##// END OF EJS Templates
deltas: set estimated compression upper bound to "3x" instead of "10x"...
deltas: set estimated compression upper bound to "3x" instead of "10x" In pratice, we very rarely observer compression better than "3x" on manifest deltas. Having a more aggressive estimate significantly helps our pathological use case on a private repository. Here are a comparison of timings using different upper bound. Estimated compression | ø | ×10 | ×5 | ×3 | timing | 14.11 | 2.61 | 1.96 | 1.53 | We also tested the impact of this series on an array of public repositories. This shown no impact in either size nor timing. Full data set below for those interested. Size ---- Regarding size, not significant impact have been noticed on neither public nor private repositories. Here are the number we gathered on public repositories: zlib/upperbound | no | 10x | 5x | 3x mercurial | 5 875 730 | 5 875 730 | 5 875 730 | 5 875 730 pypy | 27 782 913 | 27 782 913 | 27 782 913 | 27 782 913 netbeans | 159 161 207 | 159 161 207 | 159 161 207 | 159 959 879 (+0.5%) mozilla-central | 323 841 642 | 323 841 642 | 323 841 642 | 319 867 519 (-2.5%) mozilla-try | 746 649 123 | 746 649 123 | 746 649 123 | 741 155 568 (-0.7%) private-repo | 1 485 287 294 | 1 485 287 294 | 1 485 287 294 | 1 409 248 382 (-5.1%) zstd/upperbound | no | 10x | 5x | 3x mercurial | 5 895 206 | 5 895 206 | 5 895 206 | 5 895 206 pypy | 28 689 230 | 28 689 230 | 28 689 230 | 28 689 230 netbeans | 157 636 387 | 157 636 387 | 157 636 387 | 159 692 678 (+1.3%) mozilla-central | 317 650 281 | 317 650 281 | 317 650 281 | 319 613 603 (+0.6%) mozilla-try | 737 555 275 | 737 555 275 | 737 555 275 | 738 079 473 (+0.1%) private-repo | 1 352 362 982 | 1 352 362 982 | 1 346 961 880 | 1 361 327 384 (+0.7%) Speed ------ Timing gathered using `hg perfrevlogwrite -m`. Value are in seconds. mercurial zlib | no | 10x | 5x | 3x | total | 65.551783 | 65.388887 | 65.260658 | 65.321199 | max | 0.034544 | 0.034571 | 0.034659 | 0.034521 | 99.99% | 0.034544 | 0.034571 | 0.034659 | 0.034521 | zstd | no | 10x | 5x | 3x | total | 49.118449 | 49.054062 | 48.753588 | 48.740230 | max | 0.009338 | 0.009239 | 0.009202 | 0.009178 | 99.99% | 0.007618 | 0.007639 | 0.007626 | 0.007621 | pypy zlib | no | 10x | 5x | 3x | total | 560.865984 | 558.983817 | 559.083815 | 559.349152 | max | 0.219614 | 0.215922 | 0.218112 | 0.218107 | 99.99% | 0.219614 | 0.215922 | 0.218112 | 0.218107 | zstd | no | 10x | 5x | 3x | total | 349.393280 | 347.395819 | 347.185407 | 345.643985 | max | 0.084143 | 0.083536 | 0.081834 | 0.082178 | 99.99% | 0.039445 | 0.039639 | 0.039612 | 0.039175 | netbeans zlib | no | 10x | 5x | 3x | total | 33103.327727 | 33314.932260 | 33211.745233 | 33345.891778 | max | 2.666852 | 2.672059 | 2.662453 | 2.662936 | 99.99% | 2.058772 | 2.070429 | 2.069569 | 2.064653 | zstd | no | 10x | 5x | 3x | total | 20112.102708 | 20095.879719 | 20083.390300 | 20123.221859 | max | 2.063482 | 2.062851 | 2.065229 | 2.060147 | 99.99% | 1.146647 | 1.143794 | 1.142933 | 1.146529 | mozilla zlib | no | 10x | 5x | 3x | total | 41374.102138 | 41418.816773 | 41381.956370 | 41334.280732 | max | 3.383474 | 3.387400 | 3.405711 | 3.387316 | 99.99% | 1.006755 | 1.005954 | 1.007700 | 1.007373 | zstd | no | 10x | 5x | 3x | total | 24689.691520 | 24643.939662 | 24664.630027 | 24664.512714 | max | 1.460822 | 1.449640 | 1.439747 | 1.465304 | 99.99% | 0.527111 | 0.527377 | 0.527807 | 0.527226 |

File last commit:

r42417:d345627d default
r42669:4a3abb33 default
Show More
statichttprepo.py
230 lines | 7.1 KiB | text/x-python | PythonLexer
# statichttprepo.py - simple http repository class for mercurial
#
# This provides read-only repo access to repositories exported via static http
#
# Copyright 2005-2007 Matt Mackall <mpm@selenic.com>
#
# 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 errno
from .i18n import _
from . import (
branchmap,
changelog,
error,
localrepo,
manifest,
namespaces,
pathutil,
pycompat,
url,
util,
vfs as vfsmod,
)
urlerr = util.urlerr
urlreq = util.urlreq
class httprangereader(object):
def __init__(self, url, opener):
# we assume opener has HTTPRangeHandler
self.url = url
self.pos = 0
self.opener = opener
self.name = url
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, traceback):
self.close()
def seek(self, pos):
self.pos = pos
def read(self, bytes=None):
req = urlreq.request(pycompat.strurl(self.url))
end = ''
if bytes:
end = self.pos + bytes - 1
if self.pos or end:
req.add_header(r'Range', r'bytes=%d-%s' % (self.pos, end))
try:
f = self.opener.open(req)
data = f.read()
code = f.code
except urlerr.httperror as inst:
num = inst.code == 404 and errno.ENOENT or None
raise IOError(num, inst)
except urlerr.urlerror as inst:
raise IOError(None, inst.reason)
if code == 200:
# HTTPRangeHandler does nothing if remote does not support
# Range headers and returns the full entity. Let's slice it.
if bytes:
data = data[self.pos:self.pos + bytes]
else:
data = data[self.pos:]
elif bytes:
data = data[:bytes]
self.pos += len(data)
return data
def readlines(self):
return self.read().splitlines(True)
def __iter__(self):
return iter(self.readlines())
def close(self):
pass
# _RangeError and _HTTPRangeHandler were originally in byterange.py,
# which was itself extracted from urlgrabber. See the last version of
# byterange.py from history if you need more information.
class _RangeError(IOError):
"""Error raised when an unsatisfiable range is requested."""
class _HTTPRangeHandler(urlreq.basehandler):
"""Handler that enables HTTP Range headers.
This was extremely simple. The Range header is a HTTP feature to
begin with so all this class does is tell urllib2 that the
"206 Partial Content" response from the HTTP server is what we
expected.
"""
def http_error_206(self, req, fp, code, msg, hdrs):
# 206 Partial Content Response
r = urlreq.addinfourl(fp, hdrs, req.get_full_url())
r.code = code
r.msg = msg
return r
def http_error_416(self, req, fp, code, msg, hdrs):
# HTTP's Range Not Satisfiable error
raise _RangeError('Requested Range Not Satisfiable')
def build_opener(ui, authinfo):
# urllib cannot handle URLs with embedded user or passwd
urlopener = url.opener(ui, authinfo)
urlopener.add_handler(_HTTPRangeHandler())
class statichttpvfs(vfsmod.abstractvfs):
def __init__(self, base):
self.base = base
def __call__(self, path, mode='r', *args, **kw):
if mode not in ('r', 'rb'):
raise IOError('Permission denied')
f = "/".join((self.base, urlreq.quote(path)))
return httprangereader(f, urlopener)
def join(self, path):
if path:
return pathutil.join(self.base, path)
else:
return self.base
return statichttpvfs
class statichttppeer(localrepo.localpeer):
def local(self):
return None
def canpush(self):
return False
class statichttprepository(localrepo.localrepository,
localrepo.revlogfilestorage):
supported = localrepo.localrepository._basesupported
def __init__(self, ui, path):
self._url = path
self.ui = ui
self.root = path
u = util.url(path.rstrip('/') + "/.hg")
self.path, authinfo = u.authinfo()
vfsclass = build_opener(ui, authinfo)
self.vfs = vfsclass(self.path)
self.cachevfs = vfsclass(self.vfs.join('cache'))
self._phasedefaults = []
self.names = namespaces.namespaces()
self.filtername = None
self._extrafilterid = None
try:
requirements = set(self.vfs.read(b'requires').splitlines())
except IOError as inst:
if inst.errno != errno.ENOENT:
raise
requirements = set()
# check if it is a non-empty old-style repository
try:
fp = self.vfs("00changelog.i")
fp.read(1)
fp.close()
except IOError as inst:
if inst.errno != errno.ENOENT:
raise
# we do not care about empty old-style repositories here
msg = _("'%s' does not appear to be an hg repository") % path
raise error.RepoError(msg)
supportedrequirements = localrepo.gathersupportedrequirements(ui)
localrepo.ensurerequirementsrecognized(requirements,
supportedrequirements)
localrepo.ensurerequirementscompatible(ui, requirements)
# setup store
self.store = localrepo.makestore(requirements, self.path, vfsclass)
self.spath = self.store.path
self.svfs = self.store.opener
self.sjoin = self.store.join
self._filecache = {}
self.requirements = requirements
rootmanifest = manifest.manifestrevlog(self.svfs)
self.manifestlog = manifest.manifestlog(self.svfs, self, rootmanifest,
self.narrowmatch())
self.changelog = changelog.changelog(self.svfs)
self._tags = None
self.nodetagscache = None
self._branchcaches = branchmap.BranchMapCache()
self._revbranchcache = None
self.encodepats = None
self.decodepats = None
self._transref = None
def _restrictcapabilities(self, caps):
caps = super(statichttprepository, self)._restrictcapabilities(caps)
return caps.difference(["pushkey"])
def url(self):
return self._url
def local(self):
return False
def peer(self):
return statichttppeer(self)
def wlock(self, wait=True):
raise error.LockUnavailable(0, _('lock not available'), 'lock',
_('cannot lock static-http repository'))
def lock(self, wait=True):
raise error.Abort(_('cannot lock static-http repository'))
def _writecaches(self):
pass # statichttprepository are read only
def instance(ui, path, create, intents=None, createopts=None):
if create:
raise error.Abort(_('cannot create new static-http repository'))
return statichttprepository(ui, path[7:])