forked from mtusi2026/mtusi2026lab6
Собрать наблюдаемый стенд, чтобы причину деградации API и worker было видно по метрикам, логам и трассам.
This commit is contained in:
+236
@@ -0,0 +1,236 @@
|
||||
name: mtusi-lab6
|
||||
|
||||
x-app-env: &app-env
|
||||
DATABASE_URL: postgresql://messenger:${POSTGRES_PASSWORD}@postgres:5432/messenger
|
||||
SESSION_TTL_SECONDS: ${SESSION_TTL_SECONDS:-3600}
|
||||
IDEMPOTENCY_TTL_SECONDS: ${IDEMPOTENCY_TTL_SECONDS:-86400}
|
||||
S3_ENDPOINT: http://s3:8333
|
||||
S3_REGION: us-east-1
|
||||
S3_BUCKET: messenger-attachments
|
||||
S3_ACCESS_KEY_ID: ${S3_ACCESS_KEY}
|
||||
S3_SECRET_ACCESS_KEY: ${S3_SECRET_KEY}
|
||||
BROKER_URL: amqp://${RABBITMQ_USER}:${RABBITMQ_PASSWORD}@rabbitmq:5672/%2F
|
||||
RABBITMQ_MANAGEMENT_URL: http://rabbitmq:15672
|
||||
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}
|
||||
MAX_UPLOAD_BYTES: "10485760"
|
||||
MAX_IMAGE_PIXELS: "40000000"
|
||||
DB_POOL_MAX: "8"
|
||||
OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4318
|
||||
OTEL_EXPORTER_OTLP_PROTOCOL: http/protobuf
|
||||
SERVICE_VERSION: "1.6.0"
|
||||
FAULT_DIR: /faults
|
||||
AWS_EC2_METADATA_DISABLED: "true"
|
||||
|
||||
services:
|
||||
postgres:
|
||||
image: postgres:16.6-alpine
|
||||
environment:
|
||||
POSTGRES_USER: messenger
|
||||
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
|
||||
POSTGRES_DB: messenger
|
||||
volumes:
|
||||
- pg-data:/var/lib/postgresql/data
|
||||
- ./app/schema.sql:/docker-entrypoint-initdb.d/01-schema.sql:ro
|
||||
healthcheck:
|
||||
test: ["CMD-SHELL", "pg_isready -U messenger -d messenger"]
|
||||
interval: 5s
|
||||
timeout: 3s
|
||||
retries: 20
|
||||
start_period: 10s
|
||||
mem_limit: 512m
|
||||
restart: unless-stopped
|
||||
|
||||
s3:
|
||||
image: chrislusf/seaweedfs:4.51
|
||||
command: ["server", "-dir=/data", "-ip=0.0.0.0", "-ip.bind=0.0.0.0", "-s3", "-s3.port=8333", "-s3.ip.bind=0.0.0.0", "-s3.config=/etc/seaweed/s3.json"]
|
||||
volumes:
|
||||
- s3-data:/data
|
||||
- ./infra/seaweed/s3.json:/etc/seaweed/s3.json:ro
|
||||
healthcheck:
|
||||
test: ["CMD", "weed", "version"]
|
||||
interval: 5s
|
||||
timeout: 5s
|
||||
retries: 20
|
||||
start_period: 5s
|
||||
mem_limit: 512m
|
||||
restart: unless-stopped
|
||||
|
||||
rabbitmq:
|
||||
image: rabbitmq:3.13.7-management-alpine
|
||||
environment:
|
||||
RABBITMQ_DEFAULT_USER: ${RABBITMQ_USER}
|
||||
RABBITMQ_DEFAULT_PASS: ${RABBITMQ_PASSWORD}
|
||||
volumes:
|
||||
- rabbit-data:/var/lib/rabbitmq
|
||||
healthcheck:
|
||||
test: ["CMD", "rabbitmq-diagnostics", "-q", "ping"]
|
||||
interval: 5s
|
||||
timeout: 5s
|
||||
retries: 20
|
||||
start_period: 15s
|
||||
mem_limit: 512m
|
||||
restart: unless-stopped
|
||||
|
||||
api-1: &api
|
||||
build: .
|
||||
image: mtusi-lab6-messenger:1.6.0
|
||||
environment:
|
||||
<<: *app-env
|
||||
OTEL_SERVICE_NAME: messenger-api
|
||||
INSTANCE_ID: api-1
|
||||
APP_ROLE: api
|
||||
OTEL_RESOURCE_ATTRIBUTES: deployment.environment.name=lab,service.version=1.6.0,service.instance.id=api-1
|
||||
volumes:
|
||||
- ./faults:/faults
|
||||
depends_on:
|
||||
postgres:
|
||||
condition: service_healthy
|
||||
rabbitmq:
|
||||
condition: service_healthy
|
||||
s3:
|
||||
condition: service_healthy
|
||||
healthcheck:
|
||||
test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8080/health/ready', timeout=3)"]
|
||||
interval: 5s
|
||||
timeout: 4s
|
||||
retries: 30
|
||||
start_period: 20s
|
||||
mem_limit: 512m
|
||||
restart: unless-stopped
|
||||
|
||||
api-2:
|
||||
<<: *api
|
||||
environment:
|
||||
<<: *app-env
|
||||
OTEL_SERVICE_NAME: messenger-api
|
||||
INSTANCE_ID: api-2
|
||||
APP_ROLE: api
|
||||
OTEL_RESOURCE_ATTRIBUTES: deployment.environment.name=lab,service.version=1.6.0,service.instance.id=api-2
|
||||
|
||||
worker:
|
||||
build: .
|
||||
image: mtusi-lab6-messenger:1.6.0
|
||||
command: ["python", "-m", "app.worker"]
|
||||
environment:
|
||||
<<: *app-env
|
||||
OTEL_SERVICE_NAME: messenger-worker
|
||||
INSTANCE_ID: worker-1
|
||||
APP_ROLE: worker
|
||||
OTEL_RESOURCE_ATTRIBUTES: deployment.environment.name=lab,service.version=1.6.0,service.instance.id=worker-1
|
||||
volumes:
|
||||
- ./faults:/faults
|
||||
depends_on:
|
||||
postgres:
|
||||
condition: service_healthy
|
||||
rabbitmq:
|
||||
condition: service_healthy
|
||||
s3:
|
||||
condition: service_healthy
|
||||
healthcheck:
|
||||
test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8081/health/ready', timeout=3)"]
|
||||
interval: 5s
|
||||
timeout: 4s
|
||||
retries: 30
|
||||
start_period: 20s
|
||||
mem_limit: 512m
|
||||
restart: unless-stopped
|
||||
|
||||
nginx:
|
||||
image: nginx:1.27.4-alpine
|
||||
depends_on:
|
||||
api-1:
|
||||
condition: service_healthy
|
||||
api-2:
|
||||
condition: service_healthy
|
||||
ports:
|
||||
- "127.0.0.1:8080:80"
|
||||
volumes:
|
||||
- ./infra/nginx/nginx.conf:/etc/nginx/conf.d/default.conf:ro
|
||||
mem_limit: 128m
|
||||
restart: unless-stopped
|
||||
|
||||
otel-collector:
|
||||
image: otel/opentelemetry-collector-contrib:0.120.0
|
||||
command: ["--config=/etc/otelcol/collector.yaml"]
|
||||
volumes:
|
||||
- ./infra/otel/collector.yaml:/etc/otelcol/collector.yaml:ro
|
||||
depends_on:
|
||||
- tempo
|
||||
- loki
|
||||
- prometheus
|
||||
mem_limit: 320m
|
||||
restart: unless-stopped
|
||||
|
||||
prometheus:
|
||||
image: prom/prometheus:v2.55.1
|
||||
command:
|
||||
- --config.file=/etc/prometheus/prometheus.yml
|
||||
- --storage.tsdb.path=/prometheus
|
||||
- --storage.tsdb.retention.time=2d
|
||||
- --web.enable-lifecycle
|
||||
volumes:
|
||||
- ./infra/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
|
||||
- ./infra/prometheus/rules.yml:/etc/prometheus/rules.yml:ro
|
||||
- prometheus-data:/prometheus
|
||||
ports:
|
||||
- "127.0.0.1:9090:9090"
|
||||
mem_limit: 512m
|
||||
restart: unless-stopped
|
||||
|
||||
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
|
||||
ports:
|
||||
- "127.0.0.1:3100:3100"
|
||||
mem_limit: 512m
|
||||
restart: unless-stopped
|
||||
|
||||
tempo:
|
||||
image: grafana/tempo:2.7.2
|
||||
command: ["-config.file=/etc/tempo/tempo.yml"]
|
||||
volumes:
|
||||
- ./infra/tempo/tempo.yml:/etc/tempo/tempo.yml:ro
|
||||
- tempo-data:/var/tempo
|
||||
ports:
|
||||
- "127.0.0.1:3200:3200"
|
||||
mem_limit: 512m
|
||||
restart: unless-stopped
|
||||
|
||||
grafana:
|
||||
image: grafana/grafana:11.5.2
|
||||
environment:
|
||||
GF_SECURITY_ADMIN_USER: admin
|
||||
GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD}
|
||||
GF_AUTH_ANONYMOUS_ENABLED: "true"
|
||||
GF_AUTH_ANONYMOUS_ORG_ROLE: Viewer
|
||||
GF_USERS_ALLOW_SIGN_UP: "false"
|
||||
GF_ANALYTICS_REPORTING_ENABLED: "false"
|
||||
GF_ANALYTICS_CHECK_FOR_UPDATES: "false"
|
||||
GF_SERVER_HTTP_PORT: "3000"
|
||||
volumes:
|
||||
- ./infra/grafana/provisioning:/etc/grafana/provisioning:ro
|
||||
- ./infra/grafana/dashboards:/var/lib/grafana/dashboards:ro
|
||||
- grafana-data:/var/lib/grafana
|
||||
ports:
|
||||
- "127.0.0.1:3000:3000"
|
||||
depends_on:
|
||||
- prometheus
|
||||
- loki
|
||||
- tempo
|
||||
mem_limit: 384m
|
||||
restart: unless-stopped
|
||||
|
||||
volumes:
|
||||
pg-data:
|
||||
s3-data:
|
||||
rabbit-data:
|
||||
prometheus-data:
|
||||
loki-data:
|
||||
tempo-data:
|
||||
grafana-data:
|
||||
Reference in New Issue
Block a user