i18n: cache the result of every gettext call
In looking at profiler output for 'hg log' on mozilla-central, I
noticed we spent a _huge_ amount of time in gettext relative to what
it's doing. Caching provides a roughly 15% performance improvement
even on repositories as small as hg.
== hg repo on linux ==
Before:
% cumulative self
time seconds seconds name
5.05 0.19 0.19 i18n.py:62:gettext
4.84 0.18 0.18 revlog.py:88:decompress
2.95 0.17 0.11 changelog.py:201:node
2.32 0.09 0.09 ui.py:577:write
2.11 0.08 0.08 i18n.py:72:gettext
2.11 0.08 0.08 obsolete.py:196:_fm0readmarkers
1.89 0.07 0.07 obsolete.py:569:_load
1.68 0.63 0.06 localrepo.py:29:__get__
real 0m4.026s
user 0m3.993s
sys 0m0.034s
After:
% cumulative self
time seconds seconds name
8.05 0.26 0.26 revlog.py:88:decompress
2.68 0.22 0.09 color.py:395:write
2.20 0.07 0.07 obsolete.py:196:_fm0readmarkers
1.95 0.06 0.06 obsolete.py:174:_fm0readmarkers
1.95 0.06 0.06 ui.py:577:write
1.95 0.06 0.06 util.py:1228:datestr
1.71 0.06 0.06 utf_8.py:16:decode
1.71 0.06 0.06 revlog.py:273:__len__
real 0m3.519s
user 0m3.447s
sys 0m0.073s
== mozilla-central repo on linux ==
Before:
% cumulative self
time seconds seconds name
7.72 2.35 2.35 revlog.py:88:decompress
4.46 1.36 1.36 i18n.py:62:gettext
2.22 0.67 0.67 i18n.py:72:gettext
2.19 1.14 0.67 changelog.py:201:node
2.16 0.66 0.66 ui.py:577:write
1.96 0.60 0.60 utf_8.py:16:decode
1.93 1.97 0.59 color.py:395:write
1.85 0.81 0.56 changelog.py:136:tip
real 0m30.822s
user 0m30.660s
sys 0m0.149s
After:
% cumulative self
time seconds seconds name
9.82 2.49 2.49 revlog.py:88:decompress
2.67 1.31 0.68 localrepo.py:29:__get__
2.57 0.65 0.65 utf_8.py:16:decode
2.48 1.01 0.63 changelog.py:201:node
2.10 0.82 0.53 changelog.py:136:tip
2.01 0.51 0.51 ui.py:577:write
1.91 0.49 0.49 util.py:1232:datestr
1.85 1.65 0.47 color.py:395:write
real 0m25.619s
user 0m25.446s
sys 0m0.166s
== cpython repo on os x =
Before:
% cumulative self
time seconds seconds name
5.05 1.35 1.35 cmdutil.py:982:_show
4.59 1.22 1.22 revlog.py:274:__len__
3.98 1.06 1.06 i18n.py:62:gettext
3.91 1.04 1.04 revlog.py:1016:revision
3.68 0.98 0.98 revlog.py:337:parents
3.45 0.92 0.92 revlog.py:88:decompress
2.91 0.78 0.78 revlog.py:309:rev
2.62 0.70 0.70 revlog.py:1033:revision
real 0m30.414s
user 0m28.145s
sys 0m0.541s
After:
% cumulative self
time seconds seconds name
7.98 1.66 1.66 cmdutil.py:982:_show
6.83 1.42 1.42 changelog.py:46:decodeextra
5.18 1.08 1.08 revlog.py:274:__len__
3.94 0.82 0.82 revlog.py:1016:revision
3.41 0.71 0.71 revlog.py:309:rev
3.32 0.69 0.69 revlog.py:88:decompress
2.99 0.63 0.62 revlog.py:1033:revision
2.69 0.56 0.56 revlog.py:341:start
real 0m22.811s
user 0m21.883s
sys 0m0.397s
# Mercurial extension to provide 'hg relink' command
#
# Copyright (C) 2007 Brendan Cully <brendan@kublai.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""recreates hardlinks between repository clones"""
from mercurial import cmdutil, hg, util
from mercurial.i18n import _
import os, stat
cmdtable = {}
command = cmdutil.command(cmdtable)
testedwith = 'internal'
@command('relink', [], _('[ORIGIN]'))
def relink(ui, repo, origin=None, **opts):
"""recreate hardlinks between two repositories
When repositories are cloned locally, their data files will be
hardlinked so that they only use the space of a single repository.
Unfortunately, subsequent pulls into either repository will break
hardlinks for any files touched by the new changesets, even if
both repositories end up pulling the same changes.
Similarly, passing --rev to "hg clone" will fail to use any
hardlinks, falling back to a complete copy of the source
repository.
This command lets you recreate those hardlinks and reclaim that
wasted space.
This repository will be relinked to share space with ORIGIN, which
must be on the same local disk. If ORIGIN is omitted, looks for
"default-relink", then "default", in [paths].
Do not attempt any read operations on this repository while the
command is running. (Both repositories will be locked against
writes.)
"""
if (not util.safehasattr(util, 'samefile') or
not util.safehasattr(util, 'samedevice')):
raise util.Abort(_('hardlinks are not supported on this system'))
src = hg.repository(repo.baseui, ui.expandpath(origin or 'default-relink',
origin or 'default'))
ui.status(_('relinking %s to %s\n') % (src.store.path, repo.store.path))
if repo.root == src.root:
ui.status(_('there is nothing to relink\n'))
return
if not util.samedevice(src.store.path, repo.store.path):
# No point in continuing
raise util.Abort(_('source and destination are on different devices'))
locallock = repo.lock()
try:
remotelock = src.lock()
try:
candidates = sorted(collect(src, ui))
targets = prune(candidates, src.store.path, repo.store.path, ui)
do_relink(src.store.path, repo.store.path, targets, ui)
finally:
remotelock.release()
finally:
locallock.release()
def collect(src, ui):
seplen = len(os.path.sep)
candidates = []
live = len(src['tip'].manifest())
# Your average repository has some files which were deleted before
# the tip revision. We account for that by assuming that there are
# 3 tracked files for every 2 live files as of the tip version of
# the repository.
#
# mozilla-central as of 2010-06-10 had a ratio of just over 7:5.
total = live * 3 // 2
src = src.store.path
pos = 0
ui.status(_("tip has %d files, estimated total number of files: %s\n")
% (live, total))
for dirpath, dirnames, filenames in os.walk(src):
dirnames.sort()
relpath = dirpath[len(src) + seplen:]
for filename in sorted(filenames):
if filename[-2:] not in ('.d', '.i'):
continue
st = os.stat(os.path.join(dirpath, filename))
if not stat.S_ISREG(st.st_mode):
continue
pos += 1
candidates.append((os.path.join(relpath, filename), st))
ui.progress(_('collecting'), pos, filename, _('files'), total)
ui.progress(_('collecting'), None)
ui.status(_('collected %d candidate storage files\n') % len(candidates))
return candidates
def prune(candidates, src, dst, ui):
def linkfilter(src, dst, st):
try:
ts = os.stat(dst)
except OSError:
# Destination doesn't have this file?
return False
if util.samefile(src, dst):
return False
if not util.samedevice(src, dst):
# No point in continuing
raise util.Abort(
_('source and destination are on different devices'))
if st.st_size != ts.st_size:
return False
return st
targets = []
total = len(candidates)
pos = 0
for fn, st in candidates:
pos += 1
srcpath = os.path.join(src, fn)
tgt = os.path.join(dst, fn)
ts = linkfilter(srcpath, tgt, st)
if not ts:
ui.debug('not linkable: %s\n' % fn)
continue
targets.append((fn, ts.st_size))
ui.progress(_('pruning'), pos, fn, _('files'), total)
ui.progress(_('pruning'), None)
ui.status(_('pruned down to %d probably relinkable files\n') % len(targets))
return targets
def do_relink(src, dst, files, ui):
def relinkfile(src, dst):
bak = dst + '.bak'
os.rename(dst, bak)
try:
util.oslink(src, dst)
except OSError:
os.rename(bak, dst)
raise
os.remove(bak)
CHUNKLEN = 65536
relinked = 0
savedbytes = 0
pos = 0
total = len(files)
for f, sz in files:
pos += 1
source = os.path.join(src, f)
tgt = os.path.join(dst, f)
# Binary mode, so that read() works correctly, especially on Windows
sfp = file(source, 'rb')
dfp = file(tgt, 'rb')
sin = sfp.read(CHUNKLEN)
while sin:
din = dfp.read(CHUNKLEN)
if sin != din:
break
sin = sfp.read(CHUNKLEN)
sfp.close()
dfp.close()
if sin:
ui.debug('not linkable: %s\n' % f)
continue
try:
relinkfile(source, tgt)
ui.progress(_('relinking'), pos, f, _('files'), total)
relinked += 1
savedbytes += sz
except OSError, inst:
ui.warn('%s: %s\n' % (tgt, str(inst)))
ui.progress(_('relinking'), None)
ui.status(_('relinked %d files (%s reclaimed)\n') %
(relinked, util.bytecount(savedbytes)))