managarten/docker/prometheus/prometheus.yml
Till JS 06107f6a52 feat(mana-video-gen): add AI video generation service with LTX-Video
New GPU service for fast text-to-video generation using LTX-Video (~2B params)
on the RTX 3090. Generates 480p clips in 10-30 seconds, uses ~10GB VRAM.
Includes Cloudflare Tunnel route, Prometheus monitoring, and health checks.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-02 01:17:47 +02:00

366 lines
9.7 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-auth'
static_configs:
- targets: ['mana-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: REMOVED — migrated to local-first
# Contacts Backend
- job_name: 'contacts-backend'
static_configs:
- targets: ['contacts-backend:3033']
metrics_path: '/metrics'
scrape_interval: 30s
# Storage Backend
- job_name: 'storage-backend'
static_configs:
- targets: ['storage-backend:3034']
metrics_path: '/metrics'
scrape_interval: 30s
# Presi Backend: REMOVED — replaced by Hono server
# Nutriphi Backend
- job_name: 'nutriphi-backend'
static_configs:
- targets: ['nutriphi-backend:3038']
metrics_path: '/metrics'
scrape_interval: 30s
# SkillTree Backend: REMOVED — migrated to local-first
# Photos Backend: REMOVED — migrated to local-first + direct mana-media
# CityCorners Backend: REMOVED — migrated to local-first
# Zitare Backend: REMOVED — migrated to local-first
# Mukke Backend
- job_name: 'mukke-backend'
static_configs:
- targets: ['mukke-backend:3037']
metrics_path: '/metrics'
scrape_interval: 30s
# Planta Backend
- job_name: 'planta-backend'
static_configs:
- targets: ['planta-backend:3039']
metrics_path: '/metrics'
scrape_interval: 30s
# Picture Backend
- job_name: 'picture-backend'
static_configs:
- targets: ['picture-backend:3035']
metrics_path: '/metrics'
scrape_interval: 30s
# ============================================
# Core Services
# ============================================
# Mana LLM Gateway (Ollama + Google Fallback)
- job_name: 'mana-llm'
static_configs:
- targets: ['mana-llm:3020']
metrics_path: '/metrics'
scrape_interval: 15s
# Mana Search Service
- job_name: 'mana-search'
static_configs:
- targets: ['mana-search:3012']
metrics_path: '/metrics'
scrape_interval: 30s
# Mana Media Service
- job_name: 'mana-media'
static_configs:
- targets: ['mana-media:3011']
metrics_path: '/metrics'
scrape_interval: 30s
# Matrix Synapse
- job_name: 'synapse'
static_configs:
- targets: ['synapse:9002']
metrics_path: '/_synapse/metrics'
scrape_interval: 30s
# ============================================
# GPU Server (Windows PC, LAN: 192.168.178.11)
# ============================================
# GPU: LLM Gateway
- job_name: 'gpu-llm'
static_configs:
- targets: ['192.168.178.11:3025']
labels:
instance: 'gpu-server'
metrics_path: '/metrics'
scrape_interval: 15s
# GPU: Speech-to-Text (WhisperX)
- job_name: 'gpu-stt'
static_configs:
- targets: ['192.168.178.11:3020']
labels:
instance: 'gpu-server'
metrics_path: '/health'
scrape_interval: 30s
# GPU: Text-to-Speech
- job_name: 'gpu-tts'
static_configs:
- targets: ['192.168.178.11:3022']
labels:
instance: 'gpu-server'
metrics_path: '/health'
scrape_interval: 30s
# GPU: Image Generation (FLUX.2)
- job_name: 'gpu-image-gen'
static_configs:
- targets: ['192.168.178.11:3023']
labels:
instance: 'gpu-server'
metrics_path: '/health'
scrape_interval: 30s
# GPU: Video Generation (LTX-Video)
- job_name: 'gpu-video-gen'
static_configs:
- targets: ['192.168.178.11:3026']
labels:
instance: 'gpu-server'
metrics_path: '/health'
scrape_interval: 30s
# ============================================
# Go Infrastructure Services
# ============================================
# API Gateway (Go)
- job_name: 'mana-api-gateway'
static_configs:
- targets: ['mana-api-gateway:3016']
metrics_path: '/metrics'
scrape_interval: 15s
# Matrix Bot (Go) — consolidated 21 bots
- job_name: 'mana-matrix-bot'
static_configs:
- targets: ['mana-matrix-bot:4000']
metrics_path: '/metrics'
scrape_interval: 30s
# Sync Server (Go) — local-first data sync
- job_name: 'mana-sync'
static_configs:
- targets: ['mana-core-sync:3051']
metrics_path: '/metrics'
scrape_interval: 30s
# Notification Service (Go) — email, push, matrix, webhook
- job_name: 'mana-notify'
static_configs:
- targets: ['mana-core-notify:3013']
metrics_path: '/metrics'
scrape_interval: 30s
# Crawler Service (Go)
- job_name: 'mana-crawler'
static_configs:
- targets: ['mana-crawler:3014']
metrics_path: '/metrics'
scrape_interval: 30s
# ============================================
# Blackbox Exporter — HTTP Uptime Probes
# ============================================
# Web Apps (SvelteKit frontends)
- job_name: 'blackbox-web'
metrics_path: /probe
params:
module: [http_2xx]
static_configs:
- targets:
- https://mana.how
- https://chat.mana.how
- https://todo.mana.how
- https://calendar.mana.how
- https://contacts.mana.how
- https://clock.mana.how
- https://photos.mana.how
- https://picture.mana.how
- https://storage.mana.how
- https://presi.mana.how
- https://nutriphi.mana.how
- https://planta.mana.how
- https://calc.mana.how
- https://zitare.mana.how
- https://cards.mana.how
- https://skilltree.mana.how
- https://mukke.mana.how
- https://citycorners.mana.how
- https://playground.mana.how
- https://whopxl.mana.how
- https://arcade.mana.how
relabel_configs:
- source_labels: [__address__]
target_label: __param_target
- source_labels: [__param_target]
target_label: instance
- target_label: __address__
replacement: blackbox-exporter:9115
# API Health Endpoints
- job_name: 'blackbox-api'
metrics_path: /probe
params:
module: [http_health]
static_configs:
- targets:
- https://auth.mana.how/health
- https://api.mana.how/health
- https://chat-api.mana.how/health
- https://todo-api.mana.how/health
- https://calendar-api.mana.how/health
- https://contacts-api.mana.how/health
- https://storage-api.mana.how/health
- https://nutriphi-api.mana.how/health
- https://planta-api.mana.how/health
- https://picture-api.mana.how/health
relabel_configs:
- source_labels: [__address__]
target_label: __param_target
- source_labels: [__param_target]
target_label: instance
- target_label: __address__
replacement: blackbox-exporter:9115
# Infrastructure & Monitoring Tools
- job_name: 'blackbox-infra'
metrics_path: /probe
params:
module: [http_2xx]
static_configs:
- targets:
- https://git.mana.how
- https://grafana.mana.how
- https://stats.mana.how
- https://glitchtip.mana.how
- https://matrix.mana.how
- https://element.mana.how
relabel_configs:
- source_labels: [__address__]
target_label: __param_target
- source_labels: [__param_target]
target_label: instance
- target_label: __address__
replacement: blackbox-exporter:9115
# GPU Server Services
- job_name: 'blackbox-gpu'
metrics_path: /probe
params:
module: [http_2xx]
static_configs:
- targets:
- https://gpu-ollama.mana.how
- https://gpu-stt.mana.how
- https://gpu-tts.mana.how
- https://gpu-img.mana.how
- https://gpu-video.mana.how
relabel_configs:
- source_labels: [__address__]
target_label: __param_target
- source_labels: [__param_target]
target_label: instance
- target_label: __address__
replacement: blackbox-exporter:9115
# ============================================
# Pushgateway (deploy metrics, batch jobs)
# ============================================
- job_name: 'pushgateway'
honor_labels: true
static_configs:
- targets: ['pushgateway:9091']