Files
mtusi2026lab6/compose.yaml
T

427 lines
15 KiB
YAML

name: hla-lab6
x-api-environment: &api-environment
APP_HOST: 0.0.0.0
APP_PORT: 8080
OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4318
OTEL_EXPORTER_OTLP_PROTOCOL: http/protobuf
OTEL_TRACES_EXPORTER: otlp
OTEL_METRICS_EXPORTER: otlp
OTEL_LOGS_EXPORTER: otlp
OTEL_PROPAGATORS: tracecontext,baggage
OTEL_SDK_DISABLED: ${OTEL_SDK_DISABLED:-false}
OTEL_TRACES_SAMPLER: ${OTEL_TRACES_SAMPLER:-parentbased_traceidratio}
OTEL_TRACES_SAMPLER_ARG: ${OTEL_TRACES_SAMPLER_ARG:-0.25}
OTEL_METRIC_EXPORT_INTERVAL: ${OTEL_METRIC_EXPORT_INTERVAL:-30000}
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_EXPORT_TIMEOUT: ${OTEL_BSP_EXPORT_TIMEOUT:-5000}
OTEL_ATTRIBUTE_VALUE_LENGTH_LIMIT: ${OTEL_ATTRIBUTE_VALUE_LENGTH_LIMIT:-256}
OTEL_RESOURCE_ATTRIBUTES: service.version=0.0.1,deployment.environment.name=${APP_ENV:-lab}
OTEL_INSTRUMENTATION_LOGBACK_APPENDER_EXPERIMENTAL_MDC_ATTRIBUTES_INCLUDED: request_id
OTEL_INSTRUMENTATION_COMMON_LOGGING_STRUCTURED_ATTRIBUTES_INCLUDED: event,job.type,outcome,attempt,error.code,http.request.method,http.route,http.response.status_code
OTEL_INSTRUMENTATION_HTTP_SERVER_CAPTURE_REQUEST_HEADERS: ""
OTEL_INSTRUMENTATION_HTTP_SERVER_CAPTURE_RESPONSE_HEADERS: ""
DATABASE_URL: jdbc:postgresql://postgres:5432/${DATABASE_NAME:-messenger}
DATABASE_USER: ${DATABASE_USER:-messenger}
DATABASE_PASSWORD: ${DATABASE_PASSWORD:?Set DATABASE_PASSWORD in .env}
DATABASE_POOL_SIZE: ${DATABASE_POOL_SIZE:-10}
DATABASE_MIN_IDLE: ${DATABASE_MIN_IDLE:-2}
DATABASE_QUERY_TIMEOUT_SECONDS: ${DATABASE_QUERY_TIMEOUT_SECONDS:-5}
DATABASE_TRANSACTION_TIMEOUT_SECONDS: ${DATABASE_TRANSACTION_TIMEOUT_SECONDS:-5}
REDIS_HOST: redis
REDIS_PORT: 6379
REDIS_CONNECT_TIMEOUT: ${REDIS_CONNECT_TIMEOUT:-1s}
REDIS_COMMAND_TIMEOUT: ${REDIS_COMMAND_TIMEOUT:-500ms}
REDIS_POOL_MAX_ACTIVE: ${REDIS_POOL_MAX_ACTIVE:-8}
REDIS_POOL_MAX_IDLE: ${REDIS_POOL_MAX_IDLE:-8}
REDIS_POOL_MIN_IDLE: ${REDIS_POOL_MIN_IDLE:-0}
REDIS_POOL_MAX_WAIT: ${REDIS_POOL_MAX_WAIT:-500ms}
USER_CACHE_TTL_SECONDS: ${USER_CACHE_TTL_SECONDS:-300}
SESSION_TTL_SECONDS: ${SESSION_TTL_SECONDS:-3600}
IDEMPOTENCY_TTL_SECONDS: ${IDEMPOTENCY_TTL_SECONDS:-86400}
S3_ENDPOINT: http://minio:9000
S3_REGION: ${S3_REGION:-us-east-1}
S3_BUCKET: ${S3_BUCKET:-messenger-attachments}
S3_ACCESS_KEY_ID: ${S3_ACCESS_KEY_ID:?Set S3_ACCESS_KEY_ID in .env}
S3_SECRET_ACCESS_KEY: ${S3_SECRET_ACCESS_KEY:?Set S3_SECRET_ACCESS_KEY in .env}
MAX_UPLOAD_BYTES: ${MAX_UPLOAD_BYTES:-10485760}
MAX_IMAGE_PIXELS: ${MAX_IMAGE_PIXELS:-40000000}
MAX_CONCURRENT_UPLOADS: ${MAX_CONCURRENT_UPLOADS:-3}
UPLOAD_PERMIT_WAIT_MILLIS: ${UPLOAD_PERMIT_WAIT_MILLIS:-10000}
RABBITMQ_HOST: rabbitmq
RABBITMQ_PORT: 5672
RABBITMQ_USER: ${RABBITMQ_USER:-messenger}
RABBITMQ_PASSWORD: ${RABBITMQ_PASSWORD:?Set RABBITMQ_PASSWORD in .env}
RABBITMQ_VHOST: ${RABBITMQ_VHOST:-/}
ATTACHMENT_JOB_EXCHANGE: ${ATTACHMENT_JOB_EXCHANGE:-attachments.v1}
ATTACHMENT_JOB_QUEUE: ${ATTACHMENT_JOB_QUEUE:-attachments.process.level4.v1}
ATTACHMENT_JOB_ROUTING_KEY: ${ATTACHMENT_JOB_ROUTING_KEY:-attachment.process.v1}
ATTACHMENT_DLQ_EXCHANGE: ${ATTACHMENT_DLQ_EXCHANGE:-attachments.dlx.v1}
ATTACHMENT_DLQ_QUEUE: ${ATTACHMENT_DLQ_QUEUE:-attachments.failed.v1}
ATTACHMENT_DLQ_ROUTING_KEY: ${ATTACHMENT_DLQ_ROUTING_KEY:-attachment.failed.v1}
ATTACHMENT_PIPELINE_VERSION: ${ATTACHMENT_PIPELINE_VERSION:-2}
WORKER_CONCURRENCY: ${WORKER_CONCURRENCY:-2}
WORKER_PREFETCH: ${WORKER_PREFETCH:-1}
JOB_MAX_ATTEMPTS: ${JOB_MAX_ATTEMPTS:-5}
JOB_RETRY_BASE_DELAY: ${JOB_RETRY_BASE_DELAY:-1s}
JOB_RETRY_MAX_DELAY: ${JOB_RETRY_MAX_DELAY:-30s}
JOB_TIMEOUT: ${JOB_TIMEOUT:-60s}
JOB_LEASE_DURATION: ${JOB_LEASE_DURATION:-90s}
JOB_LEASE_REAPER_INTERVAL: ${JOB_LEASE_REAPER_INTERVAL:-5s}
WORKER_MAX_IMAGE_PIXELS: ${WORKER_MAX_IMAGE_PIXELS:-40000000}
WORKER_MEMORY_BUDGET_BYTES: ${WORKER_MEMORY_BUDGET_BYTES:-536870912}
WORKER_MEMORY_WAIT: ${WORKER_MEMORY_WAIT:-2s}
STAGING_RETENTION_SECONDS: ${STAGING_RETENTION_SECONDS:-86400}
ATTACHMENT_CLEANUP_GRACE_SECONDS: ${ATTACHMENT_CLEANUP_GRACE_SECONDS:-3600}
ATTACHMENT_CLEANUP_DRY_RUN: ${ATTACHMENT_CLEANUP_DRY_RUN:-false}
ATTACHMENT_RECONCILE_INTERVAL_MILLIS: ${ATTACHMENT_RECONCILE_INTERVAL_MILLIS:-600000}
ATTACHMENT_RECONCILE_INITIAL_DELAY_MILLIS: ${ATTACHMENT_RECONCILE_INITIAL_DELAY_MILLIS:-60000}
services:
postgres:
image: postgres:16.4-bookworm
environment:
POSTGRES_DB: ${DATABASE_NAME:-messenger}
POSTGRES_USER: ${DATABASE_USER:-messenger}
POSTGRES_PASSWORD: ${DATABASE_PASSWORD:?Set DATABASE_PASSWORD in .env}
volumes:
- postgres-data:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U $${POSTGRES_USER} -d $${POSTGRES_DB}"]
interval: 2s
timeout: 2s
retries: 30
restart: unless-stopped
cpus: 1.0
mem_limit: 768m
networks: [backend]
redis:
image: redis:7.4-bookworm
command: ["redis-server", "--appendonly", "yes", "--appendfsync", "everysec"]
volumes:
- redis-data:/data
healthcheck:
test: ["CMD", "redis-cli", "ping"]
interval: 2s
timeout: 2s
retries: 30
restart: unless-stopped
cpus: 0.25
mem_limit: 256m
networks: [backend]
rabbitmq:
image: rabbitmq:4.1.4-management-alpine
environment:
RABBITMQ_DEFAULT_USER: ${RABBITMQ_USER:-messenger}
RABBITMQ_DEFAULT_PASS: ${RABBITMQ_PASSWORD:?Set RABBITMQ_PASSWORD in .env}
RABBITMQ_DEFAULT_VHOST: ${RABBITMQ_VHOST:-/}
RABBITMQ_SERVER_ADDITIONAL_ERL_ARGS: "+S 2:2"
volumes:
- rabbitmq-data:/var/lib/rabbitmq
healthcheck:
test: ["CMD", "rabbitmq-diagnostics", "-q", "ping"]
interval: 10s
timeout: 10s
start_period: 60s
retries: 12
restart: unless-stopped
cpus: 0.5
mem_limit: 1024m
networks: [backend]
minio:
image: bitnamilegacy/minio:2025.4.22-debian-12-r1@sha256:d7cd0e172c4cc0870f4bdc3142018e2a37be9acf04d68f386600daad427e0cab
environment:
MINIO_ROOT_USER: ${MINIO_ROOT_USER:?Set MINIO_ROOT_USER in .env}
MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:?Set MINIO_ROOT_PASSWORD in .env}
volumes:
- minio-data:/bitnami/minio/data
healthcheck:
test: ["CMD", "curl", "--fail", "--silent", "http://localhost:9000/minio/health/live"]
interval: 2s
timeout: 2s
retries: 30
restart: unless-stopped
cpus: 0.75
mem_limit: 512m
networks: [backend]
minio-init:
image: bitnamilegacy/minio-client:2025.4.16-debian-12-r0@sha256:28e38f52642c06a2344fa974cf55786b4c52601b6b9b0676c68d40ee0876a5bc
depends_on:
minio:
condition: service_healthy
environment:
MINIO_ROOT_USER: ${MINIO_ROOT_USER:?Set MINIO_ROOT_USER in .env}
MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:?Set MINIO_ROOT_PASSWORD in .env}
S3_BUCKET: ${S3_BUCKET:-messenger-attachments}
S3_ACCESS_KEY_ID: ${S3_ACCESS_KEY_ID:?Set S3_ACCESS_KEY_ID in .env}
S3_SECRET_ACCESS_KEY: ${S3_SECRET_ACCESS_KEY:?Set S3_SECRET_ACCESS_KEY in .env}
volumes:
- ./infra/minio-api-policy.json:/policy/minio-api-policy.json:ro
entrypoint: ["/bin/sh", "-c"]
command:
- |
set -eu
sed "s/__S3_BUCKET__/$$S3_BUCKET/g" /policy/minio-api-policy.json > /tmp/minio-api-policy.json
attempt=0
until mc alias set local http://minio:9000 "$$MINIO_ROOT_USER" "$$MINIO_ROOT_PASSWORD" \
&& mc mb --ignore-existing "local/$$S3_BUCKET" \
&& mc anonymous set none "local/$$S3_BUCKET" \
&& (mc admin user add local "$$S3_ACCESS_KEY_ID" "$$S3_SECRET_ACCESS_KEY" \
|| mc admin user info local "$$S3_ACCESS_KEY_ID") \
&& (mc admin policy create local messenger-attachments-rw /tmp/minio-api-policy.json \
|| mc admin policy info local messenger-attachments-rw) \
&& mc admin policy attach local messenger-attachments-rw --user "$$S3_ACCESS_KEY_ID"
do
attempt=$$((attempt + 1))
if [ "$$attempt" -ge 30 ]; then
echo "MinIO bootstrap did not complete after 30 attempts" >&2
exit 1
fi
sleep 2
done
restart: "no"
networks: [backend]
private-bucket-check:
profiles: ["verification"]
image: bitnamilegacy/minio-client:2025.4.16-debian-12-r0@sha256:28e38f52642c06a2344fa974cf55786b4c52601b6b9b0676c68d40ee0876a5bc
depends_on:
minio-init:
condition: service_completed_successfully
environment:
S3_BUCKET: ${S3_BUCKET:-messenger-attachments}
S3_ACCESS_KEY_ID: ${S3_ACCESS_KEY_ID:?Set S3_ACCESS_KEY_ID in .env}
S3_SECRET_ACCESS_KEY: ${S3_SECRET_ACCESS_KEY:?Set S3_SECRET_ACCESS_KEY in .env}
entrypoint: ["/bin/sh", "-c"]
command:
- |
set -eu
mc alias set anonymous http://minio:9000
if mc ls "anonymous/$$S3_BUCKET" >/dev/null 2>&1; then
echo "FAIL: anonymous bucket listing succeeded" >&2
exit 1
fi
mc alias set restricted http://minio:9000 "$$S3_ACCESS_KEY_ID" "$$S3_SECRET_ACCESS_KEY"
mc ls "restricted/$$S3_BUCKET" >/dev/null
if mc admin info restricted >/dev/null 2>&1; then
echo "FAIL: API credentials have administrative access" >&2
exit 1
fi
echo "PASS: bucket is private and API credentials are non-admin"
restart: "no"
networks: [backend]
# One-shot Flyway runner. It is invoked explicitly before API replicas.
migrate:
image: hla-lab6-app:local
build:
context: .
environment:
<<: *api-environment
FLYWAY_ENABLED: "true"
MIGRATE_ONLY: "true"
MESSENGER_ROLE: migration
SPRING_MAIN_WEB_APPLICATION_TYPE: none
OTEL_SDK_DISABLED: "true"
depends_on:
postgres:
condition: service_healthy
redis:
condition: service_healthy
rabbitmq:
condition: service_healthy
restart: "no"
cpus: 0.75
mem_limit: 768m
networks: [backend]
api:
image: hla-lab6-app:local
build:
context: .
environment:
<<: *api-environment
FLYWAY_ENABLED: "false"
MESSENGER_ROLE: api
OTEL_SERVICE_NAME: messenger-api
FAULT_CRASH_AFTER_OUTBOX_COMMIT: ${FAULT_CRASH_AFTER_OUTBOX_COMMIT:-false}
depends_on:
migrate:
condition: service_completed_successfully
redis:
condition: service_healthy
minio-init:
condition: service_completed_successfully
rabbitmq:
condition: service_healthy
otel-collector:
condition: service_started
healthcheck:
test: ["CMD", "curl", "--fail", "--silent", "http://localhost:8080/health/ready"]
interval: 2s
timeout: 2s
retries: 30
start_period: 180s
init: true
stop_grace_period: 12s
restart: unless-stopped
cpus: 0.75
mem_limit: 768m
networks: [backend]
worker:
image: hla-lab6-app:local
environment:
<<: *api-environment
FLYWAY_ENABLED: "false"
MESSENGER_ROLE: worker
OTEL_SERVICE_NAME: messenger-worker
SPRING_MAIN_WEB_APPLICATION_TYPE: none
JAVA_TOOL_OPTIONS: -XX:MaxRAMPercentage=70
FAULT_CRASH_BEFORE_SIDE_EFFECT: ${FAULT_CRASH_BEFORE_SIDE_EFFECT:-false}
FAULT_CRASH_AFTER_SIDE_EFFECT: ${FAULT_CRASH_AFTER_SIDE_EFFECT:-false}
FAULT_CRASH_AFTER_RESULT_COMMIT: ${FAULT_CRASH_AFTER_RESULT_COMMIT:-false}
depends_on:
migrate:
condition: service_completed_successfully
minio-init:
condition: service_completed_successfully
rabbitmq:
condition: service_healthy
otel-collector:
condition: service_started
healthcheck:
disable: true
init: true
stop_grace_period: 20s
restart: unless-stopped
cpus: 1.0
mem_limit: 1024m
networks: [backend]
nginx:
image: nginx:1.27.4-bookworm
ports:
- "127.0.0.1:${APP_PORT:-8080}:80"
volumes:
- ./infra/nginx.conf:/etc/nginx/nginx.conf:ro
depends_on:
api:
condition: service_healthy
healthcheck:
test: ["CMD", "nginx", "-t"]
interval: 2s
timeout: 2s
retries: 15
stop_grace_period: 10s
restart: unless-stopped
cpus: 0.25
mem_limit: 128m
networks: [backend]
otel-collector:
image: otel/opentelemetry-collector-contrib:0.165.0
command: ["--config=/etc/otelcol-contrib/collector.yaml"]
volumes:
- ./infra/otel/collector.yaml:/etc/otelcol-contrib/collector.yaml:ro
depends_on:
prometheus:
condition: service_started
loki:
condition: service_started
tempo:
condition: service_started
restart: unless-stopped
cpus: 0.5
mem_limit: 512m
networks: [backend]
prometheus:
image: prom/prometheus:v3.14.0
ports:
- "127.0.0.1:${PROMETHEUS_PORT:-9090}:9090"
command:
- --config.file=/etc/prometheus/prometheus.yml
- --storage.tsdb.path=/prometheus
- --storage.tsdb.retention.time=3d
- --web.enable-lifecycle
volumes:
- ./infra/otel/prometheus.yaml:/etc/prometheus/prometheus.yml:ro
- ./infra/otel/prometheus-alerts.yaml:/etc/prometheus/prometheus-alerts.yaml:ro
- prometheus-data:/prometheus
restart: unless-stopped
cpus: 0.5
mem_limit: 512m
networks: [backend]
loki:
image: grafana/loki:3.7.8
command: ["-config.file=/etc/loki/local-config.yaml"]
ports:
- "127.0.0.1:${LOKI_PORT:-3100}:3100"
volumes:
- ./infra/otel/loki.yaml:/etc/loki/local-config.yaml:ro
- loki-data:/loki
restart: unless-stopped
cpus: 0.5
mem_limit: 512m
networks: [backend]
tempo:
image: grafana/tempo:3.1.1
command: ["-config.file=/etc/tempo/tempo.yaml"]
ports:
- "127.0.0.1:${TEMPO_PORT:-3200}:3200"
volumes:
- ./infra/otel/tempo.yaml:/etc/tempo/tempo.yaml:ro
- tempo-data:/var/tempo
restart: unless-stopped
cpus: 0.5
mem_limit: 512m
networks: [backend]
grafana:
image: grafana/grafana:13.3.0
ports:
- "127.0.0.1:${GRAFANA_PORT:-3000}:3000"
environment:
GF_SECURITY_ADMIN_USER: ${GRAFANA_ADMIN_USER:-admin}
GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:?Set GRAFANA_ADMIN_PASSWORD in .env}
GF_USERS_ALLOW_SIGN_UP: "false"
GF_AUTH_ANONYMOUS_ENABLED: "false"
GF_UNIFIED_ALERTING_ENABLED: "true"
volumes:
- ./infra/otel/grafana/provisioning:/etc/grafana/provisioning:ro
- ./infra/otel/grafana/dashboards:/var/lib/grafana/dashboards:ro
- grafana-data:/var/lib/grafana
depends_on:
prometheus:
condition: service_started
loki:
condition: service_started
tempo:
condition: service_started
restart: unless-stopped
cpus: 0.5
mem_limit: 512m
networks: [backend]
networks:
backend:
driver: bridge
volumes:
postgres-data:
redis-data:
minio-data:
rabbitmq-data:
prometheus-data:
loki-data:
tempo-data:
grafana-data: