##// END OF EJS Templates
compression: introduce a `storage.revlog.zstd.level` configuration...
compression: introduce a `storage.revlog.zstd.level` configuration This option control the zstd compression level used when compressing revlog chunk. The usage of zstd for revlog compression has not graduated from experimental yet, but we intend to fix that soon. The option name for the compression level is more straight forward to pick, so this changesets comes first. Having a dedicated option for each compression engine is useful because they don't support the same range of values. I ran the same measurement as for the zlib compression level (in the parent changesets). The variation in repository size is stay mostly in the same (small) range. The "read/write" performance see smallish variation, but are overall much better than zlib. Write performance show the same tend of having better write performance for when reaching high-end compression. Again, we don't intend to change the default zstd compression level (currently: 3) in this series. However this is worth investigating in the future. The Performance comparison of zlib vs zstd is quite impressive. The repository size stay in the same range, but the performance are much better in all situations. Comparison summary ================== We are looking at: - performance range for zlib - performance range for zstd - comparison of default zstd (level-3) to default zlib (level 6) - comparison of the slowest zstd time to the fastest zlib time Read performance: ----------------- | zlib | zstd | cmp | f2s mercurial | 0.170159 - 0.189219 | 0.144127 - 0.149624 | 80% | 88% pypy | 2.679217 - 2.768691 | 1.532317 - 1.705044 | 60% | 63% netbeans | 122.477027 - 141.620281 | 72.996346 - 89.731560 | 58% | 73% mozilla | 147.867662 - 170.572118 | 91.700995 - 105.853099 | 56% | 71% Write performance: ------------------ | zlib | zstd | cmp | f2s mercurial | 53.250304 - 56.2936129 | 40.877025 - 45.677286 | 75% | 86% pypy | 460.721984 - 476.589918 | 270.545409 - 301.002219 | 63% | 65% netbeans | 520.560316 - 715.930400 | 370.356311 - 428.329652 | 55% | 82% mozilla | 739.803002 - 987.056093 | 505.152906 - 591.930683 | 57% | 80% Raw data -------- repo alg lvl .hg/store size 00manifest.d read write mercurial zlib 1 49,402,813 5,963,475 0.170159 53.250304 mercurial zlib 6 47,197,397 5,875,730 0.182820 56.264320 mercurial zlib 9 47,121,596 5,849,781 0.189219 56.293612 mercurial zstd 1 49,737,084 5,966,355 0.144127 40.877025 mercurial zstd 3 48,961,867 5,895,208 0.146376 42.268142 mercurial zstd 5 48,200,592 5,938,676 0.149624 43.162875 mercurial zstd 10 47,833,520 5,913,353 0.145185 44.012489 mercurial zstd 15 47,314,604 5,728,679 0.147686 45.677286 mercurial zstd 20 47,330,502 5,830,539 0.145789 45.025407 mercurial zstd 22 47,330,076 5,830,539 0.143996 44.690460 pypy zlib 1 370,830,572 28,462,425 2.679217 460.721984 pypy zlib 6 340,112,317 27,648,747 2.768691 467.537158 pypy zlib 9 338,360,736 27,639,003 2.763495 476.589918 pypy zstd 1 362,377,479 27,916,214 1.532317 270.545409 pypy zstd 3 354,137,693 27,905,988 1.686718 294.951509 pypy zstd 5 342,640,043 27,655,774 1.705044 301.002219 pypy zstd 10 334,224,327 27,164,493 1.567287 285.186239 pypy zstd 15 329,000,363 26,645,965 1.637729 299.561332 pypy zstd 20 324,534,039 26,199,547 1.526813 302.149827 pypy zstd 22 324,530,595 26,198,932 1.525718 307.821218 netbeans zlib 1 1,281,847,810 165,495,457 122.477027 520.560316 netbeans zlib 6 1,205,284,353 159,161,207 139.876147 715.930400 netbeans zlib 9 1,197,135,671 155,034,586 141.620281 678.297064 netbeans zstd 1 1,259,581,737 160,840,613 72.996346 370.356311 netbeans zstd 3 1,232,978,122 157,691,551 81.622317 396.733087 netbeans zstd 5 1,208,034,075 160,246,880 83.080549 364.342626 netbeans zstd 10 1,188,624,176 156,083,417 79.323935 403.594602 netbeans zstd 15 1,176,973,589 153,859,477 89.731560 428.329652 netbeans zstd 20 1,162,958,258 151,147,535 82.842667 392.335349 netbeans zstd 22 1,162,707,029 151,150,220 82.565695 402.840655 mozilla zlib 1 2,775,497,186 298,527,987 147.867662 751.263721 mozilla zlib 6 2,596,856,420 286,597,671 170.572118 987.056093 mozilla zlib 9 2,587,542,494 287,018,264 163.622338 739.803002 mozilla zstd 1 2,723,159,348 286,617,532 91.700995 570.042751 mozilla zstd 3 2,665,055,001 286,152,013 95.240155 561.412805 mozilla zstd 5 2,607,819,817 288,060,030 101.978048 505.152906 mozilla zstd 10 2,558,761,085 283,967,648 104.113481 497.771202 mozilla zstd 15 2,526,216,060 275,581,300 105.853099 591.930683 mozilla zstd 20 2,485,114,806 266,478,859 95.268795 576.515389 mozilla zstd 22 2,484,869,080 266,456,505 94.429282 572.785537

File last commit:

r41092:0a7f582f default
r42211:bb271ec2 default
Show More
proto.py
198 lines | 7.4 KiB | text/x-python | PythonLexer
# Copyright 2011 Fog Creek Software
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import
import os
import re
from mercurial.i18n import _
from mercurial import (
error,
exthelper,
httppeer,
util,
wireprototypes,
wireprotov1peer,
wireprotov1server,
)
from . import (
lfutil,
)
urlerr = util.urlerr
urlreq = util.urlreq
LARGEFILES_REQUIRED_MSG = ('\nThis repository uses the largefiles extension.'
'\n\nPlease enable it in your Mercurial config '
'file.\n')
eh = exthelper.exthelper()
# these will all be replaced by largefiles.uisetup
ssholdcallstream = None
httpoldcallstream = None
def putlfile(repo, proto, sha):
'''Server command for putting a largefile into a repository's local store
and into the user cache.'''
with proto.mayberedirectstdio() as output:
path = lfutil.storepath(repo, sha)
util.makedirs(os.path.dirname(path))
tmpfp = util.atomictempfile(path, createmode=repo.store.createmode)
try:
for p in proto.getpayload():
tmpfp.write(p)
tmpfp._fp.seek(0)
if sha != lfutil.hexsha1(tmpfp._fp):
raise IOError(0, _('largefile contents do not match hash'))
tmpfp.close()
lfutil.linktousercache(repo, sha)
except IOError as e:
repo.ui.warn(_('largefiles: failed to put %s into store: %s\n') %
(sha, e.strerror))
return wireprototypes.pushres(
1, output.getvalue() if output else '')
finally:
tmpfp.discard()
return wireprototypes.pushres(0, output.getvalue() if output else '')
def getlfile(repo, proto, sha):
'''Server command for retrieving a largefile from the repository-local
cache or user cache.'''
filename = lfutil.findfile(repo, sha)
if not filename:
raise error.Abort(_('requested largefile %s not present in cache')
% sha)
f = open(filename, 'rb')
length = os.fstat(f.fileno())[6]
# Since we can't set an HTTP content-length header here, and
# Mercurial core provides no way to give the length of a streamres
# (and reading the entire file into RAM would be ill-advised), we
# just send the length on the first line of the response, like the
# ssh proto does for string responses.
def generator():
yield '%d\n' % length
for chunk in util.filechunkiter(f):
yield chunk
return wireprototypes.streamreslegacy(gen=generator())
def statlfile(repo, proto, sha):
'''Server command for checking if a largefile is present - returns '2\n' if
the largefile is missing, '0\n' if it seems to be in good condition.
The value 1 is reserved for mismatched checksum, but that is too expensive
to be verified on every stat and must be caught be running 'hg verify'
server side.'''
filename = lfutil.findfile(repo, sha)
if not filename:
return wireprototypes.bytesresponse('2\n')
return wireprototypes.bytesresponse('0\n')
def wirereposetup(ui, repo):
class lfileswirerepository(repo.__class__):
def putlfile(self, sha, fd):
# unfortunately, httprepository._callpush tries to convert its
# input file-like into a bundle before sending it, so we can't use
# it ...
if issubclass(self.__class__, httppeer.httppeer):
res = self._call('putlfile', data=fd, sha=sha,
headers={r'content-type': r'application/mercurial-0.1'})
try:
d, output = res.split('\n', 1)
for l in output.splitlines(True):
self.ui.warn(_('remote: '), l) # assume l ends with \n
return int(d)
except ValueError:
self.ui.warn(_('unexpected putlfile response: %r\n') % res)
return 1
# ... but we can't use sshrepository._call because the data=
# argument won't get sent, and _callpush does exactly what we want
# in this case: send the data straight through
else:
try:
ret, output = self._callpush("putlfile", fd, sha=sha)
if ret == "":
raise error.ResponseError(_('putlfile failed:'),
output)
return int(ret)
except IOError:
return 1
except ValueError:
raise error.ResponseError(
_('putlfile failed (unexpected response):'), ret)
def getlfile(self, sha):
"""returns an iterable with the chunks of the file with sha sha"""
stream = self._callstream("getlfile", sha=sha)
length = stream.readline()
try:
length = int(length)
except ValueError:
self._abort(error.ResponseError(_("unexpected response:"),
length))
# SSH streams will block if reading more than length
for chunk in util.filechunkiter(stream, limit=length):
yield chunk
# HTTP streams must hit the end to process the last empty
# chunk of Chunked-Encoding so the connection can be reused.
if issubclass(self.__class__, httppeer.httppeer):
chunk = stream.read(1)
if chunk:
self._abort(error.ResponseError(_("unexpected response:"),
chunk))
@wireprotov1peer.batchable
def statlfile(self, sha):
f = wireprotov1peer.future()
result = {'sha': sha}
yield result, f
try:
yield int(f.value)
except (ValueError, urlerr.httperror):
# If the server returns anything but an integer followed by a
# newline, newline, it's not speaking our language; if we get
# an HTTP error, we can't be sure the largefile is present;
# either way, consider it missing.
yield 2
repo.__class__ = lfileswirerepository
# advertise the largefiles=serve capability
@eh.wrapfunction(wireprotov1server, '_capabilities')
def _capabilities(orig, repo, proto):
'''announce largefile server capability'''
caps = orig(repo, proto)
caps.append('largefiles=serve')
return caps
def heads(orig, repo, proto):
'''Wrap server command - largefile capable clients will know to call
lheads instead'''
if lfutil.islfilesrepo(repo):
return wireprototypes.ooberror(LARGEFILES_REQUIRED_MSG)
return orig(repo, proto)
def sshrepocallstream(self, cmd, **args):
if cmd == 'heads' and self.capable('largefiles'):
cmd = 'lheads'
if cmd == 'batch' and self.capable('largefiles'):
args[r'cmds'] = args[r'cmds'].replace('heads ', 'lheads ')
return ssholdcallstream(self, cmd, **args)
headsre = re.compile(br'(^|;)heads\b')
def httprepocallstream(self, cmd, **args):
if cmd == 'heads' and self.capable('largefiles'):
cmd = 'lheads'
if cmd == 'batch' and self.capable('largefiles'):
args[r'cmds'] = headsre.sub('lheads', args[r'cmds'])
return httpoldcallstream(self, cmd, **args)