refactor

docker/categraf/conf/config.toml

@@ -73,3 +73,11 @@ timeout = 5000
 dial_timeout = 2500
 max_idle_conns_per_host = 100
 
+[ibex]
+enable = true
+## ibex flush interval
+interval = "1000ms"
+## n9e ibex server rpc address
+servers = ["ibex:20090"]
+## temp script dir
+meta_dir = "./meta"

docker/categraf/conf/logs.toml

@@ -1,35 +0,0 @@
-[logs]
-## key 占位符
-api_key = "ef4ahfbwzwwtlwfpbertgq1i6mq0ab1q"
-## 是否开启日志采集
-enable = false
-## 接受日志的server地址
-send_to = "127.0.0.1:17878"
-## 发送日志的协议 http/tcp
-send_type = "http"
-## 是否压缩发送
-use_compress = false
-## 是否采用ssl
-send_with_tls = false
-##
-batch_wait = 5
-## 日志offset信息保存目录
-run_path = "/opt/categraf/run"
-## 最多同时采集多少个日志文件
-open_files_limit = 100
-## 定期扫描目录下是否有新增日志
-scan_period = 10
-##
-frame_size = 10
-##
-collect_container_all = true
-  ## 全局的处理规则
-  [[logs.Processing_rules]]
-  ## 单个日志采集配置
-  [[logs.items]]
-  ## file/journald
-  type = "file"
-  ## type=file时 path必填，type=journald时 port必填
-  path = "/opt/tomcat/logs/*.txt"
-  source = "tomcat"
-  service = "my_service"

docker/docker-compose.yaml

@@ -12,7 +12,7 @@ services:
     hostname: mysql
     restart: always
     ports:
-      - "3306:3306"
+      - "3406:3306"
     environment:
       TZ: Asia/Shanghai
       MYSQL_ROOT_PASSWORD: 1234
@@ -80,7 +80,7 @@ services:
       sh -c "/wait && /app/ibex server"
 
   n9e:
-    image: flashcatcloud/nightingale:6.0.0-beta.1
+    image: flashcatcloud/nightingale:latest
     container_name: n9e
     hostname: n9e
     restart: always
@@ -122,31 +122,13 @@ services:
       - ./categraf/conf:/etc/categraf/conf
       - /:/hostfs
       - /var/run/docker.sock:/var/run/docker.sock
-    ports:
-      - "9100:9100/tcp"
+    # ports:
+    #   - "9100:9100/tcp"
     networks:
       - nightingale
     depends_on:
       - n9e
-    links:
-      - n9e:n9e
-
-  agentd:
-    image: ulric2019/ibex:0.3
-    container_name: agentd
-    hostname: agentd
-    restart: always
-    environment:
-      GIN_MODE: release
-      TZ: Asia/Shanghai
-    volumes:
-      - ./ibexetc:/app/etc
-    networks:
-      - nightingale
-    depends_on:
       - ibex
     links:
+      - n9e:n9e
       - ibex:ibex
-    command:
-      - "/app/ibex"
-      - "agentd"

docker/ibexetc/agentd.conf

@@ -1,38 +0,0 @@
-# debug, release
-RunMode = "release"
-
-# task meta storage dir
-MetaDir = "./meta"
-
-[HTTP]
-Enable = true
-# http listening address
-Host = "0.0.0.0"
-# http listening port
-Port = 2090
-# https cert file path
-CertFile = ""
-# https key file path
-KeyFile = ""
-# whether print access log
-PrintAccessLog = true
-# whether enable pprof
-PProf = false
-# 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
-
-[Heartbeat]
-# unit: ms
-Interval = 1000
-# rpc servers
-Servers = ["ibex:20090"]
-# $ip or $hostname or specified string
-Host = "categraf01"

docker/n9eetc/config.toml

@@ -118,15 +118,6 @@ IP = ""
 Interval = 1000
 ClusterName = "default"
 
-# [Alert.SMTP]
-# Host = "smtp.163.com"
-# Port = 994
-# User = "username"
-# Pass = "password"
-# From = "username@163.com"
-# InsecureSkipVerify = true
-# Batch = 5
-
 # [Alert.Alerting]
 # NotifyConcurrency = 10
 
@@ -147,52 +138,7 @@ BasicAuthPass = "ibex"
 Timeout = 3000
 
 [Pushgw]
-# use target labels in database instead of in series
 LabelRewrite = true
-# # default busigroup key name
-# BusiGroupLabelKey = "busigroup"
-# ForceUseServerTS = false
-
-# [Pushgw.DebugSample]
-# ident = "xx"
-# __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"
-Url = "http://prometheus:9090/api/v1/write"
-# Basic auth username
-BasicAuthUser = ""
-# Basic auth password
-BasicAuthPass = ""
-# timeout settings, unit: ms
-Headers = ["X-From", "n9e"]
-Timeout = 10000
-DialTimeout = 3000
-TLSHandshakeTimeout = 30000
-ExpectContinueTimeout = 1000
-IdleConnTimeout = 90000
-# time duration, unit: ms
-KeepAlive = 30000
-MaxConnsPerHost = 0
-MaxIdleConns = 100
-MaxIdleConnsPerHost = 100
-## Optional TLS Config
-# UseTLS = false
-# TLSCA = "/etc/n9e/ca.pem"
-# TLSCert = "/etc/n9e/cert.pem"
-# TLSKey = "/etc/n9e/key.pem"
-# InsecureSkipVerify = false
-# [[Writers.WriteRelabels]]
-# Action = "replace"
-# SourceLabels = ["__address__"]
-# Regex = "([^:]+)(?::\\d+)?"
-# Replacement = "$1:80"
-# TargetLabel = "__address__"
+Url = "http://prometheus:9090/api/v1/write"

integrations/linux/alerts/linux_by_categraf.json

@@ -1,45 +1,54 @@
 [
-    {
-      "name": "Lost connection with monitoring target - categraf",
-      "note": "",
-      "severity": 1,
-      "disabled": 0,
-      "prom_for_duration": 60,
-      "prom_ql": "max_over_time(target_up[130s]) == 0",
-      "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": "host",
+    "datasource_ids": null,
+    "name": "Lost connection with monitoring target - categraf",
+    "note": "",
+    "prod": "host",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 0,
+    "disabled": 0,
+    "prom_for_duration": 0,
+    "prom_ql": "",
+    "rule_config": {
+      "inhibit": false,
+      "queries": [
+        {
+          "key": "all_hosts",
+          "op": "==",
+          "values": []
+        }
+      ],
+      "triggers": [
+        {
+          "duration": 60,
+          "severity": 2,
+          "type": "target_miss"
+        }
+      ]
     },
-    {
-      "name": "Machine load - high CPU, please pay attention - categraf",
-      "note": "",
-      "severity": 3,
-      "disabled": 0,
-      "prom_for_duration": 60,
-      "prom_ql": "cpu_usage_idle{cpu=\"cpu-total\"} < 25",
-      "prom_eval_interval": 15,
-      "enable_stime": "00:00",
-      "enable_etime": "23:59",
-      "enable_days_of_week": [
+    "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",
@@ -47,18 +56,19 @@
         "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": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [],
+    "annotations": {}
+  },
     {
       "name": "Machine load - high memory, please pay attention - categraf",
       "note": "",

integrations/linux/alerts/linux_by_telegraf.json

@@ -30,15 +30,44 @@
       "append_tags": []
     },
     {
+      "cate": "host",
+      "datasource_ids": null,
       "name": "Lost connection with monitoring target - telegraf",
       "note": "",
-      "severity": 1,
+      "prod": "host",
+      "algorithm": "",
+      "algo_params": null,
+      "delay": 0,
+      "severity": 0,
       "disabled": 0,
-      "prom_for_duration": 60,
-      "prom_ql": "target_up != 1",
+      "prom_for_duration": 0,
+      "prom_ql": "",
+      "rule_config": {
+        "inhibit": false,
+        "queries": [
+          {
+            "key": "all_hosts",
+            "op": "==",
+            "values": []
+          }
+        ],
+        "triggers": [
+          {
+            "duration": 60,
+            "severity": 2,
+            "type": "target_miss"
+          }
+        ]
+      },
       "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",
@@ -48,16 +77,27 @@
         "6",
         "0"
       ],
-      "notify_recovered": 1,
-      "notify_channels": [
-        "email",
-        "dingtalk",
-        "wecom"
+      "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": []
+      "append_tags": [],
+      "annotations": {}
     },
     {
       "name": "Port detection failed, please pay attention - telegraf",

memsto/notify_config.go

@@ -2,6 +2,7 @@ package memsto
 
 import (
 	"encoding/json"
+	"strings"
 	"sync"
 	"time"
 
@@ -57,7 +58,14 @@ func (w *NotifyConfigCacheType) syncNotifyConfigs() error {
 	if err != nil {
 		return err
 	}
-	json.Unmarshal([]byte(cval), &w.webhooks)
+
+	if strings.TrimSpace(cval) != "" {
+		err = json.Unmarshal([]byte(cval), &w.webhooks)
+		if err != nil {
+			logger.Errorf("failed to unmarshal webhooks:%s config:", cval, err)
+		}
+	}
+
 	logger.Infof("timer: sync wbhooks done number: %d", len(w.webhooks))
 
 	cval, err = models.ConfigsGet(w.ctx, models.SMTP)
@@ -65,9 +73,11 @@ func (w *NotifyConfigCacheType) syncNotifyConfigs() error {
 		return err
 	}
 
-	err = toml.Unmarshal([]byte(cval), &w.smtp)
-	if err != nil {
-		logger.Errorf("failed to unmarshal smtp:%s config:", cval, err)
+	if strings.TrimSpace(cval) != "" {
+		err = toml.Unmarshal([]byte(cval), &w.smtp)
+		if err != nil {
+			logger.Errorf("failed to unmarshal smtp:%s config:", cval, err)
+		}
 	}
 
 	logger.Infof("timer: sync smtp:%+v done", w.smtp)
@@ -76,20 +86,28 @@ func (w *NotifyConfigCacheType) syncNotifyConfigs() error {
 	if err != nil {
 		return err
 	}
-	err = json.Unmarshal([]byte(cval), &w.script)
-	if err != nil {
-		logger.Errorf("failed to unmarshal notify script:%s config:", cval, err)
+
+	if strings.TrimSpace(cval) != "" {
+		err = json.Unmarshal([]byte(cval), &w.script)
+		if err != nil {
+			logger.Errorf("failed to unmarshal notify script:%s config:", cval, err)
+		}
 	}
+
 	logger.Infof("timer: sync notify script done")
 
 	cval, err = models.ConfigsGet(w.ctx, models.IBEX)
 	if err != nil {
 		return err
 	}
-	err = toml.Unmarshal([]byte(cval), &w.ibex)
-	if err != nil {
-		logger.Errorf("failed to unmarshal ibex:%s config:", cval, err)
+
+	if strings.TrimSpace(cval) != "" {
+		err = toml.Unmarshal([]byte(cval), &w.ibex)
+		if err != nil {
+			logger.Errorf("failed to unmarshal ibex:%s config:", cval, err)
+		}
 	}
+
 	logger.Infof("timer: sync ibex done")
 
 	return nil