comparison mercurial/changegroup.py @ 41448:fa7d61f9c512

changegroup: don't try to build changelog chunks if not required

When we extend a narrow clone without ellipsis, we don't download changelog
information because that's already present with the client. However we still try
to build that chunk stream. Building that chunk stream involves calling a lookup
function and store.emitrevisions() API. The lookup function is called len(cl)
number of times.

On large repositories, where len(cl) is in millions, calling that lookup
function is not a good idea. Also it's not required to use the
store.emitrevisons() API because we already have nodes present which we can use.

This patch short-circuits state building logic if we are processing a
non-ellipsis case and changelog is not required.

This saves up ~20 seconds on our internal repo for a single extend call.

Differential Revision: https://phab.mercurial-scm.org/D5733

41445:73a33fe625bb

        cl = repo.changelog

        self._verbosenote(_('uncompressed size of bundle content:\n'))
        size = 0

        clstate, deltas = self._generatechangelog(cl, clnodes)
        for delta in deltas:
            if changelog:
                for chunk in _revisiondeltatochunks(delta,
                                                    self._builddeltaheader):
                    size += len(chunk)
                    yield chunk

        close = closechunk()
        size += len(close)
        yield closechunk()

        yield closechunk()

        if clnodes:
            repo.hook('outgoing', node=hex(clnodes[0]), source=source)

    def _generatechangelog(self, cl, nodes):
        """Generate data for changelog chunks.

        Returns a 2-tuple of a dict containing state and an iterable of
        byte chunks. The state will not be fully populated until the
        chunk stream has been fully consumed.
        """
        clrevorder = {}
        manifests = {}
        mfl = self._repo.manifestlog
        changedfiles = set()

            'clrevorder': clrevorder,
            'manifests': manifests,
            'changedfiles': changedfiles,
            'clrevtomanifestrev': clrevtomanifestrev,
        }

        # Callback for the changelog, used to collect changed files and
        # manifest nodes.
        # Returns the linkrev node (identity in the changelog case).
        def lookupcl(x):

41448:fa7d61f9c512

        cl = repo.changelog

        self._verbosenote(_('uncompressed size of bundle content:\n'))
        size = 0

        clstate, deltas = self._generatechangelog(cl, clnodes,
                                                  generate=changelog)
        for delta in deltas:
            for chunk in _revisiondeltatochunks(delta,
                                                self._builddeltaheader):
                size += len(chunk)
                yield chunk

        close = closechunk()
        size += len(close)
        yield closechunk()

        yield closechunk()

        if clnodes:
            repo.hook('outgoing', node=hex(clnodes[0]), source=source)

    def _generatechangelog(self, cl, nodes, generate=True):
        """Generate data for changelog chunks.

        Returns a 2-tuple of a dict containing state and an iterable of
        byte chunks. The state will not be fully populated until the
        chunk stream has been fully consumed.

        if generate is False, the state will be fully populated and no chunk
        stream will be yielded
        """
        clrevorder = {}
        manifests = {}
        mfl = self._repo.manifestlog
        changedfiles = set()

            'clrevorder': clrevorder,
            'manifests': manifests,
            'changedfiles': changedfiles,
            'clrevtomanifestrev': clrevtomanifestrev,
        }

        if not (generate or self._ellipses):
            # sort the nodes in storage order
            nodes = sorted(nodes, key=cl.rev)
            for node in nodes:
                c = cl.changelogrevision(node)
                clrevorder[node] = len(clrevorder)
                # record the first changeset introducing this manifest version
                manifests.setdefault(c.manifest, node)
                # Record a complete list of potentially-changed files in
                # this manifest.
                changedfiles.update(c.files)

            return state, ()

        # Callback for the changelog, used to collect changed files and
        # manifest nodes.
        # Returns the linkrev node (identity in the changelog case).
        def lookupcl(x):