trails/.github/workflows/cd-infra.yml
Ullrich Schäfer 424e692ee0
Add service health monitoring: postgres, node, cAdvisor exporters + dashboard
Exporters:
- postgres_exporter: DB connections, transactions, cache hit ratio, query stats
- node_exporter: host CPU, memory, disk, network
- cAdvisor: per-container CPU and memory usage

PostgreSQL:
- Enable pg_stat_statements for query-level performance tracking
- Track index scans vs sequential scans, cache hit ratio

Dashboard (service-health.json):
- DB: connections, size, transactions/s, slow queries, cache hit ratio, index usage
- Host: disk gauge, CPU, memory, network I/O, disk I/O
- BRouter: request latency p50/p95/p99, container CPU + memory
- All containers: CPU and memory comparison

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-27 18:50:42 +01:00

87 lines
3.2 KiB
YAML

name: CD Infra
on:
push:
branches: [main]
paths:
- "infrastructure/**"
workflow_dispatch:
inputs:
restart_all:
description: "Restart all containers (not just infra)"
type: boolean
default: false
concurrency:
group: deploy-infra
cancel-in-progress: true
jobs:
deploy:
name: Deploy Infrastructure
runs-on: ubuntu-latest
environment: infra
steps:
- uses: actions/checkout@v6
- name: Decrypt secrets
run: |
curl -sLO https://github.com/getsops/sops/releases/download/v3.9.4/sops-v3.9.4.linux.amd64
chmod +x sops-v3.9.4.linux.amd64
# Merge app + infra secrets into one .env for docker-compose
SOPS_AGE_KEY="${{ secrets.AGE_SECRET_KEY }}" ./sops-v3.9.4.linux.amd64 -d infrastructure/secrets.app.env > infrastructure/.env
SOPS_AGE_KEY="${{ secrets.AGE_SECRET_KEY }}" ./sops-v3.9.4.linux.amd64 -d infrastructure/secrets.infra.env >> infrastructure/.env
echo "DOMAIN=trails.cool" >> infrastructure/.env
- name: Copy configs to server
uses: appleboy/scp-action@v1
with:
host: ${{ secrets.DEPLOY_HOST }}
username: root
key: ${{ secrets.DEPLOY_SSH_KEY }}
source: "infrastructure/docker-compose.yml,infrastructure/Caddyfile,infrastructure/prometheus/prometheus.yml,infrastructure/loki/loki-config.yml,infrastructure/grafana/provisioning,infrastructure/grafana/dashboards"
target: /opt/trails-cool
strip_components: 1
- name: Copy secrets to server
uses: appleboy/scp-action@v1
with:
host: ${{ secrets.DEPLOY_HOST }}
username: root
key: ${{ secrets.DEPLOY_SSH_KEY }}
source: "infrastructure/.env"
target: /opt/trails-cool
strip_components: 1
- name: Deploy via SSH
uses: appleboy/ssh-action@v1
with:
host: ${{ secrets.DEPLOY_HOST }}
username: root
key: ${{ secrets.DEPLOY_SSH_KEY }}
script: |
cd /opt/trails-cool
# .env was placed by the SCP step (decrypted app + infra secrets)
# Login to ghcr.io (for pulling monitoring images)
GHCR_TOKEN=$(grep DEPLOY_GHCR_TOKEN .env | cut -d= -f2-)
echo "$GHCR_TOKEN" | docker login ghcr.io -u stigi --password-stdin 2>/dev/null || true
# Check if full restart requested via:
# - workflow_dispatch input: restart_all=true
# - commit message containing [restart-all]
RESTART_ALL="${{ github.event.inputs.restart_all }}"
if [ "$RESTART_ALL" != "true" ] && echo "${{ github.event.head_commit.message }}" | grep -q '\[restart-all\]'; then
RESTART_ALL="true"
fi
if [ "$RESTART_ALL" = "true" ]; then
docker compose --env-file .env up -d --remove-orphans
else
# Restart infra services (except Caddy — just reload its config)
docker compose --env-file .env up -d postgres prometheus loki grafana postgres-exporter node-exporter cadvisor
docker compose exec caddy caddy reload --config /etc/caddy/Caddyfile
fi
docker compose ps