verify: start to abstract file verification
Currently, the file storage interface has a handful of attributes
that are exclusively or near-exclusively used by repo verification
code. In order to support verification on non-revlog/alternate
storage backends, we'll need to abstract verification so it can
be performed in a storage-agnostic way.
This commit starts that process.
We establish a new verifyintegrity() method on revlogs and expose
it to the file storage interface. Most of verify.verifier.checklog()
has been ported to this new method.
We need a way to represent verification problems. So we invent an
interface to represent a verification problem, invent a revlog type
to implement that interface, and use it.
The arguments to verifyintegrity() will almost certainly change in
the future, once more functionality is ported from the verify code.
And the "revlogv1" version check is very hacky. (The code in verify
is actually buggy because it is comparing the full 32-bit header
integer instead of just the revlog version short. I'll likely fix
this in a subsequent commit.)
Differential Revision: https://phab.mercurial-scm.org/D4701
# 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)))