Prometheus 监控套件安装配置

1
2
3

wget https://github.com/prometheus/prometheus/releases/download/v2.40.4/prometheus-2.40.4.linux-amd64.tar.gz
tar xzvf prometheus-2.40.4.linux-amd64.tar.gz
mv prometheus-2.40.4.linux-amd64 /opt/prometheus

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12

[Unit]
Description=Prometheus
Documentation=https://prometheus.io/
After=network.target

[Service]
Type=simple
ExecStart=/opt/prometheus/prometheus --config.file=/opt/prometheus/prometheus.yml
Restart=on-failure

[Install]
WantedBy=multi-user.target

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43

# 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"]
  - job_name: node
    static_configs:
      - targets: ['10.2.1.3:9100','10.2.1.2:9100']

  # kube-state-metrics
  - job_name: k8s
    static_configs:
      - targets: ['10.2.1.3:8080']
  - job_name: 'pushgateway'
    honor_labels: true
    static_configs:
      - targets: [':9091']
       labels:
         instance: pushgateway

1
2
3
4

wget https://github.com/prometheus/node_exporter/releases/download/v1.4.0/node_exporter-1.4.0.linux-amd64.tar.gz

tar xzfv node_exporter-1.4.0.linux-amd64.tar.gz -C /opt
mv /opt/node_exporter-1.4.0.linux-amd64 /opt/node_exporter

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16

[Unit]
Description=Prometheus exporter for machine metrics, written in Go with pluggable metric collectors.
Documentation=https://github.com/prometheus/node_exporter
After=network.target

[Service]
LimitNOFILE=65535
LimitNPROC=65535
LimitCORE=infinity
ExecStart=/opt/node_exporter/node_exporter
Restart=on-failure
StartLimitInterval=1
RestartSec=3

[Install]
WantedBy=multi-user.target

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

wget https://dl.grafana.com/enterprise/release/grafana-enterprise_9.3.0_amd64.deb
sudo apt-get install -y adduser libfontconfig1
dpkg -i grafana-enterprise_9.3.0_amd64.deb
systemctl enable grafana-server.service
systemctl start grafana-server.service
grafana-cli plugins install grafana-piechart-panel
# 如果超时，通过科学下载后
unzip grafana-piechart-panel-1.6.4.any.zip
mv grafana-piechart-panel /var/lib/grafana/plugins/
systemctl restart grafana-server.service

1
2

# ls
cluster-role-binding.yaml  cluster-role.yaml  deployment.yaml  service-account.yaml  service.yaml

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12

[Unit]
Description=pushgateway
Documentation=https://prometheus.io/
After=network.target

[Service]
Type=simple
ExecStart=/opt/pushgateway/pushgateway
Restart=on-failure

[Install]
WantedBy=multi-user.target