update dockerfile for github-action

* fix: get engine cluster list

.goreleaser.yaml

@@ -115,7 +115,7 @@ dockers:
     goarch: arm64
     ids:
       - build
-    dockerfile: docker/Dockerfile.goreleaser
+    dockerfile: docker/Dockerfile.goreleaser.arm64
     extra_files:
       - pub
       - etc

alert/sender/callback.go

@@ -154,6 +154,7 @@ func handleIbex(ctx *ctx.Context, url string, event *models.AlertCurEvent, targe
 	// write db
 	record := models.TaskRecord{
 		Id:           res.Dat,
+		EventId:      event.Id,
 		GroupId:      tpl.GroupId,
 		IbexAddress:  ibexConf.Address,
 		IbexAuthUser: ibexConf.BasicAuthUser,

alert/sender/dingtalk.go

@@ -49,7 +49,7 @@ func (ds *DingtalkSender) Send(ctx MessageContext) {
 			body = dingtalk{
 				Msgtype: "markdown",
 				Markdown: dingtalkMarkdown{
-					Title: ctx.Rule.Name,
+					Title: ctx.Event.RuleName,
 					Text:  message,
 				},
 			}
@@ -57,7 +57,7 @@ func (ds *DingtalkSender) Send(ctx MessageContext) {
 			body = dingtalk{
 				Msgtype: "markdown",
 				Markdown: dingtalkMarkdown{
-					Title: ctx.Rule.Name,
+					Title: ctx.Event.RuleName,
 					Text:  message + "\n" + strings.Join(ats, " "),
 				},
 				At: dingtalkAt{

alert/sender/email.go

@@ -31,7 +31,7 @@ func (es *EmailSender) Send(ctx MessageContext) {
 	if es.subjectTpl != nil {
 		subject = BuildTplMessage(es.subjectTpl, ctx.Event)
 	} else {
-		subject = ctx.Rule.Name
+		subject = ctx.Event.RuleName
 	}
 	content := BuildTplMessage(es.contentTpl, ctx.Event)
 	es.WriteEmail(subject, content, tos)

center/center.go

@@ -78,7 +78,7 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 	writers := writer.NewWriters(config.Pushgw)
 
 	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)
+	centerRouter := centerrt.New(config.HTTP, config.Center, cconf.Operations, dsCache, notifyConfigCache, promClients, redis, sso, ctx, metas, 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

@@ -4,6 +4,7 @@ import (
 	"fmt"
 	"net/http"
 	"path"
+	"runtime"
 	"strings"
 	"time"
 
@@ -31,12 +32,13 @@ type Router struct {
 	PromClients       *prom.PromClientMap
 	Redis             storage.Redis
 	MetaSet           *metas.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) *Router {
+	pc *prom.PromClientMap, redis storage.Redis, sso *sso.SsoClient, ctx *ctx.Context, metaSet *metas.Set, tc *memsto.TargetCacheType) *Router {
 	return &Router{
 		HTTP:              httpConfig,
 		Center:            center,
@@ -46,6 +48,7 @@ func New(httpConfig httpx.Config, center cconf.Center, operations cconf.Operatio
 		PromClients:       pc,
 		Redis:             redis,
 		MetaSet:           metaSet,
+		TargetCache:       tc,
 		Sso:               sso,
 		Ctx:               ctx,
 	}
@@ -93,12 +96,18 @@ func (rt *Router) configNoRoute(r *gin.Engine) {
 		switch suffix {
 		case "png", "jpeg", "jpg", "svg", "ico", "gif", "css", "js", "html", "htm", "gz", "zip", "map":
 			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:
 			cwdarr := []string{"/"}
+			if runtime.GOOS == "windows" {
+				cwdarr[0] = ""
+			}
 			cwdarr = append(cwdarr, strings.Split(runner.Cwd, "/")...)
 			cwdarr = append(cwdarr, "pub")
 			cwdarr = append(cwdarr, "index.html")

center/router/router_heartbeat.go

@@ -36,6 +36,17 @@ func (rt *Router) heartbeat(c *gin.Context) {
 	ginx.Dangerous(err)
 
 	req.Offset = (time.Now().UnixMilli() - req.UnixTime)
+	req.RemoteAddr = c.ClientIP()
 	rt.MetaSet.Set(req.Hostname, req)
-	ginx.NewRender(c).Message(nil)
+
+	gid := ginx.QueryInt64(c, "gid", 0)
+
+	if gid != 0 {
+		target, has := rt.TargetCache.Get(req.Hostname)
+		if has && target.GroupId != gid {
+			err = models.TargetUpdateBgid(rt.Ctx, []string{req.Hostname}, gid, false)
+		}
+	}
+
+	ginx.NewRender(c).Message(err)
 }

center/router/router_notify_tpl.go

@@ -3,6 +3,7 @@ package router
 import (
 	"bytes"
 	"encoding/json"
+	"fmt"
 	"html/template"
 
 	"github.com/ccfos/nightingale/v6/center/cconf"
@@ -22,6 +23,11 @@ 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.NewRender(c).Message(f.UpdateContent(rt.Ctx))
 }
 
@@ -29,9 +35,25 @@ 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.NewRender(c).Message(f.Update(rt.Ctx))
 }
 
+func templateValidate(f models.NotifyTpl) error {
+	if f.Content == "" {
+		return nil
+	}
+	if _, err := template.New(f.Channel).Funcs(tplx.TemplateFuncMap).Parse(f.Content); err != nil {
+		return fmt.Errorf("notify template verify illegal:%s", err.Error())
+	}
+
+	return nil
+}
+
 func (rt *Router) notifyTplPreview(c *gin.Context) {
 	var event models.AlertCurEvent
 	err := json.Unmarshal([]byte(cconf.EVENT_EXAMPLE), &event)

cli/upgrade/upgrade.sql

@@ -13,6 +13,7 @@ alter table `board` add built_in tinyint(1) not null default 0 comment '0:false
 alter table `board` add hide tinyint(1) not null default 0 comment '0:false 1:true';
 
 alter table `chart_share` add datasource_id bigint unsigned not null default 0;
+alter table `chart_share` drop dashboard_id;
 
 alter table `alert_rule` add datasource_ids varchar(255) not null default '';
 alter table `alert_rule` add rule_config text not null comment 'rule_config';
@@ -41,6 +42,9 @@ alter table `alert_his_event` add annotations text not null comment 'annotations
 alter table `alert_his_event` add rule_config text not null comment 'rule_config';
 
 alter table `alerting_engines` add datasource_id bigint unsigned not null default 0;
+alter table `alerting_engines` change cluster engine_cluster varchar(128) not null default '' comment 'n9e engine cluster';
+
+alter table `task_record` add event_id bigint not null comment 'event id' default 0;
 
 CREATE TABLE `datasource`
 (

docker/Dockerfile.goreleaser

@@ -1,15 +1,12 @@
-FROM --platform=$BUILDPLATFORM python:3-slim
+FROM --platform=$TARGETPLATFORM python:3-slim
 
 
 WORKDIR /app
-ADD n9e /app
-ADD etc /app
-RUN mkdir -p /app/integrations
+ADD n9e /app/
+ADD etc /app/
 ADD integrations /app/integrations/
-ADD http://download.flashcat.cloud/wait /wait
-RUN mkdir -p /app/pub && chmod +x /wait
+ADD --chmod=755 https://github.com/ufoscout/docker-compose-wait/releases/download/2.11.0/wait_x86_64 /wait
 ADD pub /app/pub/
-RUN chmod +x n9e
 
 EXPOSE 17000
 

docker/Dockerfile.goreleaser.arm64

@@ -0,0 +1,13 @@
+FROM --platform=$TARGETPLATFORM python:3-slim
+
+
+WORKDIR /app
+ADD n9e /app/
+ADD etc /app/
+ADD integrations /app/integrations/
+ADD --chmod=755 https://github.com/ufoscout/docker-compose-wait/releases/download/2.11.0/wait_aarch64 /wait
+ADD pub /app/pub/
+
+EXPOSE 17000
+
+CMD ["/app/n9e", "-h"]

docker/experience_pg_vm/initsql_for_postgres/a-n9e-for-Postgres.sql

@@ -651,6 +651,7 @@ COMMENT ON COLUMN task_tpl_host.host IS 'ip or hostname';
 CREATE TABLE task_record
 (
     id bigint  not null ,
+    event_id bigint not null default 0,
     group_id bigint not null ,
     ibex_address   varchar(128) not null,
     ibex_auth_user varchar(128) not null default '',
@@ -669,22 +670,23 @@ CREATE TABLE task_record
 ) ;
 CREATE INDEX task_record_cg_idx ON task_record (create_at, group_id);
 CREATE INDEX task_record_create_by_idx ON task_record (create_by);
+CREATE INDEX task_record_event_id_idx ON task_record (event_id);
 COMMENT ON COLUMN task_record.id IS 'ibex task id';
 COMMENT ON COLUMN task_record.group_id IS 'busi group id';
-
+COMMENT ON COLUMN task_record.event_id IS 'event id';
 
 CREATE TABLE alerting_engines
 (
     id serial,
     instance varchar(128) not null default '' ,
     datasource_id bigint not null default 0 ,
-    cluster varchar(128) not null default '' ,
+    engine_cluster varchar(128) not null default '' ,
     clock bigint not null,
     PRIMARY KEY (id)
 ) ;
 COMMENT ON COLUMN alerting_engines.instance IS 'instance identification, e.g. 10.9.0.9:9090';
 COMMENT ON COLUMN alerting_engines.datasource_id IS 'datasource id';
-COMMENT ON COLUMN alerting_engines.cluster IS 'target reader cluster';
+COMMENT ON COLUMN alerting_engines.engine_cluster IS 'target reader cluster';
 
 
 CREATE TABLE datasource

docker/initsql/a-n9e.sql

@@ -531,6 +531,7 @@ CREATE TABLE `task_tpl_host`
 CREATE TABLE `task_record`
 (
     `id` bigint unsigned not null comment 'ibex task id',
+    `event_id` bigint not null comment 'event id' default 0,
     `group_id` bigint not null comment 'busi group id',
     `ibex_address`   varchar(128) not null,
     `ibex_auth_user` varchar(128) not null default '',
@@ -547,7 +548,8 @@ CREATE TABLE `task_record`
     `create_by` varchar(64) not null default '',
     PRIMARY KEY (`id`),
     KEY (`create_at`, `group_id`),
-    KEY (`create_by`)
+    KEY (`create_by`),
+    KEY (`event_id`)
 ) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
 
 CREATE TABLE `alerting_engines`
@@ -555,12 +557,11 @@ CREATE TABLE `alerting_engines`
     `id` int unsigned NOT NULL AUTO_INCREMENT,
     `instance` varchar(128) not null default '' comment 'instance identification, e.g. 10.9.0.9:9090',
     `datasource_id` bigint not null default 0 comment 'datasource id',
-    `cluster` varchar(128) not null default '' comment 'n9e-alert cluster',
+    `engine_cluster` varchar(128) not null default '' comment 'n9e-alert cluster',
     `clock` bigint not null,
     PRIMARY KEY (`id`)
 ) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
 
-
 CREATE TABLE `datasource`
 (
     `id` int unsigned NOT NULL AUTO_INCREMENT,

fe.sh

@@ -7,4 +7,9 @@ curl -o n9e-fe-${VERSION}.tar.gz -L https://github.com/n9e/fe/releases/download/
 
 tar zxvf n9e-fe-${VERSION}.tar.gz
 
-cp ./docker/initsql/a-n9e.sql n9e.sql
+cp ./docker/initsql/a-n9e.sql n9e.sql
+
+TAG=$(curl -sX GET https://api.github.com/repos/ccfos/nightingale/releases/latest   | awk '/tag_name/{print $4;exit}' FS='[""]')
+VERSION=$(echo $TAG)
+VERSION=${VERSION/v/}
+sed -i "s/nightingale:latest/nightingale:${VERSION}/g" ./docker/docker-compose.yaml

integrations/kubernetes/alerts/apiserver.json

@@ -0,0 +1,266 @@
+[
+  {
+    "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/kubelet.json

@@ -0,0 +1,366 @@
+[
+  {
+    "name": "Node状态异常",
+    "note": "{{ $labels.node }} has been unready for more than 15 minutes.",
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 900,
+    "prom_ql": "kube_node_status_condition{job=\"kube-state-metrics\",condition=\"Ready\",status=\"true\"} == 0\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": "Node不可达",
+    "note": "{{ $labels.node }} is unreachable and some workloads may be rescheduled.",
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 900,
+    "prom_ql": "(kube_node_spec_taint{job=\"kube-state-metrics\",key=\"node.kubernetes.io/unreachable\",effect=\"NoSchedule\"} unless ignoring(key,value) kube_node_spec_taint{job=\"kube-state-metrics\",key=~\"ToBeDeletedByClusterAutoscaler|cloud.google.com/impending-node-termination|aws-node-termination-handler/spot-itn\"}) == 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": "Node运行太多Pod",
+    "note": "Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage }} of its Pod capacity.",
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 900,
+    "prom_ql": "count by(node) (\n  (kube_pod_status_phase{job=\"kube-state-metrics\",phase=\"Running\"} == 1) * on(instance,pod,namespace,cluster) group_left(node) topk by(instance,pod,namespace,cluster) (1, kube_pod_info{job=\"kube-state-metrics\"})\n)\n/\nmax by(node) (\n  kube_node_status_capacity_pods{job=\"kube-state-metrics\"} != 1\n) > 0.95\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": "Node状态抖动",
+    "note": "The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes.",
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 900,
+    "prom_ql": "sum(changes(kube_node_status_condition{status=\"true\",condition=\"Ready\"}[15m])) by (node) > 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": "PLEG耗时高",
+    "note": "The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }}.",
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 300,
+    "prom_ql": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile=\"0.99\"} >= 10\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": "Pod启动耗时高",
+    "note": "Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }}.",
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 900,
+    "prom_ql": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job=\"kubelet\", metrics_path=\"/metrics\"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\", metrics_path=\"/metrics\"} > 60\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": "客户端证书过期-S2",
+    "note": "Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 0,
+    "prom_ql": "kubelet_certificate_manager_client_ttl_seconds < 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": "客户端证书过期-S1",
+    "note": "Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
+    "severity": 1,
+    "disabled": 0,
+    "prom_for_duration": 0,
+    "prom_ql": "kubelet_certificate_manager_client_ttl_seconds < 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": "服务端证书过期-S2",
+    "note": "Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 0,
+    "prom_ql": "kubelet_certificate_manager_server_ttl_seconds < 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": "服务端证书过期-S1",
+    "note": "Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
+    "severity": 1,
+    "disabled": 0,
+    "prom_for_duration": 0,
+    "prom_ql": "kubelet_certificate_manager_server_ttl_seconds < 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": "客户端证书续签错误",
+    "note": "Kubelet on node {{ $labels.node }} has failed to renew its client certificate ({{ $value | humanize }} errors in the last 5 minutes).",
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 900,
+    "prom_ql": "increase(kubelet_certificate_manager_client_expiration_renew_errors[5m]) > 0\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": "服务证书续签错误",
+    "note": "Kubelet on node {{ $labels.node }} has failed to renew its server certificate ({{ $value | humanize }} errors in the last 5 minutes).",
+    "severity": 2,
+    "disabled": 0,
+    "prom_for_duration": 900,
+    "prom_ql": "increase(kubelet_server_expiration_renew_errors[5m]) > 0\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": "kubelet故障",
+    "note": "Kubelet has disappeared from Prometheus target discovery.",
+    "severity": 1,
+    "disabled": 0,
+    "prom_for_duration": 900,
+    "prom_ql": "absent(up{job=\"kubelet\"} == 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": []
+  }
+]

integrations/kubernetes/dashboards/APIServer.json

@@ -0,0 +1,642 @@
+{
+  "name": "Kubernetes / API Server",
+  "tags": "Categraf",
+  "ident": "",
+  "configs": {
+    "version": "2.0.0",
+    "links": [],
+    "var": [],
+    "panels": [
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "up{job=\"apiserver\"}",
+            "legend": "{{ instance }}"
+          }
+        ],
+        "name": "API Server - Health Status",
+        "links": [],
+        "description": "apiserver的实例健康状态，0表示down，1表示up",
+        "custom": {
+          "showHeader": true,
+          "colorMode": "value",
+          "calc": "lastNotNull",
+          "displayMode": "seriesToRows"
+        },
+        "options": {
+          "valueMappings": [
+            {
+              "options": {
+                "0": {
+                  "text": "DOWN"
+                },
+                "1": {
+                  "text": "UP"
+                }
+              },
+              "type": "value"
+            },
+            {
+              "type": "special",
+              "result": {
+                "color": "#3fc453",
+                "text": "UP"
+              },
+              "match": {
+                "special": 1
+              }
+            },
+            {
+              "type": "special",
+              "result": {
+                "color": "#f80202",
+                "text": "DOWN"
+              },
+              "match": {
+                "special": 0
+              }
+            }
+          ],
+          "standardOptions": {
+            "util": "none"
+          }
+        },
+        "overrides": [
+          {}
+        ],
+        "version": "2.0.0",
+        "type": "table",
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 0,
+          "y": 0,
+          "i": "98f46bc1-c078-40f2-915c-f0836957bf2f",
+          "isResizable": true
+        },
+        "id": "98f46bc1-c078-40f2-915c-f0836957bf2f"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "apiserver_requested_deprecated_apis{job=\"apiserver\"}",
+            "legend": ""
+          }
+        ],
+        "name": "Deprecated Kubernetes Resources",
+        "links": [],
+        "description": "当前版本apiserver使用，未来版本中要移除的资源",
+        "custom": {
+          "showHeader": true,
+          "colorMode": "value",
+          "calc": "lastNotNull",
+          "displayMode": "labelsOfSeriesToRows",
+          "columns": [
+            "group",
+            "version",
+            "resource",
+            "removed_release"
+          ],
+          "sortOrder": "ascend"
+        },
+        "options": {
+          "standardOptions": {}
+        },
+        "overrides": [
+          {}
+        ],
+        "version": "2.0.0",
+        "type": "table",
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 12,
+          "y": 0,
+          "i": "73beb13a-bd10-4a68-bb9e-5b9ab63da154",
+          "isResizable": true
+        },
+        "id": "73beb13a-bd10-4a68-bb9e-5b9ab63da154"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum by (instance,code) (rate(apiserver_request_total{job=\"apiserver\"}[5m]))",
+            "legend": "{{ instance }} {{ code }}"
+          }
+        ],
+        "name": "API Server - HTTP Requests by code",
+        "links": [],
+        "description": "按照返回码分类统计apiserver请求数",
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "list",
+            "placement": "bottom"
+          },
+          "standardOptions": {
+            "util": "none"
+          },
+          "thresholds": {
+            "steps": []
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "lineWidth": 1,
+          "fillOpacity": 0.25,
+          "gradientMode": "none",
+          "stack": "off"
+        },
+        "version": "2.0.0",
+        "type": "timeseries",
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 0,
+          "y": 8,
+          "i": "1cfa42b1-9dcf-471c-90ff-8ffe656d4b11",
+          "isResizable": true
+        },
+        "id": "1cfa42b1-9dcf-471c-90ff-8ffe656d4b11"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum by (instance,verb) (rate(apiserver_request_total{job=\"apiserver\"}[5m]))",
+            "legend": "{{ instance }} {{ verb }}"
+          }
+        ],
+        "name": "API Server - HTTP Requests by verb",
+        "links": [],
+        "description": "按照请求动作分类统计apiserver的请求数",
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "desc"
+          },
+          "legend": {
+            "displayMode": "list",
+            "placement": "bottom"
+          },
+          "standardOptions": {
+            "util": "none"
+          },
+          "thresholds": {
+            "steps": []
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "lineWidth": 1,
+          "fillOpacity": 0.25,
+          "gradientMode": "none",
+          "stack": "off"
+        },
+        "version": "2.0.0",
+        "type": "timeseries",
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 12,
+          "y": 8,
+          "i": "94def0cb-0b86-42f7-a4b2-dde714bbb918",
+          "isResizable": true
+        },
+        "id": "94def0cb-0b86-42f7-a4b2-dde714bbb918"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "apiserver_current_inflight_requests{job=\"apiserver\"}",
+            "legend": "{{ instance }} {{ request_kind }}"
+          }
+        ],
+        "name": "API Server - Current Inflight Requests by kind",
+        "links": [],
+        "description": "当前并发请求apiserver的数量",
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "desc"
+          },
+          "legend": {
+            "displayMode": "list",
+            "placement": "bottom"
+          },
+          "standardOptions": {
+            "util": "none"
+          },
+          "thresholds": {
+            "steps": []
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "lineWidth": 1,
+          "fillOpacity": 0.25,
+          "gradientMode": "none",
+          "stack": "off"
+        },
+        "version": "2.0.0",
+        "type": "timeseries",
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 0,
+          "y": 16,
+          "i": "ce5a15ad-11c6-44a2-a071-be57009162e1",
+          "isResizable": true
+        },
+        "id": "fb6266a3-3da0-4310-bfe8-c64a53db5db3"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\"}[5m])) by (instance,verb,le))*1000",
+            "legend": "{{ instance }} {{ verb }}"
+          }
+        ],
+        "name": "API Server - HTTP Requets Latency by verb",
+        "links": [],
+        "description": "apiserver的响应延迟，按请求动作分类统计",
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "list",
+            "placement": "bottom"
+          },
+          "standardOptions": {
+            "util": "milliseconds"
+          },
+          "thresholds": {
+            "steps": []
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "lineWidth": 1,
+          "fillOpacity": 0.25,
+          "gradientMode": "none",
+          "stack": "off"
+        },
+        "version": "2.0.0",
+        "type": "timeseries",
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 12,
+          "y": 16,
+          "i": "045dca2d-d69b-47a7-b25e-656adb357e11",
+          "isResizable": true
+        },
+        "id": "045dca2d-d69b-47a7-b25e-656adb357e11"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket {job=\"apiserver\",verb!=\"WATCH\"}[5m])) by (instance,le))*1000",
+            "legend": "{{ instance }}"
+          }
+        ],
+        "name": "API Server - HTTP Requets Latency by instance",
+        "links": [],
+        "description": "apiserver的响应延迟(非watch请求）",
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "desc"
+          },
+          "legend": {
+            "displayMode": "list",
+            "placement": "bottom"
+          },
+          "standardOptions": {
+            "util": "milliseconds"
+          },
+          "thresholds": {
+            "steps": []
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "lineWidth": 1,
+          "fillOpacity": 0.25,
+          "gradientMode": "none",
+          "stack": "off"
+        },
+        "version": "2.0.0",
+        "type": "timeseries",
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 0,
+          "y": 24,
+          "i": "1e775704-9ee4-45ce-9d24-b49af89fb5c7",
+          "isResizable": true
+        },
+        "id": "1e775704-9ee4-45ce-9d24-b49af89fb5c7"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum by(instance,verb) (rate(apiserver_request_total{code=~\"5..\",job=\"apiserver\"}[5m]))\n / sum by(instance,verb) (rate(apiserver_request_total{job=\"apiserver\"}[5m]))",
+            "legend": "{{ instance }}  {{ verb }}"
+          }
+        ],
+        "name": "API Server - Errors by verb",
+        "links": [],
+        "description": "apiserver的5xx错误率，按请求动作分类统计",
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "desc"
+          },
+          "legend": {
+            "displayMode": "list",
+            "placement": "bottom"
+          },
+          "standardOptions": {
+            "util": "none"
+          },
+          "thresholds": {
+            "steps": []
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "lineWidth": 1,
+          "fillOpacity": 0.25,
+          "gradientMode": "none",
+          "stack": "off"
+        },
+        "version": "2.0.0",
+        "type": "timeseries",
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 12,
+          "y": 24,
+          "i": "1ca62e0b-72df-47d1-93ba-048ed49e9cb5",
+          "isResizable": true
+        },
+        "id": "1ca62e0b-72df-47d1-93ba-048ed49e9cb5"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum by(instance) (rate(apiserver_request_total{code=~\"5..\", job=\"apiserver\"}[5m]))\n / sum by(instance) (rate(apiserver_request_total{job=\"apiserver\"}[5m]))",
+            "legend": "{{ instance }}"
+          }
+        ],
+        "name": "API Server - Errors by Instance",
+        "links": [],
+        "description": "apiserver的5xx 错误率(5xx请求数/总请求数)",
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "desc"
+          },
+          "legend": {
+            "displayMode": "list",
+            "placement": "bottom"
+          },
+          "standardOptions": {
+            "util": "none"
+          },
+          "thresholds": {
+            "steps": []
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "lineWidth": 1,
+          "fillOpacity": 0.25,
+          "gradientMode": "none",
+          "stack": "off"
+        },
+        "version": "2.0.0",
+        "type": "timeseries",
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 0,
+          "y": 32,
+          "i": "92a209a1-7d30-4627-9ae1-55ded5095ed7",
+          "isResizable": true
+        },
+        "id": "92a209a1-7d30-4627-9ae1-55ded5095ed7"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(rate(workqueue_depth{job=\"apiserver\"}[5m])) by (instance,name)",
+            "legend": "{{ instance }} {{ name }}"
+          }
+        ],
+        "name": "API Server - Work Queue by instance",
+        "links": [],
+        "description": "apiserver工作队列深度，越接近0越好",
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "desc"
+          },
+          "legend": {
+            "displayMode": "list",
+            "placement": "bottom"
+          },
+          "standardOptions": {
+            "util": "none"
+          },
+          "thresholds": {
+            "steps": []
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "lineWidth": 1,
+          "fillOpacity": 0.25,
+          "gradientMode": "none",
+          "stack": "off"
+        },
+        "version": "2.0.0",
+        "type": "timeseries",
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 12,
+          "y": 32,
+          "i": "83f22cf4-9c65-4ad3-900b-fa6fc914dd88",
+          "isResizable": true
+        },
+        "id": "83f22cf4-9c65-4ad3-900b-fa6fc914dd88"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) by (instance)",
+            "legend": "{{ instance }}"
+          }
+        ],
+        "name": "API Server - HTTP Requests by instance",
+        "links": [],
+        "description": "5分钟内apiserver的请求数统计",
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "desc"
+          },
+          "legend": {
+            "displayMode": "list",
+            "placement": "bottom"
+          },
+          "standardOptions": {
+            "util": "none"
+          },
+          "thresholds": {
+            "steps": []
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "lineWidth": 1,
+          "fillOpacity": 0.25,
+          "gradientMode": "none",
+          "stack": "normal"
+        },
+        "version": "2.0.0",
+        "type": "timeseries",
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 0,
+          "y": 40,
+          "i": "3e9f9df7-d9fb-4791-b3b2-2c52678f060f",
+          "isResizable": true
+        },
+        "id": "3e9f9df7-d9fb-4791-b3b2-2c52678f060f"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "rate(process_cpu_seconds_total{job=\"apiserver\"}[5m])",
+            "legend": "{{ instance }}"
+          }
+        ],
+        "name": "API Server - CPU Usage by instance",
+        "links": [],
+        "description": "apiserver的cpu使用率",
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "desc"
+          },
+          "legend": {
+            "displayMode": "list",
+            "placement": "bottom"
+          },
+          "standardOptions": {
+            "util": "percent",
+            "decimals": 2
+          },
+          "thresholds": {
+            "steps": []
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "lineWidth": 1,
+          "fillOpacity": 0.25,
+          "gradientMode": "none",
+          "stack": "off"
+        },
+        "version": "2.0.0",
+        "type": "timeseries",
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 12,
+          "y": 40,
+          "i": "3d5c1ae5-e640-4986-9202-78258169bffb",
+          "isResizable": true
+        },
+        "id": "3d5c1ae5-e640-4986-9202-78258169bffb"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "process_resident_memory_bytes{job=\"apiserver\"}",
+            "legend": "{{ instance }}"
+          }
+        ],
+        "name": "API Server - Memory Usage by instance",
+        "links": [],
+        "description": "apiserver的内存使用量",
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "desc"
+          },
+          "legend": {
+            "displayMode": "list",
+            "placement": "bottom"
+          },
+          "standardOptions": {
+            "util": "bytesIEC"
+          },
+          "thresholds": {
+            "steps": []
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "lineWidth": 1,
+          "fillOpacity": 0.25,
+          "gradientMode": "none",
+          "stack": "off"
+        },
+        "version": "2.0.0",
+        "type": "timeseries",
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 0,
+          "y": 48,
+          "i": "1550a2d5-c808-4174-865a-a41b2c16b486",
+          "isResizable": true
+        },
+        "id": "1550a2d5-c808-4174-865a-a41b2c16b486"
+      }
+    ]
+  }
+}

integrations/kubernetes/dashboards/Cadvisor.json

@@ -0,0 +1,271 @@
+{
+  "name": "Cadvisor",
+  "tags": "",
+  "ident": "",
+  "configs": {
+    "version": "2.0.0",
+    "links": [],
+    "var": [
+      {
+        "type": "query",
+        "name": "host",
+        "definition": "label_values({__name__=~\"container.*\"},instance)",
+        "allValue": ".*",
+        "allOption": true,
+        "multi": false,
+        "reg": ""
+      },
+      {
+        "type": "query",
+        "name": "container",
+        "definition": "label_values({__name__=~\"container.*\", instance=~\"$host\"},name)",
+        "allValue": ".*",
+        "allOption": true,
+        "multi": false,
+        "reg": ""
+      }
+    ],
+    "panels": [
+      {
+        "version": "2.0.0",
+        "id": "eeb56afe-8a3e-46d6-8923-aeb3d0f124ea",
+        "type": "timeseries",
+        "name": "CPU Usage",
+        "links": [],
+        "layout": {
+          "h": 7,
+          "w": 24,
+          "x": 0,
+          "y": 0,
+          "i": "eeb56afe-8a3e-46d6-8923-aeb3d0f124ea",
+          "isResizable": true
+        },
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(rate(container_cpu_usage_seconds_total{instance=~\"$host\",name=~\"$container\",name=~\".+\"}[5m])) by (name) *100",
+            "legend": "{{name}}"
+          }
+        ],
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "version": "2.0.0",
+          "drawStyle": "lines",
+          "lineInterpolation": "linear",
+          "fillOpacity": 0.5,
+          "stack": "off"
+        },
+        "maxPerRow": 4
+      },
+      {
+        "version": "2.0.0",
+        "id": "6690fff4-c159-40e5-b340-65a3ba85e37e",
+        "type": "timeseries",
+        "name": "Memory Usage",
+        "links": [],
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 0,
+          "y": 7,
+          "i": "6690fff4-c159-40e5-b340-65a3ba85e37e",
+          "isResizable": true
+        },
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(container_memory_rss{instance=~\"$host\",name=~\"$container\",name=~\".+\"}) by (name)",
+            "legend": "{{name}}"
+          }
+        ],
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "version": "2.0.0",
+          "drawStyle": "lines",
+          "lineInterpolation": "linear",
+          "fillOpacity": 0.5,
+          "stack": "off"
+        },
+        "maxPerRow": 4
+      },
+      {
+        "version": "2.0.0",
+        "id": "3c798af5-cfae-4962-9b70-85736df44bb1",
+        "type": "timeseries",
+        "name": "Memory Cached",
+        "links": [],
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 12,
+          "y": 7,
+          "i": "3c798af5-cfae-4962-9b70-85736df44bb1",
+          "isResizable": true
+        },
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(container_memory_cache{instance=~\"$host\",name=~\"$container\",name=~\".+\"}) by (name)",
+            "legend": "{{name}}"
+          }
+        ],
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "version": "2.0.0",
+          "drawStyle": "lines",
+          "lineInterpolation": "linear",
+          "fillOpacity": 0.5,
+          "stack": "off"
+        },
+        "maxPerRow": 4
+      },
+      {
+        "version": "2.0.0",
+        "id": "111835e1-cfb5-40db-bb52-1aca74cf1a00",
+        "type": "timeseries",
+        "name": "Received Network Traffic",
+        "links": [],
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 0,
+          "y": 15,
+          "i": "111835e1-cfb5-40db-bb52-1aca74cf1a00",
+          "isResizable": true
+        },
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(rate(container_network_receive_bytes_total{instance=~\"$host\",name=~\"$container\",name=~\".+\"}[5m])) by (name)",
+            "legend": "{{name}}"
+          }
+        ],
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "version": "2.0.0",
+          "drawStyle": "lines",
+          "lineInterpolation": "linear",
+          "fillOpacity": 0.5,
+          "stack": "off"
+        },
+        "maxPerRow": 4
+      },
+      {
+        "version": "2.0.0",
+        "id": "b8050f8f-aee7-4fa5-888d-b6025df14aa1",
+        "type": "timeseries",
+        "name": "Sent Network Traffic",
+        "links": [],
+        "layout": {
+          "h": 8,
+          "w": 12,
+          "x": 12,
+          "y": 15,
+          "i": "b8050f8f-aee7-4fa5-888d-b6025df14aa1",
+          "isResizable": true
+        },
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(rate(container_network_transmit_bytes_total{instance=~\"$host\",name=~\"$container\",name=~\".+\"}[5m])) by (name)",
+            "legend": "{{name}}"
+          }
+        ],
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "version": "2.0.0",
+          "drawStyle": "lines",
+          "lineInterpolation": "linear",
+          "fillOpacity": 0.5,
+          "stack": "off"
+        },
+        "maxPerRow": 4
+      }
+    ]
+  }
+}

integrations/kubernetes/dashboards/KubeletMetrics.json

@@ -0,0 +1,438 @@
+{
+  "name": "Kubernetes / Kubelet Metrics",
+  "tags": "Categraf",
+  "ident": "",
+  "configs": {
+    "var": [
+      {
+        "name": "cluster",
+        "definition": "label_values(kubelet_running_pods, cluster)",
+        "multi": true,
+        "allOption": true
+      },
+      {
+        "name": "instance",
+        "definition": "label_values(kubelet_running_pods{cluster=~\"$cluster\"}, instance)",
+        "multi": true,
+        "allOption": true
+      }
+    ],
+    "panels": [
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(up{source=\"kubelet\", cluster=~\"$cluster\"})"
+          }
+        ],
+        "name": "Kubelet UP",
+        "custom": {
+          "textMode": "value",
+          "colorMode": "background",
+          "calc": "lastNotNull",
+          "colSpan": 1,
+          "textSize": {}
+        },
+        "options": {
+          "standardOptions": {}
+        },
+        "version": "2.0.0",
+        "type": "stat",
+        "layout": {
+          "h": 3,
+          "w": 4,
+          "x": 0,
+          "y": 0,
+          "i": "d3caf396-b3a1-449b-acec-f550967889e6",
+          "isResizable": true
+        },
+        "id": "d3caf396-b3a1-449b-acec-f550967889e6"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(kubelet_running_pods{cluster=~\"$cluster\", instance=~\"$instance\"})"
+          }
+        ],
+        "name": "Running Pods",
+        "custom": {
+          "textMode": "valueAndName",
+          "colorMode": "value",
+          "calc": "lastNotNull",
+          "colSpan": 1,
+          "textSize": {}
+        },
+        "options": {
+          "standardOptions": {}
+        },
+        "version": "2.0.0",
+        "type": "stat",
+        "layout": {
+          "h": 3,
+          "w": 4,
+          "x": 4,
+          "y": 0,
+          "i": "38c38b23-a7e3-4177-8c41-3ce955ea0434",
+          "isResizable": true
+        },
+        "id": "38c38b23-a7e3-4177-8c41-3ce955ea0434"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(kubelet_running_containers{cluster=~\"$cluster\", instance=~\"$instance\", container_state=\"running\"})"
+          }
+        ],
+        "name": "Running Containers",
+        "custom": {
+          "textMode": "valueAndName",
+          "colorMode": "value",
+          "calc": "lastNotNull",
+          "colSpan": 1,
+          "textSize": {}
+        },
+        "options": {
+          "standardOptions": {}
+        },
+        "version": "2.0.0",
+        "type": "stat",
+        "layout": {
+          "h": 3,
+          "w": 4,
+          "x": 8,
+          "y": 0,
+          "i": "26bf2320-fcff-48f8-a6fc-aa9076bb9329",
+          "isResizable": true
+        },
+        "id": "525859b9-91d7-4180-b363-bf8ceec977d8"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(volume_manager_total_volumes{cluster=~\"$cluster\", instance=~\"$instance\", state=\"desired_state_of_world\"})"
+          }
+        ],
+        "name": "Desired Volumes",
+        "custom": {
+          "textMode": "valueAndName",
+          "colorMode": "value",
+          "calc": "lastNotNull",
+          "colSpan": 1,
+          "textSize": {}
+        },
+        "options": {
+          "standardOptions": {}
+        },
+        "version": "2.0.0",
+        "type": "stat",
+        "layout": {
+          "h": 3,
+          "w": 4,
+          "x": 12,
+          "y": 0,
+          "i": "54ae4ab3-e932-418c-a637-f2f515cce1b9",
+          "isResizable": true
+        },
+        "id": "84af4617-2ae0-4b30-a82a-6e8586342224"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(volume_manager_total_volumes{cluster=~\"$cluster\", instance=~\"$instance\", state=\"actual_state_of_world\"})"
+          }
+        ],
+        "name": "Actual Volumes",
+        "custom": {
+          "textMode": "valueAndName",
+          "colorMode": "value",
+          "calc": "lastNotNull",
+          "colSpan": 1,
+          "textSize": {}
+        },
+        "options": {
+          "standardOptions": {}
+        },
+        "version": "2.0.0",
+        "type": "stat",
+        "layout": {
+          "h": 3,
+          "w": 4,
+          "x": 16,
+          "y": 0,
+          "i": "d9de76d7-2203-40e7-a792-9888ec869e82",
+          "isResizable": true
+        },
+        "id": "d431f4bd-9115-41d2-a494-1d680bdd1e0f"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(increase(kubelet_runtime_operations_errors_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]))"
+          }
+        ],
+        "name": "OP Errors in 5min",
+        "custom": {
+          "textMode": "value",
+          "colorMode": "value",
+          "calc": "lastNotNull",
+          "colSpan": 1,
+          "textSize": {}
+        },
+        "options": {
+          "valueMappings": [
+            {
+              "type": "range",
+              "match": {
+                "from": 1
+              },
+              "result": {
+                "color": "#d0021b"
+              }
+            },
+            {
+              "type": "range",
+              "match": {
+                "to": 1
+              },
+              "result": {
+                "color": "#417505"
+              }
+            }
+          ],
+          "standardOptions": {}
+        },
+        "version": "2.0.0",
+        "type": "stat",
+        "layout": {
+          "h": 3,
+          "w": 4,
+          "x": 20,
+          "y": 0,
+          "i": "bf2bbd15-347d-404c-9b8f-e524875befe2",
+          "isResizable": true
+        },
+        "id": "54de62bc-8af3-4c27-8b8e-1af567b363fc"
+      },
+      {
+        "type": "row",
+        "id": "730d4a9b-791f-4aaf-a042-668f66e73814",
+        "name": "Operations",
+        "collapsed": true,
+        "layout": {
+          "h": 1,
+          "w": 24,
+          "x": 0,
+          "y": 3,
+          "i": "730d4a9b-791f-4aaf-a042-668f66e73814",
+          "isResizable": false
+        },
+        "panels": []
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "increase(kubelet_runtime_operations_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])"
+          }
+        ],
+        "name": "Operations in 5min",
+        "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": 4,
+          "w": 12,
+          "x": 0,
+          "y": 4,
+          "i": "d26e6818-6704-492a-8cbf-58473dd85716",
+          "isResizable": true
+        },
+        "id": "d26e6818-6704-492a-8cbf-58473dd85716"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "increase(kubelet_runtime_operations_errors_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])"
+          }
+        ],
+        "name": "Operation Errors in 5min",
+        "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": 4,
+          "w": 12,
+          "x": 12,
+          "y": 4,
+          "i": "4e585d2f-c61c-4350-86ec-dca7ddc34ceb",
+          "isResizable": true
+        },
+        "id": "09a6ad5b-8c0e-4f17-b17f-3ebc514f7d20"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "increase(kubelet_runtime_operations_duration_seconds_sum{cluster=~\"$cluster\", instance=~\"$instance\"}[1h])/increase(kubelet_runtime_operations_duration_seconds_count{cluster=~\"$cluster\", instance=~\"$instance\"}[1h])"
+          }
+        ],
+        "name": "Average Operation duration in 1 hour (Unit: 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": 4,
+          "w": 24,
+          "x": 0,
+          "y": 8,
+          "i": "b5e56f3e-fa20-4c19-8578-c0610fa0a7e7",
+          "isResizable": true
+        },
+        "id": "b5e56f3e-fa20-4c19-8578-c0610fa0a7e7"
+      },
+      {
+        "type": "row",
+        "id": "dd7e84c5-03ce-467c-871a-aa110fe051f4",
+        "name": "PLEG relist",
+        "collapsed": true,
+        "layout": {
+          "h": 1,
+          "w": 24,
+          "x": 0,
+          "y": 12,
+          "i": "dd7e84c5-03ce-467c-871a-aa110fe051f4",
+          "isResizable": false
+        }
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "rate(kubelet_pleg_relist_duration_seconds_count{cluster=~\"$cluster\", instance=~\"$instance\"}[1h])"
+          }
+        ],
+        "name": "relist rate",
+        "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": 4,
+          "w": 12,
+          "x": 0,
+          "y": 13,
+          "i": "f3822da8-a9c9-4db1-ba12-465d3ece823e",
+          "isResizable": true
+        },
+        "id": "f3822da8-a9c9-4db1-ba12-465d3ece823e"
+      },
+      {
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "increase(kubelet_pleg_relist_duration_seconds_sum{cluster=~\"$cluster\", instance=~\"$instance\"}[1h])/increase(kubelet_pleg_relist_duration_seconds_count{cluster=~\"$cluster\", instance=~\"$instance\"}[1h])"
+          }
+        ],
+        "name": "relist duration (Unit: 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": 4,
+          "w": 12,
+          "x": 12,
+          "y": 13,
+          "i": "2b4ada76-6c30-42cd-9bd3-c939b4c0139c",
+          "isResizable": true
+        },
+        "id": "a6e4c914-bfca-4419-a264-f5b1cbab261a"
+      }
+    ],
+    "version": "2.0.0"
+  }
+}

integrations/linux/dashboards/linux_by_categraf.json

@@ -1437,7 +1437,7 @@
                         "displayMode": "hidden"
                     },
                     "standardOptions": {
-                        "util": "bytesIEC",
+                        "util": "bitsIEC",
                         "decimals": 0
                     },
                     "thresholds": {
@@ -1732,4 +1732,4 @@
         ],
         "version": "3.0.0"
     }
-}
+}

integrations/processes/alerts/categraf-processes.json

@@ -0,0 +1,68 @@
+[
+    {
+      "cate": "prometheus",
+      "datasource_ids": [
+        0
+      ],
+      "name": "Too many running processes",
+      "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": "processes_running > (system_n_cpus * 3)",
+            "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": 1,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "notify_max_number": 10,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [],
+      "annotations": {}
+    }
+  ]

integrations/processes/dashboards/categraf-processes.json

@@ -0,0 +1,234 @@
+{
+    "name": "Processes by UlricQin",
+    "tags": "Categraf Linux OS",
+    "ident": "",
+    "configs": {
+        "var": [
+            {
+                "name": "Datasource",
+                "label": "",
+                "type": "datasource",
+                "definition": "prometheus",
+                "defaultValue": 37
+            },
+            {
+                "name": "ident",
+                "label": "Host",
+                "type": "query",
+                "datasource": {
+                    "cate": "prometheus",
+                    "value": "${Datasource}"
+                },
+                "definition": "label_values(processes_running, ident)",
+                "multi": true,
+                "allOption": true
+            }
+        ],
+        "panels": [
+            {
+                "type": "barGauge",
+                "id": "adc3f1d3-6d0d-4c1e-80ca-5b6d8103bac5",
+                "layout": {
+                    "h": 8,
+                    "w": 12,
+                    "x": 0,
+                    "y": 0,
+                    "i": "adc3f1d3-6d0d-4c1e-80ca-5b6d8103bac5",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${Datasource}",
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "processes_running{ident=~\"$ident\"}",
+                        "legend": "{{ident}}",
+                        "instant": true
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "Running Processes",
+                "custom": {
+                    "calc": "lastNotNull",
+                    "baseColor": "#9470FF",
+                    "serieWidth": 20,
+                    "sortOrder": "desc"
+                },
+                "options": {
+                    "valueMappings": [
+                        {
+                            "type": "range",
+                            "result": {
+                                "color": "#f10808"
+                            },
+                            "match": {
+                                "from": 50
+                            }
+                        }
+                    ],
+                    "standardOptions": {}
+                }
+            },
+            {
+                "type": "barGauge",
+                "id": "659f5f75-24ca-493c-97cb-3d99abd52172",
+                "layout": {
+                    "h": 8,
+                    "w": 12,
+                    "x": 12,
+                    "y": 0,
+                    "i": "df457bf0-17c8-4d05-a527-cfaf0f2b844c",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${Datasource}",
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "processes_total{ident=~\"$ident\"}",
+                        "legend": "{{ident}}",
+                        "instant": true
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "Total Processes",
+                "custom": {
+                    "calc": "lastNotNull",
+                    "baseColor": "#9470FF",
+                    "serieWidth": 20,
+                    "sortOrder": "desc"
+                },
+                "options": {
+                    "valueMappings": [
+                        {
+                            "type": "range",
+                            "result": {
+                                "color": "#f10808"
+                            },
+                            "match": {
+                                "from": 600
+                            }
+                        }
+                    ],
+                    "standardOptions": {}
+                }
+            },
+            {
+                "type": "barGauge",
+                "id": "5e849509-1c41-44c7-85ee-d8c0adf7c623",
+                "layout": {
+                    "h": 8,
+                    "w": 12,
+                    "x": 0,
+                    "y": 8,
+                    "i": "62291285-be84-470a-9ccc-53be7a8733fd",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${Datasource}",
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "processes_total_threads{ident=~\"$ident\"}",
+                        "legend": "{{ident}}",
+                        "instant": true
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "Total Threads",
+                "custom": {
+                    "calc": "lastNotNull",
+                    "baseColor": "#9470FF",
+                    "serieWidth": 20,
+                    "sortOrder": "desc"
+                },
+                "options": {
+                    "valueMappings": [
+                        {
+                            "type": "range",
+                            "result": {
+                                "color": "#ff8286"
+                            },
+                            "match": {
+                                "from": 2000
+                            }
+                        },
+                        {
+                            "type": "range",
+                            "result": {
+                                "color": "#f30909"
+                            },
+                            "match": {
+                                "from": 4000
+                            }
+                        }
+                    ],
+                    "standardOptions": {}
+                }
+            },
+            {
+                "type": "table",
+                "id": "b2850506-6cdd-48cc-9223-70acff9212b0",
+                "layout": {
+                    "h": 8,
+                    "w": 12,
+                    "x": 12,
+                    "y": 8,
+                    "i": "b2850506-6cdd-48cc-9223-70acff9212b0",
+                    "isResizable": true
+                },
+                "version": "3.0.0",
+                "datasourceCate": "prometheus",
+                "datasourceValue": "${Datasource}",
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "sum({__name__=~\"processes_sleeping|processes_dead|processes_paging|processes_total_threads|processes_total|processes_idle|processes_running|processes_zombies|processes_stopped|processes_unknown|processes_blocked\", ident=~\"$ident\"}) by (__name__)",
+                        "instant": true
+                    }
+                ],
+                "transformations": [
+                    {
+                        "id": "organize",
+                        "options": {}
+                    }
+                ],
+                "name": "SUM by Process state",
+                "custom": {
+                    "showHeader": true,
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "displayMode": "labelsOfSeriesToRows",
+                    "sortColumn": "value",
+                    "sortOrder": "descend",
+                    "columns": []
+                },
+                "options": {
+                    "standardOptions": {}
+                },
+                "overrides": [
+                    {}
+                ]
+            }
+        ],
+        "version": "3.0.0"
+    }
+}

integrations/processes/markdown/readme.md

@@ -0,0 +1,22 @@
+## Categraf as collector
+
+configuration file: `conf/input.processes/processes.toml`
+
+默认配置如下（一般维持默认不用动）：
+
+```toml
+# # collect interval
+# interval = 15
+
+# # force use ps command to gather
+# force_ps = false
+
+# # force use /proc to gather
+# force_proc = false
+```
+
+有两种采集方式，使用 ps 命令，或者直接读取 `/proc` 目录，默认是后者。如果想强制使用 ps 命令才采集，开启 force_ps 即可：
+
+```
+force_ps = true
+```

models/alert_cur_event.go

@@ -425,18 +425,6 @@ func AlertNumbers(ctx *ctx.Context, bgids []int64) (map[int64]int64, error) {
 	return ret, nil
 }
 
-func AlertCurEventGetAll(ctx *ctx.Context, cluster string) ([]*AlertCurEvent, error) {
-	session := DB(ctx).Model(&AlertCurEvent{})
-
-	if cluster != "" {
-		session = session.Where("cluster = ?", cluster)
-	}
-
-	var lst []*AlertCurEvent
-	err := session.Find(&lst).Error
-	return lst, err
-}
-
 func AlertCurEventGetByIds(ctx *ctx.Context, ids []int64) ([]*AlertCurEvent, error) {
 	var lst []*AlertCurEvent
 

models/alert_rule.go

@@ -278,6 +278,10 @@ func (ar *AlertRule) Update(ctx *ctx.Context, arf AlertRule) error {
 }
 
 func (ar *AlertRule) UpdateColumn(ctx *ctx.Context, column string, value interface{}) error {
+	if value == nil {
+		return nil
+	}
+
 	if column == "datasource_ids" {
 		b, err := json.Marshal(value)
 		if err != nil {
@@ -286,6 +290,68 @@ func (ar *AlertRule) UpdateColumn(ctx *ctx.Context, column string, value interfa
 		return DB(ctx).Model(ar).UpdateColumn(column, string(b)).Error
 	}
 
+	if column == "severity" {
+		severity := int(value.(float64))
+		if ar.Cate == PROMETHEUS {
+			var ruleConfig PromRuleConfig
+			err := json.Unmarshal([]byte(ar.RuleConfig), &ruleConfig)
+			if err != nil {
+				return err
+			}
+
+			if len(ruleConfig.Queries) != 1 {
+				return nil
+			}
+
+			ruleConfig.Queries[0].Severity = severity
+			b, err := json.Marshal(ruleConfig)
+			if err != nil {
+				return err
+			}
+			return DB(ctx).Model(ar).UpdateColumn("rule_config", string(b)).Error
+		} else if ar.Cate == HOST {
+			var ruleConfig HostRuleConfig
+			err := json.Unmarshal([]byte(ar.RuleConfig), &ruleConfig)
+			if err != nil {
+				return err
+			}
+
+			if len(ruleConfig.Triggers) != 1 {
+				return nil
+			}
+
+			ruleConfig.Triggers[0].Severity = severity
+
+			b, err := json.Marshal(ruleConfig)
+			if err != nil {
+				return err
+			}
+			return DB(ctx).Model(ar).UpdateColumn("rule_config", string(b)).Error
+		}
+	}
+
+	if column == "runbook_url" {
+		url := value.(string)
+
+		err := json.Unmarshal([]byte(ar.Annotations), &ar.AnnotationsJSON)
+		if err != nil {
+			return err
+		}
+
+		if ar.AnnotationsJSON == nil {
+			ar.AnnotationsJSON = make(map[string]string)
+		}
+
+		ar.AnnotationsJSON["runbook_url"] = url
+
+		b, err := json.Marshal(ar.AnnotationsJSON)
+		if err != nil {
+			return err
+		}
+
+		return DB(ctx).Model(ar).UpdateColumn("annotations", string(b)).Error
+	}
+
 	return DB(ctx).Model(ar).UpdateColumn(column, value).Error
 }
 

models/alerting_engine.go

@@ -8,11 +8,11 @@ import (
 )
 
 type AlertingEngines struct {
-	Id           int64  `json:"id" gorm:"primaryKey"`
-	Instance     string `json:"instance"`
-	Cluster      string `json:"cluster"`
-	DatasourceId int64  `json:"datasource_id"`
-	Clock        int64  `json:"clock"`
+	Id            int64  `json:"id" gorm:"primaryKey"`
+	Instance      string `json:"instance"`
+	EngineCluster string `json:"cluster" gorm:"engine_cluster"`
+	DatasourceId  int64  `json:"datasource_id"`
+	Clock         int64  `json:"clock"`
 }
 
 func (e *AlertingEngines) TableName() string {
@@ -107,11 +107,11 @@ func AlertingEngineGet(ctx *ctx.Context, where string, args ...interface{}) (*Al
 func AlertingEngineGetsClusters(ctx *ctx.Context, where string, args ...interface{}) ([]string, error) {
 	var arr []string
 	var err error
-	session := DB(ctx).Model(new(AlertingEngines)).Where("cluster != ''").Order("cluster").Distinct("cluster")
+	session := DB(ctx).Model(new(AlertingEngines)).Where("engine_cluster != ''").Order("engine_cluster").Distinct("engine_cluster")
 	if where == "" {
-		err = session.Pluck("cluster", &arr).Error
+		err = session.Pluck("engine_cluster", &arr).Error
 	} else {
-		err = session.Where(where, args...).Pluck("cluster", &arr).Error
+		err = session.Where(where, args...).Pluck("engine_cluster", &arr).Error
 	}
 	return arr, err
 }
@@ -130,7 +130,7 @@ func AlertingEngineGetsInstances(ctx *ctx.Context, where string, args ...interfa
 
 func AlertingEngineHeartbeatWithCluster(ctx *ctx.Context, instance, cluster string, datasourceId int64) error {
 	var total int64
-	err := DB(ctx).Model(new(AlertingEngines)).Where("instance=? and cluster = ? and datasource_id=?", instance, cluster, datasourceId).Count(&total).Error
+	err := DB(ctx).Model(new(AlertingEngines)).Where("instance=? and engine_cluster = ? and datasource_id=?", instance, cluster, datasourceId).Count(&total).Error
 	if err != nil {
 		return err
 	}
@@ -138,15 +138,15 @@ func AlertingEngineHeartbeatWithCluster(ctx *ctx.Context, instance, cluster stri
 	if total == 0 {
 		// insert
 		err = DB(ctx).Create(&AlertingEngines{
-			Instance:     instance,
-			DatasourceId: datasourceId,
-			Cluster:      cluster,
-			Clock:        time.Now().Unix(),
+			Instance:      instance,
+			DatasourceId:  datasourceId,
+			EngineCluster: cluster,
+			Clock:         time.Now().Unix(),
 		}).Error
 	} else {
 		// updates
 		fields := map[string]interface{}{"clock": time.Now().Unix()}
-		err = DB(ctx).Model(new(AlertingEngines)).Where("instance=? and cluster = ? and datasource_id=?", instance, cluster, datasourceId).Updates(fields).Error
+		err = DB(ctx).Model(new(AlertingEngines)).Where("instance=? and engine_cluster = ? and datasource_id=?", instance, cluster, datasourceId).Updates(fields).Error
 	}
 
 	return err

models/host_meta.go

@@ -12,6 +12,7 @@ type HostMeta struct {
 	MemUtil      float64 `json:"mem_util"`
 	Offset       int64   `json:"offset"`
 	UnixTime     int64   `json:"unixtime"`
+	RemoteAddr   string  `json:"remote_addr"`
 }
 
 func (h HostMeta) MarshalBinary() ([]byte, error) {

models/target.go

@@ -22,14 +22,15 @@ type Target struct {
 	TagsMap  map[string]string `json:"-" gorm:"-"` // internal use, append tags to series
 	UpdateAt int64             `json:"update_at"`
 
-	UnixTime int64   `json:"unixtime" gorm:"-"`
-	Offset   int64   `json:"offset" gorm:"-"`
-	TargetUp float64 `json:"target_up" gorm:"-"`
-	MemUtil  float64 `json:"mem_util" gorm:"-"`
-	CpuNum   int     `json:"cpu_num" gorm:"-"`
-	CpuUtil  float64 `json:"cpu_util" gorm:"-"`
-	OS       string  `json:"os" gorm:"-"`
-	Arch     string  `json:"arch" gorm:"-"`
+	UnixTime   int64   `json:"unixtime" gorm:"-"`
+	Offset     int64   `json:"offset" gorm:"-"`
+	TargetUp   float64 `json:"target_up" gorm:"-"`
+	MemUtil    float64 `json:"mem_util" gorm:"-"`
+	CpuNum     int     `json:"cpu_num" gorm:"-"`
+	CpuUtil    float64 `json:"cpu_util" gorm:"-"`
+	OS         string  `json:"os" gorm:"-"`
+	Arch       string  `json:"arch" gorm:"-"`
+	RemoteAddr string  `json:"remote_addr" gorm:"-"`
 }
 
 func (t *Target) TableName() string {
@@ -296,6 +297,7 @@ func (t *Target) FillMeta(meta *HostMeta) {
 	t.Offset = meta.Offset
 	t.OS = meta.OS
 	t.Arch = meta.Arch
+	t.RemoteAddr = meta.RemoteAddr
 }
 
 func TargetIdents(ctx *ctx.Context, ids []int64) ([]string, error) {

models/task_record.go

@@ -4,6 +4,7 @@ import "github.com/ccfos/nightingale/v6/pkg/ctx"
 
 type TaskRecord struct {
 	Id           int64  `json:"id" gorm:"primaryKey"`
+	EventId      int64  `json:"event_id"`
 	GroupId      int64  `json:"group_id"`
 	IbexAddress  string `json:"ibex_address"`
 	IbexAuthUser string `json:"ibex_auth_user"`