engine: prevent multiple checking of re-delta-multibase

The _perform_clone function is called for each revlog cloned, hence we should
prevent this function call overhead.

Differential Revision: https://phab.mercurial-scm.org/D9669

mercurial/upgrade_utils/actions.py

@@ -1,899 +1,904 b''
 # 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
 
 from ..i18n import _
 from .. import (
     error,
     localrepo,
     requirements,
     revlog,
     util,
 )
 
 from ..utils import compression
 
 # list of requirements that request a clone of all revlog if added/removed
 RECLONES_REQUIREMENTS = {
     b'generaldelta',
     requirements.SPARSEREVLOG_REQUIREMENT,
 }
 
 
 def preservedrequirements(repo):
     return set()
 
 
 FORMAT_VARIANT = b'deficiency'
 OPTIMISATION = b'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 ``FORMAT_VARIANT`` or ``OPTIMISATION``.
        A format variant is where we change the storage format. Not all format
        variant changes are 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 ``FORMAT_VARIANT`` 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.
 
     postupgrademessage
        Message intended for humans which will be shown post an upgrade
        operation when the improvement will be added
 
     postdowngrademessage
        Message intended for humans which will be shown post an upgrade
        operation in which this improvement was removed
     """
 
     def __init__(self, name, type, description, upgrademessage):
         self.name = name
         self.type = type
         self.description = description
         self.upgrademessage = upgrademessage
         self.postupgrademessage = None
         self.postdowngrademessage = None
 
     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 = FORMAT_VARIANT
     ### 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 ``FORMAT_VARIANT`` 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
 
     # Message intended for humans which will be shown post an upgrade
     # operation when the improvement will be added
     postupgrademessage = None
 
     # Message intended for humans which will be shown post an upgrade
     # operation in which this improvement was removed
     postdowngrademessage = 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 = b'fncache'
 
     _requirement = b'fncache'
 
     default = True
 
     description = _(
         b'long and reserved filenames may not work correctly; '
         b'repository performance is sub-optimal'
     )
 
     upgrademessage = _(
         b'repository will be more resilient to storing '
         b'certain paths and performance of certain '
         b'operations should be improved'
     )
 
 
 @registerformatvariant
 class dotencode(requirementformatvariant):
     name = b'dotencode'
 
     _requirement = b'dotencode'
 
     default = True
 
     description = _(
         b'storage of filenames beginning with a period or '
         b'space may not work correctly'
     )
 
     upgrademessage = _(
         b'repository will be better able to store files '
         b'beginning with a space or period'
     )
 
 
 @registerformatvariant
 class generaldelta(requirementformatvariant):
     name = b'generaldelta'
 
     _requirement = b'generaldelta'
 
     default = True
 
     description = _(
         b'deltas within internal storage are unable to '
         b'choose optimal revisions; repository is larger and '
         b'slower than it could be; interaction with other '
         b'repositories may require extra network and CPU '
         b'resources, making "hg push" and "hg pull" slower'
     )
 
     upgrademessage = _(
         b'repository storage will be able to create '
         b'optimal deltas; new repository data will be '
         b'smaller and read times should decrease; '
         b'interacting with other repositories using this '
         b'storage model should require less network and '
         b'CPU resources, making "hg push" and "hg pull" '
         b'faster'
     )
 
 
 @registerformatvariant
 class sharesafe(requirementformatvariant):
     name = b'exp-sharesafe'
     _requirement = requirements.SHARESAFE_REQUIREMENT
 
     default = False
 
     description = _(
         b'old shared repositories do not share source repository '
         b'requirements and config. This leads to various problems '
         b'when the source repository format is upgraded or some new '
         b'extensions are enabled.'
     )
 
     upgrademessage = _(
         b'Upgrades a repository to share-safe format so that future '
         b'shares of this repository share its requirements and configs.'
     )
 
     postdowngrademessage = _(
         b'repository downgraded to not use share safe mode, '
         b'existing shares will not work and needs to'
         b' be reshared.'
     )
 
     postupgrademessage = _(
         b'repository upgraded to share safe mode, existing'
         b' shares will still work in old non-safe mode. '
         b'Re-share existing shares to use them in safe mode'
         b' New shares will be created in safe mode.'
     )
 
 
 @registerformatvariant
 class sparserevlog(requirementformatvariant):
     name = b'sparserevlog'
 
     _requirement = requirements.SPARSEREVLOG_REQUIREMENT
 
     default = True
 
     description = _(
         b'in order to limit disk reading and memory usage on older '
         b'version, the span of a delta chain from its root to its '
         b'end is limited, whatever the relevant data in this span. '
         b'This can severly limit Mercurial ability to build good '
         b'chain of delta resulting is much more storage space being '
         b'taken and limit reusability of on disk delta during '
         b'exchange.'
     )
 
     upgrademessage = _(
         b'Revlog supports delta chain with more unused data '
         b'between payload. These gaps will be skipped at read '
         b'time. This allows for better delta chains, making a '
         b'better compression and faster exchange with server.'
     )
 
 
 @registerformatvariant
 class sidedata(requirementformatvariant):
     name = b'sidedata'
 
     _requirement = requirements.SIDEDATA_REQUIREMENT
 
     default = False
 
     description = _(
         b'Allows storage of extra data alongside a revision, '
         b'unlocking various caching options.'
     )
 
     upgrademessage = _(b'Allows storage of extra data alongside a revision.')
 
 
 @registerformatvariant
 class persistentnodemap(requirementformatvariant):
     name = b'persistent-nodemap'
 
     _requirement = requirements.NODEMAP_REQUIREMENT
 
     default = False
 
     description = _(
         b'persist the node -> rev mapping on disk to speedup lookup'
     )
 
     upgrademessage = _(b'Speedup revision lookup by node id.')
 
 
 @registerformatvariant
 class copiessdc(requirementformatvariant):
     name = b'copies-sdc'
 
     _requirement = requirements.COPIESSDC_REQUIREMENT
 
     default = False
 
     description = _(b'Stores copies information alongside changesets.')
 
     upgrademessage = _(
         b'Allows to use more efficient algorithm to deal with ' b'copy tracing.'
     )
 
 
 @registerformatvariant
 class removecldeltachain(formatvariant):
     name = b'plain-cl-delta'
 
     default = True
 
     description = _(
         b'changelog storage is using deltas instead of '
         b'raw entries; changelog reading and any '
         b'operation relying on changelog data are slower '
         b'than they could be'
     )
 
     upgrademessage = _(
         b'changelog storage will be reformated to '
         b'store raw entries; changelog reading will be '
         b'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 = b'compression'
     default = b'zlib'
 
     description = _(
         b'Compresion algorithm used to compress data. '
         b'Some engine are faster than other'
     )
 
     upgrademessage = _(
         b'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 = b'zlib'
         for req in repo.requirements:
             prefix = req.startswith
             if prefix(b'revlog-compression-') or prefix(b'exp-compression-'):
                 compression = req.split(b'-', 2)[2]
         return compression
 
     @classmethod
     def fromconfig(cls, repo):
         compengines = repo.ui.configlist(b'format', b'revlog-compression')
         # return the first valid value as the selection code would do
         for comp in compengines:
             if comp in util.compengines:
                 return comp
 
         # no valide compression found lets display it all for clarity
         return b','.join(compengines)
 
 
 @registerformatvariant
 class compressionlevel(formatvariant):
     name = b'compression-level'
     default = b'default'
 
     description = _(b'compression level')
 
     upgrademessage = _(b'revlog content will be recompressed')
 
     @classmethod
     def fromrepo(cls, repo):
         comp = compressionengine.fromrepo(repo)
         level = None
         if comp == b'zlib':
             level = repo.ui.configint(b'storage', b'revlog.zlib.level')
         elif comp == b'zstd':
             level = repo.ui.configint(b'storage', b'revlog.zstd.level')
         if level is None:
             return b'default'
         return bytes(level)
 
     @classmethod
     def fromconfig(cls, repo):
         comp = compressionengine.fromconfig(repo)
         level = None
         if comp == b'zlib':
             level = repo.ui.configint(b'storage', b'revlog.zlib.level')
         elif comp == b'zstd':
             level = repo.ui.configint(b'storage', b'revlog.zstd.level')
         if level is None:
             return b'default'
         return bytes(level)
 
 
 def find_format_upgrades(repo):
     """returns a list of format upgrades which can be perform on the repo"""
     upgrades = []
 
     # 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):
             upgrades.append(fv)
 
     return upgrades
 
 
 def find_format_downgrades(repo):
     """returns a list of format downgrades which will be performed on the repo
     because of disabled config option for them"""
 
     downgrades = []
 
     for fv in allformatvariant:
         # format variant exist in repo but does not exist in new repository
         # config
         if fv.fromrepo(repo) and not fv.fromconfig(repo):
             downgrades.append(fv)
 
     return downgrades
 
 
 ALL_OPTIMISATIONS = []
 
 
 def register_optimization(obj):
     ALL_OPTIMISATIONS.append(obj)
     return obj
 
 
 register_optimization(
     improvement(
         name=b're-delta-parent',
         type=OPTIMISATION,
         description=_(
             b'deltas within internal storage will be recalculated to '
             b'choose an optimal base revision where this was not '
             b'already done; the size of the repository may shrink and '
             b'various operations may become faster; the first time '
             b'this optimization is performed could slow down upgrade '
             b'execution considerably; subsequent invocations should '
             b'not run noticeably slower'
         ),
         upgrademessage=_(
             b'deltas within internal storage will choose a new '
             b'base revision if needed'
         ),
     )
 )
 
 register_optimization(
     improvement(
         name=b're-delta-multibase',
         type=OPTIMISATION,
         description=_(
             b'deltas within internal storage will be recalculated '
             b'against multiple base revision and the smallest '
             b'difference will be used; the size of the repository may '
             b'shrink significantly when there are many merges; this '
             b'optimization will slow down execution in proportion to '
             b'the number of merges in the repository and the amount '
             b'of files in the repository; this slow down should not '
             b'be significant unless there are tens of thousands of '
             b'files and thousands of merges'
         ),
         upgrademessage=_(
             b'deltas within internal storage will choose an '
             b'optimal delta by computing deltas against multiple '
             b'parents; may slow down execution time '
             b'significantly'
         ),
     )
 )
 
 register_optimization(
     improvement(
         name=b're-delta-all',
         type=OPTIMISATION,
         description=_(
             b'deltas within internal storage will always be '
             b'recalculated without reusing prior deltas; this will '
             b'likely make execution run several times slower; this '
             b'optimization is typically not needed'
         ),
         upgrademessage=_(
             b'deltas within internal storage will be fully '
             b'recomputed; this will likely drastically slow down '
             b'execution time'
         ),
     )
 )
 
 register_optimization(
     improvement(
         name=b're-delta-fulladd',
         type=OPTIMISATION,
         description=_(
             b'every revision will be re-added as if it was new '
             b'content. It will go through the full storage '
             b'mechanism giving extensions a chance to process it '
             b'(eg. lfs). This is similar to "re-delta-all" but even '
             b'slower since more logic is involved.'
         ),
         upgrademessage=_(
             b'each revision will be added as new content to the '
             b'internal storage; this will likely drastically slow '
             b'down execution time, but some extensions might need '
             b'it'
         ),
     )
 )
 
 
 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.
     return list(ALL_OPTIMISATIONS)
 
 
 def determine_upgrade_actions(
     repo, format_upgrades, optimizations, sourcereqs, destreqs
 ):
     """Determine upgrade actions that will be performed.
 
     Given a list of improvements as returned by ``find_format_upgrades`` 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 = []
 
     for d in format_upgrades:
         name = d._requirement
 
         # If the action is a requirement that doesn't show up in the
         # destination requirements, prune the action.
         if name is not None and name not in destreqs:
             continue
 
         newactions.append(d)
 
     newactions.extend(o for o in sorted(optimizations) if o not in newactions)
 
     # FUTURE consider adding some optimizations here for certain transitions.
     # e.g. adding generaldelta could schedule parent redeltas.
 
     return newactions
 
 
 class UpgradeOperation(object):
     """represent the work to be done during an upgrade"""
 
     def __init__(
         self,
         ui,
         new_requirements,
         current_requirements,
         upgrade_actions,
         removed_actions,
         revlogs_to_process,
     ):
         self.ui = ui
         self.new_requirements = new_requirements
         self.current_requirements = current_requirements
         # list of upgrade actions the operation will perform
         self.upgrade_actions = upgrade_actions
         self._upgrade_actions_names = set([a.name for a in upgrade_actions])
         self.removed_actions = removed_actions
         self.revlogs_to_process = revlogs_to_process
         # requirements which will be added by the operation
         self._added_requirements = (
             self.new_requirements - self.current_requirements
         )
         # requirements which will be removed by the operation
         self._removed_requirements = (
             self.current_requirements - self.new_requirements
         )
         # requirements which will be preserved by the operation
         self._preserved_requirements = (
             self.current_requirements & self.new_requirements
         )
         # optimizations which are not used and it's recommended that they
         # should use them
         all_optimizations = findoptimizations(None)
         self.unused_optimizations = [
             i for i in all_optimizations if i not in self.upgrade_actions
         ]
 
         # delta reuse mode of this upgrade operation
         self.delta_reuse_mode = revlog.revlog.DELTAREUSEALWAYS
         if b're-delta-all' in self._upgrade_actions_names:
             self.delta_reuse_mode = revlog.revlog.DELTAREUSENEVER
         elif b're-delta-parent' in self._upgrade_actions_names:
             self.delta_reuse_mode = revlog.revlog.DELTAREUSESAMEREVS
         elif b're-delta-multibase' in self._upgrade_actions_names:
             self.delta_reuse_mode = revlog.revlog.DELTAREUSESAMEREVS
         elif b're-delta-fulladd' in self._upgrade_actions_names:
             self.delta_reuse_mode = revlog.revlog.DELTAREUSEFULLADD
 
+        # should this operation force re-delta of both parents
+        self.force_re_delta_both_parents = (
+            b're-delta-multibase' in self._upgrade_actions_names
+        )
+
     def _write_labeled(self, l, label):
         """
         Utility function to aid writing of a list under one label
         """
         first = True
         for r in sorted(l):
             if not first:
                 self.ui.write(b', ')
             self.ui.write(r, label=label)
             first = False
 
     def print_requirements(self):
         self.ui.write(_(b'requirements\n'))
         self.ui.write(_(b'   preserved: '))
         self._write_labeled(
             self._preserved_requirements, "upgrade-repo.requirement.preserved"
         )
         self.ui.write((b'\n'))
         if self._removed_requirements:
             self.ui.write(_(b'   removed: '))
             self._write_labeled(
                 self._removed_requirements, "upgrade-repo.requirement.removed"
             )
             self.ui.write((b'\n'))
         if self._added_requirements:
             self.ui.write(_(b'   added: '))
             self._write_labeled(
                 self._added_requirements, "upgrade-repo.requirement.added"
             )
             self.ui.write((b'\n'))
         self.ui.write(b'\n')
 
     def print_optimisations(self):
         optimisations = [
             a for a in self.upgrade_actions if a.type == OPTIMISATION
         ]
         optimisations.sort(key=lambda a: a.name)
         if optimisations:
             self.ui.write(_(b'optimisations: '))
             self._write_labeled(
                 [a.name for a in optimisations],
                 "upgrade-repo.optimisation.performed",
             )
             self.ui.write(b'\n\n')
 
     def print_upgrade_actions(self):
         for a in self.upgrade_actions:
             self.ui.status(b'%s\n   %s\n\n' % (a.name, a.upgrademessage))
 
     def print_affected_revlogs(self):
         if not self.revlogs_to_process:
             self.ui.write((b'no revlogs to process\n'))
         else:
             self.ui.write((b'processed revlogs:\n'))
             for r in sorted(self.revlogs_to_process):
                 self.ui.write((b'  - %s\n' % r))
         self.ui.write((b'\n'))
 
     def print_unused_optimizations(self):
         for i in self.unused_optimizations:
             self.ui.status(_(b'%s\n   %s\n\n') % (i.name, i.description))
 
     def has_upgrade_action(self, name):
         """ Check whether the upgrade operation will perform this action """
         return name in self._upgrade_actions_names
 
     def print_post_op_messages(self):
         """ print post upgrade operation warning messages """
         for a in self.upgrade_actions:
             if a.postupgrademessage is not None:
                 self.ui.warn(b'%s\n' % a.postupgrademessage)
         for a in self.removed_actions:
             if a.postdowngrademessage is not None:
                 self.ui.warn(b'%s\n' % a.postdowngrademessage)
 
 
 ###  Code checking if a repository can got through the upgrade process at all. #
 
 
 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.
         b'revlogv1',
         # Introduced in Mercurial 0.9.2.
         b'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.
         requirements.TREEMANIFEST_REQUIREMENT,
         # This was a precursor to generaldelta and was never enabled by default.
         # It should (hopefully) not exist in the wild.
         b'parentdelta',
         # Upgrade should operate on the actual store, not the shared link.
         requirements.SHARED_REQUIREMENT,
     }
 
 
 def check_source_requirements(repo):
     """Ensure that no existing requirements prevent the repository upgrade"""
 
     required = requiredsourcerequirements(repo)
     missingreqs = required - repo.requirements
     if missingreqs:
         msg = _(b'cannot upgrade repository; requirement missing: %s')
         missingreqs = b', '.join(sorted(missingreqs))
         raise error.Abort(msg % missingreqs)
 
     blocking = blocksourcerequirements(repo)
     blockingreqs = blocking & repo.requirements
     if blockingreqs:
         m = _(b'cannot upgrade repository; unsupported source requirement: %s')
         blockingreqs = b', '.join(sorted(blockingreqs))
         raise error.Abort(m % blockingreqs)
 
 
 ### Verify the validity of the planned requirement changes ####################
 
 
 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.
     """
     supported = {
         requirements.SPARSEREVLOG_REQUIREMENT,
         requirements.SIDEDATA_REQUIREMENT,
         requirements.COPIESSDC_REQUIREMENT,
         requirements.NODEMAP_REQUIREMENT,
         requirements.SHARESAFE_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() == b'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.
     """
     supported = {
         b'dotencode',
         b'fncache',
         b'generaldelta',
         b'revlogv1',
         b'store',
         requirements.SPARSEREVLOG_REQUIREMENT,
         requirements.SIDEDATA_REQUIREMENT,
         requirements.COPIESSDC_REQUIREMENT,
         requirements.NODEMAP_REQUIREMENT,
         requirements.SHARESAFE_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() == b'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.
     """
     supported = {
         b'dotencode',
         b'fncache',
         b'generaldelta',
         requirements.SPARSEREVLOG_REQUIREMENT,
         requirements.SIDEDATA_REQUIREMENT,
         requirements.COPIESSDC_REQUIREMENT,
         requirements.NODEMAP_REQUIREMENT,
         requirements.SHARESAFE_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() == b'zstd':
                 supported.add(b'revlog-compression-zstd')
     return supported
 
 
 def check_requirements_changes(repo, new_reqs):
     old_reqs = repo.requirements
 
     support_removal = supportremovedrequirements(repo)
     no_remove_reqs = old_reqs - new_reqs - support_removal
     if no_remove_reqs:
         msg = _(b'cannot upgrade repository; requirement would be removed: %s')
         no_remove_reqs = b', '.join(sorted(no_remove_reqs))
         raise error.Abort(msg % no_remove_reqs)
 
     support_addition = allowednewrequirements(repo)
     no_add_reqs = new_reqs - old_reqs - support_addition
     if no_add_reqs:
         m = _(b'cannot upgrade repository; do not support adding requirement: ')
         no_add_reqs = b', '.join(sorted(no_add_reqs))
         raise error.Abort(m + no_add_reqs)
 
     supported = supporteddestrequirements(repo)
     unsupported_reqs = new_reqs - supported
     if unsupported_reqs:
         msg = _(
             b'cannot upgrade repository; do not support destination '
             b'requirement: %s'
         )
         unsupported_reqs = b', '.join(sorted(unsupported_reqs))
         raise error.Abort(msg % unsupported_reqs)

mercurial/upgrade_utils/engine.py

@@ -1,522 +1,520 b''
 # 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 ..pycompat import getattr
 from .. import (
     changelog,
     error,
     filelog,
     manifest,
     metadata,
     pycompat,
     requirements,
     revlog,
     scmutil,
     util,
     vfs as vfsmod,
 )
 
 
 def _revlogfrompath(repo, path):
     """Obtain a revlog from a repo path.
 
     An instance of the appropriate class is returned.
     """
     if path == b'00changelog.i':
         return changelog.changelog(repo.svfs)
     elif path.endswith(b'00manifest.i'):
         mandir = path[: -len(b'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 _copyrevlog(tr, destrepo, oldrl, unencodedname):
     """copy all relevant files for `oldrl` into `destrepo` store
 
     Files are copied "as is" without any transformation. The copy is performed
     without extra checks. Callers are responsible for making sure the copied
     content is compatible with format of the destination repository.
     """
     oldrl = getattr(oldrl, '_revlog', oldrl)
     newrl = _revlogfrompath(destrepo, unencodedname)
     newrl = getattr(newrl, '_revlog', newrl)
 
     oldvfs = oldrl.opener
     newvfs = newrl.opener
     oldindex = oldvfs.join(oldrl.indexfile)
     newindex = newvfs.join(newrl.indexfile)
     olddata = oldvfs.join(oldrl.datafile)
     newdata = newvfs.join(newrl.datafile)
 
     with newvfs(newrl.indexfile, b'w'):
         pass  # create all the directories
 
     util.copyfile(oldindex, newindex)
     copydata = oldrl.opener.exists(oldrl.datafile)
     if copydata:
         util.copyfile(olddata, newdata)
 
     if not (
         unencodedname.endswith(b'00changelog.i')
         or unencodedname.endswith(b'00manifest.i')
     ):
         destrepo.svfs.fncache.add(unencodedname)
         if copydata:
             destrepo.svfs.fncache.add(unencodedname[:-2] + b'.d')
 
 
 UPGRADE_CHANGELOG = b"changelog"
 UPGRADE_MANIFEST = b"manifest"
 UPGRADE_FILELOGS = b"all-filelogs"
 
 UPGRADE_ALL_REVLOGS = frozenset(
     [UPGRADE_CHANGELOG, UPGRADE_MANIFEST, UPGRADE_FILELOGS]
 )
 
 
 def getsidedatacompanion(srcrepo, dstrepo):
     sidedatacompanion = None
     removedreqs = srcrepo.requirements - dstrepo.requirements
     addedreqs = dstrepo.requirements - srcrepo.requirements
     if requirements.SIDEDATA_REQUIREMENT in removedreqs:
 
         def sidedatacompanion(rl, rev):
             rl = getattr(rl, '_revlog', rl)
             if rl.flags(rev) & revlog.REVIDX_SIDEDATA:
                 return True, (), {}, 0, 0
             return False, (), {}, 0, 0
 
     elif requirements.COPIESSDC_REQUIREMENT in addedreqs:
         sidedatacompanion = metadata.getsidedataadder(srcrepo, dstrepo)
     elif requirements.COPIESSDC_REQUIREMENT in removedreqs:
         sidedatacompanion = metadata.getsidedataremover(srcrepo, dstrepo)
     return sidedatacompanion
 
 
 def matchrevlog(revlogfilter, entry):
     """check if a revlog is selected for cloning.
 
     In other words, are there any updates which need to be done on revlog
     or it can be blindly copied.
 
     The store entry is checked against the passed filter"""
     if entry.endswith(b'00changelog.i'):
         return UPGRADE_CHANGELOG in revlogfilter
     elif entry.endswith(b'00manifest.i'):
         return UPGRADE_MANIFEST in revlogfilter
     return UPGRADE_FILELOGS in revlogfilter
 
 
 def _perform_clone(
     ui,
     dstrepo,
     tr,
     old_revlog,
     unencoded,
     upgrade_op,
     sidedatacompanion,
     oncopiedrevision,
 ):
     """ returns the new revlog object created"""
     newrl = None
     if matchrevlog(upgrade_op.revlogs_to_process, unencoded):
         ui.note(
             _(b'cloning %d revisions from %s\n') % (len(old_revlog), unencoded)
         )
         newrl = _revlogfrompath(dstrepo, unencoded)
         old_revlog.clone(
             tr,
             newrl,
             addrevisioncb=oncopiedrevision,
             deltareuse=upgrade_op.delta_reuse_mode,
-            forcedeltabothparents=upgrade_op.has_upgrade_action(
-                b're-delta-multibase'
-            ),
+            forcedeltabothparents=upgrade_op.force_re_delta_both_parents,
             sidedatacompanion=sidedatacompanion,
         )
     else:
         msg = _(b'blindly copying %s containing %i revisions\n')
         ui.note(msg % (unencoded, len(old_revlog)))
         _copyrevlog(tr, dstrepo, old_revlog, unencoded)
 
         newrl = _revlogfrompath(dstrepo, unencoded)
     return newrl
 
 
 def _clonerevlogs(
     ui,
     srcrepo,
     dstrepo,
     tr,
     upgrade_op,
 ):
     """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
 
     alldatafiles = list(srcrepo.store.walk())
     # mapping of data files which needs to be cloned
     # key is unencoded filename
     # value is revlog_object_from_srcrepo
     manifests = {}
     changelogs = {}
     filelogs = {}
 
     # 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 alldatafiles:
         if unencoded.endswith(b'.d'):
             continue
 
         rl = _revlogfrompath(srcrepo, unencoded)
 
         info = rl.storageinfo(
             exclusivefiles=True,
             revisionscount=True,
             trackedsize=True,
             storedsize=True,
         )
 
         revcount += info[b'revisionscount'] or 0
         datasize = info[b'storedsize'] or 0
         rawsize = info[b'trackedsize'] or 0
 
         srcsize += datasize
         srcrawsize += rawsize
 
         # This is for the separate progress bars.
         if isinstance(rl, changelog.changelog):
             changelogs[unencoded] = rl
             crevcount += len(rl)
             csrcsize += datasize
             crawsize += rawsize
         elif isinstance(rl, manifest.manifestrevlog):
             manifests[unencoded] = rl
             mcount += 1
             mrevcount += len(rl)
             msrcsize += datasize
             mrawsize += rawsize
         elif isinstance(rl, filelog.filelog):
             filelogs[unencoded] = rl
             fcount += 1
             frevcount += len(rl)
             fsrcsize += datasize
             frawsize += rawsize
         else:
             error.ProgrammingError(b'unknown revlog type')
 
     if not revcount:
         return
 
     ui.status(
         _(
             b'migrating %d total revisions (%d in filelogs, %d in manifests, '
             b'%d in changelog)\n'
         )
         % (revcount, frevcount, mrevcount, crevcount)
     )
     ui.status(
         _(b'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()
 
     sidedatacompanion = getsidedatacompanion(srcrepo, dstrepo)
 
     # Migrating filelogs
     ui.status(
         _(
             b'migrating %d filelogs containing %d revisions '
             b'(%s in store; %s tracked data)\n'
         )
         % (
             fcount,
             frevcount,
             util.bytecount(fsrcsize),
             util.bytecount(frawsize),
         )
     )
     progress = srcrepo.ui.makeprogress(_(b'file revisions'), total=frevcount)
     for unencoded, oldrl in sorted(filelogs.items()):
         newrl = _perform_clone(
             ui,
             dstrepo,
             tr,
             oldrl,
             unencoded,
             upgrade_op,
             sidedatacompanion,
             oncopiedrevision,
         )
         info = newrl.storageinfo(storedsize=True)
         fdstsize += info[b'storedsize'] or 0
     ui.status(
         _(
             b'finished migrating %d filelog revisions across %d '
             b'filelogs; change in size: %s\n'
         )
         % (frevcount, fcount, util.bytecount(fdstsize - fsrcsize))
     )
 
     # Migrating manifests
     ui.status(
         _(
             b'migrating %d manifests containing %d revisions '
             b'(%s in store; %s tracked data)\n'
         )
         % (
             mcount,
             mrevcount,
             util.bytecount(msrcsize),
             util.bytecount(mrawsize),
         )
     )
     if progress:
         progress.complete()
     progress = srcrepo.ui.makeprogress(
         _(b'manifest revisions'), total=mrevcount
     )
     for unencoded, oldrl in sorted(manifests.items()):
         newrl = _perform_clone(
             ui,
             dstrepo,
             tr,
             oldrl,
             unencoded,
             upgrade_op,
             sidedatacompanion,
             oncopiedrevision,
         )
         info = newrl.storageinfo(storedsize=True)
         mdstsize += info[b'storedsize'] or 0
     ui.status(
         _(
             b'finished migrating %d manifest revisions across %d '
             b'manifests; change in size: %s\n'
         )
         % (mrevcount, mcount, util.bytecount(mdstsize - msrcsize))
     )
 
     # Migrating changelog
     ui.status(
         _(
             b'migrating changelog containing %d revisions '
             b'(%s in store; %s tracked data)\n'
         )
         % (
             crevcount,
             util.bytecount(csrcsize),
             util.bytecount(crawsize),
         )
     )
     if progress:
         progress.complete()
     progress = srcrepo.ui.makeprogress(
         _(b'changelog revisions'), total=crevcount
     )
     for unencoded, oldrl in sorted(changelogs.items()):
         newrl = _perform_clone(
             ui,
             dstrepo,
             tr,
             oldrl,
             unencoded,
             upgrade_op,
             sidedatacompanion,
             oncopiedrevision,
         )
         info = newrl.storageinfo(storedsize=True)
         cdstsize += info[b'storedsize'] or 0
     progress.complete()
     ui.status(
         _(
             b'finished migrating %d changelog revisions; change in size: '
             b'%s\n'
         )
         % (crevcount, util.bytecount(cdstsize - csrcsize))
     )
 
     dstsize = fdstsize + mdstsize + cdstsize
     ui.status(
         _(
             b'finished migrating %d total revisions; total change in store '
             b'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((b'.i', b'.d', b'.n', b'.nd')):
         return False
     # Skip transaction related files.
     if path.startswith(b'undo'):
         return False
     # Only copy regular files.
     if mode != stat.S_IFREG:
         return False
     # Skip other skipped files.
     if path in (b'lock', b'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 upgrade(ui, srcrepo, dstrepo, upgrade_op):
     """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.status(
         _(
             b'(it is safe to interrupt this process any time before '
             b'data migration completes)\n'
         )
     )
 
     with dstrepo.transaction(b'upgrade') as tr:
         _clonerevlogs(
             ui,
             srcrepo,
             dstrepo,
             tr,
             upgrade_op,
         )
 
     # Now copy other files in the store directory.
     # The sorted() makes execution deterministic.
     for p, kind, st in sorted(srcrepo.store.vfs.readdir(b'', stat=True)):
         if not _filterstorefile(
             srcrepo, dstrepo, upgrade_op.new_requirements, p, kind, st
         ):
             continue
 
         srcrepo.ui.status(_(b'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.status(_(b'data fully migrated to temporary repository\n'))
 
     backuppath = pycompat.mkdtemp(prefix=b'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(b'requires'), backupvfs.join(b'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.status(
         _(
             b'marking source repository as being upgraded; clients will be '
             b'unable to read from repository\n'
         )
     )
     scmutil.writereporequirements(
         srcrepo, srcrepo.requirements | {b'upgradeinprogress'}
     )
 
     ui.status(_(b'starting in-place swap of repository data\n'))
     ui.status(_(b'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.status(_(b'replacing store...\n'))
     tstart = util.timer()
     util.rename(srcrepo.spath, backupvfs.join(b'store'))
     util.rename(dstrepo.spath, srcrepo.spath)
     elapsed = util.timer() - tstart
     ui.status(
         _(
             b'store replacement complete; repository was inconsistent for '
             b'%0.1fs\n'
         )
         % elapsed
     )
 
     # We first write the requirements file. Any new requirements will lock
     # out legacy clients.
     ui.status(
         _(
             b'finalizing requirements file and making repository readable '
             b'again\n'
         )
     )
     scmutil.writereporequirements(srcrepo, upgrade_op.new_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(b'store/lock')
 
     return backuppath