##// END OF EJS Templates
pathcopies: give up any optimization based on `introrev`...
pathcopies: give up any optimization based on `introrev` Between 8a0136f69027 and d98fb3f42f33, we sped up the search for the introduction revision during path copies. However, further checking show that finding the introduction revision is still expensive and that we are better off without it. So we simply drop it and only rely on the linkrev optimisation. I ran `perfpathcopies` on 6989 pair of revision in the pypy repository (`hg perfhelper-pathcopies`. The result is massively in favor of dropping this condition. The result of the copy tracing are unchanged. Attempt to use a smaller changes preserving linkrev usage were unsuccessful, it can return wrong result. The following changesets broke test-mv-cp-st-diff.t - if not f.isintroducedafter(limit): + if limit >= 0 and f.linkrev() < limit: return None Here are various numbers (before this changeset/after this changesets) source destination before after saved-time ratio worth cases e66f24650daf 695dfb0f493b 1.062843 1.246369 -0.183526 1.172675 c979853a3b6a 8d60fe293e79 1.036985 1.196414 -0.159429 1.153743 22349fa2fc33 fbb1c9fd86c0 0.879926 1.038682 -0.158756 1.180420 682b98f3e672 a4878080a536 0.909952 1.063801 -0.153849 1.169074 5adabc9b9848 920958a93997 0.993622 1.147452 -0.153830 1.154817 worse 1% dbfbfcf077e9 aea8f2fd3593 1.016595 1.082999 -0.066404 1.065320 worse 5% c95f1ced15f2 7d29d5e39734 0.453694 0.471156 -0.017462 1.038488 worse 10% 3e144ed1d5b7 2aef0e942480 0.035140 0.037535 -0.002395 1.068156 worse 25% 321fc60db035 801748ba582a 0.009267 0.009325 -0.000058 1.006259 median 2088ce763fc2 e6991321d78b 0.000665 0.000651 0.000014 0.978947 best 25% 915631a97de6 385b31354be6 0.040743 0.040363 0.000380 0.990673 best 10% ad495c36a765 19c10384d3e7 0.431658 0.411490 0.020168 0.953278 best 5% d13ae7d283ae 813c99f810ac 1.141404 1.075346 0.066058 0.942126 best 1% 81593cb4a496 99ae11866969 1.833297 0.063823 1.769474 0.034813 best cases c3b14617fbd7 743a0fcaa4eb 1101.811740 2.735970 1099.075770 0.002483 c3b14617fbd7 9ba6ab77fd29 1116.753953 2.800729 1113.953224 0.002508 058b99d6e81f 57e249b7a3ea 1246.128485 3.042762 1243.085723 0.002442 9a8c361aab49 0354a250d371 1253.111894 3.085796 1250.026098 0.002463 442dbbc53c68 3ec1002a818c 1261.786294 3.138607 1258.647687 0.002487 As one can see, the average case is not really impacted. However, the worth case we get after this changeset are much better than the one we had before it. We have 30 pairs where improvements are above 10 minutes. This reflect in the combined time for all pairs before: 26256s after: 1300s (-95%) If we remove these pathological 30 cases, we still see a significant improvements: before: 1631s after: 1245s (-24%)

File last commit:

r43355:eef9a2d6 default
r43469:c16fe77e default
Show More
churn.py
257 lines | 7.4 KiB | text/x-python | PythonLexer
# churn.py - create a graph of revisions count grouped by template
#
# Copyright 2006 Josef "Jeff" Sipek <jeffpc@josefsipek.net>
# Copyright 2008 Alexander Solovyov <piranha@piranha.org.ua>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
'''command to display statistics about repository history'''
from __future__ import absolute_import, division
import datetime
import os
import time
from mercurial.i18n import _
from mercurial.pycompat import open
from mercurial import (
cmdutil,
encoding,
logcmdutil,
patch,
pycompat,
registrar,
scmutil,
)
from mercurial.utils import dateutil
cmdtable = {}
command = registrar.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = b'ships-with-hg-core'
def changedlines(ui, repo, ctx1, ctx2, fns):
added, removed = 0, 0
fmatch = scmutil.matchfiles(repo, fns)
diff = b''.join(patch.diff(repo, ctx1.node(), ctx2.node(), fmatch))
for l in diff.split(b'\n'):
if l.startswith(b"+") and not l.startswith(b"+++ "):
added += 1
elif l.startswith(b"-") and not l.startswith(b"--- "):
removed += 1
return (added, removed)
def countrate(ui, repo, amap, *pats, **opts):
"""Calculate stats"""
opts = pycompat.byteskwargs(opts)
if opts.get(b'dateformat'):
def getkey(ctx):
t, tz = ctx.date()
date = datetime.datetime(*time.gmtime(float(t) - tz)[:6])
return encoding.strtolocal(
date.strftime(encoding.strfromlocal(opts[b'dateformat']))
)
else:
tmpl = opts.get(b'oldtemplate') or opts.get(b'template')
tmpl = logcmdutil.maketemplater(ui, repo, tmpl)
def getkey(ctx):
ui.pushbuffer()
tmpl.show(ctx)
return ui.popbuffer()
progress = ui.makeprogress(
_(b'analyzing'), unit=_(b'revisions'), total=len(repo)
)
rate = {}
df = False
if opts.get(b'date'):
df = dateutil.matchdate(opts[b'date'])
m = scmutil.match(repo[None], pats, opts)
def prep(ctx, fns):
rev = ctx.rev()
if df and not df(ctx.date()[0]): # doesn't match date format
return
key = getkey(ctx).strip()
key = amap.get(key, key) # alias remap
if opts.get(b'changesets'):
rate[key] = (rate.get(key, (0,))[0] + 1, 0)
else:
parents = ctx.parents()
if len(parents) > 1:
ui.note(_(b'revision %d is a merge, ignoring...\n') % (rev,))
return
ctx1 = parents[0]
lines = changedlines(ui, repo, ctx1, ctx, fns)
rate[key] = [r + l for r, l in zip(rate.get(key, (0, 0)), lines)]
progress.increment()
for ctx in cmdutil.walkchangerevs(repo, m, opts, prep):
continue
progress.complete()
return rate
@command(
b'churn',
[
(
b'r',
b'rev',
[],
_(b'count rate for the specified revision or revset'),
_(b'REV'),
),
(
b'd',
b'date',
b'',
_(b'count rate for revisions matching date spec'),
_(b'DATE'),
),
(
b't',
b'oldtemplate',
b'',
_(b'template to group changesets (DEPRECATED)'),
_(b'TEMPLATE'),
),
(
b'T',
b'template',
b'{author|email}',
_(b'template to group changesets'),
_(b'TEMPLATE'),
),
(
b'f',
b'dateformat',
b'',
_(b'strftime-compatible format for grouping by date'),
_(b'FORMAT'),
),
(b'c', b'changesets', False, _(b'count rate by number of changesets')),
(b's', b'sort', False, _(b'sort by key (default: sort by count)')),
(b'', b'diffstat', False, _(b'display added/removed lines separately')),
(b'', b'aliases', b'', _(b'file with email aliases'), _(b'FILE')),
]
+ cmdutil.walkopts,
_(b"hg churn [-d DATE] [-r REV] [--aliases FILE] [FILE]"),
helpcategory=command.CATEGORY_MAINTENANCE,
inferrepo=True,
)
def churn(ui, repo, *pats, **opts):
'''histogram of changes to the repository
This command will display a histogram representing the number
of changed lines or revisions, grouped according to the given
template. The default template will group changes by author.
The --dateformat option may be used to group the results by
date instead.
Statistics are based on the number of changed lines, or
alternatively the number of matching revisions if the
--changesets option is specified.
Examples::
# display count of changed lines for every committer
hg churn -T "{author|email}"
# display daily activity graph
hg churn -f "%H" -s -c
# display activity of developers by month
hg churn -f "%Y-%m" -s -c
# display count of lines changed in every year
hg churn -f "%Y" -s
It is possible to map alternate email addresses to a main address
by providing a file using the following format::
<alias email> = <actual email>
Such a file may be specified with the --aliases option, otherwise
a .hgchurn file will be looked for in the working directory root.
Aliases will be split from the rightmost "=".
'''
def pad(s, l):
return s + b" " * (l - encoding.colwidth(s))
amap = {}
aliases = opts.get(r'aliases')
if not aliases and os.path.exists(repo.wjoin(b'.hgchurn')):
aliases = repo.wjoin(b'.hgchurn')
if aliases:
for l in open(aliases, b"rb"):
try:
alias, actual = l.rsplit(b'=' in l and b'=' or None, 1)
amap[alias.strip()] = actual.strip()
except ValueError:
l = l.strip()
if l:
ui.warn(_(b"skipping malformed alias: %s\n") % l)
continue
rate = list(countrate(ui, repo, amap, *pats, **opts).items())
if not rate:
return
if opts.get(r'sort'):
rate.sort()
else:
rate.sort(key=lambda x: (-sum(x[1]), x))
# Be careful not to have a zero maxcount (issue833)
maxcount = float(max(sum(v) for k, v in rate)) or 1.0
maxname = max(len(k) for k, v in rate)
ttywidth = ui.termwidth()
ui.debug(b"assuming %i character terminal\n" % ttywidth)
width = ttywidth - maxname - 2 - 2 - 2
if opts.get(r'diffstat'):
width -= 15
def format(name, diffstat):
added, removed = diffstat
return b"%s %15s %s%s\n" % (
pad(name, maxname),
b'+%d/-%d' % (added, removed),
ui.label(b'+' * charnum(added), b'diffstat.inserted'),
ui.label(b'-' * charnum(removed), b'diffstat.deleted'),
)
else:
width -= 6
def format(name, count):
return b"%s %6d %s\n" % (
pad(name, maxname),
sum(count),
b'*' * charnum(sum(count)),
)
def charnum(count):
return int(count * width // maxcount)
for name, count in rate:
ui.write(format(name, count))