Files
mtusi2026lab6/compose.yaml
T
dawuduk baee48072c Подключить OpenTelemetry, Collector и Grafana для оценки 5.
API и worker отдают метрики, логи и трассы. Правила SLO записаны, прогон инцидентов ещё впереди.
2026-11-17 15:23:33 +03:00

342 lines
10 KiB
YAML

# Client -> lb:8080 -> api x2 -> Postgres + Redis + private SeaweedFS S3 + RabbitMQ.
# Worker is a separate process and is the only place that resizes images.
# API and worker export OTLP to the collector. Prometheus, Loki, Tempo and Grafana
# keep metrics, logs and traces. The collector is not required for the API to start.
# API replicas do not publish host ports. MinIO console is not published.
# API replicas do not publish host ports. Migrations run once in `migrate`.
# Check period: HAProxy inter 1s, fall 2, rise 1. Worst detection of a dead
# or not-ready replica is about 2s, plus the 1s DNS hold. API on SIGTERM
# fails /health/ready immediately and exits after LB_DRAIN_SECONDS (default 2).
services:
migrate:
build:
context: .
dockerfile: Dockerfile
image: mtusi-messenger:lab6
command: ["python", "-m", "app.migrate"]
environment:
APP_ENV: lab
LOG_LEVEL: info
DATABASE_URL: postgresql://messenger:${POSTGRES_PASSWORD}@postgres:5432/messenger
DB_POOL_MIN: "1"
DB_POOL_MAX: "2"
MIGRATIONS_ON_START: "1"
depends_on:
postgres:
condition: service_healthy
restart: "no"
mem_limit: 256m
cpus: "0.50"
api:
build:
context: .
dockerfile: Dockerfile
image: mtusi-messenger:lab6
environment:
APP_HOST: 0.0.0.0
APP_PORT: "8080"
APP_ENV: lab
LOG_LEVEL: info
TELEMETRY_ENABLED: ${TELEMETRY_ENABLED:-1}
TRACE_SAMPLE_RATIO: ${TRACE_SAMPLE_RATIO:-1}
OTEL_SERVICE_NAME: messenger-api
OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4318
SERVICE_VERSION: lab6
SHUTDOWN_GRACE_SECONDS: "3"
LB_DRAIN_SECONDS: ${LB_DRAIN_SECONDS:-2}
SESSION_TTL_SECONDS: ${SESSION_TTL_SECONDS:-3600}
CACHE_TTL_SECONDS: ${CACHE_TTL_SECONDS:-60}
IDEMPOTENCY_TTL_SECONDS: ${IDEMPOTENCY_TTL_SECONDS:-86400}
SESSION_STORE: redis
DATABASE_URL: postgresql://messenger:${POSTGRES_PASSWORD}@postgres:5432/messenger
REDIS_URL: redis://redis:6379/0
S3_ENDPOINT: http://s3:9000
S3_REGION: ${S3_REGION:-us-east-1}
S3_BUCKET: ${S3_BUCKET:-messenger-attachments}
S3_ACCESS_KEY_ID: ${S3_ACCESS_KEY_ID}
S3_SECRET_ACCESS_KEY: ${S3_SECRET_ACCESS_KEY}
MAX_UPLOAD_BYTES: ${MAX_UPLOAD_BYTES:-10485760}
MAX_IMAGE_PIXELS: ${MAX_IMAGE_PIXELS:-40000000}
ORPHAN_GRACE_SECONDS: ${ORPHAN_GRACE_SECONDS:-120}
BROKER_URL: amqp://messenger:${RABBITMQ_PASSWORD}@rabbitmq:5672/
JOB_MAX_ATTEMPTS: ${JOB_MAX_ATTEMPTS:-5}
JOB_TIMEOUT_SECONDS: ${JOB_TIMEOUT_SECONDS:-60}
STAGING_RETENTION_SECONDS: ${STAGING_RETENTION_SECONDS:-86400}
S3_SWEEP_INTERVAL_SECONDS: ${S3_SWEEP_INTERVAL_SECONDS:-30}
S3_PUBLIC_ENDPOINT: ${S3_PUBLIC_ENDPOINT:-http://127.0.0.1:9000}
PRESIGN_TTL_SECONDS: ${PRESIGN_TTL_SECONDS:-60}
DB_POOL_MIN: "1"
DB_POOL_MAX: ${DB_POOL_MAX:-4}
DB_COMMAND_TIMEOUT: "5"
DB_CONNECT_TIMEOUT: "5"
MIGRATIONS_ON_START: "0"
depends_on:
migrate:
condition: service_completed_successfully
postgres:
condition: service_healthy
redis:
condition: service_healthy
s3-init:
condition: service_completed_successfully
rabbitmq:
condition: service_healthy
expose:
- "8080"
restart: unless-stopped
mem_limit: ${API_MEM:-256m}
cpus: ${API_CPUS:-0.50}
stop_grace_period: 8s
healthcheck:
test:
[
"CMD",
"python",
"-c",
"import urllib.request; urllib.request.urlopen('http://127.0.0.1:8080/health/ready', timeout=2)",
]
interval: 5s
timeout: 3s
retries: 6
start_period: 5s
lb:
image: haproxy:2.8.14-alpine
volumes:
- ./infra/haproxy.cfg:/usr/local/etc/haproxy/haproxy.cfg:ro
ports:
- "127.0.0.1:8080:8080"
depends_on:
api:
condition: service_started
restart: unless-stopped
mem_limit: 128m
cpus: "0.25"
postgres:
image: postgres:16.6-alpine
environment:
POSTGRES_USER: messenger
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
POSTGRES_DB: messenger
volumes:
- pg_data:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U messenger -d messenger"]
interval: 3s
timeout: 3s
retries: 20
restart: unless-stopped
mem_limit: ${POSTGRES_MEM:-512m}
cpus: ${POSTGRES_CPUS:-1.0}
s3:
image: chrislusf/seaweedfs:3.85
entrypoint: ["/bin/sh", "/seaweed-entrypoint.sh"]
environment:
S3_BUCKET: ${S3_BUCKET:-messenger-attachments}
S3_ACCESS_KEY_ID: ${S3_ACCESS_KEY_ID}
S3_SECRET_ACCESS_KEY: ${S3_SECRET_ACCESS_KEY}
ports:
- "127.0.0.1:9000:9000"
volumes:
- s3_data:/data
- ./infra/s3/seaweed-entrypoint.sh:/seaweed-entrypoint.sh:ro
healthcheck:
test:
[
"CMD-SHELL",
"wget -q -O /dev/null http://127.0.0.1:9333/cluster/status || exit 1; wget -q -O /dev/null http://127.0.0.1:9000/ || test $$? -ne 4",
]
interval: 3s
timeout: 5s
retries: 20
start_period: 8s
restart: unless-stopped
mem_limit: 256m
cpus: "0.50"
s3-init:
build:
context: .
dockerfile: Dockerfile
image: mtusi-messenger:lab6
command: ["python", "-m", "app.s3bootstrap"]
environment:
S3_ENDPOINT: http://s3:9000
S3_REGION: ${S3_REGION:-us-east-1}
S3_BUCKET: ${S3_BUCKET:-messenger-attachments}
S3_ACCESS_KEY_ID: ${S3_ACCESS_KEY_ID}
S3_SECRET_ACCESS_KEY: ${S3_SECRET_ACCESS_KEY}
depends_on:
s3:
condition: service_healthy
restart: "no"
rabbitmq:
image: rabbitmq:3.13.7-alpine
hostname: rabbitmq
environment:
RABBITMQ_DEFAULT_USER: messenger
RABBITMQ_DEFAULT_PASS: ${RABBITMQ_PASSWORD}
RABBITMQ_DEFAULT_VHOST: /
volumes:
- rabbitmq_data:/var/lib/rabbitmq
healthcheck:
test: ["CMD", "rabbitmq-diagnostics", "-q", "ping"]
interval: 5s
timeout: 5s
retries: 20
start_period: 15s
restart: unless-stopped
mem_limit: 256m
cpus: "0.50"
worker:
build:
context: .
dockerfile: Dockerfile
image: mtusi-messenger:lab6
command: ["python", "-m", "app.worker"]
environment:
APP_ENV: lab
LOG_LEVEL: info
TELEMETRY_ENABLED: ${TELEMETRY_ENABLED:-1}
TRACE_SAMPLE_RATIO: ${TRACE_SAMPLE_RATIO:-1}
OTEL_SERVICE_NAME: messenger-worker
OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4318
SERVICE_VERSION: lab6
DATABASE_URL: postgresql://messenger:${POSTGRES_PASSWORD}@postgres:5432/messenger
S3_ENDPOINT: http://s3:9000
S3_REGION: ${S3_REGION:-us-east-1}
S3_BUCKET: ${S3_BUCKET:-messenger-attachments}
S3_ACCESS_KEY_ID: ${S3_ACCESS_KEY_ID}
S3_SECRET_ACCESS_KEY: ${S3_SECRET_ACCESS_KEY}
MAX_UPLOAD_BYTES: ${MAX_UPLOAD_BYTES:-10485760}
MAX_IMAGE_PIXELS: ${MAX_IMAGE_PIXELS:-40000000}
BROKER_URL: amqp://messenger:${RABBITMQ_PASSWORD}@rabbitmq:5672/
WORKER_CONCURRENCY: ${WORKER_CONCURRENCY:-2}
JOB_MAX_ATTEMPTS: ${JOB_MAX_ATTEMPTS:-5}
JOB_TIMEOUT_SECONDS: ${JOB_TIMEOUT_SECONDS:-60}
STAGING_RETENTION_SECONDS: ${STAGING_RETENTION_SECONDS:-86400}
DB_POOL_MIN: "1"
DB_POOL_MAX: "4"
MIGRATIONS_ON_START: "0"
depends_on:
migrate:
condition: service_completed_successfully
postgres:
condition: service_healthy
rabbitmq:
condition: service_healthy
s3-init:
condition: service_completed_successfully
restart: unless-stopped
mem_limit: 768m
cpus: "1.0"
stop_grace_period: 20s
healthcheck:
disable: true
redis:
image: redis:7.4.2-alpine
command:
- redis-server
- --appendonly
- "yes"
- --appendfsync
- everysec
- --save
- "60"
- "1"
volumes:
- redis_data:/data
healthcheck:
test: ["CMD", "redis-cli", "ping"]
interval: 3s
timeout: 3s
retries: 20
restart: unless-stopped
mem_limit: 128m
cpus: "0.50"
otel-collector:
image: otel/opentelemetry-collector-contrib:0.128.0
command: ["--config=/etc/otel/collector.yaml"]
volumes:
- ./infra/otel/collector.yaml:/etc/otel/collector.yaml:ro
restart: unless-stopped
mem_limit: 320m
cpus: "0.50"
prometheus:
image: prom/prometheus:v2.55.1
command:
- --config.file=/etc/prometheus/prometheus.yml
- --web.enable-remote-write-receiver
- --storage.tsdb.path=/prometheus
- --storage.tsdb.retention.time=7d
volumes:
- ./infra/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
- ./infra/prometheus/alerts.yml:/etc/prometheus/alerts.yml:ro
- prometheus_data:/prometheus
ports:
- "127.0.0.1:9090:9090"
restart: unless-stopped
mem_limit: 512m
cpus: "0.50"
loki:
image: grafana/loki:3.3.2
command: ["-config.file=/etc/loki/loki.yml"]
volumes:
- ./infra/loki/loki.yml:/etc/loki/loki.yml:ro
- loki_data:/loki
restart: unless-stopped
mem_limit: 512m
cpus: "0.50"
tempo:
image: grafana/tempo:2.7.1
command: ["-config.file=/etc/tempo/tempo.yml"]
volumes:
- ./infra/tempo/tempo.yml:/etc/tempo/tempo.yml:ro
- tempo_data:/var/tempo
restart: unless-stopped
mem_limit: 512m
cpus: "0.50"
grafana:
image: grafana/grafana:11.4.0
environment:
GF_SECURITY_ADMIN_USER: admin
GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:-lab6-dev-only-change-me}
GF_AUTH_ANONYMOUS_ENABLED: "true"
GF_AUTH_ANONYMOUS_ORG_ROLE: Admin
GF_USERS_DEFAULT_THEME: light
ports:
- "127.0.0.1:3000:3000"
volumes:
- ./infra/grafana/provisioning:/etc/grafana/provisioning:ro
- ./infra/grafana/dashboards:/var/lib/grafana/dashboards:ro
- grafana_data:/var/lib/grafana
depends_on:
- prometheus
- loki
- tempo
restart: unless-stopped
mem_limit: 256m
cpus: "0.50"
volumes:
pg_data:
redis_data:
s3_data:
rabbitmq_data:
prometheus_data:
loki_data:
tempo_data:
grafana_data: