Promethus普罗米修斯介绍及Linux系统下的安装与配置

[root@node2 ~]# wget https://github.com/prometheus/prometheus/releases/download/v2.31.1/prometheus-2.31.1.linux-amd64.tar.gz

[root@node2 ~]# tar xf prometheus-2.31.1.linux-amd64.tar.gz -C /usr/local/
[root@node2 src]# cd /usr/local/
[root@node2 local]# ls
bin  games    lib    libexec                        redis  share
etc  include  lib64  prometheus-2.31.1.linux-amd64  sbin   src
[root@node2 local]# mv prometheus-2.31.1.linux-amd64/  prometheus

[root@node2 local]# cd prometheus/
[root@node2 prometheus]# ./prometheus --config.file=prometheus.yml

root@node2 prometheus]# vim /usr/local/prometheus/prometheus.yml
#全局配置
global:
  scrape_interval: 15s #每隔15秒向目标抓取一次数，默认为一分钟
  evaluation_interval: 15s #每隔15秒执行一次告警规则，默认为一分钟
  # scrape_timeout: 600s  #抓取数据的超时时间，默认为10s
#告警配置
alerting:
  alertmanagers:
    - static_configs:
        - targets:
          # - alertmanager:9093	 #alertmanager所部署机器的ip和端口
#定义告警规则和阈值的yml文件
rule_files:
  # - "first_rules.yml"
  # - "second_rules.yml"
#收集数据配置
#以下是Prometheus自身的一个配置.
scrape_configs:
  #这个配置是表示在这个配置内的时间序例，每一条都会自动添加上这个{job_name:"prometheus"}的标签.
  - job_name: "prometheus"
    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.
    static_configs:			
#静态配置
    - targets: ["localhost:9090"]

[root@node2 prometheus]# ./promtool check config ./prometheus.yml
Checking ./prometheus.yml
  SUCCESS: 0 rule files found

[root@node2 prometheus]# cat > /usr/lib/systemd/system/prometheus.service <<EOF
[Unit]
Description=The Prometheus Server
After=network.target
[Service]
Restart=on-failure
ExecStart=/usr/local/prometheus/prometheus --config.file=/usr/local/prometheus/prometheus.yml
RestartSec=15s
[Install]
WantedBy=multi-user.target
EOF
[root@node2 prometheus]# systemctl daemon-reload 
[root@node2 prometheus]# systemctl restart prometheus
[root@node2 local]# ss -antl
State  Recv-Q Send-Q Local Address:Port   Peer Address:Port Process 
LISTEN 0      128          0.0.0.0:6379        0.0.0.0:*            
LISTEN 0      128          0.0.0.0:22          0.0.0.0:*            
LISTEN 0      128             [::]:22             [::]:*            
LISTEN 0      128                *:9090              *:* 

##启动
/usr/local/prometheus/prometheus --config.file=/usr/local/prometheus/prometheus.yml &
##启动参数介绍
--config.file      	   #加载prometheus的配置文件
--web.listen-address   #监听prometheus的web地址和端口
--web.enable-lifecycle #热启动参数，可以在不中断服务的情况下重启加载配置文件
--storage.tsdb.retention   #数据持久化的时间                         
--storage.tsdb.path        #数据持久化的保存路径

wget https://github.com/prometheus/node_exporter/releases/download/v1.3.0/node_exporter-1.3.0.linux-amd64.tar.gz

[root@node1 ~]# ls
anaconda-ks.cfg  node_exporter-1.3.0.linux-amd64.tar.gz
[root@node1 ~]# tar xf node_exporter-1.3.0.linux-amd64.tar.gz -C /usr/local/
[root@node1 ~]# 
[root@node1 ~]# cd /usr/local/
[root@node1 local]# ls
bin  games    lib    libexec                          sbin   src
etc  include  lib64  node_exporter-1.3.0.linux-amd64  share

[root@node1 local]# mv node_exporter-1.3.0.linux-amd64/ node_exporter
[root@node1 local]# 

注意：相关启动的参数
--web.listen-address     #node_expoetrt暴露的端口
--collector.systemd	     #从systemd中收集
--collector.systemd.unit-whitelist   ##白名单，收集目标
		".+"         		      #从systemd中循环正则匹配单元
		"(docker|sshd|nginx).service"  #白名单，收集目标，收集参数node_systemd_unit_state

[root@node1 local]# vi /usr/lib/systemd/system/node_exporter.service
[unit]
Description=The node_exporter Server
After=network.target

[Service]
ExecStart=/usr/local/node_exporter/node_exporter
Restart=on-failure
RestartSec=15s
SyslogIdentifier=node_exporter

[Install]
WantedBy=multi-user.target

[root@node1 local]# systemctl daemon-reload 
[root@node1 local]# systemctl enable node_exporter 
[root@node1 local]# systemctl restart node_exporter
Created symlink /etc/systemd/system/multi-user.target.wants/node_exporter.service → /usr/lib/systemd/system/node_exporter.service.

[root@node1 local]# ss -antl
State  Recv-Q Send-Q Local Address:Port   Peer Address:Port Process 
LISTEN 0      128          0.0.0.0:22          0.0.0.0:*            
LISTEN 0      128             [::]:22             [::]:*            
LISTEN 0      128                *:9100              *:*            
[root@node1 local]# 

[root@node2 prometheus]# vim /usr/local/prometheus/prometheus.yml
......
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: ["192.168.200.144:9100"]    //此处指定客户端ip和端口