##// END OF EJS Templates
strip: make query to get new bookmark target cheaper...
strip: make query to get new bookmark target cheaper The current query to get the new bookmark target for stripped revisions involves multiple walks up the DAG, and is really expensive, taking over 2.5 seconds on a repository with over 400,000 changesets even if just one changeset is being stripped. A slightly simplified version of the current query is max(heads(::<tostrip> - <tostrip>)) We make two observations here. 1. For any set s, max(heads(s)) == max(s). That is because revision numbers define a topological order, so that the element with the highest revision number in s will not have any children in s. 2. For any set s, max(::s - s) == max(parents(s) - s). In other words, the ancestor of s with the highest revision number not in s is a parent of one of the revs in s. Why? Because if it were an ancestor but not a parent of s, it would have a descendant that would be a parent of s. This descendant would have a higher revision number, leading to a contradiction. Combining these two observations, we rewrite the revset query as max(parents(<tostrip>) - <tostrip>) The time complexity is now linear in the number of changesets being stripped. For the above repository, the query now takes 0.1 seconds when one changeset is stripped. This speeds up operations that use repair.strip, like the rebase and strip commands.

File last commit:

r18040:fe8caf28 default
r18040:fe8caf28 default
Show More
repair.py
203 lines | 7.0 KiB | text/x-python | PythonLexer
# repair.py - functions for repository repair for mercurial
#
# Copyright 2005, 2006 Chris Mason <mason@suse.com>
# Copyright 2007 Matt Mackall
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from mercurial import changegroup
from mercurial.node import short
from mercurial.i18n import _
import os
import errno
def _bundle(repo, bases, heads, node, suffix, compress=True):
"""create a bundle with the specified revisions as a backup"""
cg = repo.changegroupsubset(bases, heads, 'strip')
backupdir = repo.join("strip-backup")
if not os.path.isdir(backupdir):
os.mkdir(backupdir)
name = os.path.join(backupdir, "%s-%s.hg" % (short(node), suffix))
if compress:
bundletype = "HG10BZ"
else:
bundletype = "HG10UN"
return changegroup.writebundle(cg, name, bundletype)
def _collectfiles(repo, striprev):
"""find out the filelogs affected by the strip"""
files = set()
for x in xrange(striprev, len(repo)):
files.update(repo[x].files())
return sorted(files)
def _collectbrokencsets(repo, files, striprev):
"""return the changesets which will be broken by the truncation"""
s = set()
def collectone(revlog):
linkgen = (revlog.linkrev(i) for i in revlog)
# find the truncation point of the revlog
for lrev in linkgen:
if lrev >= striprev:
break
# see if any revision after this point has a linkrev
# less than striprev (those will be broken by strip)
for lrev in linkgen:
if lrev < striprev:
s.add(lrev)
collectone(repo.manifest)
for fname in files:
collectone(repo.file(fname))
return s
def strip(ui, repo, nodelist, backup="all", topic='backup'):
repo = repo.unfiltered()
# It simplifies the logic around updating the branchheads cache if we only
# have to consider the effect of the stripped revisions and not revisions
# missing because the cache is out-of-date.
repo.updatebranchcache()
cl = repo.changelog
# TODO handle undo of merge sets
if isinstance(nodelist, str):
nodelist = [nodelist]
striplist = [cl.rev(node) for node in nodelist]
striprev = min(striplist)
# Generate set of branches who will have nodes stripped.
striprevs = repo.revs("%ld::", striplist)
stripbranches = set([repo[rev].branch() for rev in striprevs])
# Set of potential new heads resulting from the strip. The parents of any
# node removed could be a new head because the node to be removed could have
# been the only child of the parent.
newheadrevs = repo.revs("parents(%ld::) - %ld::", striprevs, striprevs)
newheadnodes = set([cl.node(rev) for rev in newheadrevs])
newheadbranches = set([repo[rev].branch() for rev in newheadrevs])
keeppartialbundle = backup == 'strip'
# Some revisions with rev > striprev may not be descendants of striprev.
# We have to find these revisions and put them in a bundle, so that
# we can restore them after the truncations.
# To create the bundle we use repo.changegroupsubset which requires
# the list of heads and bases of the set of interesting revisions.
# (head = revision in the set that has no descendant in the set;
# base = revision in the set that has no ancestor in the set)
tostrip = set(striplist)
for rev in striplist:
for desc in cl.descendants([rev]):
tostrip.add(desc)
files = _collectfiles(repo, striprev)
saverevs = _collectbrokencsets(repo, files, striprev)
# compute heads
saveheads = set(saverevs)
for r in xrange(striprev + 1, len(cl)):
if r not in tostrip:
saverevs.add(r)
saveheads.difference_update(cl.parentrevs(r))
saveheads.add(r)
saveheads = [cl.node(r) for r in saveheads]
# compute base nodes
if saverevs:
descendants = set(cl.descendants(saverevs))
saverevs.difference_update(descendants)
savebases = [cl.node(r) for r in saverevs]
stripbases = [cl.node(r) for r in tostrip]
# For a set s, max(parents(s) - s) is the same as max(heads(::s - s)), but
# is much faster
newbmtarget = repo.revs('max(parents(%ld) - (%ld))', tostrip, tostrip)
if newbmtarget:
newbmtarget = repo[newbmtarget[0]].node()
else:
newbmtarget = '.'
bm = repo._bookmarks
updatebm = []
for m in bm:
rev = repo[bm[m]].rev()
if rev in tostrip:
updatebm.append(m)
# create a changegroup for all the branches we need to keep
backupfile = None
if backup == "all":
backupfile = _bundle(repo, stripbases, cl.heads(), node, topic)
repo.ui.status(_("saved backup bundle to %s\n") % backupfile)
if saveheads or savebases:
# do not compress partial bundle if we remove it from disk later
chgrpfile = _bundle(repo, savebases, saveheads, node, 'temp',
compress=keeppartialbundle)
mfst = repo.manifest
tr = repo.transaction("strip")
offset = len(tr.entries)
try:
tr.startgroup()
cl.strip(striprev, tr)
mfst.strip(striprev, tr)
for fn in files:
repo.file(fn).strip(striprev, tr)
tr.endgroup()
try:
for i in xrange(offset, len(tr.entries)):
file, troffset, ignore = tr.entries[i]
repo.sopener(file, 'a').truncate(troffset)
tr.close()
except: # re-raises
tr.abort()
raise
if saveheads or savebases:
ui.note(_("adding branch\n"))
f = open(chgrpfile, "rb")
gen = changegroup.readbundle(f, chgrpfile)
if not repo.ui.verbose:
# silence internal shuffling chatter
repo.ui.pushbuffer()
repo.addchangegroup(gen, 'strip', 'bundle:' + chgrpfile, True)
if not repo.ui.verbose:
repo.ui.popbuffer()
f.close()
if not keeppartialbundle:
os.unlink(chgrpfile)
# remove undo files
for undofile in repo.undofiles():
try:
os.unlink(undofile)
except OSError, e:
if e.errno != errno.ENOENT:
ui.warn(_('error removing %s: %s\n') % (undofile, str(e)))
for m in updatebm:
bm[m] = repo[newbmtarget].node()
bm.write()
except: # re-raises
if backupfile:
ui.warn(_("strip failed, full bundle stored in '%s'\n")
% backupfile)
elif saveheads:
ui.warn(_("strip failed, partial bundle stored in '%s'\n")
% chgrpfile)
raise
if len(stripbranches) == 1 and len(newheadbranches) == 1 \
and stripbranches == newheadbranches:
repo.destroyed(newheadnodes)
else:
# Multiple branches involved in strip. Will allow branchcache to become
# invalid and later on rebuilt from scratch
repo.destroyed()