一 prometheus安装部署
1.1 下载
1.2 解压
tar -xvf prometheus-2.40.4.linux-amd64.tar.gz
1.3 安装
- 进入目录
cd prometheus-2.40.4.linux-amd64
- 将可执行命令转移到/usr/bin
mv prometheus promtool /usr/bin/
- 将配置文件转移
mkdir /etc/prometheus/
cp -r console_libraries consoles prometheus.yml /etc/prometheus/
- 添加prometheus用户
useradd -M -r -s /bin/false prometheus
- 创建所需路径并赋予权限
mkdir -p /etc/prometheus /var/lib/prometheus/metrics2 /var/run/prometheus /var/log/prometheus
chown -R prometheus:prometheus /var/lib/prometheus/ /etc/prometheus/ /var/run/prometheus /var/log/prometheus
- 创建prometheus服务启动配置文件
vim /etc/init.d/prometheus
#!/bin/sh
# kFreeBSD do not accept scripts as interpreters, using #!/bin/sh and sourcing.
if [ true != "$INIT_D_SCRIPT_SOURCED" ] ; then
set "$0" "$@"; INIT_D_SCRIPT_SOURCED=true . /lib/init/init-d-script
fi
### BEGIN INIT INFO
# Provides: prometheus
# Required-Start: $remote_fs $syslog
# Required-Stop: $remote_fs $syslog
# Default-Start: 2 3 4 5
# Default-Stop: 0 1 6
# Short-Description: Monitoring system and time series database
# Description: Prometheus is a systems and services monitoring system. It
# collects metrics from configured targets at given
# intervals, evaluates rule expressions, displays the
# results, and can trigger alerts if some condition is
# observed to be true.
### END INIT INFO
# Author: Martín Ferrari <tincho@debian.org>
DESC="monitoring system and time series database"
DAEMON=/usr/bin/prometheus
NAME=prometheus
USER=prometheus
PIDFILE=/var/run/prometheus/prometheus.pid
LOGFILE=/var/log/prometheus/prometheus.log
CFGFILE=/etc/prometheus/prometheus.yml
HELPER=/usr/bin/daemon
HELPER_ARGS="--name=$NAME --output=$LOGFILE --pidfile=$PIDFILE --user=$USER"
ARGS="--config.file=/etc/prometheus/prometheus.yml \
--web.console.templates=/etc/prometheus/consoles \
--web.console.libraries=/etc/prometheus/console_libraries \
--storage.tsdb.path=/var/lib/prometheus/metrics2/ \
--storage.tsdb.retention.time=180d \
--query.max-samples=200000000 \
--web.enable-admin-api \
--storage.tsdb.wal-compression \
--web.enable-lifecycle"
config_check()
{
retcode=0
errors="$(/usr/bin/promtool check config $CFGFILE 2>&1)" || retcode=$?
if [ $retcode -ne 0 ]; then
log_failure_msg
echo "Configuration test failed. Output of config test was:" >&2
echo "$errors" >&2
return $retcode
fi
}
do_start_prepare()
{
mkdir -p `dirname $PIDFILE` || true
chown -R $USER: /var/lib/prometheus/metrics2
chown -R $USER: `dirname $LOGFILE`
chown -R $USER: `dirname $PIDFILE`
}
do_start_cmd()
{
# Return
# 0 if daemon has been started
# 1 if daemon was already running
# 2 if daemon could not be started
$HELPER $HELPER_ARGS --running && return 1
config_check || return 2
$HELPER $HELPER_ARGS -- $DAEMON $ARGS || return 2
return 0
}
do_stop_cmd()
{
# Return
# 0 if daemon has been stopped
# 1 if daemon was already stopped
# 2 if daemon could not be stopped
# other if a failure occurred
$HELPER $HELPER_ARGS --running || return 1
$HELPER $HELPER_ARGS --stop || return 2
# wait for the process to really terminate
for n in 1 2 3 4 5; do
sleep $n
$HELPER $HELPER_ARGS --running || break
done
$HELPER $HELPER_ARGS --running || return 0
return 2
}
do_reload()
{
log_daemon_msg "Reloading $DESC configuration files" "$NAME"
$HELPER $HELPER_ARGS --running || return 1
config_check || return 2
helper_pid=$(cat $PIDFILE)
if [ -z "$helper_pid" ]; then
log_failure_msg "Unable to find PID"
return 1
fi
start-stop-daemon --stop --signal 1 --quiet \
--ppid "$helper_pid" --exec "$DAEMON"
log_end_msg $?
}
- 服务的启停、重启
chmod +x /etc/init.d/prometheus
/etc/init.d/prometheus start/stop/restart
1.4 打开web页面
prometheus安装成功后,打开http://localhost:9090会出现如下页面,即表示安装成功
二 node_exporter部署和prometheus对接
2.1 下载
2.2 解压
tar xvf node_exporter-1.7.0.linux-amd64.tar.gz
2.3 运行
./node_exporter --web.listen-address=“192.168.10.131:9100” --log.level=warn
2.4 测试验证
curl -g -X GET http://192.168.10.131:9100/metrics?collect[]=cpu
注意这里一定要保证listen-address和url的ip端口一致,最好都用同网段ip,不要用localhost和127.0.0.1
2.5 prometheus配置
修改prometheus配置/etc/prometheus/prometheus.yml文件
scrape-configs:
- job_name: "prometheus"
static-configs:
- targets: ["192.168.10.131:9100"]
将node_exporter监控地址后,重启prometheus
systemctl restart prometheus
2.6 查看验证
通过prometheus自带的ui界面,可以看到新的监控节点已经接入
点击进去,能够看到监控的内容选项
三 grafana安装部署
3.1 下载
下载地址:https://dl.grafana.com/enterprise/release/grafana-enterprise_10.4.1_amd64.deb
3.2 安装
因为我使用的是离线安装,因此需要很多离线包,这里我统一下载放到云盘,需要自取
链接:https://pan.baidu.com/s/1k-6lmtGgAOCJug9btWW6SQ
提取码:20zs
注意,这里的离线包参考的是ubuntu 20.04的版本,其他版本的系统请自我调整
安装指令:
dpkg -i *.deb
查看版本号
grafana-cli -version
3.3 启动grafana
启动:systemctl start grafana-server
停止:systemctl stop grafana-server
重启:systemctl restart grafana-server
查看状态:systemctl status grafana-server
3.4 登录web页
web页地址:http://localhost:3000
用户名:admin
第一次登录,会让设置密码。