##// END OF EJS Templates
revlog: linearize created changegroups in generaldelta revlogs...
revlog: linearize created changegroups in generaldelta revlogs This greatly improves the speed of the bundling process, and often reduces the bundle size considerably. (Although if the repository is already ordered, this has little effect on both time and bundle size.) For non-generaldelta clients, the reduced bundle size translates to a reduced repository size, similar to shrinking the revlogs (which uses the exact same algorithm). For generaldelta clients the difference is minor. When the new bundle format comes, reordering will not be necessary since we can then store the deltaparent relationsships directly. The eventual default behavior for clients and servers is presented in the table below, where "new" implies support for GD as well as the new bundle format: old client new client old server old bundle, no reorder old bundle, no reorder new server, non-GD old bundle, no reorder[1] old bundle, no reorder[2] new server, GD old bundle, reorder[3] new bundle, no reorder[4] [1] reordering is expensive on the server in this case, skip it [2] client can choose to do its own redelta here [3] reordering is needed because otherwise the pull does a lot of extra work on the server [4] reordering isn't needed because client can get deltabase in bundle format Currently, the default is to reorder on GD-servers, and not otherwise. A new setting, bundle.reorder, has been added to override the default reordering behavior. It can be set to either 'auto' (the default), or any true or false value as a standard boolean setting, to either force the reordering on or off regardless of generaldelta. Some timing data from a relatively branch test repository follows. All bundling is done with --all --type none options. Non-generaldelta, non-shrunk repo: ----------------------------------- Size: 276M Without reorder (default): Bundle time: 14.4 seconds Bundle size: 939M With reorder: Bundle time: 1 minute, 29.3 seconds Bundle size: 381M Generaldelta, non-shrunk repo: ----------------------------------- Size: 87M Without reorder: Bundle time: 2 minutes, 1.4 seconds Bundle size: 939M With reorder (default): Bundle time: 25.5 seconds Bundle size: 381M

File last commit:

r13408:19ad316e default
r14365:a8e3931e default
Show More
transaction.py
183 lines | 5.1 KiB | text/x-python | PythonLexer
# transaction.py - simple journalling scheme for mercurial
#
# This transaction scheme is intended to gracefully handle program
# errors and interruptions. More serious failures like system crashes
# can be recovered with an fsck-like tool. As the whole repository is
# effectively log-structured, this should amount to simply truncating
# anything that isn't referenced in the changelog.
#
# Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from i18n import _
import os, errno
import error, util
def active(func):
def _active(self, *args, **kwds):
if self.count == 0:
raise error.Abort(_(
'cannot use transaction when it is already committed/aborted'))
return func(self, *args, **kwds)
return _active
def _playback(journal, report, opener, entries, unlink=True):
for f, o, ignore in entries:
if o or not unlink:
try:
fp = opener(f, 'a')
fp.truncate(o)
fp.close()
except IOError:
report(_("failed to truncate %s\n") % f)
raise
else:
try:
fp = opener(f)
fn = fp.name
fp.close()
util.unlink(fn)
except (IOError, OSError), inst:
if inst.errno != errno.ENOENT:
raise
util.unlink(journal)
class transaction(object):
def __init__(self, report, opener, journal, after=None, createmode=None):
self.count = 1
self.usages = 1
self.report = report
self.opener = opener
self.after = after
self.entries = []
self.map = {}
self.journal = journal
self._queue = []
self.file = util.posixfile(self.journal, "w")
if createmode is not None:
os.chmod(self.journal, createmode & 0666)
def __del__(self):
if self.journal:
self._abort()
@active
def startgroup(self):
self._queue.append([])
@active
def endgroup(self):
q = self._queue.pop()
d = ''.join(['%s\0%d\n' % (x[0], x[1]) for x in q])
self.entries.extend(q)
self.file.write(d)
self.file.flush()
@active
def add(self, file, offset, data=None):
if file in self.map:
return
if self._queue:
self._queue[-1].append((file, offset, data))
return
self.entries.append((file, offset, data))
self.map[file] = len(self.entries) - 1
# add enough data to the journal to do the truncate
self.file.write("%s\0%d\n" % (file, offset))
self.file.flush()
@active
def find(self, file):
if file in self.map:
return self.entries[self.map[file]]
return None
@active
def replace(self, file, offset, data=None):
'''
replace can only replace already committed entries
that are not pending in the queue
'''
if file not in self.map:
raise KeyError(file)
index = self.map[file]
self.entries[index] = (file, offset, data)
self.file.write("%s\0%d\n" % (file, offset))
self.file.flush()
@active
def nest(self):
self.count += 1
self.usages += 1
return self
def release(self):
if self.count > 0:
self.usages -= 1
# if the transaction scopes are left without being closed, fail
if self.count > 0 and self.usages == 0:
self._abort()
def running(self):
return self.count > 0
@active
def close(self):
'''commit the transaction'''
self.count -= 1
if self.count != 0:
return
self.file.close()
self.entries = []
if self.after:
self.after()
if os.path.isfile(self.journal):
util.unlink(self.journal)
self.journal = None
@active
def abort(self):
'''abort the transaction (generally called on error, or when the
transaction is not explicitly committed before going out of
scope)'''
self._abort()
def _abort(self):
self.count = 0
self.usages = 0
self.file.close()
try:
if not self.entries:
if self.journal:
util.unlink(self.journal)
return
self.report(_("transaction abort!\n"))
try:
_playback(self.journal, self.report, self.opener,
self.entries, False)
self.report(_("rollback completed\n"))
except:
self.report(_("rollback failed - please run hg recover\n"))
finally:
self.journal = None
def rollback(opener, file, report):
entries = []
fp = util.posixfile(file)
lines = fp.readlines()
fp.close()
for l in lines:
f, o = l.split('\0')
entries.append((f, int(o), None))
_playback(file, report, opener, entries)