perf: clear vfs audit_cache before each run
When generating a stream clone, we spend a large amount of time auditing path.
Before this changes, the first run was warming the vfs cache for the other
runs, leading to a large runtime difference and a "faulty" reported timing for
the operation.
We now clear this important cache between run to get a more realistic timing.
Below are some example of median time change when clearing these cases. The
maximum time for a run did not changed significantly.
### data-env-vars.name = mozilla-central-2018-08-01-zstd-sparse-revlog
# benchmark.name = hg.perf.exchange.stream.generate
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.version = latest
no-clearing: 17.289905
cache-clearing: 21.587965 (+24.86%, +4.30)
## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog
no-clearing: 32.670748
cache-clearing: 40.467095 (+23.86%, +7.80)
## data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog
no-clearing: 37.838858
cache-clearing: 46.072749 (+21.76%, +8.23)
## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog
no-clearing: 32.969395
cache-clearing: 39.646209 (+20.25%, +6.68)
In addition, this significantly reduce the timing difference between the
performance command, from the perf extensions and a `real `hg bundle` call
producing a stream bundle. Some significant differences remain especially on
the "mozilla-try" repositories, but they are now smaller.
Note that some of that difference will actually not be
attributable to the stream generation (like maybe phases or branch map
computation).
Below are some benchmarks done on a currently draft changeset fixing some
unrelated slowness in `hg bundle` (34a78972af409d1ff37c29e60f6ca811ad1a457d)
### data-env-vars.name = mozilla-central-2018-08-01-zstd-sparse-revlog
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
hg.perf.exchange.stream.generate: 21.587965
hg.command.bundle: 24.301799 (+12.57%, +2.71)
## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog
hg.perf.exchange.stream.generate: 40.467095
hg.command.bundle: 44.831317 (+10.78%, +4.36)
## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog
hg.perf.exchange.stream.generate: 39.646209
hg.command.bundle: 45.395258 (+14.50%, +5.75)
## data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog
hg.perf.exchange.stream.generate: 46.072749
hg.command.bundle: 55.882608 (+21.29%, +9.81)
## data-env-vars.name = mozilla-try-2023-03-22-zlib-general-delta
hg.perf.exchange.stream.generate: 334.716708
hg.command.bundle: 377.856767 (+12.89%, +43.14)
## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
hg.perf.exchange.stream.generate: 302.972301
hg.command.bundle: 326.098755 (+7.63%, +23.13)
import sys
import unittest
from mercurial.node import wdirrev
from mercurial.testing import revlog as revlogtesting
try:
from mercurial import rustext
rustext.__name__ # trigger immediate actual import
except ImportError:
rustext = None
else:
# this would fail already without appropriate ancestor.__package__
from mercurial.rustext.ancestor import (
AncestorsIterator,
LazyAncestors,
MissingAncestors,
)
from mercurial.rustext import dagop
try:
from mercurial.cext import parsers as cparsers
except ImportError:
cparsers = None
@unittest.skipIf(
rustext is None,
'The Rust version of the "ancestor" module is not available. It is needed'
' for this test.',
)
@unittest.skipIf(
rustext is None,
'The Rust or C version of the "parsers" module, which the "ancestor" module'
' relies on, is not available.',
)
class rustancestorstest(revlogtesting.RustRevlogBasedTestBase):
"""Test the correctness of binding to Rust code.
This test is merely for the binding to Rust itself: extraction of
Python variable, giving back the results etc.
It is not meant to test the algorithmic correctness of the operations
on ancestors it provides. Hence the very simple embedded index data is
good enough.
Algorithmic correctness is asserted by the Rust unit tests.
"""
def testiteratorrevlist(self):
idx = self.parserustindex()
# checking test assumption about the index binary data:
self.assertEqual(
{i: (r[5], r[6]) for i, r in enumerate(idx)},
{0: (-1, -1), 1: (0, -1), 2: (1, -1), 3: (2, -1)},
)
ait = AncestorsIterator(idx, [3], 0, True)
self.assertEqual([r for r in ait], [3, 2, 1, 0])
ait = AncestorsIterator(idx, [3], 0, False)
self.assertEqual([r for r in ait], [2, 1, 0])
def testlazyancestors(self):
idx = self.parserustindex()
start_count = sys.getrefcount(idx) # should be 2 (see Python doc)
self.assertEqual(
{i: (r[5], r[6]) for i, r in enumerate(idx)},
{0: (-1, -1), 1: (0, -1), 2: (1, -1), 3: (2, -1)},
)
lazy = LazyAncestors(idx, [3], 0, True)
# we have two more references to the index:
# - in its inner iterator for __contains__ and __bool__
# - in the LazyAncestors instance itself (to spawn new iterators)
self.assertEqual(sys.getrefcount(idx), start_count + 2)
self.assertTrue(2 in lazy)
self.assertTrue(bool(lazy))
self.assertEqual(list(lazy), [3, 2, 1, 0])
# a second time to validate that we spawn new iterators
self.assertEqual(list(lazy), [3, 2, 1, 0])
# now let's watch the refcounts closer
ait = iter(lazy)
self.assertEqual(sys.getrefcount(idx), start_count + 3)
del ait
self.assertEqual(sys.getrefcount(idx), start_count + 2)
del lazy
self.assertEqual(sys.getrefcount(idx), start_count)
# let's check bool for an empty one
self.assertFalse(LazyAncestors(idx, [0], 0, False))
def testmissingancestors(self):
idx = self.parserustindex()
missanc = MissingAncestors(idx, [1])
self.assertTrue(missanc.hasbases())
self.assertEqual(missanc.missingancestors([3]), [2, 3])
missanc.addbases({2})
self.assertEqual(missanc.bases(), {1, 2})
self.assertEqual(missanc.missingancestors([3]), [3])
self.assertEqual(missanc.basesheads(), {2})
def testmissingancestorsremove(self):
idx = self.parserustindex()
missanc = MissingAncestors(idx, [1])
revs = {0, 1, 2, 3}
missanc.removeancestorsfrom(revs)
self.assertEqual(revs, {2, 3})
def testrefcount(self):
idx = self.parserustindex()
start_count = sys.getrefcount(idx)
# refcount increases upon iterator init...
ait = AncestorsIterator(idx, [3], 0, True)
self.assertEqual(sys.getrefcount(idx), start_count + 1)
self.assertEqual(next(ait), 3)
# and decreases once the iterator is removed
del ait
self.assertEqual(sys.getrefcount(idx), start_count)
# and removing ref to the index after iterator init is no issue
ait = AncestorsIterator(idx, [3], 0, True)
del idx
self.assertEqual(list(ait), [3, 2, 1, 0])
# the index is not tracked by the GC, hence there is nothing more
# we can assert to check that it is properly deleted once its refcount
# drops to 0
def testgrapherror(self):
data = (
revlogtesting.data_non_inlined[: 64 + 27]
+ b'\xf2'
+ revlogtesting.data_non_inlined[64 + 28 :]
)
idx = self.parserustindex(data=data)
with self.assertRaises(rustext.GraphError) as arc:
AncestorsIterator(idx, [1], -1, False)
exc = arc.exception
self.assertIsInstance(exc, ValueError)
# rust-cpython issues appropriate str instances for Python 2 and 3
self.assertEqual(exc.args, ('ParentOutOfRange', 1))
def testwdirunsupported(self):
# trying to access ancestors of the working directory raises
idx = self.parserustindex()
with self.assertRaises(rustext.GraphError) as arc:
list(AncestorsIterator(idx, [wdirrev], -1, False))
exc = arc.exception
self.assertIsInstance(exc, ValueError)
# rust-cpython issues appropriate str instances for Python 2 and 3
self.assertEqual(exc.args, ('InvalidRevision', wdirrev))
def testheadrevs(self):
idx = self.parserustindex()
self.assertEqual(dagop.headrevs(idx, [1, 2, 3]), {3})
if __name__ == '__main__':
import silenttestrunner
silenttestrunner.main(__name__)