forked from mtusi2026/mtusi2026lab4
- compose: сервис s3 (SeaweedFS 4.46 по digest, volume s3data, внутренняя сеть storage,
web-интерфейсы только на 127.0.0.1 внутри контейнера), одноразовый s3-init;
- три пары ключей S3: admin (только bootstrap), api (Read+Write своего bucket),
reconciler (+List); bootstrap идемпотентен и проверяет приватность и права;
- миграция 0004: attachments (pending -> ready, случайный object_key), message_attachments,
post_message_v2 с проверкой вложений в той же транзакции;
- POST /chats/{id}/attachments: лимиты до чтения/декодирования, потоковая проверка PNG
(CRC + zlib до точного размера), JPEG через djpeg -strict, семафор загрузок;
- GET метаданных и /content (стриминг из S3, без redirect), readiness с S3,
HAProxy: деградированный режим без S3 через /health/ready/core;
- janitor незавершённых загрузок с grace period.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
117 lines
6.3 KiB
INI
117 lines
6.3 KiB
INI
# HAProxy 3.2 LTS — the single public entry point of the lab 4 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 + S3 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 fallback servers without checks: a replica that
|
|
# answers /health/live but not /health/ready never gets traffic while a fully ready one exists.
|
|
#
|
|
# Degraded mode (lab 4): S3 is a SHARED dependency. If it is down, /health/ready is 503 on
|
|
# every replica and backend `api` has no server. Instead of answering 503 to everything, the
|
|
# frontend then switches to backend `api_core`: the same replicas, checked by
|
|
# /health/ready/core (PostgreSQL + Valkey, not draining). Chats and text messages keep working,
|
|
# every attachment request is answered 503 by the API itself (fast, S3_TIMEOUT_SECONDS).
|
|
# A replica that alone lost S3 (e.g. its storage network) is DOWN in `api` while the others are
|
|
# UP, so it gets no traffic at all.
|
|
# Worst case detection of a failed replica (a check answered at once counts at once, a check
|
|
# that hangs counts only after `timeout check`):
|
|
# fast explicit 503 (drain after SIGTERM): inter 1 s + fastinter 0.5 s ~= 1.5 s;
|
|
# slow ready (PostgreSQL/Valkey unreachable: the answer takes ~1 s = timeout check)
|
|
# or frozen process: inter 1 s + 1 s + fastinter 0.5 s + 1 s ~= 3.5 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\""
|
|
use_backend api if { nbsrv(api) gt 0 }
|
|
default_backend api_core
|
|
|
|
backend api
|
|
balance roundrobin
|
|
# Uploads (<= 10 MiB body + verification + S3 PUT): the API's own budget is
|
|
# UPLOAD_READ_TIMEOUT 30 s + IMAGE_VERIFY 10 s + S3; the LB must not cut it at 10 s (a 504
|
|
# after a successful upload would make the client upload a duplicate).
|
|
acl is_upload path_reg ^/api/v1/chats/[^/]+/attachments$
|
|
http-request set-timeout server 60s if is_upload METH_POST
|
|
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
|
|
|
|
# Degraded mode only (see the header): used when NO replica is fully ready.
|
|
backend api_core
|
|
balance roundrobin
|
|
acl is_upload path_reg ^/api/v1/chats/[^/]+/attachments$
|
|
http-request set-timeout server 60s if is_upload METH_POST
|
|
option httpchk
|
|
http-check send meth GET uri /health/ready/core 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 core 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
|