Prometheus && Grafana

快速配置单节点k8s

从官方仓库下载 minikube 工具

curl -LO https://storage.googleapis.com/minikube/releases/latest/minikube-linux-amd64
sudo install minikube-linux-amd64 /usr/local/bin/minikube

启动 minikube 集群

检查集群的状态

minikube start
# minikube start --cpus 1 --force  # cpu资源不足 2c 的时候强制启动
minikube status

给它一分钟的时间开始并再次检查状态

运行后，您应该会看到

host: Running
kubelet: Running
apiserver: Running
kubeconfig: Configured

配置监控组件

1. 安装 Node_exporter

wget https://github.com/prometheus/node_exporter/releases/download/v1.7.0/node_exporter-1.7.0.linux-amd64.tar.gz

tar -xvf node_exporter-1.7.0.linux-amd64.tar.gz && cd node_exporter-1.7.0.linux-amd64 && sudo cp node_exporter /usr/local/bin

sudo useradd -rs /bin/false node_exporter && echo -e "[Unit]\nDescription=Node Exporter\nAfter=network.target\n\n[Service]\nUser=node_exporter\nGroup=node_exporter\nType=simple\nExecStart=/usr/local/bin/node_exporter\n\n[Install]\nWantedBy=multi-user.target" | sudo tee /etc/systemd/system/node_exporter.service > /dev/null && sudo systemctl daemon-reload && sudo systemctl start node_exporter

curl 127.0.0.1:9100/metrics

2 安装 Prometheus

wget https://github.com/prometheus/prometheus/releases/download/v2.50.1/prometheus-2.50.1.linux-amd64.tar.gz

tar -xvf prometheus-2.50.1.linux-amd64.tar.gz && cd prometheus-2.50.1.linux-amd64 && sudo cp prometheus /usr/local/bin

sudo useradd -rs /bin/false prometheus && sudo mkdir /etc/prometheus /var/lib/prometheus && sudo cp -r consoles/ console_libraries/ /etc/prometheus/ && sudo chown -R prometheus:prometheus /etc/prometheus /var/lib/prometheus && echo -e "[Unit]\nDescription=Prometheus\nAfter=network.target\n\n[Service]\nUser=prometheus\nGroup=prometheus\nType=simple\nExecStart=/usr/local/bin/prometheus --config.file=/etc/prometheus/prometheus.yml --storage.tsdb.path=/var/lib/prometheus --web.console.templates=/etc/prometheus/consoles --web.console.libraries=/etc/prometheus/console_libraries\n\n[Install]\nWantedBy=multi-user.target" | sudo tee /etc/systemd/system/prometheus.service > /dev/null && sudo systemctl daemon-reload && sudo systemctl start prometheus

cat > /etc/prometheus/prometheus.yml << 'EOF'
# 1 全局配置
global:
  scrape_interval: 5s  # 数据采集间隔，默认每1分钟，这里改为每5秒
  evaluation_interval: 5s  # 规则评估间隔（如告警规则），默认每1分钟，这里改为每5秒
  # scrape_timeout: 10s  # 采集超时时间，默认10秒（此处未显式配置，使用默认值）

# 2 告警组件
alerting:
  alertmanagers:
    - static_configs:
        - targets:
          # - alertmanager:9093  # 注释掉的Alertmanager地址，暂不启用Alertmanager
# 告警规则文件
rule_files:
  # - "first_rules.yml"
  # - "second_rules.yml"

# 3 采集配置
scrape_configs:
  # 数组中的第一个采集任务
  - job_name: "Node Exporter"
    # metrics_path: '/metrics'  # 目标服务暴露指标的路径，默认就是'/metrics'（可省略）
    # scheme: 'http'  # 通信协议，默认http（可省略）
    static_configs:    # 静态配置监控目标
      - targets: ["0.0.0.0:9100"]
      - targets: ["127.0.0.1:9100"] 
EOF

sudo systemctl restart prometheus

curl 127.0.0.1:9090

3 安装 Grafana

sudo apt-get install -y apt-transport-https software-properties-common wget &&
sudo mkdir -p /etc/apt/keyrings/ &&
wget -q -O - https://apt.grafana.com/gpg.key | gpg --dearmor | sudo tee /etc/apt/keyrings/grafana.gpg > /dev/null &&
echo "deb [signed-by=/etc/apt/keyrings/grafana.gpg] https://apt.grafana.com stable main" | sudo tee -a /etc/apt/sources.list.d/grafana.list &&
sudo apt-get update && sudo apt-get install -y grafana

sudo systemctl start grafana-server && sudo systemctl status grafana-server
curl 127.0.0.1:3000
admin/admin

4 配置 Grafana

# 1. 添加数据源
# 2. 创建Dashboard
315  
1860  
13671
13677