view contrib/hgperf @ 43044:f9d35f01b8b3

setup: build extensions in parallel by default The build_ext distutils command in Python 3.5+ has a "parallel" option that controls whether to build extensions in parallel. It is disabled by default (None) and can be set to an integer value for number of cores or True to indicate use all available CPU cores. This commit changes our build_ext command override to set "parallel" to True unless a value has been provided by the caller. On my machine, this makes `python setup.py build_ext` 1-4s faster. It is worth noting that at this time, each individual source file constituting the extension is still built serially. For Mercurial, this means that we can't build faster than the slowest-to-build extension, which is the zstd extension by a long shot. This means that setup.py is still not very efficient at utilizing multiple cores. But we're better than before. Differential Revision: https://phab.mercurial-scm.org/D6923 # no-check-commit because of foo_bar naming
author Gregory Szorc <gregory.szorc@gmail.com>
date Mon, 30 Sep 2019 17:26:41 -0700
parents 163fa0aea71e
children 99e231afc29c
line wrap: on
line source

#!/usr/bin/env python
#
# hgperf - measure performance of Mercurial commands
#
# Copyright 2014 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''measure performance of Mercurial commands

Using ``hgperf`` instead of ``hg`` measures performance of the target
Mercurial command. For example, the execution below measures
performance of :hg:`heads --topo`::

    $ hgperf heads --topo

All command output via ``ui`` is suppressed, and just measurement
result is displayed: see also "perf" extension in "contrib".

Costs of processing before dispatching to the command function like
below are not measured::

    - parsing command line (e.g. option validity check)
    - reading configuration files in

But ``pre-`` and ``post-`` hook invocation for the target command is
measured, even though these are invoked before or after dispatching to
the command function, because these may be required to repeat
execution of the target command correctly.
'''

import os
import sys

libdir = '@LIBDIR@'

if libdir != '@' 'LIBDIR' '@':
    if not os.path.isabs(libdir):
        libdir = os.path.join(os.path.dirname(os.path.realpath(__file__)),
                              libdir)
        libdir = os.path.abspath(libdir)
    sys.path.insert(0, libdir)

# enable importing on demand to reduce startup time
try:
    from mercurial import demandimport; demandimport.enable()
except ImportError:
    import sys
    sys.stderr.write("abort: couldn't find mercurial libraries in [%s]\n" %
                     ' '.join(sys.path))
    sys.stderr.write("(check your install and PYTHONPATH)\n")
    sys.exit(-1)

from mercurial import (
    dispatch,
    util,
)

def timer(func, title=None):
    results = []
    begin = util.timer()
    count = 0
    while True:
        ostart = os.times()
        cstart = util.timer()
        r = func()
        cstop = util.timer()
        ostop = os.times()
        count += 1
        a, b = ostart, ostop
        results.append((cstop - cstart, b[0] - a[0], b[1]-a[1]))
        if cstop - begin > 3 and count >= 100:
            break
        if cstop - begin > 10 and count >= 3:
            break
    if title:
        sys.stderr.write("! %s\n" % title)
    if r:
        sys.stderr.write("! result: %s\n" % r)
    m = min(results)
    sys.stderr.write("! wall %f comb %f user %f sys %f (best of %d)\n"
                     % (m[0], m[1] + m[2], m[1], m[2], count))

orgruncommand = dispatch.runcommand

def runcommand(lui, repo, cmd, fullargs, ui, options, d, cmdpats, cmdoptions):
    ui.pushbuffer()
    lui.pushbuffer()
    timer(lambda : orgruncommand(lui, repo, cmd, fullargs, ui,
                                 options, d, cmdpats, cmdoptions))
    ui.popbuffer()
    lui.popbuffer()

dispatch.runcommand = runcommand

dispatch.run()