共计 6489 个字符,预计需要花费 17 分钟才能阅读完成。
筹备工作
1、创立用户和配置环境参数
(1)、创立用户和创立所需目录
[root@centos ~]# groupadd prometheus
[root@centos ~]# useradd -d /home/prometheus -g prometheus -m prometheus
[root@centos ~]# chmod 755 /home/prometheus
[root@centos ~]# mkdir -p /home/prometheus/software
[root@centos ~]# mkdir -p /home/prometheus/yunwei
[root@centos ~]# chown -R prometheus:prometheus /home/prometheus
[root@centos ~]# mkdir -p /data/prometheus
[root@centos ~]# chown -R prometheus:prometheus /data/prometheus
(2)、下载
https://github.com/prometheus/prometheus/releases/download/v2.42.0/prometheus-2.42.0.linux-amd64.tar.gz
部署计划
1、部署
(1)、敞开防火墙
[root@centos ~]# systemctl stop firewalld
[root@centos ~]# systemctl disable firewalld
Removed symlink /etc/systemd/system/multi-user.target.wants/firewalld.service.
Removed symlink /etc/systemd/system/dbus-org.fedoraproject.FirewallD1.service.
[root@centos ~]# setenforce 0
[root@centos ~]# getenforce
Permissive
[root@centos ~]# vi /etc/sysconfig/selinux
# This file controls the state of SELinux on the system.
# SELINUX= can take one of these three values:
# enforcing - SELinux security policy is enforced.
# permissive - SELinux prints warnings instead of enforcing.
# disabled - No SELinux policy is loaded.
SELINUX=disabled
# SELINUXTYPE= can take one of three values:
# targeted - Targeted processes are protected,
# minimum - Modification of targeted policy. Only selected processes are protected.
# mls - Multi Level Security protection.
SELINUXTYPE=targeted
(2)、解压安装包并备份配置文件
[prometheus@centos ~]$ tar zxf $HOME/software/prometheus-2.42.0.linux-amd64.tar.gz -C $HOME
[prometheus@centos ~]$ mv prometheus-2.42.0.linux-amd64 prometheus-2.42.0
[prometheus@centos ~]$ cp prometheus-2.42.0/prometheus.yml prometheus-2.42.0/prometheus.yml_init
(3)、创立所需目录
[prometheus@centos ~]$ mkdir -p /data/prometheus/prometheus-2.42.0/logs
[prometheus@centos ~]$ mkdir -p /data/prometheus/prometheus-2.42.0/data
2、调整配置文件
[prometheus@centos ~]$ vi $HOME/prometheus-2.42.0/prometheus.yml
# my global config
global:
scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
# scrape_timeout is set to the global default (10s).
# Alertmanager configuration
alerting:
alertmanagers:
- static_configs:
- targets:
# - alertmanager:9093
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
# - "first_rules.yml"
# - "second_rules.yml"
# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
# The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
- job_name: "prometheus"
# metrics_path defaults to '/metrics'
# scheme defaults to 'http'.
static_configs:
- targets: ["192.168.19.149:9090"]
3、启停服务与创立脚本
(1)、查看 prometheus 版本信息
# 查看版本信息
[prometheus@centos ~]$ $HOME/prometheus-2.42.0/prometheus --version
prometheus, version 2.42.0 (branch: HEAD, revision: 225c61122d88b01d1f0eaaee0e05b6f3e0567ac0)
build user: root@c67d48967507
build date: 20230201-07:53:32
go version: go1.19.5
platform: linux/amd64
(2)、失常启动命令及参数抉择
# 启动服务
[prometheus@centos ~]$ $HOME/prometheus-2.42.0/prometheus --config.file=prometheus.yml
# 指定配置文件
--config.file="prometheus.yml"
# 默认指定监听地址端口,可批改端口
--web.listen-address="0.0.0.0:9090"
# 开启 API 服务(为管理控制操作启用 API 端点。)--web.enable-admin-api
# 最大连接数
--web.max-connections=512
# tsdb 数据存储的目录,默认以后 data/
--storage.tsdb.path="data/"
# premetheus 存储数据的工夫,默认保留 15 天
--storage.tsdb.retention.time=365d
#通过命令热加载无需重启 curl -XPOST 192.168.19.149:9090/-/reload
--web.enable-lifecycle
# 能够启用 TLS 或身份验证 的配置文件的门路
--web.config.file=""
# 启动选项理解:
[prometheus@centos ~]$ $HOME/prometheus-2.42.0/prometheus --help
(3)、启动脚本配置
[prometheus@centos ~]$ vi $HOME/yunwei/prometheus-2.42.0_start.sh
#!/bin/bash
#
cd $HOME/prometheus-2.42.0
nohup ./prometheus --config.file="prometheus.yml" --web.max-connections=512 --storage.tsdb.path="/data/prometheus/prometheus-2.42.0/data/" --storage.tsdb.retention.time=365d --web.enable-lifecycle --web.enable-admin-api >> /data/prometheus/prometheus-2.42.0/logs/prometheus-2.42.0.log 2>&1 &
tail -f /data/prometheus/prometheus-2.42.0/logs/prometheus-2.42.0.log
(4)、进行脚本配置
[prometheus@centos ~]$ vi $HOME/yunwei/prometheus-2.42.0_stop.sh
#!/bin/bash
#
prom_pid=`ps -ef|grep prometheus|grep storage.tsdb.retention.time|grep -v grep|awk '{print $2}'`
kill -9 $prom_pid
(5)、热加载重启配置
[prometheus@centos ~]$ vi $HOME/yunwei/prometheus-2.42.0_reload.sh
#!/bin/bash
#
curl -XPOST 192.168.19.149:9090/-/reload
治理配置
1、创立目录
[prometheus@centos ~]$ mkdir $HOME/exporter
[prometheus@centos ~]$ mkdir -p $HOME/yunwei/exporter/node
[prometheus@centos ~]$ mkdir -p /data/prometheus/exporter/node_exporter_1.5.0/logs
2、下载
https://github.com/prometheus/node_exporter/releases/download/v1.5.0/node_exporter-1.5.0.linux-amd64.tar.gz
3、部署 node_exporter
[prometheus@centos ~]$ tar zxf $HOME/software/node_exporter-1.5.0.linux-amd64.tar.gz -C $HOME/exporter
[prometheus@centos ~]$ mv $HOME/exporter/node_exporter-1.5.0.linux-amd64 $HOME/exporter/node_exporter
4、查看 node_exporter 版本及参数
# 查看版本
[prometheus@centos node_exporter]$ $HOME/exporter/node_exporter/node_exporter --version
node_exporter, version 1.5.0 (branch: HEAD, revision: 1b48970ffcf5630534fb00bb0687d73c66d1c959)
build user: root@6e7732a7b81b
build date: 20221129-18:59:09
go version: go1.19.3
platform: linux/amd64
# 查看相干参数
[prometheus@centos ~]$ $HOME/node_exporter --help
# 申请 URL 门路地址
--web.telemetry-path="/metrics"
# 最大申请数量
--web.max-requests=40
# web 监听端口地址
--web.listen-address=:9100
# 指定配置文件
--web.config.file=""
5、配置 prometheus.yml
[prometheus@centos ~]$ vi prometheus-2.42.0/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: ["192.168.19.149:9090"]
# 新增 job_name 并增加治理主机参数
- job_name: "node_exporter"
static_configs:
- targets: ['192.168.19.149:9100']
labels:
host_ip: 192.168.19.149
6、脚本配置
(1)、启动脚本
[prometheus@centos ~]$ vi $HOME/yunwei/exporter/node/node_exporter_1.5.0_start.sh
#!/bin/bash
#
cd $HOME/exporter/node_exporter
./node_exporter --web.listen-address=:9100 >> /data/prometheus/exporter/node_exporter_1.5.0/logs/node_exporter.log &
(2)、进行脚本
[prometheus@centos ~]$ vi $HOME/yunwei/exporter/node/node_exporter_1.5.0_stop.sh
#!/bin/bash
#
node_exp_pid=`ps -ef|grep node_exporter|grep 9100|awk '{print $2}'`
kill -9 $node_exp_pid
正文完
发表至: prometheus
2023-04-08