mirror of
https://github.com/element-hq/synapse.git
synced 2025-11-19 00:00:49 -05:00
07468a0f1c
This PR addresses a test failure for `tests.handlers.test_worker_lock.WorkerLockTestCase.test_lock_contention` which consistently times out on the RISC-V (specifically `riscv64`) architecture. The test simulates high lock contention and has a default timeout of 5 seconds, which seems sufficient for architectures like x86_64 but proves too short for current RISC-V hardware/environment performance characteristics, leading to spurious `tests.utils.TestTimeout` failures. This fix introduces architecture detection using `platform.machine()`. If a RISC-V architecture is detected: * The timeout for this specific test is increased (e.g., to 15 seconds ). The original, stricter timeout (5 seconds) and lock count (500) are maintained for all other architectures to avoid masking potential performance regressions elsewhere. This change has been tested locally on RISC-V, where the test now passes reliably, and on x86_64, where it continues to pass with the original constraints. --- ### Pull Request Checklist <!-- Please read https://element-hq.github.io/synapse/latest/development/contributing_guide.html before submitting your pull request --> * [X] Pull request is based on the develop branch *(Assuming you based it correctly)* * [X] Pull request includes a [changelog file](https://element-hq.github.io/synapse/latest/development/contributing_guide.html#changelog). *(See below)* * [X] [Code style](https://element-hq.github.io/synapse/latest/code_style.html) is correct (run the [linters](https://element-hq.github.io/synapse/latest/development/contributing_guide.html#run-the-linters)) *(Please run linters locally)*
125 lines
4.3 KiB
Python
125 lines
4.3 KiB
Python
#
|
|
# This file is licensed under the Affero General Public License (AGPL) version 3.
|
|
#
|
|
# Copyright 2023 The Matrix.org Foundation C.I.C.
|
|
# Copyright (C) 2023 New Vector, Ltd
|
|
#
|
|
# This program is free software: you can redistribute it and/or modify
|
|
# it under the terms of the GNU Affero General Public License as
|
|
# published by the Free Software Foundation, either version 3 of the
|
|
# License, or (at your option) any later version.
|
|
#
|
|
# See the GNU Affero General Public License for more details:
|
|
# <https://www.gnu.org/licenses/agpl-3.0.html>.
|
|
#
|
|
# Originally licensed under the Apache License, Version 2.0:
|
|
# <http://www.apache.org/licenses/LICENSE-2.0>.
|
|
#
|
|
# [This file includes modifications made by New Vector Limited]
|
|
#
|
|
#
|
|
|
|
import logging
|
|
import platform
|
|
|
|
from twisted.internet import defer
|
|
from twisted.test.proto_helpers import MemoryReactor
|
|
|
|
from synapse.server import HomeServer
|
|
from synapse.util import Clock
|
|
|
|
from tests import unittest
|
|
from tests.replication._base import BaseMultiWorkerStreamTestCase
|
|
from tests.utils import test_timeout
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class WorkerLockTestCase(unittest.HomeserverTestCase):
|
|
def prepare(
|
|
self, reactor: MemoryReactor, clock: Clock, homeserver: HomeServer
|
|
) -> None:
|
|
self.worker_lock_handler = self.hs.get_worker_locks_handler()
|
|
|
|
def test_wait_for_lock_locally(self) -> None:
|
|
"""Test waiting for a lock on a single worker"""
|
|
|
|
lock1 = self.worker_lock_handler.acquire_lock("name", "key")
|
|
self.get_success(lock1.__aenter__())
|
|
|
|
lock2 = self.worker_lock_handler.acquire_lock("name", "key")
|
|
d2 = defer.ensureDeferred(lock2.__aenter__())
|
|
self.assertNoResult(d2)
|
|
|
|
self.get_success(lock1.__aexit__(None, None, None))
|
|
|
|
self.get_success(d2)
|
|
self.get_success(lock2.__aexit__(None, None, None))
|
|
|
|
def test_lock_contention(self) -> None:
|
|
"""Test lock contention when a lot of locks wait on a single worker"""
|
|
nb_locks_to_test = 500
|
|
current_machine = platform.machine().lower()
|
|
if current_machine.startswith("riscv"):
|
|
# RISC-V specific settings
|
|
timeout_seconds = 15 # Increased timeout for RISC-V
|
|
# add a print or log statement here for visibility in CI logs
|
|
logger.info( # use logger.info
|
|
f"Detected RISC-V architecture ({current_machine}). "
|
|
f"Adjusting test_lock_contention: timeout={timeout_seconds}s"
|
|
)
|
|
else:
|
|
# Settings for other architectures
|
|
timeout_seconds = 5
|
|
# It takes around 0.5s on a 5+ years old laptop
|
|
with test_timeout(timeout_seconds): # Use the dynamically set timeout
|
|
d = self._take_locks(
|
|
nb_locks_to_test
|
|
) # Use the (potentially adjusted) number of locks
|
|
self.assertEqual(
|
|
self.get_success(d), nb_locks_to_test
|
|
) # Assert against the used number of locks
|
|
|
|
async def _take_locks(self, nb_locks: int) -> int:
|
|
locks = [
|
|
self.hs.get_worker_locks_handler().acquire_lock("test_lock", "")
|
|
for _ in range(nb_locks)
|
|
]
|
|
|
|
nb_locks_taken = 0
|
|
for lock in locks:
|
|
async with lock:
|
|
nb_locks_taken += 1
|
|
|
|
return nb_locks_taken
|
|
|
|
|
|
class WorkerLockWorkersTestCase(BaseMultiWorkerStreamTestCase):
|
|
def prepare(
|
|
self, reactor: MemoryReactor, clock: Clock, homeserver: HomeServer
|
|
) -> None:
|
|
self.main_worker_lock_handler = self.hs.get_worker_locks_handler()
|
|
|
|
def test_wait_for_lock_worker(self) -> None:
|
|
"""Test waiting for a lock on another worker"""
|
|
|
|
worker = self.make_worker_hs(
|
|
"synapse.app.generic_worker",
|
|
extra_config={
|
|
"redis": {"enabled": True},
|
|
},
|
|
)
|
|
worker_lock_handler = worker.get_worker_locks_handler()
|
|
|
|
lock1 = self.main_worker_lock_handler.acquire_lock("name", "key")
|
|
self.get_success(lock1.__aenter__())
|
|
|
|
lock2 = worker_lock_handler.acquire_lock("name", "key")
|
|
d2 = defer.ensureDeferred(lock2.__aenter__())
|
|
self.assertNoResult(d2)
|
|
|
|
self.get_success(lock1.__aexit__(None, None, None))
|
|
|
|
self.get_success(d2)
|
|
self.get_success(lock2.__aexit__(None, None, None))
|