view contrib/hgperf @ 48178:f12a19d03d2c

fix: reduce number of tool executions

By grouping together (path, ctx) pairs according to the inputs they would
provide to fixer tools, we can deduplicate executions of fixer tools to
significantly reduce the amount of time spent running slow tools.

This change does not handle clean files in the working copy, which could still
be deduplicated against the files in the checked out commit. It's a little
harder to do that because the filerev is not available in the workingfilectx
(and it doesn't exist for added files).

Anecdotally, this change makes some real uses cases at Google 10x faster. I
think we were originally hesitant to do this because the benefits weren't
obvious, and implementing it efficiently is kind of tricky. If we simply
memoized the formatter execution function, we would be keeping tons of file
content in memory.

Also included is a regression test for a corner case that I broke with my first
attempt at optimizing this code.

Differential Revision: https://phab.mercurial-scm.org/D11280

#!/usr/bin/env python3
#
# hgperf - measure performance of Mercurial commands
#
# Copyright 2014 Olivia Mackall <[e-mail]>
#
# 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()