##// END OF EJS Templates
manifest: refer to bytestrings as bytes, not str...
manifest: refer to bytestrings as bytes, not str Required on Python 3.

File last commit:

r31324:e712a9c3 default
r31531:326bca54 default
Show More
repair.py
1102 lines | 40.9 KiB | text/x-python | PythonLexer
Matt Mackall
strip: move strip code to a new repair module
r4702 # repair.py - functions for repository repair for mercurial
#
# Copyright 2005, 2006 Chris Mason <mason@suse.com>
# Copyright 2007 Matt Mackall
#
Martin Geisler
updated license to be explicit about GPL version 2
r8225 # This software may be used and distributed according to the terms of the
Matt Mackall
Update license to GPLv2+
r10263 # GNU General Public License version 2 or any later version.
Matt Mackall
strip: move strip code to a new repair module
r4702
Gregory Szorc
repair: use absolute_import
r25970 from __future__ import absolute_import
Alain Leufroy
repair: fix missing import...
r16440 import errno
Augie Fackler
cleanup: replace uses of util.(md5|sha1|sha256|sha512) with hashlib.\1...
r29341 import hashlib
Gregory Szorc
repair: copy non-revlog store files during upgrade...
r30780 import stat
Gregory Szorc
repair: begin implementation of in-place upgrading...
r30777 import tempfile
Matt Mackall
strip: move strip code to a new repair module
r4702
Gregory Szorc
repair: use absolute_import
r25970 from .i18n import _
from .node import short
from . import (
bundle2,
changegroup,
Gregory Szorc
repair: migrate revlogs during upgrade...
r30779 changelog,
Pierre-Yves David
error: get Abort from 'error' instead of 'util'...
r26587 error,
Gregory Szorc
repair: use absolute_import
r25970 exchange,
Gregory Szorc
repair: migrate revlogs during upgrade...
r30779 manifest,
Kostia Balytskyi
obsstore: move delete function from obsstore class to repair module...
r28868 obsolete,
Gregory Szorc
repair: migrate revlogs during upgrade...
r30779 revlog,
Gregory Szorc
repair: begin implementation of in-place upgrading...
r30777 scmutil,
Gregory Szorc
repair: use absolute_import
r25970 util,
Pierre-Yves David
vfs: use 'vfs' module directly in 'mercurial.repair'...
r31232 vfs as vfsmod,
Gregory Szorc
repair: use absolute_import
r25970 )
Matt Mackall
strip: backout 73307643a09f (issue3077)
r15386 def _bundle(repo, bases, heads, node, suffix, compress=True):
Alexis S. L. Carvalho
repair.py: don't use nested functions.
r5905 """create a bundle with the specified revisions as a backup"""
Martin von Zweigbergk
repair: use cg3 for treemanifests...
r27930 cgversion = changegroup.safeversion(repo)
Eric Sumner
repair: add experimental option to write bundle2 files...
r23898
cg = changegroup.changegroupsubset(repo, bases, heads, 'strip',
version=cgversion)
FUJIWARA Katsunori
repair: make paths in "_bundle()" relative to ".hg"...
r20977 backupdir = "strip-backup"
vfs = repo.vfs
if not vfs.isdir(backupdir):
vfs.mkdir(backupdir)
Durham Goode
bundles: do not overwrite existing backup bundles (BC)...
r23835
# Include a hash of all the nodes in the filename for uniqueness
Yuya Nishihara
repair: use _hexlist() to build revset expression from binary nodes...
r25340 allcommits = repo.set('%ln::%ln', bases, heads)
Durham Goode
bundles: do not overwrite existing backup bundles (BC)...
r23835 allhashes = sorted(c.hex() for c in allcommits)
Augie Fackler
cleanup: replace uses of util.(md5|sha1|sha256|sha512) with hashlib.\1...
r29341 totalhash = hashlib.sha1(''.join(allhashes)).hexdigest()
Durham Goode
bundles: do not overwrite existing backup bundles (BC)...
r23835 name = "%s/%s-%s-%s.hg" % (backupdir, short(node), totalhash[:8], suffix)
Pierre-Yves David
strip: compress bundle2 backup using BZ...
r26425 comp = None
Pierre-Yves David
strip: use bundle2 + cg2 by default when repository use general delta...
r26423 if cgversion != '01':
Pierre-Yves David
bundle2: rename format, parts and config to final names...
r24686 bundletype = "HG20"
Pierre-Yves David
strip: compress bundle2 backup using BZ...
r26425 if compress:
comp = 'BZ'
Eric Sumner
repair: add experimental option to write bundle2 files...
r23898 elif compress:
Nicolas Dumazet
repair: do not compress partial bundle if we do not keep it on disk...
r11791 bundletype = "HG10BZ"
else:
bundletype = "HG10UN"
Martin von Zweigbergk
bundle: move writebundle() from changegroup.py to bundle2.py (API)...
r28666 return bundle2.writebundle(repo.ui, cg, name, bundletype, vfs,
Pierre-Yves David
strip: compress bundle2 backup using BZ...
r26425 compression=comp)
Matt Mackall
strip: move strip code to a new repair module
r4702
Alexis S. L. Carvalho
simplify revlog.strip interface and callers; add docstring...
r5910 def _collectfiles(repo, striprev):
"""find out the filelogs affected by the strip"""
Benoit Boissinot
repair: use set instead of dict
r8462 files = set()
Matt Mackall
strip: move strip code to a new repair module
r4702
Matt Mackall
add __len__ and __iter__ methods to repo and revlog
r6750 for x in xrange(striprev, len(repo)):
Martin Geisler
repair: bulk update sets...
r8479 files.update(repo[x].files())
Alexis S. L. Carvalho
repair.py: split stripall into two functions; clean it up a bit
r5902
Benoit Boissinot
repair: use set instead of dict
r8462 return sorted(files)
Alexis S. L. Carvalho
repair.py: split stripall into two functions; clean it up a bit
r5902
Benoit Boissinot
strip: remove usage of extranodes...
r13702 def _collectbrokencsets(repo, files, striprev):
"""return the changesets which will be broken by the truncation"""
Matt Mackall
strip: simplify collectone
r13705 s = set()
Benoit Boissinot
strip: remove usage of extranodes...
r13702 def collectone(revlog):
Durham Goode
strip: add faster revlog strip computation...
r20074 _, brokenset = revlog.getstrippoint(striprev)
s.update([revlog.linkrev(r) for r in brokenset])
Alexis S. L. Carvalho
strip: calculate list of extra nodes to save and pass it to changegroupsubset...
r5909
Durham Goode
manifest: remove last uses of repo.manifest...
r30375 collectone(repo.manifestlog._revlog)
Matt Mackall
strip: simplify collectone
r13705 for fname in files:
collectone(repo.file(fname))
Alexis S. L. Carvalho
strip: calculate list of extra nodes to save and pass it to changegroupsubset...
r5909
Matt Mackall
strip: simplify collectone
r13705 return s
Alexis S. L. Carvalho
strip: calculate list of extra nodes to save and pass it to changegroupsubset...
r5909
Jordi Gutiérrez Hermoso
strip: remove -b/--backup codepaths...
r22057 def strip(ui, repo, nodelist, backup=True, topic='backup'):
Laurent Charignon
repair: improves documentation of strip regarding locks...
r27553 # This function operates within a transaction of its own, but does
# not take any lock on the repo.
Jordi Gutiérrez Hermoso
strip: remove -b/--backup codepaths...
r22057 # Simple way to maintain backwards compatibility for this
# argument.
if backup in ['none', 'strip']:
backup = False
Pierre-Yves David
clfilter: strip logic should be unfiltered...
r18004 repo = repo.unfiltered()
Idan Kamara
localrepo: introduce destroying function
r18310 repo.destroying()
Joshua Redstone
strip: incrementally update the branchheads cache after a strip...
r17013
Alexis S. L. Carvalho
repair.py: rename chlog to cl
r5901 cl = repo.changelog
Idan Kamara
repair: remove undo files after strip
r16237 # TODO handle undo of merge sets
Wagner Bruna
strip: enhance repair.strip to receive a list of nodes (issue3299)...
r16252 if isinstance(nodelist, str):
nodelist = [nodelist]
striplist = [cl.rev(node) for node in nodelist]
striprev = min(striplist)
Matt Mackall
strip: move strip code to a new repair module
r4702
Martin von Zweigbergk
repair: combine two loops over changelog revisions...
r30707 files = _collectfiles(repo, striprev)
saverevs = _collectbrokencsets(repo, files, striprev)
Alexis S. L. Carvalho
repair.py: rewrite a loop, making it cleaner and faster
r6147 # Some revisions with rev > striprev may not be descendants of striprev.
# We have to find these revisions and put them in a bundle, so that
# we can restore them after the truncations.
# To create the bundle we use repo.changegroupsubset which requires
# the list of heads and bases of the set of interesting revisions.
# (head = revision in the set that has no descendant in the set;
# base = revision in the set that has no ancestor in the set)
Wagner Bruna
strip: enhance repair.strip to receive a list of nodes (issue3299)...
r16252 tostrip = set(striplist)
Martin von Zweigbergk
repair: combine two loops over changelog revisions...
r30707 saveheads = set(saverevs)
Martin von Zweigbergk
repair: speed up stripping of many roots...
r30706 for r in cl.revs(start=striprev + 1):
if any(p in tostrip for p in cl.parentrevs(r)):
tostrip.add(r)
Benoit Boissinot
strip: remove usage of extranodes...
r13702
if r not in tostrip:
saverevs.add(r)
saveheads.difference_update(cl.parentrevs(r))
saveheads.add(r)
saveheads = [cl.node(r) for r in saveheads]
Matt Mackall
strip: move strip code to a new repair module
r4702
Matt Mackall
strip: backout 73307643a09f (issue3077)
r15386 # compute base nodes
if saverevs:
Bryan O'Sullivan
revlog: descendants(*revs) becomes descendants(revs) (API)...
r16867 descendants = set(cl.descendants(saverevs))
Matt Mackall
strip: backout 73307643a09f (issue3077)
r15386 saverevs.difference_update(descendants)
savebases = [cl.node(r) for r in saverevs]
Wagner Bruna
strip: enhance repair.strip to receive a list of nodes (issue3299)...
r16252 stripbases = [cl.node(r) for r in tostrip]
Siddharth Agarwal
strip: make query to get new bookmark target cheaper...
r18040
# For a set s, max(parents(s) - s) is the same as max(heads(::s - s)), but
# is much faster
newbmtarget = repo.revs('max(parents(%ld) - (%ld))', tostrip, tostrip)
Augie Fackler
strip: move bookmarks to nearest ancestor rather than '.'...
r17264 if newbmtarget:
Pierre-Yves David
repair: use `first` instead of direct indexing...
r22818 newbmtarget = repo[newbmtarget.first()].node()
Augie Fackler
strip: move bookmarks to nearest ancestor rather than '.'...
r17264 else:
newbmtarget = '.'
Matt Mackall
strip: move strip code to a new repair module
r4702
Matt Mackall
bookmarks: move strip support to repair
r13362 bm = repo._bookmarks
updatebm = []
for m in bm:
rev = repo[bm[m]].rev()
if rev in tostrip:
updatebm.append(m)
Matt Mackall
strip: move strip code to a new repair module
r4702 # create a changegroup for all the branches we need to keep
Matt Mackall
strip: be quiet about temporary internal bundle
r11197 backupfile = None
FUJIWARA Katsunori
repair: make "strip()" treat bundle files via vfs...
r20979 vfs = repo.vfs
Mike Edgar
repair: define explicit local variable, don't reuse a comprehension variable...
r24252 node = nodelist[-1]
Jordi Gutiérrez Hermoso
strip: remove -b/--backup codepaths...
r22057 if backup:
Idan Kamara
repair: allow giving strip backup a different name...
r16388 backupfile = _bundle(repo, stripbases, cl.heads(), node, topic)
FUJIWARA Katsunori
repair: make "strip()" treat bundle files via vfs...
r20979 repo.ui.status(_("saved backup bundle to %s\n") %
vfs.join(backupfile))
repo.ui.log("backupbundle", "saved backup bundle to %s\n",
vfs.join(backupfile))
Martin von Zweigbergk
strip: don't use "full" and "partial" to describe bundles...
r29954 tmpbundlefile = None
Martin von Zweigbergk
strip: simplify some repeated conditions...
r29951 if saveheads:
Martin von Zweigbergk
strip: don't use "full" and "partial" to describe bundles...
r29954 # do not compress temporary bundle if we remove it from disk later
tmpbundlefile = _bundle(repo, savebases, saveheads, node, 'temp',
Jordi Gutiérrez Hermoso
strip: remove -b/--backup codepaths...
r22057 compress=False)
Matt Mackall
strip: move strip code to a new repair module
r4702
Durham Goode
manifest: remove last uses of repo.manifest...
r30375 mfst = repo.manifestlog._revlog
Henrik Stuart
strip: make repair.strip transactional to avoid repository corruption...
r8073
Pierre-Yves David
repair: forbid strip from inside a transaction...
r25300 curtr = repo.currenttransaction()
if curtr is not None:
del curtr # avoid carrying reference to transaction for nothing
msg = _('programming error: cannot strip from inside a transaction')
Pierre-Yves David
error: get Abort from 'error' instead of 'util'...
r26587 raise error.Abort(msg, hint=_('contact your extension maintainer'))
Pierre-Yves David
repair: forbid strip from inside a transaction...
r25300
Bryan O'Sullivan
with: use context manager for transaction in strip
r27873 try:
with repo.transaction("strip") as tr:
offset = len(tr.entries)
Henrik Stuart
strip: make repair.strip transactional to avoid repository corruption...
r8073
Bryan O'Sullivan
with: use context manager for transaction in strip
r27873 tr.startgroup()
cl.strip(striprev, tr)
mfst.strip(striprev, tr)
Martin von Zweigbergk
treemanifests: actually strip directory manifests...
r29464 if 'treemanifest' in repo.requirements: # safe but unnecessary
# otherwise
for unencoded, encoded, size in repo.store.datafiles():
if (unencoded.startswith('meta/') and
unencoded.endswith('00manifest.i')):
dir = unencoded[5:-12]
Durham Goode
manifest: delete unused dirlog and _newmanifest functions...
r30371 repo.manifestlog._revlog.dirlog(dir).strip(striprev, tr)
Bryan O'Sullivan
with: use context manager for transaction in strip
r27873 for fn in files:
repo.file(fn).strip(striprev, tr)
tr.endgroup()
Henrik Stuart
strip: make repair.strip transactional to avoid repository corruption...
r8073
Matt Mackall
strip: be quiet about temporary internal bundle
r11197 for i in xrange(offset, len(tr.entries)):
file, troffset, ignore = tr.entries[i]
FUJIWARA Katsunori
repair: open a file with checkambig=True to avoid file stat ambiguity...
r30001 with repo.svfs(file, 'a', checkambig=True) as fp:
fp.truncate(troffset)
Durham Goode
fncache: clean up fncache during strips...
r20885 if troffset == 0:
repo.store.markremoved(file)
Matt Mackall
strip: be quiet about temporary internal bundle
r11197
Martin von Zweigbergk
strip: don't use "full" and "partial" to describe bundles...
r29954 if tmpbundlefile:
Matt Mackall
strip: hide unbundle messages by default...
r11202 ui.note(_("adding branch\n"))
Martin von Zweigbergk
strip: don't use "full" and "partial" to describe bundles...
r29954 f = vfs.open(tmpbundlefile, "rb")
gen = exchange.readbundle(ui, f, tmpbundlefile, vfs)
Matt Mackall
strip: hide unbundle messages by default...
r11202 if not repo.ui.verbose:
# silence internal shuffling chatter
repo.ui.pushbuffer()
Eric Sumner
repair: add experimental option to write bundle2 files...
r23898 if isinstance(gen, bundle2.unbundle20):
Bryan O'Sullivan
with: use context manager for transaction in strip
r27875 with repo.transaction('strip') as tr:
tr.hookargs = {'source': 'strip',
Martin von Zweigbergk
strip: don't use "full" and "partial" to describe bundles...
r29954 'url': 'bundle:' + vfs.join(tmpbundlefile)}
Pierre-Yves David
strip: pass source and url to bundle2 processing...
r26797 bundle2.applybundle(repo, gen, tr, source='strip',
Martin von Zweigbergk
strip: don't use "full" and "partial" to describe bundles...
r29954 url='bundle:' + vfs.join(tmpbundlefile))
Eric Sumner
repair: add experimental option to write bundle2 files...
r23898 else:
Martin von Zweigbergk
strip: don't use "full" and "partial" to describe bundles...
r29954 gen.apply(repo, 'strip', 'bundle:' + vfs.join(tmpbundlefile),
True)
Matt Mackall
strip: hide unbundle messages by default...
r11202 if not repo.ui.verbose:
repo.ui.popbuffer()
Matt Mackall
strip: be quiet about temporary internal bundle
r11197 f.close()
Laurent Charignon
strip: invalidate phase cache after stripping changeset (issue5235)...
r29196 repo._phasecache.invalidate()
Matt Mackall
bookmarks: move strip support to repair
r13362
Laurent Charignon
repair: use bookmarks.recordchange instead of bookmarks.write...
r27157 for m in updatebm:
bm[m] = repo[newbmtarget].node()
lock = tr = None
try:
lock = repo.lock()
tr = repo.transaction('repair')
bm.recordchange(tr)
tr.close()
finally:
tr.release()
lock.release()
Idan Kamara
repair: remove undo files after strip
r16237 # remove undo files
FUJIWARA Katsunori
localrepo: make "undofiles()" return list of tuples "(vfs, relative filename)"...
r20975 for undovfs, undofile in repo.undofiles():
Idan Kamara
repair: remove undo files after strip
r16237 try:
FUJIWARA Katsunori
localrepo: make "undofiles()" return list of tuples "(vfs, relative filename)"...
r20975 undovfs.unlink(undofile)
Gregory Szorc
global: mass rewrite to use modern exception syntax...
r25660 except OSError as e:
Idan Kamara
repair: remove undo files after strip
r16237 if e.errno != errno.ENOENT:
FUJIWARA Katsunori
localrepo: make "undofiles()" return list of tuples "(vfs, relative filename)"...
r20975 ui.warn(_('error removing %s: %s\n') %
(undovfs.join(undofile), str(e)))
Idan Kamara
repair: remove undo files after strip
r16237
Brodie Rao
check-code: ignore naked excepts with a "re-raise" comment...
r16705 except: # re-raises
Matt Mackall
strip: be quiet about temporary internal bundle
r11197 if backupfile:
Martin von Zweigbergk
strip: don't use "full" and "partial" to describe bundles...
r29954 ui.warn(_("strip failed, backup bundle stored in '%s'\n")
FUJIWARA Katsunori
repair: make "strip()" treat bundle files via vfs...
r20979 % vfs.join(backupfile))
Martin von Zweigbergk
strip: don't use "full" and "partial" to describe bundles...
r29954 if tmpbundlefile:
Martin von Zweigbergk
strip: clarify that user action is required to recover temp bundle...
r29953 ui.warn(_("strip failed, unrecovered changes stored in '%s'\n")
Martin von Zweigbergk
strip: don't use "full" and "partial" to describe bundles...
r29954 % vfs.join(tmpbundlefile))
Martin von Zweigbergk
strip: clarify that user action is required to recover temp bundle...
r29953 ui.warn(_("(fix the problem, then recover the changesets with "
Martin von Zweigbergk
strip: don't use "full" and "partial" to describe bundles...
r29954 "\"hg unbundle '%s'\")\n") % vfs.join(tmpbundlefile))
Henrik Stuart
strip: make repair.strip transactional to avoid repository corruption...
r8073 raise
Jordi Gutiérrez Hermoso
strip: remove -b/--backup codepaths...
r22057 else:
Martin von Zweigbergk
strip: don't use "full" and "partial" to describe bundles...
r29954 if tmpbundlefile:
# Remove temporary bundle only if there were no exceptions
vfs.unlink(tmpbundlefile)
Matt Mackall
strip: move strip code to a new repair module
r4702
Pierre-Yves David
destroyed: drop complex branchcache rebuilt logic...
r18395 repo.destroyed()
Martin von Zweigbergk
repair: make strip() return backup file path...
r30274 # return the backup file path (or None if 'backup' was False) so
# extensions can use it
return backupfile
Gregory Szorc
repair: add functionality to rebuild fncache...
r25652
def rebuildfncache(ui, repo):
"""Rebuilds the fncache file from repo history.
Missing entries will be added. Extra entries will be removed.
"""
repo = repo.unfiltered()
if 'fncache' not in repo.requirements:
ui.warn(_('(not rebuilding fncache because repository does not '
Wagner Bruna
repair: fix typo in warning message
r25874 'support fncache)\n'))
Gregory Szorc
repair: add functionality to rebuild fncache...
r25652 return
Bryan O'Sullivan
with: use context manager in rebuildfncache again
r27860 with repo.lock():
Gregory Szorc
repair: add functionality to rebuild fncache...
r25652 fnc = repo.store.fncache
# Trigger load of fncache.
if 'irrelevant' in fnc:
pass
oldentries = set(fnc.entries)
newentries = set()
seenfiles = set()
repolen = len(repo)
for rev in repo:
av6
repair: specify unit for ui.progress in rebuildfncache()
r28466 ui.progress(_('rebuilding'), rev, total=repolen,
unit=_('changesets'))
Gregory Szorc
repair: add functionality to rebuild fncache...
r25652
ctx = repo[rev]
for f in ctx.files():
# This is to minimize I/O.
if f in seenfiles:
continue
seenfiles.add(f)
i = 'data/%s.i' % f
d = 'data/%s.d' % f
if repo.store._exists(i):
newentries.add(i)
if repo.store._exists(d):
newentries.add(d)
av6
repair: use 'rebuilding' progress topic in rebuildfncache()
r28465 ui.progress(_('rebuilding'), None)
Gregory Szorc
repair: add functionality to rebuild fncache...
r25652
Martin von Zweigbergk
treemanifest: fix debugrebuildfncache...
r28031 if 'treemanifest' in repo.requirements: # safe but unnecessary otherwise
Martin von Zweigbergk
treemanifests: fix streaming clone...
r28007 for dir in util.dirs(seenfiles):
i = 'meta/%s/00manifest.i' % dir
d = 'meta/%s/00manifest.d' % dir
if repo.store._exists(i):
newentries.add(i)
if repo.store._exists(d):
newentries.add(d)
Gregory Szorc
repair: add functionality to rebuild fncache...
r25652 addcount = len(newentries - oldentries)
removecount = len(oldentries - newentries)
for p in sorted(oldentries - newentries):
ui.write(_('removing %s\n') % p)
for p in sorted(newentries - oldentries):
ui.write(_('adding %s\n') % p)
if addcount or removecount:
ui.write(_('%d items added, %d removed from fncache\n') %
(addcount, removecount))
fnc.entries = newentries
fnc._dirty = True
Bryan O'Sullivan
with: use context manager in rebuildfncache
r27871 with repo.transaction('fncache') as tr:
Gregory Szorc
repair: add functionality to rebuild fncache...
r25652 fnc.write(tr)
else:
ui.write(_('fncache already up to date\n'))
Ryan McElroy
strip: factor out revset calculation for strip -B...
r26624 def stripbmrevset(repo, mark):
"""
The revset to strip when strip is called with -B mark
Needs to live here so extensions can use it and wrap it even when strip is
not enabled or not present on a box.
"""
return repo.revs("ancestors(bookmark(%s)) - "
"ancestors(head() and not bookmark(%s)) - "
"ancestors(bookmark() and not bookmark(%s))",
mark, mark, mark)
Kostia Balytskyi
obsstore: move delete function from obsstore class to repair module...
r28868
def deleteobsmarkers(obsstore, indices):
"""Delete some obsmarkers from obsstore and return how many were deleted
'indices' is a list of ints which are the indices
of the markers to be deleted.
Every invocation of this function completely rewrites the obsstore file,
skipping the markers we want to be removed. The new temporary file is
created, remaining markers are written there and on .close() this file
gets atomically renamed to obsstore, thus guaranteeing consistency."""
if not indices:
# we don't want to rewrite the obsstore with the same content
return
left = []
current = obsstore._all
n = 0
for i, m in enumerate(current):
if i in indices:
n += 1
continue
left.append(m)
newobsstorefile = obsstore.svfs('obsstore', 'w', atomictemp=True)
for bytes in obsolete.encodemarkers(left, True, obsstore._version):
newobsstorefile.write(bytes)
newobsstorefile.close()
return n
Gregory Szorc
repair: implement requirements checking for upgrades...
r30775
def upgraderequiredsourcerequirements(repo):
"""Obtain requirements required to be present to upgrade a repo.
An upgrade will not be allowed if the repository doesn't have the
requirements returned by this function.
"""
return set([
# Introduced in Mercurial 0.9.2.
'revlogv1',
# Introduced in Mercurial 0.9.2.
'store',
])
def upgradeblocksourcerequirements(repo):
"""Obtain requirements that will prevent an upgrade from occurring.
An upgrade cannot be performed if the source repository contains a
requirements in the returned set.
"""
return set([
# The upgrade code does not yet support these experimental features.
# This is an artificial limitation.
'manifestv2',
'treemanifest',
# This was a precursor to generaldelta and was never enabled by default.
# It should (hopefully) not exist in the wild.
'parentdelta',
# Upgrade should operate on the actual store, not the shared link.
'shared',
])
def upgradesupportremovedrequirements(repo):
"""Obtain requirements that can be removed during an upgrade.
If an upgrade were to create a repository that dropped a requirement,
the dropped requirement must appear in the returned set for the upgrade
to be allowed.
"""
return set()
def upgradesupporteddestrequirements(repo):
"""Obtain requirements that upgrade supports in the destination.
If the result of the upgrade would create requirements not in this set,
the upgrade is disallowed.
Extensions should monkeypatch this to add their custom requirements.
"""
return set([
'dotencode',
'fncache',
'generaldelta',
'revlogv1',
'store',
])
def upgradeallowednewrequirements(repo):
"""Obtain requirements that can be added to a repository during upgrade.
This is used to disallow proposed requirements from being added when
they weren't present before.
We use a list of allowed requirement additions instead of a list of known
bad additions because the whitelist approach is safer and will prevent
future, unknown requirements from accidentally being added.
"""
return set([
'dotencode',
'fncache',
'generaldelta',
])
Gregory Szorc
repair: determine what upgrade will do...
r30776 deficiency = 'deficiency'
optimisation = 'optimization'
class upgradeimprovement(object):
"""Represents an improvement that can be made as part of an upgrade.
The following attributes are defined on each instance:
name
Machine-readable string uniquely identifying this improvement. It
will be mapped to an action later in the upgrade process.
type
Either ``deficiency`` or ``optimisation``. A deficiency is an obvious
problem. An optimization is an action (sometimes optional) that
can be taken to further improve the state of the repository.
description
Message intended for humans explaining the improvement in more detail,
including the implications of it. For ``deficiency`` types, should be
worded in the present tense. For ``optimisation`` types, should be
worded in the future tense.
upgrademessage
Message intended for humans explaining what an upgrade addressing this
issue will do. Should be worded in the future tense.
fromdefault (``deficiency`` types only)
Boolean indicating whether the current (deficient) state deviates
from Mercurial's default configuration.
fromconfig (``deficiency`` types only)
Boolean indicating whether the current (deficient) state deviates
from the current Mercurial configuration.
"""
def __init__(self, name, type, description, upgrademessage, **kwargs):
self.name = name
self.type = type
self.description = description
self.upgrademessage = upgrademessage
for k, v in kwargs.items():
setattr(self, k, v)
def upgradefindimprovements(repo):
"""Determine improvements that can be made to the repo during upgrade.
Returns a list of ``upgradeimprovement`` describing repository deficiencies
and optimizations.
"""
# Avoid cycle: cmdutil -> repair -> localrepo -> cmdutil
from . import localrepo
newreporeqs = localrepo.newreporequirements(repo)
improvements = []
# We could detect lack of revlogv1 and store here, but they were added
# in 0.9.2 and we don't support upgrading repos without these
# requirements, so let's not bother.
if 'fncache' not in repo.requirements:
improvements.append(upgradeimprovement(
name='fncache',
type=deficiency,
description=_('long and reserved filenames may not work correctly; '
'repository performance is sub-optimal'),
upgrademessage=_('repository will be more resilient to storing '
'certain paths and performance of certain '
'operations should be improved'),
fromdefault=True,
fromconfig='fncache' in newreporeqs))
if 'dotencode' not in repo.requirements:
improvements.append(upgradeimprovement(
name='dotencode',
type=deficiency,
description=_('storage of filenames beginning with a period or '
'space may not work correctly'),
upgrademessage=_('repository will be better able to store files '
'beginning with a space or period'),
fromdefault=True,
fromconfig='dotencode' in newreporeqs))
if 'generaldelta' not in repo.requirements:
improvements.append(upgradeimprovement(
name='generaldelta',
type=deficiency,
description=_('deltas within internal storage are unable to '
'choose optimal revisions; repository is larger and '
'slower than it could be; interaction with other '
'repositories may require extra network and CPU '
'resources, making "hg push" and "hg pull" slower'),
upgrademessage=_('repository storage will be able to create '
'optimal deltas; new repository data will be '
'smaller and read times should decrease; '
'interacting with other repositories using this '
'storage model should require less network and '
'CPU resources, making "hg push" and "hg pull" '
'faster'),
fromdefault=True,
fromconfig='generaldelta' in newreporeqs))
# Mercurial 4.0 changed changelogs to not use delta chains. Search for
# changelogs with deltas.
cl = repo.changelog
for rev in cl:
chainbase = cl.chainbase(rev)
if chainbase != rev:
improvements.append(upgradeimprovement(
name='removecldeltachain',
type=deficiency,
description=_('changelog storage is using deltas instead of '
'raw entries; changelog reading and any '
'operation relying on changelog data are slower '
'than they could be'),
upgrademessage=_('changelog storage will be reformated to '
'store raw entries; changelog reading will be '
'faster; changelog size may be reduced'),
fromdefault=True,
fromconfig=True))
break
# Now for the optimizations.
# These are unconditionally added. There is logic later that figures out
# which ones to apply.
improvements.append(upgradeimprovement(
name='redeltaparent',
type=optimisation,
description=_('deltas within internal storage will be recalculated to '
'choose an optimal base revision where this was not '
'already done; the size of the repository may shrink and '
'various operations may become faster; the first time '
'this optimization is performed could slow down upgrade '
'execution considerably; subsequent invocations should '
'not run noticeably slower'),
upgrademessage=_('deltas within internal storage will choose a new '
'base revision if needed')))
improvements.append(upgradeimprovement(
name='redeltamultibase',
type=optimisation,
description=_('deltas within internal storage will be recalculated '
'against multiple base revision and the smallest '
'difference will be used; the size of the repository may '
'shrink significantly when there are many merges; this '
'optimization will slow down execution in proportion to '
'the number of merges in the repository and the amount '
'of files in the repository; this slow down should not '
'be significant unless there are tens of thousands of '
'files and thousands of merges'),
upgrademessage=_('deltas within internal storage will choose an '
'optimal delta by computing deltas against multiple '
'parents; may slow down execution time '
'significantly')))
improvements.append(upgradeimprovement(
name='redeltaall',
type=optimisation,
description=_('deltas within internal storage will always be '
'recalculated without reusing prior deltas; this will '
'likely make execution run several times slower; this '
'optimization is typically not needed'),
upgrademessage=_('deltas within internal storage will be fully '
'recomputed; this will likely drastically slow down '
'execution time')))
return improvements
def upgradedetermineactions(repo, improvements, sourcereqs, destreqs,
optimize):
"""Determine upgrade actions that will be performed.
Given a list of improvements as returned by ``upgradefindimprovements``,
determine the list of upgrade actions that will be performed.
The role of this function is to filter improvements if needed, apply
recommended optimizations from the improvements list that make sense,
etc.
Returns a list of action names.
"""
newactions = []
knownreqs = upgradesupporteddestrequirements(repo)
for i in improvements:
name = i.name
# If the action is a requirement that doesn't show up in the
# destination requirements, prune the action.
if name in knownreqs and name not in destreqs:
continue
if i.type == deficiency:
newactions.append(name)
newactions.extend(o for o in sorted(optimize) if o not in newactions)
# FUTURE consider adding some optimizations here for certain transitions.
# e.g. adding generaldelta could schedule parent redeltas.
return newactions
Gregory Szorc
repair: migrate revlogs during upgrade...
r30779 def _revlogfrompath(repo, path):
"""Obtain a revlog from a repo path.
An instance of the appropriate class is returned.
"""
if path == '00changelog.i':
return changelog.changelog(repo.svfs)
elif path.endswith('00manifest.i'):
mandir = path[:-len('00manifest.i')]
return manifest.manifestrevlog(repo.svfs, dir=mandir)
else:
# Filelogs don't do anything special with settings. So we can use a
# vanilla revlog.
return revlog.revlog(repo.svfs, path)
def _copyrevlogs(ui, srcrepo, dstrepo, tr, deltareuse, aggressivemergedeltas):
"""Copy revlogs between 2 repos."""
revcount = 0
srcsize = 0
srcrawsize = 0
dstsize = 0
fcount = 0
frevcount = 0
fsrcsize = 0
frawsize = 0
fdstsize = 0
mcount = 0
mrevcount = 0
msrcsize = 0
mrawsize = 0
mdstsize = 0
crevcount = 0
csrcsize = 0
crawsize = 0
cdstsize = 0
# Perform a pass to collect metadata. This validates we can open all
# source files and allows a unified progress bar to be displayed.
for unencoded, encoded, size in srcrepo.store.walk():
if unencoded.endswith('.d'):
continue
rl = _revlogfrompath(srcrepo, unencoded)
revcount += len(rl)
datasize = 0
rawsize = 0
idx = rl.index
for rev in rl:
e = idx[rev]
datasize += e[1]
rawsize += e[2]
srcsize += datasize
srcrawsize += rawsize
# This is for the separate progress bars.
if isinstance(rl, changelog.changelog):
crevcount += len(rl)
csrcsize += datasize
crawsize += rawsize
elif isinstance(rl, manifest.manifestrevlog):
mcount += 1
mrevcount += len(rl)
msrcsize += datasize
mrawsize += rawsize
elif isinstance(rl, revlog.revlog):
fcount += 1
frevcount += len(rl)
fsrcsize += datasize
frawsize += rawsize
if not revcount:
return
ui.write(_('migrating %d total revisions (%d in filelogs, %d in manifests, '
'%d in changelog)\n') %
(revcount, frevcount, mrevcount, crevcount))
ui.write(_('migrating %s in store; %s tracked data\n') % (
(util.bytecount(srcsize), util.bytecount(srcrawsize))))
# Used to keep track of progress.
progress = []
def oncopiedrevision(rl, rev, node):
progress[1] += 1
srcrepo.ui.progress(progress[0], progress[1], total=progress[2])
# Do the actual copying.
# FUTURE this operation can be farmed off to worker processes.
seen = set()
for unencoded, encoded, size in srcrepo.store.walk():
if unencoded.endswith('.d'):
continue
oldrl = _revlogfrompath(srcrepo, unencoded)
newrl = _revlogfrompath(dstrepo, unencoded)
if isinstance(oldrl, changelog.changelog) and 'c' not in seen:
ui.write(_('finished migrating %d manifest revisions across %d '
'manifests; change in size: %s\n') %
(mrevcount, mcount, util.bytecount(mdstsize - msrcsize)))
ui.write(_('migrating changelog containing %d revisions '
'(%s in store; %s tracked data)\n') %
(crevcount, util.bytecount(csrcsize),
util.bytecount(crawsize)))
seen.add('c')
progress[:] = [_('changelog revisions'), 0, crevcount]
elif isinstance(oldrl, manifest.manifestrevlog) and 'm' not in seen:
ui.write(_('finished migrating %d filelog revisions across %d '
'filelogs; change in size: %s\n') %
(frevcount, fcount, util.bytecount(fdstsize - fsrcsize)))
ui.write(_('migrating %d manifests containing %d revisions '
'(%s in store; %s tracked data)\n') %
(mcount, mrevcount, util.bytecount(msrcsize),
util.bytecount(mrawsize)))
seen.add('m')
progress[:] = [_('manifest revisions'), 0, mrevcount]
elif 'f' not in seen:
ui.write(_('migrating %d filelogs containing %d revisions '
'(%s in store; %s tracked data)\n') %
(fcount, frevcount, util.bytecount(fsrcsize),
util.bytecount(frawsize)))
seen.add('f')
progress[:] = [_('file revisions'), 0, frevcount]
ui.progress(progress[0], progress[1], total=progress[2])
ui.note(_('cloning %d revisions from %s\n') % (len(oldrl), unencoded))
oldrl.clone(tr, newrl, addrevisioncb=oncopiedrevision,
deltareuse=deltareuse,
aggressivemergedeltas=aggressivemergedeltas)
datasize = 0
idx = newrl.index
for rev in newrl:
datasize += idx[rev][1]
dstsize += datasize
if isinstance(newrl, changelog.changelog):
cdstsize += datasize
elif isinstance(newrl, manifest.manifestrevlog):
mdstsize += datasize
else:
fdstsize += datasize
ui.progress(progress[0], None)
ui.write(_('finished migrating %d changelog revisions; change in size: '
'%s\n') % (crevcount, util.bytecount(cdstsize - csrcsize)))
ui.write(_('finished migrating %d total revisions; total change in store '
'size: %s\n') % (revcount, util.bytecount(dstsize - srcsize)))
Gregory Szorc
repair: copy non-revlog store files during upgrade...
r30780 def _upgradefilterstorefile(srcrepo, dstrepo, requirements, path, mode, st):
"""Determine whether to copy a store file during upgrade.
This function is called when migrating store files from ``srcrepo`` to
``dstrepo`` as part of upgrading a repository.
Args:
srcrepo: repo we are copying from
dstrepo: repo we are copying to
requirements: set of requirements for ``dstrepo``
path: store file being examined
mode: the ``ST_MODE`` file type of ``path``
st: ``stat`` data structure for ``path``
Function should return ``True`` if the file is to be copied.
"""
# Skip revlogs.
if path.endswith(('.i', '.d')):
return False
# Skip transaction related files.
if path.startswith('undo'):
return False
# Only copy regular files.
if mode != stat.S_IFREG:
return False
# Skip other skipped files.
if path in ('lock', 'fncache'):
return False
return True
def _upgradefinishdatamigration(ui, srcrepo, dstrepo, requirements):
"""Hook point for extensions to perform additional actions during upgrade.
This function is called after revlogs and store files have been copied but
before the new store is swapped into the original location.
"""
Gregory Szorc
repair: begin implementation of in-place upgrading...
r30777 def _upgraderepo(ui, srcrepo, dstrepo, requirements, actions):
"""Do the low-level work of upgrading a repository.
The upgrade is effectively performed as a copy between a source
repository and a temporary destination repository.
The source repository is unmodified for as long as possible so the
upgrade can abort at any time without causing loss of service for
readers and without corrupting the source repository.
"""
assert srcrepo.currentwlock()
assert dstrepo.currentwlock()
Gregory Szorc
repair: migrate revlogs during upgrade...
r30779 ui.write(_('(it is safe to interrupt this process any time before '
'data migration completes)\n'))
if 'redeltaall' in actions:
deltareuse = revlog.revlog.DELTAREUSENEVER
elif 'redeltaparent' in actions:
deltareuse = revlog.revlog.DELTAREUSESAMEREVS
elif 'redeltamultibase' in actions:
deltareuse = revlog.revlog.DELTAREUSESAMEREVS
else:
deltareuse = revlog.revlog.DELTAREUSEALWAYS
with dstrepo.transaction('upgrade') as tr:
_copyrevlogs(ui, srcrepo, dstrepo, tr, deltareuse,
'redeltamultibase' in actions)
Gregory Szorc
repair: copy non-revlog store files during upgrade...
r30780 # Now copy other files in the store directory.
for p, kind, st in srcrepo.store.vfs.readdir('', stat=True):
if not _upgradefilterstorefile(srcrepo, dstrepo, requirements,
p, kind, st):
continue
srcrepo.ui.write(_('copying %s\n') % p)
src = srcrepo.store.vfs.join(p)
dst = dstrepo.store.vfs.join(p)
util.copyfile(src, dst, copystat=True)
_upgradefinishdatamigration(ui, srcrepo, dstrepo, requirements)
Gregory Szorc
repair: migrate revlogs during upgrade...
r30779
ui.write(_('data fully migrated to temporary repository\n'))
Gregory Szorc
repair: begin implementation of in-place upgrading...
r30777
backuppath = tempfile.mkdtemp(prefix='upgradebackup.', dir=srcrepo.path)
Pierre-Yves David
vfs: use 'vfs' module directly in 'mercurial.repair'...
r31232 backupvfs = vfsmod.vfs(backuppath)
Gregory Szorc
repair: begin implementation of in-place upgrading...
r30777
# Make a backup of requires file first, as it is the first to be modified.
Pierre-Yves David
repair: directly use repo.vfs.join...
r31324 util.copyfile(srcrepo.vfs.join('requires'), backupvfs.join('requires'))
Gregory Szorc
repair: begin implementation of in-place upgrading...
r30777
# We install an arbitrary requirement that clients must not support
# as a mechanism to lock out new clients during the data swap. This is
# better than allowing a client to continue while the repository is in
# an inconsistent state.
ui.write(_('marking source repository as being upgraded; clients will be '
'unable to read from repository\n'))
scmutil.writerequires(srcrepo.vfs,
srcrepo.requirements | set(['upgradeinprogress']))
ui.write(_('starting in-place swap of repository data\n'))
ui.write(_('replaced files will be backed up at %s\n') %
backuppath)
Gregory Szorc
repair: migrate revlogs during upgrade...
r30779 # Now swap in the new store directory. Doing it as a rename should make
# the operation nearly instantaneous and atomic (at least in well-behaved
# environments).
ui.write(_('replacing store...\n'))
Simon Farnsworth
mercurial: switch to util.timer for all interval timings...
r30975 tstart = util.timer()
Gregory Szorc
repair: migrate revlogs during upgrade...
r30779 util.rename(srcrepo.spath, backupvfs.join('store'))
util.rename(dstrepo.spath, srcrepo.spath)
Simon Farnsworth
mercurial: switch to util.timer for all interval timings...
r30975 elapsed = util.timer() - tstart
Gregory Szorc
repair: migrate revlogs during upgrade...
r30779 ui.write(_('store replacement complete; repository was inconsistent for '
'%0.1fs\n') % elapsed)
Gregory Szorc
repair: begin implementation of in-place upgrading...
r30777
# We first write the requirements file. Any new requirements will lock
# out legacy clients.
ui.write(_('finalizing requirements file and making repository readable '
'again\n'))
scmutil.writerequires(srcrepo.vfs, requirements)
Gregory Szorc
repair: clean up stale lock file from store backup...
r30781 # The lock file from the old store won't be removed because nothing has a
# reference to its new location. So clean it up manually. Alternatively, we
# could update srcrepo.svfs and other variables to point to the new
# location. This is simpler.
backupvfs.unlink('store/lock')
Gregory Szorc
repair: begin implementation of in-place upgrading...
r30777 return backuppath
Gregory Szorc
repair: implement requirements checking for upgrades...
r30775 def upgraderepo(ui, repo, run=False, optimize=None):
"""Upgrade a repository in place."""
# Avoid cycle: cmdutil -> repair -> localrepo -> cmdutil
from . import localrepo
Gregory Szorc
repair: determine what upgrade will do...
r30776 optimize = set(optimize or [])
Gregory Szorc
repair: implement requirements checking for upgrades...
r30775 repo = repo.unfiltered()
# Ensure the repository can be upgraded.
missingreqs = upgraderequiredsourcerequirements(repo) - repo.requirements
if missingreqs:
raise error.Abort(_('cannot upgrade repository; requirement '
'missing: %s') % _(', ').join(sorted(missingreqs)))
blockedreqs = upgradeblocksourcerequirements(repo) & repo.requirements
if blockedreqs:
raise error.Abort(_('cannot upgrade repository; unsupported source '
'requirement: %s') %
_(', ').join(sorted(blockedreqs)))
# FUTURE there is potentially a need to control the wanted requirements via
# command arguments or via an extension hook point.
newreqs = localrepo.newreporequirements(repo)
noremovereqs = (repo.requirements - newreqs -
upgradesupportremovedrequirements(repo))
if noremovereqs:
raise error.Abort(_('cannot upgrade repository; requirement would be '
'removed: %s') % _(', ').join(sorted(noremovereqs)))
noaddreqs = (newreqs - repo.requirements -
upgradeallowednewrequirements(repo))
if noaddreqs:
raise error.Abort(_('cannot upgrade repository; do not support adding '
'requirement: %s') %
_(', ').join(sorted(noaddreqs)))
unsupportedreqs = newreqs - upgradesupporteddestrequirements(repo)
if unsupportedreqs:
raise error.Abort(_('cannot upgrade repository; do not support '
'destination requirement: %s') %
_(', ').join(sorted(unsupportedreqs)))
Gregory Szorc
repair: determine what upgrade will do...
r30776 # Find and validate all improvements that can be made.
improvements = upgradefindimprovements(repo)
for i in improvements:
if i.type not in (deficiency, optimisation):
raise error.Abort(_('unexpected improvement type %s for %s') % (
i.type, i.name))
# Validate arguments.
unknownoptimize = optimize - set(i.name for i in improvements
if i.type == optimisation)
if unknownoptimize:
raise error.Abort(_('unknown optimization action requested: %s') %
', '.join(sorted(unknownoptimize)),
hint=_('run without arguments to see valid '
'optimizations'))
actions = upgradedetermineactions(repo, improvements, repo.requirements,
newreqs, optimize)
Gregory Szorc
repair: implement requirements checking for upgrades...
r30775 def printrequirements():
ui.write(_('requirements\n'))
ui.write(_(' preserved: %s\n') %
_(', ').join(sorted(newreqs & repo.requirements)))
if repo.requirements - newreqs:
ui.write(_(' removed: %s\n') %
_(', ').join(sorted(repo.requirements - newreqs)))
if newreqs - repo.requirements:
ui.write(_(' added: %s\n') %
_(', ').join(sorted(newreqs - repo.requirements)))
ui.write('\n')
Gregory Szorc
repair: determine what upgrade will do...
r30776 def printupgradeactions():
for action in actions:
for i in improvements:
if i.name == action:
ui.write('%s\n %s\n\n' %
(i.name, i.upgrademessage))
Gregory Szorc
repair: implement requirements checking for upgrades...
r30775 if not run:
Gregory Szorc
repair: determine what upgrade will do...
r30776 fromdefault = []
fromconfig = []
optimizations = []
for i in improvements:
assert i.type in (deficiency, optimisation)
if i.type == deficiency:
if i.fromdefault:
fromdefault.append(i)
if i.fromconfig:
fromconfig.append(i)
else:
optimizations.append(i)
if fromdefault or fromconfig:
fromconfignames = set(x.name for x in fromconfig)
onlydefault = [i for i in fromdefault
if i.name not in fromconfignames]
if fromconfig:
ui.write(_('repository lacks features recommended by '
'current config options:\n\n'))
for i in fromconfig:
ui.write('%s\n %s\n\n' % (i.name, i.description))
if onlydefault:
ui.write(_('repository lacks features used by the default '
'config options:\n\n'))
for i in onlydefault:
ui.write('%s\n %s\n\n' % (i.name, i.description))
ui.write('\n')
else:
ui.write(_('(no feature deficiencies found in existing '
'repository)\n'))
Gregory Szorc
repair: implement requirements checking for upgrades...
r30775 ui.write(_('performing an upgrade with "--run" will make the following '
'changes:\n\n'))
printrequirements()
Gregory Szorc
repair: determine what upgrade will do...
r30776 printupgradeactions()
unusedoptimize = [i for i in improvements
if i.name not in actions and i.type == optimisation]
if unusedoptimize:
ui.write(_('additional optimizations are available by specifying '
'"--optimize <name>":\n\n'))
for i in unusedoptimize:
ui.write(_('%s\n %s\n\n') % (i.name, i.description))
Gregory Szorc
repair: begin implementation of in-place upgrading...
r30777 return
# Else we're in the run=true case.
ui.write(_('upgrade will perform the following actions:\n\n'))
printrequirements()
printupgradeactions()
ui.write(_('beginning upgrade...\n'))
with repo.wlock():
with repo.lock():
ui.write(_('repository locked and read-only\n'))
# Our strategy for upgrading the repository is to create a new,
# temporary repository, write data to it, then do a swap of the
# data. There are less heavyweight ways to do this, but it is easier
# to create a new repo object than to instantiate all the components
# (like the store) separately.
tmppath = tempfile.mkdtemp(prefix='upgrade.', dir=repo.path)
backuppath = None
try:
ui.write(_('creating temporary repository to stage migrated '
'data: %s\n') % tmppath)
dstrepo = localrepo.localrepository(repo.baseui,
path=tmppath,
create=True)
with dstrepo.wlock():
with dstrepo.lock():
backuppath = _upgraderepo(ui, repo, dstrepo, newreqs,
actions)
finally:
ui.write(_('removing temporary repository %s\n') % tmppath)
repo.vfs.rmtree(tmppath, forcibly=True)
if backuppath:
ui.warn(_('copy of old repository backed up at %s\n') %
backuppath)
ui.warn(_('the old repository will not be deleted; remove '
'it to free up disk space once the upgraded '
'repository is verified\n'))