##// 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:

r25964:d740df4e default
r26117:4dc5b51f default
Show More
pathutil.py
202 lines | 7.0 KiB | text/x-python | PythonLexer
from __future__ import absolute_import
import errno
import os
import posixpath
import stat
from .i18n import _
from . import (
encoding,
util,
)
def _lowerclean(s):
return encoding.hfsignoreclean(s.lower())
class pathauditor(object):
'''ensure that a filesystem path contains no banned components.
the following properties of a path are checked:
- ends with a directory separator
- under top-level .hg
- starts at the root of a windows drive
- contains ".."
- traverses a symlink (e.g. a/symlink_here/b)
- inside a nested repository (a callback can be used to approve
some nested repositories, e.g., subrepositories)
'''
def __init__(self, root, callback=None):
self.audited = set()
self.auditeddir = set()
self.root = root
self.callback = callback
if os.path.lexists(root) and not util.checkcase(root):
self.normcase = util.normcase
else:
self.normcase = lambda x: x
def __call__(self, path):
'''Check the relative path.
path may contain a pattern (e.g. foodir/**.txt)'''
path = util.localpath(path)
normpath = self.normcase(path)
if normpath in self.audited:
return
# AIX ignores "/" at end of path, others raise EISDIR.
if util.endswithsep(path):
raise util.Abort(_("path ends in directory separator: %s") % path)
parts = util.splitpath(path)
if (os.path.splitdrive(path)[0]
or _lowerclean(parts[0]) in ('.hg', '.hg.', '')
or os.pardir in parts):
raise util.Abort(_("path contains illegal component: %s") % path)
# Windows shortname aliases
for p in parts:
if "~" in p:
first, last = p.split("~", 1)
if last.isdigit() and first.upper() in ["HG", "HG8B6C"]:
raise util.Abort(_("path contains illegal component: %s")
% path)
if '.hg' in _lowerclean(path):
lparts = [_lowerclean(p.lower()) for p in parts]
for p in '.hg', '.hg.':
if p in lparts[1:]:
pos = lparts.index(p)
base = os.path.join(*parts[:pos])
raise util.Abort(_("path '%s' is inside nested repo %r")
% (path, base))
normparts = util.splitpath(normpath)
assert len(parts) == len(normparts)
parts.pop()
normparts.pop()
prefixes = []
while parts:
prefix = os.sep.join(parts)
normprefix = os.sep.join(normparts)
if normprefix in self.auditeddir:
break
curpath = os.path.join(self.root, prefix)
try:
st = os.lstat(curpath)
except OSError as err:
# EINVAL can be raised as invalid path syntax under win32.
# They must be ignored for patterns can be checked too.
if err.errno not in (errno.ENOENT, errno.ENOTDIR, errno.EINVAL):
raise
else:
if stat.S_ISLNK(st.st_mode):
raise util.Abort(
_('path %r traverses symbolic link %r')
% (path, prefix))
elif (stat.S_ISDIR(st.st_mode) and
os.path.isdir(os.path.join(curpath, '.hg'))):
if not self.callback or not self.callback(curpath):
raise util.Abort(_("path '%s' is inside nested "
"repo %r")
% (path, prefix))
prefixes.append(normprefix)
parts.pop()
normparts.pop()
self.audited.add(normpath)
# only add prefixes to the cache after checking everything: we don't
# want to add "foo/bar/baz" before checking if there's a "foo/.hg"
self.auditeddir.update(prefixes)
def check(self, path):
try:
self(path)
return True
except (OSError, util.Abort):
return False
def canonpath(root, cwd, myname, auditor=None):
'''return the canonical path of myname, given cwd and root'''
if util.endswithsep(root):
rootsep = root
else:
rootsep = root + os.sep
name = myname
if not os.path.isabs(name):
name = os.path.join(root, cwd, name)
name = os.path.normpath(name)
if auditor is None:
auditor = pathauditor(root)
if name != rootsep and name.startswith(rootsep):
name = name[len(rootsep):]
auditor(name)
return util.pconvert(name)
elif name == root:
return ''
else:
# Determine whether `name' is in the hierarchy at or beneath `root',
# by iterating name=dirname(name) until that causes no change (can't
# check name == '/', because that doesn't work on windows). The list
# `rel' holds the reversed list of components making up the relative
# file name we want.
rel = []
while True:
try:
s = util.samefile(name, root)
except OSError:
s = False
if s:
if not rel:
# name was actually the same as root (maybe a symlink)
return ''
rel.reverse()
name = os.path.join(*rel)
auditor(name)
return util.pconvert(name)
dirname, basename = util.split(name)
rel.append(basename)
if dirname == name:
break
name = dirname
# A common mistake is to use -R, but specify a file relative to the repo
# instead of cwd. Detect that case, and provide a hint to the user.
hint = None
try:
if cwd != root:
canonpath(root, root, myname, auditor)
hint = (_("consider using '--cwd %s'")
% os.path.relpath(root, cwd))
except util.Abort:
pass
raise util.Abort(_("%s not under root '%s'") % (myname, root),
hint=hint)
def normasprefix(path):
'''normalize the specified path as path prefix
Returned value can be used safely for "p.startswith(prefix)",
"p[len(prefix):]", and so on.
For efficiency, this expects "path" argument to be already
normalized by "os.path.normpath", "os.path.realpath", and so on.
See also issue3033 for detail about need of this function.
>>> normasprefix('/foo/bar').replace(os.sep, '/')
'/foo/bar/'
>>> normasprefix('/').replace(os.sep, '/')
'/'
'''
d, p = os.path.splitdrive(path)
if len(p) != len(os.sep):
return path + os.sep
else:
return path
# forward two methods from posixpath that do what we need, but we'd
# rather not let our internals know that we're thinking in posix terms
# - instead we'll let them be oblivious.
join = posixpath.join
dirname = posixpath.dirname