comparison mercurial/localrepo.py @ 9820:0b999aec64e8

bundle: don't send too many changesets (Issue1704)

The fast path in changegroupsubset can send too many csets. This happens
because it uses the parents of all bases as common nodes and then goes
forward from this again. If a base has a parent that has another child,
which is -not- a base, then this other child will nevertheless end up in
the changegroup.

The fix is to not use findmissing(), but use nodesbetween() instead, as
do the slow path and incoming/outgoing.

The change to test-notify.out is correct, because it actually hits this
bug, as can be seen by glog'ing the two repos:

@    22c88
|\
| o  0a184
| |
o |  0647d
|/
o  cb9a9

and

o  0647d
|
@  cb9a9

It used to pull 0647d again, which is unnecessary.

9818:72d670c43f6e

                self.ui.warn(_("note: unsynced remote changes!\n"))


        if revs is None:
            # use the fast path, no race possible on push
            cg = self._changegroup(common.keys(), 'push')
        else:
            cg = self.changegroupsubset(update, revs, 'push')
        return cg, remote_heads

    def push_addchangegroup(self, remote, force, revs):

        values are lists of (node, linknode) tuples, where node is a wanted
        node and linknode is the changelog node that should be transmitted as
        the linkrev.
        """

        if extranodes is None:
            # can we go through the fast path ?
            heads.sort()
            allheads = self.heads()
            allheads.sort()
            if heads == allheads:
                common = []
                # parents of bases are known from both sides
                for n in bases:
                    for p in self.changelog.parents(n):
                        if p != nullid:
                            common.append(p)
                return self._changegroup(common, source)

        self.hook('preoutgoing', throw=True, source=source)

        # Set up some initial variables
        # Make it easy to refer to self.changelog
        cl = self.changelog
        # msng is short for missing - compute the list of changesets in this
        # changegroup.
        msng_cl_lst, bases, heads = cl.nodesbetween(bases, heads)
        self.changegroupinfo(msng_cl_lst, source)
        # Some bases may turn out to be superfluous, and some heads may be
        # too.  nodesbetween will return the minimal set of bases and heads
        # necessary to re-create the changegroup.

    def changegroup(self, basenodes, source):
        # to avoid a race we use changegroupsubset() (issue1320)
        return self.changegroupsubset(basenodes, self.heads(), source)

    def _changegroup(self, common, source):
        """Compute the changegroup of all nodes that we have that a recipient
        doesn't.  Return a chunkbuffer object whose read() method will return
        successive changegroup chunks.

        This is much easier than the previous function as we can assume that
        the recipient has any changenode we aren't sending them.

        common is the set of common nodes between remote and self"""

        self.hook('preoutgoing', throw=True, source=source)

        cl = self.changelog
        nodes = cl.findmissing(common)
        revset = set([cl.rev(n) for n in nodes])
        self.changegroupinfo(nodes, source)

        def identity(x):
            return x

9820:0b999aec64e8

                self.ui.warn(_("note: unsynced remote changes!\n"))


        if revs is None:
            # use the fast path, no race possible on push
            nodes = self.changelog.findmissing(common.keys())
            cg = self._changegroup(nodes, 'push')
        else:
            cg = self.changegroupsubset(update, revs, 'push')
        return cg, remote_heads

    def push_addchangegroup(self, remote, force, revs):

        values are lists of (node, linknode) tuples, where node is a wanted
        node and linknode is the changelog node that should be transmitted as
        the linkrev.
        """

        # Set up some initial variables
        # Make it easy to refer to self.changelog
        cl = self.changelog
        # msng is short for missing - compute the list of changesets in this
        # changegroup.
        if not bases:
            bases = [nullid]
        msng_cl_lst, bases, heads = cl.nodesbetween(bases, heads)

        if extranodes is None:
            # can we go through the fast path ?
            heads.sort()
            allheads = self.heads()
            allheads.sort()
            if heads == allheads:
                return self._changegroup(msng_cl_lst, source)

        # slow path
        self.hook('preoutgoing', throw=True, source=source)

        self.changegroupinfo(msng_cl_lst, source)
        # Some bases may turn out to be superfluous, and some heads may be
        # too.  nodesbetween will return the minimal set of bases and heads
        # necessary to re-create the changegroup.

    def changegroup(self, basenodes, source):
        # to avoid a race we use changegroupsubset() (issue1320)
        return self.changegroupsubset(basenodes, self.heads(), source)

    def _changegroup(self, nodes, source):
        """Compute the changegroup of all nodes that we have that a recipient
        doesn't.  Return a chunkbuffer object whose read() method will return
        successive changegroup chunks.

        This is much easier than the previous function as we can assume that
        the recipient has any changenode we aren't sending them.

        nodes is the set of nodes to send"""

        self.hook('preoutgoing', throw=True, source=source)

        cl = self.changelog
        revset = set([cl.rev(n) for n in nodes])
        self.changegroupinfo(nodes, source)

        def identity(x):
            return x