##// 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:

r41925:aaad36b8 default
r42211:bb271ec2 default
Show More
p4.py
378 lines | 12.4 KiB | text/x-python | PythonLexer
# Perforce source for convert extension.
#
# Copyright 2009, Frank Kingswood <frank@kingswood-consulting.co.uk>
#
# 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 marshal
import re
from mercurial.i18n import _
from mercurial import (
error,
util,
)
from mercurial.utils import (
dateutil,
procutil,
stringutil,
)
from . import common
def loaditer(f):
"Yield the dictionary objects generated by p4"
try:
while True:
d = marshal.load(f)
if not d:
break
yield d
except EOFError:
pass
def decodefilename(filename):
"""Perforce escapes special characters @, #, *, or %
with %40, %23, %2A, or %25 respectively
>>> decodefilename(b'portable-net45%252Bnetcore45%252Bwp8%252BMonoAndroid')
'portable-net45%2Bnetcore45%2Bwp8%2BMonoAndroid'
>>> decodefilename(b'//Depot/Directory/%2525/%2523/%23%40.%2A')
'//Depot/Directory/%25/%23/#@.*'
"""
replacements = [('%2A', '*'), ('%23', '#'), ('%40', '@'), ('%25', '%')]
for k, v in replacements:
filename = filename.replace(k, v)
return filename
class p4_source(common.converter_source):
def __init__(self, ui, repotype, path, revs=None):
# avoid import cycle
from . import convcmd
super(p4_source, self).__init__(ui, repotype, path, revs=revs)
if "/" in path and not path.startswith('//'):
raise common.NoRepo(_('%s does not look like a P4 repository') %
path)
common.checktool('p4', abort=False)
self.revmap = {}
self.encoding = self.ui.config('convert', 'p4.encoding',
convcmd.orig_encoding)
self.re_type = re.compile(
br"([a-z]+)?(text|binary|symlink|apple|resource|unicode|utf\d+)"
br"(\+\w+)?$")
self.re_keywords = re.compile(
br"\$(Id|Header|Date|DateTime|Change|File|Revision|Author)"
br":[^$\n]*\$")
self.re_keywords_old = re.compile(br"\$(Id|Header):[^$\n]*\$")
if revs and len(revs) > 1:
raise error.Abort(_("p4 source does not support specifying "
"multiple revisions"))
def setrevmap(self, revmap):
"""Sets the parsed revmap dictionary.
Revmap stores mappings from a source revision to a target revision.
It is set in convertcmd.convert and provided by the user as a file
on the commandline.
Revisions in the map are considered beeing present in the
repository and ignored during _parse(). This allows for incremental
imports if a revmap is provided.
"""
self.revmap = revmap
def _parse_view(self, path):
"Read changes affecting the path"
cmd = 'p4 -G changes -s submitted %s' % procutil.shellquote(path)
stdout = procutil.popen(cmd, mode='rb')
p4changes = {}
for d in loaditer(stdout):
c = d.get("change", None)
if c:
p4changes[c] = True
return p4changes
def _parse(self, ui, path):
"Prepare list of P4 filenames and revisions to import"
p4changes = {}
changeset = {}
files_map = {}
copies_map = {}
localname = {}
depotname = {}
heads = []
ui.status(_('reading p4 views\n'))
# read client spec or view
if "/" in path:
p4changes.update(self._parse_view(path))
if path.startswith("//") and path.endswith("/..."):
views = {path[:-3]:""}
else:
views = {"//": ""}
else:
cmd = 'p4 -G client -o %s' % procutil.shellquote(path)
clientspec = marshal.load(procutil.popen(cmd, mode='rb'))
views = {}
for client in clientspec:
if client.startswith("View"):
sview, cview = clientspec[client].split()
p4changes.update(self._parse_view(sview))
if sview.endswith("...") and cview.endswith("..."):
sview = sview[:-3]
cview = cview[:-3]
cview = cview[2:]
cview = cview[cview.find("/") + 1:]
views[sview] = cview
# list of changes that affect our source files
p4changes = p4changes.keys()
p4changes.sort(key=int)
# list with depot pathnames, longest first
vieworder = views.keys()
vieworder.sort(key=len, reverse=True)
# handle revision limiting
startrev = self.ui.config('convert', 'p4.startrev')
# now read the full changelists to get the list of file revisions
ui.status(_('collecting p4 changelists\n'))
lastid = None
for change in p4changes:
if startrev and int(change) < int(startrev):
continue
if self.revs and int(change) > int(self.revs[0]):
continue
if change in self.revmap:
# Ignore already present revisions, but set the parent pointer.
lastid = change
continue
if lastid:
parents = [lastid]
else:
parents = []
d = self._fetch_revision(change)
c = self._construct_commit(d, parents)
descarr = c.desc.splitlines(True)
if len(descarr) > 0:
shortdesc = descarr[0].rstrip('\r\n')
else:
shortdesc = '**empty changelist description**'
t = '%s %s' % (c.rev, repr(shortdesc)[1:-1])
ui.status(stringutil.ellipsis(t, 80) + '\n')
files = []
copies = {}
copiedfiles = []
i = 0
while ("depotFile%d" % i) in d and ("rev%d" % i) in d:
oldname = d["depotFile%d" % i]
filename = None
for v in vieworder:
if oldname.lower().startswith(v.lower()):
filename = decodefilename(views[v] + oldname[len(v):])
break
if filename:
files.append((filename, d["rev%d" % i]))
depotname[filename] = oldname
if (d.get("action%d" % i) == "move/add"):
copiedfiles.append(filename)
localname[oldname] = filename
i += 1
# Collect information about copied files
for filename in copiedfiles:
oldname = depotname[filename]
flcmd = ('p4 -G filelog %s'
% procutil.shellquote(oldname))
flstdout = procutil.popen(flcmd, mode='rb')
copiedfilename = None
for d in loaditer(flstdout):
copiedoldname = None
i = 0
while ("change%d" % i) in d:
if (d["change%d" % i] == change and
d["action%d" % i] == "move/add"):
j = 0
while ("file%d,%d" % (i, j)) in d:
if d["how%d,%d" % (i, j)] == "moved from":
copiedoldname = d["file%d,%d" % (i, j)]
break
j += 1
i += 1
if copiedoldname and copiedoldname in localname:
copiedfilename = localname[copiedoldname]
break
if copiedfilename:
copies[filename] = copiedfilename
else:
ui.warn(_("cannot find source for copied file: %s@%s\n")
% (filename, change))
changeset[change] = c
files_map[change] = files
copies_map[change] = copies
lastid = change
if lastid and len(changeset) > 0:
heads = [lastid]
return {
'changeset': changeset,
'files': files_map,
'copies': copies_map,
'heads': heads,
'depotname': depotname,
}
@util.propertycache
def _parse_once(self):
return self._parse(self.ui, self.path)
@util.propertycache
def copies(self):
return self._parse_once['copies']
@util.propertycache
def files(self):
return self._parse_once['files']
@util.propertycache
def changeset(self):
return self._parse_once['changeset']
@util.propertycache
def heads(self):
return self._parse_once['heads']
@util.propertycache
def depotname(self):
return self._parse_once['depotname']
def getheads(self):
return self.heads
def getfile(self, name, rev):
cmd = ('p4 -G print %s'
% procutil.shellquote("%s#%s" % (self.depotname[name], rev)))
lasterror = None
while True:
stdout = procutil.popen(cmd, mode='rb')
mode = None
contents = []
keywords = None
for d in loaditer(stdout):
code = d["code"]
data = d.get("data")
if code == "error":
# if this is the first time error happened
# re-attempt getting the file
if not lasterror:
lasterror = IOError(d["generic"], data)
# this will exit inner-most for-loop
break
else:
raise lasterror
elif code == "stat":
action = d.get("action")
if action in ["purge", "delete", "move/delete"]:
return None, None
p4type = self.re_type.match(d["type"])
if p4type:
mode = ""
flags = ((p4type.group(1) or "")
+ (p4type.group(3) or ""))
if "x" in flags:
mode = "x"
if p4type.group(2) == "symlink":
mode = "l"
if "ko" in flags:
keywords = self.re_keywords_old
elif "k" in flags:
keywords = self.re_keywords
elif code == "text" or code == "binary":
contents.append(data)
lasterror = None
if not lasterror:
break
if mode is None:
return None, None
contents = ''.join(contents)
if keywords:
contents = keywords.sub("$\\1$", contents)
if mode == "l" and contents.endswith("\n"):
contents = contents[:-1]
return contents, mode
def getchanges(self, rev, full):
if full:
raise error.Abort(_("convert from p4 does not support --full"))
return self.files[rev], self.copies[rev], set()
def _construct_commit(self, obj, parents=None):
"""
Constructs a common.commit object from an unmarshalled
`p4 describe` output
"""
desc = self.recode(obj.get("desc", ""))
date = (int(obj["time"]), 0) # timezone not set
if parents is None:
parents = []
return common.commit(author=self.recode(obj["user"]),
date=dateutil.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'),
parents=parents, desc=desc, branch=None, rev=obj['change'],
extra={"p4": obj['change'], "convert_revision": obj['change']})
def _fetch_revision(self, rev):
"""Return an output of `p4 describe` including author, commit date as
a dictionary."""
cmd = "p4 -G describe -s %s" % rev
stdout = procutil.popen(cmd, mode='rb')
return marshal.load(stdout)
def getcommit(self, rev):
if rev in self.changeset:
return self.changeset[rev]
elif rev in self.revmap:
d = self._fetch_revision(rev)
return self._construct_commit(d, parents=None)
raise error.Abort(
_("cannot find %s in the revmap or parsed changesets") % rev)
def gettags(self):
return {}
def getchangedfiles(self, rev, i):
return sorted([x[0] for x in self.files[rev]])