view contrib/revsetbenchmarks.py @ 21424:d13b4ecdb680

test: split test-largefile.t in multiple file The `test-largefiles.t` unified test is significantly longer (about 30%) than any other tests in the mercurial test suite. As a result, its is alway the last test my test runner is waiting for at the end of a run. In practice, this means that `test-largefile.t` is wasting half a minute of my life every times I'm running the mercurial test suites. This probably mean more a few cumulated day by now. I've finally decided to split it up in multiple smaller tests to bring it back in reasonable length. This changeset extracts independent test cases in two files. One dedicated to wire protocole testing, and another one dedicated to all other tests that could be independently extracted. No test case were haltered in the making of this changeset. Various timing available below. All timing have been done on a with 90 jobs on a 64 cores machine. Similar result are shown on firefly (20 jobs on 12 core). General timing of the whole run -------------------------------- We see a 25% real time improvement for no significant cpu time impact. Before split: real 2m1.149s user 58m4.662s sys 11m28.563s After split: real 1m31.977s user 57m45.993s sys 11m33.634s Last test to finish (using run-test.py --time) ---------------------------------------------- test-largefile.t is now finishing at the same time than other slow tests. Before split: Time Test 119.280 test-largefiles.t 93.995 test-mq.t 89.897 test-subrepo.t 86.920 test-glog.t 85.508 test-rename-merge2.t 83.594 test-revset.t 79.824 test-keyword.t 78.077 test-mq-header-date.t After split: Time Test 90.414 test-mq.t 88.594 test-largefiles.t 85.363 test-subrepo.t 81.059 test-glog.t 78.927 test-rename-merge2.t 78.021 test-revset.t 77.777 test-command-template.t Timing of largefile test themself ----------------------------------- Running only tests prefixed with "test-largefiles". No significant change in cumulated time. Before: Time Test 58.673 test-largefiles.t 2.931 test-largefiles-cache.t 0.583 test-largefiles-small-disk.t After: Time Test 31.754 test-largefiles.t 17.460 test-largefiles-misc.t 8.888 test-largefiles-wireproto.t 2.864 test-largefiles-cache.t 0.580 test-largefiles-small-disk.t
author Pierre-Yves David <pierre-yves.david@fb.com>
date Fri, 16 May 2014 13:18:57 -0700
parents 2d93b74335a2
children 651d7548a744
line wrap: on
line source

#!/usr/bin/env python

# Measure the performance of a list of revsets against multiple revisions
# defined by parameter. Checkout one by one and run perfrevset with every
# revset in the list to benchmark its performance.
#
# - First argument is a revset of mercurial own repo to runs against.
# - Second argument is the file from which the revset array will be taken
#   If second argument is omitted read it from standard input
#
# You should run this from the root of your mercurial repository.
#
# This script also does one run of the current version of mercurial installed
# to compare performance.

import sys
from subprocess import check_call, Popen, CalledProcessError, STDOUT, PIPE
# cannot use argparse, python 2.7 only
from optparse import OptionParser



def check_output(*args, **kwargs):
    kwargs.setdefault('stderr', PIPE)
    kwargs.setdefault('stdout', PIPE)
    proc = Popen(*args, **kwargs)
    output, error = proc.communicate()
    if proc.returncode != 0:
        raise CalledProcessError(proc.returncode, ' '.join(args[0]))
    return output

def update(rev):
    """update the repo to a revision"""
    try:
        check_call(['hg', 'update', '--quiet', '--check', str(rev)])
    except CalledProcessError, exc:
        print >> sys.stderr, 'update to revision %s failed, aborting' % rev
        sys.exit(exc.returncode)

def perf(revset):
    """run benchmark for this very revset"""
    try:
        output = check_output(['./hg',
                               '--config',
                               'extensions.perf=contrib/perf.py',
                               'perfrevset',
                               revset],
                               stderr=STDOUT)
        output = output.lstrip('!') # remove useless ! in this context
        return output.strip()
    except CalledProcessError, exc:
        print >> sys.stderr, 'abort: cannot run revset benchmark'
        sys.exit(exc.returncode)

def printrevision(rev):
    """print data about a revision"""
    sys.stdout.write("Revision: ")
    sys.stdout.flush()
    check_call(['hg', 'log', '--rev', str(rev), '--template',
               '{desc|firstline}\n'])

def getrevs(spec):
    """get the list of rev matched by a revset"""
    try:
        out = check_output(['hg', 'log', '--template={rev}\n', '--rev', spec])
    except CalledProcessError, exc:
        print >> sys.stderr, "abort, can't get revision from %s" % spec
        sys.exit(exc.returncode)
    return [r for r in out.split() if r]


parser = OptionParser(usage="usage: %prog [options] <revs>")
parser.add_option("-f", "--file",
                  help="read revset from FILE", metavar="FILE")

(options, args) = parser.parse_args()

if len(sys.argv) < 2:
    parser.print_help()
    sys.exit(255)


target_rev = args[0]

revsetsfile = sys.stdin
if options.file:
    revsetsfile = open(options.file)

revsets = [l.strip() for l in revsetsfile]

print "Revsets to benchmark"
print "----------------------------"

for idx, rset in enumerate(revsets):
    print "%i) %s" % (idx, rset)

print "----------------------------"
print


revs = getrevs(target_rev)

results = []
for r in revs:
    print "----------------------------"
    printrevision(r)
    print "----------------------------"
    update(r)
    res = []
    results.append(res)
    for idx, rset in enumerate(revsets):
        data = perf(rset)
        res.append(data)
        print "%i)" % idx, data
        sys.stdout.flush()
    print "----------------------------"


print """

Result by revset
================
"""

print 'Revision:', revs
for idx, rev in enumerate(revs):
    sys.stdout.write('%i) ' % idx)
    sys.stdout.flush()
    printrevision(rev)

print
print

for ridx, rset in enumerate(revsets):

    print "revset #%i: %s" % (ridx, rset)
    for idx, data in enumerate(results):
        print '%i) %s' % (idx, data[ridx])
    print