update: add a Rust fast-path when updating from null (and clean)
This case is easy to detect and we have all we need to generate a valid
working copy and dirstate entirely in Rust, which speeds things up
considerably:
On my machine updating a repo of ~300k files goes from 10.00s down to 4.2s,
all while consuming 50% less system time, with all caches hot.
Something to note is that further improvements will probably happen
with the upcoming `InnerRevlog` series that does smarter
mmap hanlding, especially for filelogs.
Here are benchmark numbers on a machine with only 4 cores (and no SMT enabled)
```
### data-env-vars.name = heptapod-public-2024-03-25-ds2-pnm
# benchmark.name = hg.command.update
# bin-env-vars.hg.py-re2-module = default
# bin-env-vars.hg.changeset.node = <this change>
# benchmark.variants.atomic-update = no
# benchmark.variants.scenario = null-to-tip
# benchmark.variants.worker = default
default: 5.328762 ~~~~~
rust: 1.308654 (-75.44%, -4.02)
### data-env-vars.name = mercurial-devel-2024-03-22-ds2-pnm
# benchmark.name = hg.command.update
# bin-env-vars.hg.py-re2-module = default
# bin-env-vars.hg.changeset.node = <this change>
# benchmark.variants.atomic-update = no
# benchmark.variants.scenario = null-to-tip
# benchmark.variants.worker = default
default: 1.693271 ~~~~~
rust: 1.151053 (-32.02%, -0.54)
### data-env-vars.name = mozilla-unified-2024-03-22-ds2-pnm
# benchmark.name = hg.command.update
# bin-env-vars.hg.py-re2-module = default
# bin-env-vars.hg.changeset.node = <this change>
# benchmark.variants.atomic-update = no
# benchmark.variants.scenario = null-to-tip
# benchmark.variants.worker = default
default: 38.901613 ~~~~~
rust: 11.637880 (-70.08%, -27.26)
### data-env-vars.name = netbsd-xsrc-public-2024-09-19-ds2-pnm
# benchmark.name = hg.command.update
# bin-env-vars.hg.py-re2-module = default
# bin-env-vars.hg.changeset.node = <this change>
# benchmark.variants.atomic-update = no
# benchmark.variants.scenario = null-to-tip
# benchmark.variants.worker = default
default: 4.793727 ~~~~~
rust: 1.505905 (-68.59%, -3.29)
```
# unit tests for mercuril.util utilities
import contextlib
import io
import itertools
import unittest
from mercurial import pycompat, util, utils
@contextlib.contextmanager
def mocktimer(incr=0.1, *additional_targets):
"""Replaces util.timer and additional_targets with a mock
The timer starts at 0. On each call the time incremented by the value
of incr. If incr is an iterable, then the time is incremented by the
next value from that iterable, looping in a cycle when reaching the end.
additional_targets must be a sequence of (object, attribute_name) tuples;
the mock is set with setattr(object, attribute_name, mock).
"""
time = [0]
try:
incr = itertools.cycle(incr)
except TypeError:
incr = itertools.repeat(incr)
def timer():
time[0] += next(incr)
return time[0]
# record original values
orig = util.timer
additional_origs = [(o, a, getattr(o, a)) for o, a in additional_targets]
# mock out targets
util.timer = timer
for obj, attr in additional_targets:
setattr(obj, attr, timer)
try:
yield
finally:
# restore originals
util.timer = orig
for args in additional_origs:
setattr(*args)
# attr.s default factory for util.timedstats.start binds the timer we
# need to mock out.
_start_default = (util.timedcmstats.__attrs_attrs__.start.default, 'factory')
@contextlib.contextmanager
def capturestderr():
"""Replace utils.procutil.stderr with an io.BytesIO instance
The instance is made available as the return value of __enter__.
This contextmanager is reentrant.
"""
orig = utils.procutil.stderr
utils.procutil.stderr = io.BytesIO()
try:
yield utils.procutil.stderr
finally:
utils.procutil.stderr = orig
class timedtests(unittest.TestCase):
def testtimedcmstatsstr(self):
stats = util.timedcmstats()
self.assertEqual(str(stats), '<unknown>')
self.assertEqual(bytes(stats), b'<unknown>')
stats.elapsed = 12.34
self.assertEqual(str(stats), pycompat.sysstr(util.timecount(12.34)))
self.assertEqual(bytes(stats), util.timecount(12.34))
def testtimedcmcleanexit(self):
# timestamps 1, 4, elapsed time of 4 - 1 = 3
with mocktimer([1, 3], _start_default):
with util.timedcm('pass') as stats:
# actual context doesn't matter
pass
self.assertEqual(stats.start, 1)
self.assertEqual(stats.elapsed, 3)
self.assertEqual(stats.level, 1)
def testtimedcmnested(self):
# timestamps 1, 3, 6, 10, elapsed times of 6 - 3 = 3 and 10 - 1 = 9
with mocktimer([1, 2, 3, 4], _start_default):
with util.timedcm('outer') as outer_stats:
with util.timedcm('inner') as inner_stats:
# actual context doesn't matter
pass
self.assertEqual(outer_stats.start, 1)
self.assertEqual(outer_stats.elapsed, 9)
self.assertEqual(outer_stats.level, 1)
self.assertEqual(inner_stats.start, 3)
self.assertEqual(inner_stats.elapsed, 3)
self.assertEqual(inner_stats.level, 2)
def testtimedcmexception(self):
# timestamps 1, 4, elapsed time of 4 - 1 = 3
with mocktimer([1, 3], _start_default):
try:
with util.timedcm('exceptional') as stats:
raise ValueError()
except ValueError:
pass
self.assertEqual(stats.start, 1)
self.assertEqual(stats.elapsed, 3)
self.assertEqual(stats.level, 1)
def testtimeddecorator(self):
@util.timed
def testfunc(callcount=1):
callcount -= 1
if callcount:
testfunc(callcount)
# timestamps 1, 2, 3, 4, elapsed time of 3 - 2 = 1 and 4 - 1 = 3
with mocktimer(1, _start_default):
with capturestderr() as out:
testfunc(2)
self.assertEqual(
out.getvalue(),
(b' testfunc: 1.000 s\n' b' testfunc: 3.000 s\n'),
)
if __name__ == '__main__':
import silenttestrunner
silenttestrunner.main(__name__)