comparison mercurial/exchangev2.py @ 40393:229d23cdb203

exchangev2: support fetching shallow files history

This commit teaches the exchangev2 client code to handle fetching shallow
files data.

Only shallow fetching of files data is supported: shallow fetching of
changeset and manifest data is explicitly not yet supported.

Previously, we would fetch file revisions for changesets that were received
by the current pull operation. In the new model, we calculate the set of
"relevant" changesets given the pull depth and only fetch files data for
those changesets.

We also teach the "filesdata" command invocation to vary parameters as needed.

The implementation here is far from complete or optimal. Subsequent pulls will
end up re-fetching a lot of files data. But the application of this data should
mostly be a no-op on the client, so it isn't a big deal.

Depending on the order file revisions are fetched in, revisions could get
inserted with the wrong revision number relationships. I think the best way
to deal with this is to remove revision numbers from storage and to either
dynamically derive them (by reconstructing a DAG from nodes/parents) or remove
revision numbers from the file storage interface completely.

A missing API that we'll likely want to write pretty soon is "ensure files
for revision(s) are present." We can kind of cajole exchangev2.pull() to do
this. But it isn't very efficient. For example, in simple cases like
widening the store to obtain data for a single revision, it is probably
more efficient to walk the manifest and find exactly which file revisions
are missing and to make explicit requests for just their data. In more
advanced cases, asking the server for all files data may be more efficient,
even though it requires sending data the client already has. There is tons
of room for future experimentation here. And TBH I'm not sure what the
final state will be.

Anyway, this commit gets us pretty close to being able to have shallow
and narrow checkouts with exchangev2/sqlite storage. Close enough that a
minimal extension should be able to provide fill in the gaps until the code
in core stabilizes and there is a user-facing way to trigger the
narrow/shallow bits from `hg clone` without also implying using of the
narrow extension...

Differential Revision: https://phab.mercurial-scm.org/D5169

40392:595641bd8404

    error,
    mdiff,
    narrowspec,
    phases,
    pycompat,
    setdiscovery,
)

def pull(pullop):
    """Pull using wire protocol version 2."""

                               remote.url(), pullop.gettransaction,
                               explicit=pullop.explicitbookmarks)

    manres = _fetchmanifests(repo, tr, remote, csetres['manifestnodes'])

    # If obtaining the raw store files, we need to scan the full repo to
    # derive all the changesets, manifests, and linkrevs.
    if usingrawchangelogandmanifest:
        csetsforfiles = []
        mnodesforfiles = []
        manifestlinkrevs = {}

        for rev in repo:
            ctx = repo[rev]
            mnode = ctx.manifestnode()

            csetsforfiles.append(ctx.node())
            mnodesforfiles.append(mnode)
            manifestlinkrevs[mnode] = rev

    else:
        csetsforfiles = csetres['added']
        mnodesforfiles = manres['added']
        manifestlinkrevs = manres['linkrevs']

    # Find all file nodes referenced by added manifests and fetch those
    # revisions.
    fnodes = _derivefilesfrommanifests(repo, narrowmatcher, mnodesforfiles)
    _fetchfilesfromcsets(repo, tr, remote, pathfilter, fnodes, csetsforfiles,
                         manifestlinkrevs)

def _checkuserawstorefiledata(pullop):
    """Check whether we should use rawstorefiledata command to retrieve data."""

    repo = pullop.repo

                    iterrevisions(objs, progress),
                    locallinkrevs[path].__getitem__,
                    weakref.proxy(tr))

def _fetchfilesfromcsets(repo, tr, remote, pathfilter, fnodes, csets,
                         manlinkrevs):
    """Fetch file data from explicit changeset revisions."""

    def iterrevisions(objs, remaining, progress):
        while remaining:
            filerevision = next(objs)

                revision = extrafields[b'revision']
                delta = mdiff.trivialdiffheader(len(revision)) + revision
            else:
                continue

            yield (
                node,
                filerevision[b'parents'][0],
                filerevision[b'parents'][1],
                node,
                basenode,
                delta,
                # Flags not yet supported.
                0,
            )

        _('files'), unit=_('chunks'),
        total=sum(len(v) for v in fnodes.itervalues()))

    commandmeta = remote.apidescriptor[b'commands'][b'filesdata']
    batchsize = commandmeta.get(b'recommendedbatchsize', 50000)

    for i in pycompat.xrange(0, len(csets), batchsize):
        batch = [x for x in csets[i:i + batchsize]]
        if not batch:
            continue

            args = {
                b'revisions': [{
                    b'type': b'changesetexplicit',
                    b'nodes': batch,
                }],
                b'fields': {b'parents', b'revision'},
                b'haveparents': True,
            }

            if pathfilter:
                args[b'pathfilter'] = pathfilter

                linkrevs = {
                    fnode: manlinkrevs[mnode]
                    for fnode, mnode in fnodes[path].iteritems()}

                store.addgroup(iterrevisions(objs, header[b'totalitems'],
                                             progress),
                               linkrevs.__getitem__,
                               weakref.proxy(tr))

40393:229d23cdb203

    error,
    mdiff,
    narrowspec,
    phases,
    pycompat,
    repository,
    setdiscovery,
)

def pull(pullop):
    """Pull using wire protocol version 2."""

                               remote.url(), pullop.gettransaction,
                               explicit=pullop.explicitbookmarks)

    manres = _fetchmanifests(repo, tr, remote, csetres['manifestnodes'])

    # We don't properly support shallow changeset and manifest yet. So we apply
    # depth limiting locally.
    if pullop.depth:
        relevantcsetnodes = set()
        clnode = repo.changelog.node

        for rev in repo.revs(b'ancestors(%ln, %d)',
                             pullheads, pullop.depth - 1):
            relevantcsetnodes.add(clnode(rev))

        csetrelevantfilter = lambda n: n in relevantcsetnodes

    else:
        csetrelevantfilter = lambda n: True

    # If obtaining the raw store files, we need to scan the full repo to
    # derive all the changesets, manifests, and linkrevs.
    if usingrawchangelogandmanifest:
        csetsforfiles = []
        mnodesforfiles = []
        manifestlinkrevs = {}

        for rev in repo:
            ctx = repo[rev]
            node = ctx.node()

            if not csetrelevantfilter(node):
                continue

            mnode = ctx.manifestnode()

            csetsforfiles.append(node)
            mnodesforfiles.append(mnode)
            manifestlinkrevs[mnode] = rev

    else:
        csetsforfiles = [n for n in csetres['added'] if csetrelevantfilter(n)]
        mnodesforfiles = manres['added']
        manifestlinkrevs = manres['linkrevs']

    # Find all file nodes referenced by added manifests and fetch those
    # revisions.
    fnodes = _derivefilesfrommanifests(repo, narrowmatcher, mnodesforfiles)
    _fetchfilesfromcsets(repo, tr, remote, pathfilter, fnodes, csetsforfiles,
                         manifestlinkrevs, shallow=bool(pullop.depth))

def _checkuserawstorefiledata(pullop):
    """Check whether we should use rawstorefiledata command to retrieve data."""

    repo = pullop.repo

                    iterrevisions(objs, progress),
                    locallinkrevs[path].__getitem__,
                    weakref.proxy(tr))

def _fetchfilesfromcsets(repo, tr, remote, pathfilter, fnodes, csets,
                         manlinkrevs, shallow=False):
    """Fetch file data from explicit changeset revisions."""

    def iterrevisions(objs, remaining, progress):
        while remaining:
            filerevision = next(objs)

                revision = extrafields[b'revision']
                delta = mdiff.trivialdiffheader(len(revision)) + revision
            else:
                continue

            if b'linknode' in filerevision:
                linknode = filerevision[b'linknode']
            else:
                linknode = node

            yield (
                node,
                filerevision[b'parents'][0],
                filerevision[b'parents'][1],
                linknode,
                basenode,
                delta,
                # Flags not yet supported.
                0,
            )

        _('files'), unit=_('chunks'),
        total=sum(len(v) for v in fnodes.itervalues()))

    commandmeta = remote.apidescriptor[b'commands'][b'filesdata']
    batchsize = commandmeta.get(b'recommendedbatchsize', 50000)

    shallowfiles = repository.REPO_FEATURE_SHALLOW_FILE_STORAGE in repo.features
    fields = {b'parents', b'revision'}
    clrev = repo.changelog.rev

    # There are no guarantees that we'll have ancestor revisions if
    # a) this repo has shallow file storage b) shallow data fetching is enabled.
    # Force remote to not delta against possibly unknown revisions when these
    # conditions hold.
    haveparents = not (shallowfiles or shallow)

    # Similarly, we may not have calculated linkrevs for all incoming file
    # revisions. Ask the remote to do work for us in this case.
    if not haveparents:
        fields.add(b'linknode')

    for i in pycompat.xrange(0, len(csets), batchsize):
        batch = [x for x in csets[i:i + batchsize]]
        if not batch:
            continue

            args = {
                b'revisions': [{
                    b'type': b'changesetexplicit',
                    b'nodes': batch,
                }],
                b'fields': fields,
                b'haveparents': haveparents,
            }

            if pathfilter:
                args[b'pathfilter'] = pathfilter

                linkrevs = {
                    fnode: manlinkrevs[mnode]
                    for fnode, mnode in fnodes[path].iteritems()}

                def getlinkrev(node):
                    if node in linkrevs:
                        return linkrevs[node]
                    else:
                        return clrev(node)

                store.addgroup(iterrevisions(objs, header[b'totalitems'],
                                             progress),
                               getlinkrev,
                               weakref.proxy(tr),
                               maybemissingparents=shallow)