alerts rule and dashboards for pg

* add kafka dashboard and alert rules based on categraf acquisition

* add kafka dashboard and alert rules based on categraf acquisition

.gitignore

@@ -43,6 +43,7 @@ _test
 /docker/mysqldata
 /docker/experience_pg_vm/pgdata
 /etc.local*
+/front/statik/statik.go
 
 .alerts
 .idea

.goreleaser.yaml

@@ -15,7 +15,8 @@ builds:
   - id: build
     hooks:
       pre:
-       - ./fe.sh
+      - cmd: sh -x ./fe.sh
+        output: true
     main: ./cmd/center/
     binary: n9e
     env:
@@ -41,22 +42,9 @@ builds:
     ldflags:
       - -s -w
       - -X github.com/ccfos/nightingale/v6/pkg/version.Version={{ .Tag }}-{{.Commit}}
-  - id: build-alert
-    main: ./cmd/alert/
-    binary: n9e-alert
-    env:
-      - CGO_ENABLED=0
-    goos:
-      - linux
-    goarch:
-      - amd64
-      - arm64
-    ldflags:
-      - -s -w
-      - -X github.com/ccfos/nightingale/v6/pkg/version.Version={{ .Tag }}-{{.Commit}}
-  - id: build-pushgw
-    main: ./cmd/pushgw/
-    binary: n9e-pushgw
+  - id: build-edge
+    main: ./cmd/edge/
+    binary: n9e-edge
     env:
       - CGO_ENABLED=0
     goos:
@@ -73,8 +61,7 @@ archives:
     builds:
       - build
       - build-cli
-      - build-alert
-      - build-pushgw
+      - build-edge
     format: tar.gz
     format_overrides:
       - goos: windows
@@ -84,7 +71,6 @@ archives:
     files:
       - docker/*
       - etc/*
-      - pub/*
       - integrations/*
       - cli/*
       - n9e.sql
@@ -104,7 +90,6 @@ dockers:
       - build
     dockerfile: docker/Dockerfile.goreleaser
     extra_files:
-      - pub
       - etc
       - integrations
     use: buildx
@@ -118,7 +103,6 @@ dockers:
       - build
     dockerfile: docker/Dockerfile.goreleaser.arm64
     extra_files:
-      - pub
       - etc
       - integrations
     use: buildx

Makefile

@@ -1,4 +1,4 @@
-.PHONY: prebuild start build
+.PHONY: prebuild build
 
 ROOT:=$(shell pwd -P)
 GIT_COMMIT:=$(shell git --work-tree ${ROOT}  rev-parse 'HEAD^{commit}')
@@ -6,16 +6,19 @@ _GIT_VERSION:=$(shell git --work-tree ${ROOT} describe --tags --abbrev=14 "${GIT
 TAG=$(shell echo "${_GIT_VERSION}" |  awk -F"-" '{print $$1}')
 RELEASE_VERSION:="$(TAG)-$(GIT_COMMIT)"
 
+all: prebuild build
+
 prebuild:
 	echo "begin download and embed the front-end file..."
 	sh fe.sh
 	echo "front-end file download and embedding completed."
 
-all: build
-
 build:
 	go build -ldflags "-w -s -X github.com/ccfos/nightingale/v6/pkg/version.Version=$(RELEASE_VERSION)" -o n9e ./cmd/center/main.go
 
+build-edge:
+	go build -ldflags "-w -s -X github.com/ccfos/nightingale/v6/pkg/version.Version=$(RELEASE_VERSION)" -o n9e-edge ./cmd/edge/
+
 build-alert:
 	go build -ldflags "-w -s -X github.com/ccfos/nightingale/v6/pkg/version.Version=$(RELEASE_VERSION)" -o n9e-alert ./cmd/alert/main.go
 
@@ -28,10 +31,10 @@ build-cli:
 run:
 	nohup ./n9e > n9e.log 2>&1 &
 
-run_alert:
+run-alert:
 	nohup ./n9e-alert > n9e-alert.log 2>&1 &
 
-run_pushgw:
+run-pushgw:
 	nohup ./n9e-pushgw > n9e-pushgw.log 2>&1 &
 
 release:

README.md

@@ -4,65 +4,71 @@
 </p>
 
 <p align="center">
-<img alt="GitHub latest release" src="https://img.shields.io/github/v/release/ccfos/nightingale"/>
-<a href="https://n9e.github.io">
+<a href="https://flashcat.cloud/docs/">
   <img alt="Docs" src="https://img.shields.io/badge/docs-get%20started-brightgreen"/></a>
 <a href="https://hub.docker.com/u/flashcatcloud">
   <img alt="Docker pulls" src="https://img.shields.io/docker/pulls/flashcatcloud/nightingale"/></a>
-<img alt="GitHub Repo stars" src="https://img.shields.io/github/stars/ccfos/nightingale">
-<img alt="GitHub Repo issues" src="https://img.shields.io/github/issues/ccfos/nightingale">
-<img alt="GitHub Repo issues closed" src="https://img.shields.io/github/issues-closed/ccfos/nightingale">
-<img alt="GitHub forks" src="https://img.shields.io/github/forks/ccfos/nightingale">
 <a href="https://github.com/ccfos/nightingale/graphs/contributors">
   <img alt="GitHub contributors" src="https://img.shields.io/github/contributors-anon/ccfos/nightingale"/></a>
+<img alt="GitHub Repo stars" src="https://img.shields.io/github/stars/ccfos/nightingale">
+<br/><img alt="GitHub Repo issues" src="https://img.shields.io/github/issues/ccfos/nightingale">
+<img alt="GitHub Repo issues closed" src="https://img.shields.io/github/issues-closed/ccfos/nightingale">
+<img alt="GitHub forks" src="https://img.shields.io/github/forks/ccfos/nightingale">
+<img alt="GitHub latest release" src="https://img.shields.io/github/v/release/ccfos/nightingale"/>
+<img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-blue"/>
 <a href="https://n9e-talk.slack.com/">
   <img alt="GitHub contributors" src="https://img.shields.io/badge/join%20slack-%23n9e-brightgreen.svg"/></a>
-<img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-blue"/>
 </p>
+
 <p align="center">
-  告警管理专家，一体化开源观测平台！
+  告警管理专家，一体化的开源可观测平台
 </p>
 
 [English](./README_en.md) | [中文](./README.md)
 
+夜莺Nightingale是中国计算机学会托管的开源云原生可观测工具，最早由滴滴于 2020 年孵化并开源，并于 2022 年正式捐赠予中国计算机学会。夜莺采用 All-in-One 的设计理念，集数据采集、可视化、监控告警、数据分析于一体，与云原生生态紧密集成，融入了顶级互联网公司可观测性最佳实践，沉淀了众多社区专家经验，开箱即用。
+
 ## 资料
 
-- 文档：[https://flashcat.cloud/docs/](https://flashcat.cloud/docs/)
-- 论坛提问：[https://answer.flashcat.cloud/](https://answer.flashcat.cloud/)
-- 报Bug：[https://github.com/ccfos/nightingale/issues](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Fbug&projects=&template=bug_report.yml)
-- 商业版本：[企业版](https://mp.weixin.qq.com/s/FOwnnGPkRao2ZDV574EHrw) | [专业版](https://mp.weixin.qq.com/s/uM2a8QUDJEYwdBpjkbQDxA) 感兴趣请 [联系我们交流试用](https://flashcat.cloud/contact/)
+- 文档：[flashcat.cloud/docs](https://flashcat.cloud/docs/)
+- 提问：[answer.flashcat.cloud](https://answer.flashcat.cloud/)
+- 报Bug：[github.com/ccfos/nightingale/issues](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Fbug&projects=&template=bug_report.yml)
+
 
 ## 功能和特点
 
-- **统一接入各种时序库**：支持对接 Prometheus、VictoriaMetrics、Thanos、Mimir、M3DB 等多种时序库，实现统一告警管理
-- **专业告警能力**：内置支持多种告警规则，可以扩展支持所有通知媒介，支持告警屏蔽、告警抑制、告警自愈、告警事件管理
-- **无缝搭配 [FlashDuty](https://flashcat.cloud/product/flashcat-duty/)**：实现告警聚合收敛、认领、升级、排班、IM集成，确保告警处理不遗漏，减少打扰，更好协同
-- **支持所有常见采集器**：支持 categraf、telegraf、grafana-agent、datadog-agent、给类 exporter 作为采集器，没有什么数据是不能监控的
-- **统一的观测平台**：从 v6 版本开始，支持接入 ElasticSearch、Jaeger 数据源，逐步实现日志、链路、指标的一体化观测
+- 统一接入各种时序库：支持对接 Prometheus、VictoriaMetrics、Thanos、Mimir、M3DB 等多种时序库，实现统一告警管理
+- 专业告警能力：内置支持多种告警规则，可以扩展支持所有通知媒介，支持告警屏蔽、告警抑制、告警自愈、告警事件管理
+- 高性能可视化引擎：支持多种图表样式，内置众多Dashboard模版，也可导入Grafana模版，开箱即用，开源协议商业友好
+- 无缝搭配 [Flashduty](https://flashcat.cloud/product/flashcat-duty/)：实现告警聚合收敛、认领、升级、排班、IM集成，确保告警处理不遗漏，减少打扰，更好协同
+- 支持所有常见采集器：支持 [Categraf](https://flashcat.cloud/product/categraf)、telegraf、grafana-agent、datadog-agent、各种 exporter 作为采集器，没有什么数据是不能监控的
+- 一体化观测平台：从 v6 版本开始，支持接入 ElasticSearch、Jaeger 数据源，实现日志、链路、指标多维度的统一可观测
 
-## 产品示意图
 
-https://user-images.githubusercontent.com/792850/216888712-2565fcea-9df5-47bd-a49e-d60af9bd76e8.mp4
+## 产品演示
 
+![演示](doc/img/n9e-screenshot-gif-v6.gif)
+
+## 部署架构
+
+![架构](doc/img/n9e-arch-latest.png)
 
 ## 加入交流群
 
-欢迎加入 QQ 交流群，群号：479290895，也可以扫下方二维码加入微信交流群：
-
-<img src="doc/img/wecom.png" width="240">
+欢迎加入 QQ 交流群，群号：479290895，QQ 群适合群友互助，夜莺研发人员通常不在群里。如果要报 bug 请到[这里](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Fbug&projects=&template=bug_report.yml)，提问到[这里](https://answer.flashcat.cloud/)。
 
 ## Stargazers over time
-[![Stargazers over time](https://starchart.cc/ccfos/nightingale.svg)](https://starchart.cc/ccfos/nightingale)
+
+[![Stargazers over time](https://api.star-history.com/svg?repos=ccfos/nightingale&type=Date)](https://star-history.com/#ccfos/nightingale&Date)
+
 
 ## Contributors
 <a href="https://github.com/ccfos/nightingale/graphs/contributors">
   <img src="https://contrib.rocks/image?repo=ccfos/nightingale" />
 </a>
 
-## License
-[Apache License V2.0](https://github.com/didi/nightingale/blob/main/LICENSE)
-
-## 社区管理
-
+## 社区治理
 [夜莺开源项目和社区治理架构（草案）](./doc/community-governance.md)
 
+## License
+[Apache License V2.0](https://github.com/didi/nightingale/blob/main/LICENSE)

alert/aconf/conf.go

@@ -7,6 +7,7 @@ import (
 )
 
 type Alert struct {
+	Disable     bool
 	EngineDelay int64
 	Heartbeat   HeartbeatConfig
 	Alerting    Alerting
@@ -70,4 +71,8 @@ func (a *Alert) PreCheck() {
 	if a.Heartbeat.EngineName == "" {
 		a.Heartbeat.EngineName = "default"
 	}
+
+	if a.EngineDelay == 0 {
+		a.EngineDelay = 30
+	}
 }

alert/dispatch/dispatch.go

@@ -83,12 +83,13 @@ func (e *Dispatch) relaodTpls() error {
 	smtp := e.notifyConfigCache.GetSMTP()
 
 	senders := map[string]sender.Sender{
-		models.Email:    sender.NewSender(models.Email, tmpTpls, smtp),
-		models.Dingtalk: sender.NewSender(models.Dingtalk, tmpTpls, smtp),
-		models.Wecom:    sender.NewSender(models.Wecom, tmpTpls, smtp),
-		models.Feishu:   sender.NewSender(models.Feishu, tmpTpls, smtp),
-		models.Mm:       sender.NewSender(models.Mm, tmpTpls, smtp),
-		models.Telegram: sender.NewSender(models.Telegram, tmpTpls, smtp),
+		models.Email:      sender.NewSender(models.Email, tmpTpls, smtp),
+		models.Dingtalk:   sender.NewSender(models.Dingtalk, tmpTpls, smtp),
+		models.Wecom:      sender.NewSender(models.Wecom, tmpTpls, smtp),
+		models.Feishu:     sender.NewSender(models.Feishu, tmpTpls, smtp),
+		models.Mm:         sender.NewSender(models.Mm, tmpTpls, smtp),
+		models.Telegram:   sender.NewSender(models.Telegram, tmpTpls, smtp),
+		models.FeishuCard: sender.NewSender(models.FeishuCard, tmpTpls, smtp),
 	}
 
 	e.RwLock.RLock()

alert/mute/mute.go

@@ -156,7 +156,10 @@ func matchMute(event *models.AlertCurEvent, mute *models.AlertMute, clock ...int
 
 		for i := 0; i < len(mute.PeriodicMutesJson); i++ {
 			if strings.Contains(mute.PeriodicMutesJson[i].EnableDaysOfWeek, triggerWeek) {
-				if mute.PeriodicMutesJson[i].EnableStime <= mute.PeriodicMutesJson[i].EnableEtime {
+				if mute.PeriodicMutesJson[i].EnableStime == mute.PeriodicMutesJson[i].EnableEtime {
+					matchTime = true
+					break
+				} else if mute.PeriodicMutesJson[i].EnableStime < mute.PeriodicMutesJson[i].EnableEtime {
 					if triggerTime >= mute.PeriodicMutesJson[i].EnableStime && triggerTime < mute.PeriodicMutesJson[i].EnableEtime {
 						matchTime = true
 						break

alert/naming/hashring.go

@@ -16,7 +16,7 @@ type DatasourceHashRingType struct {
 }
 
 // for alert_rule sharding
-var HostDatasource int64 = 100000
+var HostDatasource int64 = 99999999
 var DatasourceHashRing = DatasourceHashRingType{Rings: make(map[int64]*consistent.Consistent)}
 
 func NewConsistentHashRing(replicas int32, nodes []string) *consistent.Consistent {
@@ -53,9 +53,7 @@ func (chr *DatasourceHashRingType) GetNode(datasourceId int64, pk string) (strin
 func (chr *DatasourceHashRingType) IsHit(datasourceId int64, pk string, currentNode string) bool {
 	node, err := chr.GetNode(datasourceId, pk)
 	if err != nil {
-		if errors.Is(err, consistent.ErrEmptyCircle) {
-			logger.Debugf("rule id:%s is not work, datasource id:%d is not assigned to active alert engine", pk, datasourceId)
-		} else {
+		if !errors.Is(err, consistent.ErrEmptyCircle) {
 			logger.Debugf("rule id:%s is not work, datasource id:%d failed to get node from hashring:%v", pk, datasourceId, err)
 		}
 		return false
@@ -68,3 +66,14 @@ func (chr *DatasourceHashRingType) Set(datasourceId int64, r *consistent.Consist
 	defer chr.Unlock()
 	chr.Rings[datasourceId] = r
 }
+
+func (chr *DatasourceHashRingType) Clear() {
+	chr.Lock()
+	defer chr.Unlock()
+	for id := range chr.Rings {
+		if id == HostDatasource {
+			continue
+		}
+		delete(chr.Rings, id)
+	}
+}

alert/naming/heartbeat.go

@@ -96,6 +96,16 @@ func (n *Naming) heartbeat() error {
 		}
 	}
 
+	if len(datasourceIds) == 0 {
+		DatasourceHashRing.Clear()
+		for dsId := range localss {
+			if dsId == HostDatasource {
+				continue
+			}
+			delete(localss, dsId)
+		}
+	}
+
 	for i := 0; i < len(datasourceIds); i++ {
 		servers, err := n.ActiveServers(datasourceIds[i])
 		if err != nil {

alert/router/router.go

@@ -39,13 +39,13 @@ func New(httpConfig httpx.Config, alert aconf.Alert, amc *memsto.AlertMuteCacheT
 }
 
 func (rt *Router) Config(r *gin.Engine) {
-	if !rt.HTTP.Alert.Enable {
+	if !rt.HTTP.APIForService.Enable {
 		return
 	}
 
 	service := r.Group("/v1/n9e")
-	if len(rt.HTTP.Alert.BasicAuth) > 0 {
-		service.Use(gin.BasicAuth(rt.HTTP.Alert.BasicAuth))
+	if len(rt.HTTP.APIForService.BasicAuth) > 0 {
+		service.Use(gin.BasicAuth(rt.HTTP.APIForService.BasicAuth))
 	}
 	service.POST("/event", rt.pushEventToQueue)
 	service.POST("/event-persist", rt.eventPersist)

alert/sender/callback.go

@@ -1,6 +1,7 @@
 package sender
 
 import (
+	"encoding/json"
 	"strconv"
 	"strings"
 	"time"
@@ -50,6 +51,7 @@ type TaskForm struct {
 	Pause     string   `json:"pause"`
 	Script    string   `json:"script"`
 	Args      string   `json:"args"`
+	Stdin     string   `json:"stdin"`
 	Action    string   `json:"action"`
 	Creator   string   `json:"creator"`
 	Hosts     []string `json:"hosts"`
@@ -114,6 +116,30 @@ func handleIbex(ctx *ctx.Context, url string, event *models.AlertCurEvent, targe
 		return
 	}
 
+	tagsMap := make(map[string]string)
+	for i := 0; i < len(event.TagsJSON); i++ {
+		pair := strings.TrimSpace(event.TagsJSON[i])
+		if pair == "" {
+			continue
+		}
+
+		arr := strings.Split(pair, "=")
+		if len(arr) != 2 {
+			continue
+		}
+
+		tagsMap[arr[0]] = arr[1]
+	}
+	// 附加告警级别  告警触发值标签
+	tagsMap["alert_severity"] = strconv.Itoa(event.Severity)
+	tagsMap["alert_trigger_value"] = event.TriggerValue
+
+	tags, err := json.Marshal(tagsMap)
+	if err != nil {
+		logger.Errorf("event_callback_ibex: failed to marshal tags to json: %v", tagsMap)
+		return
+	}
+
 	// call ibex
 	in := TaskForm{
 		Title:     tpl.Title + " FH: " + host,
@@ -124,6 +150,7 @@ func handleIbex(ctx *ctx.Context, url string, event *models.AlertCurEvent, targe
 		Pause:     tpl.Pause,
 		Script:    tpl.Script,
 		Args:      tpl.Args,
+		Stdin:     string(tags),
 		Action:    "start",
 		Creator:   tpl.UpdateBy,
 		Hosts:     []string{host},

alert/sender/feishucard.go

@@ -0,0 +1,144 @@
+package sender
+
+import (
+	"fmt"
+	"html/template"
+	"strings"
+	"time"
+
+	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/poster"
+
+	"github.com/toolkits/pkg/logger"
+)
+
+type Conf struct {
+	WideScreenMode bool `json:"wide_screen_mode"`
+	EnableForward  bool `json:"enable_forward"`
+}
+
+type Te struct {
+	Content string `json:"content"`
+	Tag     string `json:"tag"`
+}
+
+type Element struct {
+	Tag      string    `json:"tag"`
+	Text     Te        `json:"text"`
+	Content  string    `json:"content"`
+	Elements []Element `json:"elements"`
+}
+
+type Titles struct {
+	Content string `json:"content"`
+	Tag     string `json:"tag"`
+}
+
+type Headers struct {
+	Title    Titles `json:"title"`
+	Template string `json:"template"`
+}
+
+type Cards struct {
+	Config   Conf      `json:"config"`
+	Elements []Element `json:"elements"`
+	Header   Headers   `json:"header"`
+}
+
+type feishuCard struct {
+	feishu
+	Card Cards `json:"card"`
+}
+
+type FeishuCardSender struct {
+	tpl *template.Template
+}
+
+const (
+	Recovered = "recovered"
+	Triggered = "triggered"
+)
+
+var (
+	body = feishuCard{
+		feishu: feishu{Msgtype: "interactive"},
+		Card: Cards{
+			Config: Conf{
+				WideScreenMode: true,
+				EnableForward:  true,
+			},
+			Header: Headers{
+				Title: Titles{
+					Tag: "plain_text",
+				},
+			},
+			Elements: []Element{
+				{
+					Tag: "div",
+					Text: Te{
+						Tag: "lark_md",
+					},
+				},
+				{
+					Tag: "hr",
+				},
+				{
+					Tag: "note",
+					Elements: []Element{
+						{
+							Tag: "lark_md",
+						},
+					},
+				},
+			},
+		},
+	}
+)
+
+func (fs *FeishuCardSender) Send(ctx MessageContext) {
+	if len(ctx.Users) == 0 || ctx.Rule == nil || ctx.Event == nil {
+		return
+	}
+	urls, _ := fs.extract(ctx.Users)
+	message := BuildTplMessage(fs.tpl, ctx.Event)
+	color := "red"
+	lowerUnicode := strings.ToLower(message)
+	if strings.Count(lowerUnicode, Recovered) > 0 && strings.Count(lowerUnicode, Triggered) > 0 {
+		color = "orange"
+	} else if strings.Count(lowerUnicode, Recovered) > 0 {
+		color = "green"
+	}
+
+	SendTitle := fmt.Sprintf("🔔 %s", ctx.Event.RuleName)
+	body.Card.Header.Title.Content = SendTitle
+	body.Card.Header.Template = color
+	body.Card.Elements[0].Text.Content = message
+	body.Card.Elements[2].Elements[0].Content = SendTitle
+	for _, url := range urls {
+		fs.doSend(url, body)
+	}
+}
+
+func (fs *FeishuCardSender) extract(users []*models.User) ([]string, []string) {
+	urls := make([]string, 0, len(users))
+	ats := make([]string, 0)
+	for i := range users {
+		if token, has := users[i].ExtractToken(models.FeishuCard); has {
+			url := token
+			if !strings.HasPrefix(token, "https://") {
+				url = "https://open.feishu.cn/open-apis/bot/v2/hook/" + strings.TrimSpace(token)
+			}
+			urls = append(urls, url)
+		}
+	}
+	return urls, ats
+}
+
+func (fs *FeishuCardSender) doSend(url string, body feishuCard) {
+	res, code, err := poster.PostJSON(url, time.Second*5, body, 3)
+	if err != nil {
+		logger.Errorf("feishucard_sender: result=fail url=%s code=%d error=%v response=%s", url, code, err, string(res))
+	} else {
+		logger.Debugf("feishucard_sender: result=succ url=%s code=%d response=%s", url, code, string(res))
+	}
+}

alert/sender/sender.go

@@ -31,6 +31,8 @@ func NewSender(key string, tpls map[string]*template.Template, smtp aconf.SMTPCo
 		return &WecomSender{tpl: tpls[models.Wecom]}
 	case models.Feishu:
 		return &FeishuSender{tpl: tpls[models.Feishu]}
+	case models.FeishuCard:
+		return &FeishuCardSender{tpl: tpls[models.FeishuCard]}
 	case models.Email:
 		return &EmailSender{subjectTpl: tpls["mailsubject"], contentTpl: tpls[models.Email], smtp: smtp}
 	case models.Mm:

center/cconf/conf.go

@@ -8,6 +8,7 @@ type Center struct {
 	I18NHeaderKey          string
 	MetricDesc             MetricDescType
 	AnonymousAccess        AnonymousAccess
+	UseFileAssets          bool
 }
 
 type Plugin struct {

center/center.go

@@ -13,6 +13,7 @@ import (
 	"github.com/ccfos/nightingale/v6/conf"
 	"github.com/ccfos/nightingale/v6/memsto"
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/models/migrate"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
 	"github.com/ccfos/nightingale/v6/pkg/httpx"
 	"github.com/ccfos/nightingale/v6/pkg/i18nx"
@@ -49,6 +50,7 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 	}
 	ctx := ctx.NewContext(context.Background(), db, true)
 	models.InitRoot(ctx)
+	migrate.Migrate(db)
 
 	redis, err := storage.NewRedis(config.Redis)
 	if err != nil {
@@ -77,8 +79,10 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 
 	writers := writer.NewWriters(config.Pushgw)
 
+	httpx.InitRSAConfig(&config.HTTP.RSA)
+
 	alertrtRouter := alertrt.New(config.HTTP, config.Alert, alertMuteCache, targetCache, busiGroupCache, alertStats, ctx, externalProcessors)
-	centerRouter := centerrt.New(config.HTTP, config.Center, cconf.Operations, dsCache, notifyConfigCache, promClients, redis, sso, ctx, metas, targetCache)
+	centerRouter := centerrt.New(config.HTTP, config.Center, cconf.Operations, dsCache, notifyConfigCache, promClients, redis, sso, ctx, metas, idents, targetCache)
 	pushgwRouter := pushgwrt.New(config.HTTP, config.Pushgw, targetCache, busiGroupCache, idents, writers, ctx)
 
 	r := httpx.GinEngine(config.Global.RunMode, config.HTTP)

center/router/router.go

@@ -3,6 +3,8 @@ package router
 import (
 	"fmt"
 	"net/http"
+	"path"
+	"runtime"
 	"strings"
 	"time"
 
@@ -16,11 +18,13 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
 	"github.com/ccfos/nightingale/v6/pkg/httpx"
 	"github.com/ccfos/nightingale/v6/prom"
+	"github.com/ccfos/nightingale/v6/pushgw/idents"
 	"github.com/ccfos/nightingale/v6/storage"
 
 	"github.com/gin-gonic/gin"
 	"github.com/rakyll/statik/fs"
 	"github.com/toolkits/pkg/logger"
+	"github.com/toolkits/pkg/runner"
 )
 
 type Router struct {
@@ -32,13 +36,14 @@ type Router struct {
 	PromClients       *prom.PromClientMap
 	Redis             storage.Redis
 	MetaSet           *metas.Set
+	IdentSet          *idents.Set
 	TargetCache       *memsto.TargetCacheType
 	Sso               *sso.SsoClient
 	Ctx               *ctx.Context
 }
 
 func New(httpConfig httpx.Config, center cconf.Center, operations cconf.Operation, ds *memsto.DatasourceCacheType, ncc *memsto.NotifyConfigCacheType,
-	pc *prom.PromClientMap, redis storage.Redis, sso *sso.SsoClient, ctx *ctx.Context, metaSet *metas.Set, tc *memsto.TargetCacheType) *Router {
+	pc *prom.PromClientMap, redis storage.Redis, sso *sso.SsoClient, ctx *ctx.Context, metaSet *metas.Set, idents *idents.Set, tc *memsto.TargetCacheType) *Router {
 	return &Router{
 		HTTP:              httpConfig,
 		Center:            center,
@@ -48,6 +53,7 @@ func New(httpConfig httpx.Config, center cconf.Center, operations cconf.Operatio
 		PromClients:       pc,
 		Redis:             redis,
 		MetaSet:           metaSet,
+		IdentSet:          idents,
 		TargetCache:       tc,
 		Sso:               sso,
 		Ctx:               ctx,
@@ -96,9 +102,31 @@ func (rt *Router) configNoRoute(r *gin.Engine, fs *http.FileSystem) {
 
 		switch suffix {
 		case "png", "jpeg", "jpg", "svg", "ico", "gif", "css", "js", "html", "htm", "gz", "zip", "map":
-			c.FileFromFS(c.Request.URL.Path, *fs)
+			if !rt.Center.UseFileAssets {
+				c.FileFromFS(c.Request.URL.Path, *fs)
+			} else {
+				cwdarr := []string{"/"}
+				if runtime.GOOS == "windows" {
+					cwdarr[0] = ""
+				}
+				cwdarr = append(cwdarr, strings.Split(runner.Cwd, "/")...)
+				cwdarr = append(cwdarr, "pub")
+				cwdarr = append(cwdarr, strings.Split(c.Request.URL.Path, "/")...)
+				c.File(path.Join(cwdarr...))
+			}
 		default:
-			c.FileFromFS("/", *fs)
+			if !rt.Center.UseFileAssets {
+				c.FileFromFS("/", *fs)
+			} else {
+				cwdarr := []string{"/"}
+				if runtime.GOOS == "windows" {
+					cwdarr[0] = ""
+				}
+				cwdarr = append(cwdarr, strings.Split(runner.Cwd, "/")...)
+				cwdarr = append(cwdarr, "pub")
+				cwdarr = append(cwdarr, "index.html")
+				c.File(path.Join(cwdarr...))
+			}
 		}
 	})
 }
@@ -113,7 +141,10 @@ func (rt *Router) Config(r *gin.Engine) {
 	if err != nil {
 		logger.Errorf("cannot create statik fs: %v", err)
 	}
-	r.StaticFS("/pub", statikFS)
+
+	if !rt.Center.UseFileAssets {
+		r.StaticFS("/pub", statikFS)
+	}
 
 	pagesPrefix := "/api/n9e"
 	pages := r.Group(pagesPrefix)
@@ -132,10 +163,14 @@ func (rt *Router) Config(r *gin.Engine) {
 		}
 
 		pages.POST("/auth/login", rt.jwtMock(), rt.loginPost)
-		pages.POST("/auth/logout", rt.jwtMock(), rt.logoutPost)
+		pages.POST("/auth/logout", rt.jwtMock(), rt.auth(), rt.logoutPost)
 		pages.POST("/auth/refresh", rt.jwtMock(), rt.refreshPost)
+		pages.POST("/auth/captcha", rt.jwtMock(), rt.generateCaptcha)
+		pages.POST("/auth/captcha-verify", rt.jwtMock(), rt.captchaVerify)
+		pages.GET("/auth/ifshowcaptcha", rt.ifShowCaptcha)
 
 		pages.GET("/auth/sso-config", rt.ssoConfigNameGet)
+		pages.GET("/auth/rsa-config", rt.rsaConfigGet)
 		pages.GET("/auth/redirect", rt.loginRedirect)
 		pages.GET("/auth/redirect/cas", rt.loginRedirectCas)
 		pages.GET("/auth/redirect/oauth", rt.loginRedirectOAuth)
@@ -303,6 +338,8 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.GET("/notify-tpls", rt.auth(), rt.admin(), rt.notifyTplGets)
 		pages.PUT("/notify-tpl/content", rt.auth(), rt.admin(), rt.notifyTplUpdateContent)
 		pages.PUT("/notify-tpl", rt.auth(), rt.admin(), rt.notifyTplUpdate)
+		pages.POST("/notify-tpl", rt.auth(), rt.admin(), rt.notifyTplAdd)
+		pages.DELETE("/notify-tpl/:id", rt.auth(), rt.admin(), rt.notifyTplDel)
 		pages.POST("/notify-tpl/preview", rt.auth(), rt.admin(), rt.notifyTplPreview)
 
 		pages.GET("/sso-configs", rt.auth(), rt.admin(), rt.ssoConfigGets)
@@ -324,10 +361,10 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.PUT("/notify-config", rt.auth(), rt.admin(), rt.notifyConfigPut)
 	}
 
-	if rt.HTTP.Service.Enable {
+	if rt.HTTP.APIForService.Enable {
 		service := r.Group("/v1/n9e")
-		if len(rt.HTTP.Service.BasicAuth) > 0 {
-			service.Use(gin.BasicAuth(rt.HTTP.Service.BasicAuth))
+		if len(rt.HTTP.APIForService.BasicAuth) > 0 {
+			service.Use(gin.BasicAuth(rt.HTTP.APIForService.BasicAuth))
 		}
 		{
 			service.Any("/prometheus/*url", rt.dsProxy)
@@ -387,11 +424,11 @@ func (rt *Router) Config(r *gin.Engine) {
 		}
 	}
 
-	if rt.HTTP.Heartbeat.Enable {
+	if rt.HTTP.APIForAgent.Enable {
 		heartbeat := r.Group("/v1/n9e")
 		{
-			if len(rt.HTTP.Heartbeat.BasicAuth) > 0 {
-				heartbeat.Use(gin.BasicAuth(rt.HTTP.Heartbeat.BasicAuth))
+			if len(rt.HTTP.APIForAgent.BasicAuth) > 0 {
+				heartbeat.Use(gin.BasicAuth(rt.HTTP.APIForAgent.BasicAuth))
 			}
 			heartbeat.POST("/heartbeat", rt.heartbeat)
 		}

center/router/router_alert_subscribe.go

@@ -83,6 +83,9 @@ func (rt *Router) alertSubscribePut(c *gin.Context) {
 			rt.Ctx,
 			"name",
 			"disabled",
+			"prod",
+			"cate",
+			"datasource_ids",
 			"cluster",
 			"rule_id",
 			"tags",
@@ -96,7 +99,6 @@ func (rt *Router) alertSubscribePut(c *gin.Context) {
 			"webhooks",
 			"for_duration",
 			"redefine_webhooks",
-			"datasource_ids",
 		))
 	}
 

center/router/router_captcha.go

@@ -0,0 +1,114 @@
+package router
+
+import (
+	"context"
+	"time"
+
+	"github.com/ccfos/nightingale/v6/storage"
+	"github.com/gin-gonic/gin"
+	captcha "github.com/mojocn/base64Captcha"
+	"github.com/toolkits/pkg/ginx"
+	"github.com/toolkits/pkg/logger"
+)
+
+type CaptchaRedisStore struct {
+	redis storage.Redis
+}
+
+func (s *CaptchaRedisStore) Set(id string, value string) error {
+	ctx := context.Background()
+	err := s.redis.Set(ctx, id, value, time.Duration(300*time.Second)).Err()
+	if err != nil {
+		logger.Errorf("captcha id set to redis error : %s", err.Error())
+		return err
+	}
+	return nil
+}
+
+func (s *CaptchaRedisStore) Get(id string, clear bool) string {
+	ctx := context.Background()
+	val, err := s.redis.Get(ctx, id).Result()
+	if err != nil {
+		logger.Errorf("captcha id get from redis error : %s", err.Error())
+		return ""
+	}
+
+	if clear {
+		s.redis.Del(ctx, id)
+	}
+
+	return val
+}
+
+func (s *CaptchaRedisStore) Verify(id, answer string, clear bool) bool {
+
+	old := s.Get(id, clear)
+	return old == answer
+}
+
+func (rt *Router) newCaptchaRedisStore() *CaptchaRedisStore {
+	if captchaStore == nil {
+		captchaStore = &CaptchaRedisStore{redis: rt.Redis}
+	}
+	return captchaStore
+}
+
+var captchaStore *CaptchaRedisStore
+
+type CaptchaReqBody struct {
+	Id          string
+	VerifyValue string
+}
+
+// 生成图形验证码
+func (rt *Router) generateCaptcha(c *gin.Context) {
+	var driver = captcha.NewDriverMath(60, 200, 0, captcha.OptionShowHollowLine, nil, nil, []string{"wqy-microhei.ttc"})
+	cc := captcha.NewCaptcha(driver, rt.newCaptchaRedisStore())
+	//data:image/png;base64
+	id, b64s, err := cc.Generate()
+
+	if err != nil {
+		ginx.NewRender(c).Message(err)
+		return
+	}
+
+	ginx.NewRender(c).Data(gin.H{
+		"imgdata":   b64s,
+		"captchaid": id,
+	}, nil)
+}
+
+// 验证
+func (rt *Router) captchaVerify(c *gin.Context) {
+
+	var param CaptchaReqBody
+	ginx.BindJSON(c, &param)
+
+	//verify the captcha
+	if captchaStore.Verify(param.Id, param.VerifyValue, true) {
+		ginx.NewRender(c).Message("")
+		return
+	}
+	ginx.NewRender(c).Message("incorrect verification code")
+}
+
+// 验证码开关
+func (rt *Router) ifShowCaptcha(c *gin.Context) {
+
+	if rt.HTTP.ShowCaptcha.Enable {
+		ginx.NewRender(c).Data(gin.H{
+			"show": true,
+		}, nil)
+		return
+	}
+
+	ginx.NewRender(c).Data(gin.H{
+		"show": false,
+	}, nil)
+}
+
+// 验证
+func CaptchaVerify(id string, value string) bool {
+	//verify the captcha
+	return captchaStore.Verify(id, value, true)
+}

center/router/router_datasource.go

@@ -125,8 +125,6 @@ func DatasourceCheck(ds models.Datasource) error {
 		query := url.Values{}
 		if strings.Contains(fullURL, "loki") {
 			subPath = "/api/v1/labels"
-			query.Add("start", "1")
-			query.Add("end", "2")
 		} else {
 			query.Add("query", "1+1")
 		}

center/router/router_heartbeat.go

@@ -35,9 +35,19 @@ func (rt *Router) heartbeat(c *gin.Context) {
 	err = json.Unmarshal(bs, &req)
 	ginx.Dangerous(err)
 
-	req.Offset = (time.Now().UnixMilli() - req.UnixTime)
-	req.RemoteAddr = c.ClientIP()
+	// maybe from pushgw
+	if req.Offset == 0 {
+		req.Offset = (time.Now().UnixMilli() - req.UnixTime)
+	}
+
+	if req.RemoteAddr == "" {
+		req.RemoteAddr = c.ClientIP()
+	}
+
 	rt.MetaSet.Set(req.Hostname, req)
+	var items = make(map[string]struct{})
+	items[req.Hostname] = struct{}{}
+	rt.IdentSet.MSet(items)
 
 	gid := ginx.QueryInt64(c, "gid", 0)
 

center/router/router_login.go

@@ -1,6 +1,7 @@
 package router
 
 import (
+	"encoding/base64"
 	"fmt"
 	"net/http"
 	"strconv"
@@ -12,6 +13,7 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/ldapx"
 	"github.com/ccfos/nightingale/v6/pkg/oauth2x"
 	"github.com/ccfos/nightingale/v6/pkg/oidcx"
+	"github.com/ccfos/nightingale/v6/pkg/secu"
 	"github.com/pelletier/go-toml/v2"
 
 	"github.com/dgrijalva/jwt-go"
@@ -21,20 +23,40 @@ import (
 )
 
 type loginForm struct {
-	Username string `json:"username" binding:"required"`
-	Password string `json:"password" binding:"required"`
+	Username    string `json:"username" binding:"required"`
+	Password    string `json:"password" binding:"required"`
+	Captchaid   string `json:"captchaid"`
+	Verifyvalue string `json:"verifyvalue"`
 }
 
 func (rt *Router) loginPost(c *gin.Context) {
 	var f loginForm
 	ginx.BindJSON(c, &f)
+	logger.Infof("username:%s login from:%s", f.Username, c.ClientIP())
 
-	user, err := models.PassLogin(rt.Ctx, f.Username, f.Password)
+	if rt.HTTP.ShowCaptcha.Enable {
+		if !CaptchaVerify(f.Captchaid, f.Verifyvalue) {
+			ginx.NewRender(c).Message("incorrect verification code")
+			return
+		}
+	}
+	authPassWord := f.Password
+	// need decode
+	if rt.HTTP.RSA.OpenRSA {
+		decPassWord, err := secu.Decrypt(f.Password, rt.HTTP.RSA.RSAPrivateKey, rt.HTTP.RSA.RSAPassWord)
+		if err != nil {
+			logger.Errorf("RSA Decrypt failed: %v username: %s", err, f.Username)
+			ginx.NewRender(c).Message(err)
+			return
+		}
+		authPassWord = decPassWord
+	}
+	user, err := models.PassLogin(rt.Ctx, f.Username, authPassWord)
 	if err != nil {
 		// pass validate fail, try ldap
 		if rt.Sso.LDAP.Enable {
 			roles := strings.Join(rt.Sso.LDAP.DefaultRoles, " ")
-			user, err = models.LdapLogin(rt.Ctx, f.Username, f.Password, roles, rt.Sso.LDAP)
+			user, err = models.LdapLogin(rt.Ctx, f.Username, authPassWord, roles, rt.Sso.LDAP)
 			if err != nil {
 				logger.Debugf("ldap login failed: %v username: %s", err, f.Username)
 				ginx.NewRender(c).Message(err)
@@ -67,6 +89,7 @@ func (rt *Router) loginPost(c *gin.Context) {
 }
 
 func (rt *Router) logoutPost(c *gin.Context) {
+	logger.Infof("username:%s login from:%s", c.GetString("username"), c.ClientIP())
 	metadata, err := rt.extractTokenMetadata(c.Request)
 	if err != nil {
 		ginx.NewRender(c, http.StatusBadRequest).Message("failed to parse jwt token")
@@ -537,3 +560,19 @@ func (rt *Router) ssoConfigUpdate(c *gin.Context) {
 
 	ginx.NewRender(c).Message(nil)
 }
+
+type RSAConfigOutput struct {
+	OpenRSA      bool
+	RSAPublicKey string
+}
+
+func (rt *Router) rsaConfigGet(c *gin.Context) {
+	publicKey := ""
+	if rt.HTTP.RSA.OpenRSA {
+		publicKey = base64.StdEncoding.EncodeToString(rt.HTTP.RSA.RSAPublicKey)
+	}
+	ginx.NewRender(c).Data(RSAConfigOutput{
+		OpenRSA:      rt.HTTP.RSA.OpenRSA,
+		RSAPublicKey: publicKey,
+	}, nil)
+}

center/router/router_notify_tpl.go

@@ -10,12 +10,25 @@ import (
 	"github.com/ccfos/nightingale/v6/center/cconf"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/tplx"
+
 	"github.com/gin-gonic/gin"
 	"github.com/toolkits/pkg/ginx"
+	"github.com/toolkits/pkg/str"
 )
 
 func (rt *Router) notifyTplGets(c *gin.Context) {
+	m := make(map[string]struct{})
+	for _, channel := range models.DefaultChannels {
+		m[channel] = struct{}{}
+	}
+	m["mailsubject"] = struct{}{}
+
 	lst, err := models.NotifyTplGets(rt.Ctx)
+	for i := 0; i < len(lst); i++ {
+		if _, exists := m[lst[i].Channel]; exists {
+			lst[i].BuiltIn = true
+		}
+	}
 
 	ginx.NewRender(c).Data(lst, err)
 }
@@ -23,11 +36,7 @@ func (rt *Router) notifyTplGets(c *gin.Context) {
 func (rt *Router) notifyTplUpdateContent(c *gin.Context) {
 	var f models.NotifyTpl
 	ginx.BindJSON(c, &f)
-
-	if err := templateValidate(f); err != nil {
-		ginx.NewRender(c).Message(err.Error())
-		return
-	}
+	ginx.Dangerous(templateValidate(f))
 
 	ginx.NewRender(c).Message(f.UpdateContent(rt.Ctx))
 }
@@ -35,16 +44,28 @@ func (rt *Router) notifyTplUpdateContent(c *gin.Context) {
 func (rt *Router) notifyTplUpdate(c *gin.Context) {
 	var f models.NotifyTpl
 	ginx.BindJSON(c, &f)
-
-	if err := templateValidate(f); err != nil {
-		ginx.NewRender(c).Message(err.Error())
-		return
-	}
+	ginx.Dangerous(templateValidate(f))
 
 	ginx.NewRender(c).Message(f.Update(rt.Ctx))
 }
 
 func templateValidate(f models.NotifyTpl) error {
+	if len(f.Channel) > 32 {
+		return fmt.Errorf("channel length should not exceed 32")
+	}
+
+	if str.Dangerous(f.Channel) {
+		return fmt.Errorf("channel should not contain dangerous characters")
+	}
+
+	if len(f.Name) > 255 {
+		return fmt.Errorf("name length should not exceed 255")
+	}
+
+	if str.Dangerous(f.Name) {
+		return fmt.Errorf("name should not contain dangerous characters")
+	}
+
 	if f.Content == "" {
 		return nil
 	}
@@ -65,10 +86,7 @@ func templateValidate(f models.NotifyTpl) error {
 func (rt *Router) notifyTplPreview(c *gin.Context) {
 	var event models.AlertCurEvent
 	err := json.Unmarshal([]byte(cconf.EVENT_EXAMPLE), &event)
-	if err != nil {
-		ginx.NewRender(c).Message(err.Error())
-		return
-	}
+	ginx.Dangerous(err)
 
 	var f models.NotifyTpl
 	ginx.BindJSON(c, &f)
@@ -106,3 +124,25 @@ func (rt *Router) notifyTplPreview(c *gin.Context) {
 
 	ginx.NewRender(c).Data(ret, nil)
 }
+
+// add new notify template
+func (rt *Router) notifyTplAdd(c *gin.Context) {
+	var f models.NotifyTpl
+	ginx.BindJSON(c, &f)
+	f.Channel = strings.TrimSpace(f.Channel)
+	ginx.Dangerous(templateValidate(f))
+
+	count, err := models.NotifyTplCountByChannel(rt.Ctx, f.Channel)
+	ginx.Dangerous(err)
+	if count != 0 {
+		ginx.Bomb(200, "Refuse to create duplicate channel(unique)")
+	}
+	ginx.NewRender(c).Message(f.Create(rt.Ctx))
+}
+
+// delete notify template, not allowed to delete the system defaults(models.DefaultChannels)
+func (rt *Router) notifyTplDel(c *gin.Context) {
+	f := new(models.NotifyTpl)
+	id := ginx.UrlParamInt64(c, "id")
+	ginx.NewRender(c).Message(f.NotifyTplDelete(rt.Ctx, id))
+}

center/router/router_proxy.go

@@ -8,6 +8,7 @@ import (
 	"net/http/httputil"
 	"net/url"
 	"strings"
+	"sync"
 	"time"
 
 	pkgprom "github.com/ccfos/nightingale/v6/pkg/prom"
@@ -139,14 +140,18 @@ func (rt *Router) dsProxy(c *gin.Context) {
 		http.Error(w, err.Error(), http.StatusBadGateway)
 	}
 
-	transport := &http.Transport{
-		TLSClientConfig: &tls.Config{InsecureSkipVerify: ds.HTTPJson.TLS.SkipTlsVerify},
-		Proxy:           http.ProxyFromEnvironment,
-		DialContext: (&net.Dialer{
-			Timeout: time.Duration(ds.HTTPJson.DialTimeout) * time.Millisecond,
-		}).DialContext,
-		ResponseHeaderTimeout: time.Duration(ds.HTTPJson.Timeout) * time.Millisecond,
-		MaxIdleConnsPerHost:   ds.HTTPJson.MaxIdleConnsPerHost,
+	transport, has := transportGet(dsId, ds.UpdatedAt)
+	if !has {
+		transport = &http.Transport{
+			TLSClientConfig: &tls.Config{InsecureSkipVerify: ds.HTTPJson.TLS.SkipTlsVerify},
+			Proxy:           http.ProxyFromEnvironment,
+			DialContext: (&net.Dialer{
+				Timeout: time.Duration(ds.HTTPJson.DialTimeout) * time.Millisecond,
+			}).DialContext,
+			ResponseHeaderTimeout: time.Duration(ds.HTTPJson.Timeout) * time.Millisecond,
+			MaxIdleConnsPerHost:   ds.HTTPJson.MaxIdleConnsPerHost,
+		}
+		transportPut(dsId, ds.UpdatedAt, transport)
 	}
 
 	proxy := &httputil.ReverseProxy{
@@ -157,3 +162,44 @@ func (rt *Router) dsProxy(c *gin.Context) {
 
 	proxy.ServeHTTP(c.Writer, c.Request)
 }
+
+var (
+	transports     = map[int64]http.RoundTripper{}
+	updatedAts     = map[int64]int64{}
+	transportsLock = &sync.Mutex{}
+)
+
+func transportGet(dsid, newUpdatedAt int64) (http.RoundTripper, bool) {
+	transportsLock.Lock()
+	defer transportsLock.Unlock()
+
+	tran, has := transports[dsid]
+	if !has {
+		return nil, false
+	}
+
+	oldUpdateAt, has := updatedAts[dsid]
+	if !has {
+		oldtran := tran.(*http.Transport)
+		oldtran.CloseIdleConnections()
+		delete(transports, dsid)
+		return nil, false
+	}
+
+	if oldUpdateAt != newUpdatedAt {
+		oldtran := tran.(*http.Transport)
+		oldtran.CloseIdleConnections()
+		delete(transports, dsid)
+		delete(updatedAts, dsid)
+		return nil, false
+	}
+
+	return tran, has
+}
+
+func transportPut(dsid, updatedat int64, tran http.RoundTripper) {
+	transportsLock.Lock()
+	transports[dsid] = tran
+	updatedAts[dsid] = updatedat
+	transportsLock.Unlock()
+}

center/router/router_target.go

@@ -80,16 +80,18 @@ func (rt *Router) targetGets(c *gin.Context) {
 			}
 
 			for i := 0; i < len(list); i++ {
-				if now.Unix()-list[i].UpdateAt < 120 {
-					list[i].TargetUp = 1
-				}
-
 				if meta, ok := metaMap[list[i].Ident]; ok {
 					list[i].FillMeta(meta)
 				} else {
 					// 未上报过元数据的主机，cpuNum默认为-1, 用于前端展示 unknown
 					list[i].CpuNum = -1
 				}
+
+				if now.Unix()-list[i].UnixTime/1000 < 60 {
+					list[i].TargetUp = 2
+				} else if now.Unix()-list[i].UnixTime/1000 < 180 {
+					list[i].TargetUp = 1
+				}
 			}
 		}
 

cli/upgrade/upgrade.go

@@ -18,9 +18,9 @@ func Upgrade(configFile string) error {
 		return err
 	}
 
-	ctx := ctx.NewContext(context.Background(), db, false)
+	ctx := ctx.NewContext(context.Background(), db, true)
 	for _, cluster := range config.Clusters {
-		count, err := models.GetDatasourcesCountBy(ctx, "", "", cluster.Name)
+		count, err := models.GetDatasourcesCountByName(ctx, cluster.Name)
 		if err != nil {
 			logger.Errorf("get datasource %s count error: %v", cluster.Name, err)
 			continue

cli/upgrade/upgrade.sql

@@ -8,6 +8,13 @@ insert into `role_operation`(role_name, operation) values('Standard', '/trace/ex
 insert into `role_operation`(role_name, operation) values('Standard', '/alert-rules-built-in');
 insert into `role_operation`(role_name, operation) values('Standard', '/dashboards-built-in');
 insert into `role_operation`(role_name, operation) values('Standard', '/trace/dependencies');
+insert into `role_operation`(role_name, operation) values('Standard', '/help/servers');
+insert into `role_operation`(role_name, operation) values('Standard', '/help/migrate');
+
+insert into `role_operation`(role_name, operation) values('Admin', '/help/source');
+insert into `role_operation`(role_name, operation) values('Admin', '/help/sso');
+insert into `role_operation`(role_name, operation) values('Admin', '/help/notification-tpls');
+insert into `role_operation`(role_name, operation) values('Admin', '/help/notification-settings');
 
 alter table `board` add built_in tinyint(1) not null default 0 comment '0:false 1:true';
 alter table `board` add hide tinyint(1) not null default 0 comment '0:false 1:true';

cmd/alert/main.go

@@ -17,7 +17,7 @@ import (
 
 var (
 	showVersion = flag.Bool("version", false, "Show version.")
-	configDir   = flag.String("configs", osx.GetEnv("N9E_CONFIGS", "etc"), "Specify configuration directory.(env:N9E_CONFIGS)")
+	configDir   = flag.String("configs", osx.GetEnv("N9E_ALERT_CONFIGS", "etc"), "Specify configuration directory.(env:N9E_ALERT_CONFIGS)")
 	cryptoKey   = flag.String("crypto-key", "", "Specify the secret key for configuration file field encryption.")
 )
 

cmd/edge/edge.go

@@ -0,0 +1,69 @@
+package main
+
+import (
+	"context"
+	"fmt"
+
+	"github.com/ccfos/nightingale/v6/alert"
+	"github.com/ccfos/nightingale/v6/alert/astats"
+	"github.com/ccfos/nightingale/v6/alert/process"
+	"github.com/ccfos/nightingale/v6/conf"
+	"github.com/ccfos/nightingale/v6/memsto"
+	"github.com/ccfos/nightingale/v6/pkg/ctx"
+	"github.com/ccfos/nightingale/v6/pkg/httpx"
+	"github.com/ccfos/nightingale/v6/pkg/logx"
+	"github.com/ccfos/nightingale/v6/prom"
+	"github.com/ccfos/nightingale/v6/pushgw/idents"
+	"github.com/ccfos/nightingale/v6/pushgw/writer"
+
+	alertrt "github.com/ccfos/nightingale/v6/alert/router"
+	pushgwrt "github.com/ccfos/nightingale/v6/pushgw/router"
+)
+
+func Initialize(configDir string, cryptoKey string) (func(), error) {
+	config, err := conf.InitConfig(configDir, cryptoKey)
+	if err != nil {
+		return nil, fmt.Errorf("failed to init config: %v", err)
+	}
+
+	logxClean, err := logx.Init(config.Log)
+	if err != nil {
+		return nil, err
+	}
+
+	ctx := ctx.NewContext(context.Background(), nil, false, config.CenterApi)
+
+	syncStats := memsto.NewSyncStats()
+
+	targetCache := memsto.NewTargetCache(ctx, syncStats, nil)
+	busiGroupCache := memsto.NewBusiGroupCache(ctx, syncStats)
+	idents := idents.New(ctx)
+	writers := writer.NewWriters(config.Pushgw)
+	pushgwRouter := pushgwrt.New(config.HTTP, config.Pushgw, targetCache, busiGroupCache, idents, writers, ctx)
+	r := httpx.GinEngine(config.Global.RunMode, config.HTTP)
+	pushgwRouter.Config(r)
+
+	if !config.Alert.Disable {
+		alertStats := astats.NewSyncStats()
+		dsCache := memsto.NewDatasourceCache(ctx, syncStats)
+		alertMuteCache := memsto.NewAlertMuteCache(ctx, syncStats)
+		alertRuleCache := memsto.NewAlertRuleCache(ctx, syncStats)
+		notifyConfigCache := memsto.NewNotifyConfigCache(ctx)
+
+		promClients := prom.NewPromClient(ctx, config.Alert.Heartbeat)
+		externalProcessors := process.NewExternalProcessors()
+
+		alert.Start(config.Alert, config.Pushgw, syncStats, alertStats, externalProcessors, targetCache, busiGroupCache, alertMuteCache, alertRuleCache, notifyConfigCache, dsCache, ctx, promClients)
+
+		alertrtRouter := alertrt.New(config.HTTP, config.Alert, alertMuteCache, targetCache, busiGroupCache, alertStats, ctx, externalProcessors)
+
+		alertrtRouter.Config(r)
+	}
+
+	httpClean := httpx.Init(config.HTTP, r)
+
+	return func() {
+		logxClean()
+		httpClean()
+	}, nil
+}

cmd/edge/main.go

@@ -0,0 +1,68 @@
+package main
+
+import (
+	"flag"
+	"fmt"
+	"log"
+	"os"
+	"os/signal"
+	"syscall"
+
+	"github.com/ccfos/nightingale/v6/pkg/osx"
+	"github.com/ccfos/nightingale/v6/pkg/version"
+
+	"github.com/toolkits/pkg/runner"
+)
+
+var (
+	showVersion = flag.Bool("version", false, "Show version.")
+	configDir   = flag.String("configs", osx.GetEnv("N9E_EDGE_CONFIGS", "etc"), "Specify configuration directory.(env:N9E_EDGE_CONFIGS)")
+	cryptoKey   = flag.String("crypto-key", "", "Specify the secret key for configuration file field encryption.")
+)
+
+func main() {
+	flag.Parse()
+
+	if *showVersion {
+		fmt.Println(version.Version)
+		os.Exit(0)
+	}
+
+	printEnv()
+
+	cleanFunc, err := Initialize(*configDir, *cryptoKey)
+	if err != nil {
+		log.Fatalln("failed to initialize:", err)
+	}
+
+	code := 1
+	sc := make(chan os.Signal, 1)
+	signal.Notify(sc, syscall.SIGHUP, syscall.SIGINT, syscall.SIGTERM, syscall.SIGQUIT)
+
+EXIT:
+	for {
+		sig := <-sc
+		fmt.Println("received signal:", sig.String())
+		switch sig {
+		case syscall.SIGQUIT, syscall.SIGTERM, syscall.SIGINT:
+			code = 0
+			break EXIT
+		case syscall.SIGHUP:
+			// reload configuration?
+		default:
+			break EXIT
+		}
+	}
+
+	cleanFunc()
+	fmt.Println("process exited")
+	os.Exit(code)
+}
+
+func printEnv() {
+	runner.Init()
+	fmt.Println("runner.cwd:", runner.Cwd)
+	fmt.Println("runner.hostname:", runner.Hostname)
+	fmt.Println("runner.fd_limits:", runner.FdLimits())
+	fmt.Println("runner.vm_limits:", runner.VMLimits())
+}

cmd/pushgw/main.go

@@ -17,7 +17,7 @@ import (
 
 var (
 	showVersion = flag.Bool("version", false, "Show version.")
-	configDir   = flag.String("configs", osx.GetEnv("N9E_CONFIGS", "etc"), "Specify configuration directory.(env:N9E_CONFIGS)")
+	configDir   = flag.String("configs", osx.GetEnv("N9E_PUSHGW_CONFIGS", "etc"), "Specify configuration directory.(env:N9E_PUSHGW_CONFIGS)")
 	cryptoKey   = flag.String("crypto-key", "", "Specify the secret key for configuration file field encryption.")
 )
 

conf/conf.go

@@ -14,8 +14,6 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/ormx"
 	"github.com/ccfos/nightingale/v6/pushgw/pconf"
 	"github.com/ccfos/nightingale/v6/storage"
-
-	"github.com/gin-gonic/gin"
 )
 
 type ConfigType struct {
@@ -32,8 +30,10 @@ type ConfigType struct {
 }
 
 type CenterApi struct {
-	Addrs     []string
-	BasicAuth gin.Accounts
+	Addrs         []string
+	BasicAuthUser string
+	BasicAuthPass string
+	Timeout       int64
 }
 
 type GlobalConfig struct {

conf/crypto.go

@@ -14,39 +14,22 @@ func decryptConfig(config *ConfigType, cryptoKey string) error {
 
 	config.DB.DSN = decryptDsn
 
-	for k := range config.HTTP.Alert.BasicAuth {
-		decryptPwd, err := secu.DealWithDecrypt(config.HTTP.Alert.BasicAuth[k], cryptoKey)
+	for k := range config.HTTP.APIForService.BasicAuth {
+		decryptPwd, err := secu.DealWithDecrypt(config.HTTP.APIForService.BasicAuth[k], cryptoKey)
 		if err != nil {
 			return fmt.Errorf("failed to decrypt http basic auth password: %s", err)
 		}
 
-		config.HTTP.Alert.BasicAuth[k] = decryptPwd
+		config.HTTP.APIForService.BasicAuth[k] = decryptPwd
 	}
 
-	for k := range config.HTTP.Pushgw.BasicAuth {
-		decryptPwd, err := secu.DealWithDecrypt(config.HTTP.Pushgw.BasicAuth[k], cryptoKey)
+	for k := range config.HTTP.APIForAgent.BasicAuth {
+		decryptPwd, err := secu.DealWithDecrypt(config.HTTP.APIForAgent.BasicAuth[k], cryptoKey)
 		if err != nil {
 			return fmt.Errorf("failed to decrypt http basic auth password: %s", err)
 		}
 
-		config.HTTP.Pushgw.BasicAuth[k] = decryptPwd
-	}
-
-	for k := range config.HTTP.Heartbeat.BasicAuth {
-		decryptPwd, err := secu.DealWithDecrypt(config.HTTP.Heartbeat.BasicAuth[k], cryptoKey)
-		if err != nil {
-			return fmt.Errorf("failed to decrypt http basic auth password: %s", err)
-		}
-
-		config.HTTP.Heartbeat.BasicAuth[k] = decryptPwd
-	}
-
-	for k := range config.HTTP.Service.BasicAuth {
-		decryptPwd, err := secu.DealWithDecrypt(config.HTTP.Service.BasicAuth[k], cryptoKey)
-		if err != nil {
-			return fmt.Errorf("failed to decrypt http basic auth password: %s", err)
-		}
-		config.HTTP.Service.BasicAuth[k] = decryptPwd
+		config.HTTP.APIForAgent.BasicAuth[k] = decryptPwd
 	}
 
 	for i, v := range config.Pushgw.Writers {

docker/experience_pg_vm/initsql_for_postgres/b-ibex-for-Postgres.sql

@@ -1,16 +1,17 @@
 CREATE TABLE task_meta
 (
-    id        bigserial,
-    title     varchar(255)    not null default '',
-    account   varchar(64)     not null,
-    batch     int     not null default 0,
-    tolerance int     not null default 0,
-    timeout   int     not null default 0,
-    pause     varchar(255)    not null default '',
-    script    text            not null,
-    args      varchar(512)    not null default '',
-    creator   varchar(64)     not null default '',
-    created   timestamp       not null default CURRENT_TIMESTAMP,
+    id          bigserial,
+    title       varchar(255)    not null default '',
+    account     varchar(64)     not null,
+    batch       int     not null default 0,
+    tolerance   int     not null default 0,
+    timeout     int     not null default 0,
+    pause       varchar(255)    not null default '',
+    script      text            not null,
+    args        varchar(512)    not null default '',
+    stdin       varchar(1024)   not null default '' ,
+    creator     varchar(64)     not null default '',
+    created     timestamp       not null default CURRENT_TIMESTAMP,
     PRIMARY KEY (id)
 ) ;
 CREATE INDEX task_meta_creator_idx ON task_meta (creator);

docker/initsql/a-n9e.sql

@@ -54,7 +54,7 @@ insert into user_group_member(group_id, user_id) values(1, 1);
 CREATE TABLE `configs` (
     `id` bigint unsigned not null auto_increment,
     `ckey` varchar(191) not null,
-    `cval` varchar(4096) not null default '',
+    `cval` text not null,
     PRIMARY KEY (`id`),
     UNIQUE KEY (`ckey`)
 ) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
@@ -94,10 +94,17 @@ insert into `role_operation`(role_name, operation) values('Standard', '/log/expl
 insert into `role_operation`(role_name, operation) values('Standard', '/trace/explorer');
 insert into `role_operation`(role_name, operation) values('Standard', '/help/version');
 insert into `role_operation`(role_name, operation) values('Standard', '/help/contact');
+insert into `role_operation`(role_name, operation) values('Standard', '/help/servers');
+insert into `role_operation`(role_name, operation) values('Standard', '/help/migrate');
 insert into `role_operation`(role_name, operation) values('Standard', '/alert-rules-built-in');
 insert into `role_operation`(role_name, operation) values('Standard', '/dashboards-built-in');
 insert into `role_operation`(role_name, operation) values('Standard', '/trace/dependencies');
 
+insert into `role_operation`(role_name, operation) values('Admin', '/help/source');
+insert into `role_operation`(role_name, operation) values('Admin', '/help/sso');
+insert into `role_operation`(role_name, operation) values('Admin', '/help/notification-tpls');
+insert into `role_operation`(role_name, operation) values('Admin', '/help/notification-settings');
+
 insert into `role_operation`(role_name, operation) values('Standard', '/users');
 insert into `role_operation`(role_name, operation) values('Standard', '/user-groups');
 insert into `role_operation`(role_name, operation) values('Standard', '/user-groups/add');
@@ -395,6 +402,7 @@ CREATE TABLE `recording_rule` (
     `prom_ql` varchar(8192) not null comment 'promql',
     `prom_eval_interval` int not null comment 'evaluate interval',
     `append_tags` varchar(255) default '' comment 'split by space: service=n9e mod=api',
+    `query_configs` text not null comment 'query configs',
     `create_at` bigint default '0',
     `create_by` varchar(64) default '',
     `update_at` bigint default '0',

docker/initsql/b-ibex.sql

@@ -6,17 +6,18 @@ use ibex;
 
 CREATE TABLE `task_meta`
 (
-    `id`        bigint unsigned NOT NULL AUTO_INCREMENT,
-    `title`     varchar(255)    not null default '',
-    `account`   varchar(64)     not null,
-    `batch`     int unsigned    not null default 0,
-    `tolerance` int unsigned    not null default 0,
-    `timeout`   int unsigned    not null default 0,
-    `pause`     varchar(255)    not null default '',
-    `script`    text            not null,
-    `args`      varchar(512)    not null default '',
-    `creator`   varchar(64)     not null default '',
-    `created`   timestamp       not null default CURRENT_TIMESTAMP,
+    `id`          bigint unsigned NOT NULL AUTO_INCREMENT,
+    `title`       varchar(255)    not null default '',
+    `account`     varchar(64)     not null,
+    `batch`       int unsigned    not null default 0,
+    `tolerance`   int unsigned    not null default 0,
+    `timeout`     int unsigned    not null default 0,
+    `pause`       varchar(255)    not null default '',
+    `script`      text            not null,
+    `args`        varchar(512)    not null default '',
+    `stdin`       varchar(1024)   not null default '',
+    `creator`     varchar(64)     not null default '',
+    `created`     timestamp       not null default CURRENT_TIMESTAMP,
     PRIMARY KEY (`id`),
     KEY (`creator`),
     KEY (`created`)

etc/alert.toml.example

@@ -1,60 +0,0 @@
-[Global]
-RunMode = "release"
-
-[CenterApi]
-Addrs = ["http://127.0.0.1:17000"]
-[CenterApi.BasicAuth]
-user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
-
-[Alert]
-[Alert.Heartbeat]
-# auto detect if blank
-IP = ""
-# unit ms
-Interval = 1000
-EngineName = "default02"
-
-[Log]
-# log write dir
-Dir = "logs"
-# log level: DEBUG INFO WARNING ERROR
-Level = "DEBUG"
-# stdout, stderr, file
-Output = "stdout"
-# # rotate by time
-# KeepHours = 4
-# # rotate by size
-# RotateNum = 3
-# # unit: MB
-# RotateSize = 256
-
-[HTTP]
-# http listening address
-Host = "0.0.0.0"
-# http listening port
-Port = 17001
-# https cert file path
-CertFile = ""
-# https key file path
-KeyFile = ""
-# whether print access log
-PrintAccessLog = false
-# whether enable pprof
-PProf = false
-# expose prometheus /metrics?
-ExposeMetrics = true
-# http graceful shutdown timeout, unit: s
-ShutdownTimeout = 30
-# max content length: 64M
-MaxContentLength = 67108864
-# http server read timeout, unit: s
-ReadTimeout = 20
-# http server write timeout, unit: s
-WriteTimeout = 40
-# http server idle timeout, unit: s
-IdleTimeout = 120
-
-[HTTP.Alert]
-Enable = true 
-[HTTP.Alert.BasicAuth]
-user001 = "ccc26da7b9aba533cbb263a36c07dcc5"

etc/config.toml

@@ -41,24 +41,17 @@ WriteTimeout = 40
 # http server idle timeout, unit: s
 IdleTimeout = 120
 
-[HTTP.Pushgw]
+[HTTP.ShowCaptcha]
+Enable = false 
+
+[HTTP.APIForAgent]
 Enable = true 
-# [HTTP.Pushgw.BasicAuth]
+# [HTTP.APIForAgent.BasicAuth]
 # user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
-[HTTP.Alert]
+[HTTP.APIForService]
 Enable = true 
-[HTTP.Alert.BasicAuth]
-user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
-
-[HTTP.Heartbeat]
-Enable = true 
-# [HTTP.Heartbeat.BasicAuth]
-# user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
-
-[HTTP.Service]
-Enable = true 
-[HTTP.Service.BasicAuth]
+[HTTP.APIForService.BasicAuth]
 user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
 [HTTP.JWTAuth]
@@ -77,6 +70,16 @@ Enable = false
 HeaderUserNameKey = "X-User-Name"
 DefaultRoles = ["Standard"]
 
+[HTTP.RSA]
+# open RSA
+OpenRSA = false
+# RSA public key
+RSAPublicKeyPath = "/etc/n9e/public.pem"
+# RSA private key
+RSAPrivateKeyPath = "/etc/n9e/private.pem"
+# RSA private key password
+RSAPassWord = ""
+
 [DB]
 # postgres: host=%s port=%s user=%s dbname=%s password=%s sslmode=%s
 DSN="root:1234@tcp(127.0.0.1:3306)/n9e_v6?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"
@@ -141,12 +144,8 @@ LabelRewrite = true
 # __name__ = "xx"
 
 # [Pushgw.WriterOpt]
-# # Writer Options
-# QueueCount = 1000
 # QueueMaxSize = 1000000
 # QueuePopSize = 1000
-# # ident or metric
-# ShardingKey = "ident"
 
 [[Pushgw.Writers]] 
 # Url = "http://127.0.0.1:8480/insert/0/prometheus/api/v1/write"

etc/edge/edge.toml

@@ -3,9 +3,72 @@ RunMode = "release"
 
 [CenterApi]
 Addrs = ["http://127.0.0.1:17000"]
-[CenterApi.BasicAuth]
+BasicAuthUser = "user001"
+BasicAuthPass = "ccc26da7b9aba533cbb263a36c07dcc5"
+# unit: ms
+Timeout = 9000
+
+[Log]
+# log write dir
+Dir = "logs"
+# log level: DEBUG INFO WARNING ERROR
+Level = "DEBUG"
+# stdout, stderr, file
+Output = "stdout"
+# # rotate by time
+# KeepHours = 4
+# # rotate by size
+# RotateNum = 3
+# # unit: MB
+# RotateSize = 256
+
+[HTTP]
+# http listening address
+Host = "0.0.0.0"
+# http listening port
+Port = 19000
+# https cert file path
+CertFile = ""
+# https key file path
+KeyFile = ""
+# whether print access log
+PrintAccessLog = false
+# whether enable pprof
+PProf = false
+# expose prometheus /metrics?
+ExposeMetrics = true
+# http graceful shutdown timeout, unit: s
+ShutdownTimeout = 30
+# max content length: 64M
+MaxContentLength = 67108864
+# http server read timeout, unit: s
+ReadTimeout = 20
+# http server write timeout, unit: s
+WriteTimeout = 40
+# http server idle timeout, unit: s
+IdleTimeout = 120
+
+[HTTP.APIForAgent]
+Enable = true 
+# [HTTP.APIForAgent.BasicAuth]
+# user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
+
+[HTTP.APIForService]
+Enable = true 
+[HTTP.APIForService.BasicAuth]
 user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
+[Alert]
+[Alert.Heartbeat]
+# auto detect if blank
+IP = ""
+# unit ms
+Interval = 1000
+EngineName = "edge"
+
+# [Alert.Alerting]
+# NotifyConcurrency = 10
+
 [Pushgw]
 # use target labels in database instead of in series
 LabelRewrite = true
@@ -18,12 +81,8 @@ LabelRewrite = true
 # __name__ = "xx"
 
 # [Pushgw.WriterOpt]
-# # Writer Options
-# QueueCount = 1000
 # QueueMaxSize = 1000000
 # QueuePopSize = 1000
-# # ident or metric
-# ShardingKey = "ident"
 
 [[Pushgw.Writers]] 
 # Url = "http://127.0.0.1:8480/insert/0/prometheus/api/v1/write"
@@ -56,48 +115,3 @@ MaxIdleConnsPerHost = 100
 # Regex = "([^:]+)(?::\\d+)?"
 # Replacement = "$1:80"
 # TargetLabel = "__address__"
-
-[Log]
-# log write dir
-Dir = "logs"
-# log level: DEBUG INFO WARNING ERROR
-Level = "DEBUG"
-# stdout, stderr, file
-Output = "stdout"
-# # rotate by time
-# KeepHours = 4
-# # rotate by size
-# RotateNum = 3
-# # unit: MB
-# RotateSize = 256
-
-[HTTP]
-# http listening address
-Host = "0.0.0.0"
-# http listening port
-Port = 17000
-# https cert file path
-CertFile = ""
-# https key file path
-KeyFile = ""
-# whether print access log
-PrintAccessLog = false
-# whether enable pprof
-PProf = false
-# expose prometheus /metrics?
-ExposeMetrics = true
-# http graceful shutdown timeout, unit: s
-ShutdownTimeout = 30
-# max content length: 64M
-MaxContentLength = 67108864
-# http server read timeout, unit: s
-ReadTimeout = 20
-# http server write timeout, unit: s
-WriteTimeout = 40
-# http server idle timeout, unit: s
-IdleTimeout = 120
-
-[HTTP.Pushgw]
-Enable = true 
-# [HTTP.Pushgw.BasicAuth]
-# user001 = "ccc26da7b9aba533cbb263a36c07dcc5"

etc/metrics.yaml

@@ -40,14 +40,14 @@ zh:
   kernel_processes_forked: fork的进程数
 
   mem_active: 活跃使用的内存总数(包括cache和buffer内存)
-  mem_available: 应用程序可用内存数
+  mem_available: 可用内存大小(bytes)
   mem_available_percent: 内存剩余百分比(0~100)
   mem_buffered: 用来给文件做缓冲大小
   mem_cached: 被高速缓冲存储器（cache memory）用的内存的大小（等于 diskcache minus SwapCache ）
   mem_commit_limit: 根据超额分配比率（'vm.overcommit_ratio'），这是当前在系统上分配可用的内存总量，这个限制只是在模式2('vm.overcommit_memory')时启用
   mem_committed_as: 目前在系统上分配的内存量。是所有进程申请的内存的总和
   mem_dirty: 等待被写回到磁盘的内存大小
-  mem_free: 空闲内存数
+  mem_free: 空闲内存大小(bytes)
   mem_high_free: 未被使用的高位内存大小
   mem_high_total: 高位内存总大小（Highmem是指所有内存高于860MB的物理内存,Highmem区域供用户程序使用，或用于页面缓存。该区域不是直接映射到内核空间。内核必须使用不同的手法使用该段内存）
   mem_huge_page_size: 每个大页的大小

etc/ops.yaml

@@ -107,4 +107,5 @@ ops:
   - "/help/source"
   - "/help/sso"
   - "/help/notification-tpls"
-  - "/help/notification-settings"
+  - "/help/notification-settings"
+  - "/help/migrate"

etc/template/README.md

@@ -1,26 +0,0 @@
-# 告警消息模版文件
-
-模版中可以使用的变量参考`AlertCurEvent`对象
-模版语法如何使用可以参考[html/template](https://pkg.go.dev/html/template)
-
-## 如何在告警模版中添加监控详情url
-
-假设web的地址是http://127.0.0.1:18000/, 实际使用时用web地址替换该地址
-
-在监控模版中添加以下行:
-
-* dingtalk / wecom / feishu
-```markdown
-[监控详情](http://127.0.0.1:18000/metric/explorer?promql={{ .PromQl | escape }})
-```
-
-* mailbody
-
-```html
-<tr>
-  <th>监控详情：</th>
-  <td>
-    <a href="http://127.0.0.1:18000/metric/explorer?promql={{ .PromQl | escape }}" target="_blank">点击查看</a>
-  </td>
-</tr>
-```

etc/template/dingtalk.tpl

@@ -1,11 +0,0 @@
-#### {{if .IsRecovered}}<font color="#008800">S{{.Severity}} - Recovered - {{.RuleName}}</font>{{else}}<font color="#FF0000">S{{.Severity}} - Triggered - {{.RuleName}}</font>{{end}}
-
----
-
-- **规则标题**: {{.RuleName}}{{if .RuleNote}}
-- **规则备注**: {{.RuleNote}}{{end}}
-{{if not .IsRecovered}}- **触发时值**: {{.TriggerValue}}{{end}}
-{{if .TargetIdent}}- **监控对象**: {{.TargetIdent}}{{end}}
-- **监控指标**: {{.TagsJSON}}
-- {{if .IsRecovered}}**恢复时间**: {{timeformat .LastEvalTime}}{{else}}**触发时间**: {{timeformat .TriggerTime}}{{end}}
-- **发送时间**: {{timestamp}}

etc/template/email.tpl

@@ -1,217 +0,0 @@
-<!DOCTYPE html>
-<html lang="en">
-<head>
-    <meta charset="UTF-8">
-    <meta http-equiv="X-UA-Compatible" content="ie=edge">
-    <title>夜莺告警通知</title>
-    <style type="text/css">
-        .wrapper {
-            background-color: #f8f8f8;
-            padding: 15px;
-            height: 100%;
-        }
-        .main {
-            width: 600px;
-            padding: 30px;
-            margin: 0 auto;
-            background-color: #fff;
-            font-size: 12px;
-            font-family: verdana,'Microsoft YaHei',Consolas,'Deja Vu Sans Mono','Bitstream Vera Sans Mono';
-        }
-        header {
-            border-radius: 2px 2px 0 0;
-        }
-        header .title {
-            font-size: 14px;
-            color: #333333;
-            margin: 0;
-        }
-        header .sub-desc {
-            color: #333;
-            font-size: 14px;
-            margin-top: 6px;
-            margin-bottom: 0;
-        }
-        hr {
-            margin: 20px 0;
-            height: 0;
-            border: none;
-            border-top: 1px solid #e5e5e5;
-        }
-        em {
-            font-weight: 600;
-        }
-        table {
-            margin: 20px 0;
-            width: 100%;
-        }
-
-        table tbody tr{
-            font-weight: 200;
-            font-size: 12px;
-            color: #666;
-            height: 32px;
-        }
-
-        .succ {
-            background-color: green;
-            color: #fff;
-        }
-
-        .fail {
-            background-color: red;
-            color: #fff;
-        }
-
-        .succ th, .succ td, .fail th, .fail td {
-            color: #fff;
-        }
-
-        table tbody tr th {
-            width: 80px;
-            text-align: right;
-        }
-        .text-right {
-            text-align: right;
-        }
-        .body {
-            margin-top: 24px;
-        }
-        .body-text {
-            color: #666666;
-            -webkit-font-smoothing: antialiased;
-        }
-        .body-extra {
-            -webkit-font-smoothing: antialiased;
-        }
-        .body-extra.text-right a {
-            text-decoration: none;
-            color: #333;
-        }
-        .body-extra.text-right a:hover {
-            color: #666;
-        }
-        .button {
-            width: 200px;
-            height: 50px;
-            margin-top: 20px;
-            text-align: center;
-            border-radius: 2px;
-            background: #2D77EE;
-            line-height: 50px;
-            font-size: 20px;
-            color: #FFFFFF;
-            cursor: pointer;
-        }
-        .button:hover {
-            background: rgb(25, 115, 255);
-            border-color: rgb(25, 115, 255);
-            color: #fff;
-        }
-        footer {
-            margin-top: 10px;
-            text-align: right;
-        }
-        .footer-logo {
-            text-align: right;
-        }
-        .footer-logo-image {
-            width: 108px;
-            height: 27px;
-            margin-right: 10px;
-        }
-        .copyright {
-            margin-top: 10px;
-            font-size: 12px;
-            text-align: right;
-            color: #999;
-            -webkit-font-smoothing: antialiased;
-        }
-    </style>
-</head>
-<body>
-<div class="wrapper">
-    <div class="main">
-        <header>
-            <h3 class="title">{{.RuleName}}</h3>
-            <p class="sub-desc"></p>
-        </header>
-
-        <hr>
-
-        <div class="body">
-            <table cellspacing="0" cellpadding="0" border="0">
-                <tbody>
-                {{if .IsRecovered}}
-                <tr class="succ">
-                    <th>级别状态：</th>
-                    <td>S{{.Severity}} Recovered</td>
-                </tr>
-                {{else}}
-                <tr class="fail">
-                    <th>级别状态：</th>
-                    <td>S{{.Severity}} Triggered</td>
-                </tr>
-                {{end}}
-
-                <tr>
-                    <th>策略备注：</th>
-                    <td>{{.RuleNote}}</td>
-                </tr>
-                <tr>
-                    <th>设备备注：</th>
-                    <td>{{.TargetNote}}</td>
-                </tr>
-                {{if not .IsRecovered}}
-                <tr>
-                    <th>触发时值：</th>
-                    <td>{{.TriggerValue}}</td>
-                </tr>
-                {{end}}
-
-                {{if .TargetIdent}}
-                <tr>
-                    <th>监控对象：</th>
-                    <td>{{.TargetIdent}}</td>
-                </tr>
-                {{end}}
-                <tr>
-                    <th>监控指标：</th>
-                    <td>{{.TagsJSON}}</td>
-                </tr>
-
-                {{if .IsRecovered}}
-                <tr>
-                    <th>恢复时间：</th>
-                    <td>{{timeformat .LastEvalTime}}</td>
-                </tr>
-                {{else}}
-                <tr>
-                    <th>触发时间：</th>
-                    <td>
-                        {{timeformat .TriggerTime}}
-                    </td>
-                </tr>
-                {{end}}
-
-                <tr>
-                    <th>发送时间：</th>
-                    <td>
-                        {{timestamp}}
-                    </td>
-                </tr>
-                </tbody>
-            </table>
-
-            <hr>
-
-            <footer>
-                <div class="copyright" style="font-style: italic">
-                    我们希望与您一起，将监控这个事情，做到极致！
-                </div>
-            </footer>
-        </div>
-    </div>
-</div>
-</body>
-</html>

etc/template/feishu.tpl

@@ -1,7 +0,0 @@
-级别状态: S{{.Severity}} {{if .IsRecovered}}Recovered{{else}}Triggered{{end}}
-规则名称: {{.RuleName}}{{if .RuleNote}}
-规则备注: {{.RuleNote}}{{end}}
-监控指标: {{.TagsJSON}}
-{{if .IsRecovered}}恢复时间：{{timeformat .LastEvalTime}}{{else}}触发时间: {{timeformat .TriggerTime}}
-触发时值: {{.TriggerValue}}{{end}}
-发送时间: {{timestamp}}

etc/template/mailsubject.tpl

@@ -1 +0,0 @@
-{{if .IsRecovered}}Recovered{{else}}Triggered{{end}}: {{.RuleName}} {{.TagsJSON}}

etc/template/mm.tpl

@@ -1,7 +0,0 @@
-级别状态: S{{.Severity}} {{if .IsRecovered}}Recovered{{else}}Triggered{{end}}
-规则名称: {{.RuleName}}{{if .RuleNote}}
-规则备注: {{.RuleNote}}{{end}}
-监控指标: {{.TagsJSON}}
-{{if .IsRecovered}}恢复时间：{{timeformat .LastEvalTime}}{{else}}触发时间: {{timeformat .TriggerTime}}
-触发时值: {{.TriggerValue}}{{end}}
-发送时间: {{timestamp}}

etc/template/telegram.tpl

@@ -1,9 +0,0 @@
-**级别状态**: {{if .IsRecovered}}<font color="info">S{{.Severity}} Recovered</font>{{else}}<font color="warning">S{{.Severity}} Triggered</font>{{end}}
-**规则标题**: {{.RuleName}}{{if .RuleNote}}
-**规则备注**: {{.RuleNote}}{{end}}{{if .TargetIdent}}
-**监控对象**: {{.TargetIdent}}{{end}}
-**监控指标**: {{.TagsJSON}}{{if not .IsRecovered}}
-**触发时值**: {{.TriggerValue}}{{end}}
-{{if .IsRecovered}}**恢复时间**: {{timeformat .LastEvalTime}}{{else}}**首次触发时间**: {{timeformat .FirstTriggerTime}}{{end}}
-{{$time_duration := sub now.Unix .FirstTriggerTime }}{{if .IsRecovered}}{{$time_duration = sub .LastEvalTime .FirstTriggerTime }}{{end}}**持续时长**: {{humanizeDurationInterface $time_duration}}
-**发送时间**: {{timestamp}}

etc/template/wecom.tpl

@@ -1,9 +0,0 @@
-**级别状态**: {{if .IsRecovered}}<font color="info">S{{.Severity}} Recovered</font>{{else}}<font color="warning">S{{.Severity}} Triggered</font>{{end}}
-**规则标题**: {{.RuleName}}{{if .RuleNote}}
-**规则备注**: {{.RuleNote}}{{end}}{{if .TargetIdent}}
-**监控对象**: {{.TargetIdent}}{{end}}
-**监控指标**: {{.TagsJSON}}{{if not .IsRecovered}}
-**触发时值**: {{.TriggerValue}}{{end}}
-{{if .IsRecovered}}**恢复时间**: {{timeformat .LastEvalTime}}{{else}}**首次触发时间**: {{timeformat .FirstTriggerTime}}{{end}}
-{{$time_duration := sub now.Unix .FirstTriggerTime }}{{if .IsRecovered}}{{$time_duration = sub .LastEvalTime .FirstTriggerTime }}{{end}}**持续时长**: {{humanizeDurationInterface $time_duration}}
-**发送时间**: {{timestamp}}

fe.sh

@@ -1,17 +1,26 @@
 #!/bin/bash
 
-TAG=$(curl -sX GET https://api.github.com/repos/n9e/fe/releases/latest   | awk '/tag_name/{print $4;exit}' FS='[""]')
-VERSION=$(echo $TAG)
+cp -f ./docker/initsql/a-n9e.sql n9e.sql
 
-curl -o n9e-fe-${VERSION}.tar.gz -L https://github.com/n9e/fe/releases/download/${TAG}/n9e-fe-${VERSION}.tar.gz  
+if [ ! -d "./pub" ]; then
+    TAG=$(curl -sX GET https://api.github.com/repos/n9e/fe/releases/latest   | awk '/tag_name/{print $4;exit}' FS='[""]')
 
-tar zxvf n9e-fe-${VERSION}.tar.gz
+    if ! curl -o n9e-fe-${TAG}.tar.gz -L https://github.com/n9e/fe/releases/download/${TAG}/n9e-fe-${TAG}.tar.gz; then
+        echo "failed to download n9e-fe-${TAG}.tar.gz!"
+        exit 1
+    fi
 
-cp ./docker/initsql/a-n9e.sql n9e.sql
+    if ! tar zxf n9e-fe-${TAG}.tar.gz; then
+        echo "failed to untar n9e-fe-${TAG}.tar.gz!"
+        exit 2
+    fi
+fi
 
-# Embed files into a Go executable
-statik -src=./pub -dest=./front
+GOPATH=$(go env GOPATH)
+GOPATH=${GOPATH:-/home/runner/go}
 
-# rm the fe file
-rm n9e-fe-${VERSION}.tar.gz
-rm -r ./pub
+# Embed files into a go binary
+if ! $GOPATH/bin/statik -src=./pub -dest=./front; then
+    echo "failed to embed files into a go binary!"
+    exit 4
+fi

go.mod

@@ -7,18 +7,20 @@ require (
 	github.com/coreos/go-oidc v2.2.1+incompatible
 	github.com/dgrijalva/jwt-go v3.2.0+incompatible
 	github.com/gin-contrib/pprof v1.4.0
-	github.com/gin-gonic/gin v1.9.0
+	github.com/gin-gonic/gin v1.9.1
 	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
 	github.com/golang/protobuf v1.5.2
 	github.com/golang/snappy v0.0.4
 	github.com/google/uuid v1.3.0
+	github.com/hashicorp/go-version v1.6.0
 	github.com/json-iterator/go v1.1.12
 	github.com/koding/multiconfig v0.0.0-20171124222453-69c27309b2d7
 	github.com/mailru/easyjson v0.7.7
-	github.com/mattn/go-isatty v0.0.17
-	github.com/pelletier/go-toml/v2 v2.0.6
+	github.com/mattn/go-isatty v0.0.19
+	github.com/mojocn/base64Captcha v1.3.5
+	github.com/pelletier/go-toml/v2 v2.0.8
 	github.com/pkg/errors v0.9.1
 	github.com/prometheus/client_golang v1.14.0
 	github.com/prometheus/common v0.39.0
@@ -27,7 +29,7 @@ require (
 	github.com/redis/go-redis/v9 v9.0.2
 	github.com/tidwall/gjson v1.14.0
 	github.com/toolkits/pkg v1.3.3
-	golang.org/x/oauth2 v0.3.0
+	golang.org/x/oauth2 v0.4.0
 	gopkg.in/gomail.v2 v2.0.0-20160411212932-81ebce5c23df
 	gorm.io/driver/mysql v1.4.4
 	gorm.io/driver/postgres v1.4.5
@@ -37,19 +39,21 @@ require (
 require (
 	github.com/Azure/go-ntlmssp v0.0.0-20220621081337-cb9428e4ac1e // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
-	github.com/bytedance/sonic v1.8.0 // indirect
+	github.com/bytedance/sonic v1.9.1 // indirect
 	github.com/cespare/xxhash/v2 v2.2.0 // indirect
 	github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/fatih/camelcase v1.0.0 // indirect
 	github.com/fatih/structs v1.1.0 // indirect
+	github.com/gabriel-vasile/mimetype v1.4.2 // indirect
 	github.com/gin-contrib/sse v0.1.0 // indirect
 	github.com/go-asn1-ber/asn1-ber v1.5.4 // indirect
 	github.com/go-playground/locales v0.14.1 // indirect
 	github.com/go-playground/universal-translator v0.18.1 // indirect
-	github.com/go-playground/validator/v10 v10.11.2 // indirect
+	github.com/go-playground/validator/v10 v10.14.0 // indirect
 	github.com/go-sql-driver/mysql v1.6.0 // indirect
-	github.com/goccy/go-json v0.10.0 // indirect
+	github.com/goccy/go-json v0.10.2 // indirect
+	github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0 // indirect
 	github.com/grpc-ecosystem/grpc-gateway v1.16.0 // indirect
 	github.com/jackc/chunkreader/v2 v2.0.1 // indirect
 	github.com/jackc/pgconn v1.13.0 // indirect
@@ -62,8 +66,8 @@ require (
 	github.com/jinzhu/inflection v1.0.0 // indirect
 	github.com/jinzhu/now v1.1.5 // indirect
 	github.com/josharian/intern v1.0.0 // indirect
-	github.com/klauspost/cpuid/v2 v2.0.9 // indirect
-	github.com/leodido/go-urn v1.2.1 // indirect
+	github.com/klauspost/cpuid/v2 v2.2.4 // indirect
+	github.com/leodido/go-urn v1.2.4 // indirect
 	github.com/matttproud/golang_protobuf_extensions v1.0.4 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
@@ -74,17 +78,18 @@ require (
 	github.com/tidwall/match v1.1.1 // indirect
 	github.com/tidwall/pretty v1.2.0 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
-	github.com/ugorji/go/codec v1.2.9 // indirect
+	github.com/ugorji/go/codec v1.2.11 // indirect
 	go.uber.org/automaxprocs v1.4.0 // indirect
-	golang.org/x/arch v0.0.0-20210923205945-b76863e36670 // indirect
-	golang.org/x/crypto v0.5.0 // indirect
-	golang.org/x/net v0.7.0 // indirect
-	golang.org/x/sys v0.5.0 // indirect
-	golang.org/x/text v0.7.0 // indirect
+	golang.org/x/arch v0.3.0 // indirect
+	golang.org/x/crypto v0.9.0 // indirect
+	golang.org/x/image v0.5.0 // indirect
+	golang.org/x/net v0.10.0 // indirect
+	golang.org/x/sys v0.8.0 // indirect
+	golang.org/x/text v0.9.0 // indirect
 	google.golang.org/appengine v1.6.7 // indirect
-	google.golang.org/genproto v0.0.0-20221227171554-f9683d7f8bef // indirect
-	google.golang.org/grpc v1.51.0 // indirect
-	google.golang.org/protobuf v1.28.1 // indirect
+	google.golang.org/genproto v0.0.0-20230110181048-76db0878b65f // indirect
+	google.golang.org/grpc v1.53.0 // indirect
+	google.golang.org/protobuf v1.30.0 // indirect
 	gopkg.in/alexcesaro/quotedprintable.v3 v3.0.0-20150716171945-2caba252f4dc // indirect
 	gopkg.in/square/go-jose.v2 v2.6.0 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect

go.sum

@@ -12,8 +12,8 @@ github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6r
 github.com/bsm/ginkgo/v2 v2.5.0 h1:aOAnND1T40wEdAtkGSkvSICWeQ8L3UASX7YVCqQx+eQ=
 github.com/bsm/gomega v1.20.0 h1:JhAwLmtRzXFTx2AkALSLa8ijZafntmhSoU63Ok18Uq8=
 github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=
-github.com/bytedance/sonic v1.8.0 h1:ea0Xadu+sHlu7x5O3gKhRpQ1IKiMrSiHttPF0ybECuA=
-github.com/bytedance/sonic v1.8.0/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZXU064P/U=
+github.com/bytedance/sonic v1.9.1 h1:6iJ6NqdoxCDr6mbY8h18oSO+cShGSMRGCEo7F2h0x8s=
+github.com/bytedance/sonic v1.9.1/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZXU064P/U=
 github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
 github.com/cespare/xxhash/v2 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj44=
 github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
@@ -45,6 +45,8 @@ github.com/fatih/camelcase v1.0.0 h1:hxNvNX/xYBp0ovncs8WyWZrOrpBNub/JfaMvbURyft8
 github.com/fatih/camelcase v1.0.0/go.mod h1:yN2Sb0lFhZJUdVvtELVWefmrXpuZESvPmqwoZc+/fpc=
 github.com/fatih/structs v1.1.0 h1:Q7juDM0QtcnhCpeyLGQKyg4TOIghuNXrkL32pHAUMxo=
 github.com/fatih/structs v1.1.0/go.mod h1:9NiDSp5zOcgEDl+j00MP/WkGVPOlPRLejGD8Ga6PJ7M=
+github.com/gabriel-vasile/mimetype v1.4.2 h1:w5qFW6JKBz9Y393Y4q372O9A7cUSequkh1Q7OhCmWKU=
+github.com/gabriel-vasile/mimetype v1.4.2/go.mod h1:zApsH/mKG4w07erKIaJPFiX0Tsq9BFQgN3qGY5GnNgA=
 github.com/garyburd/redigo v1.6.2/go.mod h1:NR3MbYisc3/PwhQ00EMzDiPmrwpPxAn5GI05/YaO1SY=
 github.com/ghodss/yaml v1.0.0/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04=
 github.com/gin-contrib/pprof v1.4.0 h1:XxiBSf5jWZ5i16lNOPbMTVdgHBdhfGRD5PZ1LWazzvg=
@@ -53,8 +55,8 @@ github.com/gin-contrib/sse v0.1.0 h1:Y/yl/+YNO8GZSjAhjMsSuLt29uWRFHdHYUb5lYOV9qE
 github.com/gin-contrib/sse v0.1.0/go.mod h1:RHrZQHXnP2xjPF+u1gW/2HnVO7nvIa9PG3Gm+fLHvGI=
 github.com/gin-gonic/gin v1.7.7/go.mod h1:axIBovoeJpVj8S3BwE0uPMTeReE4+AfFtqpqaZ1qq1U=
 github.com/gin-gonic/gin v1.8.1/go.mod h1:ji8BvRH1azfM+SYow9zQ6SZMvR8qOMZHmsCuWR9tTTk=
-github.com/gin-gonic/gin v1.9.0 h1:OjyFBKICoexlu99ctXNR2gg+c5pKrKMuyjgARg9qeY8=
-github.com/gin-gonic/gin v1.9.0/go.mod h1:W1Me9+hsUSyj3CePGrd1/QrKJMSJ1Tu/0hFEH89961k=
+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/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=
@@ -73,20 +75,22 @@ github.com/go-playground/universal-translator v0.18.1 h1:Bcnm0ZwsGyWbCzImXv+pAJn
 github.com/go-playground/universal-translator v0.18.1/go.mod h1:xekY+UJKNuX9WP91TpwSH2VMlDf28Uj24BCp08ZFTUY=
 github.com/go-playground/validator/v10 v10.4.1/go.mod h1:nlOn6nFhuKACm19sB/8EGNn9GlaMV7XkbRSipzJ0Ii4=
 github.com/go-playground/validator/v10 v10.10.0/go.mod h1:74x4gJWsvQexRdW8Pn3dXSGrTK4nAUsbPlLADvpJkos=
-github.com/go-playground/validator/v10 v10.11.2 h1:q3SHpufmypg+erIExEKUmsgmhDTyhcJ38oeKGACXohU=
-github.com/go-playground/validator/v10 v10.11.2/go.mod h1:NieE624vt4SCTJtD87arVLvdmjPAeV8BQlHtMnw9D7s=
+github.com/go-playground/validator/v10 v10.14.0 h1:vgvQWe3XCz3gIeFDm/HnTIbj6UGmg/+t63MyGU2n5js=
+github.com/go-playground/validator/v10 v10.14.0/go.mod h1:9iXMNT7sEkjXb0I+enO7QXmzG6QCsPWY4zveKFVRSyU=
 github.com/go-sql-driver/mysql v1.6.0 h1:BCTh4TKNUYmOmMUcQ3IipzF5prigylS7XXjEkfCHuOE=
 github.com/go-sql-driver/mysql v1.6.0/go.mod h1:DCzpHaOWr8IXmIStZouvnhqoel9Qv2LBy8hT2VhHyBg=
 github.com/go-stack/stack v1.8.0/go.mod h1:v0f6uXyyMGvRgIKkXu+yp6POWl0qKG85gN/melR3HDY=
 github.com/goccy/go-json v0.9.7/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
-github.com/goccy/go-json v0.10.0 h1:mXKd9Qw4NuzShiRlOXKews24ufknHO7gx30lsDyokKA=
-github.com/goccy/go-json v0.10.0/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
+github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
+github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
 github.com/gofrs/uuid v4.0.0+incompatible h1:1SD/1F5pU8p29ybwgQSwpQk+mwdRrXCYuPhW6m+TnJw=
 github.com/gofrs/uuid v4.0.0+incompatible/go.mod h1:b2aQJv3Z4Fp6yNu3cdSllBxTCLRxnplIgP/c0N/04lM=
 github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
 github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q=
 github.com/golang-jwt/jwt v3.2.2+incompatible h1:IfV12K8xAKAnZqdXVzCZ+TOjboZ2keLg81eXfW3O+oY=
 github.com/golang-jwt/jwt v3.2.2+incompatible/go.mod h1:8pz2t5EyA70fFQQSrl6XZXzqecmYZeUEB8OUGHkxJ+I=
+github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0 h1:DACJavvAHhabrF08vX0COfcOBJRhZ8lUbR+ZWIs0Y5g=
+github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0/go.mod h1:E/TSTwGwJL78qG/PmXZO1EjYhfJinVAhrmmHX6Z8B9k=
 github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q=
 github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
 github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
@@ -102,7 +106,7 @@ github.com/golang/snappy v0.0.4/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEW
 github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M=
 github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
-github.com/google/go-cmp v0.5.8 h1:e6P7q2lk1O+qJJb4BtCQXlK8vWEO8V1ZeuEdJNOqZyg=
+github.com/google/go-cmp v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/renameio v0.1.0/go.mod h1:KWCgfxg9yswjAJkECMjeO8J8rahYeXnNhOm40UhjYkI=
 github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
@@ -110,6 +114,8 @@ github.com/google/uuid v1.3.0 h1:t6JiXgmwXMjEs8VusXIJk2BXHsn+wx8BZdTaoZ5fu7I=
 github.com/google/uuid v1.3.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/grpc-ecosystem/grpc-gateway v1.16.0 h1:gmcG1KaJ57LophUzW0Hy8NmPhnMZb4M0+kPpLofRdBo=
 github.com/grpc-ecosystem/grpc-gateway v1.16.0/go.mod h1:BDjrQk3hbvj6Nolgz8mAMFbcEtjT1g+wF4CSlocrBnw=
+github.com/hashicorp/go-version v1.6.0 h1:feTTfFNnjP967rlCxM/I9g701jU+RN74YKx2mOkIeek=
+github.com/hashicorp/go-version v1.6.0/go.mod h1:fltr4n8CU8Ke44wwGCBoEymUuxUHl09ZGVZPK5anwXA=
 github.com/jackc/chunkreader v1.0.0/go.mod h1:RT6O25fNZIuasFJRyZ4R/Y2BbhasbmZXF9QQ7T3kePo=
 github.com/jackc/chunkreader/v2 v2.0.0/go.mod h1:odVSm741yZoC3dpHEUXIqA9tQRhFrgOHwnPIn9lDKlk=
 github.com/jackc/chunkreader/v2 v2.0.1 h1:i+RDz65UE+mmpjTfyz0MoVTnzeYxroil2G82ki7MGG8=
@@ -169,8 +175,9 @@ github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnr
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
 github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8=
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
-github.com/klauspost/cpuid/v2 v2.0.9 h1:lgaqFMSdTdQYdZ04uHyN2d/eKdOMyi2YLSvlQIBFYa4=
 github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
+github.com/klauspost/cpuid/v2 v2.2.4 h1:acbojRNwl3o09bUq+yDCtZFc1aiwaAAxtcn8YkZXnvk=
+github.com/klauspost/cpuid/v2 v2.2.4/go.mod h1:RVVoqg1df56z8g3pUjL/3lE5UfnlrJX8tyFgg4nqhuY=
 github.com/koding/multiconfig v0.0.0-20171124222453-69c27309b2d7 h1:SWlt7BoQNASbhTUD0Oy5yysI2seJ7vWuGUp///OM4TM=
 github.com/koding/multiconfig v0.0.0-20171124222453-69c27309b2d7/go.mod h1:Y2SaZf2Rzd0pXkLVhLlCiAXFCLSXAIbTKDivVgff/AM=
 github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
@@ -185,8 +192,9 @@ github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/leodido/go-urn v1.2.0/go.mod h1:+8+nEpDfqqsY+g338gtMEUOtuK+4dEMhiQEgxpxOKII=
-github.com/leodido/go-urn v1.2.1 h1:BqpAaACuzVSgi/VLzGZIobT2z4v53pjosyNd9Yv6n/w=
 github.com/leodido/go-urn v1.2.1/go.mod h1:zt4jvISO2HfUBqxjfIshjdMTYS56ZS/qv49ictyFfxY=
+github.com/leodido/go-urn v1.2.4 h1:XlAE/cm/ms7TE/VMVoduSpNBoyc2dOxHs5MZSwAN63Q=
+github.com/leodido/go-urn v1.2.4/go.mod h1:7ZrI8mTSeBSHl/UaRyKQW1qZeMgak41ANeCNaVckg+4=
 github.com/lib/pq v1.0.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
 github.com/lib/pq v1.1.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
 github.com/lib/pq v1.2.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
@@ -200,8 +208,8 @@ github.com/mattn/go-isatty v0.0.5/go.mod h1:Iq45c/XA43vh69/j3iqttzPXn0bhXyGjM0Hd
 github.com/mattn/go-isatty v0.0.7/go.mod h1:Iq45c/XA43vh69/j3iqttzPXn0bhXyGjM0Hdxcsrc5s=
 github.com/mattn/go-isatty v0.0.12/go.mod h1:cbi8OIDigv2wuxKPP5vlRcQ1OAZbq2CE4Kysco4FUpU=
 github.com/mattn/go-isatty v0.0.14/go.mod h1:7GGIvUiUoEMVVmxf/4nioHXj79iQHKdU27kJ6hsGG94=
-github.com/mattn/go-isatty v0.0.17 h1:BTarxUcIeDqL27Mc+vyvdWYSL28zpIhv3RoTdsLMPng=
-github.com/mattn/go-isatty v0.0.17/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
+github.com/mattn/go-isatty v0.0.19 h1:JITubQf0MOLdlGRuRq+jtsDlekdYPia9ZFsB8h/APPA=
+github.com/mattn/go-isatty v0.0.19/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
 github.com/matttproud/golang_protobuf_extensions v1.0.4 h1:mmDVorXM7PCGKw94cs5zkfA9PSy5pEvNWRP0ET0TIVo=
 github.com/matttproud/golang_protobuf_extensions v1.0.4/go.mod h1:BSXmuO+STAnVfrANrmjBb36TMTDstsz7MSK+HVaYKv4=
 github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
@@ -210,9 +218,11 @@ github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJ
 github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
 github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
 github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
+github.com/mojocn/base64Captcha v1.3.5 h1:Qeilr7Ta6eDtG4S+tQuZ5+hO+QHbiGAJdi4PfoagaA0=
+github.com/mojocn/base64Captcha v1.3.5/go.mod h1:/tTTXn4WTpX9CfrmipqRytCpJ27Uw3G6I7NcP2WwcmY=
 github.com/pelletier/go-toml/v2 v2.0.1/go.mod h1:r9LEWfGN8R5k0VXJ+0BkIe7MYkRdwZOjgMj2KwnJFUo=
-github.com/pelletier/go-toml/v2 v2.0.6 h1:nrzqCb7j9cDFj2coyLNLaZuJTLjWjlaz6nvTvIwycIU=
-github.com/pelletier/go-toml/v2 v2.0.6/go.mod h1:eumQOmlWiOPt5WriQQqoM5y18pDHwha2N+QD+EUNTek=
+github.com/pelletier/go-toml/v2 v2.0.8 h1:0ctb6s9mE31h0/lhu+J6OPmVeDxJn+kYnJc2jZR9tGQ=
+github.com/pelletier/go-toml/v2 v2.0.8/go.mod h1:vuYfssBdrU2XDZ9bYydBu6t+6a6PYNcZljzZR9VXg+4=
 github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
 github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
@@ -267,8 +277,10 @@ github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/
 github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.7.2/go.mod h1:R6va5+xMeoiuVRoj+gSkQ7d3FALtqAAGI1FQKckRals=
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
-github.com/stretchr/testify v1.8.1 h1:w7B6lhMri9wdJUVmEZPGGhZzrYTPvgJArz7wNPgYKsk=
 github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
+github.com/stretchr/testify v1.8.2/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
+github.com/stretchr/testify v1.8.3 h1:RP3t2pwF7cMEbC1dqtB6poj3niw/9gnV4Cjg5oW5gtY=
+github.com/stretchr/testify v1.8.3/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 github.com/tidwall/gjson v1.14.0 h1:6aeJ0bzojgWLa82gDQHcx3S0Lr/O51I9bJ5nv6JFx5w=
 github.com/tidwall/gjson v1.14.0/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
 github.com/tidwall/match v1.1.1 h1:+Ho715JplO36QYgwN9PGYNhgZvoUSc9X2c80KVTi+GA=
@@ -283,8 +295,8 @@ github.com/ugorji/go v1.1.7/go.mod h1:kZn38zHttfInRq0xu/PH0az30d+z6vm202qpg1oXVM
 github.com/ugorji/go v1.2.7/go.mod h1:nF9osbDWLy6bDVv/Rtoh6QgnvNDpmCalQV5urGCCS6M=
 github.com/ugorji/go/codec v1.1.7/go.mod h1:Ax+UKWsSmolVDwsd+7N3ZtXu+yMGCf907BLYF3GoBXY=
 github.com/ugorji/go/codec v1.2.7/go.mod h1:WGN1fab3R1fzQlVQTkfxVtIBhWDRqOviHU95kRgeqEY=
-github.com/ugorji/go/codec v1.2.9 h1:rmenucSohSTiyL09Y+l2OCk+FrMxGMzho2+tjr5ticU=
-github.com/ugorji/go/codec v1.2.9/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
+github.com/ugorji/go/codec v1.2.11 h1:BMaWp1Bb6fHwEtbplGBGJ498wD+LKlNSl25MjdZY4dU=
+github.com/ugorji/go/codec v1.2.11/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
 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=
@@ -302,8 +314,9 @@ go.uber.org/tools v0.0.0-20190618225709-2cfd321de3ee/go.mod h1:vJERXedbb3MVM5f9E
 go.uber.org/zap v1.9.1/go.mod h1:vwi/ZaCAaUcBkycHslxD9B2zi4UTXhF60s6SWpuDF0Q=
 go.uber.org/zap v1.10.0/go.mod h1:vwi/ZaCAaUcBkycHslxD9B2zi4UTXhF60s6SWpuDF0Q=
 go.uber.org/zap v1.13.0/go.mod h1:zwrFLgMcdUuIBviXEYEH1YKNaOBnKXsx2IPda5bBwHM=
-golang.org/x/arch v0.0.0-20210923205945-b76863e36670 h1:18EFjUmQOcUvxNYSkA6jO9VAiXCnxFY6NyDX0bHDmkU=
 golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
+golang.org/x/arch v0.3.0 h1:02VY4/ZcO/gBOH6PUaoiptASxtXU10jazRCP865E97k=
+golang.org/x/arch v0.3.0/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20190411191339-88737f569e3a/go.mod h1:WFFai1msRO1wXaEeE5yQxYXgSfI8pQAWXbQop6sCtWE=
 golang.org/x/crypto v0.0.0-20190510104115-cbcb75029529/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
@@ -316,9 +329,12 @@ golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5y
 golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.0.0-20220622213112-05595931fe9d/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
 golang.org/x/crypto v0.0.0-20220722155217-630584e8d5aa/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
-golang.org/x/crypto v0.5.0 h1:U/0M97KRkSFvyD/3FSmdP5W5swImpNgle/EHFhOsQPE=
-golang.org/x/crypto v0.5.0/go.mod h1:NK/OQwhpMQP3MwtdjgLlYHnH9ebylxKWv3e0fK+mkQU=
+golang.org/x/crypto v0.9.0 h1:LF6fAI+IutBocDJ2OT0Q1g8plpYljMZ4+lty+dsqw3g=
+golang.org/x/crypto v0.9.0/go.mod h1:yrmDGqONDYtNj3tH8X9dzUun2m2lzPa9ngI6/RUPGR0=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
+golang.org/x/image v0.0.0-20190501045829-6d32002ffd75/go.mod h1:kZ7UVZpmo3dzQBMxlp+ypCbDeSB+sBbTgSJuh5dn5js=
+golang.org/x/image v0.5.0 h1:5JMiNunQeQw++mMOz48/ISeNu3Iweh/JaZU8ZLqHRrI=
+golang.org/x/image v0.5.0/go.mod h1:FVC7BI/5Ym8R25iw5OLsgshdUBbT1h5jZTpA+mvAdZ4=
 golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
 golang.org/x/lint v0.0.0-20190227174305-5b3e6a55c961/go.mod h1:wehouNa3lNwaWXcvxsM5YxQ5yQlVC4a0KAMCusXpPoU=
 golang.org/x/lint v0.0.0-20190313153728-d0100b6bd8b3/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
@@ -343,12 +359,12 @@ golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwY
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
-golang.org/x/net v0.7.0 h1:rJrUqqhjsgNp7KqAIc25s9pZnjU7TUcSY7HcVZjdn1g=
-golang.org/x/net v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
+golang.org/x/net v0.10.0 h1:X2//UzNDwYmtCLn7To6G58Wr6f5ahEAQgKNzv9Y951M=
+golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20200107190931-bf48bf16ab8d/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
-golang.org/x/oauth2 v0.3.0 h1:6l90koy8/LaBLmLu8jpHeHexzMwEita0zFfYlggy2F8=
-golang.org/x/oauth2 v0.3.0/go.mod h1:rQrIauxkUhJ6CuwEXwymO2/eh4xz2ZWF1nBkcxS+tGk=
+golang.org/x/oauth2 v0.4.0 h1:NF0gk8LVPg1Ml7SSbGyySuoxdsXitj7TvgvuRxIMc/M=
+golang.org/x/oauth2 v0.4.0/go.mod h1:RznEsdpjGAINPTOF0UH/t+xJ75L18YO3Ho6Pyn+uRec=
 golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
@@ -375,10 +391,11 @@ golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210806184541-e5e7981a1069/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220704084225-05e143d24a9e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.5.0 h1:MUK/U/4lj1t1oPg0HfuXDN/Z1wv31ZJ/YcPiGccS4DU=
-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 h1:EBmGv8NaZBZTWvrbjNoL6HVt+IVy3QDQpJs7VRIw3tU=
+golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 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=
@@ -389,8 +406,9 @@ golang.org/x/text v0.3.4/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
 golang.org/x/text v0.3.8/go.mod h1:E6s5w1FMmriuDzIBO73fBruAKo1PCIq6d2Q6DHfQ8WQ=
-golang.org/x/text v0.7.0 h1:4BRB4x83lYWy72KwLD/qYDuTu7q9PjSagHvijDw7cLo=
 golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
+golang.org/x/text v0.9.0 h1:2sjJmO8cDvYveuX97RDLsxlyUxLl+GHoLxBiRdHllBE=
+golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
@@ -419,20 +437,20 @@ google.golang.org/appengine v1.6.7/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCID
 google.golang.org/genproto v0.0.0-20180817151627-c66870c02cf8/go.mod h1:JiN7NxoALGmiZfu7CAH4rXhgtRTLTxftemlI0sWmxmc=
 google.golang.org/genproto v0.0.0-20190819201941-24fa4b261c55/go.mod h1:DMBHOl98Agz4BDEuKkezgsaosCRResVns1a3J2ZsMNc=
 google.golang.org/genproto v0.0.0-20200513103714-09dca8ec2884/go.mod h1:55QSHmfGQM9UVYDPBsyGGes0y52j32PQ3BqQfXhyH3c=
-google.golang.org/genproto v0.0.0-20221227171554-f9683d7f8bef h1:uQ2vjV/sHTsWSqdKeLqmwitzgvjMl7o4IdtHwUDXSJY=
-google.golang.org/genproto v0.0.0-20221227171554-f9683d7f8bef/go.mod h1:RGgjbofJ8xD9Sq1VVhDM1Vok1vRONV+rg+CjzG4SZKM=
+google.golang.org/genproto v0.0.0-20230110181048-76db0878b65f h1:BWUVssLB0HVOSY78gIdvk1dTVYtT1y8SBWtPYuTJ/6w=
+google.golang.org/genproto v0.0.0-20230110181048-76db0878b65f/go.mod h1:RGgjbofJ8xD9Sq1VVhDM1Vok1vRONV+rg+CjzG4SZKM=
 google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
 google.golang.org/grpc v1.23.0/go.mod h1:Y5yQAOtifL1yxbo5wqy6BxZv8vAUGQwXBOALyacEbxg=
 google.golang.org/grpc v1.25.1/go.mod h1:c3i+UQWmh7LiEpx4sFZnkU36qjEYZ0imhYfXVyQciAY=
 google.golang.org/grpc v1.27.0/go.mod h1:qbnxyOmOxrQa7FizSgH+ReBfzJrCY1pSN7KXBS8abTk=
 google.golang.org/grpc v1.33.1/go.mod h1:fr5YgcSWrqhRRxogOsw7RzIpsmvOZ6IcH4kBYTpR3n0=
-google.golang.org/grpc v1.51.0 h1:E1eGv1FTqoLIdnBCZufiSHgKjlqG6fKFf6pPWtMTh8U=
-google.golang.org/grpc v1.51.0/go.mod h1:wgNDFcnuBGmxLKI/qn4T+m5BtEBYXJPvibbUPsAIPww=
+google.golang.org/grpc v1.53.0 h1:LAv2ds7cmFV/XTS3XG1NneeENYrXGmorPxsBbptIjNc=
+google.golang.org/grpc v1.53.0/go.mod h1:OnIrk0ipVdj4N5d9IUoFUx72/VlD7+jUsHwZgwSMQpw=
 google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
 google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
 google.golang.org/protobuf v1.28.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
-google.golang.org/protobuf v1.28.1 h1:d0NfwRgPtno5B1Wa6L2DAG+KivqkdutMf1UhdNx175w=
-google.golang.org/protobuf v1.28.1/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
+google.golang.org/protobuf v1.30.0 h1:kPPoIgf3TsEvrm0PFe15JQ+570QVxYzEvvHqChK+cng=
+google.golang.org/protobuf v1.30.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
 gopkg.in/alexcesaro/quotedprintable.v3 v3.0.0-20150716171945-2caba252f4dc h1:2gGKlE2+asNV9m7xrywl36YYNnBG5ZQ0r/BOOxqPpmk=
 gopkg.in/alexcesaro/quotedprintable.v3 v3.0.0-20150716171945-2caba252f4dc/go.mod h1:m7x9LTH6d71AHyAX77c9yqWCCa3UKHcVEj9y7hAtKDk=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=

integrations/AliYun/dashboards/ecs.json

@@ -0,0 +1,313 @@
+{
+  "name": "阿里云ECS",
+  "tags": "",
+  "ident": "",
+  "configs": {
+    "var": [
+      {
+        "name": "ident",
+        "type": "query",
+        "datasource": {
+          "cate": "prometheus"
+        },
+        "definition": "label_values(aliyun_acs_ecs_dashboard_cpu_utilization_average,ident)",
+        "multi": true,
+        "allOption": true
+      }
+    ],
+    "panels": [
+      {
+        "type": "timeseries",
+        "id": "8606d5ad-c3c7-4b1d-86bf-474d3302ee17",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 0,
+          "i": "8606d5ad-c3c7-4b1d-86bf-474d3302ee17",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "datasourceName": "Default",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_ecs_dashboard_cpu_utilization_average{ident=~\"$ident\"}) by (ident,instance_id)"
+          }
+        ],
+        "name": "CPU平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "c7034fe3-5521-4867-a8bd-429767cc03a2",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 0,
+          "i": "55404296-0bd9-409d-aeaf-e9c7cceea0dd",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "datasourceName": "Default",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_ecs_dashboard_memory_usedutilization_average{ident=~\"$ident\"}) by (ident,instance_id)"
+          }
+        ],
+        "name": "内存平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "e4c11925-b359-4edb-9269-4bdd4d230224",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 4,
+          "i": "0c7b3a5a-ef12-4349-be9b-7a245bf01418",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "datasourceName": "Default",
+        "targets": [
+          {
+            "expr": "sum(aliyun_acs_ecs_dashboard_load_5m_average{ident=~\"$ident\"}) by (ident,instance_id)",
+            "refId": "B",
+            "legend": "{{ident}} {{instance_id}} 5分钟负载"
+          }
+        ],
+        "name": "系统负载[5m]",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {
+            "util": "percent"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "388d4da6-eb1f-48f1-955d-37579809dfec",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 5,
+          "i": "5abea3d2-ea82-4bdb-a4f0-4dd1316c0377",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "datasourceName": "Default",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_ecs_dashboard_diskusage_utilization_average{ident=~\"$ident\"}) by (ident,instance_id)"
+          }
+        ],
+        "name": "磁盘平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {
+            "util": "percent"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "f8d19cc9-0168-4c13-b9a9-c7980eced974",
+        "layout": {
+          "x": 0,
+          "y": 9,
+          "w": 12,
+          "h": 4,
+          "i": "f8d19cc9-0168-4c13-b9a9-c7980eced974"
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_ecs_dashboard_intranet_in_average{ident=~\"$ident\"}) by (ident,instance_id)",
+            "legend": "主机：{{ident}} 实例ID: {{instance_id}} 入流量",
+            "step": 300,
+            "time": {
+              "start": "now-5m",
+              "end": "now"
+            }
+          },
+          {
+            "expr": "sum(aliyun_acs_ecs_dashboard_intranet_out_average{ident=~\"$ident\"}) by (ident,instance_id)",
+            "refId": "B",
+            "legend": "主机：{{ident}} 实例ID: {{instance_id}} 出流量",
+            "step": 300,
+            "time": {
+              "start": "now-5m",
+              "end": "now"
+            }
+          }
+        ],
+        "name": "网络流量",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {
+            "util": "bitsSI"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      }
+    ],
+    "version": "2.0.0"
+  }
+}

integrations/AliYun/dashboards/rds.json

@@ -0,0 +1,313 @@
+{
+  "name": "阿里云RDS",
+  "tags": "",
+  "ident": "",
+  "configs": {
+    "var": [
+      {
+        "name": "instance_id",
+        "type": "query",
+        "datasource": {
+          "cate": "prometheus"
+        },
+        "definition": "label_values(aliyun_acs_rds_dashboard_cpu_usage_average,instance_id)",
+        "multi": false
+      }
+    ],
+    "panels": [
+      {
+        "type": "timeseries",
+        "id": "01f4d444-aa2d-466d-9615-c76baf60a40c",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 0,
+          "i": "01f4d444-aa2d-466d-9615-c76baf60a40c",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_rds_dashboard_cpu_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "CPU平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "c43eb882-915f-4c38-a0b5-8f33c21ab44a",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 0,
+          "i": "09903231-6557-42be-9cf3-2873878e9bf2",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_rds_dashboard_memory_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "内存平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "37447883-ad79-46bc-888a-1be2835c1c64",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 4,
+          "i": "378a5a26-c28e-4612-af09-f82ec2e11d80",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_rds_dashboard_disk_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "磁盘平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "c9735607-3f24-44a7-bbf1-3ad39441c5c9",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 4,
+          "i": "93a4c8a6-ac23-4e26-8a38-781ec1668820",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_rds_dashboard_iops_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "IOPS平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "b516e7dc-8022-409d-b907-18c4143df891",
+        "layout": {
+          "h": 5,
+          "w": 24,
+          "x": 0,
+          "y": 8,
+          "i": "b516e7dc-8022-409d-b907-18c4143df891",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_delete_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": "delete"
+          },
+          {
+            "expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_insert_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "refId": "B",
+            "legend": "insert"
+          },
+          {
+            "expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_insert_select_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "refId": "C",
+            "legend": "insert_select"
+          },
+          {
+            "expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_update_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "refId": "D",
+            "legend": "update"
+          },
+          {
+            "expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_select_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "refId": "E",
+            "legend": "select"
+          }
+        ],
+        "name": "SQL执行量",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {
+            "util": "percent"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      }
+    ],
+    "version": "2.0.0"
+  }
+}

integrations/AliYun/dashboards/redis.json

@@ -0,0 +1,298 @@
+{
+  "name": "阿里云REDIS",
+  "tags": "",
+  "ident": "",
+  "configs": {
+    "var": [
+      {
+        "name": "instance_id",
+        "type": "query",
+        "datasource": {
+          "cate": "prometheus"
+        },
+        "definition": "label_values(aliyun_acs_kvstore_cpu_usage_average,instance_id)",
+        "multi": false
+      }
+    ],
+    "panels": [
+      {
+        "type": "timeseries",
+        "id": "01f4d444-aa2d-466d-9615-c76baf60a40c",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 0,
+          "i": "01f4d444-aa2d-466d-9615-c76baf60a40c",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_kvstore_cpu_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "CPU平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "c43eb882-915f-4c38-a0b5-8f33c21ab44a",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 0,
+          "i": "09903231-6557-42be-9cf3-2873878e9bf2",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_kvstore_memory_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "内存平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "37447883-ad79-46bc-888a-1be2835c1c64",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 4,
+          "i": "378a5a26-c28e-4612-af09-f82ec2e11d80",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_kvstore_connection_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "连接数平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "c9735607-3f24-44a7-bbf1-3ad39441c5c9",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 4,
+          "i": "93a4c8a6-ac23-4e26-8a38-781ec1668820",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_kvstore_failed_count_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "失败统计平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "b516e7dc-8022-409d-b907-18c4143df891",
+        "layout": {
+          "h": 5,
+          "w": 24,
+          "x": 0,
+          "y": 8,
+          "i": "b516e7dc-8022-409d-b907-18c4143df891",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_kvstore_intranet_in_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": "in"
+          },
+          {
+            "expr": "sum(aliyun_acs_kvstore_intranet_out_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "refId": "B",
+            "legend": "out"
+          }
+        ],
+        "name": "网络流量",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {
+            "util": "bitsSI"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      }
+    ],
+    "version": "2.0.0"
+  }
+}

integrations/AliYun/dashboards/slb.json

@@ -0,0 +1,376 @@
+{
+  "name": "阿里云SLB",
+  "tags": "",
+  "ident": "",
+  "configs": {
+    "var": [
+      {
+        "name": "instance_id",
+        "type": "query",
+        "datasource": {
+          "cate": "prometheus"
+        },
+        "definition": "label_values(aliyun_acs_slb_dashboard_active_connection_average ,instance_id)",
+        "multi": true,
+        "allOption": true
+      }
+    ],
+    "panels": [
+      {
+        "type": "timeseries",
+        "id": "aa8b2623-1e14-43cd-a3c4-33944a61fcc5",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 0,
+          "i": "aa8b2623-1e14-43cd-a3c4-33944a61fcc5",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "datasourceName": "Default",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_slb_dashboard_instance_qps_utilization_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}} QPS使用率 "
+          }
+        ],
+        "name": "七层实例QPS使用率(%)",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "b2002c63-8f0b-436c-b765-5bb65191f3c2",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 0,
+          "i": "b2002c63-8f0b-436c-b765-5bb65191f3c2",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_slb_dashboard_upstream_code4xx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}} 状态码 4xx "
+          },
+          {
+            "expr": "sum(aliyun_acs_slb_dashboard_upstream_code5xx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "refId": "B",
+            "legend": "{{instance_id}} 状态码 5xx "
+          }
+        ],
+        "name": "7层协议实例Upstream状态码分布",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "71028d82-4804-468f-92f4-3444953b22cc",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 4,
+          "i": "71028d82-4804-468f-92f4-3444953b22cc",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_slb_dashboard_instance_new_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}} 新建连接数"
+          }
+        ],
+        "name": "新建连接数",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "25f90635-ff68-4dc2-bfb0-c6634f0e6867",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 4,
+          "i": "25f90635-ff68-4dc2-bfb0-c6634f0e6867",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_slb_dashboard_active_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}} 活跃连接数"
+          },
+          {
+            "expr": "sum(aliyun_acs_slb_dashboard_inactive_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "refId": "B",
+            "legend": "{{instance_id}} 非活跃连接数"
+          },
+          {
+            "expr": "sum(aliyun_acs_slb_dashboard_max_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "refId": "C",
+            "legend": "{{instance_id}} 最大活跃连接数"
+          }
+        ],
+        "name": "并发连接数",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "fde27e57-bdd6-4fd6-b3c0-75222f736d3b",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 8,
+          "i": "fde27e57-bdd6-4fd6-b3c0-75222f736d3b",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_slb_dashboard_packet_rx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}} 接受数据包数"
+          },
+          {
+            "expr": "sum(aliyun_acs_slb_dashboard_packet_tx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "refId": "B",
+            "legend": "{{instance_id}} 发送数据包数"
+          }
+        ],
+        "name": "数据包数",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {
+            "util": "none"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "a0fd47db-0b49-4b71-ae16-b4108324e35a",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 8,
+          "i": "a0fd47db-0b49-4b71-ae16-b4108324e35a",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_slb_dashboard_instance_traffic_rx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}} 出流量"
+          },
+          {
+            "expr": "sum(aliyun_acs_slb_dashboard_instance_traffic_tx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "refId": "B",
+            "legend": "{{instance_id}} 入流量"
+          }
+        ],
+        "name": "流量",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {
+            "util": "bitsSI"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      }
+    ],
+    "version": "2.0.0"
+  }
+}

integrations/AliYun/dashboards/waf.json

@@ -0,0 +1,346 @@
+{
+  "name": "阿里云WAF",
+  "tags": "",
+  "ident": "",
+  "configs": {
+    "var": [
+      {
+        "name": "instance_id",
+        "type": "query",
+        "datasource": {
+          "cate": "prometheus"
+        },
+        "definition": "label_values(aliyun_waf_qps_ratio_maximum,instance_id)",
+        "multi": true,
+        "allOption": true
+      }
+    ],
+    "panels": [
+      {
+        "type": "timeseries",
+        "id": "ec46b990-faf5-4ed7-a791-bbac5df91636",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 0,
+          "i": "ec46b990-faf5-4ed7-a791-bbac5df91636",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_waf_4xx_ratio_wafv3_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "4xx 环比率V3"
+          }
+        ],
+        "name": "4xx 环比率V3",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "efc75e62-5e75-470d-b12b-a98ca44b268a",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 0,
+          "i": "584b5a3c-2b7a-4e11-bee5-c2ed8661933e",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_waf_5xx_ratio_wafv3_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "5xx 环比率V3"
+          }
+        ],
+        "name": "5xx 环比率V3",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "79aefa1b-5e50-4c0c-980d-e5523b859509",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 4,
+          "i": "fc875397-c1a4-4713-b564-09abf852bcf3",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_waf_4xx_ratio_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "4xx 环比率"
+          }
+        ],
+        "name": "4xx 环比率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "60c211d4-d51a-4681-b23b-ec8cc5dce7fe",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 4,
+          "i": "946be0db-32a3-48ea-9473-88fdfa77201d",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_waf_5xx_ratio_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "5xx 环比率"
+          }
+        ],
+        "name": "5xx 环比率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "0de9271c-7b19-4003-ae56-2e273b4b99c4",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 8,
+          "i": "0de9271c-7b19-4003-ae56-2e273b4b99c4",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_waf_qps_ratio_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}}QPS 环比增长率"
+          }
+        ],
+        "name": "QPS环比增长率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "ccf2ffc1-6f22-4a13-b795-68072c077e1f",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 8,
+          "i": "d0320716-f704-4b6e-8671-b58fb77a5d7c",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_waf_qps_ratio_down_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}}QPS 环比下降率"
+          }
+        ],
+        "name": "QPS环比下降率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      }
+    ],
+    "version": "2.0.0"
+  }
+}

integrations/AliYun/markdown/README.md

@@ -0,0 +1,58 @@
+## AliYun Dashboard & Configurable
+
+使用[categraf](https://github.com/flashcatcloud/categraf)中[input.aliyun](https://github.com/flashcatcloud/categraf/blob/main/conf/input.aliyun/cloud.toml)插件采集Vmware指标数据:
+
+1. 在阿里云控制创建AK/SK，在IAM中赋予阿里云监控的权限；
+2. 把创建好的AK/SK配置到Categraf的阿里云插件配置文件中。
+
+### Categraf中conf/input.aliyun/cloud.toml配置文件：
+
+```toml
+# # categraf采集周期，阿里云指标的粒度一般是60秒，建议设置不要少于60秒
+interval = 60
+[[instances]]
+## 阿里云资源所处的region
+## endpoint region 参考 https://help.aliyun.com/document_detail/28616.html#section-72p-xhs-6qt
+region="cn-beijing"
+#endpoint="metrics.cn-hangzhou.aliyuncs.com"
+endpoint="metrics.aliyuncs.com"
+## 填入你的acces_key_id
+access_key_id="admin"
+## 填入你的access_key_secret
+access_key_secret="admin"
+
+## 可能无法获取当前最新指标，这个指标是指监控指标的截止时间距离现在多久
+delay="2m"
+## 阿里云指标的最小粒度，60s 是推荐值，再小了部分指标不支持
+period="60s"
+## 指标所属的namespace ,为空，则表示所有空间指标都要采集
+## namespace 参考 https://help.aliyun.com/document_detail/163515.htm?spm=a2c4g.11186623.0.0.44d65c58mhgNw3
+#namespaces=["waf"]
+namespaces=["waf","acs_ecs_dashboard","acs_rds_dashboard","acs_slb_dashboard","acs_kvstore"]
+
+# 阿里云查询指标接口的QPS是50， 这里默认设置为一半
+ratelimit=25
+# 查询指定namesapce指标后, namespace/metric_name等meta信息会缓存起来，catch_ttl 是指标的缓存时间
+catch_ttl="1h"
+# 每次请求阿里云endpoint的超时时间
+timeout="5s"
+
+## 过滤某个namespace下的一个或多个指标
+## metric name 参考 https://help.aliyun.com/document_detail/163515.htm?spm=a2c4g.11186623.0.0.401d15c73Z0dZh
+## 参考页面中的Metric Id 填入下面的metricName ,页面中包含中文的Metric Name对应接口中的Description
+#[[instances.metric_filters]]
+#namespace=""
+#metric_names=["cpu_cores","vm.TcpCount", "cpu_idle"]
+```
+
+### 效果图
+
+![ecs](./ecs.png)
+
+![rds](./rds.png)
+
+![redis](./redis.png)
+
+![slb](./slb.png)
+
+![waf](./waf.png)

integrations/RabbitMQ/alerts/alerts.json

@@ -0,0 +1,512 @@
+[
+  {
+    "cate": "",
+    "name": "[RabbitMQ] Cluster Operator Unavailable Replicas",
+    "note": "There are kube_pod_names that are either running but not yet available or kube_pod_names that still have not been created.",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 300,
+    "prom_ql": "kube_deployment_status_replicas_unavailable > 0\n",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": []
+  },
+  {
+    "cate": "",
+    "name": "[RabbitMQ] Container Restarts",
+    "note": "Over the last 10 minutes a rabbitmq container was restarted",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 300,
+    "prom_ql": "increase(kube__container_status_restarts_total[10m]) >= 1\n",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": []
+  },
+  {
+    "cate": "",
+    "name": "[RabbitMQ] File Descriptors Near Limit",
+    "note": "The file descriptors are near to the limit",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 600,
+    "prom_ql": "sum (max_over_time(rabbitmq_process_open_fds[5m]))/sum (rabbitmq_process_max_tcp_sockets)> 0.8\n",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": []
+  },
+  {
+    "cate": "",
+    "name": "[RabbitMQ] High Connection Churn",
+    "note": "There are a high connection churn",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 600,
+    "prom_ql": "( sum(rate(rabbitmq_connections_closed_total[5m]) )  + sum(rate(rabbitmq_connections_opened_total[5m]) ) )/sum (rabbitmq_connections) > 0.1 unless sum (rabbitmq_connections) < 100\n",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": []
+  },
+  {
+    "cate": "",
+    "name": "[RabbitMQ] Insufficient Established Erlang Distribution Links",
+    "note": "Insuffient establised erland distribution links",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 600,
+    "prom_ql": "count (erlang_vm_dist_node_state) == 3< count (rabbitmq_build_info ) *(count (rabbitmq_build_info - 1 ))\n",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": []
+  },
+  {
+    "cate": "",
+    "name": "[RabbitMQ] Low Disk Watermark Predicted",
+    "note": "The predicted free disk space in 24 hours from now is low",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 3600,
+    "prom_ql": "( predict_linear(rabbitmq_disk_space_available_bytes[24h], 60*60*24) < rabbitmq_disk_space_available_limit_bytes )and( count_over_time(rabbitmq_disk_space_available_limit_bytes[2h] offset 22h) > 0)\n",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": []
+  },
+  {
+    "cate": "",
+    "name": "[RabbitMQ] No MajorityOfNodesReady",
+    "note": "There are so many nodes not ready",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 300,
+    "prom_ql": "kube_statefulset_status_replicas_ready<=kube_statefulset_replicas/ 2 unless kube_statefulset_replicas== 0\n",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": []
+  },
+  {
+    "cate": "",
+    "name": "[RabbitMQ] Persistent Volume Missing",
+    "note": "There is at least one pvc not bound",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 1,
+    "disabled": 0,
+    "prom_for_duration": 600,
+    "prom_ql": "kube_persistentvolumeclaim_status_phase{phase=\"Bound\"} == 0\n",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": []
+  },
+  {
+    "cate": "",
+    "name": "[RabbitMQ] TCP Sockets Near Limit",
+    "note": "The TCP sockets are near to the limit",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 600,
+    "prom_ql": "sum (max_over_time(rabbitmq_process_open_tcp_sockets[5m]))/sum (rabbitmq_process_max_tcp_sockets)> 0.8\n",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": []
+  },
+  {
+    "cate": "",
+    "name": "[RabbitMQ] Unroutable Messages",
+    "note": "There were unroutable message within the last 5 minutes in RabbitMQ cluster",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 300,
+    "prom_ql": "sum (increase(rabbitmq_channel_messages_unroutable_dropped_total[5m])) >= 1 or sum (increase(rabbitmq_channel_messages_unroutable_returned_total[5m])) >= 1\n",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": []
+  }
+]

integrations/RabbitMQ/markdown/README.md

@@ -0,0 +1,31 @@
+## RabbitMQ Dashboard & Configuration
+
+使用[categraf](https://github.com/flashcatcloud/categraf)中[inputs.prometheus](https://github.com/flashcatcloud/categraf/tree/main/inputs/prometheus)插件采集[RabbitMQ](https://www.rabbitmq.com/)默认暴露的指标数据:
+
+
+### 配置文件示例：
+
+初始化好集群后，使用`rabbitmq-plugins enable rabbitmq_prometheus`命令开启集群默认暴露Prometheus指标，配置测试版本为3.8.19，理论上版本大于3.8+的版本都可以使用。
+
+```toml
+# conf/input.prometheus/prometheus.toml
+[[instances]]
+urls = [
+    "http://192.168.x.11:15692/metrics",
+    "http://192.168.x.12:15692/metrics"
+]
+
+url_label_key = "instance"
+url_label_value = "{{.Host}}"
+labels = {service="rabbitmq-cluster"}
+
+```
+
+### 告警规则
+
+[alerts](../alerts/alerts.json)
+
+
+### 效果图：
+
+![rabbitmq](./rabbitmq.png)

integrations/SNMP/dashboards/dashboards.json

@@ -0,0 +1,891 @@
+{
+    "name": "SNMP Stats",
+    "tags": "",
+    "ident": "",
+    "configs": {
+        "version": "3.0.0",
+        "links": [],
+        "var": [
+            {
+                "name": "ident",
+                "type": "query",
+                "datasource": {
+                    "cate": "prometheus",
+                    "value": 4
+                },
+                "definition": "label_values(snmp_interface_ifInOctets,  ident)",
+                "reg": "",
+                "multi": false
+            },
+            {
+                "name": "role",
+                "label": "role",
+                "type": "query",
+                "datasource": {
+                    "cate": "prometheus",
+                    "value": 4
+                },
+                "definition": "label_values(snmp_uptime,role)"
+            }
+        ],
+        "panels": [
+            {
+                "type": "stat",
+                "id": "d5e905cf-da22-48be-9fca-1f92695ca730",
+                "layout": {
+                    "h": 3,
+                    "w": 8,
+                    "x": 0,
+                    "y": 0,
+                    "i": "d5e905cf-da22-48be-9fca-1f92695ca730",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": 4,
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "snmp_uptime{ident=\"$ident\",role=\"$role\"} /100",
+                        "legend": "In"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "Uptime",
+                "links": [],
+                "description": "系统启动时间，timetick转换为秒，大盘自动转换为时 天 周 月……",
+                "maxPerRow": 4,
+                "custom": {
+                    "textMode": "value",
+                    "graphMode": "none",
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "valueField": "Value",
+                    "colSpan": 1,
+                    "textSize": {}
+                },
+                "options": {
+                    "standardOptions": {
+                        "util": "seconds"
+                    },
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                }
+            },
+            {
+                "type": "stat",
+                "id": "26ae7fc1-230e-451e-9415-ea93ae8b2abb",
+                "layout": {
+                    "h": 3,
+                    "w": 8,
+                    "x": 8,
+                    "y": 0,
+                    "i": "26ae7fc1-230e-451e-9415-ea93ae8b2abb",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": 4,
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "max(irate(snmp_interface_ifOutOctets{ident=\"$ident\",role=\"$role\"}[5m]))",
+                        "legend": "Out"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "Max Out (Current)",
+                "links": [],
+                "description": "端口每秒最大出流量  单位是bit，大盘自动转换",
+                "maxPerRow": 4,
+                "custom": {
+                    "textMode": "value",
+                    "graphMode": "none",
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "valueField": "Value",
+                    "colSpan": 1,
+                    "textSize": {}
+                },
+                "options": {
+                    "standardOptions": {},
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                }
+            },
+            {
+                "type": "stat",
+                "id": "c5496f39-e194-401c-888c-556292e39254",
+                "layout": {
+                    "h": 3,
+                    "w": 8,
+                    "x": 16,
+                    "y": 0,
+                    "i": "c5496f39-e194-401c-888c-556292e39254",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": 4,
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "max(irate(snmp_interface_ifInOctets{ident=\"$ident\",role=\"$role\"}[5m]))",
+                        "legend": "In"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "Max In (Current)",
+                "links": [],
+                "description": "端口每秒最大入流量",
+                "maxPerRow": 4,
+                "custom": {
+                    "textMode": "value",
+                    "graphMode": "none",
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "valueField": "Value",
+                    "colSpan": 1,
+                    "textSize": {}
+                },
+                "options": {
+                    "standardOptions": {},
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                }
+            },
+            {
+                "type": "stat",
+                "id": "d755c99d-a323-41e6-8117-6bc006bef8b7",
+                "layout": {
+                    "h": 3,
+                    "w": 8,
+                    "x": 0,
+                    "y": 3,
+                    "i": "bd2cd5b0-50ac-42d7-b29d-ea89ceb015a7",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": 4,
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "snmp_sys_cpu_usage{ident=\"$ident\",role=\"$role\"}",
+                        "legend": "Out"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "CPU 使用率 %",
+                "links": [],
+                "description": "",
+                "maxPerRow": 4,
+                "custom": {
+                    "textMode": "value",
+                    "graphMode": "none",
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "valueField": "Value",
+                    "colSpan": 1,
+                    "textSize": {}
+                },
+                "options": {
+                    "standardOptions": {},
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                }
+            },
+            {
+                "type": "stat",
+                "id": "c3991b49-1ad8-4f63-87b8-d41bbf729833",
+                "layout": {
+                    "h": 3,
+                    "w": 8,
+                    "x": 8,
+                    "y": 3,
+                    "i": "109aad94-79bd-4aec-b8ac-db73cb6601a8",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": 4,
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "snmp_sys_mem_usage{ident=\"$ident\",role=\"$role\"}",
+                        "legend": "mem_usage"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "内存使用率 %",
+                "links": [],
+                "description": "内存使用率 ",
+                "maxPerRow": 4,
+                "custom": {
+                    "textMode": "value",
+                    "graphMode": "none",
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "valueField": "Value",
+                    "colSpan": 1,
+                    "textSize": {}
+                },
+                "options": {
+                    "standardOptions": {},
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                }
+            },
+            {
+                "type": "stat",
+                "id": "024c8f3e-b632-4177-9a71-396d81ede19e",
+                "layout": {
+                    "h": 3,
+                    "w": 8,
+                    "x": 16,
+                    "y": 3,
+                    "i": "55c508d9-acaa-4bd2-a473-7b6176a5a44a",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": 4,
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "snmp_sys_mem_usage{ident=\"$ident\",role=\"$role\"}",
+                        "legend": "mem_usage"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "并发连接数（当前）",
+                "links": [],
+                "description": "当前并发连接数",
+                "maxPerRow": 4,
+                "custom": {
+                    "textMode": "value",
+                    "graphMode": "none",
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "valueField": "Value",
+                    "colSpan": 1,
+                    "textSize": {}
+                },
+                "options": {
+                    "standardOptions": {},
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                }
+            },
+            {
+                "type": "stat",
+                "id": "49e0453c-328c-4499-9097-a6bb52d92ad1",
+                "layout": {
+                    "h": 3,
+                    "w": 8,
+                    "x": 0,
+                    "y": 6,
+                    "i": "c7ddd2b8-5803-4de0-a8e7-3466020684e9",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": 4,
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "snmp_sys_session_rate{ident=\"$ident\",role=\"$role\"}",
+                        "legend": "mem_usage"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "每秒新建连接数",
+                "links": [],
+                "description": "最近10分钟平均每秒新建连接数",
+                "maxPerRow": 4,
+                "custom": {
+                    "textMode": "value",
+                    "graphMode": "none",
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "valueField": "Value",
+                    "colSpan": 1,
+                    "textSize": {}
+                },
+                "options": {
+                    "standardOptions": {},
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                }
+            },
+            {
+                "type": "stat",
+                "id": "ad0d02bb-9eb0-47d8-8529-1ce66150e4f9",
+                "layout": {
+                    "h": 3,
+                    "w": 8,
+                    "x": 8,
+                    "y": 6,
+                    "i": "ad0d02bb-9eb0-47d8-8529-1ce66150e4f9",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": 4,
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "max(delta(snmp_interface_ifOutOctets{ident=\"$ident\",role=\"$role\"}[1m]))",
+                        "legend": "Out"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "Total Out",
+                "links": [],
+                "description": "最近1分钟总计出流量",
+                "maxPerRow": 4,
+                "custom": {
+                    "textMode": "value",
+                    "graphMode": "none",
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "valueField": "Value",
+                    "colSpan": 1,
+                    "textSize": {}
+                },
+                "options": {
+                    "standardOptions": {},
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                }
+            },
+            {
+                "type": "stat",
+                "id": "616de58a-70a7-4c0b-b0f2-5151b9f0e9c5",
+                "layout": {
+                    "h": 3,
+                    "w": 8,
+                    "x": 16,
+                    "y": 6,
+                    "i": "616de58a-70a7-4c0b-b0f2-5151b9f0e9c5",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": 4,
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "max(delta(snmp_interface_ifInOctets{role=\"$role\",ident=\"$ident\"}[1m]))",
+                        "legend": "In"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "Total In",
+                "links": [],
+                "description": "最近1分钟总计入流量",
+                "maxPerRow": 4,
+                "custom": {
+                    "textMode": "value",
+                    "graphMode": "none",
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "valueField": "Value",
+                    "colSpan": 1,
+                    "textSize": {}
+                },
+                "options": {
+                    "standardOptions": {},
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                }
+            },
+            {
+                "type": "stat",
+                "id": "fcdf91de-394f-4d9c-abb9-d750583ce6cf",
+                "layout": {
+                    "h": 3,
+                    "w": 8,
+                    "x": 0,
+                    "y": 9,
+                    "i": "da757839-0fc0-4d1b-b486-7070aa3d70f8",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": 4,
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "sum(irate(snmp_interface_ifInDiscards{role=\"$role\",ident=\"$ident\"}[1m]))",
+                        "legend": "In"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "Drop Packets (In)",
+                "links": [],
+                "description": "入方向1m内丢包数",
+                "maxPerRow": 4,
+                "custom": {
+                    "textMode": "value",
+                    "graphMode": "none",
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "valueField": "Value",
+                    "colSpan": 1,
+                    "textSize": {}
+                },
+                "options": {
+                    "standardOptions": {},
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                }
+            },
+            {
+                "type": "stat",
+                "id": "b5d3c6de-6512-40d2-b167-a1e00bfaa795",
+                "layout": {
+                    "h": 3,
+                    "w": 8,
+                    "x": 8,
+                    "y": 9,
+                    "i": "ab9b1070-a81a-4a30-9dcd-7071dfafcdc6",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": 4,
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "sum(irate(snmp_interface_ifOutDiscards{role=\"$role\",ident=\"$ident\"}[1m]))",
+                        "legend": "In"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "Drop Packets (Out)",
+                "links": [],
+                "description": "出方向1m的丢包数",
+                "maxPerRow": 4,
+                "custom": {
+                    "textMode": "value",
+                    "graphMode": "none",
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "valueField": "Value",
+                    "colSpan": 1,
+                    "textSize": {}
+                },
+                "options": {
+                    "standardOptions": {},
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                }
+            },
+            {
+                "type": "barGauge",
+                "id": "a925c635-0ff8-4984-a8b0-ca99948960f0",
+                "layout": {
+                    "h": 9,
+                    "w": 12,
+                    "x": 0,
+                    "y": 12,
+                    "i": "a925c635-0ff8-4984-a8b0-ca99948960f0",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": 4,
+                "targets": [
+                    {
+                        "refId": "B",
+                        "expr": "irate(snmp_interface_ifOutOctets{ident=\"$ident\",role=\"$role\"}[5m])",
+                        "legend": "{{ifDescr}}( {{ifIndex}})"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "Out (Current)",
+                "links": [],
+                "description": "Max: 10MB  \nRed Status: 9MB",
+                "maxPerRow": 4,
+                "custom": {
+                    "calc": "lastNotNull",
+                    "baseColor": "#9470FF",
+                    "serieWidth": 20,
+                    "sortOrder": "desc"
+                },
+                "options": {
+                    "standardOptions": {}
+                }
+            },
+            {
+                "type": "barGauge",
+                "id": "86345d37-977a-44e0-96ca-e46fe388b529",
+                "layout": {
+                    "h": 9,
+                    "w": 12,
+                    "x": 12,
+                    "y": 12,
+                    "i": "86345d37-977a-44e0-96ca-e46fe388b529",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": 4,
+                "targets": [
+                    {
+                        "refId": "B",
+                        "expr": "irate(snmp_interface_ifInOctets{ident=\"$ident\",role=\"$role\"}[5m])",
+                        "legend": "{{ifDescr}}({{ifIndex}})"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "In (Current)",
+                "links": [],
+                "description": "Max: 10MB  \nRed Status: 9MB",
+                "maxPerRow": 4,
+                "custom": {
+                    "calc": "lastNotNull",
+                    "baseColor": "#9470FF",
+                    "serieWidth": 20,
+                    "sortOrder": "desc"
+                },
+                "options": {
+                    "standardOptions": {}
+                }
+            },
+            {
+                "type": "timeseries",
+                "id": "4bd4c3ad-e00f-4eac-89fc-6b146f36d922",
+                "layout": {
+                    "h": 10,
+                    "w": 24,
+                    "x": 0,
+                    "y": 21,
+                    "i": "4bd4c3ad-e00f-4eac-89fc-6b146f36d922",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": 4,
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "irate(snmp_interface_ifOutOctets{ident=\"$ident\",role=\"$role\"}[5m])",
+                        "legend": "Out: {{ifDescr}} "
+                    },
+                    {
+                        "refId": "B",
+                        "expr": "-irate(snmp_interface_ifInOctets{ident=\"$ident\",role=\"$role\"}[5m])",
+                        "legend": "In: {{ifDescr}} "
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "Out / In",
+                "links": [],
+                "maxPerRow": 4,
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "linear",
+                    "spanNulls": false,
+                    "lineWidth": 1,
+                    "fillOpacity": 0.5,
+                    "gradientMode": "none",
+                    "stack": "off",
+                    "scaleDistribution": {
+                        "type": "linear"
+                    }
+                }
+            },
+            {
+                "type": "table",
+                "id": "b663d53d-41a9-4e28-a60e-6ced1b9d46ce",
+                "layout": {
+                    "h": 10,
+                    "w": 24,
+                    "x": 0,
+                    "y": 31,
+                    "i": "b663d53d-41a9-4e28-a60e-6ced1b9d46ce",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": 4,
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "snmp_interface_ifOperStatus{ident=\"$ident\",role=\"$role\"}",
+                        "legend": "out"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "Interface Status",
+                "links": [],
+                "maxPerRow": 4,
+                "custom": {
+                    "showHeader": true,
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "displayMode": "labelsOfSeriesToRows",
+                    "columns": [
+                        "shop",
+                        "role",
+                        "ifIndex",
+                        "value"
+                    ],
+                    "sortColumn": "ifDescr",
+                    "sortOrder": "ascend"
+                },
+                "options": {
+                    "valueMappings": [
+                        {
+                            "type": "special",
+                            "result": {
+                                "color": "#3fc453",
+                                "text": "UP"
+                            },
+                            "match": {
+                                "special": 1
+                            }
+                        },
+                        {
+                            "type": "special",
+                            "result": {
+                                "color": "#ce4f52",
+                                "text": "DOWN"
+                            },
+                            "match": {
+                                "special": 2
+                            }
+                        },
+                        {
+                            "type": "special",
+                            "result": {
+                                "color": "#9470ff",
+                                "text": "TESTING"
+                            },
+                            "match": {
+                                "special": 3
+                            }
+                        },
+                        {
+                            "type": "special",
+                            "result": {
+                                "color": "#000000",
+                                "text": "UNKNOWN"
+                            },
+                            "match": {
+                                "special": 4
+                            }
+                        },
+                        {
+                            "type": "special",
+                            "result": {
+                                "color": "#ffae39",
+                                "text": "DORMANT"
+                            },
+                            "match": {
+                                "special": 5
+                            }
+                        },
+                        {
+                            "type": "special",
+                            "result": {
+                                "color": "#e6c627",
+                                "text": "NotPresent"
+                            },
+                            "match": {
+                                "special": 6
+                            }
+                        },
+                        {
+                            "type": "special",
+                            "result": {
+                                "color": "#ff8286",
+                                "text": "LowerLayerDown"
+                            },
+                            "match": {
+                                "special": 7
+                            }
+                        }
+                    ],
+                    "standardOptions": {}
+                },
+                "overrides": [
+                    {}
+                ]
+            }
+        ]
+    }
+}

integrations/SNMP/dashboards/placeholder.json

@@ -1,10 +0,0 @@
-{
-    "name": "占位的，等待老炮 PR",
-    "tags": "",
-    "ident": "",
-    "configs": {
-        "var": [],
-        "panels": [],
-        "version": "3.0.0"
-    }
-}

integrations/TiDB/icon/2_TiDB_ICON.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 216 249.42"><defs><style>.cls-1{fill:#e30c34;}.cls-2{fill:#fff;}</style></defs><g id="图层_2" data-name="图层 2"><g id="图层_1-2" data-name="图层 1"><polygon class="cls-1" points="0 62.35 0 187.06 108 249.41 216 187.06 216 62.35 108 0 0 62.35"/><polygon class="cls-2" points="107.94 41.63 36.21 83.04 36.21 124.45 72.08 103.73 72.08 187.11 107.94 207.78 107.94 207.78 107.94 83.03 143.79 62.33 107.94 41.63"/><polygon class="cls-2" points="144 103.95 144 187.06 180 166.28 180 83.14 144 103.95"/></g></g></svg>

integrations/elasticsearch/alerts/elasticsearch_by_categraf.json

@@ -0,0 +1,392 @@
+[
+    {
+      "name": "Elastic Cluster Red status",
+      "note": "",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": " elasticsearch_cluster_health_status{color=\"red\"} == 1",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=ElasticsearchClusterRed"
+      ]
+    },
+    {
+      "name": "Elastic Cluster Yellow status",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "elasticsearch_cluster_health_status{color=\"yellow\"} == 1",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=ElasticsearchClusterYellow"
+      ]
+    },
+    {
+      "name": "Elasticsearch disk out of space of the instance",
+      "note": "",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 120,
+      "prom_ql": "elasticsearch_filesystem_data_available_bytes / elasticsearch_filesystem_data_size_bytes * 100 < 10",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=ElasticsearchDiskOutOfSpace"
+      ]
+    },
+    {
+      "name": "Elasticsearch disk space low of the instance",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 120,
+      "prom_ql": "elasticsearch_filesystem_data_available_bytes / elasticsearch_filesystem_data_size_bytes * 100 < 20",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=ElasticsearchDiskSpaceLow"
+      ]
+    },
+    {
+      "name": "Elasticsearch Heap Usage Too High of the instance",
+      "note": "",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 120,
+      "prom_ql": "(elasticsearch_jvm_memory_used_bytes{area=\"heap\"} / elasticsearch_jvm_memory_max_bytes{area=\"heap\"}) * 100 > 90",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=ElasticsearchHeapUsageTooHigh"
+      ]
+    },
+    {
+      "name": "Elasticsearch Heap Usage warning of the instance",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 120,
+      "prom_ql": "(elasticsearch_jvm_memory_used_bytes{area=\"heap\"} / elasticsearch_jvm_memory_max_bytes{area=\"heap\"}) * 100 > 80",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=ElasticsearchHeapUsageWarning"
+      ]
+    },
+    {
+      "name": "Elasticsearch initializing shards of the instance",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 900,
+      "prom_ql": "elasticsearch_cluster_health_initializing_shards > 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=ElasticsearchInitializingShards"
+      ]
+    },
+    {
+      "name": "Elasticsearch no new documents of the instance",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 300,
+      "prom_ql": "rate(elasticsearch_indices_docs{es_data_node=\"true\"}[5m]) == 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=ElasticsearchNoNewDocuments"
+      ]
+    },
+    {
+      "name": "Elasticsearch pending tasks of the instance",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 900,
+      "prom_ql": "elasticsearch_cluster_health_number_of_pending_tasks > 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=ElasticsearchPendingTasks"
+      ]
+    },
+    {
+      "name": "Elasticsearch relocation shards of the instance",
+      "note": "",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 900,
+      "prom_ql": "elasticsearch_cluster_health_relocating_shards > 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=ElasticsearchRelocationShards"
+      ]
+    },
+    {
+      "name": "Elasticsearch unassigned shards of the instance",
+      "note": "",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "elasticsearch_cluster_health_unassigned_shards > 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=ElasticsearchUnassignedShards"
+      ]
+    },
+    {
+      "name": "Elasticsearch Unhealthy Data Nodes",
+      "note": "",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "elasticsearch_cluster_health_number_of_data_nodes < number_of_data_nodes",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=ElasticsearchHealthyDataNodes"
+      ]
+    },
+    {
+      "name": "Elasticsearch Unhealthy Nodes",
+      "note": "",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": " elasticsearch_cluster_health_number_of_nodes < number_of_nodes",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=ElasticsearchHealthyNodes"
+      ]
+    }
+  ]

integrations/elasticsearch/markdown/README.md

@@ -0,0 +1,26 @@
+### 采集方式
+
+使用Categraf插件[elasticsearch](https://github.com/flashcatcloud/categraf/blob/main/conf/input.elasticsearch/elasticsearch.toml)采集ES指标；
+
+### 配置示例
+
+```yaml
+cat conf/input.elasticsearch/elasticsearch.toml | egrep -v "^#|^$"
+[[instances]]
+servers = ["http://192.168.11.177:9200"]
+http_timeout = "5s"
+local = true
+cluster_health = true
+cluster_health_level = "cluster"
+cluster_stats = true
+indices_level = ""
+node_stats = ["jvm", "breaker", "process", "os", "fs", "indices"]
+username = "elastic"
+password = "xxxxxxxx"
+num_most_recent_indices = 1
+labels = { instance="default-es" , service="es" }
+```
+
+### 效果图：
+
+![](./es-dashboard.jpeg)

integrations/ipmi/alerts/alerts.json

@@ -0,0 +1,266 @@
+[
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "CPU温度超过90",
+    "note": "",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 0,
+    "severities": [
+      2
+    ],
+    "disabled": 0,
+    "prom_for_duration": 60,
+    "prom_ql": "",
+    "rule_config": {
+      "queries": [
+        {
+          "prom_ql": "ipmi_cpu1_temp{} > 90 or ipmi_cpu2_temp{} > 90",
+          "severity": 2
+        }
+      ]
+    },
+    "prom_eval_interval": 30,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "0",
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "0",
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": {}
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "CPU电压大于10",
+    "note": "",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 0,
+    "severities": [
+      2
+    ],
+    "disabled": 0,
+    "prom_for_duration": 60,
+    "prom_ql": "",
+    "rule_config": {
+      "queries": [
+        {
+          "prom_ql": "ipmi_vcpu1 > 10 or ipmi_vcpu1 > 10",
+          "severity": 2
+        }
+      ]
+    },
+    "prom_eval_interval": 30,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "0",
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "0",
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": {}
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "CPU风扇转速超过1000",
+    "note": "",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 0,
+    "severities": [
+      2
+    ],
+    "disabled": 0,
+    "prom_for_duration": 60,
+    "prom_ql": "",
+    "rule_config": {
+      "queries": [
+        {
+          "prom_ql": "ipmi_fan1  > 1000 or ipmi_fan2  > 1000 or ipmi_fan3  > 1000 or ipmi_fan4  > 1000 or ipmi_fan5  > 1000 or ipmi_fan6 > 1000",
+          "severity": 2
+        }
+      ]
+    },
+    "prom_eval_interval": 30,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "0",
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "0",
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": {}
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "主板温度超过90",
+    "note": "",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 0,
+    "severities": [
+      2
+    ],
+    "disabled": 0,
+    "prom_for_duration": 60,
+    "prom_ql": "",
+    "rule_config": {
+      "queries": [
+        {
+          "prom_ql": "ipmi_system_temp > 90 or ipmi_pch_temp > 90",
+          "severity": 2
+        }
+      ]
+    },
+    "prom_eval_interval": 30,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "0",
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "0",
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": {}
+  }
+]

integrations/ipmi/dashboards/IPMI.json

@@ -0,0 +1,367 @@
+{
+  "name": "IPMI",
+  "tags": "Categraf",
+  "ident": "",
+  "configs": {
+    "var": [
+      {
+        "name": "datasource",
+        "type": "datasource",
+        "definition": "prometheus",
+        "defaultValue": 5
+      },
+      {
+        "type": "query",
+        "name": "server",
+        "definition": "label_values(ipmi_system_temp,server)",
+        "datasource": {
+          "cate": "prometheus",
+          "value": "${datasource}"
+        }
+      }
+    ],
+    "panels": [
+      {
+        "type": "row",
+        "id": "1007833d-b9fb-4199-979e-6f70c0904770",
+        "name": "分组",
+        "collapsed": false,
+        "layout": {
+          "h": 1,
+          "w": 24,
+          "x": 0,
+          "y": 0,
+          "i": "1007833d-b9fb-4199-979e-6f70c0904770",
+          "isResizable": false
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "3d7ca439-38fa-4f22-9b6a-98323f167ee9",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 1,
+          "i": "3d7ca439-38fa-4f22-9b6a-98323f167ee9",
+          "isResizable": true
+        },
+        "version": "3.0.0",
+        "datasourceCate": "prometheus",
+        "datasourceValue": "${datasource}",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "ipmi_cpu1_temp{server=\"$server\"}",
+            "legend": "CPU1"
+          },
+          {
+            "expr": "ipmi_cpu2_temp{server=\"$server\"}",
+            "refId": "B",
+            "legend": "CPU2"
+          }
+        ],
+        "transformations": [
+          {
+            "id": "organize",
+            "options": {}
+          }
+        ],
+        "name": "CPU温度",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "32ccc47c-6841-4b1d-a8b5-f6034ddca3e8",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 1,
+          "i": "32ccc47c-6841-4b1d-a8b5-f6034ddca3e8",
+          "isResizable": true
+        },
+        "version": "3.0.0",
+        "datasourceCate": "prometheus",
+        "datasourceValue": 5,
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "ipmi_vcpu1",
+            "legend": "CPU1 "
+          },
+          {
+            "expr": "ipmi_vcpu2",
+            "refId": "B",
+            "legend": "CPU2"
+          }
+        ],
+        "transformations": [
+          {
+            "id": "organize",
+            "options": {}
+          }
+        ],
+        "name": "CPU电压",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "ipmi_system_temp{server=\"$server\"}",
+            "legend": "system_temp"
+          },
+          {
+            "expr": "ipmi_pch_temp{server=\"$server\"}",
+            "refId": "B",
+            "legend": "pch_temp"
+          }
+        ],
+        "name": "主板温度",
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {}
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off"
+        },
+        "version": "2.0.0",
+        "type": "timeseries",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 5,
+          "i": "899d2ed2-4b9e-4a45-82f4-9aa8287842ea",
+          "isResizable": true
+        },
+        "id": "899d2ed2-4b9e-4a45-82f4-9aa8287842ea",
+        "datasourceCate": "prometheus",
+        "datasourceValue": "${datasource}"
+      },
+      {
+        "type": "timeseries",
+        "id": "fab67c57-8c83-4bc3-82a6-b304b14ece84",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 5,
+          "i": "fab67c57-8c83-4bc3-82a6-b304b14ece84",
+          "isResizable": true
+        },
+        "version": "3.0.0",
+        "datasourceCate": "prometheus",
+        "datasourceValue": "${datasource}",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "ipmi_fan1{server=\"$server\"}",
+            "legend": "fan1"
+          },
+          {
+            "expr": "ipmi_fan2{server=\"$server\"}",
+            "refId": "B",
+            "legend": "fan2"
+          },
+          {
+            "expr": "ipmi_fan3{server=\"$server\"}",
+            "refId": "C",
+            "legend": "fan3"
+          },
+          {
+            "expr": "ipmi_fan4{server=\"$server\"}",
+            "refId": "D",
+            "legend": "fan4"
+          },
+          {
+            "expr": "ipmi_fan5{server=\"$server\"}",
+            "refId": "E",
+            "legend": "fan5"
+          },
+          {
+            "expr": "ipmi_fan6{server=\"$server\"}",
+            "refId": "F",
+            "legend": "fan6"
+          }
+        ],
+        "transformations": [
+          {
+            "id": "organize",
+            "options": {}
+          }
+        ],
+        "name": "风扇转速",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "a5ee9813-4f4c-4928-8aed-b93d78b63199",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 9,
+          "i": "a5ee9813-4f4c-4928-8aed-b93d78b63199",
+          "isResizable": true
+        },
+        "version": "3.0.0",
+        "datasourceCate": "prometheus",
+        "datasourceValue": 5,
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "ipmi_12v{server=~\"$server\"}",
+            "legend": "12V"
+          }
+        ],
+        "transformations": [
+          {
+            "id": "organize",
+            "options": {}
+          }
+        ],
+        "name": "电压",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      }
+    ],
+    "version": "3.0.0"
+  }
+}

integrations/ipmi/markdown/README.md

@@ -0,0 +1,152 @@
+### 使用Categraf基于IPMI工具监控硬件温度、功率、电压
+
+实现原理：
+
+利用ipmitool sdr命令， 采集硬件的温度、功率、电压等信息，并转化为指标。 依赖工具ipmitool ,所以需要安装ipmitool。
+
+IPMI配置：
+
+```bash
+#  此处的主机必须支持ipmi bmc，不然openipmi启动不了
+# Ubuntu 
+apt install openipmi ipmitool
+# Centos
+yum install OpenIPMI  ipmitool
+# 加载模块
+modprobe ipmi_msghandler
+modprobe ipmi_devintf
+modprobe ipmi_si
+modprobe ipmi_poweroff
+modprobe ipmi_watchdog
+# 此处有一点一定要注意，如果不是真实的服务器的话，在加载ipmi_si的时候会报错，因为在虚拟化中使用虚拟机测试，安装完成以后，ipmi_si模块无法加载。
+lsmod |grep ^ipmi
+ipmi_watchdog          28672  0
+ipmi_poweroff          16384  0
+ipmi_ssif              32768  0
+ipmi_si                61440  1
+ipmi_devintf           20480  0
+ipmi_msghandler       102400  5 ipmi_devintf,ipmi_si,ipmi_watchdog,ipmi_ssif,ipmi_poweroff
+# 配置ipm访问，在目标主机，我这里是server01做实例。
+ipmitool user list 1 # 查看当前的用户列表
+ID  Name         Callin  Link Auth  IPMI Msg   Channel Priv Limit
+1                    true    false      false      NO ACCESS
+2   root             true    true       true       ADMINISTRATOR
+3                    true    false      false      NO ACCESS
+4                    true    false      false      NO ACCESS
+5                    true    false      false      NO ACCESS
+6                    true    false      false      NO ACCESS
+7                    true    false      false      NO ACCESS
+8                    true    false      false      NO ACCESS
+9                    true    false      false      NO ACCESS
+10                   true    false      false      NO ACCESS
+# 设置ID 3 为 user为 test 密码 test
+ipmitool  user  set name 3 test
+ipmitool  user  set password 3 test
+ipmitool  user  enable 3
+# 验证
+ipmitool user list 1 
+ID  Name         Callin  Link Auth  IPMI Msg   Channel Priv Limit
+1                    true    false      false      NO ACCESS
+2   root             true    true       true       ADMINISTRATOR
+3   test             true    false      false      NO ACCESS
+4                    true    false      false      NO ACCESS
+5                    true    false      false      NO ACCESS
+6                    true    false      false      NO ACCESS
+7                    true    false      false      NO ACCESS
+8                    true    false      false      NO ACCESS
+9                    true    false      false      NO ACCESS
+10                   true    false      false      NO ACCESS
+# privilege value：1 callback 2 user 3 operator 4 administrator 5 OEM
+# 设置用户test权限 channel 为 1，user ID 为 3，privilege 为 4
+ipmitool channel setaccess 1 3 callin=on ipmi=on link=on privilege=4
+# 验证权限
+ipmitool channel getaccess 1 3
+Maximum User IDs     : 10
+Enabled User IDs     : 1
+
+User ID              : 3
+User Name            : test
+Fixed Name           : No
+Access Available     : call-in / callback
+Link Authentication  : enabled
+IPMI Messaging       : enabled
+Privilege Level      : ADMINISTRATOR
+Enable Status        : disabled
+ipmitool  user list 1
+# 再次使用ipmitool  user list 1验证
+ipmitool  user list 1
+ID  Name         Callin  Link Auth  IPMI Msg   Channel Priv Limit
+1                    true    false      false      NO ACCESS
+2   root             true    true       true       ADMINISTRATOR
+3   test             true    true       true       ADMINISTRATOR
+4                    true    false      false      NO ACCESS
+5                    true    false      false      NO ACCESS
+6                    true    false      false      NO ACCESS
+7                    true    false      false      NO ACCESS
+8                    true    false      false      NO ACCESS
+9                    true    false      false      NO ACCESS
+10                   true    false      false      NO ACCESS
+# OK，针对网络做下配置，注意主机的网段与子网掩码
+ipmitool lan set 1 ipaddr 192.168.1.229
+ipmitool lan set 1 netmask 255.255.252.0
+ipmitool lan set 1 defgw ipaddr 192.168.1.123
+ipmitool lan set 1 access on
+# 验证网络配置
+ipmitool lan print 1
+IP Address Source       : Static Address
+IP Address              : 192.168.1.227
+Subnet Mask             : 255.255.252.0
+MAC Address             : xx:xx:52:xx:xx:81
+SNMP Community String   : public
+```
+
+### 采集配置
+使用[categraf](https://github.com/flashcatcloud/categraf)中[inputs.ipmi](https://github.com/flashcatcloud/categraf/tree/main/inputs/ipmi)插件采集服务器指标:
+```yaml
+cat /opt/categraf/conf/input.ipmi/conf.toml
+  [[instances]]
+  ## optionally specify the path to the ipmitool executable
+  # path = "/usr/bin/ipmitool"
+  ##
+  ## Setting 'use_sudo' to true will make use of sudo to run ipmitool.
+  ## Sudo must be configured to allow the telegraf user to run ipmitool
+  ## without a password.
+  # use_sudo = false
+  ##
+  ## optionally force session privilege level. Can be CALLBACK, USER, OPERATOR, ADMINISTRATOR
+  # privilege = "ADMINISTRATOR"
+  ##
+  ## optionally specify one or more servers via a url matching
+  ##  [username[:password]@][protocol[(address)]]
+  ##  e.g.
+  ##    root:passwd@lan(127.0.0.1)
+  ##
+  ## if no servers are specified, local machine sensor stats will be queried
+  ##
+  servers = ["ADMIN:1234567@lan(192.168.1.123)"]
+
+  ## Recommended: use metric 'interval' that is a multiple of 'timeout' to avoid
+  ## gaps or overlap in pulled data
+  interval = "30s"
+
+  ## Timeout for the ipmitool command to complete. Default is 20 seconds.
+  timeout = "20s"
+
+  ## Schema Version: (Optional, defaults to version 1)
+  metric_version = 2
+
+  ## Optionally provide the hex key for the IMPI connection.
+  # hex_key = ""
+
+  ## If ipmitool should use a cache
+  ## for me ipmitool runs about 2 to 10 times faster with cache enabled on HP G10 servers (when using ubuntu20.04)
+  ## the cache file may not work well for you if some sensors come up late
+  # use_cache = false
+
+  ## Path to the ipmitools cache file (defaults to OS temp dir)
+  ## The provided path must exist and must be writable
+```
+
+[告警规则](../alerts/alerts.json)
+
+效果图：![ipmi](./ipmi.png)

integrations/kafka/alerts/kafka_by_categraf.json

@@ -0,0 +1,164 @@
+[
+  {
+    "cate": "prometheus",
+    "name": "kafka 数据有丢失风险-副本数小于3",
+    "note": "",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "disabled": 1,
+    "prom_for_duration": 60,
+    "prom_ql": "sum(kafka_topic_partition_in_sync_replica) by (topic) < 3",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [
+      "service=kafka",
+      "type=categraf"
+    ]
+  },
+  {
+    "cate": "prometheus",
+    "name": "kafka 服务宕机",
+    "note": "",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 1,
+    "disabled": 1,
+    "prom_for_duration": 60,
+    "prom_ql": "kafka_broker_info{service=~\"kafka\"} < 1",
+    "prom_eval_interval": 60,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [
+      "type=categraf",
+      "service=kafka"
+    ]
+  },
+  {
+    "cate": "prometheus",
+    "name": "kafka 消费能力不足-延迟超过5分钟",
+    "note": "",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "disabled": 1,
+    "prom_for_duration": 60,
+    "prom_ql": "max(kafka_consumer_lag_millis) by (topic, consumergroup)  / 1000 > 300",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [
+      "service=kafka",
+      "type=categraf"
+    ]
+  }
+]

integrations/kafka/dashboards/kafka_by_categraf.json

@@ -0,0 +1,370 @@
+{
+  "name": "Kafka By Categraf",
+  "tags": "Kafka Prometheus Categraf",
+  "ident": "",
+  "configs": {
+    "var": [
+      {
+        "name": "cluster",
+        "definition": "label_values(kafka_brokers,  cluster)",
+        "type": "query"
+      }
+    ],
+    "version": "2.0.0",
+    "panels": [
+      {
+        "id": "51502c3a-dd6f-41c7-b8f1-87b88826c96e",
+        "type": "row",
+        "name": "overview",
+        "layout": {
+          "h": 1,
+          "w": 24,
+          "x": 0,
+          "y": 0,
+          "i": "51502c3a-dd6f-41c7-b8f1-87b88826c96e",
+          "isResizable": false
+        },
+        "collapsed": true
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "kafka_brokers{cluster=\"$cluster\"}"
+          }
+        ],
+        "name": "brokers",
+        "custom": {
+          "textMode": "value",
+          "colorMode": "value",
+          "calc": "lastNotNull",
+          "colSpan": 1,
+          "textSize": {
+            "value": 50
+          }
+        },
+        "options": {
+          "standardOptions": {}
+        },
+        "version": "2.0.0",
+        "type": "stat",
+        "layout": {
+          "h": 3,
+          "w": 6,
+          "x": 0,
+          "y": 1,
+          "i": "e2c1d271-ec43-4821-aa19-451e856af755",
+          "isResizable": true
+        },
+        "id": "e2c1d271-ec43-4821-aa19-451e856af755"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "count(count by (topic) (kafka_topic_partitions{cluster=\"$cluster\"}))"
+          }
+        ],
+        "name": "topics",
+        "custom": {
+          "textMode": "value",
+          "colorMode": "value",
+          "calc": "lastNotNull",
+          "colSpan": 1,
+          "textSize": {
+            "value": 50
+          }
+        },
+        "options": {
+          "standardOptions": {}
+        },
+        "version": "2.0.0",
+        "type": "stat",
+        "layout": {
+          "h": 3,
+          "w": 6,
+          "x": 6,
+          "y": 1,
+          "i": "fd3a0b9f-fd67-4360-a94c-869fee7b5b98",
+          "isResizable": true
+        },
+        "id": "fd3a0b9f-fd67-4360-a94c-869fee7b5b98"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(kafka_topic_partitions{cluster=\"$cluster\"})"
+          }
+        ],
+        "name": "partitions",
+        "custom": {
+          "textMode": "value",
+          "colorMode": "value",
+          "calc": "lastNotNull",
+          "colSpan": 1,
+          "textSize": {
+            "value": 50
+          }
+        },
+        "options": {
+          "standardOptions": {}
+        },
+        "version": "2.0.0",
+        "type": "stat",
+        "layout": {
+          "h": 3,
+          "w": 6,
+          "x": 12,
+          "y": 1,
+          "i": "e228d857-746b-41b6-8d2d-0152453c46f4",
+          "isResizable": true
+        },
+        "id": "e228d857-746b-41b6-8d2d-0152453c46f4"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(kafka_topic_partition_replicas{cluster=\"$cluster\"})"
+          }
+        ],
+        "name": "Replicas",
+        "custom": {
+          "textMode": "valueAndName",
+          "colorMode": "value",
+          "calc": "lastNotNull",
+          "colSpan": 1,
+          "textSize": {}
+        },
+        "options": {
+          "standardOptions": {}
+        },
+        "version": "2.0.0",
+        "type": "stat",
+        "layout": {
+          "h": 3,
+          "w": 6,
+          "x": 18,
+          "y": 1,
+          "i": "85438099-8d6b-4817-b9b9-1d0ed36029cd",
+          "isResizable": true
+        },
+        "id": "85438099-8d6b-4817-b9b9-1d0ed36029cd"
+      },
+      {
+        "id": "0db4aac4-86cf-44cd-950e-6c6a99be8ff4",
+        "type": "row",
+        "name": "throughput",
+        "layout": {
+          "h": 1,
+          "w": 24,
+          "x": 0,
+          "y": 4,
+          "i": "0db4aac4-86cf-44cd-950e-6c6a99be8ff4",
+          "isResizable": false
+        },
+        "collapsed": true
+      },
+      {
+        "targets": [
+          {
+            "expr": "sum(rate(kafka_topic_partition_current_offset{cluster=\"$cluster\"}[1m])) by (topic)"
+          }
+        ],
+        "name": "Messages produced per second",
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {}
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "fillOpacity": 0.5,
+          "stack": "off"
+        },
+        "version": "2.0.0",
+        "type": "timeseries",
+        "layout": {
+          "h": 7,
+          "w": 8,
+          "x": 0,
+          "y": 5,
+          "i": "c2ec4036-3081-45cc-b672-024c6df93833",
+          "isResizable": true
+        },
+        "id": "c2ec4036-3081-45cc-b672-024c6df93833"
+      },
+      {
+        "targets": [
+          {
+            "expr": "sum(rate(kafka_consumergroup_current_offset{cluster=\"$cluster\"}[1m])) by (topic)"
+          }
+        ],
+        "name": "Messages consumed per second",
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {}
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "fillOpacity": 0.5,
+          "stack": "off"
+        },
+        "version": "2.0.0",
+        "type": "timeseries",
+        "layout": {
+          "h": 7,
+          "w": 8,
+          "x": 8,
+          "y": 5,
+          "i": "7ad651a6-c12c-4d46-8d01-749fa776faef",
+          "isResizable": true
+        },
+        "id": "7ad651a6-c12c-4d46-8d01-749fa776faef"
+      },
+      {
+        "targets": [
+          {
+            "expr": "sum(kafka_consumer_lag_millis{cluster=\"$cluster\"}) by (consumergroup, topic)",
+            "legend": "{{consumergroup}} (topic: {{topic}})"
+          }
+        ],
+        "name": "Latency by Consumer Group",
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {
+            "util": "humantimeMilliseconds"
+          },
+          "thresholds": {}
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "fillOpacity": 0.5,
+          "stack": "off"
+        },
+        "version": "2.0.0",
+        "type": "timeseries",
+        "layout": {
+          "h": 7,
+          "w": 8,
+          "x": 16,
+          "y": 5,
+          "i": "855aa8f5-0c51-42d4-b9a4-5460b7cd0f5a",
+          "isResizable": true
+        },
+        "id": "855aa8f5-0c51-42d4-b9a4-5460b7cd0f5a"
+      },
+      {
+        "id": "20166830-7f85-4665-8f39-bf904267af29",
+        "type": "row",
+        "name": "patition/replicate",
+        "layout": {
+          "h": 1,
+          "w": 24,
+          "x": 0,
+          "y": 18,
+          "i": "20166830-7f85-4665-8f39-bf904267af29",
+          "isResizable": false
+        },
+        "collapsed": true
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "kafka_topic_partitions{cluster=\"$cluster\"}",
+            "legend": "{{topic}}"
+          }
+        ],
+        "name": "Partitions per Topic",
+        "custom": {
+          "showHeader": true,
+          "colorMode": "value",
+          "calc": "lastNotNull",
+          "displayMode": "seriesToRows"
+        },
+        "options": {
+          "standardOptions": {}
+        },
+        "overrides": [
+          {}
+        ],
+        "version": "2.0.0",
+        "type": "table",
+        "layout": {
+          "h": 7,
+          "w": 12,
+          "x": 0,
+          "y": 19,
+          "i": "8837a52e-c9eb-4afa-acc1-c3a5dac72d3b",
+          "isResizable": true
+        },
+        "id": "8837a52e-c9eb-4afa-acc1-c3a5dac72d3b"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "kafka_topic_partition_under_replicated_partition{cluster=\"$cluster\"}",
+            "legend": "{{topic}}-{{partition}}"
+          }
+        ],
+        "name": "Partitions Under Replicated",
+        "description": "副本不同步预案\n1. Restart the Zookeeper leader.\n2. Restart the broker\\brokers that are not replicating some of the partitions.",
+        "custom": {
+          "showHeader": true,
+          "colorMode": "value",
+          "calc": "lastNotNull",
+          "displayMode": "seriesToRows"
+        },
+        "options": {
+          "standardOptions": {}
+        },
+        "overrides": [
+          {}
+        ],
+        "version": "2.0.0",
+        "type": "table",
+        "layout": {
+          "h": 7,
+          "w": 12,
+          "x": 12,
+          "y": 19,
+          "i": "dd615767-dda7-4da6-b37f-0d484553aac6",
+          "isResizable": true
+        },
+        "id": "dd615767-dda7-4da6-b37f-0d484553aac6"
+      }
+    ],
+    "links": [
+      {
+        "title": "文档",
+        "url": "https://github.com/ccfos/nightingale/tree/main/integrations/kafka/markdown/",
+        "targetBlank": true
+      }
+    ]
+  }
+}

integrations/kafka/markdown/README.md

@@ -0,0 +1,26 @@
+## VictoriaMetrics Dashboard & Alerts
+
+使用[categraf](https://github.com/flashcatcloud/categraf)中[inputs.kafka](https://github.com/flashcatcloud/categraf/tree/main/inputs/kafka)插件采集[kafka](https://kafka.apache.org/)服务监控指标数据:
+
+### 配置文件示例：
+
+下面为配置示例，如果是多个kafka就可以写多个[[instances]];
+
+```toml
+[[instances]]
+log_level = "error"
+kafka_uris = ["192.168.0.250:9092"]
+labels = { cluster="kafka-cluster", service="kafka" }
+```
+
+### 告警规则
+
+![alerts](./alerts..png)
+
+[alerts](../alerts/kafka_by_categraf.json)
+
+### 仪表盘：
+
+![dashboard](./dashboards.png)
+
+[dashboard](../dashboards/kafka_by_categraf.json)

integrations/kubernetes/alerts/apiserver.json

@@ -1,266 +0,0 @@
-[
-  {
-    "name": "KubeClientCertificateExpiration-S2",
-    "note": "A client certificate used to authenticate to the apiserver is expiring in less than 7.0 days.",
-    "severity": 2,
-    "disabled": 0,
-    "prom_for_duration": 0,
-    "prom_ql": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 604800\n",
-    "prom_eval_interval": 15,
-    "enable_stime": "00:00",
-    "enable_etime": "23:59",
-    "enable_days_of_week": [
-      "1",
-      "2",
-      "3",
-      "4",
-      "5",
-      "6",
-      "0"
-    ],
-    "enable_in_bg": 0,
-    "notify_recovered": 1,
-    "notify_channels": [],
-    "notify_repeat_step": 60,
-    "recover_duration": 0,
-    "callbacks": [],
-    "runbook_url": "",
-    "append_tags": []
-  },
-  {
-    "name": "KubeClientCertificateExpiration-S1",
-    "note": "A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours.",
-    "severity": 1,
-    "disabled": 0,
-    "prom_for_duration": 0,
-    "prom_ql": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 86400\n",
-    "prom_eval_interval": 15,
-    "enable_stime": "00:00",
-    "enable_etime": "23:59",
-    "enable_days_of_week": [
-      "1",
-      "2",
-      "3",
-      "4",
-      "5",
-      "6",
-      "0"
-    ],
-    "enable_in_bg": 0,
-    "notify_recovered": 1,
-    "notify_channels": [],
-    "notify_repeat_step": 60,
-    "recover_duration": 0,
-    "callbacks": [],
-    "runbook_url": "",
-    "append_tags": []
-  },
-  {
-    "name": "AggregatedAPIErrors",
-    "note": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. The number of errors have increased for it in the past five minutes. High values indicate that the availability of the service changes too often.",
-    "severity": 2,
-    "disabled": 0,
-    "prom_for_duration": 0,
-    "prom_ql": "sum by(name, namespace)(increase(aggregator_unavailable_apiservice_count[5m])) > 2\n",
-    "prom_eval_interval": 15,
-    "enable_stime": "00:00",
-    "enable_etime": "23:59",
-    "enable_days_of_week": [
-      "1",
-      "2",
-      "3",
-      "4",
-      "5",
-      "6",
-      "0"
-    ],
-    "enable_in_bg": 0,
-    "notify_recovered": 1,
-    "notify_channels": [],
-    "notify_repeat_step": 60,
-    "recover_duration": 0,
-    "callbacks": [],
-    "runbook_url": "",
-    "append_tags": []
-  },
-  {
-    "name": "AggregatedAPIDown",
-    "note": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has been only {{ $value | humanize }}% available over the last 10m.",
-    "severity": 2,
-    "disabled": 0,
-    "prom_for_duration": 300,
-    "prom_ql": "(1 - max by(name, namespace)(avg_over_time(aggregator_unavailable_apiservice[10m]))) * 100 < 85\n",
-    "prom_eval_interval": 15,
-    "enable_stime": "00:00",
-    "enable_etime": "23:59",
-    "enable_days_of_week": [
-      "1",
-      "2",
-      "3",
-      "4",
-      "5",
-      "6",
-      "0"
-    ],
-    "enable_in_bg": 0,
-    "notify_recovered": 1,
-    "notify_channels": [],
-    "notify_repeat_step": 60,
-    "recover_duration": 0,
-    "callbacks": [],
-    "runbook_url": "",
-    "append_tags": []
-  },
-  {
-    "name": "KubeAPIDown",
-    "note": "KubeAPI has disappeared from Prometheus target discovery.",
-    "severity": 1,
-    "disabled": 0,
-    "prom_for_duration": 900,
-    "prom_ql": "absent(up{job=\"apiserver\"} == 1)\n",
-    "prom_eval_interval": 15,
-    "enable_stime": "00:00",
-    "enable_etime": "23:59",
-    "enable_days_of_week": [
-      "1",
-      "2",
-      "3",
-      "4",
-      "5",
-      "6",
-      "0"
-    ],
-    "enable_in_bg": 0,
-    "notify_recovered": 1,
-    "notify_channels": [],
-    "notify_repeat_step": 60,
-    "recover_duration": 0,
-    "callbacks": [],
-    "runbook_url": "",
-    "append_tags": []
-  },
-  {
-    "name": "KubeAPIErrorBudgetBurn-S1-120秒",
-    "note": "The API server is burning too much error budget.",
-    "severity": 1,
-    "disabled": 0,
-    "prom_for_duration": 120,
-    "prom_ql": "sum(apiserver_request:burnrate1h) > (14.40 * 0.01000)\nand\nsum(apiserver_request:burnrate5m) > (14.40 * 0.01000)\n",
-    "prom_eval_interval": 15,
-    "enable_stime": "00:00",
-    "enable_etime": "23:59",
-    "enable_days_of_week": [
-      "1",
-      "2",
-      "3",
-      "4",
-      "5",
-      "6",
-      "0"
-    ],
-    "enable_in_bg": 0,
-    "notify_recovered": 1,
-    "notify_channels": [],
-    "notify_repeat_step": 60,
-    "recover_duration": 0,
-    "callbacks": [],
-    "runbook_url": "",
-    "append_tags": [
-      "long=1h",
-      "short=5m"
-    ]
-  },
-  {
-    "name": "KubeAPIErrorBudgetBurn-S1-900秒",
-    "note": "The API server is burning too much error budget.",
-    "severity": 1,
-    "disabled": 0,
-    "prom_for_duration": 900,
-    "prom_ql": "sum(apiserver_request:burnrate6h) > (6.00 * 0.01000)\nand\nsum(apiserver_request:burnrate30m) > (6.00 * 0.01000)\n",
-    "prom_eval_interval": 15,
-    "enable_stime": "00:00",
-    "enable_etime": "23:59",
-    "enable_days_of_week": [
-      "1",
-      "2",
-      "3",
-      "4",
-      "5",
-      "6",
-      "0"
-    ],
-    "enable_in_bg": 0,
-    "notify_recovered": 1,
-    "notify_channels": [],
-    "notify_repeat_step": 60,
-    "recover_duration": 0,
-    "callbacks": [],
-    "runbook_url": "",
-    "append_tags": [
-      "long=6h",
-      "short=30m"
-    ]
-  },
-  {
-    "name": "KubeAPIErrorBudgetBurn-S2-3600秒",
-    "note": "The API server is burning too much error budget.",
-    "severity": 2,
-    "disabled": 0,
-    "prom_for_duration": 3600,
-    "prom_ql": "sum(apiserver_request:burnrate1d) > (3.00 * 0.01000)\nand\nsum(apiserver_request:burnrate2h) > (3.00 * 0.01000)\n",
-    "prom_eval_interval": 15,
-    "enable_stime": "00:00",
-    "enable_etime": "23:59",
-    "enable_days_of_week": [
-      "1",
-      "2",
-      "3",
-      "4",
-      "5",
-      "6",
-      "0"
-    ],
-    "enable_in_bg": 0,
-    "notify_recovered": 1,
-    "notify_channels": [],
-    "notify_repeat_step": 60,
-    "recover_duration": 0,
-    "callbacks": [],
-    "runbook_url": "",
-    "append_tags": [
-      "long=1d",
-      "short=2h"
-    ]
-  },
-  {
-    "name": "KubeAPIErrorBudgetBurn-S2-10800秒",
-    "note": "The API server is burning too much error budget.",
-    "severity": 2,
-    "disabled": 0,
-    "prom_for_duration": 10800,
-    "prom_ql": "sum(apiserver_request:burnrate3d) > (1.00 * 0.01000)\nand\nsum(apiserver_request:burnrate6h) > (1.00 * 0.01000)\n",
-    "prom_eval_interval": 15,
-    "enable_stime": "00:00",
-    "enable_etime": "23:59",
-    "enable_days_of_week": [
-      "1",
-      "2",
-      "3",
-      "4",
-      "5",
-      "6",
-      "0"
-    ],
-    "enable_in_bg": 0,
-    "notify_recovered": 1,
-    "notify_channels": [],
-    "notify_repeat_step": 60,
-    "recover_duration": 0,
-    "callbacks": [],
-    "runbook_url": "",
-    "append_tags": [
-      "long=3d",
-      "short=6h"
-    ]
-  }
-]

integrations/kubernetes/alerts/prometheus-operator.json

@@ -0,0 +1,562 @@
+[
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "ConfigReloaderSidecarErrors",
+    "note": "Errors encountered while the {{$labels.pod}} config-reloader sidecar attempts to sync config in {{$labels.namespace}} namespace.\nAs a result, configuration for service running in {{$labels.pod}} may be stale and cannot be updated anymore.",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "severities": [
+      2
+    ],
+    "disabled": 1,
+    "prom_for_duration": 600,
+    "prom_ql": "max_over_time(reloader_last_reload_successful{namespace=~\".+\"}[5m]) == 0\n",
+    "rule_config": {
+      "algo_params": null,
+      "inhibit": false,
+      "prom_ql": "",
+      "queries": [
+        {
+          "prom_ql": "max_over_time(reloader_last_reload_successful{namespace=~\".+\"}[5m]) == 0\n",
+          "severity": 2
+        }
+      ],
+      "severity": 0
+    },
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": null
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "PrometheusOperatorListErrors",
+    "note": "Errors while performing List operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "severities": [
+      2
+    ],
+    "disabled": 1,
+    "prom_for_duration": 900,
+    "prom_ql": "(sum by (cluster,controller,namespace) (rate(prometheus_operator_list_operations_failed_total{job=\"prometheus-operator\",namespace=\"monitoring\"}[10m])) / sum by (cluster,controller,namespace) (rate(prometheus_operator_list_operations_total{job=\"prometheus-operator\",namespace=\"monitoring\"}[10m]))) > 0.4\n",
+    "rule_config": {
+      "algo_params": null,
+      "inhibit": false,
+      "prom_ql": "",
+      "queries": [
+        {
+          "prom_ql": "(sum by (cluster,controller,namespace) (rate(prometheus_operator_list_operations_failed_total{job=\"prometheus-operator\",namespace=\"monitoring\"}[10m])) / sum by (cluster,controller,namespace) (rate(prometheus_operator_list_operations_total{job=\"prometheus-operator\",namespace=\"monitoring\"}[10m]))) > 0.4\n",
+          "severity": 2
+        }
+      ],
+      "severity": 0
+    },
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": null
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "PrometheusOperatorNodeLookupErrors",
+    "note": "Errors while reconciling Prometheus in {{ $labels.namespace }} Namespace.",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "severities": [
+      2
+    ],
+    "disabled": 1,
+    "prom_for_duration": 600,
+    "prom_ql": "rate(prometheus_operator_node_address_lookup_errors_total{job=\"prometheus-operator\",namespace=\"monitoring\"}[5m]) > 0.1\n",
+    "rule_config": {
+      "algo_params": null,
+      "inhibit": false,
+      "prom_ql": "",
+      "queries": [
+        {
+          "prom_ql": "rate(prometheus_operator_node_address_lookup_errors_total{job=\"prometheus-operator\",namespace=\"monitoring\"}[5m]) > 0.1\n",
+          "severity": 2
+        }
+      ],
+      "severity": 0
+    },
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": null
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "PrometheusOperatorNotReady",
+    "note": "Prometheus operator in {{ $labels.namespace }} namespace isn't ready to reconcile {{ $labels.controller }} resources.",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "severities": [
+      2
+    ],
+    "disabled": 1,
+    "prom_for_duration": 300,
+    "prom_ql": "min by (cluster,controller,namespace) (max_over_time(prometheus_operator_ready{job=\"prometheus-operator\",namespace=\"monitoring\"}[5m]) == 0)\n",
+    "rule_config": {
+      "algo_params": null,
+      "inhibit": false,
+      "prom_ql": "",
+      "queries": [
+        {
+          "prom_ql": "min by (cluster,controller,namespace) (max_over_time(prometheus_operator_ready{job=\"prometheus-operator\",namespace=\"monitoring\"}[5m]) == 0)\n",
+          "severity": 2
+        }
+      ],
+      "severity": 0
+    },
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": null
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "PrometheusOperatorReconcileErrors",
+    "note": "{{ $value | humanizePercentage }} of reconciling operations failed for {{ $labels.controller }} controller in {{ $labels.namespace }} namespace.",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "severities": [
+      2
+    ],
+    "disabled": 1,
+    "prom_for_duration": 600,
+    "prom_ql": "(sum by (cluster,controller,namespace) (rate(prometheus_operator_reconcile_errors_total{job=\"prometheus-operator\",namespace=\"monitoring\"}[5m]))) / (sum by (cluster,controller,namespace) (rate(prometheus_operator_reconcile_operations_total{job=\"prometheus-operator\",namespace=\"monitoring\"}[5m]))) > 0.1\n",
+    "rule_config": {
+      "algo_params": null,
+      "inhibit": false,
+      "prom_ql": "",
+      "queries": [
+        {
+          "prom_ql": "(sum by (cluster,controller,namespace) (rate(prometheus_operator_reconcile_errors_total{job=\"prometheus-operator\",namespace=\"monitoring\"}[5m]))) / (sum by (cluster,controller,namespace) (rate(prometheus_operator_reconcile_operations_total{job=\"prometheus-operator\",namespace=\"monitoring\"}[5m]))) > 0.1\n",
+          "severity": 2
+        }
+      ],
+      "severity": 0
+    },
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": null
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "PrometheusOperatorRejectedResources",
+    "note": "Prometheus operator in {{ $labels.namespace }} namespace rejected {{ printf \"%0.0f\" $value }} {{ $labels.controller }}/{{ $labels.resource }} resources.",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "severities": [
+      2
+    ],
+    "disabled": 1,
+    "prom_for_duration": 300,
+    "prom_ql": "min_over_time(prometheus_operator_managed_resources{state=\"rejected\",job=\"prometheus-operator\",namespace=\"monitoring\"}[5m]) > 0\n",
+    "rule_config": {
+      "algo_params": null,
+      "inhibit": false,
+      "prom_ql": "",
+      "queries": [
+        {
+          "prom_ql": "min_over_time(prometheus_operator_managed_resources{state=\"rejected\",job=\"prometheus-operator\",namespace=\"monitoring\"}[5m]) > 0\n",
+          "severity": 2
+        }
+      ],
+      "severity": 0
+    },
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": null
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "PrometheusOperatorSyncFailed",
+    "note": "Controller {{ $labels.controller }} in {{ $labels.namespace }} namespace fails to reconcile {{ $value }} objects.",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "severities": [
+      2
+    ],
+    "disabled": 1,
+    "prom_for_duration": 600,
+    "prom_ql": "min_over_time(prometheus_operator_syncs{status=\"failed\",job=\"prometheus-operator\",namespace=\"monitoring\"}[5m]) > 0\n",
+    "rule_config": {
+      "algo_params": null,
+      "inhibit": false,
+      "prom_ql": "",
+      "queries": [
+        {
+          "prom_ql": "min_over_time(prometheus_operator_syncs{status=\"failed\",job=\"prometheus-operator\",namespace=\"monitoring\"}[5m]) > 0\n",
+          "severity": 2
+        }
+      ],
+      "severity": 0
+    },
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": null
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "PrometheusOperatorWatchErrors",
+    "note": "Errors while performing watch operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "severities": [
+      2
+    ],
+    "disabled": 1,
+    "prom_for_duration": 900,
+    "prom_ql": "(sum by (cluster,controller,namespace) (rate(prometheus_operator_watch_operations_failed_total{job=\"prometheus-operator\",namespace=\"monitoring\"}[5m])) / sum by (cluster,controller,namespace) (rate(prometheus_operator_watch_operations_total{job=\"prometheus-operator\",namespace=\"monitoring\"}[5m]))) > 0.4\n",
+    "rule_config": {
+      "algo_params": null,
+      "inhibit": false,
+      "prom_ql": "",
+      "queries": [
+        {
+          "prom_ql": "(sum by (cluster,controller,namespace) (rate(prometheus_operator_watch_operations_failed_total{job=\"prometheus-operator\",namespace=\"monitoring\"}[5m])) / sum by (cluster,controller,namespace) (rate(prometheus_operator_watch_operations_total{job=\"prometheus-operator\",namespace=\"monitoring\"}[5m]))) > 0.4\n",
+          "severity": 2
+        }
+      ],
+      "severity": 0
+    },
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": null
+  }
+]

integrations/kubernetes/record-rules/kube-controller-plane.json

@@ -0,0 +1,322 @@
+[
+  {
+    "cluster": "",
+    "name": ":node_memory_MemAvailable_bytes:sum",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "sum(\n  node_memory_MemAvailable_bytes{job=\"node-exporter\"} or\n  (\n    node_memory_Buffers_bytes{job=\"node-exporter\"} +\n    node_memory_Cached_bytes{job=\"node-exporter\"} +\n    node_memory_MemFree_bytes{job=\"node-exporter\"} +\n    node_memory_Slab_bytes{job=\"node-exporter\"}\n  )\n) by (cluster)\n",
+    "prom_eval_interval": 15,
+    "append_tags": []
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:availability30d",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "1 - (\n  (\n    # write too slow\n    sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n    -\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"})\n  ) +\n  (\n    # read too slow\n    sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n    -\n    (\n      (\n        sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n      +\n      sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"})\n    )\n  ) +\n  # errors\n  sum by (cluster) (code:apiserver_request_total:increase30d{code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d)\n",
+    "prom_eval_interval": 180,
+    "append_tags": [
+      "verb=all"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:availability30d",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "1 - (\n  sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n  -\n  (\n    # too slow\n    (\n      sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n      or\n      vector(0)\n    )\n    +\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n    +\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"})\n  )\n  +\n  # errors\n  sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\"})\n",
+    "prom_eval_interval": 180,
+    "append_tags": [
+      "verb=read"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:availability30d",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "1 - (\n  (\n    # too slow\n    sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n    -\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"})\n  )\n  +\n  # errors\n  sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"write\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"write\"})\n",
+    "prom_eval_interval": 180,
+    "append_tags": [
+      "verb=write"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:burnrate1d",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[1d]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[1d]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[1d]))\n      +\n      sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[1d]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "verb=read"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:burnrate1d",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[1d]))\n    -\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[1d]))\n  )\n  +\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1d]))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "verb=write"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:burnrate1h",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[1h]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[1h]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[1h]))\n      +\n      sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[1h]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "verb=read"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:burnrate1h",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[1h]))\n    -\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[1h]))\n  )\n  +\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1h]))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "verb=write"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:burnrate2h",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[2h]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[2h]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[2h]))\n      +\n      sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[2h]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "verb=read"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:burnrate2h",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[2h]))\n    -\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[2h]))\n  )\n  +\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[2h]))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "verb=write"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:burnrate30m",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[30m]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[30m]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[30m]))\n      +\n      sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[30m]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "verb=read"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:burnrate30m",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[30m]))\n    -\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[30m]))\n  )\n  +\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[30m]))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "verb=write"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:burnrate3d",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[3d]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[3d]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[3d]))\n      +\n      sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[3d]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "verb=read"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:burnrate3d",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[3d]))\n    -\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[3d]))\n  )\n  +\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[3d]))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "verb=write"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:burnrate5m",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[5m]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[5m]))\n      +\n      sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[5m]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "verb=read"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:burnrate5m",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))\n    -\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[5m]))\n  )\n  +\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "verb=write"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:burnrate6h",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[6h]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[6h]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[6h]))\n      +\n      sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[6h]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "verb=read"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "apiserver_request:burnrate6h",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[6h]))\n    -\n    sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[6h]))\n  )\n  +\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[6h]))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "verb=write"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "kube_pod_container_resource_limits{resource=\"cpu\",job=\"kube-state-metrics\"}  * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n  )\n",
+    "prom_eval_interval": 15,
+    "append_tags": []
+  },
+  {
+    "cluster": "",
+    "name": "cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "kube_pod_container_resource_requests{resource=\"cpu\",job=\"kube-state-metrics\"}  * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n",
+    "prom_eval_interval": 15,
+    "append_tags": []
+  },
+  {
+    "cluster": "",
+    "name": "cluster:namespace:pod_memory:active:kube_pod_container_resource_limits",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "kube_pod_container_resource_limits{resource=\"memory\",job=\"kube-state-metrics\"}  * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n",
+    "prom_eval_interval": 15,
+    "append_tags": []
+  },
+  {
+    "cluster": "",
+    "name": "cluster:namespace:pod_memory:active:kube_pod_container_resource_requests",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "kube_pod_container_resource_requests{resource=\"memory\",job=\"kube-state-metrics\"}  * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n",
+    "prom_eval_interval": 15,
+    "append_tags": []
+  },
+  {
+    "cluster": "",
+    "name": "cluster:node_cpu:ratio_rate5m",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "avg by (cluster) (\n  node:node_cpu_utilization:ratio_rate5m\n)\n",
+    "prom_eval_interval": 15,
+    "append_tags": []
+  },
+  {
+    "cluster": "",
+    "name": "cluster_quantile:apiserver_request_slo_duration_seconds:histogram_quantile",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))) > 0\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "quantile=0.99",
+      "verb=read"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "cluster_quantile:apiserver_request_slo_duration_seconds:histogram_quantile",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_slo_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))) > 0\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "quantile=0.99",
+      "verb=write"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{job=\"kube-scheduler\"}[5m])) without(instance, pod))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "quantile=0.99"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "histogram_quantile(0.9, sum(rate(scheduler_binding_duration_seconds_bucket{job=\"kube-scheduler\"}[5m])) without(instance, pod))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "quantile=0.9"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "histogram_quantile(0.5, sum(rate(scheduler_binding_duration_seconds_bucket{job=\"kube-scheduler\"}[5m])) without(instance, pod))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "quantile=0.5"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job=\"kube-scheduler\"}[5m])) without(instance, pod))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "quantile=0.99"
+    ]
+  },
+  {
+    "cluster": "",
+    "name": "cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "histogram_quantile(0.9, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job=\"kube-scheduler\"}[5m])) without(instance, pod))\n",
+    "prom_eval_interval": 15,
+    "append_tags": [
+      "quantile=0.9"
+    ]
+  }
+]

integrations/kubernetes/record-rules/node-exporer.json

@@ -0,0 +1,74 @@
+[
+  {
+    "cluster": "",
+    "name": "cluster:node_cpu:ratio",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "cluster:node_cpu:sum_rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu))",
+    "prom_eval_interval": 15,
+    "append_tags": []
+  },
+  {
+    "cluster": "",
+    "name": "cluster:node_cpu:sum_rate5m",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "sum(rate(node_cpu_seconds_total{mode!=\"idle\",mode!=\"iowait\",mode!=\"steal\"}[5m]))",
+    "prom_eval_interval": 15,
+    "append_tags": []
+  },
+  {
+    "cluster": "",
+    "name": "count:up0",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "count without(instance, pod, node) (up == 0)",
+    "prom_eval_interval": 15,
+    "append_tags": []
+  },
+  {
+    "cluster": "",
+    "name": "count:up1",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "count without(instance, pod, node) (up == 1)",
+    "prom_eval_interval": 15,
+    "append_tags": []
+  },
+  {
+    "cluster": "",
+    "name": "instance:node_cpu:rate:sum",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "sum(rate(node_cpu_seconds_total{mode!=\"idle\",mode!=\"iowait\",mode!=\"steal\"}[3m])) BY (instance)",
+    "prom_eval_interval": 15,
+    "append_tags": []
+  },
+  {
+    "cluster": "",
+    "name": "instance:node_cpu:ratio",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "sum(rate(node_cpu_seconds_total{mode!=\"idle\",mode!=\"iowait\",mode!=\"steal\"}[5m])) WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance)",
+    "prom_eval_interval": 15,
+    "append_tags": []
+  },
+  {
+    "cluster": "",
+    "name": "instance:node_network_receive_bytes:rate:sum",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "sum(rate(node_network_receive_bytes_total[3m])) BY (instance)",
+    "prom_eval_interval": 15,
+    "append_tags": []
+  },
+  {
+    "cluster": "",
+    "name": "instance:node_network_transmit_bytes:rate:sum",
+    "note": "",
+    "disabled": 0,
+    "prom_ql": "sum(rate(node_network_transmit_bytes_total[3m])) BY (instance)",
+    "prom_eval_interval": 15,
+    "append_tags": []
+  }
+]

integrations/linux/alerts/linux_by_categraf.json

@@ -1,7 +1,141 @@
 [
   {
-    "cate": "host",
-    "datasource_ids": null,
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "Hard disk - expected to be written full in 4 hours - categraf",
+    "note": "",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 1,
+    "severities": [
+      1
+    ],
+    "disabled": 1,
+    "prom_for_duration": 60,
+    "prom_ql": "predict_linear(disk_free[1h], 4*3600) < 0",
+    "rule_config": {
+      "algo_params": null,
+      "inhibit": false,
+      "prom_ql": "",
+      "queries": [
+        {
+          "prom_ql": "predict_linear(disk_free[1h], 4*3600) < 0",
+          "severity": 1
+        }
+      ],
+      "severity": 0
+    },
+    "prom_eval_interval": 15,
+    "enable_stime": "",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": null,
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [
+      "email",
+      "dingtalk",
+      "wecom"
+    ],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": null
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "Hard disk - IO is a bit busy - categraf",
+    "note": "",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "severities": [
+      2
+    ],
+    "disabled": 0,
+    "prom_for_duration": 60,
+    "prom_ql": "rate(diskio_io_time[1m])/10 > 99",
+    "rule_config": {
+      "algo_params": null,
+      "inhibit": false,
+      "prom_ql": "",
+      "queries": [
+        {
+          "prom_ql": "rate(diskio_io_time[1m])/10 > 99",
+          "severity": 2
+        }
+      ],
+      "severity": 0
+    },
+    "prom_eval_interval": 15,
+    "enable_stime": "",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": null,
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [
+      "email",
+      "dingtalk",
+      "wecom"
+    ],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": null
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
     "name": "Lost connection with monitoring target - categraf",
     "note": "",
     "prod": "host",
@@ -9,6 +143,9 @@
     "algo_params": null,
     "delay": 0,
     "severity": 0,
+    "severities": [
+      0
+    ],
     "disabled": 0,
     "prom_for_duration": 0,
     "prom_ql": "",
@@ -30,23 +167,15 @@
       ]
     },
     "prom_eval_interval": 15,
-    "enable_stime": "00:00",
+    "enable_stime": "",
     "enable_stimes": [
       "00:00"
     ],
-    "enable_etime": "23:59",
+    "enable_etime": "",
     "enable_etimes": [
       "23:59"
     ],
-    "enable_days_of_week": [
-      "1",
-      "2",
-      "3",
-      "4",
-      "5",
-      "6",
-      "0"
-    ],
+    "enable_days_of_week": null,
     "enable_days_of_weeks": [
       [
         "1",
@@ -69,47 +198,55 @@
     "append_tags": [],
     "annotations": {}
   },
-    {
-      "name": "Machine load - high memory, please pay attention - categraf",
-      "note": "",
-      "severity": 2,
-      "disabled": 0,
-      "prom_for_duration": 60,
-      "prom_ql": "mem_available_percent < 25",
-      "prom_eval_interval": 15,
-      "enable_stime": "00:00",
-      "enable_etime": "23:59",
-      "enable_days_of_week": [
-        "1",
-        "2",
-        "3",
-        "4",
-        "5",
-        "6",
-        "0"
-      ],
-      "notify_recovered": 1,
-      "notify_channels": [
-        "email",
-        "dingtalk",
-        "wecom"
-      ],
-      "notify_repeat_step": 60,
-      "callbacks": [],
-      "runbook_url": "",
-      "append_tags": []
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "Machine load - high memory, please pay attention - categraf",
+    "note": "",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 0,
+    "severities": [
+      3,
+      2,
+      1
+    ],
+    "disabled": 0,
+    "prom_for_duration": 60,
+    "prom_ql": "",
+    "rule_config": {
+      "inhibit": true,
+      "queries": [
+        {
+          "prom_ql": "mem_available_percent < 25",
+          "severity": 3
+        },
+        {
+          "prom_ql": "mem_available_percent < 15",
+          "severity": 2
+        },
+        {
+          "prom_ql": "mem_available_percent < 5",
+          "severity": 1
+        }
+      ]
     },
-    {
-      "name": "Hard disk - IO is a bit busy - categraf",
-      "note": "",
-      "severity": 2,
-      "disabled": 0,
-      "prom_for_duration": 60,
-      "prom_ql": "rate(diskio_io_time[1m])/10 > 99",
-      "prom_eval_interval": 15,
-      "enable_stime": "00:00",
-      "enable_etime": "23:59",
-      "enable_days_of_week": [
+    "prom_eval_interval": 15,
+    "enable_stime": "",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": null,
+    "enable_days_of_weeks": [
+      [
         "1",
         "2",
         "3",
@@ -117,29 +254,65 @@
         "5",
         "6",
         "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [
+      "email",
+      "dingtalk",
+      "wecom"
+    ],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": {}
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "number of TME_WAIT exceeds 20,000 - categraf",
+    "note": "",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "severities": [
+      2
+    ],
+    "disabled": 0,
+    "prom_for_duration": 60,
+    "prom_ql": "netstat_tcp_time_wait > 20000",
+    "rule_config": {
+      "algo_params": null,
+      "inhibit": false,
+      "prom_ql": "",
+      "queries": [
+        {
+          "prom_ql": "netstat_tcp_time_wait > 20000",
+          "severity": 2
+        }
       ],
-      "notify_recovered": 1,
-      "notify_channels": [
-        "email",
-        "dingtalk",
-        "wecom"
-      ],
-      "notify_repeat_step": 60,
-      "callbacks": [],
-      "runbook_url": "",
-      "append_tags": []
+      "severity": 0
     },
-    {
-      "name": "Hard disk - expected to be written full in 4 hours - categraf",
-      "note": "",
-      "severity": 1,
-      "disabled": 0,
-      "prom_for_duration": 60,
-      "prom_ql": "predict_linear(disk_free[1h], 4*3600) < 0",
-      "prom_eval_interval": 15,
-      "enable_stime": "00:00",
-      "enable_etime": "23:59",
-      "enable_days_of_week": [
+    "prom_eval_interval": 15,
+    "enable_stime": "",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": null,
+    "enable_days_of_weeks": [
+      [
         "1",
         "2",
         "3",
@@ -147,29 +320,65 @@
         "5",
         "6",
         "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [
+      "email",
+      "dingtalk",
+      "wecom"
+    ],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": null
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "packet loss in the inbound direction - categraf",
+    "note": "",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 3,
+    "severities": [
+      3
+    ],
+    "disabled": 0,
+    "prom_for_duration": 60,
+    "prom_ql": "increase(net_drop_in[1m]) > 0",
+    "rule_config": {
+      "algo_params": null,
+      "inhibit": false,
+      "prom_ql": "",
+      "queries": [
+        {
+          "prom_ql": "increase(net_drop_in[1m]) > 0",
+          "severity": 3
+        }
       ],
-      "notify_recovered": 1,
-      "notify_channels": [
-        "email",
-        "dingtalk",
-        "wecom"
-      ],
-      "notify_repeat_step": 60,
-      "callbacks": [],
-      "runbook_url": "",
-      "append_tags": []
+      "severity": 0
     },
-    {
-      "name": "packet loss in the inbound direction - categraf",
-      "note": "",
-      "severity": 3,
-      "disabled": 0,
-      "prom_for_duration": 60,
-      "prom_ql": "increase(net_drop_in[1m]) > 0",
-      "prom_eval_interval": 15,
-      "enable_stime": "00:00",
-      "enable_etime": "23:59",
-      "enable_days_of_week": [
+    "prom_eval_interval": 15,
+    "enable_stime": "",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": null,
+    "enable_days_of_weeks": [
+      [
         "1",
         "2",
         "3",
@@ -177,29 +386,65 @@
         "5",
         "6",
         "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [
+      "email",
+      "dingtalk",
+      "wecom"
+    ],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": null
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "packet loss in the outbound direction - categraf",
+    "note": "",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 3,
+    "severities": [
+      3
+    ],
+    "disabled": 0,
+    "prom_for_duration": 60,
+    "prom_ql": "increase(net_drop_out[1m]) > 0",
+    "rule_config": {
+      "algo_params": null,
+      "inhibit": false,
+      "prom_ql": "",
+      "queries": [
+        {
+          "prom_ql": "increase(net_drop_out[1m]) > 0",
+          "severity": 3
+        }
       ],
-      "notify_recovered": 1,
-      "notify_channels": [
-        "email",
-        "dingtalk",
-        "wecom"
-      ],
-      "notify_repeat_step": 60,
-      "callbacks": [],
-      "runbook_url": "",
-      "append_tags": []
+      "severity": 0
     },
-    {
-      "name": "packet loss in the outbound direction - categraf",
-      "note": "",
-      "severity": 3,
-      "disabled": 0,
-      "prom_for_duration": 60,
-      "prom_ql": "increase(net_drop_out[1m]) > 0",
-      "prom_eval_interval": 15,
-      "enable_stime": "00:00",
-      "enable_etime": "23:59",
-      "enable_days_of_week": [
+    "prom_eval_interval": 15,
+    "enable_stime": "",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": null,
+    "enable_days_of_weeks": [
+      [
         "1",
         "2",
         "3",
@@ -207,47 +452,159 @@
         "5",
         "6",
         "0"
-      ],
-      "notify_recovered": 1,
-      "notify_channels": [
-        "email",
-        "dingtalk",
-        "wecom"
-      ],
-      "notify_repeat_step": 60,
-      "callbacks": [],
-      "runbook_url": "",
-      "append_tags": []
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [
+      "email",
+      "dingtalk",
+      "wecom"
+    ],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": null
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "大于200G的盘，空间不足了",
+    "note": "",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 0,
+    "severities": [
+      3,
+      2,
+      1
+    ],
+    "disabled": 0,
+    "prom_for_duration": 60,
+    "prom_ql": "",
+    "rule_config": {
+      "inhibit": true,
+      "queries": [
+        {
+          "prom_ql": "disk_free/1024/1024/1024 < 20 and disk_total/1024/1024/1024 >= 200",
+          "severity": 3
+        },
+        {
+          "prom_ql": "disk_free/1024/1024/1024 < 10 and disk_total/1024/1024/1024 >= 200",
+          "severity": 2
+        },
+        {
+          "prom_ql": "disk_free/1024/1024/1024 < 2 and disk_total/1024/1024/1024 >= 200",
+          "severity": 1
+        }
+      ]
     },
-    {
-      "name": "number of TME_WAIT exceeds 20,000 - categraf",
-      "note": "",
-      "severity": 2,
-      "disabled": 0,
-      "prom_for_duration": 60,
-      "prom_ql": "netstat_tcp_time_wait > 20000",
-      "prom_eval_interval": 15,
-      "enable_stime": "00:00",
-      "enable_etime": "23:59",
-      "enable_days_of_week": [
+    "prom_eval_interval": 30,
+    "enable_stime": "",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": null,
+    "enable_days_of_weeks": [
+      [
+        "0",
         "1",
         "2",
         "3",
         "4",
         "5",
-        "6",
-        "0"
-      ],
-      "notify_recovered": 1,
-      "notify_channels": [
-        "email",
-        "dingtalk",
-        "wecom"
-      ],
-      "notify_repeat_step": 60,
-      "callbacks": [],
-      "runbook_url": "",
-      "append_tags": []
-    }
-]
-  
+        "6"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": {}
+  },
+  {
+    "cate": "prometheus",
+    "datasource_ids": [
+      0
+    ],
+    "name": "小于200G的盘，空间不足了",
+    "note": "",
+    "prod": "metric",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 0,
+    "severities": [
+      3,
+      2,
+      1
+    ],
+    "disabled": 0,
+    "prom_for_duration": 60,
+    "prom_ql": "",
+    "rule_config": {
+      "inhibit": true,
+      "queries": [
+        {
+          "prom_ql": "disk_used_percent > 90 and disk_total/1024/1024/1024 < 200",
+          "severity": 3
+        },
+        {
+          "prom_ql": "disk_used_percent > 95 and disk_total/1024/1024/1024 < 200",
+          "severity": 2
+        },
+        {
+          "prom_ql": "disk_used_percent > 99 and disk_total/1024/1024/1024 < 200",
+          "severity": 1
+        }
+      ]
+    },
+    "prom_eval_interval": 30,
+    "enable_stime": "",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": null,
+    "enable_days_of_weeks": [
+      [
+        "0",
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": {}
+  }
+]

integrations/n9e/dashboards/n9e_v6.json

@@ -0,0 +1,259 @@
+{
+    "name": "nightingale v6",
+    "tags": "",
+    "ident": "",
+    "configs": {
+        "panels": [
+            {
+                "type": "timeseries",
+                "id": "53fcb9dc-23f9-41e0-bc5e-121eed14c3a4",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 0,
+                    "y": 0,
+                    "i": "53fcb9dc-23f9-41e0-bc5e-121eed14c3a4",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "targets": [
+                    {
+                        "expr": "irate(n9e_pushgw_samples_received_total[1m])",
+                        "refId": "A"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "number of data points received per second",
+                "maxPerRow": 4,
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "spanNulls": false,
+                    "lineWidth": 1,
+                    "fillOpacity": 0.5,
+                    "gradientMode": "none",
+                    "stack": "off",
+                    "scaleDistribution": {
+                        "type": "linear"
+                    }
+                }
+            },
+            {
+                "type": "timeseries",
+                "id": "caf23e58-d907-42b0-9ed6-722c8c6f3c5f",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 12,
+                    "y": 0,
+                    "i": "ad1af16c-de0c-45f4-8875-cea4e85d51d0",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "targets": [
+                    {
+                        "expr": "n9e_alert_alert_queue_size",
+                        "refId": "A"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "queue length of alarm events",
+                "maxPerRow": 4,
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "spanNulls": false,
+                    "lineWidth": 1,
+                    "fillOpacity": 0.5,
+                    "gradientMode": "none",
+                    "stack": "off",
+                    "scaleDistribution": {
+                        "type": "linear"
+                    }
+                }
+            },
+            {
+                "type": "timeseries",
+                "id": "d7c253bd-05f3-4b43-a7bd-34ffacd16fbd",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 0,
+                    "y": 4,
+                    "i": "d7c253bd-05f3-4b43-a7bd-34ffacd16fbd",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "n9e_cron_sync_number"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "last sync records count",
+                "maxPerRow": 4,
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "desc"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "spanNulls": false,
+                    "lineWidth": 1,
+                    "fillOpacity": 0.5,
+                    "gradientMode": "none",
+                    "stack": "off",
+                    "scaleDistribution": {
+                        "type": "linear"
+                    }
+                }
+            },
+            {
+                "type": "timeseries",
+                "id": "7c725076-a986-4414-abd4-ce06605665b5",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 12,
+                    "y": 4,
+                    "i": "7c725076-a986-4414-abd4-ce06605665b5",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${prom}",
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "n9e_cron_duration"
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "last sync time duration",
+                "maxPerRow": 4,
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {
+                        "util": "milliseconds"
+                    },
+                    "thresholds": {
+                        "steps": [
+                            {
+                                "color": "#634CD9",
+                                "value": null,
+                                "type": "base"
+                            }
+                        ]
+                    }
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "spanNulls": false,
+                    "lineWidth": 1,
+                    "fillOpacity": 0.5,
+                    "gradientMode": "none",
+                    "stack": "off",
+                    "scaleDistribution": {
+                        "type": "linear"
+                    }
+                }
+            }
+        ],
+        "var": [
+            {
+                "definition": "prometheus",
+                "name": "prom",
+                "type": "datasource"
+            }
+        ],
+        "version": "3.0.0"
+    }
+}