# 安装Prometheus
wget https://github.com/prometheus/prometheus/releases/download/v2.35.0/prometheus-2.35.0.linux-amd64.tar.gz
tar -xzvf prometheus-2.35.0.linux-amd64.tar.gz -C /bigdata/app

# 安装Grafana
wget https://dl.grafana.com/oss/release/grafana-8.5.0.linux-amd64.tar.gz
tar -xzvf grafana-8.5.0.linux-amd64.tar.gz -C /bigdata/app

# 安装Node Exporter
wget https://github.com/prometheus/node_exporter/releases/download/v1.3.1/node_exporter-1.3.1.linux-amd64.tar.gz
tar -xzvf node_exporter-1.3.1.linux-amd64.tar.gz -C /bigdata/app

# 安装JMX Exporter
wget https://repo1.maven.org/maven2/io/prometheus/jmx/jmx_prometheus_javaagent/0.16.1/jmx_prometheus_javaagent-0.16.1.jar
cp jmx_prometheus_javaagent-0.16.1.jar /bigdata/app

# 配置Prometheus
cat > /bigdata/app/prometheus-2.35.0.linux-amd64/prometheus.yml << 'EOF' global: scrape_interval: 15s evaluation_interval: 15s scrape_configs: - job_name: 'node' static_configs: - targets: ['fgedu01:9100', 'fgedu02:9100', 'fgedu03:9100'] - job_name: 'hadoop' static_configs: - targets: ['fgedu01:9104', 'fgedu02:9104', 'fgedu03:9104'] - job_name: 'hive' static_configs: - targets: ['fgedu01:9105'] - job_name: 'hbase' static_configs: - targets: ['fgedu01:9106', 'fgedu02:9106', 'fgedu03:9106'] EOF # 配置JMX Exporter for Hadoop echo 'HEAP_OPTS="$HEAP_OPTS -javaagent:/bigdata/app/jmx_prometheus_javaagent-0.16.1.jar=9104:/bigdata/app/prometheus-2.35.0.linux-amd64/hadoop.yml"' >> /bigdata/app/hadoop-3.3.5/etc/hadoop/hadoop-env.sh

# 启动Node Exporter
nohup /bigdata/app/node_exporter-1.3.1.linux-amd64/node_exporter > /bigdata/fgdata/logs/node_exporter.log 2>&1 &

# 启动Prometheus
nohup /bigdata/app/prometheus-2.35.0.linux-amd64/prometheus –config.file=/bigdata/app/prometheus-2.35.0.linux-amd64/prometheus.yml > /bigdata/fgdata/logs/prometheus.log 2>&1 &

# 启动Grafana
nohup /bigdata/app/grafana-8.5.0/bin/grafana-server > /bigdata/fgdata/logs/grafana.log 2>&1 &

# 创建告警规则文件
cat > /bigdata/app/prometheus-2.35.0.linux-amd64/rules.yml << 'EOF' groups: - name: node_alerts rules: - alert: HighCPUUsage expr: (100 - (avg by(instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
for: 5m
labels:
severity: warning
annotations:
summary: “High CPU Usage on {{ $labels.instance }}”
description: “CPU usage is above 80% for 5 minutes”

– alert: HighMemoryUsage
expr: (node_memory_MemTotal_bytes – node_memory_MemFree_bytes – node_memory_Buffers_bytes – node_memory_Cached_bytes) / node_memory_MemTotal_bytes * 100 > 85
for: 5m
labels:
severity: warning
annotations:
summary: “High Memory Usage on {{ $labels.instance }}”
description: “Memory usage is above 85% for 5 minutes”

– alert: DiskSpaceLow
expr: (node_filesystem_size_bytes{mountpoint=”/”} – node_filesystem_free_bytes{mountpoint=”/”}) / node_filesystem_size_bytes{mountpoint=”/”} * 100 > 90
for: 5m
labels:
severity: critical
annotations:
summary: “Disk Space Low on {{ $labels.instance }}”
description: “Disk space usage is above 90% for 5 minutes”

– name: hadoop_alerts
rules:
– alert: HDFSSafeMode
expr: hdfs_namenode_safemode{state=”in safemode”} == 1
for: 1m
labels:
severity: critical
annotations:
summary: “HDFS in Safe Mode”
description: “HDFS is in safe mode”

– alert: YARNResourceManagerDown
expr: yarn_resourcemanager_active == 0
for: 1m
labels:
severity: critical
annotations:
summary: “YARN ResourceManager Down”
description: “YARN ResourceManager is not active”
EOF

# 配置Prometheus告警
cat >> /bigdata/app/prometheus-2.35.0.linux-amd64/prometheus.yml << 'EOF' rule_files: - "rules.yml" alerting: alertmanagers: - static_configs: - targets: ['localhost:9093'] EOF