一、安装Prometheus

配置文件目录

mkdir -p /etc/prometheus

配置文件

[root@izs3l77ihmekj0z ~]# cat /etc/prometheus/prometheus.yml 
# my global config
global:
  scrape_interval:     15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
  # scrape_timeout is set to the global default (10s).

# Alertmanager configuration
alerting:
  alertmanagers:
  - static_configs:
    - targets:
      # - alertmanager:9093

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
  # - "first_rules.yml"
  # - "second_rules.yml"

# 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'

    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.

    static_configs:
    - targets: ['localhost:9090']

数据目录

mkdir -p /data/prometheus
chmod -R 777 /data

安装

docker run -d --restart=always --name prometheus -p 9090:9090 -v /etc/prometheus:/etc/prometheus -v /data/prometheus:/data -v /etc/localtime:/etc/localtime prom/prometheus --config.file=/etc/prometheus/prometheus.yml --storage.tsdb.retention=90d --storage.tsdb.path=/data   --storage.remote.read-sample-limit=5e6 --storage.remote.flush-deadline=60s --web.read-timeout=2m --query.timeout=2m --web.enable-lifecycle --web.enable-admin-api --query.max-concurrency=100 --alertmanager.timeout=10s

验证

Prometheus

二、安装node-exporter

安装

docker run -d --restart=always --name=node-exporter -p 9100:9100 prom/node-exporter

数据采集验证

node-exporter

创建job配置目录

mkdir -p /etc/prometheus/files

创建targets配置文件(可以自定义需要的标签)

[root@prometheus files]# pwd
/etc/prometheus/files
[root@prometheus files]# cat prometheus.yml 
[{
        "labels": {
                "monitortype": "system",
                "name": "192.168.153.130"
        },
        "targets": ["192.168.153.130:9100"]
}]

修改prometheus配置文件

[root@prometheus prometheus]# cat prometheus.yml 
# my global config
global:
  scrape_interval:     15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
  # scrape_timeout is set to the global default (10s).

# Alertmanager configuration
alerting:
  alertmanagers:
  - static_configs:
    - targets:
      # - alertmanager:9093

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
  # - "first_rules.yml"
  # - "second_rules.yml"

# 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: 60s
    honor_labels: true
    metrics_path: '/metrics'
    
    scheme: http
    file_sd_configs:
    - files:
      - /etc/prometheus/files/prometheus.yml

重载配置

curl -X POST http://localhost:9090/-/reload

验证

prometheus

三、安装Grafana

数据目录

mkdir -p /data/grafana
chmod -R 777 /data/grafana

安装

docker run -d -p 3000:3000 --name=grafana -v /data/grafana:/var/lib/grafana grafana/grafana

验证

grafana登录页面
配置Prometheus数据源
数据源配置
数据源配置
数据源配置
新建系统监控
新建DashBoard
新建DashBoard
新建DashBoard 新建DashBoard
系统监控