##// 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:

r41714:83d62df2 default
r42211:bb271ec2 default
Show More
monotone.py
373 lines | 13.1 KiB | text/x-python | PythonLexer
# monotone.py - monotone support for the convert extension
#
# Copyright 2008, 2009 Mikkel Fahnoe Jorgensen <mikkel@dvide.com> and
# others
#
# 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,
pycompat,
)
from mercurial.utils import dateutil
from . import common
class monotone_source(common.converter_source, common.commandline):
def __init__(self, ui, repotype, path=None, revs=None):
common.converter_source.__init__(self, ui, repotype, path, revs)
if revs and len(revs) > 1:
raise error.Abort(_('monotone source does not support specifying '
'multiple revs'))
common.commandline.__init__(self, ui, 'mtn')
self.ui = ui
self.path = path
self.automatestdio = False
self.revs = revs
norepo = common.NoRepo(_("%s does not look like a monotone repository")
% path)
if not os.path.exists(os.path.join(path, '_MTN')):
# Could be a monotone repository (SQLite db file)
try:
f = open(path, 'rb')
header = f.read(16)
f.close()
except IOError:
header = ''
if header != 'SQLite format 3\x00':
raise norepo
# regular expressions for parsing monotone output
space = br'\s*'
name = br'\s+"((?:\\"|[^"])*)"\s*'
value = name
revision = br'\s+\[(\w+)\]\s*'
lines = br'(?:.|\n)+'
self.dir_re = re.compile(space + "dir" + name)
self.file_re = re.compile(space + "file" + name +
"content" + revision)
self.add_file_re = re.compile(space + "add_file" + name +
"content" + revision)
self.patch_re = re.compile(space + "patch" + name +
"from" + revision + "to" + revision)
self.rename_re = re.compile(space + "rename" + name + "to" + name)
self.delete_re = re.compile(space + "delete" + name)
self.tag_re = re.compile(space + "tag" + name + "revision" +
revision)
self.cert_re = re.compile(lines + space + "name" + name +
"value" + value)
attr = space + "file" + lines + space + "attr" + space
self.attr_execute_re = re.compile(attr + '"mtn:execute"' +
space + '"true"')
# cached data
self.manifest_rev = None
self.manifest = None
self.files = None
self.dirs = None
common.checktool('mtn', abort=False)
def mtnrun(self, *args, **kwargs):
if self.automatestdio:
return self.mtnrunstdio(*args, **kwargs)
else:
return self.mtnrunsingle(*args, **kwargs)
def mtnrunsingle(self, *args, **kwargs):
kwargs[r'd'] = self.path
return self.run0('automate', *args, **kwargs)
def mtnrunstdio(self, *args, **kwargs):
# Prepare the command in automate stdio format
kwargs = pycompat.byteskwargs(kwargs)
command = []
for k, v in kwargs.iteritems():
command.append("%d:%s" % (len(k), k))
if v:
command.append("%d:%s" % (len(v), v))
if command:
command.insert(0, 'o')
command.append('e')
command.append('l')
for arg in args:
command.append("%d:%s" % (len(arg), arg))
command.append('e')
command = ''.join(command)
self.ui.debug("mtn: sending '%s'\n" % command)
self.mtnwritefp.write(command)
self.mtnwritefp.flush()
return self.mtnstdioreadcommandoutput(command)
def mtnstdioreadpacket(self):
read = None
commandnbr = ''
while read != ':':
read = self.mtnreadfp.read(1)
if not read:
raise error.Abort(_('bad mtn packet - no end of commandnbr'))
commandnbr += read
commandnbr = commandnbr[:-1]
stream = self.mtnreadfp.read(1)
if stream not in 'mewptl':
raise error.Abort(_('bad mtn packet - bad stream type %s') % stream)
read = self.mtnreadfp.read(1)
if read != ':':
raise error.Abort(_('bad mtn packet - no divider before size'))
read = None
lengthstr = ''
while read != ':':
read = self.mtnreadfp.read(1)
if not read:
raise error.Abort(_('bad mtn packet - no end of packet size'))
lengthstr += read
try:
length = pycompat.long(lengthstr[:-1])
except TypeError:
raise error.Abort(_('bad mtn packet - bad packet size %s')
% lengthstr)
read = self.mtnreadfp.read(length)
if len(read) != length:
raise error.Abort(_("bad mtn packet - unable to read full packet "
"read %s of %s") % (len(read), length))
return (commandnbr, stream, length, read)
def mtnstdioreadcommandoutput(self, command):
retval = []
while True:
commandnbr, stream, length, output = self.mtnstdioreadpacket()
self.ui.debug('mtn: read packet %s:%s:%d\n' %
(commandnbr, stream, length))
if stream == 'l':
# End of command
if output != '0':
raise error.Abort(_("mtn command '%s' returned %s") %
(command, output))
break
elif stream in 'ew':
# Error, warning output
self.ui.warn(_('%s error:\n') % self.command)
self.ui.warn(output)
elif stream == 'p':
# Progress messages
self.ui.debug('mtn: ' + output)
elif stream == 'm':
# Main stream - command output
retval.append(output)
return ''.join(retval)
def mtnloadmanifest(self, rev):
if self.manifest_rev == rev:
return
self.manifest = self.mtnrun("get_manifest_of", rev).split("\n\n")
self.manifest_rev = rev
self.files = {}
self.dirs = {}
for e in self.manifest:
m = self.file_re.match(e)
if m:
attr = ""
name = m.group(1)
node = m.group(2)
if self.attr_execute_re.match(e):
attr += "x"
self.files[name] = (node, attr)
m = self.dir_re.match(e)
if m:
self.dirs[m.group(1)] = True
def mtnisfile(self, name, rev):
# a non-file could be a directory or a deleted or renamed file
self.mtnloadmanifest(rev)
return name in self.files
def mtnisdir(self, name, rev):
self.mtnloadmanifest(rev)
return name in self.dirs
def mtngetcerts(self, rev):
certs = {"author":"<missing>", "date":"<missing>",
"changelog":"<missing>", "branch":"<missing>"}
certlist = self.mtnrun("certs", rev)
# mtn < 0.45:
# key "test@selenic.com"
# mtn >= 0.45:
# key [ff58a7ffb771907c4ff68995eada1c4da068d328]
certlist = re.split(br'\n\n key ["\[]', certlist)
for e in certlist:
m = self.cert_re.match(e)
if m:
name, value = m.groups()
value = value.replace(br'\"', '"')
value = value.replace(br'\\', '\\')
certs[name] = value
# Monotone may have subsecond dates: 2005-02-05T09:39:12.364306
# and all times are stored in UTC
certs["date"] = certs["date"].split('.')[0] + " UTC"
return certs
# implement the converter_source interface:
def getheads(self):
if not self.revs:
return self.mtnrun("leaves").splitlines()
else:
return self.revs
def getchanges(self, rev, full):
if full:
raise error.Abort(_("convert from monotone does not support "
"--full"))
revision = self.mtnrun("get_revision", rev).split("\n\n")
files = {}
ignoremove = {}
renameddirs = []
copies = {}
for e in revision:
m = self.add_file_re.match(e)
if m:
files[m.group(1)] = rev
ignoremove[m.group(1)] = rev
m = self.patch_re.match(e)
if m:
files[m.group(1)] = rev
# Delete/rename is handled later when the convert engine
# discovers an IOError exception from getfile,
# but only if we add the "from" file to the list of changes.
m = self.delete_re.match(e)
if m:
files[m.group(1)] = rev
m = self.rename_re.match(e)
if m:
toname = m.group(2)
fromname = m.group(1)
if self.mtnisfile(toname, rev):
ignoremove[toname] = 1
copies[toname] = fromname
files[toname] = rev
files[fromname] = rev
elif self.mtnisdir(toname, rev):
renameddirs.append((fromname, toname))
# Directory renames can be handled only once we have recorded
# all new files
for fromdir, todir in renameddirs:
renamed = {}
for tofile in self.files:
if tofile in ignoremove:
continue
if tofile.startswith(todir + '/'):
renamed[tofile] = fromdir + tofile[len(todir):]
# Avoid chained moves like:
# d1(/a) => d3/d1(/a)
# d2 => d3
ignoremove[tofile] = 1
for tofile, fromfile in renamed.items():
self.ui.debug (_("copying file in renamed directory "
"from '%s' to '%s'")
% (fromfile, tofile), '\n')
files[tofile] = rev
copies[tofile] = fromfile
for fromfile in renamed.values():
files[fromfile] = rev
return (files.items(), copies, set())
def getfile(self, name, rev):
if not self.mtnisfile(name, rev):
return None, None
try:
data = self.mtnrun("get_file_of", name, r=rev)
except Exception:
return None, None
self.mtnloadmanifest(rev)
node, attr = self.files.get(name, (None, ""))
return data, attr
def getcommit(self, rev):
extra = {}
certs = self.mtngetcerts(rev)
if certs.get('suspend') == certs["branch"]:
extra['close'] = 1
dateformat = "%Y-%m-%dT%H:%M:%S"
return common.commit(
author=certs["author"],
date=dateutil.datestr(dateutil.strdate(certs["date"], dateformat)),
desc=certs["changelog"],
rev=rev,
parents=self.mtnrun("parents", rev).splitlines(),
branch=certs["branch"],
extra=extra)
def gettags(self):
tags = {}
for e in self.mtnrun("tags").split("\n\n"):
m = self.tag_re.match(e)
if m:
tags[m.group(1)] = m.group(2)
return tags
def getchangedfiles(self, rev, i):
# This function is only needed to support --filemap
# ... and we don't support that
raise NotImplementedError
def before(self):
# Check if we have a new enough version to use automate stdio
try:
versionstr = self.mtnrunsingle("interface_version")
version = float(versionstr)
except Exception:
raise error.Abort(_("unable to determine mtn automate interface "
"version"))
if version >= 12.0:
self.automatestdio = True
self.ui.debug("mtn automate version %f - using automate stdio\n" %
version)
# launch the long-running automate stdio process
self.mtnwritefp, self.mtnreadfp = self._run2('automate', 'stdio',
'-d', self.path)
# read the headers
read = self.mtnreadfp.readline()
if read != 'format-version: 2\n':
raise error.Abort(_('mtn automate stdio header unexpected: %s')
% read)
while read != '\n':
read = self.mtnreadfp.readline()
if not read:
raise error.Abort(_("failed to reach end of mtn automate "
"stdio headers"))
else:
self.ui.debug("mtn automate version %s - not using automate stdio "
"(automate >= 12.0 - mtn >= 0.46 is needed)\n" % version)
def after(self):
if self.automatestdio:
self.mtnwritefp.close()
self.mtnwritefp = None
self.mtnreadfp.close()
self.mtnreadfp = None