feat(deploy): add HAProxy blue/green stack for zero-downtime relay updates

.changeset/haproxy-blue-green.md

@@ -0,0 +1,7 @@
+---
+"nostream": minor
+---
+
+feat(deploy): add HAProxy blue/green compose stack
+
+Two relays behind HAProxy with `/readyz` health checks and `option redispatch`, plus a rolling recreate script that replaces one relay at a time for zero-downtime image updates.

deploy/README.md

@@ -152,3 +152,31 @@ the new checkout (or copy the updated files). Automated sync is planned separate
 ```
 
 Existing `.env` and `.nostr/settings.yaml` are preserved.
+
+## Zero-downtime updates (HAProxy blue/green)
+
+`deploy/docker-compose.haproxy.yml` replaces the single-relay stack with two
+relays (`nostream-blue`, `nostream-green`) behind HAProxy on `127.0.0.1:8008`.
+Postgres, Redis, and migrations are unchanged.
+
+Install alongside `.env` and `postgresql.conf`, then start:
+
+```bash
+cp deploy/docker-compose.haproxy.yml deploy/rolling-relay-recreate.sh /opt/nostream/
+cp -r deploy/haproxy /opt/nostream/
+cd /opt/nostream
+docker compose -f docker-compose.haproxy.yml up -d
+curl -s http://127.0.0.1:8008/readyz
+```
+
+To update, load the new image, then replace relays one at a time:
+
+```bash
+./rolling-relay-recreate.sh
+```
+
+The script stops a relay, waits for the replacement to report healthy, and only
+then moves to the second one, so a ready backend is always serving. HAProxy
+health-checks `/readyz` every 2s and retries failed requests on the other
+backend (`option redispatch`). Relays get `stop_grace_period: 45s` so the
+`WS_DRAIN_TIMEOUT_MS` drain (default 30s) finishes before Docker sends SIGKILL.

deploy/docker-compose.haproxy.yml

@@ -0,0 +1,126 @@
+# Blue/green alternative to docker-compose.prod.yml: two relays behind HAProxy.
+# Keep the shared services below in sync with docker-compose.prod.yml.
+#
+#   docker compose -f docker-compose.haproxy.yml up -d
+
+x-nostream-relay: &nostream-relay
+  image: ghcr.io/cameri/nostream:main
+  pull_policy: never
+  env_file: .env
+  environment:
+    RELAY_PORT: 8008
+    NOSTR_CONFIG_DIR: /home/node/.nostr
+    DB_HOST: nostream-db
+    DB_PORT: 5432
+    DB_USER: ${DB_USER}
+    DB_PASSWORD: ${DB_PASSWORD}
+    DB_NAME: ${DB_NAME}
+    DB_MIN_POOL_SIZE: ${DB_MIN_POOL_SIZE:-16}
+    DB_MAX_POOL_SIZE: ${DB_MAX_POOL_SIZE:-64}
+    DB_ACQUIRE_CONNECTION_TIMEOUT: ${DB_ACQUIRE_CONNECTION_TIMEOUT:-60000}
+    REDIS_HOST: nostream-cache
+    REDIS_PORT: 6379
+    REDIS_USER: default
+    REDIS_PASSWORD: ${REDIS_PASSWORD}
+    READ_REPLICA_ENABLED: 'false'
+    WORKER_COUNT: ${WORKER_COUNT:-2}
+    WS_DRAIN_TIMEOUT_MS: ${WS_DRAIN_TIMEOUT_MS:-30000}
+  user: node:node
+  volumes:
+    - ${PWD}/.nostr:/home/node/.nostr
+  depends_on:
+    nostream-cache:
+      condition: service_healthy
+    nostream-db:
+      condition: service_healthy
+    nostream-migrate:
+      condition: service_completed_successfully
+  restart: on-failure
+  stop_grace_period: 45s
+  # Gates `up --wait` during rolling recreate, so the next relay is only
+  # replaced once this one serves traffic.
+  healthcheck:
+    test:
+      [
+        'CMD-SHELL',
+        "node -e \"fetch('http://127.0.0.1:8008/readyz').then(r=>process.exit(r.ok?0:1)).catch(()=>process.exit(1))\"",
+      ]
+    interval: 5s
+    timeout: 5s
+    retries: 6
+    start_period: 60s
+
+services:
+  haproxy:
+    image: haproxy:3.0-alpine
+    container_name: nostream-haproxy
+    volumes:
+      - ./haproxy/haproxy.cfg:/usr/local/etc/haproxy/haproxy.cfg:ro
+    ports:
+      - 127.0.0.1:8008:8008
+    depends_on:
+      - nostream-blue
+      - nostream-green
+    restart: on-failure
+
+  nostream-blue:
+    <<: *nostream-relay
+    container_name: nostream-blue
+
+  nostream-green:
+    <<: *nostream-relay
+    container_name: nostream-green
+
+  nostream-db:
+    image: postgres:15
+    container_name: nostream-db
+    environment:
+      POSTGRES_DB: ${DB_NAME}
+      POSTGRES_USER: ${DB_USER}
+      POSTGRES_PASSWORD: ${DB_PASSWORD}
+    volumes:
+      - ${PWD}/.nostr/data:/var/lib/postgresql/data
+      - ${PWD}/.nostr/db-logs:/var/log/postgresql
+      - ${PWD}/postgresql.conf:/postgresql.conf
+    command: postgres -c 'config_file=/postgresql.conf'
+    restart: always
+    healthcheck:
+      test: ['CMD-SHELL', 'pg_isready -U ${DB_USER}']
+      interval: 5s
+      timeout: 5s
+      retries: 5
+      start_period: 360s
+
+  nostream-cache:
+    image: redis:7.0.5-alpine3.16
+    container_name: nostream-cache
+    environment:
+      REDIS_PASSWORD: ${REDIS_PASSWORD}
+    volumes:
+      - cache:/data
+    command: sh -c 'redis-server --loglevel warning --requirepass "$$REDIS_PASSWORD"'
+    restart: always
+    healthcheck:
+      test: ['CMD-SHELL', 'redis-cli -a "$$REDIS_PASSWORD" ping | grep PONG']
+      interval: 2s
+      timeout: 5s
+      retries: 10
+
+  nostream-migrate:
+    image: ghcr.io/cameri/nostream:main
+    pull_policy: never
+    container_name: nostream-migrate
+    user: node:node
+    command: ['node_modules/.bin/knex', 'migrate:latest']
+    environment:
+      DB_HOST: nostream-db
+      DB_PORT: 5432
+      DB_USER: ${DB_USER}
+      DB_PASSWORD: ${DB_PASSWORD}
+      DB_NAME: ${DB_NAME}
+    depends_on:
+      nostream-db:
+        condition: service_healthy
+
+volumes:
+  cache:

deploy/haproxy/haproxy.cfg

@@ -0,0 +1,39 @@
+global
+    log stdout format raw local0 info
+    maxconn 4096
+
+defaults
+    mode http
+    log global
+    option httplog
+    timeout connect 5s
+    timeout client 30s
+    timeout server 30s
+    timeout tunnel 1h
+    timeout check 5s
+    retries 3
+    option redispatch
+    retry-on conn-failure empty-response response-timeout 502 503 504
+
+# Docker's embedded DNS, so recreated relay containers are picked up by IP change.
+resolvers docker
+    nameserver dns 127.0.0.11:53
+    resolve_retries 3
+    timeout resolve 1s
+    timeout retry 1s
+    hold valid 2s
+
+frontend nostream_in
+    bind *:8008
+    default_backend nostream_relays
+
+backend nostream_relays
+    balance roundrobin
+    option httpchk
+    http-check send meth GET uri /readyz
+    http-check expect status 200
+
+    default-server check inter 2s fall 2 rise 1 resolvers docker resolve-prefer ipv4 init-addr libc,none
+
+    server blue nostream-blue:8008
+    server green nostream-green:8008

deploy/rolling-relay-recreate.sh

@@ -0,0 +1,38 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Rolling relay recreate for the HAProxy blue/green stack. Replaces one relay
+# at a time so the other keeps serving traffic.
+#
+# Usage:
+#   ./rolling-relay-recreate.sh [/opt/nostream]
+#
+# Load the new image and run migrations before calling this.
+
+TARGET="${1:-.}"
+COMPOSE_FILE="${COMPOSE_FILE:-docker-compose.haproxy.yml}"
+
+cd "$TARGET"
+
+if [[ ! -f "$COMPOSE_FILE" ]]; then
+  echo "error: compose file not found: $TARGET/$COMPOSE_FILE" >&2
+  exit 1
+fi
+
+compose() {
+  docker compose -f "$COMPOSE_FILE" "$@"
+}
+
+for service in nostream-blue nostream-green; do
+  if [[ -z "$(compose ps -q "$service")" ]]; then
+    echo "Skipping $service (not running)"
+    continue
+  fi
+
+  echo "Replacing $service..."
+  compose stop "$service"
+  compose rm -f "$service"
+  compose up -d --no-deps --wait "$service"
+done
+
+echo "Rolling recreate complete"