comparison mercurial/revlogutils/deltas.py @ 39505:c6b8eab5db19

snapshot: also consider the snapshot chain of one unrelated revision

To maximize the chance of good delta chain reuse, we inject an unrelated delta
chain into our search. To do so, we search for the highest revision unrelated
to the parents of the current revision and use its snapshot chain too.

Adding this extra snapshot into the mix can have a performance impact. We'll
deal with performance impact in a later series.

39504:05a165dc4f55

                if not revlog.issnapshot(s):
                    break
                parents_snaps[idx].add(s)
        snapfloor = min(parents_snaps[0]) + 1
        _findsnapshots(revlog, snapshots, snapfloor)
        # Test them as possible intermediate snapshot base
        # We test them from highest to lowest level. High level one are more
        # likely to result in small delta
        floor = None
        for idx, snaps in sorted(parents_snaps.items(), reverse=True):

        # revisions instead of starting our own. Without such re-use,
        # topological branches would keep reopening new full chains. Creating
        # more and more snapshot as the repository grow.
        yield tuple(snapshots[nullrev])

    # other approach failed try against prev to hopefully save us a
    # fulltext.
    yield (prev,)

class deltacomputer(object):
    def __init__(self, revlog):
        self.revlog = revlog

39505:c6b8eab5db19

                if not revlog.issnapshot(s):
                    break
                parents_snaps[idx].add(s)
        snapfloor = min(parents_snaps[0]) + 1
        _findsnapshots(revlog, snapshots, snapfloor)
        # search for the highest "unrelated" revision
        #
        # Adding snapshots used by "unrelated" revision increase the odd we
        # reuse an independant, yet better snapshot chain.
        #
        # XXX instead of building a set of revisions, we could lazily enumerate
        # over the chains. That would be more efficient, however we stick to
        # simple code for now.
        all_revs = set()
        for chain in candidate_chains:
            all_revs.update(chain)
        other = None
        for r in revlog.revs(prev, snapfloor):
            if r not in all_revs:
                other = r
                break
        if other is not None:
            # To avoid unfair competition, we won't use unrelated intermediate
            # snapshot that are deeper than the ones from the parent delta
            # chain.
            max_depth = max(parents_snaps.keys())
            chain = deltachain(other)
            for idx, s in enumerate(chain):
                if s < snapfloor:
                    continue
                if max_depth < idx:
                    break
                if not revlog.issnapshot(s):
                    break
                parents_snaps[idx].add(s)
        # Test them as possible intermediate snapshot base
        # We test them from highest to lowest level. High level one are more
        # likely to result in small delta
        floor = None
        for idx, snaps in sorted(parents_snaps.items(), reverse=True):

        # revisions instead of starting our own. Without such re-use,
        # topological branches would keep reopening new full chains. Creating
        # more and more snapshot as the repository grow.
        yield tuple(snapshots[nullrev])

    if not sparse:
        # other approach failed try against prev to hopefully save us a
        # fulltext.
        yield (prev,)

class deltacomputer(object):
    def __init__(self, revlog):
        self.revlog = revlog