forked from mtusi2026/mtusi2026lab2
Brings the system changes of lab 2 from 8cddb09..102579e onto the lab 3 code, resolving each conflict by meaning: - the request pipeline counts the body bytes actually received, so a chunked body over the limit gets 413 instead of reaching the app; - logout revokes through a SessionRevocations port and withdraws the mark when PostgreSQL rejects the delete, so 503 means the session still works; PostgresSessionDirectory loses its no-op invalidate; - an empty cursor is 400 on history and on the chat list; - EventBus.project and the test that allowed importing an event across zones are gone, the config rules speak of the schema foreign key; - the worker waits one second less than the rest of the shutdown budget, so it cancels a stuck request with 500 and exits 0 instead of being killed by the gunicorn master. Lab 3 keeps 3 s after the drain window for the database timeouts, so SHUTDOWN_TIMEOUT_SECONDS becomes 6 s and the stop hooks wait 7 s, still under the 8 s grace; - the lab 3 single statement post already locks the chat only for a member, so lab 2's LOCK_CHAT edit is not needed; its test is kept; - lab 2 tests come along with Idempotency-Key where lab 3 needs it; the short TTL after restart runs without api-shortttl by shortening the session in the database; test_drain adds a stuck request; - make validate uses .venv with openapi-spec-validator, PYTEST_ARGS, faults-evidence, down with the bench profile, the image is tagged by the compose project, start probes every 200 ms, cache evidence fails without a tombstone and checks the key expiry, kdf.txt shows the seed stub apart. The track 2 tooling of lab 2 (track.py, postgres-restore and the database argument of migrate) and its evidence scripts stay out. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01V1d3RLHNBBMA6UqBLLJv27
62 lines
2.6 KiB
Python
62 lines
2.6 KiB
Python
import re
|
||
from pathlib import Path
|
||
from typing import Any
|
||
|
||
import yaml
|
||
|
||
from messenger.shared.infrastructure.postgres import PING_TIMEOUT_SECONDS
|
||
|
||
ROOT = Path(__file__).resolve().parents[2]
|
||
DEFAULT = re.compile(r"\$\{\w+:?-([^}]*)\}")
|
||
UNITS = {"ms": 0.001, "s": 1.0, "": 1.0}
|
||
|
||
|
||
def seconds(value: object) -> float:
|
||
found = re.fullmatch(r"([\d.]+)(ms|s|)", str(value))
|
||
assert found is not None, value
|
||
return float(found[1]) * UNITS[found[2]]
|
||
|
||
|
||
def services() -> dict[str, Any]:
|
||
return yaml.safe_load(DEFAULT.sub(r"\1", (ROOT / "compose.yaml").read_text()))["services"]
|
||
|
||
|
||
def balancer() -> dict[str, float]:
|
||
text = (ROOT / "infra/haproxy/haproxy.cfg").read_text()
|
||
found = {
|
||
f"timeout {name}": seconds(value)
|
||
for name, value in re.findall(r"timeout ([\w-]+) (\S+)\n", text)
|
||
}
|
||
found["hard-stop-after"] = seconds(re.findall(r"hard-stop-after (\S+)", text)[0])
|
||
check = re.findall(r"default-server .*", text)[0]
|
||
for key in ("inter", "fastinter", "fall", "rise"):
|
||
found[key] = seconds(re.findall(rf"\b{key} (\S+)", check)[0])
|
||
return found
|
||
|
||
|
||
def test_timeouts_shrink_inwards_and_shutdown_fits_the_stop_budget() -> None:
|
||
lb, stand = balancer(), services()
|
||
api = {k: seconds(v) for k, v in stand["api"]["environment"].items() if k.endswith("SECONDS")}
|
||
hook = seconds(
|
||
re.findall(r"STOP_TIMEOUT:-(\d+)", (ROOT / "scripts/stop-one.sh").read_text())[0]
|
||
)
|
||
grace = seconds(stand["api"]["stop_grace_period"])
|
||
detection = lb["inter"] + (lb["fall"] - 1) * lb["fastinter"]
|
||
hung = detection + lb["fall"] * lb["timeout check"]
|
||
database = api["DB_ACQUIRE_TIMEOUT_SECONDS"] + api["DB_COMMAND_TIMEOUT_SECONDS"]
|
||
drain, shutdown = api["DRAIN_SECONDS"], api["SHUTDOWN_TIMEOUT_SECONDS"]
|
||
print(
|
||
f"обнаружение {detection} с (зависание {hung} с), окно {drain} с,"
|
||
f" дообработка {shutdown - drain - 1} с, остановка {shutdown} с, хук {hook} с,"
|
||
f" stop_grace_period {grace} с; LB server {lb['timeout server']} с >"
|
||
f" запрос {api['REQUEST_TIMEOUT_SECONDS']} с > БД {database} с;"
|
||
f" readiness {2 * PING_TIMEOUT_SECONDS} с < check {lb['timeout check']} с"
|
||
)
|
||
assert lb["timeout server"] > api["REQUEST_TIMEOUT_SECONDS"] > database
|
||
assert lb["timeout check"] > 2 * PING_TIMEOUT_SECONDS
|
||
assert drain > detection
|
||
assert shutdown - drain - 1 >= database
|
||
assert shutdown < hook < grace < 10
|
||
assert lb["hard-stop-after"] < seconds(stand["lb"]["stop_grace_period"])
|
||
assert (detection, hung) == (1.5, 3.5)
|