annotate contrib/revsetbenchmarks.py @ 23787:678f53865c68

revset: use localrepo revbranchcache for branch name filtering

Branch name filtering in revsets was expensive. For every rev it created a
changectx and called .branch() which retrieved the branch name from the
changelog.

Instead, use the revbranchcache.

The revbranchcache is used read-only. The revset implementation with generators
and callbacks makes it hard to figure out when we are done using/updating the
cache and could write it back. It would also be 'tricky' to lock the repo for
writing from within a revset execution. Finally, the branchmap update will
usually make sure that the cache is updated before any revset can be run.
The revbranchcache is used without any locking but is short-lived and used in a
tight loop where we can assume that the changelog doesn't change ... or where
it not is relevant to us if it does.

perfrevset 'branch(mobile)' on mozilla-central.
Before:
! wall 10.989637 comb 10.970000 user 10.940000 sys 0.030000 (best of 3)
After, no cache:
! wall 7.368656 comb 7.370000 user 7.360000 sys 0.010000 (best of 3)
After, with cache:
! wall 0.528098 comb 0.530000 user 0.530000 sys 0.000000 (best of 18)

The performance improvement even without cache come from being based on
branchinfo on the changelog instead of using ctx.branch().

Some tests are added to verify that the revbranchcache works and keep an eye on
when the cache files actually are updated.

#!/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
import os
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, target=None):
    """run benchmark for this very revset"""
    try:
        cmd = ['./hg',
               '--config',
               'extensions.perf='
               + os.path.join(contribdir, 'perf.py'),
               'perfrevset',
               revset]
        if target is not None:
            cmd.append('-R')
            cmd.append(target)
        output = check_output(cmd, 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 (stdin if omitted)",
                  metavar="FILE")
parser.add_option("-R", "--repo",
                  help="run benchmark on REPO", metavar="REPO")

(options, args) = parser.parse_args()

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

# the directory where both this script and the perf.py extension live.
contribdir = os.path.dirname(__file__)

target_rev = args[0]

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

revsets = [l.strip() for l in revsetsfile if not l.startswith('#')]

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, target=options.repo)
        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