mirror of
https://github.com/Memo-2023/mana-monorepo.git
synced 2026-05-14 21:41:09 +02:00
acc8de36ee
Medium priority stability improvements: Alerting: - Add vmalert for evaluating Prometheus alert rules - Add alertmanager for alert routing and grouping - Add alert-notifier service for Telegram/ntfy notifications - Enable cadvisor scraping in prometheus config Disk Monitoring: - Add check-disk-space.sh for hourly disk monitoring - Alert on 80% (warning) and 90% (critical) thresholds - Auto-cleanup Docker when disk is critical - Add com.manacore.disk-check.plist for LaunchD Weekly Reports: - Add weekly-report.sh for system health summary - Includes: backup status, disk usage, container health, database stats, error log summary - Runs every Sunday at 10 AM via LaunchD Health Check Updates: - Add checks for vmalert, alertmanager, alert-notifier Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
113 lines
2.8 KiB
YAML
113 lines
2.8 KiB
YAML
# ManaCore Prometheus Configuration
|
|
# Scrapes metrics from all services
|
|
|
|
global:
|
|
scrape_interval: 15s
|
|
evaluation_interval: 15s
|
|
|
|
# Load alerting rules
|
|
rule_files:
|
|
- /etc/prometheus/alerts.yml
|
|
|
|
# Alertmanager configuration
|
|
alerting:
|
|
alertmanagers:
|
|
- static_configs:
|
|
- targets: ['alertmanager:9093']
|
|
|
|
scrape_configs:
|
|
# Prometheus self-monitoring
|
|
- job_name: 'prometheus'
|
|
static_configs:
|
|
- targets: ['localhost:9090']
|
|
|
|
# Host system metrics via node-exporter
|
|
- job_name: 'node'
|
|
static_configs:
|
|
- targets: ['node-exporter:9100']
|
|
relabel_configs:
|
|
- source_labels: [__address__]
|
|
target_label: instance
|
|
replacement: 'mac-mini'
|
|
|
|
# Docker container metrics via cAdvisor
|
|
- job_name: 'cadvisor'
|
|
static_configs:
|
|
- targets: ['cadvisor:8080']
|
|
|
|
# PostgreSQL metrics
|
|
- job_name: 'postgres'
|
|
static_configs:
|
|
- targets: ['postgres-exporter:9187']
|
|
|
|
# Redis metrics
|
|
- job_name: 'redis'
|
|
static_configs:
|
|
- targets: ['redis-exporter:9121']
|
|
|
|
# ============================================
|
|
# Application Backends (after /metrics added)
|
|
# ============================================
|
|
|
|
# Auth Service
|
|
- job_name: 'mana-core-auth'
|
|
static_configs:
|
|
- targets: ['mana-core-auth:3001']
|
|
metrics_path: '/metrics'
|
|
scrape_interval: 30s
|
|
|
|
# Chat Backend
|
|
- job_name: 'chat-backend'
|
|
static_configs:
|
|
- targets: ['chat-backend:3030']
|
|
metrics_path: '/metrics'
|
|
scrape_interval: 30s
|
|
|
|
# Todo Backend
|
|
- job_name: 'todo-backend'
|
|
static_configs:
|
|
- targets: ['todo-backend:3031']
|
|
metrics_path: '/metrics'
|
|
scrape_interval: 30s
|
|
|
|
# Calendar Backend
|
|
- job_name: 'calendar-backend'
|
|
static_configs:
|
|
- targets: ['calendar-backend:3032']
|
|
metrics_path: '/metrics'
|
|
scrape_interval: 30s
|
|
|
|
# Clock Backend
|
|
- job_name: 'clock-backend'
|
|
static_configs:
|
|
- targets: ['clock-backend:3033']
|
|
metrics_path: '/metrics'
|
|
scrape_interval: 30s
|
|
|
|
# Contacts Backend
|
|
- job_name: 'contacts-backend'
|
|
static_configs:
|
|
- targets: ['contacts-backend:3034']
|
|
metrics_path: '/metrics'
|
|
scrape_interval: 30s
|
|
|
|
# Storage Backend (disabled - no /metrics endpoint yet)
|
|
# - job_name: 'storage-backend'
|
|
# static_configs:
|
|
# - targets: ['storage-backend:3035']
|
|
# metrics_path: '/metrics'
|
|
# scrape_interval: 30s
|
|
|
|
# Presi Backend (disabled - no /metrics endpoint yet)
|
|
# - job_name: 'presi-backend'
|
|
# static_configs:
|
|
# - targets: ['presi-backend:3036']
|
|
# metrics_path: '/metrics'
|
|
# scrape_interval: 30s
|
|
|
|
# Nutriphi Backend (disabled - no /metrics endpoint yet)
|
|
# - job_name: 'nutriphi-backend'
|
|
# static_configs:
|
|
# - targets: ['nutriphi-backend:3037']
|
|
# metrics_path: '/metrics'
|
|
# scrape_interval: 30s
|