##// END OF EJS Templates
engine: refactor how total dstsize is calculated...
engine: refactor how total dstsize is calculated Instead of increasing it with each revlog, we just get the sum of total destination changelog, manifest and filelogs sizes. Differential Revision: https://phab.mercurial-scm.org/D9665

File last commit:

r46831:5dfa837d default
r46831:5dfa837d default
Show More
engine.py
543 lines | 15.9 KiB | text/x-python | PythonLexer
upgrade: split actual upgrade code away from the main module...
r46661 # 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
Pulkit Goyal
engine: refactor actual cloning code into separate function...
r46809 def _perform_clone(
ui,
dstrepo,
tr,
old_revlog,
unencoded,
deltareuse,
forcedeltabothparents,
revlogs,
sidedatacompanion,
oncopiedrevision,
):
""" returns the new revlog object created"""
newrl = None
if matchrevlog(revlogs, 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=deltareuse,
forcedeltabothparents=forcedeltabothparents,
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
upgrade: split actual upgrade code away from the main module...
r46661 def _clonerevlogs(
ui,
srcrepo,
dstrepo,
tr,
deltareuse,
forcedeltabothparents,
revlogs=UPGRADE_ALL_REVLOGS,
):
"""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())
Pulkit Goyal
engine: unwrap a hard to understand for loop...
r46810 # mapping of data files which needs to be cloned
# key is unencoded filename
# value is revlog_object_from_srcrepo
manifests = {}
changelogs = {}
filelogs = {}
upgrade: split actual upgrade code away from the main module...
r46661
# 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):
Pulkit Goyal
engine: unwrap a hard to understand for loop...
r46810 changelogs[unencoded] = rl
upgrade: split actual upgrade code away from the main module...
r46661 crevcount += len(rl)
csrcsize += datasize
crawsize += rawsize
elif isinstance(rl, manifest.manifestrevlog):
Pulkit Goyal
engine: unwrap a hard to understand for loop...
r46810 manifests[unencoded] = rl
upgrade: split actual upgrade code away from the main module...
r46661 mcount += 1
mrevcount += len(rl)
msrcsize += datasize
mrawsize += rawsize
elif isinstance(rl, filelog.filelog):
Pulkit Goyal
engine: unwrap a hard to understand for loop...
r46810 filelogs[unencoded] = rl
upgrade: split actual upgrade code away from the main module...
r46661 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)
Pulkit Goyal
engine: unwrap a hard to understand for loop...
r46810 # 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()):
Pulkit Goyal
engine: refactor actual cloning code into separate function...
r46809 newrl = _perform_clone(
ui,
dstrepo,
tr,
oldrl,
unencoded,
deltareuse,
forcedeltabothparents,
revlogs,
sidedatacompanion,
oncopiedrevision,
)
upgrade: split actual upgrade code away from the main module...
r46661 info = newrl.storageinfo(storedsize=True)
Pulkit Goyal
engine: refactor how total dstsize is calculated...
r46831 fdstsize += info[b'storedsize'] or 0
Pulkit Goyal
engine: unwrap a hard to understand for loop...
r46810 ui.status(
_(
b'finished migrating %d filelog revisions across %d '
b'filelogs; change in size: %s\n'
)
% (frevcount, fcount, util.bytecount(fdstsize - fsrcsize))
)
upgrade: split actual upgrade code away from the main module...
r46661
Pulkit Goyal
engine: unwrap a hard to understand for loop...
r46810 # 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,
deltareuse,
forcedeltabothparents,
revlogs,
sidedatacompanion,
oncopiedrevision,
)
info = newrl.storageinfo(storedsize=True)
Pulkit Goyal
engine: refactor how total dstsize is calculated...
r46831 mdstsize += info[b'storedsize'] or 0
Pulkit Goyal
engine: unwrap a hard to understand for loop...
r46810 ui.status(
_(
b'finished migrating %d manifest revisions across %d '
b'manifests; change in size: %s\n'
)
% (mrevcount, mcount, util.bytecount(mdstsize - msrcsize))
)
upgrade: split actual upgrade code away from the main module...
r46661
Pulkit Goyal
engine: unwrap a hard to understand for loop...
r46810 # 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,
deltareuse,
forcedeltabothparents,
revlogs,
sidedatacompanion,
oncopiedrevision,
)
info = newrl.storageinfo(storedsize=True)
Pulkit Goyal
engine: refactor how total dstsize is calculated...
r46831 cdstsize += info[b'storedsize'] or 0
upgrade: split actual upgrade code away from the main module...
r46661 progress.complete()
ui.status(
_(
b'finished migrating %d changelog revisions; change in size: '
b'%s\n'
)
% (crevcount, util.bytecount(cdstsize - csrcsize))
)
Pulkit Goyal
engine: refactor how total dstsize is calculated...
r46831 dstsize = fdstsize + mdstsize + cdstsize
upgrade: split actual upgrade code away from the main module...
r46661 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.
"""
upgrade: start moving the "to be happening" data in a dedicated object...
r46673 def upgrade(ui, srcrepo, dstrepo, upgrade_op):
upgrade: split actual upgrade code away from the main module...
r46661 """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'
)
)
Pulkit Goyal
upgrade: rename actions to upgrade_actions...
r46827 if upgrade_op.has_upgrade_action(b're-delta-all'):
upgrade: split actual upgrade code away from the main module...
r46661 deltareuse = revlog.revlog.DELTAREUSENEVER
Pulkit Goyal
upgrade: rename actions to upgrade_actions...
r46827 elif upgrade_op.has_upgrade_action(b're-delta-parent'):
upgrade: split actual upgrade code away from the main module...
r46661 deltareuse = revlog.revlog.DELTAREUSESAMEREVS
Pulkit Goyal
upgrade: rename actions to upgrade_actions...
r46827 elif upgrade_op.has_upgrade_action(b're-delta-multibase'):
upgrade: split actual upgrade code away from the main module...
r46661 deltareuse = revlog.revlog.DELTAREUSESAMEREVS
Pulkit Goyal
upgrade: rename actions to upgrade_actions...
r46827 elif upgrade_op.has_upgrade_action(b're-delta-fulladd'):
upgrade: split actual upgrade code away from the main module...
r46661 deltareuse = revlog.revlog.DELTAREUSEFULLADD
else:
deltareuse = revlog.revlog.DELTAREUSEALWAYS
with dstrepo.transaction(b'upgrade') as tr:
_clonerevlogs(
ui,
srcrepo,
dstrepo,
tr,
deltareuse,
Pulkit Goyal
upgrade: rename actions to upgrade_actions...
r46827 upgrade_op.has_upgrade_action(b're-delta-multibase'),
upgrade: start moving the "to be happening" data in a dedicated object...
r46673 revlogs=upgrade_op.revlogs_to_process,
upgrade: split actual upgrade code away from the main module...
r46661 )
# 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)):
upgrade: start moving the "to be happening" data in a dedicated object...
r46673 if not _filterstorefile(
Pulkit Goyal
upgrade: move `printrequirements()` to UpgradeOperation class...
r46807 srcrepo, dstrepo, upgrade_op.new_requirements, p, kind, st
upgrade: start moving the "to be happening" data in a dedicated object...
r46673 ):
upgrade: split actual upgrade code away from the main module...
r46661 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'
)
)
Pulkit Goyal
upgrade: move `printrequirements()` to UpgradeOperation class...
r46807 scmutil.writereporequirements(srcrepo, upgrade_op.new_requirements)
upgrade: split actual upgrade code away from the main module...
r46661
# 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