upgrade: support upgrade to/from zstd storage (issue6088)

Now that we have an official config option for a shiny format improvement, we
better make it simple to migrate to/from it.

mercurial/upgrade.py

@@ -1,955 +1,980
 # upgrade.py - functions for in place upgrade of Mercurial repository
 #
 # Copyright (c) 2016-present, Gregory Szorc
 #
 # 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 stat
 
 from .i18n import _
 from . import (
     changelog,
     error,
     filelog,
     hg,
     localrepo,
     manifest,
     pycompat,
     revlog,
     scmutil,
     util,
     vfs as vfsmod,
 )
 
+from .utils import (
+    compression,
+)
+
 def requiredsourcerequirements(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 {
         # Introduced in Mercurial 0.9.2.
         'revlogv1',
         # Introduced in Mercurial 0.9.2.
         'store',
     }
 
 def blocksourcerequirements(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 {
         # The upgrade code does not yet support these experimental features.
         # This is an artificial limitation.
         '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 supportremovedrequirements(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 {
+    supported = {
         localrepo.SPARSEREVLOG_REQUIREMENT,
     }
+    for name in compression.compengines:
+        engine = compression.compengines[name]
+        if engine.available() and engine.revlogheader():
+            supported.add(b'exp-compression-%s' % name)
+            if engine.name() == 'zstd':
+                supported.add(b'revlog-compression-zstd')
+    return supported
 
 def supporteddestrequirements(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 {
+    supported = {
         'dotencode',
         'fncache',
         'generaldelta',
         'revlogv1',
         'store',
         localrepo.SPARSEREVLOG_REQUIREMENT,
     }
+    for name in compression.compengines:
+        engine = compression.compengines[name]
+        if engine.available() and engine.revlogheader():
+            supported.add(b'exp-compression-%s' % name)
+            if engine.name() == 'zstd':
+                supported.add(b'revlog-compression-zstd')
+    return supported
 
 def allowednewrequirements(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 {
+    supported = {
         'dotencode',
         'fncache',
         'generaldelta',
         localrepo.SPARSEREVLOG_REQUIREMENT,
     }
+    for name in compression.compengines:
+        engine = compression.compengines[name]
+        if engine.available() and engine.revlogheader():
+            supported.add(b'exp-compression-%s' % name)
+            if engine.name() == 'zstd':
+                supported.add(b'revlog-compression-zstd')
+    return supported
 
 def preservedrequirements(repo):
     return set()
 
 deficiency = 'deficiency'
 optimisation = 'optimization'
 
 class improvement(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.
     """
     def __init__(self, name, type, description, upgrademessage):
         self.name = name
         self.type = type
         self.description = description
         self.upgrademessage = upgrademessage
 
     def __eq__(self, other):
         if not isinstance(other, improvement):
             # This is what python tell use to do
             return NotImplemented
         return self.name == other.name
 
     def __ne__(self, other):
         return not (self == other)
 
     def __hash__(self):
         return hash(self.name)
 
 allformatvariant = []
 
 def registerformatvariant(cls):
     allformatvariant.append(cls)
     return cls
 
 class formatvariant(improvement):
     """an improvement subclass dedicated to repository format"""
     type = deficiency
     ### The following attributes should be defined for each class:
 
     # machine-readable string uniquely identifying this improvement. it will be
     # mapped to an action later in the upgrade process.
     name = None
 
     # message intended for humans explaining the improvement in more detail,
     # including the implications of it ``deficiency`` types, should be worded
     # in the present tense.
     description = None
 
     # message intended for humans explaining what an upgrade addressing this
     # issue will do. should be worded in the future tense.
     upgrademessage = None
 
     # value of current Mercurial default for new repository
     default = None
 
     def __init__(self):
         raise NotImplementedError()
 
     @staticmethod
     def fromrepo(repo):
         """current value of the variant in the repository"""
         raise NotImplementedError()
 
     @staticmethod
     def fromconfig(repo):
         """current value of the variant in the configuration"""
         raise NotImplementedError()
 
 class requirementformatvariant(formatvariant):
     """formatvariant based on a 'requirement' name.
 
     Many format variant are controlled by a 'requirement'. We define a small
     subclass to factor the code.
     """
 
     # the requirement that control this format variant
     _requirement = None
 
     @staticmethod
     def _newreporequirements(ui):
         return localrepo.newreporequirements(
             ui, localrepo.defaultcreateopts(ui))
 
     @classmethod
     def fromrepo(cls, repo):
         assert cls._requirement is not None
         return cls._requirement in repo.requirements
 
     @classmethod
     def fromconfig(cls, repo):
         assert cls._requirement is not None
         return cls._requirement in cls._newreporequirements(repo.ui)
 
 @registerformatvariant
 class fncache(requirementformatvariant):
     name = 'fncache'
 
     _requirement = 'fncache'
 
     default = True
 
     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')
 
 @registerformatvariant
 class dotencode(requirementformatvariant):
     name = 'dotencode'
 
     _requirement = 'dotencode'
 
     default = True
 
     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')
 
 @registerformatvariant
 class generaldelta(requirementformatvariant):
     name = 'generaldelta'
 
     _requirement = 'generaldelta'
 
     default = True
 
     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')
 
 @registerformatvariant
 class sparserevlog(requirementformatvariant):
     name = 'sparserevlog'
 
     _requirement = localrepo.SPARSEREVLOG_REQUIREMENT
 
     default = True
 
     description = _('in order to limit disk reading and memory usage on older '
                     'version, the span of a delta chain from its root to its '
                     'end is limited, whatever the relevant data in this span. '
                     'This can severly limit Mercurial ability to build good '
                     'chain of delta resulting is much more storage space being '
                     'taken and limit reusability of on disk delta during '
                     'exchange.'
                    )
 
     upgrademessage = _('Revlog supports delta chain with more unused data '
                        'between payload. These gaps will be skipped at read '
                        'time. This allows for better delta chains, making a '
                        'better compression and faster exchange with server.')
 
 @registerformatvariant
 class removecldeltachain(formatvariant):
     name = 'plain-cl-delta'
 
     default = True
 
     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')
 
     @staticmethod
     def fromrepo(repo):
         # Mercurial 4.0 changed changelogs to not use delta chains. Search for
         # changelogs with deltas.
         cl = repo.changelog
         chainbase = cl.chainbase
         return all(rev == chainbase(rev) for rev in cl)
 
     @staticmethod
     def fromconfig(repo):
         return True
 
 @registerformatvariant
 class compressionengine(formatvariant):
     name = 'compression'
     default = 'zlib'
 
     description = _('Compresion algorithm used to compress data. '
                     'Some engine are faster than other')
 
     upgrademessage = _('revlog content will be recompressed with the new '
                        'algorithm.')
 
     @classmethod
     def fromrepo(cls, repo):
         # we allow multiple compression engine requirement to co-exist because
         # strickly speaking, revlog seems to support mixed compression style.
         #
         # The compression used for new entries will be "the last one"
         compression = 'zlib'
         for req in repo.requirements:
             prefix = req.startswith
             if prefix('revlog-compression-') or prefix('exp-compression-'):
                 compression = req.split('-', 2)[2]
         return compression
 
     @classmethod
     def fromconfig(cls, repo):
         return repo.ui.config('format', 'revlog-compression')
 
 @registerformatvariant
 class compressionlevel(formatvariant):
     name = 'compression-level'
     default = 'default'
 
     description = _('compression level')
 
     upgrademessage = _('revlog content will be recompressed')
 
     @classmethod
     def fromrepo(cls, repo):
         comp = compressionengine.fromrepo(repo)
         level = None
         if comp == 'zlib':
             level = repo.ui.configint('storage', 'revlog.zlib.level')
         elif comp == 'zstd':
             level = repo.ui.configint('storage', 'revlog.zstd.level')
         if level is None:
             return 'default'
         return bytes(level)
 
     @classmethod
     def fromconfig(cls, repo):
         comp = compressionengine.fromconfig(repo)
         level = None
         if comp == 'zlib':
             level = repo.ui.configint('storage', 'revlog.zlib.level')
         elif comp == 'zstd':
             level = repo.ui.configint('storage', 'revlog.zstd.level')
         if level is None:
             return 'default'
         return bytes(level)
 
 def finddeficiencies(repo):
     """returns a list of deficiencies that the repo suffer from"""
     deficiencies = []
 
     # 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.
 
     for fv in allformatvariant:
         if not fv.fromrepo(repo):
             deficiencies.append(fv)
 
     return deficiencies
 
 # search without '-' to support older form on newer client.
 #
 # We don't enforce backward compatibility for debug command so this
 # might eventually be dropped. However, having to use two different
 # forms in script when comparing result is anoying enough to add
 # backward compatibility for a while.
 legacy_opts_map = {
     'redeltaparent': 're-delta-parent',
     'redeltamultibase': 're-delta-multibase',
     'redeltaall': 're-delta-all',
     'redeltafulladd': 're-delta-fulladd',
 }
 
 def findoptimizations(repo):
     """Determine optimisation that could be used during upgrade"""
     # These are unconditionally added. There is logic later that figures out
     # which ones to apply.
     optimizations = []
 
     optimizations.append(improvement(
         name='re-delta-parent',
         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')))
 
     optimizations.append(improvement(
         name='re-delta-multibase',
         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')))
 
     optimizations.append(improvement(
         name='re-delta-all',
         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')))
 
     optimizations.append(improvement(
         name='re-delta-fulladd',
         type=optimisation,
         description=_('every revision will be re-added as if it was new '
                       'content. It will go through the full storage '
                       'mechanism giving extensions a chance to process it '
                       '(eg. lfs). This is similar to "re-delta-all" but even '
                       'slower since more logic is involved.'),
         upgrademessage=_('each revision will be added as new content to the '
                          'internal storage; this will likely drastically slow '
                          'down execution time, but some extensions might need '
                          'it')))
 
     return optimizations
 
 def determineactions(repo, deficiencies, sourcereqs, destreqs):
     """Determine upgrade actions that will be performed.
 
     Given a list of improvements as returned by ``finddeficiencies`` and
     ``findoptimizations``, 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 = supporteddestrequirements(repo)
 
     for d in deficiencies:
         name = d.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
 
         newactions.append(d)
 
     # FUTURE consider adding some optimizations here for certain transitions.
     # e.g. adding generaldelta could schedule parent redeltas.
 
     return newactions
 
 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, tree=mandir)
     else:
         #reverse of "/".join(("data", path + ".i"))
         return filelog.filelog(repo.svfs, path[5:-2])
 
 def _copyrevlogs(ui, srcrepo, dstrepo, tr, deltareuse, forcedeltabothparents):
     """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)
 
         info = rl.storageinfo(exclusivefiles=True, revisionscount=True,
                               trackedsize=True, storedsize=True)
 
         revcount += info['revisionscount'] or 0
         datasize = info['storedsize'] or 0
         rawsize = info['trackedsize'] or 0
 
         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, filelog.filelog):
             fcount += 1
             frevcount += len(rl)
             fsrcsize += datasize
             frawsize += rawsize
         else:
             error.ProgrammingError('unknown revlog type')
 
     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 = None
     def oncopiedrevision(rl, rev, node):
         progress.increment()
 
     # 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 = srcrepo.ui.makeprogress(_('changelog revisions'),
                                                total=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')
             if progress:
                 progress.complete()
             progress = srcrepo.ui.makeprogress(_('manifest revisions'),
                                                total=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')
             if progress:
                 progress.complete()
             progress = srcrepo.ui.makeprogress(_('file revisions'),
                                                total=frevcount)
 
 
         ui.note(_('cloning %d revisions from %s\n') % (len(oldrl), unencoded))
         oldrl.clone(tr, newrl, addrevisioncb=oncopiedrevision,
                     deltareuse=deltareuse,
                     forcedeltabothparents=forcedeltabothparents)
 
         info = newrl.storageinfo(storedsize=True)
         datasize = info['storedsize'] or 0
 
         dstsize += datasize
 
         if isinstance(newrl, changelog.changelog):
             cdstsize += datasize
         elif isinstance(newrl, manifest.manifestrevlog):
             mdstsize += datasize
         else:
             fdstsize += datasize
 
     progress.complete()
 
     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)))
 
 def _filterstorefile(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 _finishdatamigration(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.
     """
 
 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()
 
     ui.write(_('(it is safe to interrupt this process any time before '
                'data migration completes)\n'))
 
     if 're-delta-all' in actions:
         deltareuse = revlog.revlog.DELTAREUSENEVER
     elif 're-delta-parent' in actions:
         deltareuse = revlog.revlog.DELTAREUSESAMEREVS
     elif 're-delta-multibase' in actions:
         deltareuse = revlog.revlog.DELTAREUSESAMEREVS
     elif 're-delta-fulladd' in actions:
         deltareuse = revlog.revlog.DELTAREUSEFULLADD
     else:
         deltareuse = revlog.revlog.DELTAREUSEALWAYS
 
     with dstrepo.transaction('upgrade') as tr:
         _copyrevlogs(ui, srcrepo, dstrepo, tr, deltareuse,
                      're-delta-multibase' in actions)
 
     # Now copy other files in the store directory.
     # The sorted() makes execution deterministic.
     for p, kind, st in sorted(srcrepo.store.vfs.readdir('', stat=True)):
         if not _filterstorefile(srcrepo, dstrepo, requirements,
                                        p, kind, st):
             continue
 
         srcrepo.ui.write(_('copying %s\n') % p)
         src = srcrepo.store.rawvfs.join(p)
         dst = dstrepo.store.rawvfs.join(p)
         util.copyfile(src, dst, copystat=True)
 
     _finishdatamigration(ui, srcrepo, dstrepo, requirements)
 
     ui.write(_('data fully migrated to temporary repository\n'))
 
     backuppath = pycompat.mkdtemp(prefix='upgradebackup.', dir=srcrepo.path)
     backupvfs = vfsmod.vfs(backuppath)
 
     # Make a backup of requires file first, as it is the first to be modified.
     util.copyfile(srcrepo.vfs.join('requires'), backupvfs.join('requires'))
 
     # 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 | {'upgradeinprogress'})
 
     ui.write(_('starting in-place swap of repository data\n'))
     ui.write(_('replaced files will be backed up at %s\n') %
              backuppath)
 
     # 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'))
     tstart = util.timer()
     util.rename(srcrepo.spath, backupvfs.join('store'))
     util.rename(dstrepo.spath, srcrepo.spath)
     elapsed = util.timer() - tstart
     ui.write(_('store replacement complete; repository was inconsistent for '
                '%0.1fs\n') % elapsed)
 
     # 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)
 
     # 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')
 
     return backuppath
 
 def upgraderepo(ui, repo, run=False, optimize=None, backup=True):
     """Upgrade a repository in place."""
     if optimize is None:
         optimize = []
     optimize = set(legacy_opts_map.get(o, o) for o in optimize)
     repo = repo.unfiltered()
 
     # Ensure the repository can be upgraded.
     missingreqs = requiredsourcerequirements(repo) - repo.requirements
     if missingreqs:
         raise error.Abort(_('cannot upgrade repository; requirement '
                             'missing: %s') % _(', ').join(sorted(missingreqs)))
 
     blockedreqs = blocksourcerequirements(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.ui, localrepo.defaultcreateopts(repo.ui))
     newreqs.update(preservedrequirements(repo))
 
     noremovereqs = (repo.requirements - newreqs -
                    supportremovedrequirements(repo))
     if noremovereqs:
         raise error.Abort(_('cannot upgrade repository; requirement would be '
                             'removed: %s') % _(', ').join(sorted(noremovereqs)))
 
     noaddreqs = (newreqs - repo.requirements -
                  allowednewrequirements(repo))
     if noaddreqs:
         raise error.Abort(_('cannot upgrade repository; do not support adding '
                             'requirement: %s') %
                           _(', ').join(sorted(noaddreqs)))
 
     unsupportedreqs = newreqs - supporteddestrequirements(repo)
     if unsupportedreqs:
         raise error.Abort(_('cannot upgrade repository; do not support '
                             'destination requirement: %s') %
                           _(', ').join(sorted(unsupportedreqs)))
 
     # Find and validate all improvements that can be made.
     alloptimizations = findoptimizations(repo)
 
     # Apply and Validate arguments.
     optimizations = []
     for o in alloptimizations:
         if o.name in optimize:
             optimizations.append(o)
             optimize.discard(o.name)
 
     if optimize: # anything left is unknown
         raise error.Abort(_('unknown optimization action requested: %s') %
                           ', '.join(sorted(optimize)),
                           hint=_('run without arguments to see valid '
                                  'optimizations'))
 
     deficiencies = finddeficiencies(repo)
     actions = determineactions(repo, deficiencies, repo.requirements, newreqs)
     actions.extend(o for o in sorted(optimizations)
                    # determineactions could have added optimisation
                    if o not in actions)
 
     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')
 
     def printupgradeactions():
         for a in actions:
             ui.write('%s\n   %s\n\n' % (a.name, a.upgrademessage))
 
     if not run:
         fromconfig = []
         onlydefault = []
 
         for d in deficiencies:
             if d.fromconfig(repo):
                 fromconfig.append(d)
             elif d.default:
                 onlydefault.append(d)
 
         if fromconfig or onlydefault:
 
             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'))
 
         ui.write(_('performing an upgrade with "--run" will make the following '
                    'changes:\n\n'))
 
         printrequirements()
         printupgradeactions()
 
         unusedoptimize = [i for i in alloptimizations if i not in actions]
 
         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))
         return
 
     # Else we're in the run=true case.
     ui.write(_('upgrade will perform the following actions:\n\n'))
     printrequirements()
     printupgradeactions()
 
     upgradeactions = [a.name for a in actions]
 
     ui.write(_('beginning upgrade...\n'))
     with repo.wlock(), 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 = pycompat.mkdtemp(prefix='upgrade.', dir=repo.path)
         backuppath = None
         try:
             ui.write(_('creating temporary repository to stage migrated '
                        'data: %s\n') % tmppath)
 
             # clone ui without using ui.copy because repo.ui is protected
             repoui = repo.ui.__class__(repo.ui)
             dstrepo = hg.repository(repoui, path=tmppath, create=True)
 
             with dstrepo.wlock(), dstrepo.lock():
                 backuppath = _upgraderepo(ui, repo, dstrepo, newreqs,
                                           upgradeactions)
             if not (backup or backuppath is None):
                 ui.write(_('removing old repository content%s\n') % backuppath)
                 repo.vfs.rmtree(backuppath, forcibly=True)
                 backuppath = None
 
         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'))

tests/test-upgrade-repo.t

@@ -1,857 +1,931
 #require no-reposimplestore
 
   $ cat >> $HGRCPATH << EOF
   > [extensions]
   > share =
   > EOF
 
 store and revlogv1 are required in source
 
   $ hg --config format.usestore=false init no-store
   $ hg -R no-store debugupgraderepo
   abort: cannot upgrade repository; requirement missing: store
   [255]
 
   $ hg init no-revlogv1
   $ cat > no-revlogv1/.hg/requires << EOF
   > dotencode
   > fncache
   > generaldelta
   > store
   > EOF
 
   $ hg -R no-revlogv1 debugupgraderepo
   abort: cannot upgrade repository; requirement missing: revlogv1
   [255]
 
 Cannot upgrade shared repositories
 
   $ hg init share-parent
   $ hg -q share share-parent share-child
 
   $ hg -R share-child debugupgraderepo
   abort: cannot upgrade repository; unsupported source requirement: shared
   [255]
 
 Do not yet support upgrading treemanifest repos
 
   $ hg --config experimental.treemanifest=true init treemanifest
   $ hg -R treemanifest debugupgraderepo
   abort: cannot upgrade repository; unsupported source requirement: treemanifest
   [255]
 
 Cannot add treemanifest requirement during upgrade
 
   $ hg init disallowaddedreq
   $ hg -R disallowaddedreq --config experimental.treemanifest=true debugupgraderepo
   abort: cannot upgrade repository; do not support adding requirement: treemanifest
   [255]
 
 An upgrade of a repository created with recommended settings only suggests optimizations
 
   $ hg init empty
   $ cd empty
   $ hg debugformat
   format-variant    repo
   fncache:           yes
   dotencode:         yes
   generaldelta:      yes
   sparserevlog:      yes
   plain-cl-delta:    yes
   compression:       zlib
   compression-level: default
   $ hg debugformat --verbose
   format-variant    repo config default
   fncache:           yes    yes     yes
   dotencode:         yes    yes     yes
   generaldelta:      yes    yes     yes
   sparserevlog:      yes    yes     yes
   plain-cl-delta:    yes    yes     yes
   compression:       zlib   zlib    zlib
   compression-level: default default default
   $ hg debugformat --verbose --config format.usefncache=no
   format-variant    repo config default
   fncache:           yes     no     yes
   dotencode:         yes     no     yes
   generaldelta:      yes    yes     yes
   sparserevlog:      yes    yes     yes
   plain-cl-delta:    yes    yes     yes
   compression:       zlib   zlib    zlib
   compression-level: default default default
   $ hg debugformat --verbose --config format.usefncache=no --color=debug
   format-variant    repo config default
   [formatvariant.name.mismatchconfig|fncache:          ][formatvariant.repo.mismatchconfig| yes][formatvariant.config.special|     no][formatvariant.default|     yes]
   [formatvariant.name.mismatchconfig|dotencode:        ][formatvariant.repo.mismatchconfig| yes][formatvariant.config.special|     no][formatvariant.default|     yes]
   [formatvariant.name.uptodate|generaldelta:     ][formatvariant.repo.uptodate| yes][formatvariant.config.default|    yes][formatvariant.default|     yes]
   [formatvariant.name.uptodate|sparserevlog:     ][formatvariant.repo.uptodate| yes][formatvariant.config.default|    yes][formatvariant.default|     yes]
   [formatvariant.name.uptodate|plain-cl-delta:   ][formatvariant.repo.uptodate| yes][formatvariant.config.default|    yes][formatvariant.default|     yes]
   [formatvariant.name.uptodate|compression:      ][formatvariant.repo.uptodate| zlib][formatvariant.config.default|   zlib][formatvariant.default|    zlib]
   [formatvariant.name.uptodate|compression-level:][formatvariant.repo.uptodate| default][formatvariant.config.default| default][formatvariant.default| default]
   $ hg debugformat -Tjson
   [
    {
     "config": true,
     "default": true,
     "name": "fncache",
     "repo": true
    },
    {
     "config": true,
     "default": true,
     "name": "dotencode",
     "repo": true
    },
    {
     "config": true,
     "default": true,
     "name": "generaldelta",
     "repo": true
    },
    {
     "config": true,
     "default": true,
     "name": "sparserevlog",
     "repo": true
    },
    {
     "config": true,
     "default": true,
     "name": "plain-cl-delta",
     "repo": true
    },
    {
     "config": "zlib",
     "default": "zlib",
     "name": "compression",
     "repo": "zlib"
    },
    {
     "config": "default",
     "default": "default",
     "name": "compression-level",
     "repo": "default"
    }
   ]
   $ hg debugupgraderepo
   (no feature deficiencies found in existing repository)
   performing an upgrade with "--run" will make the following changes:
   
   requirements
      preserved: dotencode, fncache, generaldelta, revlogv1, sparserevlog, store
   
   additional optimizations are available by specifying "--optimize <name>":
   
   re-delta-parent
      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
   
   re-delta-multibase
      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
   
   re-delta-all
      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
   
   re-delta-fulladd
      every revision will be re-added as if it was new content. It will go through the full storage mechanism giving extensions a chance to process it (eg. lfs). This is similar to "re-delta-all" but even slower since more logic is involved.
   
 
 --optimize can be used to add optimizations
 
   $ hg debugupgrade --optimize redeltaparent
   (no feature deficiencies found in existing repository)
   performing an upgrade with "--run" will make the following changes:
   
   requirements
      preserved: dotencode, fncache, generaldelta, revlogv1, sparserevlog, store
   
   re-delta-parent
      deltas within internal storage will choose a new base revision if needed
   
   additional optimizations are available by specifying "--optimize <name>":
   
   re-delta-multibase
      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
   
   re-delta-all
      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
   
   re-delta-fulladd
      every revision will be re-added as if it was new content. It will go through the full storage mechanism giving extensions a chance to process it (eg. lfs). This is similar to "re-delta-all" but even slower since more logic is involved.
   
 
 modern form of the option
 
   $ hg debugupgrade --optimize re-delta-parent
   (no feature deficiencies found in existing repository)
   performing an upgrade with "--run" will make the following changes:
   
   requirements
      preserved: dotencode, fncache, generaldelta, revlogv1, sparserevlog, store
   
   re-delta-parent
      deltas within internal storage will choose a new base revision if needed
   
   additional optimizations are available by specifying "--optimize <name>":
   
   re-delta-multibase
      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
   
   re-delta-all
      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
   
   re-delta-fulladd
      every revision will be re-added as if it was new content. It will go through the full storage mechanism giving extensions a chance to process it (eg. lfs). This is similar to "re-delta-all" but even slower since more logic is involved.
   
 
 unknown optimization:
 
   $ hg debugupgrade --optimize foobar
   abort: unknown optimization action requested: foobar
   (run without arguments to see valid optimizations)
   [255]
 
 Various sub-optimal detections work
 
   $ cat > .hg/requires << EOF
   > revlogv1
   > store
   > EOF
 
   $ hg debugformat
   format-variant    repo
   fncache:            no
   dotencode:          no
   generaldelta:       no
   sparserevlog:       no
   plain-cl-delta:    yes
   compression:       zlib
   compression-level: default
   $ hg debugformat --verbose
   format-variant    repo config default
   fncache:            no    yes     yes
   dotencode:          no    yes     yes
   generaldelta:       no    yes     yes
   sparserevlog:       no    yes     yes
   plain-cl-delta:    yes    yes     yes
   compression:       zlib   zlib    zlib
   compression-level: default default default
   $ hg debugformat --verbose --config format.usegeneraldelta=no
   format-variant    repo config default
   fncache:            no    yes     yes
   dotencode:          no    yes     yes
   generaldelta:       no     no     yes
   sparserevlog:       no     no     yes
   plain-cl-delta:    yes    yes     yes
   compression:       zlib   zlib    zlib
   compression-level: default default default
   $ hg debugformat --verbose --config format.usegeneraldelta=no --color=debug
   format-variant    repo config default
   [formatvariant.name.mismatchconfig|fncache:          ][formatvariant.repo.mismatchconfig|  no][formatvariant.config.default|    yes][formatvariant.default|     yes]
   [formatvariant.name.mismatchconfig|dotencode:        ][formatvariant.repo.mismatchconfig|  no][formatvariant.config.default|    yes][formatvariant.default|     yes]
   [formatvariant.name.mismatchdefault|generaldelta:     ][formatvariant.repo.mismatchdefault|  no][formatvariant.config.special|     no][formatvariant.default|     yes]
   [formatvariant.name.mismatchdefault|sparserevlog:     ][formatvariant.repo.mismatchdefault|  no][formatvariant.config.special|     no][formatvariant.default|     yes]
   [formatvariant.name.uptodate|plain-cl-delta:   ][formatvariant.repo.uptodate| yes][formatvariant.config.default|    yes][formatvariant.default|     yes]
   [formatvariant.name.uptodate|compression:      ][formatvariant.repo.uptodate| zlib][formatvariant.config.default|   zlib][formatvariant.default|    zlib]
   [formatvariant.name.uptodate|compression-level:][formatvariant.repo.uptodate| default][formatvariant.config.default| default][formatvariant.default| default]
   $ hg debugupgraderepo
   repository lacks features recommended by current config options:
   
   fncache
      long and reserved filenames may not work correctly; repository performance is sub-optimal
   
   dotencode
      storage of filenames beginning with a period or space may not work correctly
   
   generaldelta
      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
   
   sparserevlog
      in order to limit disk reading and memory usage on older version, the span of a delta chain from its root to its end is limited, whatever the relevant data in this span. This can severly limit Mercurial ability to build good chain of delta resulting is much more storage space being taken and limit reusability of on disk delta during exchange.
   
   
   performing an upgrade with "--run" will make the following changes:
   
   requirements
      preserved: revlogv1, store
      added: dotencode, fncache, generaldelta, sparserevlog
   
   fncache
      repository will be more resilient to storing certain paths and performance of certain operations should be improved
   
   dotencode
      repository will be better able to store files beginning with a space or period
   
   generaldelta
      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
   
   sparserevlog
      Revlog supports delta chain with more unused data between payload. These gaps will be skipped at read time. This allows for better delta chains, making a better compression and faster exchange with server.
   
   additional optimizations are available by specifying "--optimize <name>":
   
   re-delta-parent
      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
   
   re-delta-multibase
      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
   
   re-delta-all
      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
   
   re-delta-fulladd
      every revision will be re-added as if it was new content. It will go through the full storage mechanism giving extensions a chance to process it (eg. lfs). This is similar to "re-delta-all" but even slower since more logic is involved.
   
 
   $ hg --config format.dotencode=false debugupgraderepo
   repository lacks features recommended by current config options:
   
   fncache
      long and reserved filenames may not work correctly; repository performance is sub-optimal
   
   generaldelta
      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
   
   sparserevlog
      in order to limit disk reading and memory usage on older version, the span of a delta chain from its root to its end is limited, whatever the relevant data in this span. This can severly limit Mercurial ability to build good chain of delta resulting is much more storage space being taken and limit reusability of on disk delta during exchange.
   
   repository lacks features used by the default config options:
   
   dotencode
      storage of filenames beginning with a period or space may not work correctly
   
   
   performing an upgrade with "--run" will make the following changes:
   
   requirements
      preserved: revlogv1, store
      added: fncache, generaldelta, sparserevlog
   
   fncache
      repository will be more resilient to storing certain paths and performance of certain operations should be improved
   
   generaldelta
      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
   
   sparserevlog
      Revlog supports delta chain with more unused data between payload. These gaps will be skipped at read time. This allows for better delta chains, making a better compression and faster exchange with server.
   
   additional optimizations are available by specifying "--optimize <name>":
   
   re-delta-parent
      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
   
   re-delta-multibase
      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
   
   re-delta-all
      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
   
   re-delta-fulladd
      every revision will be re-added as if it was new content. It will go through the full storage mechanism giving extensions a chance to process it (eg. lfs). This is similar to "re-delta-all" but even slower since more logic is involved.
   
 
   $ cd ..
 
 Upgrading a repository that is already modern essentially no-ops
 
   $ hg init modern
   $ hg -R modern debugupgraderepo --run
   upgrade will perform the following actions:
   
   requirements
      preserved: dotencode, fncache, generaldelta, revlogv1, sparserevlog, store
   
   beginning upgrade...
   repository locked and read-only
   creating temporary repository to stage migrated data: $TESTTMP/modern/.hg/upgrade.* (glob)
   (it is safe to interrupt this process any time before data migration completes)
   data fully migrated to temporary repository
   marking source repository as being upgraded; clients will be unable to read from repository
   starting in-place swap of repository data
   replaced files will be backed up at $TESTTMP/modern/.hg/upgradebackup.* (glob)
   replacing store...
   store replacement complete; repository was inconsistent for *s (glob)
   finalizing requirements file and making repository readable again
   removing temporary repository $TESTTMP/modern/.hg/upgrade.* (glob)
   copy of old repository backed up at $TESTTMP/modern/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
 
 Upgrading a repository to generaldelta works
 
   $ hg --config format.usegeneraldelta=false init upgradegd
   $ cd upgradegd
   $ touch f0
   $ hg -q commit -A -m initial
   $ touch f1
   $ hg -q commit -A -m 'add f1'
   $ hg -q up -r 0
   $ touch f2
   $ hg -q commit -A -m 'add f2'
 
   $ hg debugupgraderepo --run --config format.sparse-revlog=false
   upgrade will perform the following actions:
   
   requirements
      preserved: dotencode, fncache, revlogv1, store
      added: generaldelta
   
   generaldelta
      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
   
   beginning upgrade...
   repository locked and read-only
   creating temporary repository to stage migrated data: $TESTTMP/upgradegd/.hg/upgrade.* (glob)
   (it is safe to interrupt this process any time before data migration completes)
   migrating 9 total revisions (3 in filelogs, 3 in manifests, 3 in changelog)
   migrating 917 bytes in store; 401 bytes tracked data
   migrating 3 filelogs containing 3 revisions (192 bytes in store; 0 bytes tracked data)
   finished migrating 3 filelog revisions across 3 filelogs; change in size: 0 bytes
   migrating 1 manifests containing 3 revisions (349 bytes in store; 220 bytes tracked data)
   finished migrating 3 manifest revisions across 1 manifests; change in size: 0 bytes
   migrating changelog containing 3 revisions (376 bytes in store; 181 bytes tracked data)
   finished migrating 3 changelog revisions; change in size: 0 bytes
   finished migrating 9 total revisions; total change in store size: 0 bytes
   copying phaseroots
   data fully migrated to temporary repository
   marking source repository as being upgraded; clients will be unable to read from repository
   starting in-place swap of repository data
   replaced files will be backed up at $TESTTMP/upgradegd/.hg/upgradebackup.* (glob)
   replacing store...
   store replacement complete; repository was inconsistent for *s (glob)
   finalizing requirements file and making repository readable again
   removing temporary repository $TESTTMP/upgradegd/.hg/upgrade.* (glob)
   copy of old repository backed up at $TESTTMP/upgradegd/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
 
 Original requirements backed up
 
   $ cat .hg/upgradebackup.*/requires
   dotencode
   fncache
   revlogv1
   store
 
 generaldelta added to original requirements files
 
   $ cat .hg/requires
   dotencode
   fncache
   generaldelta
   revlogv1
   store
 
 store directory has files we expect
 
   $ ls .hg/store
   00changelog.i
   00manifest.i
   data
   fncache
   phaseroots
   undo
   undo.backupfiles
   undo.phaseroots
 
 manifest should be generaldelta
 
   $ hg debugrevlog -m | grep flags
   flags  : inline, generaldelta
 
 verify should be happy
 
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 3 changesets with 3 changes to 3 files
 
 old store should be backed up
 
   $ ls -d .hg/upgradebackup.*/
   .hg/upgradebackup.*/ (glob)
   $ ls .hg/upgradebackup.*/store
   00changelog.i
   00manifest.i
   data
   fncache
   phaseroots
   undo
   undo.backup.fncache
   undo.backupfiles
   undo.phaseroots
 
 unless --no-backup is passed
 
   $ rm -rf .hg/upgradebackup.*/
   $ hg debugupgraderepo --run --no-backup
   upgrade will perform the following actions:
   
   requirements
      preserved: dotencode, fncache, generaldelta, revlogv1, store
      added: sparserevlog
   
   sparserevlog
      Revlog supports delta chain with more unused data between payload. These gaps will be skipped at read time. This allows for better delta chains, making a better compression and faster exchange with server.
   
   beginning upgrade...
   repository locked and read-only
   creating temporary repository to stage migrated data: $TESTTMP/upgradegd/.hg/upgrade.* (glob)
   (it is safe to interrupt this process any time before data migration completes)
   migrating 9 total revisions (3 in filelogs, 3 in manifests, 3 in changelog)
   migrating 917 bytes in store; 401 bytes tracked data
   migrating 3 filelogs containing 3 revisions (192 bytes in store; 0 bytes tracked data)
   finished migrating 3 filelog revisions across 3 filelogs; change in size: 0 bytes
   migrating 1 manifests containing 3 revisions (349 bytes in store; 220 bytes tracked data)
   finished migrating 3 manifest revisions across 1 manifests; change in size: 0 bytes
   migrating changelog containing 3 revisions (376 bytes in store; 181 bytes tracked data)
   finished migrating 3 changelog revisions; change in size: 0 bytes
   finished migrating 9 total revisions; total change in store size: 0 bytes
   copying phaseroots
   data fully migrated to temporary repository
   marking source repository as being upgraded; clients will be unable to read from repository
   starting in-place swap of repository data
   replaced files will be backed up at $TESTTMP/upgradegd/.hg/upgradebackup.* (glob)
   replacing store...
   store replacement complete; repository was inconsistent for * (glob)
   finalizing requirements file and making repository readable again
   removing old repository content$TESTTMP/upgradegd/.hg/upgradebackup.* (glob)
   removing temporary repository $TESTTMP/upgradegd/.hg/upgrade.* (glob)
   $ ls -1 .hg/ | grep upgradebackup
   [1]
   $ cd ..
 
 
 store files with special filenames aren't encoded during copy
 
   $ hg init store-filenames
   $ cd store-filenames
   $ touch foo
   $ hg -q commit -A -m initial
   $ touch .hg/store/.XX_special_filename
 
   $ hg debugupgraderepo --run
   upgrade will perform the following actions:
   
   requirements
      preserved: dotencode, fncache, generaldelta, revlogv1, sparserevlog, store
   
   beginning upgrade...
   repository locked and read-only
   creating temporary repository to stage migrated data: $TESTTMP/store-filenames/.hg/upgrade.* (glob)
   (it is safe to interrupt this process any time before data migration completes)
   migrating 3 total revisions (1 in filelogs, 1 in manifests, 1 in changelog)
   migrating 301 bytes in store; 107 bytes tracked data
   migrating 1 filelogs containing 1 revisions (64 bytes in store; 0 bytes tracked data)
   finished migrating 1 filelog revisions across 1 filelogs; change in size: 0 bytes
   migrating 1 manifests containing 1 revisions (110 bytes in store; 45 bytes tracked data)
   finished migrating 1 manifest revisions across 1 manifests; change in size: 0 bytes
   migrating changelog containing 1 revisions (127 bytes in store; 62 bytes tracked data)
   finished migrating 1 changelog revisions; change in size: 0 bytes
   finished migrating 3 total revisions; total change in store size: 0 bytes
   copying .XX_special_filename
   copying phaseroots
   data fully migrated to temporary repository
   marking source repository as being upgraded; clients will be unable to read from repository
   starting in-place swap of repository data
   replaced files will be backed up at $TESTTMP/store-filenames/.hg/upgradebackup.* (glob)
   replacing store...
   store replacement complete; repository was inconsistent for *s (glob)
   finalizing requirements file and making repository readable again
   removing temporary repository $TESTTMP/store-filenames/.hg/upgrade.* (glob)
   copy of old repository backed up at $TESTTMP/store-filenames/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
   $ hg debugupgraderepo --run --optimize redeltafulladd
   upgrade will perform the following actions:
   
   requirements
      preserved: dotencode, fncache, generaldelta, revlogv1, sparserevlog, store
   
   re-delta-fulladd
      each revision will be added as new content to the internal storage; this will likely drastically slow down execution time, but some extensions might need it
   
   beginning upgrade...
   repository locked and read-only
   creating temporary repository to stage migrated data: $TESTTMP/store-filenames/.hg/upgrade.* (glob)
   (it is safe to interrupt this process any time before data migration completes)
   migrating 3 total revisions (1 in filelogs, 1 in manifests, 1 in changelog)
   migrating 301 bytes in store; 107 bytes tracked data
   migrating 1 filelogs containing 1 revisions (64 bytes in store; 0 bytes tracked data)
   finished migrating 1 filelog revisions across 1 filelogs; change in size: 0 bytes
   migrating 1 manifests containing 1 revisions (110 bytes in store; 45 bytes tracked data)
   finished migrating 1 manifest revisions across 1 manifests; change in size: 0 bytes
   migrating changelog containing 1 revisions (127 bytes in store; 62 bytes tracked data)
   finished migrating 1 changelog revisions; change in size: 0 bytes
   finished migrating 3 total revisions; total change in store size: 0 bytes
   copying .XX_special_filename
   copying phaseroots
   data fully migrated to temporary repository
   marking source repository as being upgraded; clients will be unable to read from repository
   starting in-place swap of repository data
   replaced files will be backed up at $TESTTMP/store-filenames/.hg/upgradebackup.* (glob)
   replacing store...
   store replacement complete; repository was inconsistent for *s (glob)
   finalizing requirements file and making repository readable again
   removing temporary repository $TESTTMP/store-filenames/.hg/upgrade.* (glob)
   copy of old repository backed up at $TESTTMP/store-filenames/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
 
 fncache is valid after upgrade
 
   $ hg debugrebuildfncache
   fncache already up to date
 
   $ cd ..
 
 Check upgrading a large file repository
 ---------------------------------------
 
   $ hg init largefilesrepo
   $ cat << EOF >> largefilesrepo/.hg/hgrc
   > [extensions]
   > largefiles =
   > EOF
 
   $ cd largefilesrepo
   $ touch foo
   $ hg add --large foo
   $ hg -q commit -m initial
   $ cat .hg/requires
   dotencode
   fncache
   generaldelta
   largefiles
   revlogv1
   sparserevlog
   store
 
   $ hg debugupgraderepo --run
   upgrade will perform the following actions:
   
   requirements
      preserved: dotencode, fncache, generaldelta, largefiles, revlogv1, sparserevlog, store
   
   beginning upgrade...
   repository locked and read-only
   creating temporary repository to stage migrated data: $TESTTMP/largefilesrepo/.hg/upgrade.* (glob)
   (it is safe to interrupt this process any time before data migration completes)
   migrating 3 total revisions (1 in filelogs, 1 in manifests, 1 in changelog)
   migrating 355 bytes in store; 160 bytes tracked data
   migrating 1 filelogs containing 1 revisions (106 bytes in store; 41 bytes tracked data)
   finished migrating 1 filelog revisions across 1 filelogs; change in size: 0 bytes
   migrating 1 manifests containing 1 revisions (116 bytes in store; 51 bytes tracked data)
   finished migrating 1 manifest revisions across 1 manifests; change in size: 0 bytes
   migrating changelog containing 1 revisions (133 bytes in store; 68 bytes tracked data)
   finished migrating 1 changelog revisions; change in size: 0 bytes
   finished migrating 3 total revisions; total change in store size: 0 bytes
   copying phaseroots
   data fully migrated to temporary repository
   marking source repository as being upgraded; clients will be unable to read from repository
   starting in-place swap of repository data
   replaced files will be backed up at $TESTTMP/largefilesrepo/.hg/upgradebackup.* (glob)
   replacing store...
   store replacement complete; repository was inconsistent for *s (glob)
   finalizing requirements file and making repository readable again
   removing temporary repository $TESTTMP/largefilesrepo/.hg/upgrade.* (glob)
   copy of old repository backed up at $TESTTMP/largefilesrepo/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
   $ cat .hg/requires
   dotencode
   fncache
   generaldelta
   largefiles
   revlogv1
   sparserevlog
   store
 
   $ cat << EOF >> .hg/hgrc
   > [extensions]
   > lfs =
   > [lfs]
   > threshold = 10
   > EOF
   $ echo '123456789012345' > lfs.bin
   $ hg ci -Am 'lfs.bin'
   adding lfs.bin
   $ grep lfs .hg/requires
   lfs
   $ find .hg/store/lfs -type f
   .hg/store/lfs/objects/d0/beab232adff5ba365880366ad30b1edb85c4c5372442b5d2fe27adc96d653f
 
   $ hg debugupgraderepo --run
   upgrade will perform the following actions:
   
   requirements
      preserved: dotencode, fncache, generaldelta, largefiles, lfs, revlogv1, sparserevlog, store
   
   beginning upgrade...
   repository locked and read-only
   creating temporary repository to stage migrated data: $TESTTMP/largefilesrepo/.hg/upgrade.* (glob)
   (it is safe to interrupt this process any time before data migration completes)
   migrating 6 total revisions (2 in filelogs, 2 in manifests, 2 in changelog)
   migrating 801 bytes in store; 467 bytes tracked data
   migrating 2 filelogs containing 2 revisions (296 bytes in store; 182 bytes tracked data)
   finished migrating 2 filelog revisions across 2 filelogs; change in size: 0 bytes
   migrating 1 manifests containing 2 revisions (241 bytes in store; 151 bytes tracked data)
   finished migrating 2 manifest revisions across 1 manifests; change in size: 0 bytes
   migrating changelog containing 2 revisions (264 bytes in store; 134 bytes tracked data)
   finished migrating 2 changelog revisions; change in size: 0 bytes
   finished migrating 6 total revisions; total change in store size: 0 bytes
   copying phaseroots
   copying lfs blob d0beab232adff5ba365880366ad30b1edb85c4c5372442b5d2fe27adc96d653f
   data fully migrated to temporary repository
   marking source repository as being upgraded; clients will be unable to read from repository
   starting in-place swap of repository data
   replaced files will be backed up at $TESTTMP/largefilesrepo/.hg/upgradebackup.* (glob)
   replacing store...
   store replacement complete; repository was inconsistent for *s (glob)
   finalizing requirements file and making repository readable again
   removing temporary repository $TESTTMP/largefilesrepo/.hg/upgrade.* (glob)
   copy of old repository backed up at $TESTTMP/largefilesrepo/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
 
   $ grep lfs .hg/requires
   lfs
   $ find .hg/store/lfs -type f
   .hg/store/lfs/objects/d0/beab232adff5ba365880366ad30b1edb85c4c5372442b5d2fe27adc96d653f
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 2 changesets with 2 changes to 2 files
   $ hg debugdata lfs.bin 0
   version https://git-lfs.github.com/spec/v1
   oid sha256:d0beab232adff5ba365880366ad30b1edb85c4c5372442b5d2fe27adc96d653f
   size 16
   x-is-binary 0
 
   $ cd ..
 
 repository config is taken in account
 -------------------------------------
 
   $ cat << EOF >> $HGRCPATH
   > [format]
   > maxchainlen = 1
   > EOF
 
   $ hg init localconfig
   $ cd localconfig
   $ cat << EOF > file
   > some content
   > with some length
   > to make sure we get a delta
   > after changes
   > very long
   > very long
   > very long
   > very long
   > very long
   > very long
   > very long
   > very long
   > very long
   > very long
   > very long
   > EOF
   $ hg -q commit -A -m A
   $ echo "new line" >> file
   $ hg -q commit -m B
   $ echo "new line" >> file
   $ hg -q commit -m C
 
   $ cat << EOF >> .hg/hgrc
   > [format]
   > maxchainlen = 9001
   > EOF
   $ hg config format
   format.maxchainlen=9001
   $ hg debugdeltachain file
       rev  chain# chainlen     prev   delta       size    rawsize  chainsize     ratio   lindist extradist extraratio   readsize largestblk rddensity srchunks
         0       1        1       -1    base         77        182         77   0.42308        77         0    0.00000         77         77   1.00000        1
         1       1        2        0      p1         21        191         98   0.51309        98         0    0.00000         98         98   1.00000        1
         2       1        2        0   other         30        200        107   0.53500       128        21    0.19626        128        128   0.83594        1
 
   $ hg debugupgraderepo --run --optimize redeltaall
   upgrade will perform the following actions:
   
   requirements
      preserved: dotencode, fncache, generaldelta, revlogv1, sparserevlog, store
   
   re-delta-all
      deltas within internal storage will be fully recomputed; this will likely drastically slow down execution time
   
   beginning upgrade...
   repository locked and read-only
   creating temporary repository to stage migrated data: $TESTTMP/localconfig/.hg/upgrade.* (glob)
   (it is safe to interrupt this process any time before data migration completes)
   migrating 9 total revisions (3 in filelogs, 3 in manifests, 3 in changelog)
   migrating 1019 bytes in store; 882 bytes tracked data
   migrating 1 filelogs containing 3 revisions (320 bytes in store; 573 bytes tracked data)
   finished migrating 3 filelog revisions across 1 filelogs; change in size: -9 bytes
   migrating 1 manifests containing 3 revisions (333 bytes in store; 138 bytes tracked data)
   finished migrating 3 manifest revisions across 1 manifests; change in size: 0 bytes
   migrating changelog containing 3 revisions (366 bytes in store; 171 bytes tracked data)
   finished migrating 3 changelog revisions; change in size: 0 bytes
   finished migrating 9 total revisions; total change in store size: -9 bytes
   copying phaseroots
   data fully migrated to temporary repository
   marking source repository as being upgraded; clients will be unable to read from repository
   starting in-place swap of repository data
   replaced files will be backed up at $TESTTMP/localconfig/.hg/upgradebackup.* (glob)
   replacing store...
   store replacement complete; repository was inconsistent for *s (glob)
   finalizing requirements file and making repository readable again
   removing temporary repository $TESTTMP/localconfig/.hg/upgrade.* (glob)
   copy of old repository backed up at $TESTTMP/localconfig/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
   $ hg debugdeltachain file
       rev  chain# chainlen     prev   delta       size    rawsize  chainsize     ratio   lindist extradist extraratio   readsize largestblk rddensity srchunks
         0       1        1       -1    base         77        182         77   0.42308        77         0    0.00000         77         77   1.00000        1
         1       1        2        0      p1         21        191         98   0.51309        98         0    0.00000         98         98   1.00000        1
         2       1        3        1      p1         21        200        119   0.59500       119         0    0.00000        119        119   1.00000        1
   $ cd ..
 
   $ cat << EOF >> $HGRCPATH
   > [format]
   > maxchainlen = 9001
   > EOF
 
 Check upgrading a sparse-revlog repository
 ---------------------------------------
 
   $ hg init sparserevlogrepo --config format.sparse-revlog=no
   $ cd sparserevlogrepo
   $ touch foo
   $ hg add foo
   $ hg -q commit -m "foo"
   $ cat .hg/requires
   dotencode
   fncache
   generaldelta
   revlogv1
   store
 
 Check that we can add the sparse-revlog format requirement
   $ hg --config format.sparse-revlog=yes debugupgraderepo --run >/dev/null
   copy of old repository backed up at $TESTTMP/sparserevlogrepo/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
   $ cat .hg/requires
   dotencode
   fncache
   generaldelta
   revlogv1
   sparserevlog
   store
 
 Check that we can remove the sparse-revlog format requirement
   $ hg --config format.sparse-revlog=no debugupgraderepo --run >/dev/null
   copy of old repository backed up at $TESTTMP/sparserevlogrepo/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
   $ cat .hg/requires
   dotencode
   fncache
   generaldelta
   revlogv1
   store
+
+#if zstd
+
+Check upgrading to a zstd revlog
+--------------------------------
+
+upgrade
+
+  $ hg --config format.revlog-compression=zstd debugupgraderepo --run  --no-backup >/dev/null
+  $ hg debugformat -v
+  format-variant    repo config default
+  fncache:           yes    yes     yes
+  dotencode:         yes    yes     yes
+  generaldelta:      yes    yes     yes
+  sparserevlog:      yes    yes     yes
+  plain-cl-delta:    yes    yes     yes
+  compression:       zstd   zlib    zlib
+  compression-level: default default default
+  $ cat .hg/requires
+  dotencode
+  fncache
+  generaldelta
+  revlog-compression-zstd
+  revlogv1
+  sparserevlog
+  store
+
+downgrade
+
+  $ hg debugupgraderepo --run --no-backup > /dev/null
+  $ hg debugformat -v
+  format-variant    repo config default
+  fncache:           yes    yes     yes
+  dotencode:         yes    yes     yes
+  generaldelta:      yes    yes     yes
+  sparserevlog:      yes    yes     yes
+  plain-cl-delta:    yes    yes     yes
+  compression:       zlib   zlib    zlib
+  compression-level: default default default
+  $ cat .hg/requires
+  dotencode
+  fncache
+  generaldelta
+  revlogv1
+  sparserevlog
+  store
+
+upgrade from hgrc
+
+  $ cat >> .hg/hgrc << EOF
+  > [format]
+  > revlog-compression=zstd
+  > EOF
+  $ hg debugupgraderepo --run --no-backup > /dev/null
+  $ hg debugformat -v
+  format-variant    repo config default
+  fncache:           yes    yes     yes
+  dotencode:         yes    yes     yes
+  generaldelta:      yes    yes     yes
+  sparserevlog:      yes    yes     yes
+  plain-cl-delta:    yes    yes     yes
+  compression:       zstd   zstd    zlib
+  compression-level: default default default
+  $ cat .hg/requires
+  dotencode
+  fncache
+  generaldelta
+  revlog-compression-zstd
+  revlogv1
+  sparserevlog
+  store
+
   $ cd ..
+
+#endif