Files
mtusi2026lab6/compose.yaml
alenchha 0638263029 ЛР 6 — БВТ2301 — Курлова — на 5 (трек 1 «Цена наблюдаемости»)
Перенесён минимум lab5 без изменения API и добавлена наблюдаемость:
- OTel SDK в API и worker: traces, metrics, logs по OTLP; W3C trace context
  API -> outbox -> RabbitMQ -> worker (producer/consumer spans, retry в той же трассе);
- OTel Collector (memory_limiter, scrub, batch, ограниченные очереди, профиль tail sampling),
  Prometheus, Loki, Tempo, Grafana с provisioning, dashboard и 6 alert rules с runbooks;
- проверки: наблюдаемость и приватность, инциденты A/B/C, насыщение worker,
  переполнение очереди exporter, эксперимент трека 1 (4 конфигурации x 3 прогона);
- CI job со сборкой и запуском стенда; REPORT.md с доказательствами в evidence/.
2026-11-11 09:24:27 +03:00

461 lines
13 KiB
YAML

name: mtusi-lab6
# OpenTelemetry SDK settings shared by the API replicas and the worker (track 1 overrides them from the shell).
x-otel-env: &otel-env
OTEL_SDK_DISABLED: ${OTEL_SDK_DISABLED:-false}
OTEL_TRACES_SAMPLER_ARG: ${OTEL_TRACES_SAMPLER_ARG:-1.0}
OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4318
OTEL_EXPORTER_OTLP_PROTOCOL: http/protobuf
OTEL_EXPORTER_OTLP_TIMEOUT: "5"
OTEL_RESOURCE_ATTRIBUTES: deployment.environment.name=lab
OTEL_SEMCONV_STABILITY_OPT_IN: http
OTEL_METRIC_EXPORT_INTERVAL: ${OTEL_METRIC_EXPORT_INTERVAL:-10000}
OTEL_BSP_MAX_QUEUE_SIZE: "2048"
OTEL_BSP_SCHEDULE_DELAY: "2000"
OTEL_BLRP_MAX_QUEUE_SIZE: "2048"
SERVICE_VERSION: "1.6.0"
x-api: &api-defaults
build:
context: .
image: mtusi-messenger:lab6
env_file:
- .env
secrets:
- database_url
- cache_url
- s3_access_key_id
- s3_secret_access_key
- broker_url
depends_on:
rabbitmq:
condition: service_healthy
postgres:
condition: service_healthy
valkey:
condition: service_healthy
minio-init:
condition: service_completed_successfully
migrate:
condition: service_completed_successfully
deploy:
resources:
limits:
cpus: "0.50"
memory: 512M
healthcheck:
test: ["CMD-SHELL", "python -c \"import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://127.0.0.1:8080/health/ready', timeout=2).status == 200 else 1)\""]
interval: 5s
timeout: 3s
retries: 3
start_period: 15s
restart: unless-stopped
services:
nginx:
image: nginx:1.27.3-alpine
command: ["/bin/sh", "/opt/nginx-health.sh"]
environment:
API_UPSTREAMS: ${API_UPSTREAMS:-api-1 api-2}
HEALTH_INTERVAL: "1"
HEALTH_FALL: "2"
HEALTH_RISE: "2"
ports:
- "127.0.0.1:8080:8080"
volumes:
- ./infra/nginx.conf:/etc/nginx/nginx.conf:ro
- ./infra/nginx-health.sh:/opt/nginx-health.sh:ro
depends_on:
api-1:
condition: service_healthy
api-2:
condition: service_healthy
deploy:
resources:
limits:
cpus: "0.25"
memory: 64M
healthcheck:
test: ["CMD-SHELL", "wget -qO- http://127.0.0.1:8080/health/live || exit 1"]
interval: 5s
timeout: 3s
retries: 3
start_period: 5s
restart: unless-stopped
api-1:
<<: *api-defaults
environment:
<<: *otel-env
INSTANCE_ID: api-1
DATABASE_URL_FILE: /run/secrets/database_url
CACHE_URL_FILE: /run/secrets/cache_url
S3_ACCESS_KEY_ID_FILE: /run/secrets/s3_access_key_id
S3_SECRET_ACCESS_KEY_FILE: /run/secrets/s3_secret_access_key
S3_ENDPOINT: http://minio:9000
BROKER_URL_FILE: /run/secrets/broker_url
MAX_PENDING_JOBS: ${MAX_PENDING_JOBS:-200}
api-2:
<<: *api-defaults
environment:
<<: *otel-env
INSTANCE_ID: api-2
DATABASE_URL_FILE: /run/secrets/database_url
CACHE_URL_FILE: /run/secrets/cache_url
S3_ACCESS_KEY_ID_FILE: /run/secrets/s3_access_key_id
S3_SECRET_ACCESS_KEY_FILE: /run/secrets/s3_secret_access_key
S3_ENDPOINT: http://minio:9000
BROKER_URL_FILE: /run/secrets/broker_url
MAX_PENDING_JOBS: ${MAX_PENDING_JOBS:-200}
worker:
build:
context: .
image: mtusi-messenger:lab6
command: ["python", "-m", "app.worker"]
env_file:
- .env
environment:
<<: *otel-env
DATABASE_URL_FILE: /run/secrets/database_url
S3_ACCESS_KEY_ID_FILE: /run/secrets/s3_access_key_id
S3_SECRET_ACCESS_KEY_FILE: /run/secrets/s3_secret_access_key
BROKER_URL_FILE: /run/secrets/broker_url
S3_ENDPOINT: http://minio:9000
CACHE_URL_FILE: ""
INSTANCE_ID: ""
DB_POOL_MAX: "6"
# Overridable from the shell for the track-1 experiment (shell env wins over .env interpolation).
WORKER_CONCURRENCY: ${WORKER_CONCURRENCY:-2}
WORKER_PREFETCH: ${WORKER_PREFETCH:-2}
secrets:
- database_url
- s3_access_key_id
- s3_secret_access_key
- broker_url
depends_on:
rabbitmq:
condition: service_healthy
postgres:
condition: service_healthy
minio-init:
condition: service_completed_successfully
migrate:
condition: service_completed_successfully
stop_grace_period: 30s
deploy:
replicas: ${WORKER_REPLICAS:-2}
resources:
limits:
cpus: "${WORKER_CPUS:-2.00}"
memory: 1536M
healthcheck:
test: ["CMD-SHELL", "python -c \"import os,sys,time; sys.exit(0 if time.time()-os.path.getmtime('/tmp/worker-heartbeat') < 15 else 1)\""]
interval: 5s
timeout: 3s
retries: 3
start_period: 15s
restart: unless-stopped
rabbitmq:
image: rabbitmq:4.0.5-alpine@sha256:e045b5166b9188a38eee5c99411709aa1f0ffa2ac75664053e64cb69411f7c32
hostname: rabbitmq
entrypoint: ["/bin/sh", "/opt/entrypoint.sh"]
secrets:
- rabbitmq_password
volumes:
- rabbitmqdata:/var/lib/rabbitmq
- ./infra/rabbitmq/rabbitmq.conf:/etc/rabbitmq/rabbitmq.conf:ro
- ./infra/rabbitmq/entrypoint.sh:/opt/entrypoint.sh:ro
deploy:
resources:
limits:
cpus: "1.00"
memory: 512M
healthcheck:
test: ["CMD", "rabbitmq-diagnostics", "-q", "check_port_connectivity"]
interval: 5s
timeout: 10s
retries: 20
start_period: 20s
restart: unless-stopped
postgres:
image: postgres:17.7-alpine@sha256:bb377b7239d2774ac8cc76f481596ce96c5a6b5e9d141f6d0a0ee371a6e7c0f2
environment:
POSTGRES_DB: messenger
POSTGRES_USER: messenger
POSTGRES_PASSWORD_FILE: /run/secrets/postgres_password
POSTGRES_INITDB_ARGS: --data-checksums
command:
- postgres
- -c
- synchronous_commit=on
- -c
- shared_buffers=128MB
- -c
- work_mem=8MB
- -c
- max_connections=50
- -c
- track_io_timing=on
secrets:
- postgres_password
volumes:
- pgdata:/var/lib/postgresql/data
deploy:
resources:
limits:
cpus: "1.00"
memory: 512M
healthcheck:
test: ["CMD-SHELL", "pg_isready -U messenger -d messenger"]
interval: 5s
timeout: 3s
retries: 20
start_period: 10s
restart: unless-stopped
valkey:
image: valkey/valkey:8.1-alpine@sha256:081c2f5cb575efc901aa80ff9cdbd1ec6a301682fd35e1ebb4b0990a4a4a8507
command:
- valkey-server
- --save
- ""
- --appendonly
- "no"
- --maxmemory
- 64mb
- --maxmemory-policy
- allkeys-lru
deploy:
resources:
limits:
cpus: "0.25"
memory: 128M
healthcheck:
test: ["CMD", "valkey-cli", "ping"]
interval: 5s
timeout: 3s
retries: 10
start_period: 5s
restart: unless-stopped
minio:
image: madlabcg/minio@sha256:ad134b2dd572ae0d989d6807c3e45516cc75a34883a8021db2ff04be5d1d496a
command: ["server", "/data"]
environment:
MINIO_ROOT_USER_FILE: /run/secrets/minio_root_user
MINIO_ROOT_PASSWORD_FILE: /run/secrets/minio_root_password
MINIO_BROWSER: "off"
secrets:
- minio_root_user
- minio_root_password
volumes:
- miniodata:/data
deploy:
resources:
limits:
cpus: "0.50"
memory: 512M
healthcheck:
test: ["CMD-SHELL", "mc ready local || exit 1"]
interval: 5s
timeout: 3s
retries: 10
start_period: 10s
restart: unless-stopped
minio-init:
image: madlabcg/minio@sha256:ad134b2dd572ae0d989d6807c3e45516cc75a34883a8021db2ff04be5d1d496a
entrypoint: ["/bin/sh", "/opt/init.sh"]
environment:
S3_BUCKET: messenger-attachments
secrets:
- minio_root_user
- minio_root_password
- s3_access_key_id
- s3_secret_access_key
volumes:
- ./infra/minio/init.sh:/opt/init.sh:ro
- ./infra/minio/app-policy.json:/etc/minio-policy/app-policy.json:ro
depends_on:
minio:
condition: service_healthy
restart: "no"
migrate:
build:
context: .
image: mtusi-messenger:lab6
command: ["python", "scripts/migrate.py"]
environment:
DATABASE_URL_FILE: /run/secrets/database_url
secrets:
- database_url
depends_on:
postgres:
condition: service_healthy
deploy:
resources:
limits:
cpus: "0.25"
memory: 128M
restart: "no"
# ------------------------------------------------------------------ observability (lab6)
otel-collector:
image: otel/opentelemetry-collector-contrib:0.120.0@sha256:85ac41c2db88d0df9bd6145e608a3cb023f5d8443868adbfbbf66efb51087917
command:
- --config=/etc/otelcol/collector.yaml
- --config=/etc/otelcol/profile-${COLLECTOR_PROFILE:-default}.yaml
volumes:
- ./infra/otel/collector.yaml:/etc/otelcol/collector.yaml:ro
- ./infra/otel/profile-default.yaml:/etc/otelcol/profile-default.yaml:ro
- ./infra/otel/profile-tail.yaml:/etc/otelcol/profile-tail.yaml:ro
# OTLP 4317/4318 and self-metrics 8888 stay inside the compose network.
deploy:
resources:
limits:
cpus: "1.00"
memory: 256M
restart: unless-stopped
prometheus:
image: prom/prometheus:v3.2.1@sha256:6927e0919a144aa7616fd0137d4816816d42f6b816de3af269ab065250859a62
command:
- --config.file=/etc/prometheus/prometheus.yml
- --storage.tsdb.path=/prometheus
- --storage.tsdb.retention.time=15d
- --web.enable-otlp-receiver
- --web.enable-lifecycle
volumes:
- ./infra/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
- ./infra/prometheus/rules:/etc/prometheus/rules:ro
- promdata:/prometheus
ports:
- "127.0.0.1:9090:9090" # query API for evidence scripts (localhost only)
deploy:
resources:
limits:
cpus: "1.00"
memory: 512M
healthcheck:
test: ["CMD", "wget", "-qO-", "http://127.0.0.1:9090/-/ready"]
interval: 5s
timeout: 3s
retries: 20
restart: unless-stopped
loki:
image: grafana/loki:3.4.2@sha256:58a6c186ce78ba04d58bfe2a927eff296ba733a430df09645d56cdc158f3ba08
command: ["-config.file=/etc/loki/loki.yaml"]
volumes:
- ./infra/loki/loki.yaml:/etc/loki/loki.yaml:ro
- lokidata:/loki
ports:
- "127.0.0.1:3100:3100"
deploy:
resources:
limits:
cpus: "1.00"
memory: 512M
healthcheck:
test: ["CMD", "wget", "-qO-", "http://127.0.0.1:3100/ready"]
interval: 5s
timeout: 3s
retries: 30
start_period: 15s
restart: unless-stopped
tempo:
image: grafana/tempo:2.7.1@sha256:4443be217c396b065ee34845534199c36fdba4dc619cb96550e228d73fba6e69
command: ["-config.file=/etc/tempo/tempo.yaml"]
volumes:
- ./infra/tempo/tempo.yaml:/etc/tempo/tempo.yaml:ro
- tempodata:/var/tempo
ports:
- "127.0.0.1:3200:3200"
deploy:
resources:
limits:
cpus: "1.00"
memory: 1024M
healthcheck:
test: ["CMD", "wget", "-qO-", "http://127.0.0.1:3200/ready"]
interval: 5s
timeout: 3s
retries: 30
start_period: 15s
restart: unless-stopped
grafana:
image: grafana/grafana:11.5.2@sha256:8b37a2f028f164ce7b9889e1765b9d6ee23fec80f871d156fbf436d6198d32b7
environment:
GF_SECURITY_ADMIN_USER: admin
GF_SECURITY_ADMIN_PASSWORD__FILE: /run/secrets/grafana_admin_password
GF_USERS_ALLOW_SIGN_UP: "false"
GF_ANALYTICS_REPORTING_ENABLED: "false"
GF_ANALYTICS_CHECK_FOR_UPDATES: "false"
GF_NEWS_NEWS_FEED_ENABLED: "false"
GF_DASHBOARDS_DEFAULT_HOME_DASHBOARD_PATH: /var/lib/grafana/dashboards/messenger.json
secrets:
- grafana_admin_password
volumes:
- ./infra/grafana/provisioning:/etc/grafana/provisioning:ro
- ./infra/grafana/dashboards:/var/lib/grafana/dashboards:ro
- grafanadata:/var/lib/grafana
ports:
- "127.0.0.1:3000:3000"
depends_on:
prometheus:
condition: service_healthy
loki:
condition: service_started
tempo:
condition: service_started
deploy:
resources:
limits:
cpus: "0.50"
memory: 256M
healthcheck:
test: ["CMD", "wget", "-qO-", "http://127.0.0.1:3000/api/health"]
interval: 5s
timeout: 3s
retries: 30
start_period: 15s
restart: unless-stopped
volumes:
pgdata:
miniodata:
rabbitmqdata:
promdata:
lokidata:
tempodata:
grafanadata:
secrets:
minio_root_user:
file: ./secrets/minio_root_user
minio_root_password:
file: ./secrets/minio_root_password
postgres_password:
file: ./secrets/postgres_password
database_url:
file: ./secrets/database_url
cache_url:
file: ./secrets/cache_url
s3_access_key_id:
file: ./secrets/s3_access_key_id
s3_secret_access_key:
file: ./secrets/s3_secret_access_key
broker_url:
file: ./secrets/broker_url
rabbitmq_password:
file: ./secrets/rabbitmq_password
grafana_admin_password:
file: ./secrets/grafana_admin_password