Files
mtusi2026lab2/compose.yaml
T
ArtyomandClaude Opus 5.5 e927afdb09 Carry over the lab 3 fixes made after 61c0c28
Bring the system changes of lab 3 from 61c0c28..72a1e57 onto the lab 4
code, resolving each conflict by meaning and keeping everything lab 4
added:

- a message is posted with one SQL statement under the chat row lock,
  and the attachment links go into the same statement; a foreign key
  violation on the attachment link still answers 404 and leaves nothing
  behind. Text and the attachment list are checked before the write, an
  outsider gets 404 for both, as before the carry over;
- the request pipeline counts the body bytes actually received against
  the limit of the route, so a chunked body over 1 MiB gets 413 and the
  upload route keeps its MAX_UPLOAD_BYTES limit;
- a request cancelled at shutdown gets 503 unavailable in the contract
  format, the worker waits a second less than the rest of the shutdown
  budget, SHUTDOWN_TIMEOUT_SECONDS becomes 6 s and the stop hooks 7 s;
- readiness sits behind a Readiness port with the draining flag in
  shared infrastructure, and the drain window is logged through Logger;
- logout revokes through SessionRevocations and withdraws the mark when
  PostgreSQL rejects the delete; an empty cursor is 400;
- EventBus.project is gone, the sweep test subscribes and waits on a
  queue; domain tests check attachment_list instead of Chat.post;
- make up waits for every replica in the balancer, BASE_URL follows the
  lb port, the image is tagged by the compose project, retry-check and
  faults-evidence are added, detection runs three times, failover-each
  and rolling-update record the stand usage, CI checks numeric uids.
  down also takes the tools and reconcile profiles of lab 4.

Track 1 tooling of lab 3 (scaling.py, its samplers, tools/ and the CPU
pinning of api, lb, valkey and k6) stays out; stand-usage.sh queries the
database size itself instead of the track 1 sampler.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V1d3RLHNBBMA6UqBLLJv27
2026-10-30 06:25:23 +03:00

307 lines
9.2 KiB
YAML

x-app: &app
image: ${API_IMAGE:-mtusi-messenger:${COMPOSE_PROJECT_NAME}}
networks: [backend]
x-s3-env: &s3-env
S3_ENDPOINT: ${S3_ENDPOINT:-http://s3:9000}
S3_REGION: ${S3_REGION:-us-east-1}
S3_BUCKET: ${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
S3_CONNECT_TIMEOUT_SECONDS: ${S3_CONNECT_TIMEOUT_SECONDS:-1}
S3_READ_TIMEOUT_SECONDS: ${S3_READ_TIMEOUT_SECONDS:-2}
MAX_UPLOAD_BYTES: ${MAX_UPLOAD_BYTES:-10485760}
MAX_IMAGE_PIXELS: ${MAX_IMAGE_PIXELS:-40000000}
IMAGE_CHECK_CONCURRENCY: ${IMAGE_CHECK_CONCURRENCY:-2}
UPLOAD_CONCURRENCY: ${UPLOAD_CONCURRENCY:-3}
UPLOAD_GRACE_SECONDS: ${UPLOAD_GRACE_SECONDS:-900}
UPLOAD_SWEEP_INTERVAL_SECONDS: ${UPLOAD_SWEEP_INTERVAL_SECONDS:-30}
UPLOAD_SWEEP_BATCH: ${UPLOAD_SWEEP_BATCH:-100}
x-s3-client: &s3-client
image: rustfs/rc:v0.1.36@sha256:ab024bfebee49a750ce886b4c70963ccd9ddaa03f491704a90710641d7a26699
read_only: true
tmpfs: ["/tmp:size=16m"]
environment:
S3_ENDPOINT: ${S3_ENDPOINT:-http://s3:9000}
S3_BUCKET: ${S3_BUCKET:-messenger-attachments}
RC_CONFIG_DIR: /tmp/rc
volumes: ["./infra/s3:/s3:ro"]
secrets: [s3_root_user, s3_root_password, s3_access_key_id, s3_secret_access_key]
cap_drop: [ALL]
security_opt: ["no-new-privileges:true"]
restart: "no"
networks: [backend]
deploy:
resources:
limits: {cpus: "0.5", memory: 64m}
services:
lb:
image: haproxy:3.2.26-alpine@sha256:5893840576071e6217cd52ebdcc14f454c6f7a631056fa6f4e0f40d3cac4215b
environment:
API_SERVER_MAXCONN: ${API_SERVER_MAXCONN:-64}
volumes: [./infra/haproxy/haproxy.cfg:/usr/local/etc/haproxy/haproxy.cfg:ro]
ports:
- "127.0.0.1:${LB_HTTP_PORT:-8080}:8080"
- "127.0.0.1:${LB_STATS_PORT:-8404}:8404"
networks: [edge, backend]
healthcheck:
test: ["CMD", "wget", "-q", "-O", "/dev/null", "http://127.0.0.1:8404/healthz"]
interval: 2s
timeout: 2s
retries: 3
start_period: 60s
start_interval: 1s
sysctls:
net.ipv4.ip_local_port_range: "10240 65535"
net.ipv4.tcp_tw_reuse: "1"
stop_signal: SIGUSR1
stop_grace_period: 8s
restart: unless-stopped
read_only: true
cap_drop: [ALL]
deploy:
resources:
limits: {cpus: "${LB_CPUS:-1}", memory: 128m}
api:
<<: *app
build: .
environment:
<<: *s3-env
DATABASE_URL_FILE: /run/secrets/database_url
CACHE_URL_FILE: /run/secrets/cache_url
CURSOR_SECRET_FILE: /run/secrets/cursor_secret
SESSION_TTL_SECONDS: ${SESSION_TTL_SECONDS:-3600}
IDEMPOTENCY_TTL_SECONDS: ${IDEMPOTENCY_TTL_SECONDS:-86400}
WEB_CONCURRENCY: ${WEB_CONCURRENCY:-2}
DB_POOL_MAX_SIZE: ${DB_POOL_MAX_SIZE:-8}
REQUEST_TIMEOUT_SECONDS: ${REQUEST_TIMEOUT_SECONDS:-8}
DB_ACQUIRE_TIMEOUT_SECONDS: ${DB_ACQUIRE_TIMEOUT_SECONDS:-1}
DB_COMMAND_TIMEOUT_SECONDS: ${DB_COMMAND_TIMEOUT_SECONDS:-2}
DRAIN_SECONDS: ${DRAIN_SECONDS:-2}
SHUTDOWN_TIMEOUT_SECONDS: ${SHUTDOWN_TIMEOUT_SECONDS:-6}
LOG_LEVEL: ${LOG_LEVEL:-INFO}
MALLOC_MMAP_THRESHOLD_: ${MALLOC_MMAP_THRESHOLD_:-131072}
secrets: [database_url, cache_url, cursor_secret, s3_access_key_id, s3_secret_access_key]
healthcheck:
test: ["CMD", "python", "-c", "import sys,urllib.request;sys.exit(urllib.request.urlopen('http://127.0.0.1:8080/health/ready',timeout=2).status!=200)"]
interval: 5s
timeout: 3s
retries: 3
start_period: 30s
start_interval: 200ms
stop_grace_period: 8s
restart: unless-stopped
read_only: true
tmpfs: [/tmp]
sysctls:
net.ipv4.tcp_rmem: "4096 65536 262144"
net.ipv4.tcp_wmem: "4096 65536 262144"
depends_on:
migrate:
condition: service_completed_successfully
valkey:
condition: service_started
s3-init:
condition: service_completed_successfully
deploy:
replicas: ${API_REPLICAS:-2}
resources:
limits: {cpus: "${API_CPUS:-1}", memory: "${API_MEMORY:-512m}"}
migrate:
<<: *app
pull_policy: never
command: ["python", "-m", "messenger.migrate"]
environment:
DATABASE_URL_FILE: /run/secrets/database_url
LOG_LEVEL: ${LOG_LEVEL:-INFO}
secrets: [database_url]
healthcheck:
disable: true
restart: "no"
depends_on:
postgres:
condition: service_healthy
deploy:
resources:
limits: {cpus: "0.5", memory: 256m}
postgres:
image: postgres:17.11-alpine@sha256:266d3c257594e195b309ae9d1805e54c788f1d7b375f56bf6c367aac6c917e7b
user: "70:70"
command:
- postgres
- -c
- max_connections=${PG_MAX_CONNECTIONS:-200}
- -c
- shared_buffers=${PG_SHARED_BUFFERS:-256MB}
- -c
- shared_preload_libraries=pg_stat_statements
- -c
- pg_stat_statements.track=top
- -c
- track_io_timing=on
- -c
- idle_in_transaction_session_timeout=10s
environment:
POSTGRES_DB: messenger
POSTGRES_USER: messenger
POSTGRES_PASSWORD_FILE: /run/secrets/postgres_password
secrets: [postgres_password]
volumes: [pgdata:/var/lib/postgresql/data]
shm_size: 256m
cpuset: ${PG_CPUSET:-}
healthcheck:
test: ["CMD", "pg_isready", "-h", "127.0.0.1", "-U", "messenger", "-d", "messenger"]
interval: 2s
timeout: 3s
retries: 30
start_period: 10s
start_interval: 200ms
stop_grace_period: 10s
restart: unless-stopped
networks: [backend]
deploy:
resources:
limits: {cpus: "${PG_CPUS:-2}", memory: "${PG_MEMORY:-1g}"}
valkey:
image: valkey/valkey:8.1.11-alpine@sha256:2602ace2be6569bc2bbb06f873776516ab9089821525be34f4305c67eb9db02a
user: "999:1000"
command:
- valkey-server
- /run/secrets/valkey.conf
- --appendonly
- "yes"
- --appendfsync
- always
- --maxmemory
- 64mb
- --maxmemory-policy
- volatile-lru
secrets: [valkey.conf]
volumes: [valkeydata:/data]
healthcheck:
test: ["CMD-SHELL", "REDISCLI_AUTH=\"$$(sed -n 's/^requirepass //p' /run/secrets/valkey.conf)\" valkey-cli ping | grep -q PONG"]
interval: 2s
timeout: 3s
retries: 30
stop_grace_period: 10s
restart: unless-stopped
networks: [backend]
deploy:
resources:
limits: {cpus: "0.5", memory: 128m}
s3:
image: rustfs/rustfs:1.0.4@sha256:ed9210d6411d77ffceb70d94b964a3cb7d225983368bc25bebe01e995293dcc2
environment:
RUSTFS_ACCESS_KEY_FILE: /run/secrets/s3_root_user
RUSTFS_SECRET_KEY_FILE: /run/secrets/s3_root_password
RUSTFS_ADDRESS: ":9000"
RUSTFS_CONSOLE_ENABLE: "false"
RUSTFS_REGION: ${S3_REGION:-us-east-1}
RUSTFS_OBS_LOG_DIRECTORY: ""
RUSTFS_OBS_LOGGER_LEVEL: ${S3_LOG_LEVEL:-warn}
secrets: [s3_root_user, s3_root_password]
volumes: [s3data:/data]
cpuset: ${S3_CPUSET:-}
read_only: true
tmpfs: ["/tmp:size=64m"]
cap_drop: [ALL]
security_opt: ["no-new-privileges:true"]
healthcheck:
test: ["CMD", "curl", "-fsS", "-o", "/dev/null", "http://127.0.0.1:9000/health/ready"]
interval: 2s
timeout: 3s
retries: 30
start_period: 20s
stop_grace_period: 10s
restart: unless-stopped
networks: [backend]
deploy:
resources:
limits: {cpus: "${S3_CPUS:-1}", memory: "${S3_MEMORY:-512m}"}
reconciler:
<<: *app
pull_policy: never
profiles: [reconcile]
entrypoint: ["python", "-m", "messenger.attachments.entrypoints.reconcile"]
command: ["--dry-run"]
environment:
<<: *s3-env
DATABASE_URL_FILE: /run/secrets/database_url
S3_READ_TIMEOUT_SECONDS: ${RECONCILE_S3_READ_TIMEOUT_SECONDS:-10}
LOG_LEVEL: ${LOG_LEVEL:-INFO}
secrets: [database_url, s3_access_key_id, s3_secret_access_key]
healthcheck:
disable: true
restart: "no"
read_only: true
cpuset: ${RECONCILE_CPUSET:-}
depends_on:
postgres:
condition: service_healthy
s3:
condition: service_healthy
deploy:
resources:
limits: {cpus: "${RECONCILE_CPUS:-1}", memory: "${RECONCILE_MEMORY:-256m}"}
s3-init:
<<: *s3-client
entrypoint: ["/bin/sh", "/s3/init.sh"]
depends_on:
s3:
condition: service_healthy
s3-cli:
<<: *s3-client
profiles: [tools]
entrypoint: ["/bin/sh", "/s3/cli.sh"]
k6:
image: grafana/k6:2.3.0@sha256:2dd4756ec6e14e62778916e1eb850108e4b499304c02df56760fa0bdb0fba0b8
profiles: [bench]
environment:
BASE_URL: http://lb:8080
volumes: [./infra/k6:/scripts:ro]
networks: [edge]
deploy:
resources:
limits: {cpus: "${K6_CPUS:-2}", memory: "${K6_MEMORY:-512m}"}
secrets:
postgres_password:
file: ./secrets/postgres_password
database_url:
file: ./secrets/database_url
valkey.conf:
file: ./secrets/valkey.conf
cache_url:
file: ./secrets/cache_url
cursor_secret:
file: ./secrets/cursor_secret
s3_root_user:
file: ./secrets/s3_root_user
s3_root_password:
file: ./secrets/s3_root_password
s3_access_key_id:
file: ./secrets/s3_access_key_id
s3_secret_access_key:
file: ./secrets/s3_secret_access_key
volumes:
pgdata:
valkeydata:
s3data:
networks:
edge:
backend:
internal: true