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)
```
# pullext.py - Simple extension to test pulling
#
# Copyright 2018 Gregory Szorc <gregory.szorc@gmail.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from mercurial.i18n import _
from mercurial import (
commands,
error,
extensions,
localrepo,
requirements,
)
def clonecommand(orig, ui, repo, *args, **kwargs):
if kwargs.get('include') or kwargs.get('exclude'):
kwargs['narrow'] = True
if kwargs.get('depth'):
try:
kwargs['depth'] = int(kwargs['depth'])
except ValueError:
raise error.Abort(_('--depth must be an integer'))
return orig(ui, repo, *args, **kwargs)
def featuresetup(ui, features):
features.add(requirements.NARROW_REQUIREMENT)
def extsetup(ui):
entry = extensions.wrapcommand(commands.table, b'clone', clonecommand)
hasinclude = any(x[1] == b'include' for x in entry[1])
hasdepth = any(x[1] == b'depth' for x in entry[1])
if not hasinclude:
entry[1].append(
(b'', b'include', [], _(b'pattern of file/directory to clone'))
)
entry[1].append(
(b'', b'exclude', [], _(b'pattern of file/directory to not clone'))
)
if not hasdepth:
entry[1].append(
(b'', b'depth', b'', _(b'ancestry depth of changesets to fetch'))
)
localrepo.featuresetupfuncs.add(featuresetup)