##// END OF EJS Templates
rebase: skip resolved but emptied revisions...
rebase: skip resolved but emptied revisions When rebasing, if a conflict occurs and is resolved in a way the rebased revision becomes empty, it is not skipped, unlike revisions being emptied without conflicts. The reason is: - File 'x' is merged and resolved, merge.update() marks it as 'm' in the dirstate. - rebase.concludenode() calls localrepo.commit(), which calls localrepo.status() which calls dirstate.status(). 'x' shows up as 'm' and is unconditionnally added to the modified files list, instead of being checked again. - localrepo.commit() detects 'x' as changed an create a new revision where only the manifest parents and linkrev differ. Marking 'x' as modified without checking it makes sense for regular merges. But in rebase case, the merge looks normal but the second parent is usually discarded. When this happens, 'm' files in dirstate are a bit irrelevant and should be considered 'n' possibly dirty instead. That is what the current patch does. Another approach, maybe more efficient, would be to pass another flag to merge.update() saying the 'branchmerge' is a bit of a lie and recordupdate() should call dirstate.normallookup() instead of merge(). It is also tempting to add this logic to dirstate.setparents(), moving from two to one parent is what invalidates the 'm' markers. But this is a far bigger change to make. v2: succumb to the temptation and move the logic in dirstate.setparents(). mpm suggested trying _filecommit() first but it is called by commitctx() which knows nothing about the dirstate and comes too late into the game. A second approach was to rewrite the 'm' state into 'n' on the fly in dirstate.status() which failed for graft in the following case: $ hg init repo $ cd repo $ echo a > a $ hg ci -qAm0 $ echo a >> a $ hg ci -m1 $ hg up 0 1 files updated, 0 files merged, 0 files removed, 0 files unresolved $ hg mv a b $ echo c > b $ hg ci -m2 created new head $ hg graft 1 --tool internal:local grafting revision 1 $ hg --config extensions.graphlog= glog --template '{rev} {desc|firstline}\n' @ 3 1 | o 2 2 | | o 1 1 |/ o 0 0 $ hg log -r 3 --debug --patch --git --copies changeset: 3:19cd7d1417952af13161b94c32e901769104560c tag: tip phase: draft parent: 2:b5c505595c9e9a12d5dd457919c143e05fc16fb8 parent: -1:0000000000000000000000000000000000000000 manifest: 3:3d27ce8d02241aa59b60804805edf103c5c0cda4 user: test date: Thu Jan 01 00:00:00 1970 +0000 extra: branch=default extra: source=a03df74c41413a75c0a42997fc36c2de97b26658 description: 1 Here, revision 3 is created because there is a copy record for 'b' in the dirstate and thus 'b' is considered modified. But this information is discarded at commit time since 'b' content is unchanged. I do not know if discarding this information is correct or not, but at this time we cannot represent it anyway. This patch therefore implements the last solution of moving the logic into dirstate.setparents(). It does not sound crazy as 'm' files makes no sense with only one parent. It also makes dirstate.merge() calls .lookupnormal() if there is one parent, to preserve the invariant. I am a bit concerned about introducing this kind of stateful behaviour to existing code which historically treated setparents() as a basic setter without side-effects. And doing that during the code freeze.

File last commit:

r15713:cff25e4b default
r16509:eab9119c stable
Show More
setdiscovery.py
195 lines | 6.9 KiB | text/x-python | PythonLexer
# setdiscovery.py - improved discovery of common nodeset for mercurial
#
# Copyright 2010 Benoit Boissinot <bboissin@gmail.com>
# and Peter Arrenbrecht <peter@arrenbrecht.ch>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from node import nullid
from i18n import _
import random, collections, util, dagutil
import phases
def _updatesample(dag, nodes, sample, always, quicksamplesize=0):
# if nodes is empty we scan the entire graph
if nodes:
heads = dag.headsetofconnecteds(nodes)
else:
heads = dag.heads()
dist = {}
visit = collections.deque(heads)
seen = set()
factor = 1
while visit:
curr = visit.popleft()
if curr in seen:
continue
d = dist.setdefault(curr, 1)
if d > factor:
factor *= 2
if d == factor:
if curr not in always: # need this check for the early exit below
sample.add(curr)
if quicksamplesize and (len(sample) >= quicksamplesize):
return
seen.add(curr)
for p in dag.parents(curr):
if not nodes or p in nodes:
dist.setdefault(p, d + 1)
visit.append(p)
def _setupsample(dag, nodes, size):
if len(nodes) <= size:
return set(nodes), None, 0
always = dag.headsetofconnecteds(nodes)
desiredlen = size - len(always)
if desiredlen <= 0:
# This could be bad if there are very many heads, all unknown to the
# server. We're counting on long request support here.
return always, None, desiredlen
return always, set(), desiredlen
def _takequicksample(dag, nodes, size, initial):
always, sample, desiredlen = _setupsample(dag, nodes, size)
if sample is None:
return always
if initial:
fromset = None
else:
fromset = nodes
_updatesample(dag, fromset, sample, always, quicksamplesize=desiredlen)
sample.update(always)
return sample
def _takefullsample(dag, nodes, size):
always, sample, desiredlen = _setupsample(dag, nodes, size)
if sample is None:
return always
# update from heads
_updatesample(dag, nodes, sample, always)
# update from roots
_updatesample(dag.inverse(), nodes, sample, always)
assert sample
if len(sample) > desiredlen:
sample = set(random.sample(sample, desiredlen))
elif len(sample) < desiredlen:
more = desiredlen - len(sample)
sample.update(random.sample(list(nodes - sample - always), more))
sample.update(always)
return sample
def findcommonheads(ui, local, remote,
initialsamplesize=100,
fullsamplesize=200,
abortwhenunrelated=True):
'''Return a tuple (common, anyincoming, remoteheads) used to identify
missing nodes from or in remote.
shortcutlocal determines whether we try use direct access to localrepo if
remote is actually local.
'''
roundtrips = 0
cl = local.changelog
dag = dagutil.revlogdag(cl)
# early exit if we know all the specified remote heads already
ui.debug("query 1; heads\n")
roundtrips += 1
ownheads = dag.heads()
sample = ownheads
if remote.local():
# stopgap until we have a proper localpeer that supports batch()
srvheadhashes = phases.visibleheads(remote)
yesno = remote.known(dag.externalizeall(sample))
elif remote.capable('batch'):
batch = remote.batch()
srvheadhashesref = batch.heads()
yesnoref = batch.known(dag.externalizeall(sample))
batch.submit()
srvheadhashes = srvheadhashesref.value
yesno = yesnoref.value
else:
# compatibitity with pre-batch, but post-known remotes during 1.9 devel
srvheadhashes = remote.heads()
sample = []
if cl.tip() == nullid:
if srvheadhashes != [nullid]:
return [nullid], True, srvheadhashes
return [nullid], False, []
# start actual discovery (we note this before the next "if" for
# compatibility reasons)
ui.status(_("searching for changes\n"))
srvheads = dag.internalizeall(srvheadhashes, filterunknown=True)
if len(srvheads) == len(srvheadhashes):
ui.debug("all remote heads known locally\n")
return (srvheadhashes, False, srvheadhashes,)
if sample and util.all(yesno):
ui.note(_("all local heads known remotely\n"))
ownheadhashes = dag.externalizeall(ownheads)
return (ownheadhashes, True, srvheadhashes,)
# full blown discovery
undecided = dag.nodeset() # own nodes where I don't know if remote knows them
common = set() # own nodes I know we both know
missing = set() # own nodes I know remote lacks
# treat remote heads (and maybe own heads) as a first implicit sample response
common.update(dag.ancestorset(srvheads))
undecided.difference_update(common)
full = False
while undecided:
if sample:
commoninsample = set(n for i, n in enumerate(sample) if yesno[i])
common.update(dag.ancestorset(commoninsample, common))
missinginsample = [n for i, n in enumerate(sample) if not yesno[i]]
missing.update(dag.descendantset(missinginsample, missing))
undecided.difference_update(missing)
undecided.difference_update(common)
if not undecided:
break
if full:
ui.note(_("sampling from both directions\n"))
sample = _takefullsample(dag, undecided, size=fullsamplesize)
elif common:
# use cheapish initial sample
ui.debug("taking initial sample\n")
sample = _takefullsample(dag, undecided, size=fullsamplesize)
else:
# use even cheaper initial sample
ui.debug("taking quick initial sample\n")
sample = _takequicksample(dag, undecided, size=initialsamplesize,
initial=True)
roundtrips += 1
ui.progress(_('searching'), roundtrips, unit=_('queries'))
ui.debug("query %i; still undecided: %i, sample size is: %i\n"
% (roundtrips, len(undecided), len(sample)))
# indices between sample and externalized version must match
sample = list(sample)
yesno = remote.known(dag.externalizeall(sample))
full = True
result = dag.headsetofconnecteds(common)
ui.progress(_('searching'), None)
ui.debug("%d total queries\n" % roundtrips)
if not result and srvheadhashes != [nullid]:
if abortwhenunrelated:
raise util.Abort(_("repository is unrelated"))
else:
ui.warn(_("warning: repository is unrelated\n"))
return (set([nullid]), True, srvheadhashes,)
anyincoming = (srvheadhashes != [nullid])
return dag.externalizeall(result), anyincoming, srvheadhashes