forked from xiaohei/taiji-AI-PAD
配置内容: 1. 更新Prometheus配置 - 添加服务标签 - 优化抓取间隔和超时 - 配置NATS监控端点 - 添加外部标签 2. 创建Grafana数据源配置 - 配置Prometheus数据源 - 设置为默认数据源 - 配置查询超时和间隔 3. 创建Grafana仪表板配置 - 配置自动发现仪表板 - 支持UI更新 4. 创建监控仪表板 - taiji-monitoring.json - 包含HTTP请求、Agent、工具调用、MCP请求等监控面板 - 10个监控面板,覆盖系统关键指标 监控指标: - HTTP请求总数和耗时 - 活跃Agent数 - Agent注册统计 - 工具调用统计 - MCP请求统计 - WebSocket连接数 - 系统连接状态(Redis、NATS、Database) - 函数注册表大小 - 函数工具调用统计
79 lines
2.0 KiB
YAML
79 lines
2.0 KiB
YAML
global:
|
|
scrape_interval: 15s
|
|
evaluation_interval: 15s
|
|
external_labels:
|
|
cluster: 'taiji-ai-pad'
|
|
environment: 'production'
|
|
|
|
# 告警规则配置(可选,未来可添加)
|
|
# rule_files:
|
|
# - "alert_rules.yml"
|
|
|
|
# Alertmanager配置(可选,未来可添加)
|
|
# alerting:
|
|
# alertmanagers:
|
|
# - static_configs:
|
|
# - targets: ['alertmanager:9093']
|
|
|
|
scrape_configs:
|
|
# MCP Server
|
|
- job_name: 'mcp-server'
|
|
static_configs:
|
|
- targets: ['mcp-server:8000']
|
|
labels:
|
|
service: 'mcp-server'
|
|
component: 'api'
|
|
metrics_path: '/metrics'
|
|
scrape_interval: 10s
|
|
scrape_timeout: 5s
|
|
|
|
# Data Ingestion Service
|
|
- job_name: 'data-ingestion'
|
|
static_configs:
|
|
- targets: ['data-ingestion:8000']
|
|
labels:
|
|
service: 'data-ingestion'
|
|
component: 'api'
|
|
metrics_path: '/metrics'
|
|
scrape_interval: 10s
|
|
scrape_timeout: 5s
|
|
|
|
# LiteLLM Gateway (如果有metrics端点)
|
|
- job_name: 'litellm-gateway'
|
|
static_configs:
|
|
- targets: ['litellm-gateway:4000']
|
|
labels:
|
|
service: 'litellm-gateway'
|
|
component: 'gateway'
|
|
metrics_path: '/metrics'
|
|
scrape_interval: 10s
|
|
scrape_timeout: 5s
|
|
# 如果端点不存在,Prometheus会记录错误但不会影响其他服务
|
|
|
|
# PostgreSQL (需要postgres_exporter,当前未部署)
|
|
# - job_name: 'postgres'
|
|
# static_configs:
|
|
# - targets: ['postgres-exporter:9187']
|
|
# labels:
|
|
# service: 'postgres'
|
|
# component: 'database'
|
|
|
|
# Redis (需要redis_exporter,当前未部署)
|
|
# - job_name: 'redis'
|
|
# static_configs:
|
|
# - targets: ['redis-exporter:9121']
|
|
# labels:
|
|
# service: 'redis'
|
|
# component: 'cache'
|
|
|
|
# NATS (NATS自带监控端点)
|
|
- job_name: 'nats'
|
|
static_configs:
|
|
- targets: ['nats:8222']
|
|
labels:
|
|
service: 'nats'
|
|
component: 'message-queue'
|
|
metrics_path: '/varz'
|
|
scrape_interval: 30s
|
|
scrape_timeout: 10s
|