branchmap: updating triggers a write

Rather than separate updating and writing, create a subclass that doesn't write
on update. This minimises chances we forget to write out updates somewhere.

This also makes refactoring and improving the branchmap functionality easier.

Differential Revision: https://phab.mercurial-scm.org/D5636

mercurial/branchmap.py

@@ -1,561 +1,570 b''
 # branchmap.py - logic to computes, maintain and stores branchmap for local repo
 #
 # Copyright 2005-2007 Matt Mackall <[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 __future__ import absolute_import
 
 import struct
 
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
 )
 from . import (
     encoding,
     error,
     pycompat,
     scmutil,
     util,
 )
 from .utils import (
     stringutil,
 )
 
 calcsize = struct.calcsize
 pack_into = struct.pack_into
 unpack_from = struct.unpack_from
 
 
 ### Nearest subset relation
 # Nearest subset of filter X is a filter Y so that:
 # * Y is included in X,
 # * X - Y is as small as possible.
 # This create and ordering used for branchmap purpose.
 # the ordering may be partial
 subsettable = {None: 'visible',
                'visible-hidden': 'visible',
                'visible': 'served',
                'served': 'immutable',
                'immutable': 'base'}
 
 def updatecache(repo):
     cl = repo.changelog
     filtername = repo.filtername
     bcache = repo._branchcaches.get(filtername)
 
     revs = []
     if bcache is None or not bcache.validfor(repo):
         bcache = branchcache.fromfile(repo)
         if bcache is None:
             subsetname = subsettable.get(filtername)
             if subsetname is None:
                 bcache = branchcache()
             else:
                 subset = repo.filtered(subsetname)
                 bcache = subset.branchmap().copy()
                 extrarevs = subset.changelog.filteredrevs - cl.filteredrevs
                 revs.extend(r for  r in extrarevs if r <= bcache.tiprev)
     revs.extend(cl.revs(start=bcache.tiprev + 1))
     if revs:
         bcache.update(repo, revs)
-        bcache.write(repo)
 
     assert bcache.validfor(repo), filtername
     repo._branchcaches[repo.filtername] = bcache
 
 def replacecache(repo, bm):
     """Replace the branchmap cache for a repo with a branch mapping.
 
     This is likely only called during clone with a branch map from a remote.
     """
     cl = repo.changelog
     clrev = cl.rev
     clbranchinfo = cl.branchinfo
     rbheads = []
     closed = []
     for bheads in bm.itervalues():
         rbheads.extend(bheads)
         for h in bheads:
             r = clrev(h)
             b, c = clbranchinfo(r)
             if c:
                 closed.append(h)
 
     if rbheads:
         rtiprev = max((int(clrev(node))
                 for node in rbheads))
         cache = branchcache(bm,
                             repo[rtiprev].node(),
                             rtiprev,
                             closednodes=closed)
 
         # Try to stick it as low as possible
         # filter above served are unlikely to be fetch from a clone
         for candidate in ('base', 'immutable', 'served'):
             rview = repo.filtered(candidate)
             if cache.validfor(rview):
                 repo._branchcaches[candidate] = cache
                 cache.write(rview)
                 break
 
 class branchcache(dict):
     """A dict like object that hold branches heads cache.
 
     This cache is used to avoid costly computations to determine all the
     branch heads of a repo.
 
     The cache is serialized on disk in the following format:
 
     <tip hex node> <tip rev number> [optional filtered repo hex hash]
     <branch head hex node> <open/closed state> <branch name>
     <branch head hex node> <open/closed state> <branch name>
     ...
 
     The first line is used to check if the cache is still valid. If the
     branch cache is for a filtered repo view, an optional third hash is
     included that hashes the hashes of all filtered revisions.
 
     The open/closed state is represented by a single letter 'o' or 'c'.
     This field can be used to avoid changelog reads when determining if a
     branch head closes a branch or not.
     """
     @classmethod
     def fromfile(cls, repo):
         f = None
         try:
             f = repo.cachevfs(cls._filename(repo))
             lineiter = iter(f)
             cachekey = next(lineiter).rstrip('\n').split(" ", 2)
             last, lrev = cachekey[:2]
             last, lrev = bin(last), int(lrev)
             filteredhash = None
             if len(cachekey) > 2:
                 filteredhash = bin(cachekey[2])
             bcache = cls(tipnode=last, tiprev=lrev, filteredhash=filteredhash)
             if not bcache.validfor(repo):
                 # invalidate the cache
                 raise ValueError(r'tip differs')
             cl = repo.changelog
             for line in lineiter:
                 line = line.rstrip('\n')
                 if not line:
                     continue
                 node, state, label = line.split(" ", 2)
                 if state not in 'oc':
                     raise ValueError(r'invalid branch state')
                 label = encoding.tolocal(label.strip())
                 node = bin(node)
                 if not cl.hasnode(node):
                     raise ValueError(
                         r'node %s does not exist' % pycompat.sysstr(hex(node)))
                 bcache.setdefault(label, []).append(node)
                 if state == 'c':
                     bcache._closednodes.add(node)
 
         except (IOError, OSError):
             return None
 
         except Exception as inst:
             if repo.ui.debugflag:
                 msg = 'invalid branchheads cache'
                 if repo.filtername is not None:
                     msg += ' (%s)' % repo.filtername
                 msg += ': %s\n'
                 repo.ui.debug(msg % pycompat.bytestr(inst))
             bcache = None
 
         finally:
             if f:
                 f.close()
 
         return bcache
 
     @staticmethod
     def _filename(repo):
         """name of a branchcache file for a given repo or repoview"""
         filename = "branch2"
         if repo.filtername:
             filename = '%s-%s' % (filename, repo.filtername)
         return filename
 
     def __init__(self, entries=(), tipnode=nullid, tiprev=nullrev,
                  filteredhash=None, closednodes=None):
         super(branchcache, self).__init__(entries)
         self.tipnode = tipnode
         self.tiprev = tiprev
         self.filteredhash = filteredhash
         # closednodes is a set of nodes that close their branch. If the branch
         # cache has been updated, it may contain nodes that are no longer
         # heads.
         if closednodes is None:
             self._closednodes = set()
         else:
             self._closednodes = closednodes
 
     def validfor(self, repo):
         """Is the cache content valid regarding a repo
 
         - False when cached tipnode is unknown or if we detect a strip.
         - True when cache is up to date or a subset of current repo."""
         try:
             return ((self.tipnode == repo.changelog.node(self.tiprev))
                     and (self.filteredhash == \
                          scmutil.filteredhash(repo, self.tiprev)))
         except IndexError:
             return False
 
     def _branchtip(self, heads):
         '''Return tuple with last open head in heads and false,
         otherwise return last closed head and true.'''
         tip = heads[-1]
         closed = True
         for h in reversed(heads):
             if h not in self._closednodes:
                 tip = h
                 closed = False
                 break
         return tip, closed
 
     def branchtip(self, branch):
         '''Return the tipmost open head on branch head, otherwise return the
         tipmost closed head on branch.
         Raise KeyError for unknown branch.'''
         return self._branchtip(self[branch])[0]
 
     def iteropen(self, nodes):
         return (n for n in nodes if n not in self._closednodes)
 
     def branchheads(self, branch, closed=False):
         heads = self[branch]
         if not closed:
             heads = list(self.iteropen(heads))
         return heads
 
     def iterbranches(self):
         for bn, heads in self.iteritems():
             yield (bn, heads) + self._branchtip(heads)
 
     def copy(self):
         """return an deep copy of the branchcache object"""
-        return branchcache(self, self.tipnode, self.tiprev, self.filteredhash,
-                           self._closednodes)
+        return type(self)(
+            self, self.tipnode, self.tiprev, self.filteredhash,
+            self._closednodes)
 
     def write(self, repo):
         try:
             f = repo.cachevfs(self._filename(repo), "w", atomictemp=True)
             cachekey = [hex(self.tipnode), '%d' % self.tiprev]
             if self.filteredhash is not None:
                 cachekey.append(hex(self.filteredhash))
             f.write(" ".join(cachekey) + '\n')
             nodecount = 0
             for label, nodes in sorted(self.iteritems()):
                 for node in nodes:
                     nodecount += 1
                     if node in self._closednodes:
                         state = 'c'
                     else:
                         state = 'o'
                     f.write("%s %s %s\n" % (hex(node), state,
                                             encoding.fromlocal(label)))
             f.close()
             repo.ui.log('branchcache',
                         'wrote %s branch cache with %d labels and %d nodes\n',
                         repo.filtername, len(self), nodecount)
         except (IOError, OSError, error.Abort) as inst:
             # Abort may be raised by read only opener, so log and continue
             repo.ui.debug("couldn't write branch cache: %s\n" %
                           stringutil.forcebytestr(inst))
 
     def update(self, repo, revgen):
         """Given a branchhead cache, self, that may have extra nodes or be
         missing heads, and a generator of nodes that are strictly a superset of
         heads missing, this function updates self to be correct.
         """
         starttime = util.timer()
         cl = repo.changelog
         # collect new branch entries
         newbranches = {}
         getbranchinfo = repo.revbranchcache().branchinfo
         for r in revgen:
             branch, closesbranch = getbranchinfo(r)
             newbranches.setdefault(branch, []).append(r)
             if closesbranch:
                 self._closednodes.add(cl.node(r))
 
         # fetch current topological heads to speed up filtering
         topoheads = set(cl.headrevs())
 
         # if older branchheads are reachable from new ones, they aren't
         # really branchheads. Note checking parents is insufficient:
         # 1 (branch a) -> 2 (branch b) -> 3 (branch a)
         for branch, newheadrevs in newbranches.iteritems():
             bheads = self.setdefault(branch, [])
             bheadset = set(cl.rev(node) for node in bheads)
 
             # This have been tested True on all internal usage of this function.
             # run it again in case of doubt
             # assert not (set(bheadrevs) & set(newheadrevs))
             bheadset.update(newheadrevs)
 
             # This prunes out two kinds of heads - heads that are superseded by
             # a head in newheadrevs, and newheadrevs that are not heads because
             # an existing head is their descendant.
             uncertain = bheadset - topoheads
             if uncertain:
                 floorrev = min(uncertain)
                 ancestors = set(cl.ancestors(newheadrevs, floorrev))
                 bheadset -= ancestors
             bheadrevs = sorted(bheadset)
             self[branch] = [cl.node(rev) for rev in bheadrevs]
             tiprev = bheadrevs[-1]
             if tiprev > self.tiprev:
                 self.tipnode = cl.node(tiprev)
                 self.tiprev = tiprev
 
         if not self.validfor(repo):
             # cache key are not valid anymore
             self.tipnode = nullid
             self.tiprev = nullrev
             for heads in self.values():
                 tiprev = max(cl.rev(node) for node in heads)
                 if tiprev > self.tiprev:
                     self.tipnode = cl.node(tiprev)
                     self.tiprev = tiprev
         self.filteredhash = scmutil.filteredhash(repo, self.tiprev)
 
         duration = util.timer() - starttime
         repo.ui.log('branchcache', 'updated %s branch cache in %.4f seconds\n',
                     repo.filtername, duration)
 
+        self.write(repo)
+
+
+class remotebranchcache(branchcache):
+    """Branchmap info for a remote connection, should not write locally"""
+    def write(self, repo):
+        pass
+
+
 # Revision branch info cache
 
 _rbcversion = '-v1'
 _rbcnames = 'rbc-names' + _rbcversion
 _rbcrevs = 'rbc-revs' + _rbcversion
 # [4 byte hash prefix][4 byte branch name number with sign bit indicating open]
 _rbcrecfmt = '>4sI'
 _rbcrecsize = calcsize(_rbcrecfmt)
 _rbcnodelen = 4
 _rbcbranchidxmask = 0x7fffffff
 _rbccloseflag = 0x80000000
 
 class revbranchcache(object):
     """Persistent cache, mapping from revision number to branch name and close.
     This is a low level cache, independent of filtering.
 
     Branch names are stored in rbc-names in internal encoding separated by 0.
     rbc-names is append-only, and each branch name is only stored once and will
     thus have a unique index.
 
     The branch info for each revision is stored in rbc-revs as constant size
     records. The whole file is read into memory, but it is only 'parsed' on
     demand. The file is usually append-only but will be truncated if repo
     modification is detected.
     The record for each revision contains the first 4 bytes of the
     corresponding node hash, and the record is only used if it still matches.
     Even a completely trashed rbc-revs fill thus still give the right result
     while converging towards full recovery ... assuming no incorrectly matching
     node hashes.
     The record also contains 4 bytes where 31 bits contains the index of the
     branch and the last bit indicate that it is a branch close commit.
     The usage pattern for rbc-revs is thus somewhat similar to 00changelog.i
     and will grow with it but be 1/8th of its size.
     """
 
     def __init__(self, repo, readonly=True):
         assert repo.filtername is None
         self._repo = repo
         self._names = [] # branch names in local encoding with static index
         self._rbcrevs = bytearray()
         self._rbcsnameslen = 0 # length of names read at _rbcsnameslen
         try:
             bndata = repo.cachevfs.read(_rbcnames)
             self._rbcsnameslen = len(bndata) # for verification before writing
             if bndata:
                 self._names = [encoding.tolocal(bn)
                                for bn in bndata.split('\0')]
         except (IOError, OSError):
             if readonly:
                 # don't try to use cache - fall back to the slow path
                 self.branchinfo = self._branchinfo
 
         if self._names:
             try:
                 data = repo.cachevfs.read(_rbcrevs)
                 self._rbcrevs[:] = data
             except (IOError, OSError) as inst:
                 repo.ui.debug("couldn't read revision branch cache: %s\n" %
                               stringutil.forcebytestr(inst))
         # remember number of good records on disk
         self._rbcrevslen = min(len(self._rbcrevs) // _rbcrecsize,
                                len(repo.changelog))
         if self._rbcrevslen == 0:
             self._names = []
         self._rbcnamescount = len(self._names) # number of names read at
                                                # _rbcsnameslen
 
     def _clear(self):
         self._rbcsnameslen = 0
         del self._names[:]
         self._rbcnamescount = 0
         self._rbcrevslen = len(self._repo.changelog)
         self._rbcrevs = bytearray(self._rbcrevslen * _rbcrecsize)
         util.clearcachedproperty(self, '_namesreverse')
 
     @util.propertycache
     def _namesreverse(self):
         return dict((b, r) for r, b in enumerate(self._names))
 
     def branchinfo(self, rev):
         """Return branch name and close flag for rev, using and updating
         persistent cache."""
         changelog = self._repo.changelog
         rbcrevidx = rev * _rbcrecsize
 
         # avoid negative index, changelog.read(nullrev) is fast without cache
         if rev == nullrev:
             return changelog.branchinfo(rev)
 
         # if requested rev isn't allocated, grow and cache the rev info
         if len(self._rbcrevs) < rbcrevidx + _rbcrecsize:
             return self._branchinfo(rev)
 
         # fast path: extract data from cache, use it if node is matching
         reponode = changelog.node(rev)[:_rbcnodelen]
         cachenode, branchidx = unpack_from(
             _rbcrecfmt, util.buffer(self._rbcrevs), rbcrevidx)
         close = bool(branchidx & _rbccloseflag)
         if close:
             branchidx &= _rbcbranchidxmask
         if cachenode == '\0\0\0\0':
             pass
         elif cachenode == reponode:
             try:
                 return self._names[branchidx], close
             except IndexError:
                 # recover from invalid reference to unknown branch
                 self._repo.ui.debug("referenced branch names not found"
                     " - rebuilding revision branch cache from scratch\n")
                 self._clear()
         else:
             # rev/node map has changed, invalidate the cache from here up
             self._repo.ui.debug("history modification detected - truncating "
                 "revision branch cache to revision %d\n" % rev)
             truncate = rbcrevidx + _rbcrecsize
             del self._rbcrevs[truncate:]
             self._rbcrevslen = min(self._rbcrevslen, truncate)
 
         # fall back to slow path and make sure it will be written to disk
         return self._branchinfo(rev)
 
     def _branchinfo(self, rev):
         """Retrieve branch info from changelog and update _rbcrevs"""
         changelog = self._repo.changelog
         b, close = changelog.branchinfo(rev)
         if b in self._namesreverse:
             branchidx = self._namesreverse[b]
         else:
             branchidx = len(self._names)
             self._names.append(b)
             self._namesreverse[b] = branchidx
         reponode = changelog.node(rev)
         if close:
             branchidx |= _rbccloseflag
         self._setcachedata(rev, reponode, branchidx)
         return b, close
 
     def setdata(self, branch, rev, node, close):
         """add new data information to the cache"""
         if branch in self._namesreverse:
             branchidx = self._namesreverse[branch]
         else:
             branchidx = len(self._names)
             self._names.append(branch)
             self._namesreverse[branch] = branchidx
         if close:
             branchidx |= _rbccloseflag
         self._setcachedata(rev, node, branchidx)
         # If no cache data were readable (non exists, bad permission, etc)
         # the cache was bypassing itself by setting:
         #
         #   self.branchinfo = self._branchinfo
         #
         # Since we now have data in the cache, we need to drop this bypassing.
         if r'branchinfo' in vars(self):
             del self.branchinfo
 
     def _setcachedata(self, rev, node, branchidx):
         """Writes the node's branch data to the in-memory cache data."""
         if rev == nullrev:
             return
         rbcrevidx = rev * _rbcrecsize
         if len(self._rbcrevs) < rbcrevidx + _rbcrecsize:
             self._rbcrevs.extend('\0' *
                                  (len(self._repo.changelog) * _rbcrecsize -
                                   len(self._rbcrevs)))
         pack_into(_rbcrecfmt, self._rbcrevs, rbcrevidx, node, branchidx)
         self._rbcrevslen = min(self._rbcrevslen, rev)
 
         tr = self._repo.currenttransaction()
         if tr:
             tr.addfinalize('write-revbranchcache', self.write)
 
     def write(self, tr=None):
         """Save branch cache if it is dirty."""
         repo = self._repo
         wlock = None
         step = ''
         try:
             if self._rbcnamescount < len(self._names):
                 step = ' names'
                 wlock = repo.wlock(wait=False)
                 if self._rbcnamescount != 0:
                     f = repo.cachevfs.open(_rbcnames, 'ab')
                     if f.tell() == self._rbcsnameslen:
                         f.write('\0')
                     else:
                         f.close()
                         repo.ui.debug("%s changed - rewriting it\n" % _rbcnames)
                         self._rbcnamescount = 0
                         self._rbcrevslen = 0
                 if self._rbcnamescount == 0:
                     # before rewriting names, make sure references are removed
                     repo.cachevfs.unlinkpath(_rbcrevs, ignoremissing=True)
                     f = repo.cachevfs.open(_rbcnames, 'wb')
                 f.write('\0'.join(encoding.fromlocal(b)
                                   for b in self._names[self._rbcnamescount:]))
                 self._rbcsnameslen = f.tell()
                 f.close()
                 self._rbcnamescount = len(self._names)
 
             start = self._rbcrevslen * _rbcrecsize
             if start != len(self._rbcrevs):
                 step = ''
                 if wlock is None:
                     wlock = repo.wlock(wait=False)
                 revs = min(len(repo.changelog),
                            len(self._rbcrevs) // _rbcrecsize)
                 f = repo.cachevfs.open(_rbcrevs, 'ab')
                 if f.tell() != start:
                     repo.ui.debug("truncating cache/%s to %d\n"
                                   % (_rbcrevs, start))
                     f.seek(start)
                     if f.tell() != start:
                         start = 0
                         f.seek(start)
                     f.truncate()
                 end = revs * _rbcrecsize
                 f.write(self._rbcrevs[start:end])
                 f.close()
                 self._rbcrevslen = revs
         except (IOError, OSError, error.Abort, error.LockError) as inst:
             repo.ui.debug("couldn't write revision branch cache%s: %s\n"
                           % (step, stringutil.forcebytestr(inst)))
         finally:
             if wlock is not None:
                 wlock.release()

mercurial/discovery.py

@@ -1,533 +1,533 b''
 # discovery.py - protocol changeset discovery functions
 #
 # Copyright 2010 Matt Mackall <[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 __future__ import absolute_import
 
 import functools
 
 from .i18n import _
 from .node import (
     hex,
     nullid,
     short,
 )
 
 from . import (
     bookmarks,
     branchmap,
     error,
     phases,
     scmutil,
     setdiscovery,
     treediscovery,
     util,
 )
 
 def findcommonincoming(repo, remote, heads=None, force=False, ancestorsof=None):
     """Return a tuple (common, anyincoming, 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.
     "anyincoming" is testable as a boolean indicating if any nodes are missing
       locally. If remote does not support getbundle, this actually is a list of
       roots of the nodes that would be incoming, to be supplied to
       changegroupsubset. No code except for pull should be relying on this fact
       any longer.
     "heads" is either the supplied heads, or else the remote's heads.
     "ancestorsof" if not None, restrict the discovery to a subset defined by
       these nodes. Changeset outside of this set won't be considered (and
       won't appears in "common")
 
     If you pass heads and they are all known locally, the response lists just
     these heads in "common" and in "heads".
 
     Please use findcommonoutgoing to compute the set of outgoing nodes to give
     extensions a good hook into outgoing.
     """
 
     if not remote.capable('getbundle'):
         return treediscovery.findcommonincoming(repo, remote, heads, force)
 
     if heads:
         knownnode = repo.changelog.hasnode # no nodemap until it is filtered
         if all(knownnode(h) for h in heads):
             return (heads, False, heads)
 
     res = setdiscovery.findcommonheads(repo.ui, repo, remote,
                                        abortwhenunrelated=not force,
                                        ancestorsof=ancestorsof)
     common, anyinc, srvheads = res
     return (list(common), anyinc, heads or list(srvheads))
 
 class outgoing(object):
     '''Represents the set of nodes present in a local repo but not in a
     (possibly) remote one.
 
     Members:
 
       missing is a list of all nodes present in local but not in remote.
       common is a list of all nodes shared between the two repos.
       excluded is the list of missing changeset that shouldn't be sent remotely.
       missingheads is the list of heads of missing.
       commonheads is the list of heads of common.
 
     The sets are computed on demand from the heads, unless provided upfront
     by discovery.'''
 
     def __init__(self, repo, commonheads=None, missingheads=None,
                  missingroots=None):
         # at least one of them must not be set
         assert None in (commonheads, missingroots)
         cl = repo.changelog
         if missingheads is None:
             missingheads = cl.heads()
         if missingroots:
             discbases = []
             for n in missingroots:
                 discbases.extend([p for p in cl.parents(n) if p != nullid])
             # TODO remove call to nodesbetween.
             # TODO populate attributes on outgoing instance instead of setting
             # discbases.
             csets, roots, heads = cl.nodesbetween(missingroots, missingheads)
             included = set(csets)
             missingheads = heads
             commonheads = [n for n in discbases if n not in included]
         elif not commonheads:
             commonheads = [nullid]
         self.commonheads = commonheads
         self.missingheads = missingheads
         self._revlog = cl
         self._common = None
         self._missing = None
         self.excluded = []
 
     def _computecommonmissing(self):
         sets = self._revlog.findcommonmissing(self.commonheads,
                                               self.missingheads)
         self._common, self._missing = sets
 
     @util.propertycache
     def common(self):
         if self._common is None:
             self._computecommonmissing()
         return self._common
 
     @util.propertycache
     def missing(self):
         if self._missing is None:
             self._computecommonmissing()
         return self._missing
 
 def findcommonoutgoing(repo, other, onlyheads=None, force=False,
                        commoninc=None, portable=False):
     '''Return an outgoing instance to identify the nodes present in repo but
     not in other.
 
     If onlyheads is given, only nodes ancestral to nodes in onlyheads
     (inclusive) are included. If you already know the local repo's heads,
     passing them in onlyheads is faster than letting them be recomputed here.
 
     If commoninc is given, it must be the result of a prior call to
     findcommonincoming(repo, other, force) to avoid recomputing it here.
 
     If portable is given, compute more conservative common and missingheads,
     to make bundles created from the instance more portable.'''
     # declare an empty outgoing object to be filled later
     og = outgoing(repo, None, None)
 
     # get common set if not provided
     if commoninc is None:
         commoninc = findcommonincoming(repo, other, force=force,
                                        ancestorsof=onlyheads)
     og.commonheads, _any, _hds = commoninc
 
     # compute outgoing
     mayexclude = (repo._phasecache.phaseroots[phases.secret] or repo.obsstore)
     if not mayexclude:
         og.missingheads = onlyheads or repo.heads()
     elif onlyheads is None:
         # use visible heads as it should be cached
         og.missingheads = repo.filtered("served").heads()
         og.excluded = [ctx.node() for ctx in repo.set('secret() or extinct()')]
     else:
         # compute common, missing and exclude secret stuff
         sets = repo.changelog.findcommonmissing(og.commonheads, onlyheads)
         og._common, allmissing = sets
         og._missing = missing = []
         og.excluded = excluded = []
         for node in allmissing:
             ctx = repo[node]
             if ctx.phase() >= phases.secret or ctx.extinct():
                 excluded.append(node)
             else:
                 missing.append(node)
         if len(missing) == len(allmissing):
             missingheads = onlyheads
         else: # update missing heads
             missingheads = phases.newheads(repo, onlyheads, excluded)
         og.missingheads = missingheads
     if portable:
         # recompute common and missingheads as if -r<rev> had been given for
         # each head of missing, and --base <rev> for each head of the proper
         # ancestors of missing
         og._computecommonmissing()
         cl = repo.changelog
         missingrevs = set(cl.rev(n) for n in og._missing)
         og._common = set(cl.ancestors(missingrevs)) - missingrevs
         commonheads = set(og.commonheads)
         og.missingheads = [h for h in og.missingheads if h not in commonheads]
 
     return og
 
 def _headssummary(pushop):
     """compute a summary of branch and heads status before and after push
 
     return {'branch': ([remoteheads], [newheads],
                        [unsyncedheads], [discardedheads])} mapping
 
     - branch: the branch name,
     - remoteheads: the list of remote heads known locally
                    None if the branch is new,
     - newheads: the new remote heads (known locally) with outgoing pushed,
     - unsyncedheads: the list of remote heads unknown locally,
     - discardedheads: the list of heads made obsolete by the push.
     """
     repo = pushop.repo.unfiltered()
     remote = pushop.remote
     outgoing = pushop.outgoing
     cl = repo.changelog
     headssum = {}
     # A. Create set of branches involved in the push.
     branches = set(repo[n].branch() for n in outgoing.missing)
 
     with remote.commandexecutor() as e:
         remotemap = e.callcommand('branchmap', {}).result()
 
     newbranches = branches - set(remotemap)
     branches.difference_update(newbranches)
 
     # A. register remote heads
     remotebranches = set()
     for branch, heads in remotemap.iteritems():
         remotebranches.add(branch)
         known = []
         unsynced = []
         knownnode = cl.hasnode # do not use nodemap until it is filtered
         for h in heads:
             if knownnode(h):
                 known.append(h)
             else:
                 unsynced.append(h)
         headssum[branch] = (known, list(known), unsynced)
     # B. add new branch data
     missingctx = list(repo[n] for n in outgoing.missing)
     touchedbranches = set()
     for ctx in missingctx:
         branch = ctx.branch()
         touchedbranches.add(branch)
         if branch not in headssum:
             headssum[branch] = (None, [], [])
 
     # C drop data about untouched branches:
     for branch in remotebranches - touchedbranches:
         del headssum[branch]
 
     # D. Update newmap with outgoing changes.
     # This will possibly add new heads and remove existing ones.
-    newmap = branchmap.branchcache((branch, heads[1])
+    newmap = branchmap.remotebranchcache((branch, heads[1])
                                  for branch, heads in headssum.iteritems()
                                  if heads[0] is not None)
     newmap.update(repo, (ctx.rev() for ctx in missingctx))
     for branch, newheads in newmap.iteritems():
         headssum[branch][1][:] = newheads
     for branch, items in headssum.iteritems():
         for l in items:
             if l is not None:
                 l.sort()
         headssum[branch] = items + ([],)
 
     # If there are no obsstore, no post processing are needed.
     if repo.obsstore:
         torev = repo.changelog.rev
         futureheads = set(torev(h) for h in outgoing.missingheads)
         futureheads |= set(torev(h) for h in outgoing.commonheads)
         allfuturecommon = repo.changelog.ancestors(futureheads, inclusive=True)
         for branch, heads in sorted(headssum.iteritems()):
             remoteheads, newheads, unsyncedheads, placeholder = heads
             result = _postprocessobsolete(pushop, allfuturecommon, newheads)
             headssum[branch] = (remoteheads, sorted(result[0]), unsyncedheads,
                                 sorted(result[1]))
     return headssum
 
 def _oldheadssummary(repo, remoteheads, outgoing, inc=False):
     """Compute branchmapsummary for repo without branchmap support"""
 
     # 1-4b. old servers: Check for new topological heads.
     # Construct {old,new}map with branch = None (topological branch).
     # (code based on update)
     knownnode = repo.changelog.hasnode # no nodemap until it is filtered
     oldheads = sorted(h for h in remoteheads if knownnode(h))
     # all nodes in outgoing.missing are children of either:
     # - an element of oldheads
     # - another element of outgoing.missing
     # - nullrev
     # This explains why the new head are very simple to compute.
     r = repo.set('heads(%ln + %ln)', oldheads, outgoing.missing)
     newheads = sorted(c.node() for c in r)
     # set some unsynced head to issue the "unsynced changes" warning
     if inc:
         unsynced = [None]
     else:
         unsynced = []
     return {None: (oldheads, newheads, unsynced, [])}
 
 def _nowarnheads(pushop):
     # Compute newly pushed bookmarks. We don't warn about bookmarked heads.
     repo = pushop.repo.unfiltered()
     remote = pushop.remote
     localbookmarks = repo._bookmarks
 
     with remote.commandexecutor() as e:
         remotebookmarks = e.callcommand('listkeys', {
             'namespace': 'bookmarks',
         }).result()
 
     bookmarkedheads = set()
 
     # internal config: bookmarks.pushing
     newbookmarks = [localbookmarks.expandname(b)
                     for b in pushop.ui.configlist('bookmarks', 'pushing')]
 
     for bm in localbookmarks:
         rnode = remotebookmarks.get(bm)
         if rnode and rnode in repo:
             lctx, rctx = localbookmarks.changectx(bm), repo[rnode]
             if bookmarks.validdest(repo, rctx, lctx):
                 bookmarkedheads.add(lctx.node())
         else:
             if bm in newbookmarks and bm not in remotebookmarks:
                 bookmarkedheads.add(localbookmarks[bm])
 
     return bookmarkedheads
 
 def checkheads(pushop):
     """Check that a push won't add any outgoing head
 
     raise Abort error and display ui message as needed.
     """
 
     repo = pushop.repo.unfiltered()
     remote = pushop.remote
     outgoing = pushop.outgoing
     remoteheads = pushop.remoteheads
     newbranch = pushop.newbranch
     inc = bool(pushop.incoming)
 
     # Check for each named branch if we're creating new remote heads.
     # To be a remote head after push, node must be either:
     # - unknown locally
     # - a local outgoing head descended from update
     # - a remote head that's known locally and not
     #   ancestral to an outgoing head
     if remoteheads == [nullid]:
         # remote is empty, nothing to check.
         return
 
     if remote.capable('branchmap'):
         headssum = _headssummary(pushop)
     else:
         headssum = _oldheadssummary(repo, remoteheads, outgoing, inc)
     pushop.pushbranchmap = headssum
     newbranches = [branch for branch, heads in headssum.iteritems()
                    if heads[0] is None]
     # 1. Check for new branches on the remote.
     if newbranches and not newbranch:  # new branch requires --new-branch
         branchnames = ', '.join(sorted(newbranches))
         raise error.Abort(_("push creates new remote branches: %s!")
                            % branchnames,
                          hint=_("use 'hg push --new-branch' to create"
                                 " new remote branches"))
 
     # 2. Find heads that we need not warn about
     nowarnheads = _nowarnheads(pushop)
 
     # 3. Check for new heads.
     # If there are more heads after the push than before, a suitable
     # error message, depending on unsynced status, is displayed.
     errormsg = None
     for branch, heads in sorted(headssum.iteritems()):
         remoteheads, newheads, unsyncedheads, discardedheads = heads
         # add unsynced data
         if remoteheads is None:
             oldhs = set()
         else:
             oldhs = set(remoteheads)
         oldhs.update(unsyncedheads)
         dhs = None # delta heads, the new heads on branch
         newhs = set(newheads)
         newhs.update(unsyncedheads)
         if unsyncedheads:
             if None in unsyncedheads:
                 # old remote, no heads data
                 heads = None
             else:
                 heads = scmutil.nodesummaries(repo, unsyncedheads)
             if heads is None:
                 repo.ui.status(_("remote has heads that are "
                                  "not known locally\n"))
             elif branch is None:
                 repo.ui.status(_("remote has heads that are "
                                  "not known locally: %s\n") % heads)
             else:
                 repo.ui.status(_("remote has heads on branch '%s' that are "
                                  "not known locally: %s\n") % (branch, heads))
         if remoteheads is None:
             if len(newhs) > 1:
                 dhs = list(newhs)
                 if errormsg is None:
                     errormsg = (_("push creates new branch '%s' "
                                   "with multiple heads") % (branch))
                     hint = _("merge or"
                              " see 'hg help push' for details about"
                              " pushing new heads")
         elif len(newhs) > len(oldhs):
             # remove bookmarked or existing remote heads from the new heads list
             dhs = sorted(newhs - nowarnheads - oldhs)
         if dhs:
             if errormsg is None:
                 if branch not in ('default', None):
                     errormsg = _("push creates new remote head %s "
                                  "on branch '%s'!") % (short(dhs[0]), branch)
                 elif repo[dhs[0]].bookmarks():
                     errormsg = _("push creates new remote head %s "
                                  "with bookmark '%s'!") % (
                                  short(dhs[0]), repo[dhs[0]].bookmarks()[0])
                 else:
                     errormsg = _("push creates new remote head %s!"
                                  ) % short(dhs[0])
                 if unsyncedheads:
                     hint = _("pull and merge or"
                              " see 'hg help push' for details about"
                              " pushing new heads")
                 else:
                     hint = _("merge or"
                              " see 'hg help push' for details about"
                              " pushing new heads")
             if branch is None:
                 repo.ui.note(_("new remote heads:\n"))
             else:
                 repo.ui.note(_("new remote heads on branch '%s':\n") % branch)
             for h in dhs:
                 repo.ui.note((" %s\n") % short(h))
     if errormsg:
         raise error.Abort(errormsg, hint=hint)
 
 def _postprocessobsolete(pushop, futurecommon, candidate_newhs):
     """post process the list of new heads with obsolescence information
 
     Exists as a sub-function to contain the complexity and allow extensions to
     experiment with smarter logic.
 
     Returns (newheads, discarded_heads) tuple
     """
     # known issue
     #
     # * We "silently" skip processing on all changeset unknown locally
     #
     # * if <nh> is public on the remote, it won't be affected by obsolete
     #     marker and a new is created
 
     # define various utilities and containers
     repo = pushop.repo
     unfi = repo.unfiltered()
     tonode = unfi.changelog.node
     torev = unfi.changelog.nodemap.get
     public = phases.public
     getphase = unfi._phasecache.phase
     ispublic = (lambda r: getphase(unfi, r) == public)
     ispushed = (lambda n: torev(n) in futurecommon)
     hasoutmarker = functools.partial(pushingmarkerfor, unfi.obsstore, ispushed)
     successorsmarkers = unfi.obsstore.successors
     newhs = set() # final set of new heads
     discarded = set() # new head of fully replaced branch
 
     localcandidate = set() # candidate heads known locally
     unknownheads = set() # candidate heads unknown locally
     for h in candidate_newhs:
         if h in unfi:
             localcandidate.add(h)
         else:
             if successorsmarkers.get(h) is not None:
                 msg = ('checkheads: remote head unknown locally has'
                        ' local marker: %s\n')
                 repo.ui.debug(msg % hex(h))
             unknownheads.add(h)
 
     # fast path the simple case
     if len(localcandidate) == 1:
         return unknownheads | set(candidate_newhs), set()
 
     # actually process branch replacement
     while localcandidate:
         nh = localcandidate.pop()
         # run this check early to skip the evaluation of the whole branch
         if (torev(nh) in futurecommon or ispublic(torev(nh))):
             newhs.add(nh)
             continue
 
         # Get all revs/nodes on the branch exclusive to this head
         # (already filtered heads are "ignored"))
         branchrevs = unfi.revs('only(%n, (%ln+%ln))',
                                nh, localcandidate, newhs)
         branchnodes = [tonode(r) for r in branchrevs]
 
         # The branch won't be hidden on the remote if
         # * any part of it is public,
         # * any part of it is considered part of the result by previous logic,
         # * if we have no markers to push to obsolete it.
         if (any(ispublic(r) for r in branchrevs)
                 or any(torev(n) in futurecommon for n in branchnodes)
                 or any(not hasoutmarker(n) for n in branchnodes)):
             newhs.add(nh)
         else:
             # note: there is a corner case if there is a merge in the branch.
             # we might end up with -more- heads.  However, these heads are not
             # "added" by the push, but more by the "removal" on the remote so I
             # think is a okay to ignore them,
             discarded.add(nh)
     newhs |= unknownheads
     return newhs, discarded
 
 def pushingmarkerfor(obsstore, ispushed, node):
     """true if some markers are to be pushed for node
 
     We cannot just look in to the pushed obsmarkers from the pushop because
     discovery might have filtered relevant markers. In addition listing all
     markers relevant to all changesets in the pushed set would be too expensive
     (O(len(repo)))
 
     (note: There are cache opportunity in this function. but it would requires
     a two dimensional stack.)
     """
     successorsmarkers = obsstore.successors
     stack = [node]
     seen = set(stack)
     while stack:
         current = stack.pop()
         if ispushed(current):
             return True
         markers = successorsmarkers.get(current, ())
         # markers fields = ('prec', 'succs', 'flag', 'meta', 'date', 'parents')
         for m in markers:
             nexts = m[1] # successors
             if not nexts: # this is a prune marker
                 nexts = m[5] or () # parents
             for n in nexts:
                 if n not in seen:
                     seen.add(n)
                     stack.append(n)
     return False