- Added /metrics/gpu-health endpoint with live health scores (VRAM 40%, temp 30%, load 30%) - Added /metrics/latency endpoint for dashboard KPIs - Added GPU_LABELS for human-readable model names - Dashboard v2: rewired to real data endpoints - KPI cards: GPUs online, circuit trips, avg latency, req/min, active requests - Health scores from actual gpu_health_score() function - Rolling 60-sample history chart (real data, no simulation) - Status: green/yellow/red based on tripped circuits - No CDN dependency (pure CSS) - Auto-refresh every 15s - nginx: /dashboard/ serves static files with cache headers - docker-compose: dashboard volume mount Co-authored-by: Abiba <abiba@sysloggh.com>
119 lines
3.7 KiB
Nginx Configuration File
119 lines
3.7 KiB
Nginx Configuration File
worker_processes auto;
|
|
error_log /var/log/nginx/error.log warn;
|
|
pid /var/run/nginx.pid;
|
|
|
|
events { worker_connections 1024; }
|
|
|
|
http {
|
|
include /etc/nginx/mime.types;
|
|
default_type application/octet-stream;
|
|
|
|
log_format main '$remote_addr - $remote_user [$time_local] "$request" '
|
|
'$status $body_bytes_sent "$http_referer" '
|
|
'"$http_user_agent" rt=$request_time';
|
|
access_log /var/log/nginx/access.log main;
|
|
error_log /var/log/nginx/error.log;
|
|
sendfile on;
|
|
keepalive_timeout 65;
|
|
|
|
upstream router_api { server router:9000; }
|
|
upstream dashboard_ui { server dashboard:3000; }
|
|
upstream litellm_backend { server litellm:4000; }
|
|
|
|
server {
|
|
listen 80;
|
|
|
|
# Security headers
|
|
add_header X-Content-Type-Options nosniff always;
|
|
add_header X-Frame-Options SAMEORIGIN always;
|
|
add_header X-XSS-Protection "1; mode=block" always;
|
|
|
|
# Disable buffering for SSE streams
|
|
proxy_buffering off;
|
|
|
|
# API through router
|
|
location /v1/ {
|
|
proxy_pass http://router_api;
|
|
proxy_http_version 1.1;
|
|
proxy_set_header Host $host;
|
|
proxy_set_header X-Real-IP $remote_addr;
|
|
proxy_set_header Authorization $http_authorization;
|
|
proxy_connect_timeout 10s;
|
|
proxy_read_timeout 600s;
|
|
proxy_buffering off;
|
|
}
|
|
|
|
location /admin/ {
|
|
proxy_pass http://router_api;
|
|
proxy_http_version 1.1;
|
|
proxy_set_header Host $host;
|
|
proxy_set_header X-Real-IP $remote_addr;
|
|
proxy_set_header Authorization $http_authorization;
|
|
}
|
|
|
|
# SSE streaming endpoint
|
|
location /stream {
|
|
proxy_pass http://router_api;
|
|
proxy_http_version 1.1;
|
|
proxy_set_header Host $host;
|
|
proxy_set_header Connection "";
|
|
proxy_buffering off;
|
|
chunked_transfer_encoding off;
|
|
}
|
|
|
|
# Dashboard API proxy for SSE
|
|
location /api/ {
|
|
proxy_pass http://dashboard_ui;
|
|
proxy_http_version 1.1;
|
|
proxy_set_header Host $host;
|
|
proxy_buffering off;
|
|
}
|
|
|
|
# LiteLLM debug
|
|
location /litellm/ {
|
|
rewrite ^/litellm/(.*) /$1 break;
|
|
proxy_pass http://litellm_backend;
|
|
proxy_http_version 1.1;
|
|
proxy_set_header Host $host;
|
|
proxy_set_header Authorization $http_authorization;
|
|
}
|
|
|
|
# Professional Dashboard (Phase 1-3) - Static HTML served via Nginx
|
|
location /dashboard/ {
|
|
alias /opt/inference-harness/dashboard/;
|
|
index dashboard.html;
|
|
add_header Cache-Control "public, max-age=3600";
|
|
add_header X-Content-Type-Options nosniff;
|
|
}
|
|
|
|
# Legacy Dashboard (root) - Proxy to Flask app
|
|
location / {
|
|
proxy_pass http://dashboard_ui;
|
|
proxy_http_version 1.1;
|
|
proxy_set_header Host $host;
|
|
proxy_buffering off;
|
|
}
|
|
|
|
# Performance analytics
|
|
location /metrics/ {
|
|
proxy_pass http://router_api;
|
|
proxy_http_version 1.1;
|
|
proxy_set_header Host $host;
|
|
}
|
|
|
|
# Circuit Breaker metrics (Phase 1)
|
|
location /metrics/circuit-breaker {
|
|
proxy_pass http://router_api/metrics/circuit-breaker;
|
|
proxy_http_version 1.1;
|
|
proxy_set_header Host $host;
|
|
}
|
|
|
|
location /health {
|
|
proxy_pass http://router_api/health;
|
|
proxy_http_version 1.1;
|
|
proxy_set_header Host $host;
|
|
proxy_set_header X-Real-IP $remote_addr;
|
|
}
|
|
}
|
|
}
|