##// END OF EJS Templates
revlog: change generaldelta delta parent heuristic...
revlog: change generaldelta delta parent heuristic The old generaldelta heuristic was "if p1 (or p2) was closer than the last full text, use it, otherwise use prev". This was problematic when a repo contained multiple branches that were very different. If commits to branch A were pushed, and the last full text was branch B, it would generate a fulltext. Then if branch B was pushed, it would generate another fulltext. The problem is that the last fulltext (and delta'ing against `prev` in general) has no correlation with the contents of the incoming revision, and therefore will always have degenerate cases. According to the blame, that algorithm was chosen to minimize the chain length. Since there is already code that protects against that (the delta-vs-fulltext code), and since it has been improved since the original generaldelta algorithm went in (2011), I believe the chain length criteria will still be preserved. The new algorithm always diffs against p1 (or p2 if it's closer), unless the resulting delta will fail the delta-vs-fulltext check, in which case we delta against prev. Some before and after stats on manifest.d size. internal large repo old heuristic - 2.0 GB new heuristic - 1.2 GB mozilla-central old heuristic - 242 MB new heuristic - 261 MB The regression in mozilla central is due to the new heuristic choosing p2r as the delta when it's closer to the tip. Switching the algorithm to always prefer p1r brings the size back down (242 MB). This is result of the way in which mozilla does merges and pushes, and the result could easily swing the other direction in other repos (depending on if they merge X into Y or Y into X), but will never be as degenerate as before. I future patch will address the regression by introducing an optional, even more aggressive delta heuristic which will knock the mozilla manifest size down dramatically.

File last commit:

r25978:762f4c6d default
r26117:4dc5b51f default
Show More
statichttprepo.py
179 lines | 5.1 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
import os
import urllib
import urllib2
from .i18n import _
from . import (
byterange,
changelog,
error,
localrepo,
manifest,
namespaces,
scmutil,
store,
url,
util,
)
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 seek(self, pos):
self.pos = pos
def read(self, bytes=None):
req = urllib2.Request(self.url)
end = ''
if bytes:
end = self.pos + bytes - 1
if self.pos or end:
req.add_header('Range', 'bytes=%d-%s' % (self.pos, end))
try:
f = self.opener.open(req)
data = f.read()
code = f.code
except urllib2.HTTPError as inst:
num = inst.code == 404 and errno.ENOENT or None
raise IOError(num, inst)
except urllib2.URLError as inst:
raise IOError(None, inst.reason[1])
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
def build_opener(ui, authinfo):
# urllib cannot handle URLs with embedded user or passwd
urlopener = url.opener(ui, authinfo)
urlopener.add_handler(byterange.HTTPRangeHandler())
class statichttpvfs(scmutil.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, urllib.quote(path)))
return httprangereader(f, urlopener)
def join(self, path):
if path:
return os.path.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):
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()
opener = build_opener(ui, authinfo)
self.opener = opener(self.path)
self.vfs = self.opener
self._phasedefaults = []
self.names = namespaces.namespaces()
try:
requirements = scmutil.readrequires(self.vfs, self.supported)
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)
# setup store
self.store = store.store(requirements, self.path, opener)
self.spath = self.store.path
self.svfs = self.store.opener
self.sjoin = self.store.join
self._filecache = {}
self.requirements = requirements
self.manifest = manifest.manifest(self.svfs)
self.changelog = changelog.changelog(self.svfs)
self._tags = None
self.nodetagscache = None
self._branchcaches = {}
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 lock(self, wait=True):
raise util.Abort(_('cannot lock static-http repository'))
def instance(ui, path, create):
if create:
raise util.Abort(_('cannot create new static-http repository'))
return statichttprepository(ui, path[7:])