Files
mtusi2026lab6/compose.yaml
T

347 lines
11 KiB
YAML

x-otel-environment: &otel-environment
OTEL_SDK_DISABLED: ${OTEL_SDK_DISABLED:-false}
OTEL_EXPORTER_OTLP_ENDPOINT: ${OTEL_EXPORTER_OTLP_ENDPOINT:-http://otel-collector:4318}
OTEL_EXPORTER_OTLP_PROTOCOL: ${OTEL_EXPORTER_OTLP_PROTOCOL:-http/protobuf}
OTEL_EXPORTER_OTLP_TIMEOUT: ${OTEL_EXPORTER_OTLP_TIMEOUT:-2}
OTEL_SERVICE_VERSION: ${OTEL_SERVICE_VERSION:-1.6.0}
OTEL_DEPLOYMENT_ENVIRONMENT: ${OTEL_DEPLOYMENT_ENVIRONMENT:-lab}
OTEL_BSP_MAX_QUEUE_SIZE: ${OTEL_BSP_MAX_QUEUE_SIZE:-2048}
OTEL_BLRP_MAX_QUEUE_SIZE: ${OTEL_BLRP_MAX_QUEUE_SIZE:-2048}
OTEL_METRIC_EXPORT_INTERVAL: ${OTEL_METRIC_EXPORT_INTERVAL:-5000}
services:
postgres:
image: postgres:17.4-alpine
cpus: "1.0"
mem_limit: 512m
environment:
POSTGRES_USER: ${POSTGRES_USER}
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
POSTGRES_DB: ${POSTGRES_DB}
volumes:
- postgres_data:/var/lib/postgresql/data
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
cpus: "0.25"
mem_limit: 128m
command: ["redis-server", "--appendonly", "yes", "--appendfsync", "always"]
volumes:
- redis_data:/data
healthcheck:
test: ["CMD", "redis-cli", "ping"]
interval: 5s
timeout: 3s
retries: 20
broker:
image: rabbitmq:4.1.4-alpine
cpus: "0.5"
mem_limit: 384m
environment:
RABBITMQ_DEFAULT_USER: ${BROKER_USER:-messenger}
RABBITMQ_DEFAULT_PASS: ${BROKER_PASSWORD:-change-me-rabbitmq}
volumes:
- broker_data:/var/lib/rabbitmq
healthcheck:
test: ["CMD", "rabbitmq-diagnostics", "-q", "ping"]
interval: 5s
timeout: 5s
retries: 20
s3:
image: cgr.dev/chainguard/minio@sha256:3c60a2a8c4d33409a9bc7a623a7fcbfb4605adc3d89422d2f53b3f673a6e5597
user: "0"
cpus: "0.5"
mem_limit: 256m
command: ["server", "/data", "--console-address", ":9001"]
environment:
MINIO_ROOT_USER: ${MINIO_ROOT_USER:-local-minio-admin}
MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:-change-me-minio-root}
S3_BUCKET: ${S3_BUCKET:-messenger-attachments}
volumes:
- s3_data:/data
healthcheck:
test: ["CMD", "mc", "ready", "local"]
interval: 5s
timeout: 3s
retries: 20
s3-bootstrap:
image: cgr.dev/chainguard/minio-client@sha256:39768db4c3fa811bc8f2e2a3e0add8ea391648b1c980de179985e1c353dc1805
cpus: "0.25"
mem_limit: 128m
entrypoint: ["/bin/sh", "-c"]
command:
- |
set -eu
mc alias set local http://s3:9000 "$$MINIO_ROOT_USER" "$$MINIO_ROOT_PASSWORD"
mc mb --ignore-existing local/"$$S3_BUCKET"
mc anonymous set none local/"$$S3_BUCKET"
mc admin user info local "$$S3_ACCESS_KEY_ID" >/dev/null 2>&1 || mc admin user add local "$$S3_ACCESS_KEY_ID" "$$S3_SECRET_ACCESS_KEY"
sed "s/BUCKET_NAME/$$S3_BUCKET/g" /policy/s3-api-policy.json >/tmp/s3-api-policy.json
mc admin policy create local messenger-api /tmp/s3-api-policy.json
mc admin policy attach local messenger-api --user "$$S3_ACCESS_KEY_ID"
environment:
MINIO_ROOT_USER: ${MINIO_ROOT_USER:-local-minio-admin}
MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:-change-me-minio-root}
S3_BUCKET: ${S3_BUCKET:-messenger-attachments}
S3_ACCESS_KEY_ID: ${S3_ACCESS_KEY_ID:-messenger-api}
S3_SECRET_ACCESS_KEY: ${S3_SECRET_ACCESS_KEY:-change-me-minio-api}
volumes:
- ./infra/s3-api-policy.json:/policy/s3-api-policy.json:ro
depends_on:
s3:
condition: service_healthy
restart: "no"
migrate:
build: .
cpus: "0.5"
mem_limit: 256m
command: ["alembic", "upgrade", "head"]
environment:
DATABASE_URL: ${DATABASE_URL}
REDIS_URL: ${REDIS_URL}
SESSION_TTL_SECONDS: ${SESSION_TTL_SECONDS}
S3_ACCESS_KEY_ID: ${S3_ACCESS_KEY_ID:-messenger-api}
S3_SECRET_ACCESS_KEY: ${S3_SECRET_ACCESS_KEY:-change-me-minio-api}
BROKER_URL: ${BROKER_URL}
depends_on:
postgres:
condition: service_healthy
restart: "no"
api:
build: .
cpus: "0.5"
mem_limit: 256m
environment:
<<: *otel-environment
OTEL_SERVICE_NAME: messenger-api
DATABASE_URL: ${DATABASE_URL}
REDIS_URL: ${REDIS_URL}
SESSION_TTL_SECONDS: ${SESSION_TTL_SECONDS}
LOG_LEVEL: ${LOG_LEVEL:-info}
S3_ENDPOINT: ${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:-messenger-api}
S3_SECRET_ACCESS_KEY: ${S3_SECRET_ACCESS_KEY:-change-me-minio-api}
MAX_UPLOAD_BYTES: ${MAX_UPLOAD_BYTES:-10485760}
MAX_IMAGE_PIXELS: ${MAX_IMAGE_PIXELS:-40000000}
BROKER_URL: ${BROKER_URL}
JOB_MAX_ATTEMPTS: ${JOB_MAX_ATTEMPTS:-5}
expose:
- "8080"
deploy:
replicas: 2
depends_on:
migrate:
condition: service_completed_successfully
redis:
condition: service_healthy
s3-bootstrap:
condition: service_completed_successfully
healthcheck:
test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8080/health/ready', timeout=3).read()"]
interval: 2s
timeout: 2s
retries: 5
stop_grace_period: 10s
publisher:
build: .
command: ["python", "-m", "app.jobs.publisher"]
cpus: "0.25"
mem_limit: 192m
environment:
<<: *otel-environment
OTEL_SERVICE_NAME: messenger-publisher
DATABASE_URL: ${DATABASE_URL}
REDIS_URL: ${REDIS_URL}
SESSION_TTL_SECONDS: ${SESSION_TTL_SECONDS}
S3_ENDPOINT: ${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:-messenger-api}
S3_SECRET_ACCESS_KEY: ${S3_SECRET_ACCESS_KEY:-change-me-minio-api}
BROKER_URL: ${BROKER_URL}
JOB_MAX_ATTEMPTS: ${JOB_MAX_ATTEMPTS:-5}
JOB_LEASE_SECONDS: ${JOB_LEASE_SECONDS:-90}
depends_on:
migrate:
condition: service_completed_successfully
broker:
condition: service_healthy
healthcheck:
test: ["CMD", "python", "-c", "import os; os.kill(1, 0)"]
interval: 10s
timeout: 3s
retries: 3
restart: unless-stopped
stop_grace_period: 10s
worker:
build: .
command: ["python", "-m", "app.jobs.worker"]
cpus: "1.0"
mem_limit: 768m
environment:
<<: *otel-environment
OTEL_SERVICE_NAME: messenger-worker
DATABASE_URL: ${DATABASE_URL}
REDIS_URL: ${REDIS_URL}
SESSION_TTL_SECONDS: ${SESSION_TTL_SECONDS}
S3_ENDPOINT: ${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:-messenger-api}
S3_SECRET_ACCESS_KEY: ${S3_SECRET_ACCESS_KEY:-change-me-minio-api}
MAX_UPLOAD_BYTES: ${MAX_UPLOAD_BYTES:-10485760}
MAX_IMAGE_PIXELS: ${MAX_IMAGE_PIXELS:-40000000}
BROKER_URL: ${BROKER_URL}
WORKER_CONCURRENCY: ${WORKER_CONCURRENCY:-2}
WORKER_PREFETCH: ${WORKER_PREFETCH:-2}
JOB_MAX_ATTEMPTS: ${JOB_MAX_ATTEMPTS:-5}
JOB_TIMEOUT_SECONDS: ${JOB_TIMEOUT_SECONDS:-60}
JOB_LEASE_SECONDS: ${JOB_LEASE_SECONDS:-90}
RETRY_BASE_SECONDS: ${RETRY_BASE_SECONDS:-2}
RETRY_MAX_SECONDS: ${RETRY_MAX_SECONDS:-60}
STAGING_RETENTION_SECONDS: ${STAGING_RETENTION_SECONDS:-86400}
THUMBNAIL_JPEG_QUALITY: ${THUMBNAIL_JPEG_QUALITY:-85}
CROP_JPEG_QUALITY: ${CROP_JPEG_QUALITY:-85}
OPTIMIZED_WEBP_QUALITY: ${OPTIMIZED_WEBP_QUALITY:-82}
depends_on:
migrate:
condition: service_completed_successfully
broker:
condition: service_healthy
s3-bootstrap:
condition: service_completed_successfully
healthcheck:
test: ["CMD", "python", "-c", "import os; os.kill(1, 0)"]
interval: 10s
timeout: 3s
retries: 3
restart: unless-stopped
stop_grace_period: 70s
lb:
image: haproxy:3.2.26-alpine
cpus: "0.25"
mem_limit: 128m
ports:
- "${APP_PORT:-8080}:8080"
volumes:
- ./infra/haproxy.cfg:/usr/local/etc/haproxy/haproxy.cfg:ro
depends_on:
api:
condition: service_healthy
healthcheck:
test: ["CMD", "wget", "-q", "-O", "/dev/null", "http://127.0.0.1:8080/health/live"]
interval: 2s
timeout: 2s
retries: 5
stop_grace_period: 5s
otel-collector:
image: otel/opentelemetry-collector-contrib:0.123.0
cpus: "0.5"
mem_limit: 256m
command: ["--config=/etc/otelcol-contrib/collector.yaml"]
volumes:
- ./infra/otel/collector.yaml:/etc/otelcol-contrib/collector.yaml:ro
depends_on:
loki:
condition: service_started
tempo:
condition: service_started
restart: unless-stopped
prometheus:
image: prom/prometheus:v3.2.1
cpus: "0.5"
mem_limit: 384m
command:
- --config.file=/etc/prometheus/prometheus.yml
- --storage.tsdb.path=/prometheus
- --storage.tsdb.retention.time=7d
- --storage.tsdb.retention.size=1GB
volumes:
- ./infra/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
- prometheus_data:/prometheus
depends_on:
otel-collector:
condition: service_started
restart: unless-stopped
loki:
image: grafana/loki:3.4.2
user: "0"
cpus: "0.5"
mem_limit: 384m
command: ["-config.file=/etc/loki/loki.yaml"]
volumes:
- ./infra/loki/loki.yaml:/etc/loki/loki.yaml:ro
- loki_data:/loki
restart: unless-stopped
tempo:
image: grafana/tempo:2.7.2
user: "0"
cpus: "0.5"
mem_limit: 384m
command: ["-config.file=/etc/tempo/tempo.yaml"]
volumes:
- ./infra/tempo/tempo.yaml:/etc/tempo/tempo.yaml:ro
- tempo_data:/var/tempo
restart: unless-stopped
grafana:
image: grafana/grafana:11.6.0
cpus: "0.5"
mem_limit: 384m
environment:
GF_SECURITY_ADMIN_USER: ${GRAFANA_ADMIN_USER:-admin}
GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:-change-me-grafana}
GF_USERS_ALLOW_SIGN_UP: "false"
GF_ANALYTICS_REPORTING_ENABLED: "false"
GF_ANALYTICS_CHECK_FOR_UPDATES: "false"
GF_PLUGINS_PREINSTALL_DISABLED: "true"
ports:
- "127.0.0.1:${GRAFANA_PORT:-3000}:3000"
volumes:
- ./infra/grafana/provisioning:/etc/grafana/provisioning:ro
- ./infra/grafana/dashboards:/var/lib/grafana/dashboards:ro
- ./infra/grafana/runbooks:/var/lib/grafana/runbooks:ro
- grafana_data:/var/lib/grafana
depends_on:
prometheus:
condition: service_started
loki:
condition: service_started
tempo:
condition: service_started
healthcheck:
test: ["CMD-SHELL", "wget -q -O /dev/null http://127.0.0.1:3000/api/health"]
interval: 5s
timeout: 3s
retries: 20
restart: unless-stopped
volumes:
postgres_data:
redis_data:
s3_data:
broker_data:
prometheus_data:
loki_data:
tempo_data:
grafana_data: