A way to install metrics exporter based monitoring for a group of nodes or cluster

cvs/monitors/metrics_exp/.env.example

@@ -0,0 +1,37 @@
+# AMD GPU Fleet Monitoring - Environment Configuration
+# Copy this file to .env and customize values
+
+# ============================================
+# PostgreSQL Configuration
+# ============================================
+POSTGRES_DB=fleet_monitor
+POSTGRES_USER=fleet
+POSTGRES_PASSWORD=change_this_password
+
+# ============================================
+# Prometheus Configuration
+# ============================================
+# Data retention settings
+PROMETHEUS_RETENTION_TIME=15d
+PROMETHEUS_RETENTION_SIZE=50GB
+
+# ============================================
+# Grafana Configuration
+# ============================================
+GRAFANA_ADMIN_USER=admin
+GRAFANA_ADMIN_PASSWORD=change_this_password
+GRAFANA_ROOT_URL=http://localhost:30030
+# Generate API key from Grafana UI: Configuration > API Keys
+GRAFANA_API_KEY=
+
+# ============================================
+# Fleet Manager Configuration
+# ============================================
+# Secret key for JWT tokens and encryption (change in production!)
+SECRET_KEY=your-secret-key-change-in-production
+
+# ============================================
+# Loki Configuration (via loki-config.yml)
+# ============================================
+# Default retention: 168h (7 days)
+# Modify server/config/loki/loki-config.yml for custom retention

cvs/monitors/metrics_exp/.gitignore

@@ -0,0 +1,72 @@
+# Environment files
+.env
+*.env.local
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+venv/
+env/
+.venv/
+
+# Node.js
+node_modules/
+dist/
+.npm
+*.log
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+
+# Docker
+.docker/
+
+# Secrets
+*.pem
+*.key
+id_rsa*
+ssh_keys/
+
+# Database
+*.db
+*.sqlite
+
+# Volumes (when running locally)
+prometheus_data/
+loki_data/
+grafana_data/
+postgres_data/
+
+# Auto-generated target files (contain real IPs/hostnames)
+server/config/prometheus/targets/*.json
+!server/config/prometheus/targets/.gitkeep
+
+# Environment-specific scripts
+nuke-and-rebuild.sh
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Build artifacts
+*.egg-info/
+build/
+*.egg
+
+# Testing
+.coverage
+htmlcov/
+.pytest_cache/
+
+# Temporary files
+*.tmp
+*.temp
+tmp/
+temp/

cvs/monitors/metrics_exp/Dockerfile.fleet-manager

@@ -0,0 +1,60 @@
+# AMD GPU Fleet Manager - Docker Image
+# Multi-stage build: Node for frontend, Python for backend
+
+# Stage 1: Build React frontend
+FROM node:20-alpine AS frontend-builder
+
+WORKDIR /app/ui
+
+# Copy package files
+COPY server/ui/package.json server/ui/package-lock.json* ./
+
+# Install dependencies
+RUN npm install
+
+# Copy UI source
+COPY server/ui/ ./
+
+# Build production bundle
+RUN npm run build
+
+# Stage 2: Python backend with frontend
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    curl \
+    openssh-client \
+    unzip \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Python dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY server/fleet_manager /app/fleet_manager
+COPY server/config /app/config
+COPY scripts /app/scripts
+COPY templates /app/templates
+
+# Copy built frontend from Stage 1
+COPY --from=frontend-builder /app/ui/dist /app/fleet_manager/static
+
+# Create directories
+RUN mkdir -p /app/ssh_keys /prometheus-config /prometheus-targets
+
+# Set permissions
+RUN chmod +x /app/scripts/*.sh 2>/dev/null || true
+
+# Expose port
+EXPOSE 8080
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:8080/health || exit 1
+
+# Run application
+CMD ["uvicorn", "fleet_manager.main:app", "--host", "0.0.0.0", "--port", "8080"]