##// END OF EJS Templates
namespaces: let namespaces override singlenode() definition...
namespaces: let namespaces override singlenode() definition Some namespaces have multiple nodes per name (meaning that their namemap() returns multiple nodes). One such namespace is the "topics" namespace (from the evolve repo). We also have our own internal namespace at Google (for review units) that has multiple nodes per name. These namespaces may not want to use the default "pick highest revnum" resolution that we currently use when resolving a name to a single node. As an example, they may decide that `hg co <name>` should check out a commit that's last in some sense even if an earlier commit had just been amended and thus had a higher revnum [1]. This patch gives the namespace the option to continue to return multiple nodes and to override how the best node is picked. Allowing namespaces to override that may also be useful as an optimization (it may be cheaper for the namespace to find just that node). I have been arguing (in D3715) for using all the nodes returned from namemap() when resolving the symbol to a revset, so e.g. `hg log -r stable` would resolve to *all* nodes on stable, not just the one with the highest revnum (except that I don't actually think we should change it for the branch namespace because of BC). Most people seem opposed to that. If we decide not to do it, I think we can deprecate the namemap() function in favor of the new singlenode() (I find it weird to have namespaces, like the branch namespace, where namemap() isn't nodemap()'s inverse). I therefore think this patch makes sense regardless of what we decide on that issue. [1] Actually, even the branch namespace would have wanted to override singlenode() if it had supported multiple nodes. That's because closes branch heads are mostly ignored, so "hg co default" will not check out the highest-revnum node if that's a closed head. Differential Revision: https://phab.mercurial-scm.org/D3852

File last commit:

r38461:36edfbac @52 default
r38505:4c068365 @58 default
Show More
relink.py
194 lines | 6.5 KiB | text/x-python | PythonLexer
# Mercurial extension to provide 'hg relink' command
#
# Copyright (C) 2007 Brendan Cully <brendan@kublai.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""recreates hardlinks between repository clones"""
from __future__ import absolute_import
import os
import stat
from mercurial.i18n import _
from mercurial import (
error,
hg,
registrar,
util,
)
from mercurial.utils import (
stringutil,
)
cmdtable = {}
command = registrar.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = 'ships-with-hg-core'
@command('relink', [], _('[ORIGIN]'))
def relink(ui, repo, origin=None, **opts):
"""recreate hardlinks between two repositories
When repositories are cloned locally, their data files will be
hardlinked so that they only use the space of a single repository.
Unfortunately, subsequent pulls into either repository will break
hardlinks for any files touched by the new changesets, even if
both repositories end up pulling the same changes.
Similarly, passing --rev to "hg clone" will fail to use any
hardlinks, falling back to a complete copy of the source
repository.
This command lets you recreate those hardlinks and reclaim that
wasted space.
This repository will be relinked to share space with ORIGIN, which
must be on the same local disk. If ORIGIN is omitted, looks for
"default-relink", then "default", in [paths].
Do not attempt any read operations on this repository while the
command is running. (Both repositories will be locked against
writes.)
"""
if (not util.safehasattr(util, 'samefile') or
not util.safehasattr(util, 'samedevice')):
raise error.Abort(_('hardlinks are not supported on this system'))
src = hg.repository(repo.baseui, ui.expandpath(origin or 'default-relink',
origin or 'default'))
ui.status(_('relinking %s to %s\n') % (src.store.path, repo.store.path))
if repo.root == src.root:
ui.status(_('there is nothing to relink\n'))
return
if not util.samedevice(src.store.path, repo.store.path):
# No point in continuing
raise error.Abort(_('source and destination are on different devices'))
with repo.lock(), src.lock():
candidates = sorted(collect(src, ui))
targets = prune(candidates, src.store.path, repo.store.path, ui)
do_relink(src.store.path, repo.store.path, targets, ui)
def collect(src, ui):
seplen = len(os.path.sep)
candidates = []
live = len(src['tip'].manifest())
# Your average repository has some files which were deleted before
# the tip revision. We account for that by assuming that there are
# 3 tracked files for every 2 live files as of the tip version of
# the repository.
#
# mozilla-central as of 2010-06-10 had a ratio of just over 7:5.
total = live * 3 // 2
src = src.store.path
progress = ui.makeprogress(_('collecting'), unit=_('files'), total=total)
pos = 0
ui.status(_("tip has %d files, estimated total number of files: %d\n")
% (live, total))
for dirpath, dirnames, filenames in os.walk(src):
dirnames.sort()
relpath = dirpath[len(src) + seplen:]
for filename in sorted(filenames):
if filename[-2:] not in ('.d', '.i'):
continue
st = os.stat(os.path.join(dirpath, filename))
if not stat.S_ISREG(st.st_mode):
continue
pos += 1
candidates.append((os.path.join(relpath, filename), st))
progress.update(pos, item=filename)
progress.complete()
ui.status(_('collected %d candidate storage files\n') % len(candidates))
return candidates
def prune(candidates, src, dst, ui):
def linkfilter(src, dst, st):
try:
ts = os.stat(dst)
except OSError:
# Destination doesn't have this file?
return False
if util.samefile(src, dst):
return False
if not util.samedevice(src, dst):
# No point in continuing
raise error.Abort(
_('source and destination are on different devices'))
if st.st_size != ts.st_size:
return False
return st
targets = []
progress = ui.makeprogress(_('pruning'), unit=_('files'),
total=len(candidates))
pos = 0
for fn, st in candidates:
pos += 1
srcpath = os.path.join(src, fn)
tgt = os.path.join(dst, fn)
ts = linkfilter(srcpath, tgt, st)
if not ts:
ui.debug('not linkable: %s\n' % fn)
continue
targets.append((fn, ts.st_size))
progress.update(pos, item=fn)
progress.complete()
ui.status(_('pruned down to %d probably relinkable files\n') % len(targets))
return targets
def do_relink(src, dst, files, ui):
def relinkfile(src, dst):
bak = dst + '.bak'
os.rename(dst, bak)
try:
util.oslink(src, dst)
except OSError:
os.rename(bak, dst)
raise
os.remove(bak)
CHUNKLEN = 65536
relinked = 0
savedbytes = 0
progress = ui.makeprogress(_('relinking'), unit=_('files'),
total=len(files))
pos = 0
for f, sz in files:
pos += 1
source = os.path.join(src, f)
tgt = os.path.join(dst, f)
# Binary mode, so that read() works correctly, especially on Windows
sfp = open(source, 'rb')
dfp = open(tgt, 'rb')
sin = sfp.read(CHUNKLEN)
while sin:
din = dfp.read(CHUNKLEN)
if sin != din:
break
sin = sfp.read(CHUNKLEN)
sfp.close()
dfp.close()
if sin:
ui.debug('not linkable: %s\n' % f)
continue
try:
relinkfile(source, tgt)
progress.update(pos, item=f)
relinked += 1
savedbytes += sz
except OSError as inst:
ui.warn('%s: %s\n' % (tgt, stringutil.forcebytestr(inst)))
progress.complete()
ui.status(_('relinked %d files (%s reclaimed)\n') %
(relinked, util.bytecount(savedbytes)))