hgwebdir: avoid systematic full garbage collection
Forcing a systematic full garbage collection upon each request
can serioulsy harm performance. This is reported as
https://bz.mercurial-scm.org/show_bug.cgi?id=6075
With this change we're performing the full collection according
to a new setting, `experimental.web.full-garbage-collection-rate`.
The default value is 1, which doesn't change the behavior and will
allow us to test on real use cases. If the value is 0, no full garbage
collection occurs.
Regardless of the value of the setting, a partial garbage collection
still occurs upon each request (not attempting to collect objects from
the oldest generation). This should be enough to take care of
reference cycles that have been created by the last request
(assessment of this requires changing the setting, not to be 1).
In my experience chasing memory leaks in Mercurial servers,
the full collection never reclaimed any memory, but this is with
Python 3 and biased towards small repositories.
On the other hand, as explained in the Python developer docs [1],
frequent full collections are very harmful in terms of performance if
lots of objects survive the collection, and hence stay in the
oldest generation. Note that `gc.collect()` is indeed trying to
collect the oldest generation [2]. This happens usually in two cases:
- unwanted lingering objects (i.e., an actual memory leak that
the GC cannot do anything about). Sadly, we have lots of those
these days.
- desireable long-term objects, typically in caches (not inner caches
carried by repositories, which should be collected with them). This
is a subject of interest for the Heptapod project.
In short, the flat rate that this change still permits is
probably a bad idea in most cases, and the default value can
be tweaked later on (or even be set to 0) according to experiments
in the wild.
The test is inspired from test-hgwebdir-paths.py
[1] https://devguide.python.org/garbage_collector/#collecting-the-oldest-generation
[2] https://docs.python.org/3/library/gc.html#gc.collect
Differential Revision: https://phab.mercurial-scm.org/D11204
from __future__ import absolute_import
import copy
import errno
import tempfile
import types
import unittest
import silenttestrunner
from mercurial import (
encoding,
error,
lock,
vfs as vfsmod,
)
testlockname = b'testlock'
# work around http://bugs.python.org/issue1515
if types.MethodType not in copy._deepcopy_dispatch:
def _deepcopy_method(x, memo):
return type(x)(x.__func__, copy.deepcopy(x.__self__, memo), x.im_class)
copy._deepcopy_dispatch[types.MethodType] = _deepcopy_method
class lockwrapper(lock.lock):
def __init__(self, pidoffset, *args, **kwargs):
# lock.lock.__init__() calls lock(), so the pidoffset assignment needs
# to be earlier
self._pidoffset = pidoffset
super(lockwrapper, self).__init__(*args, **kwargs)
def _getpid(self):
return super(lockwrapper, self)._getpid() + self._pidoffset
class teststate(object):
def __init__(self, testcase, dir, pidoffset=0):
self._testcase = testcase
self._acquirecalled = False
self._releasecalled = False
self._postreleasecalled = False
self.vfs = vfsmod.vfs(dir, audit=False)
self._pidoffset = pidoffset
def makelock(self, *args, **kwargs):
l = lockwrapper(
self._pidoffset,
self.vfs,
testlockname,
releasefn=self.releasefn,
acquirefn=self.acquirefn,
*args,
**kwargs
)
l.postrelease.append(self.postreleasefn)
return l
def acquirefn(self):
self._acquirecalled = True
def releasefn(self):
self._releasecalled = True
def postreleasefn(self, success):
self._postreleasecalled = True
def assertacquirecalled(self, called):
self._testcase.assertEqual(
self._acquirecalled,
called,
'expected acquire to be %s but was actually %s'
% (
self._tocalled(called),
self._tocalled(self._acquirecalled),
),
)
def resetacquirefn(self):
self._acquirecalled = False
def assertreleasecalled(self, called):
self._testcase.assertEqual(
self._releasecalled,
called,
'expected release to be %s but was actually %s'
% (
self._tocalled(called),
self._tocalled(self._releasecalled),
),
)
def assertpostreleasecalled(self, called):
self._testcase.assertEqual(
self._postreleasecalled,
called,
'expected postrelease to be %s but was actually %s'
% (
self._tocalled(called),
self._tocalled(self._postreleasecalled),
),
)
def assertlockexists(self, exists):
actual = self.vfs.lexists(testlockname)
self._testcase.assertEqual(
actual,
exists,
'expected lock to %s but actually did %s'
% (
self._toexists(exists),
self._toexists(actual),
),
)
def _tocalled(self, called):
if called:
return 'called'
else:
return 'not called'
def _toexists(self, exists):
if exists:
return 'exist'
else:
return 'not exist'
class testlock(unittest.TestCase):
def testlock(self):
state = teststate(self, tempfile.mkdtemp(dir=encoding.getcwd()))
lock = state.makelock()
state.assertacquirecalled(True)
lock.release()
state.assertreleasecalled(True)
state.assertpostreleasecalled(True)
state.assertlockexists(False)
def testrecursivelock(self):
state = teststate(self, tempfile.mkdtemp(dir=encoding.getcwd()))
lock = state.makelock()
state.assertacquirecalled(True)
state.resetacquirefn()
lock.lock()
# recursive lock should not call acquirefn again
state.assertacquirecalled(False)
lock.release() # brings lock refcount down from 2 to 1
state.assertreleasecalled(False)
state.assertpostreleasecalled(False)
state.assertlockexists(True)
lock.release() # releases the lock
state.assertreleasecalled(True)
state.assertpostreleasecalled(True)
state.assertlockexists(False)
def testlockfork(self):
state = teststate(self, tempfile.mkdtemp(dir=encoding.getcwd()))
lock = state.makelock()
state.assertacquirecalled(True)
# fake a fork
forklock = copy.copy(lock)
forklock._pidoffset = 1
forklock.release()
state.assertreleasecalled(False)
state.assertpostreleasecalled(False)
state.assertlockexists(True)
# release the actual lock
lock.release()
state.assertreleasecalled(True)
state.assertpostreleasecalled(True)
state.assertlockexists(False)
def testfrequentlockunlock(self):
"""This tests whether lock acquisition fails as expected, even if
(1) lock can't be acquired (makelock fails by EEXIST), and
(2) locker info can't be read in (readlock fails by ENOENT) while
retrying 5 times.
"""
d = tempfile.mkdtemp(dir=encoding.getcwd())
state = teststate(self, d)
def emulatefrequentlock(*args):
raise OSError(errno.EEXIST, "File exists")
def emulatefrequentunlock(*args):
raise OSError(errno.ENOENT, "No such file or directory")
state.vfs.makelock = emulatefrequentlock
state.vfs.readlock = emulatefrequentunlock
try:
state.makelock(timeout=0)
self.fail("unexpected lock acquisition")
except error.LockHeld as why:
self.assertTrue(why.errno == errno.ETIMEDOUT)
self.assertTrue(why.locker == b"")
state.assertlockexists(False)
if __name__ == '__main__':
silenttestrunner.main(__name__)