99 lines
2.3 KiB
YAML
99 lines
2.3 KiB
YAML
# QAUP 健康检查配置
|
|
# 用于配置各服务的健康检查参数
|
|
|
|
healthchecks:
|
|
qaup-app:
|
|
endpoint: "http://localhost:8080/actuator/health"
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 5
|
|
start_period: 120s
|
|
expected_status: 200
|
|
expected_content: '"status":"UP"'
|
|
|
|
qaup-nginx:
|
|
endpoint: "http://localhost/health"
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 30s
|
|
expected_status: 200
|
|
expected_content: "healthy"
|
|
|
|
qaup-postgres:
|
|
command: "pg_isready -h localhost -p 5432 -U postgres"
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 5
|
|
start_period: 60s
|
|
|
|
qaup-redis:
|
|
command: "redis-cli ping"
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 30s
|
|
expected_output: "PONG"
|
|
|
|
# 监控阈值配置
|
|
thresholds:
|
|
cpu_usage: 80 # CPU使用率告警阈值 (%)
|
|
memory_usage: 85 # 内存使用率告警阈值 (%)
|
|
disk_usage: 80 # 磁盘使用率告警阈值 (%)
|
|
response_time: 5000 # 响应时间告警阈值 (ms)
|
|
error_rate: 5 # 错误率告警阈值 (%)
|
|
|
|
# 日志监控配置
|
|
log_monitoring:
|
|
error_patterns:
|
|
- "ERROR"
|
|
- "FATAL"
|
|
- "Exception"
|
|
- "failed"
|
|
- "timeout"
|
|
|
|
warning_patterns:
|
|
- "WARN"
|
|
- "WARNING"
|
|
- "deprecated"
|
|
|
|
ignore_patterns:
|
|
- "health check"
|
|
- "actuator"
|
|
- "favicon.ico"
|
|
|
|
# 告警配置
|
|
alerts:
|
|
enabled: true
|
|
channels:
|
|
- type: "log"
|
|
path: "./logs/alerts.log"
|
|
- type: "email"
|
|
enabled: false
|
|
smtp_server: "smtp.example.com"
|
|
smtp_port: 587
|
|
username: "alerts@example.com"
|
|
password: "password"
|
|
recipients:
|
|
- "admin@example.com"
|
|
|
|
rules:
|
|
- name: "容器停止"
|
|
condition: "container_stopped"
|
|
severity: "critical"
|
|
message: "容器 {{container_name}} 已停止运行"
|
|
|
|
- name: "健康检查失败"
|
|
condition: "health_check_failed"
|
|
severity: "warning"
|
|
message: "服务 {{service_name}} 健康检查失败"
|
|
|
|
- name: "资源使用率过高"
|
|
condition: "resource_usage_high"
|
|
severity: "warning"
|
|
message: "{{resource_type}} 使用率达到 {{usage}}%"
|
|
|
|
- name: "错误日志增加"
|
|
condition: "error_log_increase"
|
|
severity: "warning"
|
|
message: "检测到错误日志数量异常增加" |