forked from mtusi2026/mtusi2026lab3
- compose: один масштабируемый сервис api (deploy.replicas=2, без ports и container_name), HAProxy 3.2 LTS по digest — единственная точка входа (127.0.0.1), разовый migrate до старта реплик, CPU/RAM-лимиты у всех сервисов, каждому сервису только его secrets. - HAProxy: server-template + Docker DNS (re-resolve 1 с), активная проверка GET /health/ready каждую 1 с (fall 2 / rise 2), без backup-серверов, retry только conn-failure, ошибки самого LB — в формате контракта с X-Request-Id. - API: X-Instance-Id = hostname контейнера на каждом ответе (и на 500/503); Idempotency-Key обязателен; ключ, сообщение и результат пишутся в ОДНОЙ транзакции (миграция 0002), конкурентный повтор ждёт уникальный индекс; другой body — 409, посторонний — всегда 404; attachment_ids=[] равен отсутствию поля; дубли ключей JSON и тело у POST /auth/sessions — 400. - SIGTERM: readiness 503 + DRAIN_SECONDS=3 обслуживания, затем graceful stop. - scripts: stop-one.sh (+ .cmd для Windows), restore-api.sh, restart.sh перезапускает и LB, lbctl.py — состояние бэкендов HAProxy -> контейнеры. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
90 lines
4.6 KiB
INI
90 lines
4.6 KiB
INI
# HAProxy 3.2 LTS — the single public entry point of the lab 3 stand (compose service `lb`).
|
|
#
|
|
# Backend discovery: Docker DNS name `api` returns one A record per RUNNING replica of the
|
|
# compose service `api` (deploy.replicas / --scale). server-template keeps 8 slots and
|
|
# re-resolves every second, so scale up/down, a restarted container with a new IP and a
|
|
# full stack restart are picked up without restarting the LB. A stopped container drops
|
|
# out of DNS and its slot goes to MAINT.
|
|
#
|
|
# Readiness: an ACTIVE check `GET /health/ready` (PostgreSQL + Valkey reachable, not draining)
|
|
# every 1 s; 2 failures -> DOWN, 2 successes -> UP. Passive errors do not decide anything on
|
|
# their own, and there are NO backup/fallback servers without checks: a replica that answers
|
|
# /health/live but not /health/ready never gets business traffic.
|
|
# Worst case detection of a failed replica:
|
|
# inter 1 s + fall 2 x (check timeout 1 s) ~= 3 s (frozen process);
|
|
# refused connection / 503 ready: inter 1 s + fastinter 0.5 s ~= 1.5 s.
|
|
# Requests that could not even be SENT (connection refused/reset before the request)
|
|
# are retried on another replica (retry-on conn-failure + redispatch) - safe for POST,
|
|
# because the API has not seen them. Nothing that may have reached the API is retried by
|
|
# the LB: an uncertain POST is retried by the CLIENT with the same Idempotency-Key.
|
|
# No sticky sessions: sessions live in Valkey, every replica serves every user.
|
|
|
|
global
|
|
log stdout format raw local0 info
|
|
maxconn 4096
|
|
# Runtime API for `show servers state` / `show stat` (scripts and tests, no network port).
|
|
stats socket /var/lib/haproxy/admin.sock mode 600 level admin
|
|
hard-stop-after 15s
|
|
|
|
resolvers docker
|
|
nameserver dns1 127.0.0.11:53
|
|
accepted_payload_size 8192
|
|
resolve_retries 3
|
|
timeout resolve 1s
|
|
timeout retry 1s
|
|
hold valid 1s
|
|
hold other 1s
|
|
hold refused 1s
|
|
hold nx 1s
|
|
hold timeout 1s
|
|
hold obsolete 1s
|
|
|
|
defaults
|
|
mode http
|
|
log global
|
|
option httplog
|
|
option dontlognull
|
|
option http-keep-alive
|
|
timeout connect 1s
|
|
timeout client 30s
|
|
timeout server 10s # > DB_TIMEOUT_SECONDS (3 s): the API answers 503 itself first
|
|
timeout http-request 10s
|
|
timeout http-keep-alive 10s
|
|
timeout queue 3s
|
|
timeout check 1s
|
|
retries 2
|
|
retry-on conn-failure
|
|
option redispatch 1
|
|
# Errors generated by the LB itself, in the contract error format with the same request id.
|
|
# They carry no X-Instance-Id: no API replica produced them. 502/504 = the outcome of the
|
|
# request is unknown (a replica died mid-request / did not answer in time): retry with the
|
|
# same Idempotency-Key. 503 = no ready replica at all.
|
|
http-error status 502 content-type application/json lf-string "{\"error\":{\"code\":\"unavailable\",\"message\":\"API-реплика оборвала ответ; повторите с тем же Idempotency-Key\",\"request_id\":\"%[var(txn.request_id)]\"}}" hdr X-Request-Id "%[var(txn.request_id)]"
|
|
http-error status 503 content-type application/json lf-string "{\"error\":{\"code\":\"unavailable\",\"message\":\"Нет готовых API-реплик\",\"request_id\":\"%[var(txn.request_id)]\"}}" hdr X-Request-Id "%[var(txn.request_id)]"
|
|
http-error status 504 content-type application/json lf-string "{\"error\":{\"code\":\"unavailable\",\"message\":\"API-реплика не ответила вовремя; повторите с тем же Idempotency-Key\",\"request_id\":\"%[var(txn.request_id)]\"}}" hdr X-Request-Id "%[var(txn.request_id)]"
|
|
|
|
frontend public
|
|
bind :8080
|
|
# One request id end to end: keep a valid client X-Request-Id, otherwise create one; the
|
|
# API echoes it, and errors generated by the LB itself carry the same value.
|
|
http-request set-header X-Request-Id %[uuid()] unless { req.hdr(x-request-id) -m reg ^[A-Za-z0-9._:-]{1,128}$ }
|
|
http-request set-var(txn.request_id) req.hdr(x-request-id)
|
|
log-format "%ci:%cp [%tr] %ft %b/%s %TR/%Tw/%Tc/%Tr/%Ta %ST %B %tsc %ac/%fc/%bc/%sc/%rc %sq/%bq rid=%[var(txn.request_id)] \"%HM %HPO\""
|
|
default_backend api
|
|
|
|
backend api
|
|
balance roundrobin
|
|
option httpchk
|
|
http-check send meth GET uri /health/ready ver HTTP/1.1 hdr Host api
|
|
http-check expect status 200
|
|
default-server inter 1s fastinter 500ms downinter 1s fall 2 rise 2 check resolvers docker init-addr none resolve-prefer ipv4 maxconn 200
|
|
server-template api 8 api:8080
|
|
|
|
# Local-only status page (127.0.0.1:8404 on the host): which replica is UP/DOWN right now.
|
|
frontend stats
|
|
bind :8404
|
|
stats enable
|
|
stats uri /
|
|
stats refresh 2s
|
|
stats show-legends
|