forked from mtusi2026/mtusi2026lab4
upload_memory.py recreates the replicas and the balancer for every run of 10, 20 and 40 concurrent uploads of 1 and 10 MiB with 64 slots (effectively no limit) and with 3, drives them through lab4_seed.py from the prepared tooling, and keeps per-run JSON plus a summary with the cgroup memory.peak of each replica and of the balancer and the oom_kill counters. The seed script now also records memory.current before the load and reads X-Instance-Id regardless of case. The first run showed that slots alone only move a waiting body out of the worker: with 3 slots and 40 uploads of 10 MiB the kernel grew the socket buffers of HAProxy to about 110 MB and the 128 MiB balancer was killed. HAProxy now caps its client and server socket buffers at 64 KiB and the API replicas cap tcp_rmem and tcp_wmem at 256 KiB, which keeps the balancer at 30 MiB. glibc raised its mmap threshold after the first large free and kept freed 10 MiB bodies in the heap, so the API fixes MALLOC_MMAP_THRESHOLD_ at 128 KiB. With these settings 40 concurrent uploads of 10 MiB peak at 323 MiB of 512 per replica and all 80 succeed, while without the slot limit the same load reaches 512 MiB, a worker is killed and only 31 of 80 succeed. UPLOAD_CONCURRENCY stays at 3. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01V1d3RLHNBBMA6UqBLLJv27
72 lines
2.8 KiB
INI
72 lines
2.8 KiB
INI
global
|
|
log stdout format raw local0 info
|
|
maxconn 4096
|
|
hard-stop-after 5s
|
|
tune.bufsize 32768
|
|
tune.rcvbuf.client 65536
|
|
tune.rcvbuf.server 65536
|
|
tune.sndbuf.client 65536
|
|
tune.sndbuf.server 65536
|
|
|
|
resolvers docker
|
|
nameserver dns 127.0.0.11:53
|
|
accepted_payload_size 8192
|
|
resolve_retries 3
|
|
timeout resolve 1s
|
|
timeout retry 1s
|
|
hold nx 2s
|
|
hold other 2s
|
|
hold refused 2s
|
|
hold timeout 2s
|
|
|
|
defaults
|
|
mode http
|
|
log global
|
|
option dontlognull
|
|
option dontlog-normal
|
|
log-format "%ci [%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"
|
|
option http-server-close
|
|
option redispatch 1
|
|
retries 2
|
|
retry-on conn-failure empty-response
|
|
timeout connect 500ms
|
|
timeout client 30s
|
|
timeout server 10s
|
|
timeout http-request 5s
|
|
timeout http-keep-alive 5s
|
|
timeout queue 3s
|
|
timeout check 1s
|
|
http-error status 502 content-type application/json hdr X-Request-Id "%[var(txn.request_id)]" lf-string '{"error":{"code":"unavailable","message":"Upstream replica failed","request_id":"%[var(txn.request_id)]"}}'
|
|
http-error status 503 content-type application/json hdr X-Request-Id "%[var(txn.request_id)]" lf-string '{"error":{"code":"unavailable","message":"No ready API replica","request_id":"%[var(txn.request_id)]"}}'
|
|
http-error status 504 content-type application/json hdr X-Request-Id "%[var(txn.request_id)]" lf-string '{"error":{"code":"unavailable","message":"Upstream timeout","request_id":"%[var(txn.request_id)]"}}'
|
|
|
|
frontend public
|
|
bind :8080
|
|
option forwardfor
|
|
http-request set-var(txn.request_id) req.fhdr(X-Request-Id) if { req.fhdr(X-Request-Id) -m len 1:200 }
|
|
http-request set-var(txn.request_id) uuid(4) unless { var(txn.request_id) -m found }
|
|
http-request set-header X-Request-Id %[var(txn.request_id)]
|
|
default_backend api
|
|
|
|
backend api
|
|
balance roundrobin
|
|
option httpchk
|
|
http-check send meth GET uri /health/ready ver HTTP/1.1 hdr Host lb
|
|
http-check expect status 200
|
|
acl message_path path_reg ^/api/v1/chats/[^/]+/messages$
|
|
acl has_key req.hdr(Idempotency-Key) -m found
|
|
http-request set-var(txn.replay_safe) bool(1) if METH_GET
|
|
http-request set-var(txn.replay_safe) bool(1) if METH_POST message_path has_key
|
|
http-request disable-l7-retry unless { var(txn.replay_safe) -m bool }
|
|
default-server check init-state fully-down inter 1s fastinter 500ms downinter 2s fall 2 rise 2 resolvers docker resolve-prefer ipv4 init-addr none maxconn "${API_SERVER_MAXCONN-64}"
|
|
server-template api 8 api:8080
|
|
|
|
frontend stats
|
|
bind :8404
|
|
monitor-uri /healthz
|
|
monitor fail if { nbsrv(api) lt 1 }
|
|
http-request use-service prometheus-exporter if { path /metrics }
|
|
stats enable
|
|
stats uri /stats
|
|
stats refresh 5s
|