setdiscovery: fix hang when #heads>200 (issue2971)

When setting up the next sample, we always add all of the heads, regardless
of the desired max sample size. But if the number of heads exceeds this
size, then we don't add any more nodes from the still undecided set.
(This is debatable per se, and I'll investigate it, but it's how we designed
it at the moment.)

The bug was that we always added the overall heads, not the heads of the
remaining undecided set. Thus, if #heads>200 (desired sample size), we
did not make progress any longer.

mercurial/setdiscovery.py

@@ -1,194 +1,194
 # setdiscovery.py - improved discovery of common nodeset for mercurial
 #
 # Copyright 2010 Benoit Boissinot <[e-mail]>
 # and Peter Arrenbrecht <[e-mail]>
 #
 # 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
 
 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 = set(dag.heads())
+    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 = remote.heads()
         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

tests/test-setdiscovery.t

@@ -1,268 +1,326
 
 Function to test discovery between two repos in both directions, using both the local shortcut
 (which is currently not activated by default) and the full remotable protocol:
 
   $ testdesc() { # revs_a, revs_b, dagdesc
   >     if [ -d foo ]; then rm -rf foo; fi
   >     hg init foo
   >     cd foo
   >     hg debugbuilddag "$3"
   >     hg clone . a $1 --quiet
   >     hg clone . b $2 --quiet
   >     echo
   >     echo "% -- a -> b tree"
   >     hg -R a debugdiscovery b --verbose --old
   >     echo
   >     echo "% -- a -> b set"
   >     hg -R a debugdiscovery b --verbose --debug
   >     echo
   >     echo "% -- b -> a tree"
   >     hg -R b debugdiscovery a --verbose --old
   >     echo
   >     echo "% -- b -> a set"
   >     hg -R b debugdiscovery a --verbose --debug
   >     cd ..
   > }
 
 
 Small superset:
 
   $ testdesc '-ra1 -ra2' '-rb1 -rb2 -rb3' '
   > +2:f +1:a1:b1
   > <f +4 :a2
   > +5 :b2
   > <f +3 :b3'
   
   % -- a -> b tree
   comparing with b
   searching for changes
   unpruned common: b5714e113bc0 66f7d451a68b 01241442b3c2
   common heads: b5714e113bc0 01241442b3c2
   local is subset
   
   % -- a -> b set
   comparing with b
   query 1; heads
   searching for changes
   all local heads known remotely
   common heads: b5714e113bc0 01241442b3c2
   local is subset
   
   % -- b -> a tree
   comparing with a
   searching for changes
   unpruned common: b5714e113bc0 01241442b3c2
   common heads: b5714e113bc0 01241442b3c2
   remote is subset
   
   % -- b -> a set
   comparing with a
   query 1; heads
   searching for changes
   all remote heads known locally
   common heads: b5714e113bc0 01241442b3c2
   remote is subset
 
 
 Many new:
 
   $ testdesc '-ra1 -ra2' '-rb' '
   > +2:f +3:a1 +3:b
   > <f +30 :a2'
   
   % -- a -> b tree
   comparing with b
   searching for changes
   unpruned common: bebd167eb94d
   common heads: bebd167eb94d
   
   % -- a -> b set
   comparing with b
   query 1; heads
   searching for changes
   taking initial sample
   searching: 2 queries
   query 2; still undecided: 29, sample size is: 29
   2 total queries
   common heads: bebd167eb94d
   
   % -- b -> a tree
   comparing with a
   searching for changes
   unpruned common: bebd167eb94d 66f7d451a68b
   common heads: bebd167eb94d
   
   % -- b -> a set
   comparing with a
   query 1; heads
   searching for changes
   taking initial sample
   searching: 2 queries
   query 2; still undecided: 2, sample size is: 2
   2 total queries
   common heads: bebd167eb94d
 
 
 Both sides many new with stub:
 
   $ testdesc '-ra1 -ra2' '-rb' '
   > +2:f +2:a1 +30 :b
   > <f +30 :a2'
   
   % -- a -> b tree
   comparing with b
   searching for changes
   unpruned common: 2dc09a01254d
   common heads: 2dc09a01254d
   
   % -- a -> b set
   comparing with b
   query 1; heads
   searching for changes
   taking initial sample
   searching: 2 queries
   query 2; still undecided: 29, sample size is: 29
   2 total queries
   common heads: 2dc09a01254d
   
   % -- b -> a tree
   comparing with a
   searching for changes
   unpruned common: 66f7d451a68b 2dc09a01254d
   common heads: 2dc09a01254d
   
   % -- b -> a set
   comparing with a
   query 1; heads
   searching for changes
   taking initial sample
   searching: 2 queries
   query 2; still undecided: 29, sample size is: 29
   2 total queries
   common heads: 2dc09a01254d
 
 
 Both many new:
 
   $ testdesc '-ra' '-rb' '
   > +2:f +30 :b
   > <f +30 :a'
   
   % -- a -> b tree
   comparing with b
   searching for changes
   unpruned common: 66f7d451a68b
   common heads: 66f7d451a68b
   
   % -- a -> b set
   comparing with b
   query 1; heads
   searching for changes
   taking quick initial sample
   searching: 2 queries
   query 2; still undecided: 31, sample size is: 31
   2 total queries
   common heads: 66f7d451a68b
   
   % -- b -> a tree
   comparing with a
   searching for changes
   unpruned common: 66f7d451a68b
   common heads: 66f7d451a68b
   
   % -- b -> a set
   comparing with a
   query 1; heads
   searching for changes
   taking quick initial sample
   searching: 2 queries
   query 2; still undecided: 31, sample size is: 31
   2 total queries
   common heads: 66f7d451a68b
 
 
 Both many new skewed:
 
   $ testdesc '-ra' '-rb' '
   > +2:f +30 :b
   > <f +50 :a'
   
   % -- a -> b tree
   comparing with b
   searching for changes
   unpruned common: 66f7d451a68b
   common heads: 66f7d451a68b
   
   % -- a -> b set
   comparing with b
   query 1; heads
   searching for changes
   taking quick initial sample
   searching: 2 queries
   query 2; still undecided: 51, sample size is: 51
   2 total queries
   common heads: 66f7d451a68b
   
   % -- b -> a tree
   comparing with a
   searching for changes
   unpruned common: 66f7d451a68b
   common heads: 66f7d451a68b
   
   % -- b -> a set
   comparing with a
   query 1; heads
   searching for changes
   taking quick initial sample
   searching: 2 queries
   query 2; still undecided: 31, sample size is: 31
   2 total queries
   common heads: 66f7d451a68b
 
 
 Both many new on top of long history:
 
   $ testdesc '-ra' '-rb' '
   > +1000:f +30 :b
   > <f +50 :a'
   
   % -- a -> b tree
   comparing with b
   searching for changes
   unpruned common: 7ead0cba2838
   common heads: 7ead0cba2838
   
   % -- a -> b set
   comparing with b
   query 1; heads
   searching for changes
   taking quick initial sample
   searching: 2 queries
   query 2; still undecided: 1049, sample size is: 11
   sampling from both directions
   searching: 3 queries
   query 3; still undecided: 31, sample size is: 31
   3 total queries
   common heads: 7ead0cba2838
   
   % -- b -> a tree
   comparing with a
   searching for changes
   unpruned common: 7ead0cba2838
   common heads: 7ead0cba2838
   
   % -- b -> a set
   comparing with a
   query 1; heads
   searching for changes
   taking quick initial sample
   searching: 2 queries
   query 2; still undecided: 1029, sample size is: 11
   sampling from both directions
   searching: 3 queries
   query 3; still undecided: 15, sample size is: 15
   3 total queries
   common heads: 7ead0cba2838
 
 
+One with >200 heads, which used to use up all of the sample:
 
+  $ hg init manyheads
+  $ cd manyheads
+  $ echo "+300:r @a" >dagdesc
+  $ echo "*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3 *r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3" >>dagdesc # 20 heads
+  $ echo "*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3 *r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3" >>dagdesc # 20 heads
+  $ echo "*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3 *r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3" >>dagdesc # 20 heads
+  $ echo "*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3 *r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3" >>dagdesc # 20 heads
+  $ echo "*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3 *r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3" >>dagdesc # 20 heads
+  $ echo "*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3 *r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3" >>dagdesc # 20 heads
+  $ echo "*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3 *r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3" >>dagdesc # 20 heads
+  $ echo "*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3 *r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3" >>dagdesc # 20 heads
+  $ echo "*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3 *r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3" >>dagdesc # 20 heads
+  $ echo "*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3 *r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3" >>dagdesc # 20 heads
+  $ echo "*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3 *r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3" >>dagdesc # 20 heads
+  $ echo "*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3 *r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3" >>dagdesc # 20 heads
+  $ echo "*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3 *r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3*r+3" >>dagdesc # 20 heads
+  $ echo "@b *r+3" >>dagdesc # one more head
+  $ hg debugbuilddag <dagdesc
+  reading DAG from stdin
+
+  $ hg heads -t --template . | wc -c
+  261
+
+  $ hg clone -b a . a
+  adding changesets
+  adding manifests
+  adding file changes
+  added 1340 changesets with 0 changes to 0 files (+259 heads)
+  updating to branch a
+  0 files updated, 0 files merged, 0 files removed, 0 files unresolved
+  $ hg clone -b b . b
+  adding changesets
+  adding manifests
+  adding file changes
+  added 304 changesets with 0 changes to 0 files
+  updating to branch b
+  0 files updated, 0 files merged, 0 files removed, 0 files unresolved
+
+  $ hg -R a debugdiscovery b --debug --verbose
+  comparing with b
+  query 1; heads
+  searching for changes
+  taking quick initial sample
+  searching: 2 queries
+  query 2; still undecided: 1080, sample size is: 260
+  sampling from both directions
+  searching: 3 queries
+  query 3; still undecided: 820, sample size is: 260
+  sampling from both directions
+  searching: 4 queries
+  query 4; still undecided: 560, sample size is: 260
+  sampling from both directions
+  searching: 5 queries
+  query 5; still undecided: 300, sample size is: 200
+  5 total queries
+  common heads: 3ee37d65064a
+