##// END OF EJS Templates
copy: add flag for disabling copy tracing...
copy: add flag for disabling copy tracing Copy tracing can be up to 80% of rebase time when rebasing stacks of commits in large repos (hundreds of thousands of files). This provides the option of turning off the majority of copy tracing. It does not turn off _forwardcopies() since that is used to carry copy information inside a commit across a rebase. This will affect the situation where a user edits a file, then rebases on top of commits that have moved that file. The move will not be detected and the user will have to manually resolve the issue (possibly by redoing the rebase with this flag off). The reason to have a flag instead of trying to fix the actual copy tracing performance is that copy tracing is fundamentally an O(number of files in the repo) operation. In order to know if file X in the rebase source was copied anywhere, we have to walk the filelog for every new file that exists in the rebase destination (i.e. a file in the destination that is not in the common ancestor). Without an index that lets us trace forward (i.e. from file Y in the common ancestor forward to the rebase destination), it will never be an O(number of changes in my branch) operation. In mozilla-central, rebasing a 3 commit stack across 20,000 revs goes from 39s to 11s.

File last commit:

r25987:c6d049a5 default
r26013:38f92d12 default
Show More
treediscovery.py
160 lines | 5.2 KiB | text/x-python | PythonLexer
Peter Arrenbrecht
discovery: add new set-based discovery...
r14164 # discovery.py - protocol changeset discovery functions
#
# Copyright 2010 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.
Gregory Szorc
treediscovery: use absolute_import
r25987 from __future__ import absolute_import
Martin von Zweigbergk
util: drop alias for collections.deque...
r25113 import collections
Gregory Szorc
treediscovery: use absolute_import
r25987
from .i18n import _
from .node import (
nullid,
short,
)
from . import (
error,
util,
)
Peter Arrenbrecht
discovery: add new set-based discovery...
r14164
def findcommonincoming(repo, remote, heads=None, force=False):
"""Return a tuple (common, fetch, heads) used to identify the common
subset of nodes between repo and remote.
"common" is a list of (at least) the heads of the common subset.
"fetch" is a list of roots of the nodes that would be incoming, to be
supplied to changegroupsubset.
"heads" is either the supplied heads, or else the remote's heads.
"""
Pierre-Yves David
discovery: stop using nodemap for membership testing...
r20225 knownnode = repo.changelog.hasnode
Peter Arrenbrecht
discovery: add new set-based discovery...
r14164 search = []
fetch = set()
seen = set()
seenbranch = set()
base = set()
if not heads:
heads = remote.heads()
if repo.changelog.tip() == nullid:
base.add(nullid)
if heads != [nullid]:
return [nullid], [nullid], list(heads)
Peter Arrenbrecht
treediscovery: fix regression when run against older repos (issue2793)...
r14199 return [nullid], [], heads
Peter Arrenbrecht
discovery: add new set-based discovery...
r14164
# assume we're closer to the tip than the root
# and start by examining the heads
repo.ui.status(_("searching for changes\n"))
unknown = []
for h in heads:
Pierre-Yves David
discovery: stop using nodemap for membership testing...
r20225 if not knownnode(h):
Peter Arrenbrecht
discovery: add new set-based discovery...
r14164 unknown.append(h)
else:
base.add(h)
Peter Arrenbrecht
treediscovery: fix regression when run against older repos (issue2793)...
r14199 if not unknown:
return list(base), [], list(heads)
Peter Arrenbrecht
discovery: add new set-based discovery...
r14164 req = set(unknown)
reqcnt = 0
# search through remote branches
# a 'branch' here is a linear segment of history, with four parts:
# head, root, first parent, second parent
# (a branch always has two parents (or none) by definition)
Martin von Zweigbergk
util: drop alias for collections.deque...
r25113 unknown = collections.deque(remote.branches(unknown))
Peter Arrenbrecht
discovery: add new set-based discovery...
r14164 while unknown:
r = []
while unknown:
Bryan O'Sullivan
cleanup: use the deque type where appropriate...
r16803 n = unknown.popleft()
Peter Arrenbrecht
discovery: add new set-based discovery...
r14164 if n[0] in seen:
continue
repo.ui.debug("examining %s:%s\n"
% (short(n[0]), short(n[1])))
if n[0] == nullid: # found the end of the branch
pass
elif n in seenbranch:
repo.ui.debug("branch already found\n")
continue
Pierre-Yves David
discovery: stop using nodemap for membership testing...
r20225 elif n[1] and knownnode(n[1]): # do we know the base?
Peter Arrenbrecht
discovery: add new set-based discovery...
r14164 repo.ui.debug("found incomplete branch %s:%s\n"
% (short(n[0]), short(n[1])))
search.append(n[0:2]) # schedule branch range for scanning
seenbranch.add(n)
else:
if n[1] not in seen and n[1] not in fetch:
Pierre-Yves David
discovery: stop using nodemap for membership testing...
r20225 if knownnode(n[2]) and knownnode(n[3]):
Peter Arrenbrecht
discovery: add new set-based discovery...
r14164 repo.ui.debug("found new changeset %s\n" %
short(n[1]))
fetch.add(n[1]) # earliest unknown
for p in n[2:4]:
Pierre-Yves David
discovery: stop using nodemap for membership testing...
r20225 if knownnode(p):
Peter Arrenbrecht
discovery: add new set-based discovery...
r14164 base.add(p) # latest known
for p in n[2:4]:
Pierre-Yves David
discovery: stop using nodemap for membership testing...
r20225 if p not in req and not knownnode(p):
Peter Arrenbrecht
discovery: add new set-based discovery...
r14164 r.append(p)
req.add(p)
seen.add(n[0])
if r:
reqcnt += 1
repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
repo.ui.debug("request %d: %s\n" %
(reqcnt, " ".join(map(short, r))))
for p in xrange(0, len(r), 10):
for b in remote.branches(r[p:p + 10]):
repo.ui.debug("received %s:%s\n" %
(short(b[0]), short(b[1])))
unknown.append(b)
# do binary search on the branches we found
while search:
newsearch = []
reqcnt += 1
repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
for n, l in zip(search, remote.between(search)):
l.append(n[1])
p = n[0]
f = 1
for i in l:
repo.ui.debug("narrowing %d:%d %s\n" % (f, len(l), short(i)))
Pierre-Yves David
discovery: stop using nodemap for membership testing...
r20225 if knownnode(i):
Peter Arrenbrecht
discovery: add new set-based discovery...
r14164 if f <= 2:
repo.ui.debug("found new branch changeset %s\n" %
short(p))
fetch.add(p)
base.add(i)
else:
repo.ui.debug("narrowed branch search to %s:%s\n"
% (short(p), short(i)))
newsearch.append((p, i))
break
p, f = i, f * 2
search = newsearch
# sanity check our fetch list
for f in fetch:
Pierre-Yves David
discovery: stop using nodemap for membership testing...
r20225 if knownnode(f):
Peter Arrenbrecht
discovery: add new set-based discovery...
r14164 raise error.RepoError(_("already have changeset ")
+ short(f[:4]))
base = list(base)
if base == [nullid]:
if force:
repo.ui.warn(_("warning: repository is unrelated\n"))
else:
raise util.Abort(_("repository is unrelated"))
repo.ui.debug("found new changesets starting at " +
" ".join([short(f) for f in fetch]) + "\n")
repo.ui.progress(_('searching'), None)
repo.ui.debug("%d total queries\n" % reqcnt)
return base, list(fetch), heads