feat(server): healthchecks for PG and redis (#9590)

* HCs -> docker compose

---------

Co-authored-by: Zack Pollard <zackpollard@ymail.com>

docker/docker-compose.dev.yml

@@ -82,6 +82,8 @@ services:
   redis:
     container_name: immich_redis
     image: redis:6.2-alpine@sha256:c0634a08e74a4bb576d02d1ee993dc05dba10e8b7b9492dfa28a7af100d46c01
+    healthcheck:
+      test: redis-cli ping || exit 1
 
   database:
     container_name: immich_postgres
@@ -97,6 +99,11 @@ services:
       - ${UPLOAD_LOCATION}/postgres:/var/lib/postgresql/data
     ports:
       - 5432:5432
+    healthcheck:
+      test: pg_isready --dbname='${DB_DATABASE_NAME}' || exit 1; Chksum="$$(psql --dbname='${DB_DATABASE_NAME}' --username='${DB_USERNAME}' --tuples-only --no-align --command='SELECT SUM(checksum_failures) FROM pg_stat_database')"; echo "checksum failure count is $$Chksum"; [ "$$Chksum" = '0' ] || exit 1
+      interval: 5m
+      start_interval: 30s
+      start_period: 5m
     command: ["postgres", "-c" ,"shared_preload_libraries=vectors.so", "-c", 'search_path="$$user", public, vectors', "-c", "logging_collector=on", "-c", "max_wal_size=2GB", "-c", "shared_buffers=512MB", "-c", "wal_compression=on"]
 
   # set IMMICH_METRICS=true in .env to enable metrics

docker/docker-compose.prod.yml

@@ -12,12 +12,12 @@ services:
       - /etc/localtime:/etc/localtime:ro
     env_file:
       - .env
-    restart: always
     ports:
       - 2283:3001
     depends_on:
       - redis
       - database
+    restart: always
 
   immich-machine-learning:
     container_name: immich_machine_learning
@@ -39,6 +39,8 @@ services:
   redis:
     container_name: immich_redis
     image: redis:6.2-alpine@sha256:c0634a08e74a4bb576d02d1ee993dc05dba10e8b7b9492dfa28a7af100d46c01
+    healthcheck:
+      test: redis-cli ping || exit 1
     restart: always
 
   database:
@@ -55,7 +57,13 @@ services:
       - ${UPLOAD_LOCATION}/postgres:/var/lib/postgresql/data
     ports:
       - 5432:5432
+    healthcheck:
+      test: pg_isready --dbname='${DB_DATABASE_NAME}' || exit 1; Chksum="$$(psql --dbname='${DB_DATABASE_NAME}' --username='${DB_USERNAME}' --tuples-only --no-align --command='SELECT SUM(checksum_failures) FROM pg_stat_database')"; echo "checksum failure count is $$Chksum"; [ "$$Chksum" = '0' ] || exit 1
+      interval: 5m
+      start_interval: 30s
+      start_period: 5m
     command: ["postgres", "-c" ,"shared_preload_libraries=vectors.so", "-c", 'search_path="$$user", public, vectors', "-c", "logging_collector=on", "-c", "max_wal_size=2GB", "-c", "shared_buffers=512MB", "-c", "wal_compression=on"]
+    restart: always
 
   # set IMMICH_METRICS=true in .env to enable metrics
   immich-prometheus:

docker/docker-compose.yml

@@ -41,6 +41,8 @@ services:
   redis:
     container_name: immich_redis
     image: docker.io/redis:6.2-alpine@sha256:c0634a08e74a4bb576d02d1ee993dc05dba10e8b7b9492dfa28a7af100d46c01
+    healthcheck:
+      test: redis-cli ping || exit 1
     restart: always
 
   database:
@@ -53,8 +55,13 @@ services:
       POSTGRES_INITDB_ARGS: '--data-checksums'
     volumes:
       - ${DB_DATA_LOCATION}:/var/lib/postgresql/data
-    restart: always
+    healthcheck:
+      test: pg_isready --dbname='${DB_DATABASE_NAME}' || exit 1; Chksum="$$(psql --dbname='${DB_DATABASE_NAME}' --username='${DB_USERNAME}' --tuples-only --no-align --command='SELECT SUM(checksum_failures) FROM pg_stat_database')"; echo "checksum failure count is $$Chksum"; [ "$$Chksum" = '0' ] || exit 1
+      interval: 5m
+      start_interval: 30s
+      start_period: 5m
     command: ["postgres", "-c" ,"shared_preload_libraries=vectors.so", "-c", 'search_path="$$user", public, vectors', "-c", "logging_collector=on", "-c", "max_wal_size=2GB", "-c", "shared_buffers=512MB", "-c", "wal_compression=on"]
+    restart: always
 
 volumes:
   model-cache: