forked from mtusi2026/mtusi2026lab6
532 lines
24 KiB
YAML
532 lines
24 KiB
YAML
# Стенд lab6 (база lab5): клиент -> HAProxy -> API x N -> PostgreSQL + Redis + MinIO
|
||
# + RabbitMQ; отдельный worker читает задания из quorum-очереди и публикует
|
||
# оригинал и варианты в конечный S3-prefix. API отвечает 202 после COMMIT
|
||
# (staging-объект + attachment + job + outbox), поэтому брокер не входит в
|
||
# /health/ready и его недоступность не останавливает приём загрузок.
|
||
# Одна команда запуска: make stand-up (docker compose --env-file .env up -d --build --wait)
|
||
#
|
||
# Проект запинен именем, чтобы имена контейнеров и labels были предсказуемы для
|
||
# scripts/stop-one.sh; container_name нигде не задан, иначе масштабирование
|
||
# одного Compose-service стало бы невозможным.
|
||
name: mtusi-lab6
|
||
|
||
services:
|
||
postgres:
|
||
image: postgres:16.4-alpine
|
||
# pg_stat_statements включён для трека 1 (агрегаты SQL по репликам);
|
||
# max_connections поднят под N x DATABASE_POOL_MAX.
|
||
command:
|
||
[
|
||
'postgres',
|
||
'-c',
|
||
'shared_preload_libraries=pg_stat_statements',
|
||
'-c',
|
||
'max_connections=120',
|
||
'-c',
|
||
'shared_buffers=128MB',
|
||
'-c',
|
||
'effective_cache_size=384MB',
|
||
]
|
||
environment:
|
||
POSTGRES_DB: ${POSTGRES_DB:-messenger}
|
||
POSTGRES_USER: ${POSTGRES_USER:-messenger}
|
||
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:?set POSTGRES_PASSWORD in .env}
|
||
# Только loopback: операторские проверки (host-side npm run test:e2e,
|
||
# psql в evidence). API-реплики портов не публикуют вовсе.
|
||
ports:
|
||
- '127.0.0.1:${POSTGRES_PUBLISHED_PORT:-5432}:5432'
|
||
volumes:
|
||
- postgres-data:/var/lib/postgresql/data
|
||
deploy:
|
||
resources:
|
||
limits:
|
||
cpus: '${PG_CPUS:-1.5}'
|
||
memory: ${PG_MEMORY:-512m}
|
||
healthcheck:
|
||
test:
|
||
[
|
||
'CMD-SHELL',
|
||
'pg_isready -U $${POSTGRES_USER} -d $${POSTGRES_DB}',
|
||
]
|
||
interval: 5s
|
||
timeout: 3s
|
||
retries: 20
|
||
|
||
redis:
|
||
image: redis:7.4.2-alpine
|
||
# appendonly: сессии и кэш переживают рестарт контейнера (проверка
|
||
# сохранности с неизменным токеном). volatile-lru вытесняет только
|
||
# ключи с TTL; в стенде у них ограниченный набор и объём.
|
||
command:
|
||
[
|
||
'redis-server',
|
||
'--appendonly',
|
||
'yes',
|
||
'--appendfsync',
|
||
'everysec',
|
||
'--maxmemory',
|
||
'96mb',
|
||
'--maxmemory-policy',
|
||
'volatile-lru',
|
||
]
|
||
ports:
|
||
- '127.0.0.1:${REDIS_PUBLISHED_PORT:-6379}:6379'
|
||
volumes:
|
||
- redis-data:/data
|
||
deploy:
|
||
resources:
|
||
limits:
|
||
cpus: '${REDIS_CPUS:-0.25}'
|
||
memory: ${REDIS_MEMORY:-128m}
|
||
healthcheck:
|
||
test: ['CMD', 'redis-cli', 'ping']
|
||
interval: 5s
|
||
timeout: 3s
|
||
retries: 20
|
||
|
||
broker:
|
||
image: rabbitmq:4.1.8-alpine@sha256:153322e3974e6365c50e523e5eadd5a7fae231f0e8c58f67c03bb3e02056e34e
|
||
# Имя узла rabbit@broker должно оставаться стабильным: при смене
|
||
# hostname данные в broker-data превращаются в сирот.
|
||
hostname: broker
|
||
secrets:
|
||
- source: rabbitmq_conf
|
||
target: /etc/rabbitmq/conf.d/20-credentials.conf
|
||
volumes:
|
||
- broker-data:/var/lib/rabbitmq
|
||
# rabbitmq_prometheus: агрегированные метрики на 15692 (наружу не публикуется).
|
||
- ./infra/rabbitmq/enabled_plugins:/etc/rabbitmq/enabled_plugins:ro
|
||
# Портов нет: брокер доступен только сервисам compose-сети.
|
||
deploy:
|
||
resources:
|
||
limits:
|
||
cpus: '${BROKER_CPUS:-0.5}'
|
||
memory: ${BROKER_MEMORY:-512m}
|
||
healthcheck:
|
||
test: ['CMD', 'rabbitmq-diagnostics', '-q', 'check_port_connectivity']
|
||
interval: 5s
|
||
timeout: 5s
|
||
retries: 30
|
||
start_period: 20s
|
||
stop_grace_period: 30s
|
||
restart: unless-stopped
|
||
|
||
# One-shot: creates the worker identity and tightens the API identity.
|
||
# rabbitmqctl talks to rabbit@broker using the shared Erlang cookie, so the
|
||
# data volume is mounted read-only.
|
||
broker-init:
|
||
image: rabbitmq:4.1.8-alpine@sha256:153322e3974e6365c50e523e5eadd5a7fae231f0e8c58f67c03bb3e02056e34e
|
||
entrypoint: ['/bin/sh', '/bootstrap/init-worker.sh']
|
||
volumes:
|
||
- broker-data:/var/lib/rabbitmq:ro
|
||
- ./infra/rabbitmq:/bootstrap:ro
|
||
secrets: [broker_worker_password]
|
||
depends_on:
|
||
broker: { condition: service_healthy }
|
||
restart: 'no'
|
||
deploy:
|
||
resources:
|
||
limits:
|
||
cpus: '0.25'
|
||
memory: 128m
|
||
|
||
s3:
|
||
image: minio/minio:RELEASE.2025-09-07T16-13-09Z@sha256:14cea493d9a34af32f524e538b8346cf79f3321eff8e708c1e2960462bd8936e
|
||
command: ['server', '/data', '--address', ':9000']
|
||
environment:
|
||
MINIO_ROOT_USER_FILE: minio_root_user
|
||
MINIO_ROOT_PASSWORD_FILE: minio_root_password
|
||
MINIO_BROWSER: 'off'
|
||
secrets: [minio_root_user, minio_root_password]
|
||
# Консольный порт 9001 не публикуется, консоль отключена (MINIO_BROWSER=off).
|
||
ports:
|
||
- '${S3_PUBLIC_BIND:-127.0.0.1}:${S3_PUBLIC_PORT:-9000}:9000'
|
||
volumes:
|
||
- s3-data:/data
|
||
deploy:
|
||
resources:
|
||
limits:
|
||
cpus: '${S3_CPUS:-1.0}'
|
||
memory: ${S3_MEMORY:-512m}
|
||
healthcheck:
|
||
test: ['CMD', 'mc', 'ready', 'local']
|
||
interval: 5s
|
||
timeout: 3s
|
||
retries: 20
|
||
|
||
# Идемпотентный bootstrap: bucket, политика, пользователь API.
|
||
# Лимит 256m: mc admin policy attach на 128m получал OOM-kill (exit 137).
|
||
s3-init:
|
||
image: minio/mc:RELEASE.2025-08-13T08-35-41Z@sha256:a7fe349ef4bd8521fb8497f55c6042871b2ae640607cf99d9bede5e9bdf11727
|
||
entrypoint: ['/bin/sh', '/bootstrap/bootstrap.sh']
|
||
environment:
|
||
S3_BUCKET: '${S3_BUCKET:-messenger-attachments}'
|
||
volumes:
|
||
- ./infra/minio:/bootstrap:ro
|
||
secrets:
|
||
- minio_root_user
|
||
- minio_root_password
|
||
- s3_api_access_key_id
|
||
- s3_api_secret_access_key
|
||
- s3_worker_access_key_id
|
||
- s3_worker_secret_access_key
|
||
depends_on:
|
||
s3: { condition: service_healthy }
|
||
restart: 'no'
|
||
deploy:
|
||
resources:
|
||
limits:
|
||
cpus: '0.25'
|
||
memory: 256m
|
||
|
||
# Миграции выполняются один раз отдельным сервисом, а не гонкой реплик:
|
||
# api стартует только после его успешного завершения.
|
||
migrate:
|
||
build:
|
||
context: .
|
||
dockerfile: Dockerfile
|
||
image: ${API_IMAGE:-mtusi-messenger:lab6}
|
||
command: ['node', 'dist/database/migration.runner.js']
|
||
env_file: [.env]
|
||
deploy:
|
||
resources:
|
||
limits:
|
||
cpus: '0.5'
|
||
memory: 192m
|
||
depends_on:
|
||
postgres: { condition: service_healthy }
|
||
redis: { condition: service_healthy }
|
||
restart: 'no'
|
||
|
||
api:
|
||
build:
|
||
context: .
|
||
dockerfile: Dockerfile
|
||
args:
|
||
BUILD_ID: ${BUILD_ID:-unknown}
|
||
image: ${API_IMAGE:-mtusi-messenger:lab6}
|
||
# Портов нет намеренно: единственная точка входа — HAProxy.
|
||
env_file: [.env]
|
||
environment:
|
||
DATABASE_POOL_MAX: ${DATABASE_POOL_MAX:-10}
|
||
CACHE_MODE: ${CACHE_MODE:-protected}
|
||
CACHE_MISS_DELAY_MS: ${CACHE_MISS_DELAY_MS:-0}
|
||
SESSION_TTL_SECONDS: ${SESSION_TTL_SECONDS:-3600}
|
||
# Бюджет пробы готовности; LB проверяет ту же ручку с timeout check 500 ms.
|
||
HEALTH_TIMEOUT_MS: ${HEALTH_TIMEOUT_MS:-400}
|
||
# Дрейн длиннее обнаружения отказа LB (500 ms x fall 2 ≈ 1 s).
|
||
DRAIN_DELAY_MS: ${DRAIN_DELAY_MS:-3000}
|
||
S3_ACCESS_KEY_ID_FILE: /run/secrets/s3_api_access_key_id
|
||
S3_SECRET_ACCESS_KEY_FILE: /run/secrets/s3_api_secret_access_key
|
||
UPLOAD_TIMEOUT_MS: ${UPLOAD_TIMEOUT_MS:-25000}
|
||
DIRECT_UPLOAD_URL_TTL_SECONDS: ${DIRECT_UPLOAD_URL_TTL_SECONDS:-300}
|
||
ATTACHMENT_SWEEP_GRACE_SECONDS: ${ATTACHMENT_SWEEP_GRACE_SECONDS:-900}
|
||
ATTACHMENT_SWEEP_INTERVAL_MS: ${ATTACHMENT_SWEEP_INTERVAL_MS:-60000}
|
||
# libvips держит декодируемое изображение в памяти, а не во временном
|
||
# файле: /tmp — tmpfs 16 MiB, и изображение ~40 Мп туда не помещается.
|
||
VIPS_DISC_THRESHOLD: ${VIPS_DISC_THRESHOLD:-1g}
|
||
FAULT_INJECTION_ENABLED: ${FAULT_INJECTION_ENABLED:-0}
|
||
JOB_MAX_ATTEMPTS: ${JOB_MAX_ATTEMPTS:-5}
|
||
JOB_RETRY_BASE_MS: ${JOB_RETRY_BASE_MS:-1000}
|
||
JOB_RETRY_MAX_MS: ${JOB_RETRY_MAX_MS:-30000}
|
||
BROKER_PUBLISH_TIMEOUT_MS: ${BROKER_PUBLISH_TIMEOUT_MS:-5000}
|
||
# lab6: телеметрия. Collector НЕ в depends_on: приложение обязано
|
||
# стартовать и работать без телеметрии.
|
||
OTEL_SERVICE_NAME: messenger-api
|
||
OTEL_EXPORTER_OTLP_ENDPOINT: ${OTEL_EXPORTER_OTLP_ENDPOINT:-http://otel-collector:4318}
|
||
OTEL_EXPORTER_OTLP_PROTOCOL: http/protobuf
|
||
OTEL_SDK_DISABLED: '${OTEL_SDK_DISABLED:-false}'
|
||
OTEL_TRACES_SAMPLER_ARG: '${OTEL_TRACES_SAMPLER_ARG:-1}'
|
||
OTEL_METRIC_EXPORT_INTERVAL: '${OTEL_METRIC_EXPORT_INTERVAL:-10000}'
|
||
SERVICE_VERSION: ${BUILD_ID:-local}
|
||
OTEL_RESOURCE_ATTRIBUTES: ${OTEL_RESOURCE_ATTRIBUTES:-deployment.environment.name=lab}
|
||
LOG_LEVEL: ${LOG_LEVEL:-INFO}
|
||
OTEL_EXPORTER_OTLP_TIMEOUT: '${OTEL_EXPORTER_OTLP_TIMEOUT:-5000}'
|
||
OTEL_BSP_MAX_QUEUE_SIZE: '${OTEL_BSP_MAX_QUEUE_SIZE:-2048}'
|
||
OTEL_BSP_MAX_EXPORT_BATCH_SIZE: '${OTEL_BSP_MAX_EXPORT_BATCH_SIZE:-512}'
|
||
OTEL_BSP_SCHEDULE_DELAY: '${OTEL_BSP_SCHEDULE_DELAY:-1000}'
|
||
OTEL_BLRP_MAX_QUEUE_SIZE: '${OTEL_BLRP_MAX_QUEUE_SIZE:-2048}'
|
||
OTEL_BLRP_MAX_EXPORT_BATCH_SIZE: '${OTEL_BLRP_MAX_EXPORT_BATCH_SIZE:-512}'
|
||
OTEL_BLRP_SCHEDULE_DELAY: '${OTEL_BLRP_SCHEDULE_DELAY:-1000}'
|
||
# Недоступный otel-collector: getaddrinfo по неизвестному имени в сети
|
||
# Docker занимает поток libuv на секунды и без запаса голодают DNS-
|
||
# запросы к postgres/s3 (проверено: 5-7 с на ENOTFOUND).
|
||
UV_THREADPOOL_SIZE: '32'
|
||
dns_opt: ['timeout:1', 'attempts:1']
|
||
# Outbox закрывает недоступность брокера: API принимает загрузку и
|
||
# отвечает 202 без публикации, relay доставит задание после восстановления.
|
||
secrets:
|
||
- s3_api_access_key_id
|
||
- s3_api_secret_access_key
|
||
- broker_url
|
||
# Корневая ФС только для чтения: локального файла оригинала на API нет.
|
||
read_only: true
|
||
tmpfs: ['/tmp:size=16m']
|
||
deploy:
|
||
replicas: ${API_REPLICAS:-2}
|
||
resources:
|
||
limits:
|
||
cpus: '${API_CPUS_PER_REPLICA:-1.5}'
|
||
memory: ${API_MEMORY_PER_REPLICA:-1024m}
|
||
stop_grace_period: 20s
|
||
restart: unless-stopped
|
||
depends_on:
|
||
migrate: { condition: service_completed_successfully }
|
||
postgres: { condition: service_healthy }
|
||
redis: { condition: service_healthy }
|
||
s3-init: { condition: service_completed_successfully }
|
||
healthcheck:
|
||
test:
|
||
[
|
||
'CMD',
|
||
'node',
|
||
'-e',
|
||
"fetch('http://127.0.0.1:'+ (process.env.APP_PORT||8080) + '/health/ready').then(r=>{if(!r.ok)process.exit(1)}).catch(()=>process.exit(1))",
|
||
]
|
||
interval: 5s
|
||
timeout: 3s
|
||
retries: 20
|
||
|
||
# Worker — отдельный процесс без HTTP API. Он читает задания из quorum-
|
||
# очереди, держит lease с heartbeat, пишет варианты и коммитит результат в
|
||
# PostgreSQL. Остановка worker не блокирует приём загрузок API.
|
||
worker:
|
||
build:
|
||
context: .
|
||
dockerfile: Dockerfile
|
||
args:
|
||
BUILD_ID: ${BUILD_ID:-unknown}
|
||
image: ${API_IMAGE:-mtusi-messenger:lab6}
|
||
command: ['node', 'dist/worker.main.js']
|
||
env_file: [.env]
|
||
environment:
|
||
BROKER_URL_FILE: /run/secrets/broker_worker_url
|
||
S3_ACCESS_KEY_ID_FILE: /run/secrets/s3_worker_access_key_id
|
||
S3_SECRET_ACCESS_KEY_FILE: /run/secrets/s3_worker_secret_access_key
|
||
VIPS_DISC_THRESHOLD: ${VIPS_DISC_THRESHOLD:-1g}
|
||
FAULT_INJECTION_ENABLED: ${FAULT_INJECTION_ENABLED:-0}
|
||
WORKER_CONCURRENCY: ${WORKER_CONCURRENCY:-2}
|
||
JOB_MAX_ATTEMPTS: ${JOB_MAX_ATTEMPTS:-5}
|
||
JOB_TIMEOUT_SECONDS: ${JOB_TIMEOUT_SECONDS:-60}
|
||
JOB_LEASE_SECONDS: ${JOB_LEASE_SECONDS:-30}
|
||
JOB_RETRY_BASE_MS: ${JOB_RETRY_BASE_MS:-1000}
|
||
JOB_RETRY_MAX_MS: ${JOB_RETRY_MAX_MS:-30000}
|
||
STAGING_RETENTION_SECONDS: ${STAGING_RETENTION_SECONDS:-86400}
|
||
WORKER_HEALTH_PORT: ${WORKER_HEALTH_PORT:-8081}
|
||
BROKER_PUBLISH_TIMEOUT_MS: ${BROKER_PUBLISH_TIMEOUT_MS:-5000}
|
||
QUEUED_RECONCILE_GRACE_SECONDS: ${QUEUED_RECONCILE_GRACE_SECONDS:-15}
|
||
OUTBOX_RETENTION_SECONDS: ${OUTBOX_RETENTION_SECONDS:-86400}
|
||
JOB_EVENTS_RETENTION_SECONDS: ${JOB_EVENTS_RETENTION_SECONDS:-2592000}
|
||
# lab6: телеметрия. Collector НЕ в depends_on: приложение обязано
|
||
# стартовать и работать без телеметрии.
|
||
OTEL_SERVICE_NAME: messenger-worker
|
||
OTEL_EXPORTER_OTLP_ENDPOINT: ${OTEL_EXPORTER_OTLP_ENDPOINT:-http://otel-collector:4318}
|
||
OTEL_EXPORTER_OTLP_PROTOCOL: http/protobuf
|
||
OTEL_SDK_DISABLED: '${OTEL_SDK_DISABLED:-false}'
|
||
OTEL_TRACES_SAMPLER_ARG: '${OTEL_TRACES_SAMPLER_ARG:-1}'
|
||
OTEL_METRIC_EXPORT_INTERVAL: '${OTEL_METRIC_EXPORT_INTERVAL:-10000}'
|
||
SERVICE_VERSION: ${BUILD_ID:-local}
|
||
OTEL_RESOURCE_ATTRIBUTES: ${OTEL_RESOURCE_ATTRIBUTES:-deployment.environment.name=lab}
|
||
LOG_LEVEL: ${LOG_LEVEL:-INFO}
|
||
OTEL_EXPORTER_OTLP_TIMEOUT: '${OTEL_EXPORTER_OTLP_TIMEOUT:-5000}'
|
||
OTEL_BSP_MAX_QUEUE_SIZE: '${OTEL_BSP_MAX_QUEUE_SIZE:-2048}'
|
||
OTEL_BSP_MAX_EXPORT_BATCH_SIZE: '${OTEL_BSP_MAX_EXPORT_BATCH_SIZE:-512}'
|
||
OTEL_BSP_SCHEDULE_DELAY: '${OTEL_BSP_SCHEDULE_DELAY:-1000}'
|
||
OTEL_BLRP_MAX_QUEUE_SIZE: '${OTEL_BLRP_MAX_QUEUE_SIZE:-2048}'
|
||
OTEL_BLRP_MAX_EXPORT_BATCH_SIZE: '${OTEL_BLRP_MAX_EXPORT_BATCH_SIZE:-512}'
|
||
OTEL_BLRP_SCHEDULE_DELAY: '${OTEL_BLRP_SCHEDULE_DELAY:-1000}'
|
||
# Недоступный otel-collector: getaddrinfo по неизвестному имени в сети
|
||
# Docker занимает поток libuv на секунды и без запаса голодают DNS-
|
||
# запросы к postgres/s3 (проверено: 5-7 с на ENOTFOUND).
|
||
UV_THREADPOOL_SIZE: '32'
|
||
dns_opt: ['timeout:1', 'attempts:1']
|
||
secrets:
|
||
- s3_worker_access_key_id
|
||
- s3_worker_secret_access_key
|
||
- broker_worker_url
|
||
read_only: true
|
||
tmpfs: ['/tmp:size=16m']
|
||
deploy:
|
||
replicas: ${WORKER_REPLICAS:-1}
|
||
resources:
|
||
limits:
|
||
cpus: '${WORKER_CPUS:-1.5}'
|
||
memory: ${WORKER_MEMORY:-1280m}
|
||
stop_grace_period: 40s
|
||
restart: unless-stopped
|
||
depends_on:
|
||
migrate: { condition: service_completed_successfully }
|
||
postgres: { condition: service_healthy }
|
||
redis: { condition: service_healthy }
|
||
broker: { condition: service_healthy }
|
||
broker-init: { condition: service_completed_successfully }
|
||
s3-init: { condition: service_completed_successfully }
|
||
healthcheck:
|
||
test:
|
||
[
|
||
'CMD',
|
||
'node',
|
||
'-e',
|
||
"fetch('http://127.0.0.1:'+ (process.env.WORKER_HEALTH_PORT||8081) + '/health').then(r=>{if(!r.ok)process.exit(1)}).catch(()=>process.exit(1))",
|
||
]
|
||
interval: 5s
|
||
timeout: 3s
|
||
retries: 20
|
||
start_period: 20s
|
||
|
||
haproxy:
|
||
# PROMEX (USE_PROMEX=1) проверен `haproxy -vv`; digest закреплён.
|
||
image: haproxy:3.2-alpine@sha256:254e6370f01cd654e0744edf607c67f33777c1b6a9dc0d4b28bcba7171460122
|
||
ports:
|
||
- '${APP_PUBLIC_PORT:-8080}:8080'
|
||
# Страница статистики — интерфейс LB, публикуется только на loopback.
|
||
- '127.0.0.1:${LB_STATS_PORT:-8404}:8404'
|
||
volumes:
|
||
- ./infra/haproxy/haproxy.cfg:/usr/local/etc/haproxy/haproxy.cfg:ro
|
||
deploy:
|
||
resources:
|
||
limits:
|
||
cpus: '${LB_CPUS:-0.25}'
|
||
memory: ${LB_MEMORY:-128m}
|
||
depends_on:
|
||
api: { condition: service_healthy }
|
||
|
||
# --- lab6: наблюдаемость. Приложение от этих сервисов не зависит. ---
|
||
|
||
# One-shot: владельцы томов Loki/Tempo (UID 10001) без предположений о
|
||
# наличии shell/chown в их образах. Использует уже собранный образ приложения.
|
||
obs-volumes-init:
|
||
image: ${API_IMAGE:-mtusi-messenger:lab6}
|
||
pull_policy: never
|
||
user: '0:0'
|
||
entrypoint: ['node']
|
||
command:
|
||
[
|
||
'-e',
|
||
"const fs=require('node:fs');for(const p of ['/var/tempo','/loki']){fs.mkdirSync(p,{recursive:true});fs.chownSync(p,10001,10001)}",
|
||
]
|
||
volumes:
|
||
- tempo-data:/var/tempo
|
||
- loki-data:/loki
|
||
restart: 'no'
|
||
deploy:
|
||
resources:
|
||
limits:
|
||
cpus: '0.25'
|
||
memory: 128m
|
||
|
||
otel-collector:
|
||
image: otel/opentelemetry-collector-contrib:0.128.0@sha256:1ab0baba0ee3695d823c46653d8a6e8894896e668ce8bd7ebe002e948d827bc7
|
||
command: ['--config=/etc/otelcol-contrib/config.yaml']
|
||
volumes:
|
||
- ./infra/otel/collector.yaml:/etc/otelcol-contrib/config.yaml:ro
|
||
deploy:
|
||
resources:
|
||
limits:
|
||
cpus: '${OTELCOL_CPUS:-0.5}'
|
||
memory: ${OTELCOL_MEMORY:-256m}
|
||
restart: unless-stopped
|
||
|
||
prometheus:
|
||
image: prom/prometheus:v3.4.1@sha256:9abc6cf6aea7710d163dbb28d8eeb7dc5baef01e38fa4cd146a406dd9f07f70d
|
||
command:
|
||
[
|
||
'--config.file=/etc/prometheus/prometheus.yml',
|
||
'--storage.tsdb.path=/prometheus',
|
||
'--storage.tsdb.retention.time=7d',
|
||
'--web.enable-otlp-receiver',
|
||
]
|
||
ports:
|
||
- '127.0.0.1:${PROMETHEUS_PORT:-9090}:9090'
|
||
volumes:
|
||
- ./infra/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
|
||
- ./infra/prometheus/rules:/etc/prometheus/rules:ro
|
||
- prometheus-data:/prometheus
|
||
deploy:
|
||
resources:
|
||
limits:
|
||
cpus: '${PROMETHEUS_CPUS:-0.5}'
|
||
memory: ${PROMETHEUS_MEMORY:-768m}
|
||
restart: unless-stopped
|
||
|
||
loki:
|
||
image: grafana/loki:3.5.1@sha256:a74594532eec4cc313401beedc4dd2708c43674c032084b1aeb87c14a5be1745
|
||
command: ['-config.file=/etc/loki/loki.yaml']
|
||
volumes:
|
||
- ./infra/loki/loki.yaml:/etc/loki/loki.yaml:ro
|
||
- loki-data:/loki
|
||
depends_on:
|
||
obs-volumes-init: { condition: service_completed_successfully }
|
||
deploy:
|
||
resources:
|
||
limits:
|
||
cpus: '${LOKI_CPUS:-0.5}'
|
||
memory: ${LOKI_MEMORY:-512m}
|
||
restart: unless-stopped
|
||
|
||
tempo:
|
||
image: grafana/tempo:2.8.1@sha256:bc9245fe3da4e63dc4c6862d9c2dad9bcd8be13d0ba4f7705fa6acda4c904d0e
|
||
command: ['-config.file=/etc/tempo/tempo.yaml']
|
||
volumes:
|
||
- ./infra/tempo/tempo.yaml:/etc/tempo/tempo.yaml:ro
|
||
- tempo-data:/var/tempo
|
||
depends_on:
|
||
obs-volumes-init: { condition: service_completed_successfully }
|
||
deploy:
|
||
resources:
|
||
limits:
|
||
cpus: '${TEMPO_CPUS:-0.5}'
|
||
memory: ${TEMPO_MEMORY:-512m}
|
||
restart: unless-stopped
|
||
|
||
grafana:
|
||
image: grafana/grafana:12.0.2@sha256:b5b59bfc7561634c2d7b136c4543d702ebcc94a3da477f21ff26f89ffd4214fa
|
||
environment:
|
||
GF_SECURITY_ADMIN_USER: admin
|
||
GF_SECURITY_ADMIN_PASSWORD__FILE: /run/secrets/grafana_admin_password
|
||
GF_AUTH_ANONYMOUS_ENABLED: 'false'
|
||
GF_USERS_ALLOW_SIGN_UP: 'false'
|
||
GF_ANALYTICS_REPORTING_ENABLED: 'false'
|
||
GF_ANALYTICS_CHECK_FOR_UPDATES: 'false'
|
||
GF_ANALYTICS_CHECK_FOR_PLUGIN_UPDATES: 'false'
|
||
secrets: [grafana_admin_password]
|
||
ports:
|
||
- '127.0.0.1:${GRAFANA_PORT:-3000}:3000'
|
||
volumes:
|
||
- ./infra/grafana/provisioning:/etc/grafana/provisioning:ro
|
||
- ./infra/grafana/dashboards:/etc/grafana/dashboards:ro
|
||
- grafana-data:/var/lib/grafana
|
||
depends_on:
|
||
- prometheus
|
||
- loki
|
||
- tempo
|
||
deploy:
|
||
resources:
|
||
limits:
|
||
cpus: '${GRAFANA_CPUS:-0.5}'
|
||
memory: ${GRAFANA_MEMORY:-384m}
|
||
restart: unless-stopped
|
||
|
||
secrets:
|
||
minio_root_user: { file: ./secrets/minio_root_user }
|
||
minio_root_password: { file: ./secrets/minio_root_password }
|
||
s3_api_access_key_id: { file: ./secrets/s3_api_access_key_id }
|
||
s3_api_secret_access_key: { file: ./secrets/s3_api_secret_access_key }
|
||
s3_worker_access_key_id: { file: ./secrets/s3_worker_access_key_id }
|
||
s3_worker_secret_access_key: { file: ./secrets/s3_worker_secret_access_key }
|
||
broker_url: { file: ./secrets/broker_url }
|
||
broker_worker_url: { file: ./secrets/broker_worker_url }
|
||
broker_worker_password: { file: ./secrets/broker_worker_password }
|
||
rabbitmq_conf: { file: ./secrets/rabbitmq.conf }
|
||
grafana_admin_password: { file: ./secrets/grafana_admin_password }
|
||
|
||
volumes:
|
||
postgres-data:
|
||
redis-data:
|
||
s3-data:
|
||
broker-data:
|
||
prometheus-data:
|
||
loki-data:
|
||
tempo-data:
|
||
grafana-data:
|