利用脚本部署node_exporter
#!/bin/bash
#wget https://github.com/prometheus/node_exporter/releases/download/v0.17.0/node_exporter-0.17.0.linux-amd64.tar.gz
rsync -avPLl helen@172.16.6.86:/Users/helen/hoo-pro/hoo-PRO/software/prometheus/node_exporter-0.17.0.linux-amd64.tar.gz ./
tar zxf node_exporter-0.17.0.linux-amd64.tar.gz
mv node_exporter-0.17.0.linux-amd64 /usr/local/node_exporter
cat <<EOF >/usr/lib/systemd/system/node_exporter.service
[Unit]
Description=https://prometheus.io
[Service]
Restart=on-failure
ExecStart=/usr/local/node_exporter/node_exporter --collector.systemd --collector.systemd.unit-whitelist=(docker|kubelet|kube-proxy|flanneld).service
[Install]
WantedBy=multi-user.target
EOF
systemctl daemon-reload
systemctl enable node_exporter
systemctl restart node_exporter
在需要被普罗米修斯监控的ecs上执行此脚本
bash node_exporter.sh
然后修改prometheus.yml文件
# 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=` to any timeseries scraped from this config.
- job_name: 'prometheus'
# metrics_path defaults to '/metrics'
# scheme defaults to 'http'.
static_configs:
- targets: ['localhost:9090','10.10.249.59:9100','10.10.249.60:9100','192.168.1.35:8080','192.168.1.35:9100','10.10.249.55:9100']
# labels:
# instance: k8s-node01
修改完成,重启普罗米修斯;