监控环境基于docker和docker-compose搭建。

安装采集器

用于收集各种软件和服务器的性能指标。

Linux服务器

version: '3'
services:

  reporter_node:                                         # 服务器指标采集，用于监控远程主机
    image: prom/node-exporter:v1.7.0
    restart: always
    container_name: reporter_node
    user: root
    healthcheck:
      test: ["CMD", "nc", "-zv", "localhost", "9100"]
      interval: 6s
      timeout: 5s
      retries: 10
    ports:
      - 9100:9100

服务中心Zookeeper

Zookeeper已经提供性能指标接口无需额外安装软件。

消息中间件Kafka

version: '3'
services:
  reporter_kafka:  #【应用软件】
  # 采集Kafka指标，必须和Kafka在同一个局域网内
    image: danielqsj/kafka-exporter:v1.7.0
    restart: always
    container_name: reporter_kafka
    command:
      - '--kafka.server=localhost:29092'        #kafka服务节点1访问地址
#      - '--kafka.server=${SERVER_HOST_DOMAIN}:9092'    #kafka服务节点2访问地址
      - '--sasl.enabled'                               #kafka鉴权4要素：开启SASL
      - '--sasl.mechanism=scram-sha512'                #kafka鉴权4要素：鉴权协议  
      - '--sasl.username=thingskit'                   #kafka鉴权4要素：用户名
      - '--sasl.password=thingskit'                   #kafka鉴权4要素：密码
      
#  volumes:
#    - /_makeFile/_certs:/bitnami/kafka/config/certs:ro    # 自签名(根)证书密钥
    ports:
      - 9098:9308
    env_file:
#      - /_makeFile/_common.env
      - /_makeFile/miscroservice.env  

缓存Redis

version: '3'
services:


  reporter_redis: #【应用软件】prometheus、grafana(763)
    image: oliver006/redis_exporter:v1.55.0
    restart: always
    container_name: reporter_redis
    ports:
      - 9121:9121
    environment:
      - REDIS_EXPORTER_NAMESPACE=redis
      - REDIS_ADDR=redis://localhost:6379
      - REDIS_PASSWORD=litangyuan

关系数据库Postgres

version: '3'
services:


  reporter_pgsql:   #【应用软件】
  # Pgsql数据库监控 https://github.com/prometheus-community/postgres_exporter
    image: prometheuscommunity/postgres-exporter:v0.15.0
    restart: always
    container_name: reporter_pgsql
#    user: root
    healthcheck:
      test: ["CMD", "nc", "-zv", "localhost", "9187"]
      interval: 6s
      timeout: 5s
      retries: 10
    ports:
      - 9187:9187
    environment:
      - DATA_SOURCE_URI=localhost:5432/thingskit?sslmode=disable
      - DATA_SOURCE_USER=postgres
      - DATA_SOURCE_PASS=thingskit

负载均衡Haproxy

version: '3'
services:

  reporter_haproxy: #【应用软件】prometheus、grafana(12708)
  # Mysql数据库监控
    image: quay.io/prometheus/haproxy-exporter:latest
    restart: always
    container_name: reporter_haproxy
    healthcheck:
      test: ["CMD", "nc", "-zv", "localhost", "9101"]
      interval: 6s
      timeout: 5s
      retries: 10
    ports:
      - 9101:9101
    environment:
      - SCRAPE_URI=http://172.30.69.207:9999/status

平台服务组件

常见平台服务组件，例如：核心服务、规则引擎、设备接入(MQTT、TCP/UDP、GBT28181)服务等。

安装Prometheus

是一款基于时序数据库的开源监控告警系统。

version: '3'
services:

  prometheus:
    image: prom/prometheus:v2.42.0
    volumes:
      - ./conf/prometheus/:/etc/prometheus/
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
    ports:
      - 9090:9090
    restart: always
    container_name: prometheus
    user: root
    

global:
  scrape_interval:     15s # By default, scrape targets every 15 seconds.
  evaluation_interval: 15s # By default, scrape targets every 15 seconds.
  # scrape_timeout is set to the global default (10s).

  # Attach these labels to any time series or alerts when communicating with
  # external systems (federation, remote storage, Alertmanager).
  external_labels:
      monitor: 'thingskit'


# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.         
  - job_name: 'prometheus'
    scrape_interval: 5s
    static_configs:
     - targets: ['localhost:9090']
     
  - job_name: 'cluster_nodes'   #服务节点指标采集   
    static_configs:                     
    - targets: ['localhost:9100']                   

  - job_name: 'cluster_kafka'
#    metrics_path: /actuator/prometheus
    static_configs:
    - targets: ['localhost:9098']  
    
  - job_name: 'cluster_redis'
#    metrics_path: /actuator/prometheus
    static_configs:
    - targets: ['localhost:9121']

        
  - job_name: 'cluster_zookeeper'
#    metrics_path: /metrics
    static_configs:
    - targets: ['localhost:7070','localhost:7070']

        
        
  - job_name: 'cluster_pgsql'
#    metrics_path: /actuator/prometheus
    static_configs:
    - targets: ['localhost:9187']


  - job_name: 'cassandra_cluster'
#    metrics_path: /actuator/prometheus
    static_configs:
    - targets: ['localhost:7199']
  - job_name: 'cluster_nginx'
#    metrics_path: /metrics
    static_configs:
    - targets: ['localhost:9113']  
        
  - job_name: 'cluster_haproxy'
#    metrics_path: /metrics
    static_configs:
    - targets: ['localhost:9101']  


  - job_name: 'tb-core1'
    metrics_path: /actuator/prometheus
    static_configs:
      - targets: [ 'tb-core1:8080' ]
  - job_name: 'tb-core2'
    metrics_path: /actuator/prometheus
    static_configs:
      - targets: [ 'tb-core2:8080' ]
  - job_name: 'tb-core3'
    metrics_path: /actuator/prometheus
    static_configs:
      - targets: [ 'tb-core2:8080' ]

  - job_name: 'tb-rule-engine1'
    metrics_path: /actuator/prometheus
    static_configs:
      - targets: [ 'tb-rule-engine1:8080' ]
  - job_name: 'tb-rule-engine2'
    metrics_path: /actuator/prometheus
    static_configs:
      - targets: [ 'tb-rule-engine2:8080' ]
  - job_name: 'tb-rule-engine3'
    metrics_path: /actuator/prometheus
    static_configs:
      - targets: [ 'tb-rule-engine2:8080' ]

  - job_name: 'tb-mqtt-transport1'
    metrics_path: /actuator/prometheus
    static_configs:
      - targets: [ 'tb-mqtt-transport1:8081' ]
  - job_name: 'tb-mqtt-transport2'
    metrics_path: /actuator/prometheus
    static_configs:
      - targets: [ 'tb-mqtt-transport2:8081' ]
  - job_name: 'tb-mqtt-transport3'
    metrics_path: /actuator/prometheus
    static_configs:
      - targets: [ 'tb-mqtt-transport2:8081' ]

  - job_name: 'tb-http-transport1'
    metrics_path: /actuator/prometheus
    static_configs:
      - targets: [ 'tb-http-transport1:8081' ]
  - job_name: 'tb-http-transport2'
    metrics_path: /actuator/prometheus
    static_configs:
      - targets: [ 'tb-http-transport2:8081' ]
  - job_name: 'tb-http-transport3'
    metrics_path: /actuator/prometheus
    static_configs:
      - targets: [ 'tb-http-transport2:8081' ]

  - job_name: 'tb-coap-transport'
    metrics_path: /actuator/prometheus
    static_configs:
      - targets: [ 'tb-coap-transport:8081' ]

  - job_name: 'tb-lwm2m-transport'
    metrics_path: /actuator/prometheus
    static_configs:
      - targets: [ 'tb-lwm2m-transport:8081' ]

  - job_name: 'tb-snmp-transport'
    metrics_path: /actuator/prometheus
    static_configs:
      - targets: [ 'tb-snmp-transport:8081' ]

安装grafana

version: '3'
services:

  grafana:
    image: grafana/grafana
    user: "472"
    depends_on:
      - prometheus
    ports:
      - 3000:3000
    volumes:
      - ./conf/grafana/:/etc/grafana/provisioning/
    env_file:
      - ./conf/grafana/monitor.env
    restart: always
    container_name: grafana

配置数据源

导入看板

看板市场

Linux服务器

模板ID：1860、16522

服务中心Zookeeper

模板ID：10465

消息中间件Kafka

模板ID：12460、10122

缓存Redis

模板ID：763、11835

关系数据库Postgres

模板ID：9628

负载均衡Haproxy

模板ID：2428、12693

平台服务组件

模板ID：4701、11378、11955、14430

除了看板市场的模板，ThingsBaord也提供有基于服务的看板。