forked from mtusi2026/mtusi2026lab6
Переиспользован стек lab5. API/worker шлют OTLP (traces/metrics/logs) в otel-collector -> Prometheus/Loki/Tempo; Grafana с provisioning датасорсов, дашборда и alert rules в Git. W3C trace context переносится через поле traceparent в задании очереди (API producer span -> worker consumer span в одном trace, подтверждено прямым запросом к Tempo). Три контролируемых инцидента прогнаны и задокументированы (worker down -> queue lag + alert, DB down отличим от медленного handler по error-span, telemetry backend down не роняет API/Collector). В процессе найдены и исправлены 4 реальных бага (middleware после старта приложения, detached span context, замерзающая метрика очереди при падении её единственного источника, неатомарный XACK+XDEL) — см. REPORT.md и evidence/. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
264 lines
6.5 KiB
YAML
264 lines
6.5 KiB
YAML
name: mtusi2026lab6
|
|
|
|
services:
|
|
lb:
|
|
image: nginx:1.27.2
|
|
ports:
|
|
- "8080:8080"
|
|
volumes:
|
|
- ./infra/nginx/nginx.conf:/etc/nginx/nginx.conf:ro
|
|
depends_on:
|
|
api1:
|
|
condition: service_healthy
|
|
api2:
|
|
condition: service_healthy
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
cpus: "0.5"
|
|
memory: 128M
|
|
|
|
api1: &api
|
|
build: .
|
|
image: mtusi2026lab6-app:local
|
|
environment: &api-env
|
|
APP_HOST: 0.0.0.0
|
|
APP_PORT: 8080
|
|
APP_ENV: lab
|
|
SESSION_TTL_SECONDS: ${SESSION_TTL_SECONDS:-3600}
|
|
DATABASE_URL_FILE: /run/secrets/database_url
|
|
CACHE_URL_FILE: /run/secrets/cache_url
|
|
S3_ENDPOINT: http://seaweedfs:8333
|
|
S3_REGION: us-east-1
|
|
S3_BUCKET: messenger-attachments
|
|
S3_ACCESS_KEY_ID_FILE: /run/secrets/s3_access_key_id
|
|
S3_SECRET_ACCESS_KEY_FILE: /run/secrets/s3_secret_access_key
|
|
MAX_UPLOAD_BYTES: ${MAX_UPLOAD_BYTES:-10485760}
|
|
MAX_IMAGE_PIXELS: ${MAX_IMAGE_PIXELS:-40000000}
|
|
OTEL_SERVICE_NAME: messenger-api
|
|
OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4318
|
|
DEPLOYMENT_ENVIRONMENT: lab
|
|
INSTANCE_ID: api1
|
|
secrets: &api-secrets
|
|
- database_url
|
|
- cache_url
|
|
- s3_access_key_id
|
|
- s3_secret_access_key
|
|
depends_on:
|
|
postgres:
|
|
condition: service_healthy
|
|
redis:
|
|
condition: service_healthy
|
|
seaweedfs:
|
|
condition: service_healthy
|
|
otel-collector:
|
|
condition: service_started
|
|
healthcheck: &api-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: 5
|
|
start_period: 10s
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
cpus: "1.0"
|
|
memory: 320M
|
|
|
|
api2:
|
|
<<: *api
|
|
environment:
|
|
<<: *api-env
|
|
INSTANCE_ID: api2
|
|
|
|
worker:
|
|
build: .
|
|
image: mtusi2026lab6-app:local
|
|
command: ["python3", "-m", "app.worker"]
|
|
environment:
|
|
DATABASE_URL_FILE: /run/secrets/database_url
|
|
CACHE_URL_FILE: /run/secrets/cache_url
|
|
S3_ENDPOINT: http://seaweedfs:8333
|
|
S3_REGION: us-east-1
|
|
S3_BUCKET: messenger-attachments
|
|
S3_ACCESS_KEY_ID_FILE: /run/secrets/s3_access_key_id
|
|
S3_SECRET_ACCESS_KEY_FILE: /run/secrets/s3_secret_access_key
|
|
JOB_MAX_ATTEMPTS: ${JOB_MAX_ATTEMPTS:-5}
|
|
JOB_TIMEOUT_SECONDS: ${JOB_TIMEOUT_SECONDS:-60}
|
|
OTEL_SERVICE_NAME: messenger-worker
|
|
OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4318
|
|
DEPLOYMENT_ENVIRONMENT: lab
|
|
INSTANCE_ID: worker1
|
|
secrets: *api-secrets
|
|
depends_on:
|
|
postgres:
|
|
condition: service_healthy
|
|
redis:
|
|
condition: service_healthy
|
|
seaweedfs:
|
|
condition: service_healthy
|
|
otel-collector:
|
|
condition: service_started
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
cpus: "1.0"
|
|
memory: 384M
|
|
|
|
postgres:
|
|
image: postgres:16.4
|
|
environment:
|
|
POSTGRES_DB: messenger
|
|
POSTGRES_USER: messenger
|
|
POSTGRES_PASSWORD_FILE: /run/secrets/postgres_password
|
|
secrets:
|
|
- postgres_password
|
|
volumes:
|
|
- pgdata:/var/lib/postgresql/data
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U messenger -d messenger"]
|
|
interval: 5s
|
|
timeout: 3s
|
|
retries: 10
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
cpus: "1.0"
|
|
memory: 512M
|
|
|
|
redis:
|
|
image: redis:7.4.1
|
|
command: ["redis-server", "--appendonly", "yes", "--appendfsync", "everysec"]
|
|
volumes:
|
|
- redisdata:/data
|
|
healthcheck:
|
|
test: ["CMD", "redis-cli", "ping"]
|
|
interval: 5s
|
|
timeout: 3s
|
|
retries: 10
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
cpus: "0.5"
|
|
memory: 256M
|
|
|
|
seaweedfs:
|
|
image: chrislusf/seaweedfs:3.73
|
|
command:
|
|
- server
|
|
- -dir=/data
|
|
- -s3
|
|
- -s3.port=8333
|
|
- -s3.config=/etc/seaweedfs/s3.json
|
|
volumes:
|
|
- seaweed_data:/data
|
|
- ./secrets/s3.json:/etc/seaweedfs/s3.json:ro
|
|
healthcheck:
|
|
test: ["CMD", "nc", "-z", "127.0.0.1", "8333"]
|
|
interval: 5s
|
|
timeout: 3s
|
|
retries: 10
|
|
start_period: 10s
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
cpus: "1.0"
|
|
memory: 512M
|
|
|
|
otel-collector:
|
|
image: otel/opentelemetry-collector-contrib:0.114.0
|
|
command: ["--config=/etc/otel-collector/config.yaml"]
|
|
volumes:
|
|
- ./infra/otel-collector/config.yaml:/etc/otel-collector/config.yaml:ro
|
|
depends_on:
|
|
- prometheus
|
|
- loki
|
|
- tempo
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
cpus: "0.5"
|
|
memory: 200M
|
|
|
|
prometheus:
|
|
image: prom/prometheus:v3.0.1
|
|
command:
|
|
- --config.file=/etc/prometheus/prometheus.yml
|
|
- --storage.tsdb.path=/prometheus
|
|
- --storage.tsdb.retention.time=7d
|
|
volumes:
|
|
- ./infra/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
|
|
- prometheus_data:/prometheus
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
cpus: "0.5"
|
|
memory: 256M
|
|
|
|
loki:
|
|
image: grafana/loki:3.2.1
|
|
command: ["-config.file=/etc/loki/loki-config.yaml"]
|
|
volumes:
|
|
- ./infra/loki/loki-config.yaml:/etc/loki/loki-config.yaml:ro
|
|
- loki_data:/loki
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
cpus: "0.5"
|
|
memory: 256M
|
|
|
|
tempo:
|
|
image: grafana/tempo:2.6.1
|
|
command: ["-config.file=/etc/tempo/tempo.yaml"]
|
|
volumes:
|
|
- ./infra/tempo/tempo.yaml:/etc/tempo/tempo.yaml:ro
|
|
- tempo_data:/var/tempo
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
cpus: "0.5"
|
|
memory: 256M
|
|
|
|
grafana:
|
|
image: grafana/grafana:11.3.1
|
|
ports:
|
|
- "3000:3000"
|
|
environment:
|
|
GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD}
|
|
GF_AUTH_ANONYMOUS_ENABLED: "false"
|
|
GF_FEATURE_TOGGLES_ENABLE: traceqlEditor
|
|
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: "0.5"
|
|
memory: 256M
|
|
|
|
volumes:
|
|
pgdata:
|
|
redisdata:
|
|
seaweed_data:
|
|
prometheus_data:
|
|
loki_data:
|
|
tempo_data:
|
|
grafana_data:
|
|
|
|
secrets:
|
|
database_url:
|
|
file: ./secrets/database_url.txt
|
|
cache_url:
|
|
file: ./secrets/cache_url.txt
|
|
postgres_password:
|
|
file: ./secrets/postgres_password.txt
|
|
s3_access_key_id:
|
|
file: ./secrets/s3_access_key_id.txt
|
|
s3_secret_access_key:
|
|
file: ./secrets/s3_secret_access_key.txt
|