##// END OF EJS Templates
cext: add Python 3.10 support...
cext: add Python 3.10 support * Replace "Py_TYPE(obj) = type;" with "Py_SET_TYPE(obj, type);" * Add pythoncapi_compat.h header file to get Py_SET_TYPE() on Python 2.7-3.8. Header file added to mercurial/ and contrib/python-zstandard/zstd/common/. In Python 3.10, Py_TYPE(obj) must not longer be used as an l-value. pythoncapi_compat.h comes from: https://github.com/pythoncapi/pythoncapi_compat Differential Revision: https://phab.mercurial-scm.org/D9825

File last commit:

r47052:4b0192f5 default
r47090:e92ca942 default
Show More
actions.py
911 lines | 29.0 KiB | text/x-python | PythonLexer
# 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'share-safe'
_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:
if fv.name == b'compression':
# If there is a compression change between repository
# and config, destination repository compression will change
# and current compression will be removed.
if fv.fromrepo(repo) != fv.fromconfig(repo):
downgrades.append(fv)
continue
# 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)