4",
-                    "isResizable": true
+                    "y": 8
                 },
                 "name": "Assert Events",
                 "options": {
@@ -505,12 +472,12 @@
                 "description": "Number of operations waiting to acquire locks, Any number of queued operations for long periods of time is an indication of possible issues. Find the cause and fix it before requests get stuck in the queue.",
                 "id": "2698f0f8-a76a-499b-99cf-30504f0f4db6",
                 "layout": {
-                    "h": 4,
+                    "h": 7,
+                    "i": "2698f0f8-a76a-499b-99cf-30504f0f4db6",
+                    "isResizable": true,
                     "w": 6,
                     "x": 18,
-                    "y": 5,
-                    "i": "2698f0f8-a76a-499b-99cf-30504f0f4db6",
-                    "isResizable": true
+                    "y": 8
                 },
                 "name": "Lock Queue",
                 "options": {
@@ -547,11 +514,11 @@
                 "id": "2bdb8cc9-92f4-449e-8f70-a4c470a21604",
                 "layout": {
                     "h": 1,
+                    "i": "2bdb8cc9-92f4-449e-8f70-a4c470a21604",
+                    "isResizable": false,
                     "w": 24,
                     "x": 0,
-                    "y": 9,
-                    "i": "2bdb8cc9-92f4-449e-8f70-a4c470a21604",
-                    "isResizable": false
+                    "y": 15
                 },
                 "name": "Operation Info",
                 "type": "row"
@@ -574,12 +541,12 @@
                 "description": "Number of requests received Shows how many times a command is executed per second on average during the selected interval.",
                 "id": "c2819508-95e7-4c63-aeae-ce19f92469cd",
                 "layout": {
-                    "h": 5,
+                    "h": 7,
+                    "i": "c2819508-95e7-4c63-aeae-ce19f92469cd",
+                    "isResizable": true,
                     "w": 12,
                     "x": 0,
-                    "y": 10,
-                    "i": "c2819508-95e7-4c63-aeae-ce19f92469cd",
-                    "isResizable": true
+                    "y": 16
                 },
                 "name": "Command Operations",
                 "options": {
@@ -625,12 +592,12 @@
                 "type": "timeseries",
                 "id": "7030d97a-d69f-4916-a415-ec57503ab1ed",
                 "layout": {
-                    "h": 5,
+                    "h": 7,
+                    "i": "7030d97a-d69f-4916-a415-ec57503ab1ed",
+                    "isResizable": true,
                     "w": 12,
                     "x": 12,
-                    "y": 10,
-                    "i": "7030d97a-d69f-4916-a415-ec57503ab1ed",
-                    "isResizable": true
+                    "y": 16
                 },
                 "version": "3.0.0",
                 "datasourceCate": "prometheus",
@@ -704,19 +671,19 @@
                 "type": "timeseries",
                 "id": "1c3b73d5-c25c-449f-995d-26acc9c621e1",
                 "layout": {
-                    "h": 5,
+                    "h": 7,
+                    "i": "1c3b73d5-c25c-449f-995d-26acc9c621e1",
+                    "isResizable": true,
                     "w": 8,
                     "x": 0,
-                    "y": 15,
-                    "i": "1c3b73d5-c25c-449f-995d-26acc9c621e1",
-                    "isResizable": true
+                    "y": 23
                 },
                 "version": "3.0.0",
                 "datasourceCate": "prometheus",
                 "datasourceValue": "${prom}",
                 "targets": [
                     {
-                        "expr": "rate(mongodb_ss_opLatencies_latency{}[5m]) / rate(mongodb_ss_opLatencies_latency{}[5m]) / 1000",
+                        "expr": "rate(mongodb_ss_opLatencies_latency{instance='$instance'}[5m]) / rate(mongodb_ss_opLatencies_latency{instance='$instance'}[5m]) / 1000",
                         "legend": "{{op_type}}",
                         "refId": "A",
                         "maxDataPoints": 240
@@ -799,12 +766,12 @@
                 "description": "",
                 "id": "e642183c-8ba2-4f60-abc6-c65de49e7577",
                 "layout": {
-                    "h": 5,
+                    "h": 7,
+                    "i": "e642183c-8ba2-4f60-abc6-c65de49e7577",
+                    "isResizable": true,
                     "w": 8,
                     "x": 8,
-                    "y": 15,
-                    "i": "e642183c-8ba2-4f60-abc6-c65de49e7577",
-                    "isResizable": true
+                    "y": 23
                 },
                 "name": "Query Efficiency",
                 "options": {
@@ -861,12 +828,12 @@
                 "description": "number of cursors Helps identify why connections are increasing. Shows active cursors compared to cursors being automatically killed after 10 minutes due to an application not closing the connection.",
                 "id": "8b5a4f44-3291-4822-ab73-f56be6c62674",
                 "layout": {
-                    "h": 5,
+                    "h": 7,
+                    "i": "8b5a4f44-3291-4822-ab73-f56be6c62674",
+                    "isResizable": true,
                     "w": 8,
                     "x": 16,
-                    "y": 15,
-                    "i": "8b5a4f44-3291-4822-ab73-f56be6c62674",
-                    "isResizable": true
+                    "y": 23
                 },
                 "name": "Cursors",
                 "options": {
@@ -903,11 +870,11 @@
                 "id": "06946b19-94b4-4f72-bd87-70f87989257d",
                 "layout": {
                     "h": 1,
+                    "i": "06946b19-94b4-4f72-bd87-70f87989257d",
+                    "isResizable": false,
                     "w": 24,
                     "x": 0,
-                    "y": 20,
-                    "i": "06946b19-94b4-4f72-bd87-70f87989257d",
-                    "isResizable": false
+                    "y": 30
                 },
                 "name": "Cache Info",
                 "panels": [],
@@ -917,19 +884,19 @@
                 "type": "timeseries",
                 "id": "bb0ae571-43a1-430b-8f63-256f6f1ebee6",
                 "layout": {
-                    "h": 5,
+                    "h": 7,
+                    "i": "bb0ae571-43a1-430b-8f63-256f6f1ebee6",
+                    "isResizable": true,
                     "w": 6,
                     "x": 0,
-                    "y": 21,
-                    "i": "bb0ae571-43a1-430b-8f63-256f6f1ebee6",
-                    "isResizable": true
+                    "y": 31
                 },
                 "version": "3.0.0",
                 "datasourceCate": "prometheus",
                 "datasourceValue": "${prom}",
                 "targets": [
                     {
-                        "expr": "mongodb_ss_wt_cache_bytes_currently_in_the_cache{}",
+                        "expr": "mongodb_ss_wt_cache_bytes_currently_in_the_cache{instance='$instance'}",
                         "legend": "total",
                         "refId": "A",
                         "maxDataPoints": 240
@@ -975,8 +942,7 @@
                         "selectMode": "single"
                     },
                     "standardOptions": {
-                        "util": "bytesIEC",
-                        "decimals": 2
+                        "util": "bytesIEC"
                     },
                     "thresholds": {
                         "steps": [
@@ -1017,19 +983,19 @@
                 "type": "timeseries",
                 "id": "f1ffd169-2a1a-42bc-9647-0e6621be0fef",
                 "layout": {
-                    "h": 5,
+                    "h": 7,
+                    "i": "f1ffd169-2a1a-42bc-9647-0e6621be0fef",
+                    "isResizable": true,
                     "w": 6,
                     "x": 6,
-                    "y": 21,
-                    "i": "f1ffd169-2a1a-42bc-9647-0e6621be0fef",
-                    "isResizable": true
+                    "y": 31
                 },
                 "version": "3.0.0",
                 "datasourceCate": "prometheus",
                 "datasourceValue": "${prom}",
                 "targets": [
                     {
-                        "expr": "rate(mongodb_ss_wt_cache_bytes_read_into_cache{}[5m])",
+                        "expr": "rate(mongodb_ss_wt_cache_bytes_read_into_cache{instance='$instance'}[5m])",
                         "legend": "read",
                         "refId": "A",
                         "maxDataPoints": 240
@@ -1104,19 +1070,19 @@
                 "type": "timeseries",
                 "id": "43ee140d-ae6d-474a-9892-fa4743d7f97e",
                 "layout": {
-                    "h": 5,
+                    "h": 7,
+                    "i": "43ee140d-ae6d-474a-9892-fa4743d7f97e",
+                    "isResizable": true,
                     "w": 6,
                     "x": 12,
-                    "y": 21,
-                    "i": "43ee140d-ae6d-474a-9892-fa4743d7f97e",
-                    "isResizable": true
+                    "y": 31
                 },
                 "version": "3.0.0",
                 "datasourceCate": "prometheus",
                 "datasourceValue": "${prom}",
                 "targets": [
                     {
-                        "expr": "100 * sum(mongodb_ss_wt_cache_tracked_dirty_pages_in_the_cache{}) / sum(mongodb_ss_wt_cache_pages_currently_held_in_the_cache{})",
+                        "expr": "100 * sum(mongodb_ss_wt_cache_tracked_dirty_pages_in_the_cache{instance='$instance'}) / sum(mongodb_ss_wt_cache_pages_currently_held_in_the_cache{instance='$instance'})",
                         "legend": "dirty rate",
                         "refId": "A",
                         "maxDataPoints": 240
@@ -1185,19 +1151,19 @@
                 "type": "timeseries",
                 "id": "1a22c31a-859a-400c-af2a-ae83c308d0f2",
                 "layout": {
-                    "h": 5,
+                    "h": 7,
+                    "i": "1a22c31a-859a-400c-af2a-ae83c308d0f2",
+                    "isResizable": true,
                     "w": 6,
                     "x": 18,
-                    "y": 21,
-                    "i": "1a22c31a-859a-400c-af2a-ae83c308d0f2",
-                    "isResizable": true
+                    "y": 31
                 },
                 "version": "3.0.0",
                 "datasourceCate": "prometheus",
                 "datasourceValue": "${prom}",
                 "targets": [
                     {
-                        "expr": "rate(mongodb_mongod_wiredtiger_cache_evicted_total{}[5m])",
+                        "expr": "rate(mongodb_mongod_wiredtiger_cache_evicted_total{instance='$instance'}[5m])",
                         "legend": "evicted pages",
                         "refId": "A",
                         "maxDataPoints": 240
@@ -1265,95 +1231,125 @@
                 "id": "b0016f4a-c565-4276-a08d-bacdf94b6b5a",
                 "layout": {
                     "h": 1,
+                    "i": "b0016f4a-c565-4276-a08d-bacdf94b6b5a",
+                    "isResizable": false,
                     "w": 24,
                     "x": 0,
-                    "y": 26,
-                    "i": "b0016f4a-c565-4276-a08d-bacdf94b6b5a",
-                    "isResizable": false
+                    "y": 45
                 },
                 "name": "ReplSet Info",
                 "type": "row"
             },
             {
-                "type": "timeseries",
-                "id": "f73fd0cd-ecbe-41f0-a2dc-4e02f7eaef1c",
-                "layout": {
-                    "h": 5,
-                    "w": 12,
-                    "x": 0,
-                    "y": 27,
-                    "i": "f73fd0cd-ecbe-41f0-a2dc-4e02f7eaef1c",
-                    "isResizable": true
+                "custom": {
+                    "calc": "lastNotNull",
+                    "colSpan": 1,
+                    "colorMode": "value",
+                    "textMode": "value",
+                    "textSize": {},
+                    "valueField": "Value"
                 },
-                "version": "3.0.0",
                 "datasourceCate": "prometheus",
                 "datasourceValue": "${prom}",
-                "targets": [
-                    {
-                        "expr": "mongodb_mongod_replset_member_replication_lag{instance=\"$instance\"}",
-                        "legend": "",
-                        "refId": "A",
-                        "maxDataPoints": 240
-                    }
-                ],
-                "transformations": [
-                    {
-                        "id": "organize",
-                        "options": {}
-                    }
-                ],
-                "name": "Replset Lag Seconds",
-                "description": "replica set member master-slave synchronization delay",
-                "maxPerRow": 4,
+                "description": "",
+                "id": "6187ceee-7c25-43f2-be1b-c44ad612ab52",
+                "layout": {
+                    "h": 7,
+                    "i": "6187ceee-7c25-43f2-be1b-c44ad612ab52",
+                    "isResizable": true,
+                    "w": 12,
+                    "x": 0,
+                    "y": 46
+                },
+                "name": "Replset Election",
                 "options": {
-                    "tooltip": {
-                        "mode": "all",
-                        "sort": "none"
-                    },
-                    "legend": {
-                        "displayMode": "hidden",
-                        "heightInPercentage": 30,
-                        "placement": "bottom",
-                        "behaviour": "showItem",
-                        "selectMode": "single"
-                    },
                     "standardOptions": {
+                        "decimals": 1,
                         "util": "seconds"
                     },
                     "thresholds": {
                         "steps": [
                             {
-                                "color": "#6C53B1",
-                                "value": null,
-                                "type": "base"
+                                "color": "#634CD9",
+                                "type": "base",
+                                "value": null
                             }
                         ]
-                    }
+                    },
+                    "valueMappings": [
+                        {
+                            "match": {
+                                "to": 1800
+                            },
+                            "result": {
+                                "color": "#f24526"
+                            },
+                            "type": "range"
+                        },
+                        {
+                            "match": {
+                                "from": 1800
+                            },
+                            "result": {
+                                "color": "#53b503"
+                            },
+                            "type": "range"
+                        }
+                    ]
                 },
+                "targets": [
+                    {
+                        "expr": "time() - mongodb_mongod_replset_member_election_date",
+                        "refId": "A"
+                    }
+                ],
+                "type": "stat",
+                "version": "2.0.0"
+            },
+            {
                 "custom": {
                     "drawStyle": "lines",
-                    "lineInterpolation": "smooth",
-                    "spanNulls": false,
-                    "lineWidth": 2,
                     "fillOpacity": 0.3,
                     "gradientMode": "opacity",
-                    "stack": "off",
-                    "scaleDistribution": {
-                        "type": "linear"
-                    },
-                    "showPoints": "none",
-                    "pointSize": 5
+                    "lineInterpolation": "smooth",
+                    "lineWidth": 2,
+                    "stack": "off"
                 },
-                "overrides": [
-                    {
-                        "matcher": {
-                            "id": "byFrameRefID"
-                        },
-                        "properties": {
-                            "rightYAxisDisplay": "off"
-                        }
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "description": "replica set member master-slave synchronization delay",
+                "id": "f73fd0cd-ecbe-41f0-a2dc-4e02f7eaef1c",
+                "layout": {
+                    "h": 7,
+                    "i": "f73fd0cd-ecbe-41f0-a2dc-4e02f7eaef1c",
+                    "isResizable": true,
+                    "w": 12,
+                    "x": 12,
+                    "y": 46
+                },
+                "name": "Replset Lag Seconds",
+                "options": {
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {
+                        "util": "seconds"
+                    },
+                    "thresholds": {},
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
                     }
-                ]
+                },
+                "targets": [
+                    {
+                        "expr": "mongodb_mongod_replset_member_replication_lag{instance=\"$instance\"}",
+                        "legend": "lag",
+                        "refId": "A"
+                    }
+                ],
+                "type": "timeseries",
+                "version": "2.0.0"
             }
         ],
         "var": [
@@ -1375,4 +1371,4 @@
         "version": "3.0.0"
     },
     "uuid": 1717556328065329000
-}
+}

memsto/notify_config.go

@@ -1,25 +1,28 @@
 package memsto
 
 import (
+	"crypto/tls"
 	"encoding/json"
+	"net/http"
 	"strings"
 	"sync"
 	"time"
 
-	"github.com/ccfos/nightingale/v6/pkg/tplx"
-
-	"github.com/BurntSushi/toml"
 	"github.com/ccfos/nightingale/v6/alert/aconf"
 	"github.com/ccfos/nightingale/v6/dumper"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
+	"github.com/ccfos/nightingale/v6/pkg/poster"
+	"github.com/ccfos/nightingale/v6/pkg/tplx"
+
+	"github.com/BurntSushi/toml"
 	"github.com/toolkits/pkg/logger"
 )
 
 type NotifyConfigCacheType struct {
 	ctx         *ctx.Context
 	ConfigCache *ConfigCache
-	webhooks    []*models.Webhook
+	webhooks    map[string]*models.Webhook
 	smtp        aconf.SMTPConfig
 	script      models.NotifyScript
 
@@ -47,6 +50,7 @@ func NewNotifyConfigCache(ctx *ctx.Context, configCache *ConfigCache) *NotifyCon
 	w := &NotifyConfigCacheType{
 		ctx:         ctx,
 		ConfigCache: configCache,
+		webhooks:    make(map[string]*models.Webhook),
 	}
 	w.SyncNotifyConfigs()
 	return w
@@ -85,11 +89,60 @@ func (w *NotifyConfigCacheType) syncNotifyConfigs() error {
 	}
 
 	if strings.TrimSpace(cval) != "" {
-		err = json.Unmarshal([]byte(cval), &w.webhooks)
+		var webhooks []*models.Webhook
+		err = json.Unmarshal([]byte(cval), &webhooks)
 		if err != nil {
 			dumper.PutSyncRecord("webhooks", start.Unix(), -1, -1, "failed to unmarshal configs.webhook: "+err.Error())
 			logger.Errorf("failed to unmarshal webhooks:%s error:%v", cval, err)
 		}
+
+		newWebhooks := make(map[string]*models.Webhook, len(webhooks))
+		for i := 0; i < len(webhooks); i++ {
+			if webhooks[i].Batch == 0 {
+				webhooks[i].Batch = 1000
+			}
+
+			if webhooks[i].Timeout == 0 {
+				webhooks[i].Timeout = 10
+			}
+
+			if webhooks[i].RetryCount == 0 {
+				webhooks[i].RetryCount = 10
+			}
+
+			if webhooks[i].RetryInterval == 0 {
+				webhooks[i].RetryInterval = 10
+			}
+
+			if webhooks[i].Client == nil {
+				transport := &http.Transport{
+					TLSClientConfig: &tls.Config{InsecureSkipVerify: webhooks[i].SkipVerify},
+				}
+				if poster.UseProxy(webhooks[i].Url) {
+					transport.Proxy = http.ProxyFromEnvironment
+				}
+				webhooks[i].Client = &http.Client{
+					Timeout:   time.Second * time.Duration(webhooks[i].Timeout),
+					Transport: transport,
+				}
+			}
+
+			newWebhooks[webhooks[i].Url] = webhooks[i]
+		}
+
+		for url, wh := range newWebhooks {
+			if oldWh, has := w.webhooks[url]; has && oldWh.Hash() != wh.Hash() {
+				w.webhooks[url] = wh
+			} else {
+				w.webhooks[url] = wh
+			}
+		}
+
+		for url := range w.webhooks {
+			if _, has := newWebhooks[url]; !has {
+				delete(w.webhooks, url)
+			}
+		}
 	}
 
 	dumper.PutSyncRecord("webhooks", start.Unix(), time.Since(start).Milliseconds(), len(w.webhooks), "success, webhooks:\n"+cval)
@@ -133,7 +186,7 @@ func (w *NotifyConfigCacheType) syncNotifyConfigs() error {
 	return nil
 }
 
-func (w *NotifyConfigCacheType) GetWebhooks() []*models.Webhook {
+func (w *NotifyConfigCacheType) GetWebhooks() map[string]*models.Webhook {
 	w.RWMutex.RLock()
 	defer w.RWMutex.RUnlock()
 	return w.webhooks

models/alert_cur_event.go

@@ -115,8 +115,18 @@ func (e *AlertCurEvent) ParseRule(field string) error {
 				"{{$value := .TriggerValue}}",
 			}
 
+			templateFuncMapCopy := tplx.NewTemplateFuncMap()
+			templateFuncMapCopy["query"] = func(promql string, param ...int64) []AnomalyPoint {
+				datasourceId := e.DatasourceId
+				if len(param) > 0 {
+					datasourceId = param[0]
+				}
+				value := tplx.Query(datasourceId, promql)
+				return ConvertAnomalyPoints(value)
+			}
+
 			text := strings.Join(append(defs, f), "")
-			t, err := template.New(fmt.Sprint(e.RuleId)).Funcs(template.FuncMap(tplx.TemplateFuncMap)).Parse(text)
+			t, err := template.New(fmt.Sprint(e.RuleId)).Funcs(templateFuncMapCopy).Parse(text)
 			if err != nil {
 				e.AnnotationsJSON[k] = fmt.Sprintf("failed to parse annotations: %v", err)
 				continue

models/alert_rule.go

@@ -103,6 +103,29 @@ type AlertRule struct {
 	UUID                  int64                  `json:"uuid" gorm:"-"` // tpl identifier
 	CurEventCount         int64                  `json:"cur_event_count" gorm:"-"`
 	UpdateByNickname      string                 `json:"update_by_nickname" gorm:"-"` // for fe
+	CronPattern           string                 `json:"cron_pattern"`
+}
+
+type ChildVarConfig struct {
+	ParamVal        []map[string]ParamQuery `json:"param_val"`
+	ChildVarConfigs *ChildVarConfig         `json:"child_var_configs"`
+}
+
+type ParamQuery struct {
+	ParamType string      `json:"param_type"` // host、device、enum、threshold 三种类型
+	Query     interface{} `json:"query"`
+}
+
+type VarConfig struct {
+	ParamVal        []ParamQueryForFirst `json:"param_val"`
+	ChildVarConfigs *ChildVarConfig      `json:"child_var_configs"`
+}
+
+// ParamQueryForFirst 同 ParamQuery，仅在第一层出现
+type ParamQueryForFirst struct {
+	Name      string      `json:"name"`
+	ParamType string      `json:"param_type"`
+	Query     interface{} `json:"query"`
 }
 
 type Tpl struct {
@@ -154,6 +177,8 @@ type HostRuleConfig struct {
 type PromQuery struct {
 	PromQl        string        `json:"prom_ql"`
 	Severity      int           `json:"severity"`
+	VarEnabled    bool          `json:"var_enabled"`
+	VarConfig     VarConfig     `json:"var_config"`
 	RecoverConfig RecoverConfig `json:"recover_config"`
 	Unit          string        `json:"unit"`
 }
@@ -347,12 +372,14 @@ func GetHostsQuery(queries []HostQuery) []map[string]interface{} {
 					blank += " "
 				}
 			} else {
-				blank := " "
+				var args []interface{}
+				var query []string
 				for _, tag := range lst {
-					m["tags not like ?"+blank] = "%" + tag + "%"
-					m["host_tags not like ?"+blank] = "%" + tag + "%"
-					blank += " "
+					query = append(query, "tags not like ?",
+						"(host_tags not like ? or host_tags is null)")
+					args = append(args, "%"+tag+"%", "%"+tag+"%")
 				}
+				m[strings.Join(query, " and ")] = args
 			}
 		case "hosts":
 			lst := []string{}
@@ -373,11 +400,13 @@ func GetHostsQuery(queries []HostQuery) []map[string]interface{} {
 					blank += " "
 				}
 			} else if q.Op == "!~" {
-				blank := " "
+				var args []interface{}
+				var query []string
 				for _, host := range lst {
-					m["ident not like ?"+blank] = strings.ReplaceAll(host, "*", "%")
-					blank += " "
+					query = append(query, "ident not like ?")
+					args = append(args, strings.ReplaceAll(host, "*", "%"))
 				}
+				m[strings.Join(query, " and ")] = args
 			}
 		}
 		query = append(query, m)
@@ -852,6 +881,11 @@ func (ar *AlertRule) DB2FE() error {
 	json.Unmarshal([]byte(ar.RuleConfig), &ruleConfig)
 	ar.EventRelabelConfig = ruleConfig.EventRelabelConfig
 
+	// 兼容旧逻辑填充 cron_pattern
+	if ar.CronPattern == "" && ar.PromEvalInterval != 0 {
+		ar.CronPattern = fmt.Sprintf("@every %ds", ar.PromEvalInterval)
+	}
+
 	err := ar.FillDatasourceQueries()
 	if err != nil {
 		return err
@@ -1111,7 +1145,6 @@ func (ar *AlertRule) UpdateEvent(event *AlertCurEvent) {
 	event.PromForDuration = ar.PromForDuration
 	event.RuleConfig = ar.RuleConfig
 	event.RuleConfigJson = ar.RuleConfigJson
-	event.PromEvalInterval = ar.PromEvalInterval
 	event.Callbacks = ar.Callbacks
 	event.CallbacksJSON = ar.CallbacksJSON
 	event.RunbookUrl = ar.RunbookUrl

models/anomaly_point.go

@@ -1,11 +1,10 @@
-package common
+package models
 
 import (
 	"fmt"
 	"math"
 	"strings"
 
-	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/unit"
 	"github.com/prometheus/common/model"
 )
@@ -20,7 +19,7 @@ type AnomalyPoint struct {
 	Query         string                         `json:"query"`
 	Values        string                         `json:"values"`
 	ValuesUnit    map[string]unit.FormattedValue `json:"values_unit"`
-	RecoverConfig models.RecoverConfig           `json:"recover_config"`
+	RecoverConfig RecoverConfig                  `json:"recover_config"`
 }
 
 func NewAnomalyPoint(key string, labels map[string]string, ts int64, value float64, severity int) AnomalyPoint {

models/builtin_component.go

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

models/builtin_metrics.go

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

models/busi_group.go

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

models/configs.go

@@ -130,7 +130,7 @@ func ConfigsGetAll(ctx *ctx.Context) ([]*Configs, error) { // select built-in ty
 	}
 
 	var lst []*Configs
-	err := DB(ctx).Model(&Configs{}).Select("ckey, cval").
+	err := DB(ctx).Model(&Configs{}).Select("id, ckey, cval").
 		Where("ckey!='' and external=? ", 0).Find(&lst).Error
 	if err != nil {
 		return nil, errors.WithMessage(err, "failed to query configs")

models/migrate/migrate.go

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

models/migrate/migrate_test.go

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

models/notify_config.go

@@ -1,5 +1,12 @@
 package models
 
+import (
+	"fmt"
+	"net/http"
+
+	"github.com/toolkits/pkg/str"
+)
+
 const WEBHOOKKEY = "webhook"
 const NOTIFYSCRIPT = "notify_script"
 const NOTIFYCHANNEL = "notify_channel"
@@ -24,6 +31,11 @@ type Webhook struct {
 	RetryCount    int               `json:"retry_count"`
 	RetryInterval int               `json:"retry_interval"`
 	Batch         int               `json:"batch"`
+	Client        *http.Client      `json:"-"`
+}
+
+func (w *Webhook) Hash() string {
+	return str.MD5(fmt.Sprintf("%d_%t_%s_%s_%s_%d_%v_%t_%s_%d_%d_%d", w.Type, w.Enable, w.Url, w.BasicAuthUser, w.BasicAuthPass, w.Timeout, w.HeaderMap, w.SkipVerify, w.Note, w.RetryCount, w.RetryInterval, w.Batch))
 }
 
 type NotifyScript struct {

models/target.go

@@ -185,8 +185,16 @@ func BuildTargetWhereWithQuery(query string) BuildTargetWhereOption {
 		if query != "" {
 			arr := strings.Fields(query)
 			for i := 0; i < len(arr); i++ {
-				q := "%" + arr[i] + "%"
-				session = session.Where("ident like ? or host_ip like ? or note like ? or tags like ? or host_tags like ? or os like ?", q, q, q, q, q, q)
+				if strings.HasPrefix(arr[i], "-") {
+					q := "%" + arr[i][1:] + "%"
+					session = session.Where("ident not like ? and host_ip not like ? and "+
+						"note not like ? and tags not like ? and (host_tags not like ? or "+
+						"host_tags is null) and os not like ?", q, q, q, q, q, q)
+				} else {
+					q := "%" + arr[i] + "%"
+					session = session.Where("ident like ? or host_ip like ? or note like ? or "+
+						"tags like ? or host_tags like ? or os like ?", q, q, q, q, q, q)
+				}
 			}
 		}
 		return session
@@ -197,6 +205,8 @@ func BuildTargetWhereWithDowntime(downtime int64) BuildTargetWhereOption {
 	return func(session *gorm.DB) *gorm.DB {
 		if downtime > 0 {
 			session = session.Where("target.update_at < ?", time.Now().Unix()-downtime)
+		} else if downtime < 0 {
+			session = session.Where("target.update_at > ?", time.Now().Unix()+downtime)
 		}
 		return session
 	}
@@ -270,7 +280,11 @@ func TargetFilterQueryBuild(ctx *ctx.Context, query []map[string]interface{}, li
 	for _, q := range query {
 		tx := DB(ctx).Model(&Target{})
 		for k, v := range q {
-			tx = tx.Or(k, v)
+			if strings.Count(k, "?") > 1 {
+				tx = tx.Or(k, v.([]interface{})...)
+			} else {
+				tx = tx.Or(k, v)
+			}
 		}
 		sub = sub.Where(tx)
 	}
@@ -409,7 +423,8 @@ func TargetsGetIdentsByIdentsAndHostIps(ctx *ctx.Context, idents, hostIps []stri
 	return inexistence, identSet.ToSlice(), nil
 }
 
-func TargetGetTags(ctx *ctx.Context, idents []string, ignoreHostTag bool) ([]string, error) {
+func TargetGetTags(ctx *ctx.Context, idents []string, ignoreHostTag bool, bgLabelKey string) (
+	[]string, error) {
 	session := DB(ctx).Model(new(Target))
 
 	var arr []*Target
@@ -447,7 +462,22 @@ func TargetGetTags(ctx *ctx.Context, idents []string, ignoreHostTag bool) ([]str
 		ret = append(ret, key)
 	}
 
-	sort.Strings(ret)
+	if bgLabelKey != "" {
+		sort.Slice(ret, func(i, j int) bool {
+			if strings.HasPrefix(ret[i], bgLabelKey) && strings.HasPrefix(ret[j], bgLabelKey) {
+				return ret[i] < ret[j]
+			}
+			if strings.HasPrefix(ret[i], bgLabelKey) {
+				return true
+			}
+			if strings.HasPrefix(ret[j], bgLabelKey) {
+				return false
+			}
+			return ret[i] < ret[j]
+		})
+	} else {
+		sort.Strings(ret)
+	}
 
 	return ret, err
 }
@@ -626,7 +656,7 @@ func DoMigrateBg(ctx *ctx.Context, bgLabelKey string) error {
 		}
 		err := DB(ctx).Transaction(func(tx *gorm.DB) error {
 			// 4.1 将 group_id 迁移至关联表
-			if err := TargetBindBgids(ctx, []string{t.Ident}, []int64{t.GroupId}); err != nil {
+			if err := TargetBindBgids(ctx, []string{t.Ident}, []int64{t.GroupId}, nil); err != nil {
 				return err
 			}
 			if err := TargetUpdateBgid(ctx, []string{t.Ident}, 0, false); err != nil {

models/target_busi_group.go

@@ -1,6 +1,7 @@
 package models
 
 import (
+	"strings"
 	"time"
 
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
@@ -20,6 +21,10 @@ func (t *TargetBusiGroup) TableName() string {
 	return "target_busi_group"
 }
 
+func (t *TargetBusiGroup) TableOptions() string {
+	return "ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_general_ci"
+}
+
 func TargetBusiGroupsGetAll(ctx *ctx.Context) (map[string][]int64, error) {
 	var lst []*TargetBusiGroup
 	err := DB(ctx).Find(&lst).Error
@@ -60,7 +65,7 @@ func TargetGroupIdsGetByIdents(ctx *ctx.Context, idents []string) ([]int64, erro
 	return groupIds, nil
 }
 
-func TargetBindBgids(ctx *ctx.Context, idents []string, bgids []int64) error {
+func TargetBindBgids(ctx *ctx.Context, idents []string, bgids []int64, tags []string) error {
 	lst := make([]TargetBusiGroup, 0, len(bgids)*len(idents))
 	updateAt := time.Now().Unix()
 	for _, bgid := range bgids {
@@ -73,7 +78,6 @@ func TargetBindBgids(ctx *ctx.Context, idents []string, bgids []int64) error {
 			lst = append(lst, cur)
 		}
 	}
-
 	var cl clause.Expression = clause.Insert{Modifier: "ignore"}
 	switch DB(ctx).Dialector.Name() {
 	case "sqlite":
@@ -81,7 +85,23 @@ func TargetBindBgids(ctx *ctx.Context, idents []string, bgids []int64) error {
 	case "postgres":
 		cl = clause.OnConflict{DoNothing: true}
 	}
-	return DB(ctx).Clauses(cl).CreateInBatches(&lst, 10).Error
+
+	return DB(ctx).Transaction(func(tx *gorm.DB) error {
+		if err := DB(ctx).Clauses(cl).CreateInBatches(&lst, 10).Error; err != nil {
+			return err
+		}
+		if targets, err := TargetsGetByIdents(ctx, idents); err != nil {
+			return err
+		} else if len(tags) > 0 {
+			for _, t := range targets {
+				if err := t.AddTags(ctx, tags); err != nil {
+					return err
+				}
+			}
+		}
+
+		return nil
+	})
 }
 
 func TargetUnbindBgids(ctx *ctx.Context, idents []string, bgids []int64) error {
@@ -93,7 +113,7 @@ func TargetDeleteBgids(ctx *ctx.Context, idents []string) error {
 	return DB(ctx).Where("target_ident in ?", idents).Delete(&TargetBusiGroup{}).Error
 }
 
-func TargetOverrideBgids(ctx *ctx.Context, idents []string, bgids []int64) error {
+func TargetOverrideBgids(ctx *ctx.Context, idents []string, bgids []int64, tags []string) error {
 	return DB(ctx).Transaction(func(tx *gorm.DB) error {
 		// 先删除旧的关联
 		if err := tx.Where("target_ident IN ?", idents).Delete(&TargetBusiGroup{}).Error; err != nil {
@@ -126,7 +146,15 @@ func TargetOverrideBgids(ctx *ctx.Context, idents []string, bgids []int64) error
 		case "postgres":
 			cl = clause.OnConflict{DoNothing: true}
 		}
-		return tx.Clauses(cl).CreateInBatches(&lst, 10).Error
+		if err := tx.Clauses(cl).CreateInBatches(&lst, 10).Error; err != nil {
+			return err
+		}
+		if len(tags) == 0 {
+			return nil
+		}
+
+		return tx.Model(Target{}).Where("ident IN ?", idents).Updates(map[string]interface{}{
+			"tags": strings.Join(tags, " ") + " ", "update_at": updateAt}).Error
 	})
 }
 
@@ -156,3 +184,13 @@ func SeparateTargetIdents(ctx *ctx.Context, idents []string) (existing, nonExist
 
 	return
 }
+
+func TargetIndentsGetByBgids(ctx *ctx.Context, bgids []int64) ([]string, error) {
+	var idents []string
+	err := DB(ctx).Model(&TargetBusiGroup{}).
+		Where("group_id IN ?", bgids).
+		Distinct("target_ident").
+		Pluck("target_ident", &idents).
+		Error
+	return idents, err
+}

models/user.go

@@ -804,6 +804,10 @@ func (u *User) BusiGroups(ctx *ctx.Context, limit int, query string, all ...bool
 			return lst, err
 		}
 
+		if t == nil {
+			return lst, nil
+		}
+
 		t.GroupIds, err = TargetGroupIdsGetByIdent(ctx, t.Ident)
 		if err != nil {
 			return nil, err

pkg/cfg/cfg.go

@@ -29,16 +29,22 @@ func LoadConfigByDir(configDir string, configPtr interface{}) error {
 	if err != nil {
 		return fmt.Errorf("failed to list files under: %s : %v", configDir, err)
 	}
+
+	found := false
+
 	s := NewFileScanner()
 	for _, fpath := range files {
 		switch {
 		case strings.HasSuffix(fpath, ".toml"):
+			found = true
 			s.Read(path.Join(configDir, fpath))
 			tBuf = append(tBuf, s.Data()...)
 			tBuf = append(tBuf, []byte("\n")...)
 		case strings.HasSuffix(fpath, ".json"):
+			found = true
 			loaders = append(loaders, &multiconfig.JSONLoader{Path: path.Join(configDir, fpath)})
 		case strings.HasSuffix(fpath, ".yaml") || strings.HasSuffix(fpath, ".yml"):
+			found = true
 			loaders = append(loaders, &multiconfig.YAMLLoader{Path: path.Join(configDir, fpath)})
 		}
 		if s.Err() != nil {
@@ -46,6 +52,10 @@ func LoadConfigByDir(configDir string, configPtr interface{}) error {
 		}
 	}
 
+	if !found {
+		return fmt.Errorf("fail to found config file, config dir path: %v", configDir)
+	}
+
 	if len(tBuf) != 0 {
 		loaders = append(loaders, &multiconfig.TOMLLoader{Reader: bytes.NewReader(tBuf)})
 	}

pkg/ormx/database_init_test.go

@@ -0,0 +1,60 @@
+package ormx
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"gorm.io/driver/mysql"
+	"gorm.io/driver/postgres"
+	"gorm.io/driver/sqlite"
+	"gorm.io/gorm"
+)
+
+func TestDataBaseInit(t *testing.T) {
+	tests := []struct {
+		name   string
+		config DBConfig
+	}{
+		{
+			name: "MySQL",
+			config: DBConfig{
+				DBType: "mysql",
+				DSN:    "root:1234@tcp(127.0.0.1:3306)/test?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true",
+			},
+		},
+		{
+			name: "Postgres",
+			config: DBConfig{
+				DBType: "postgres",
+				DSN:    "host=127.0.0.1 port=5432 user=postgres dbname=test password=1234 sslmode=disable",
+			},
+		},
+		{
+			name: "SQLite",
+			config: DBConfig{
+				DBType: "sqlite",
+				DSN:    "./test.db",
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			err := createDatabase(tt.config, &gorm.Config{})
+			assert.NoError(t, err)
+			var dialector gorm.Dialector
+			switch tt.config.DBType {
+			case "mysql":
+				dialector = mysql.Open(tt.config.DSN)
+			case "postgres":
+				dialector = postgres.Open(tt.config.DSN)
+			case "sqlite":
+				dialector = sqlite.Open(tt.config.DSN)
+			}
+			db, err := gorm.Open(dialector, &gorm.Config{})
+			assert.NoError(t, err)
+			err = DataBaseInit(tt.config, db)
+			assert.NoError(t, err)
+		})
+	}
+}

pkg/ormx/ormx.go

@@ -2,14 +2,15 @@ package ormx
 
 import (
 	"fmt"
+	"os"
 	"reflect"
 	"strings"
 	"time"
 
 	tklog "github.com/toolkits/pkg/logger"
+    "github.com/glebarez/sqlite"
 	"gorm.io/driver/mysql"
 	"gorm.io/driver/postgres"
-	"gorm.io/driver/sqlite"
 	"gorm.io/gorm"
 	"gorm.io/gorm/logger"
 	"gorm.io/gorm/schema"
@@ -70,6 +71,234 @@ func (l *TKitLogger) Printf(s string, i ...interface{}) {
 	}
 }
 
+func createDatabase(c DBConfig, gconfig *gorm.Config) error {
+	switch strings.ToLower(c.DBType) {
+	case "mysql":
+		return createMysqlDatabase(c.DSN, gconfig)
+	case "postgres":
+		return createPostgresDatabase(c.DSN, gconfig)
+	case "sqlite":
+		return createSqliteDatabase(c.DSN, gconfig)
+	default:
+		return fmt.Errorf("dialector(%s) not supported", c.DBType)
+	}
+}
+
+func createSqliteDatabase(dsn string, gconfig *gorm.Config) error {
+	tempDialector := sqlite.Open(dsn)
+
+	_, err := gorm.Open(tempDialector, gconfig)
+	if err != nil {
+		return fmt.Errorf("failed to open temporary connection: %v", err)
+	}
+	
+	fmt.Println("sqlite file created")
+
+	return nil
+}
+
+func createPostgresDatabase(dsn string, gconfig *gorm.Config) error {
+	dsnParts := strings.Split(dsn, " ")
+	dbName := ""
+	connectionWithoutDB := ""
+	for _, part := range dsnParts {
+		if strings.HasPrefix(part, "dbname=") {
+			dbName = part[strings.Index(part, "=")+1:]
+		} else {
+			connectionWithoutDB += part
+			connectionWithoutDB += " "
+		}
+	}
+
+	createDBQuery := fmt.Sprintf("CREATE DATABASE %s ENCODING='UTF8' LC_COLLATE='en_US.UTF-8' LC_CTYPE='en_US.UTF-8';", dbName)
+
+	tempDialector := postgres.Open(connectionWithoutDB)
+
+	tempDB, err := gorm.Open(tempDialector, gconfig)
+	if err != nil {
+		return fmt.Errorf("failed to open temporary connection: %v", err)
+	}
+
+	result := tempDB.Exec(createDBQuery)
+	if result.Error != nil {
+		return fmt.Errorf("failed to execute create database query: %v", result.Error)
+	}
+
+	return nil
+}
+
+func createMysqlDatabase(dsn string, gconfig *gorm.Config) error {
+	dsnParts := strings.SplitN(dsn, "/", 2)
+	if len(dsnParts) != 2 {
+		return fmt.Errorf("failed to parse DSN: %s", dsn)
+	}
+
+	connectionInfo := dsnParts[0]
+	dbInfo := dsnParts[1]
+	dbName := dbInfo
+
+	queryIndex := strings.Index(dbInfo, "?")
+	if queryIndex != -1 {
+		dbName = dbInfo[:queryIndex]
+	} else {
+		return fmt.Errorf("failed to parse database name from DSN: %s", dsn)
+	}
+
+	connectionWithoutDB := connectionInfo + "/?" + dbInfo[queryIndex+1:]
+	createDBQuery := fmt.Sprintf("CREATE DATABASE IF NOT EXISTS %s CHARACTER SET utf8mb4", dbName)
+
+	tempDialector := mysql.Open(connectionWithoutDB)
+
+	tempDB, err := gorm.Open(tempDialector, gconfig)
+	if err != nil {
+		return fmt.Errorf("failed to open temporary connection: %v", err)
+	}
+
+	result := tempDB.Exec(createDBQuery)
+	if result.Error != nil {
+		return fmt.Errorf("failed to execute create database query: %v", result.Error)
+	}
+
+	return nil
+}
+
+func checkDatabaseExist(c DBConfig) (bool, error) {
+	switch strings.ToLower(c.DBType) {
+	case "mysql":
+		return checkMysqlDatabaseExist(c)
+	case "postgres":
+		return checkPostgresDatabaseExist(c)
+	case "sqlite":
+		return checkSqliteDatabaseExist(c)
+	default:
+		return false, fmt.Errorf("dialector(%s) not supported", c.DBType)
+	}
+
+}
+
+func checkSqliteDatabaseExist(c DBConfig) (bool, error) {
+	if _, err := os.Stat(c.DSN); os.IsNotExist(err) {
+		fmt.Printf("sqlite file not exists: %s\n", c.DSN)
+		return false, nil
+	} else {
+		return true, nil
+	}
+}
+
+func checkPostgresDatabaseExist(c DBConfig) (bool, error) {
+	dsnParts := strings.Split(c.DSN, " ")
+	dbName := ""
+	connectionWithoutDB := ""
+	for _, part := range dsnParts {
+		if strings.HasPrefix(part, "dbname=") {
+			dbName = part[strings.Index(part, "=")+1:]
+		} else {
+			connectionWithoutDB += part
+			connectionWithoutDB += " "
+		}
+	}
+
+	dialector := postgres.Open(connectionWithoutDB)
+
+	gconfig := &gorm.Config{
+		NamingStrategy: schema.NamingStrategy{
+			TablePrefix:   c.TablePrefix,
+			SingularTable: true,
+		},
+		Logger: gormLogger,
+	}
+
+	db, err := gorm.Open(dialector, gconfig)
+	if err != nil {
+		return false, fmt.Errorf("failed to open database: %v", err)
+	}
+
+    var databases []string
+    query := genQuery(c)
+    if err := db.Raw(query).Scan(&databases).Error; err != nil {
+        return false, fmt.Errorf("failed to query: %v", err)
+    }
+
+    for _, database := range databases {
+        if database == dbName {
+			fmt.Println("Database exist")
+            return true, nil
+        }
+    }
+
+    return false, nil
+}
+
+func checkMysqlDatabaseExist(c DBConfig) (bool, error) {
+	dsnParts := strings.SplitN(c.DSN, "/", 2)
+    if len(dsnParts) != 2 {
+        return false, fmt.Errorf("failed to parse DSN: %s", c.DSN)
+    }
+
+    connectionInfo := dsnParts[0]
+    dbInfo := dsnParts[1]
+    dbName := dbInfo
+
+    queryIndex := strings.Index(dbInfo, "?")
+    if queryIndex != -1 {
+        dbName = dbInfo[:queryIndex]
+    } else {
+        return false, fmt.Errorf("failed to parse database name from DSN: %s", c.DSN)
+    }
+
+    connectionWithoutDB := connectionInfo + "/?" + dbInfo[queryIndex+1:]
+
+    var dialector gorm.Dialector
+    switch strings.ToLower(c.DBType) {
+    case "mysql":
+        dialector = mysql.Open(connectionWithoutDB)
+    case "postgres":
+        dialector = postgres.Open(connectionWithoutDB)
+    default:
+        return false, fmt.Errorf("unsupported database type: %s", c.DBType)
+    }
+
+    gconfig := &gorm.Config{
+        NamingStrategy: schema.NamingStrategy{
+            TablePrefix:   c.TablePrefix,
+            SingularTable: true,
+        },
+        Logger: gormLogger,
+    }
+
+    db, err := gorm.Open(dialector, gconfig)
+    if err != nil {
+        return false, fmt.Errorf("failed to open database: %v", err)
+    }
+
+    var databases []string
+    query := genQuery(c)
+    if err := db.Raw(query).Scan(&databases).Error; err != nil {
+        return false, fmt.Errorf("failed to query: %v", err)
+    }
+
+    for _, database := range databases {
+        if database == dbName {
+            return true, nil
+        }
+    }
+
+    return false, nil
+}
+
+func genQuery(c DBConfig) string {
+	switch strings.ToLower(c.DBType) {
+    case "mysql":
+        return "SHOW DATABASES"
+    case "postgres":
+        return "SELECT datname FROM pg_database"
+    case "sqlite":
+        return ""
+    default:
+        return ""
+	}
+}
+
 // New Create gorm.DB instance
 func New(c DBConfig) (*gorm.DB, error) {
 	var dialector gorm.Dialector
@@ -95,9 +324,30 @@ func New(c DBConfig) (*gorm.DB, error) {
 		Logger: gormLogger,
 	}
 
+	dbExist, checkErr := checkDatabaseExist(c)
+	if checkErr != nil {
+		return nil, checkErr
+	}
+	if !dbExist {
+		fmt.Println("Database not exist, trying to create it")
+		createErr := createDatabase(c, gconfig)
+		if createErr != nil {
+			return nil, fmt.Errorf("failed to create database: %v", createErr)
+		}
+
+		db, err := gorm.Open(dialector, gconfig)
+		if err != nil {
+			return nil, fmt.Errorf("failed to reopen database after creation: %v", err)
+		}
+		err = DataBaseInit(c, db)
+		if err != nil {
+			return nil, fmt.Errorf("failed to init database: %v", err)
+		}
+	}
+
 	db, err := gorm.Open(dialector, gconfig)
 	if err != nil {
-		return nil, err
+		return nil, fmt.Errorf("failed to open database: %v", err)
 	}
 
 	if c.Debug {

pkg/poster/post.go

@@ -63,7 +63,7 @@ func GetByUrl[T any](url string, cfg conf.CenterApi) (T, error) {
 		Timeout: time.Duration(cfg.Timeout) * time.Millisecond,
 	}
 
-	if useProxy(url) {
+	if UseProxy(url) {
 		client.Transport = ProxyTransporter
 	}
 
@@ -147,7 +147,7 @@ func PostByUrl[T any](url string, cfg conf.CenterApi, v interface{}) (t T, err e
 		Timeout: time.Duration(cfg.Timeout) * time.Millisecond,
 	}
 
-	if useProxy(url) {
+	if UseProxy(url) {
 		client.Transport = ProxyTransporter
 	}
 
@@ -195,7 +195,7 @@ var ProxyTransporter = &http.Transport{
 	Proxy: http.ProxyFromEnvironment,
 }
 
-func useProxy(url string) bool {
+func UseProxy(url string) bool {
 	// N9E_PROXY_URL=oapi.dingtalk.com,feishu.com
 	patterns := os.Getenv("N9E_PROXY_URL")
 	if patterns != "" {
@@ -228,7 +228,7 @@ func PostJSON(url string, timeout time.Duration, v interface{}, retries ...int)
 		Timeout: timeout,
 	}
 
-	if useProxy(url) {
+	if UseProxy(url) {
 		client.Transport = ProxyTransporter
 	}
 

pkg/prom/reader.go

@@ -700,18 +700,24 @@ func (h *httpAPI) Query(ctx context.Context, query string, ts time.Time) (model.
 	var err error
 	var warnings Warnings
 	var value model.Value
+	var statusCode int
 	for i := 0; i < 3; i++ {
-		value, warnings, err = h.query(ctx, query, ts)
+		value, warnings, statusCode, err = h.query(ctx, query, ts)
 		if err == nil {
 			return value, warnings, nil
 		}
 
+		// statusCode 4xx do not retry
+		if statusCode >= 400 && statusCode < 500 {
+			return nil, warnings, err
+		}
+
 		time.Sleep(100 * time.Millisecond)
 	}
 	return nil, warnings, err
 }
 
-func (h *httpAPI) query(ctx context.Context, query string, ts time.Time) (model.Value, Warnings, error) {
+func (h *httpAPI) query(ctx context.Context, query string, ts time.Time) (model.Value, Warnings, int, error) {
 	u := h.client.URL(epQuery, nil)
 	q := u.Query()
 
@@ -722,15 +728,11 @@ func (h *httpAPI) query(ctx context.Context, query string, ts time.Time) (model.
 
 	resp, body, warnings, err := h.client.DoGetFallback(ctx, u, q)
 	if err != nil {
-		return nil, warnings, err
-	}
-
-	if resp.StatusCode > 200 {
-		fmt.Println("status code:", resp.StatusCode)
+		return nil, warnings, 0, err
 	}
 
 	var qres queryResult
-	return model.Value(qres.v), warnings, json.Unmarshal(body, &qres)
+	return model.Value(qres.v), warnings, resp.StatusCode, json.Unmarshal(body, &qres)
 }
 
 func (h *httpAPI) QueryRange(ctx context.Context, query string, r Range) (model.Value, Warnings, error) {

pkg/tplx/fns.go

@@ -27,6 +27,15 @@ type sample struct {
 	Value  float64
 }
 
+type QueryFunc func(int64, string) model.Value
+
+var queryFunc QueryFunc
+
+// RegisterQueryFunc 为了避免循环引用，通过外部注入的方式注册 queryFunc
+func RegisterQueryFunc(f QueryFunc) {
+	queryFunc = f
+}
+
 type queryResult []*sample
 
 type queryResultByLabelSorter struct {
@@ -564,3 +573,13 @@ func convertToFloat(i interface{}) (float64, error) {
 		return 0, fmt.Errorf("can't convert %T to float", v)
 	}
 }
+
+func Query(datasourceID int64, promql string) model.Value {
+
+	value := queryFunc(datasourceID, promql)
+	if value != nil {
+		return value
+	}
+
+	return nil
+}

pkg/tplx/tplx.go

@@ -54,6 +54,15 @@ var TemplateFuncMap = template.FuncMap{
 	"printf":                    Printf,
 }
 
+// NewTemplateFuncMap copy on write for TemplateFuncMap
+func NewTemplateFuncMap() template.FuncMap {
+	m := template.FuncMap{}
+	for k, v := range TemplateFuncMap {
+		m[k] = v
+	}
+	return m
+}
+
 // ReplaceTemplateUseHtml replaces variables in a template string with values.
 //
 // It accepts the following parameters:

pushgw/pconf/conf.go

@@ -24,8 +24,10 @@ type Pushgw struct {
 }
 
 type WriterGlobalOpt struct {
-	QueueMaxSize int
-	QueuePopSize int
+	QueueMaxSize            int
+	QueuePopSize            int
+	AllQueueMaxSize         int
+	AllQueueMaxSizeInterval int
 }
 
 type WriterOptions struct {
@@ -77,6 +79,14 @@ func (p *Pushgw) PreCheck() {
 		p.WriterOpt.QueuePopSize = 1000
 	}
 
+	if p.WriterOpt.AllQueueMaxSize <= 0 {
+		p.WriterOpt.AllQueueMaxSize = 10000000
+	}
+
+	if p.WriterOpt.AllQueueMaxSizeInterval <= 0 {
+		p.WriterOpt.AllQueueMaxSizeInterval = 200
+	}
+
 	if p.WriteConcurrency <= 0 {
 		p.WriteConcurrency = 5000
 	}

pushgw/router/fns.go

@@ -79,6 +79,10 @@ func (rt *Router) AppendLabels(pt *prompb.TimeSeries, target *models.Target, bgC
 // }
 
 func (rt *Router) debugSample(remoteAddr string, v *prompb.TimeSeries) {
+	if v == nil {
+		return
+	}
+
 	filter := rt.Pushgw.DebugSample
 	if len(filter) == 0 {
 		return
@@ -164,6 +168,7 @@ func (rt *Router) ForwardByIdent(clientIP string, ident string, v *prompb.TimeSe
 
 func (rt *Router) ForwardByMetric(clientIP string, metric string, v *prompb.TimeSeries) {
 	v = rt.BeforePush(clientIP, v)
+	rt.debugSample(clientIP, v)
 	if v == nil {
 		return
 	}

pushgw/writer/writer.go

@@ -8,6 +8,7 @@ import (
 	"net/http"
 	"strings"
 	"sync"
+	"sync/atomic"
 	"time"
 
 	"github.com/ccfos/nightingale/v6/pkg/fasttime"
@@ -138,9 +139,10 @@ func (w WriterType) Post(req []byte, headers ...map[string]string) error {
 }
 
 type WritersType struct {
-	pushgw   pconf.Pushgw
-	backends map[string]WriterType
-	queues   map[string]*IdentQueue
+	pushgw      pconf.Pushgw
+	backends    map[string]WriterType
+	queues      map[string]*IdentQueue
+	allQueueLen atomic.Value
 	sync.RWMutex
 }
 
@@ -160,14 +162,30 @@ func (ws *WritersType) ReportQueueStats(ident string, identQueue *IdentQueue) (i
 	}
 }
 
+func (ws *WritersType) SetAllQueueLen() {
+	for {
+		curMetricLen := 0
+		ws.RLock()
+		for _, q := range ws.queues {
+			curMetricLen += q.list.Len()
+		}
+		ws.RUnlock()
+		ws.allQueueLen.Store(curMetricLen)
+		time.Sleep(time.Duration(ws.pushgw.WriterOpt.AllQueueMaxSizeInterval) * time.Millisecond)
+	}
+}
+
 func NewWriters(pushgwConfig pconf.Pushgw) *WritersType {
 	writers := &WritersType{
-		backends: make(map[string]WriterType),
-		queues:   make(map[string]*IdentQueue),
-		pushgw:   pushgwConfig,
+		backends:    make(map[string]WriterType),
+		queues:      make(map[string]*IdentQueue),
+		pushgw:      pushgwConfig,
+		allQueueLen: atomic.Value{},
 	}
 
 	writers.Init()
+
+	go writers.SetAllQueueLen()
 	go writers.CleanExpQueue()
 	return writers
 }
@@ -217,6 +235,13 @@ func (ws *WritersType) PushSample(ident string, v interface{}) {
 	}
 
 	identQueue.ts = time.Now().Unix()
+	curLen := ws.allQueueLen.Load().(int)
+	if curLen > ws.pushgw.WriterOpt.AllQueueMaxSize {
+		logger.Warningf("Write %+v full, metric count over limit: %d", v, curLen)
+		CounterPushQueueErrorTotal.WithLabelValues(ident).Inc()
+		return
+	}
+
 	succ := identQueue.list.PushFront(v)
 	if !succ {
 		logger.Warningf("Write channel(%s) full, current channel size: %d", ident, identQueue.list.Len())
@@ -245,6 +270,7 @@ func (ws *WritersType) StartConsumer(identQueue *IdentQueue) {
 
 func (ws *WritersType) Init() error {
 	opts := ws.pushgw.Writers
+	ws.allQueueLen.Store(0)
 
 	for i := 0; i < len(opts); i++ {
 		tlsConf, err := opts[i].ClientConfig.TLSConfig()

storage/redis.go

@@ -7,6 +7,7 @@ import (
 	"os"
 	"strings"
 
+	"github.com/alicebob/miniredis/v2"
 	"github.com/ccfos/nightingale/v6/pkg/tlsx"
 	"github.com/redis/go-redis/v9"
 	"github.com/toolkits/pkg/logger"
@@ -28,6 +29,7 @@ type Redis redis.Cmdable
 
 func NewRedis(cfg RedisConfig) (Redis, error) {
 	var redisClient Redis
+
 	switch cfg.RedisType {
 	case "standalone", "":
 		redisOptions := &redis.Options{
@@ -88,6 +90,16 @@ func NewRedis(cfg RedisConfig) (Redis, error) {
 
 		redisClient = redis.NewFailoverClient(redisOptions)
 
+	case "miniredis":
+		s, err := miniredis.Run()
+		if err != nil {
+			fmt.Println("failed to init miniredis:", err)
+			os.Exit(1)
+		}
+		redisClient = redis.NewClient(&redis.Options{
+			Addr: s.Addr(),
+		})
+
 	default:
 		fmt.Println("failed to init redis , redis type is illegal:", cfg.RedisType)
 		os.Exit(1)

storage/redis_test.go

@@ -0,0 +1,44 @@
+package storage
+
+import (
+	"context"
+	"testing"
+
+	"github.com/alicebob/miniredis/v2"
+	"github.com/redis/go-redis/v9"
+	"github.com/stretchr/testify/assert"
+)
+
+func TestMiniRedisMGet(t *testing.T) {
+	s, err := miniredis.Run()
+	if err != nil {
+		t.Fatalf("failed to start miniredis: %v", err)
+	}
+	defer s.Close()
+
+	rdb := redis.NewClient(&redis.Options{
+		Addr: s.Addr(),
+	})
+
+	err = rdb.Ping(context.Background()).Err()
+	if err != nil {
+		t.Fatalf("failed to ping miniredis: %v", err)
+	}
+
+	mp := make(map[string]interface{})
+	mp["key1"] = "value1"
+	mp["key2"] = "value2"
+	mp["key3"] = "value3"
+
+	err = MSet(context.Background(), rdb, mp)
+	if err != nil {
+		t.Fatalf("failed to set miniredis value: %v", err)
+	}
+
+	ctx := context.Background()
+	keys := []string{"key1", "key2", "key3", "key4"}
+	vals := MGet(ctx, rdb, keys)
+
+	expected := [][]byte{[]byte("value1"), []byte("value2"), []byte("value3")}
+	assert.Equal(t, expected, vals)
+}