# 1. 在Prometheus中配置告警规则
cat > alert.rules << EOF
groups:
– name: oceanbase_alerts
rules:
– alert: OceanBaseInstanceDown
expr: up{job=”oceanbase”} == 0
for: 5m
labels:
severity: critical
annotations:
summary: “OceanBase实例宕机”
description: “OceanBase实例 {{ $labels.instance }} 已宕机超过5分钟”
– alert: OceanBaseHighCPUUsage
expr: 100 – (avg by(instance) (irate(node_cpu_seconds_total{mode=”idle”}[5m])) * 100) > 80
for: 5m
labels:
severity: warning
annotations:
，更多视频教程www.fgedu.net.cn。
summary: “OceanBase CPU使用率高”
description: “OceanBase实例 {{ $labels.instance }} CPU使用率超过80%”
– alert: OceanBaseHighMemoryUsage
expr: (node_memory_MemTotal_bytes – node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100 > 80
for: 5m
labels:
severity: warning
annotations:
summary: “OceanBase内存使用率高”
description: “OceanBase实例 {{ $labels.instance }} 内存使用率超过80%”
EOF
# 2. 更新Prometheus配置
cat > prometheus.yml << EOF
global:
scrape_interval: 15s
rule_files:
– “alert.rules”
scrape_configs:
– job_name: ‘oceanbase’
static_configs:
– targets: [‘192.168.1.100:2881’, ‘192.168.1.101:2881’, ‘192.168.1.102:2881’]
alerting:
alertmanagers:
– static_configs:
– targets: [‘localhost:9093’]
EOF
# 3. 安装和配置Alertmanager
wget https://github.com/prometheus/alertmanager/releases/download/v0.25.0/alertmanager-0.25.0.linux-amd64.tar.gz
tar -xzf alertmanager-0.25.0.linux-amd64.tar.gz
cd alertmanager-0.25.0.linux-amd64
cat > alertmanager.yml << EOF
global:
resolve_timeout: 5m
route:
group_by: [‘alertname’]
group_wait: 30s
group_interval: 5m
repeat_interval: 1h
receiver: ’email’
receivers:
，更多学习教程公众号风哥教程itpux_com。
– name: ’email’
email_configs:
– to: ‘admin@fgedu.net.cn’
from: ‘alertmanager@fgedu.net.cn’
smarthost: ‘smtp.fgedu.net.cn:25’
auth_username: ‘alertmanager’
auth_password: ‘password’
EOF
# 4. 启动Alertmanager
./alertmanager –config.file=alertmanager.yml