comparison mercurial/exchangev2.py @ 39633:ff2de4f2eb3c

exchangev2: fetch and apply phases data

Now that the server supports emitting phases data, we can request it
and apply it on the client.

Because we may receive phases-only updates from the server, we no
longer conditionally perform the "changesetdata" command depending
on whether there are revisions to fetch. In the previous wire
protocol, this case would result in us falling back to performing
"listkeys" commands to look up phases, bookmarks, etc data. But
since "changesetdata" is smart enough to handle metadata only
fetches, we can keep things consistent.

It's worth noting that because of the unified approach to changeset
data retrieval, phase handling code in wire proto v2 exchange is
drastically simpler. Contrast with all the code in exchange.py
dealing with all the variations for obtaining phases data.

Differential Revision: https://phab.mercurial-scm.org/D4484

39632:c1aacb0d76ff

    nullid,
    short,
)
from . import (
    mdiff,
    pycompat,
    setdiscovery,
)

def pull(pullop):

    # Figure out what needs to be fetched.
    common, fetch, remoteheads = _pullchangesetdiscovery(
        repo, remote, pullop.heads, abortwhenunrelated=pullop.force)

    pullheads = pullop.heads or remoteheads
    _fetchchangesets(repo, tr, remote, common, fetch, pullheads)

def _pullchangesetdiscovery(repo, remote, heads, abortwhenunrelated=True):
    """Determine which changesets need to be pulled."""

    if heads:

    common.discard(nullid)

    return common, fetch, remoteheads

def _fetchchangesets(repo, tr, remote, common, fetch, remoteheads):
    if not fetch:
        return

    # TODO consider adding a step here where we obtain the DAG shape first
    # (or ask the server to slice changesets into chunks for us) so that
    # we can perform multiple fetches in batches. This will facilitate
    # resuming interrupted clones, higher server-side cache hit rates due
    # to smaller segments, etc.
    with remote.commandexecutor() as e:
        objs = e.callcommand(b'changesetdata', {
            b'noderange': [sorted(common), sorted(remoteheads)],
            b'fields': {b'parents', b'revision'},
        }).result()

        # The context manager waits on all response data when exiting. So
        # we need to remain in the context manager in order to stream data.
        return _processchangesetdata(repo, tr, objs)

        return len(cl)

    def onchangeset(cl, node):
        progress.increment()

    # addgroup() expects a 7-tuple describing revisions. This normalizes
    # the wire data to that format.
    def iterrevisions():
        for cset in objs:
            assert b'revisionsize' in cset
            data = next(objs)

            yield (
                cset[b'node'],
                cset[b'parents'][0],
                cset[b'parents'][1],
                # Linknode is always itself for changesets.
                cset[b'node'],
                # We always send full revisions. So delta base is not set.

    progress.complete()

    return {
        'added': added,
    }

39633:ff2de4f2eb3c

    nullid,
    short,
)
from . import (
    mdiff,
    phases,
    pycompat,
    setdiscovery,
)

def pull(pullop):

    # Figure out what needs to be fetched.
    common, fetch, remoteheads = _pullchangesetdiscovery(
        repo, remote, pullop.heads, abortwhenunrelated=pullop.force)

    # And fetch the data.
    pullheads = pullop.heads or remoteheads
    csetres = _fetchchangesets(repo, tr, remote, common, fetch, pullheads)

    # New revisions are written to the changelog. But all other updates
    # are deferred. Do those now.

    # Ensure all new changesets are draft by default. If the repo is
    # publishing, the phase will be adjusted by the loop below.
    if csetres['added']:
        phases.registernew(repo, tr, phases.draft, csetres['added'])

    # And adjust the phase of all changesets accordingly.
    for phase in phases.phasenames:
        if phase == b'secret' or not csetres['nodesbyphase'][phase]:
            continue

        phases.advanceboundary(repo, tr, phases.phasenames.index(phase),
                               csetres['nodesbyphase'][phase])

def _pullchangesetdiscovery(repo, remote, heads, abortwhenunrelated=True):
    """Determine which changesets need to be pulled."""

    if heads:

    common.discard(nullid)

    return common, fetch, remoteheads

def _fetchchangesets(repo, tr, remote, common, fetch, remoteheads):
    # TODO consider adding a step here where we obtain the DAG shape first
    # (or ask the server to slice changesets into chunks for us) so that
    # we can perform multiple fetches in batches. This will facilitate
    # resuming interrupted clones, higher server-side cache hit rates due
    # to smaller segments, etc.
    with remote.commandexecutor() as e:
        objs = e.callcommand(b'changesetdata', {
            b'noderange': [sorted(common), sorted(remoteheads)],
            b'fields': {b'parents', b'phase', b'revision'},
        }).result()

        # The context manager waits on all response data when exiting. So
        # we need to remain in the context manager in order to stream data.
        return _processchangesetdata(repo, tr, objs)

        return len(cl)

    def onchangeset(cl, node):
        progress.increment()

    nodesbyphase = {phase: set() for phase in phases.phasenames}

    # addgroup() expects a 7-tuple describing revisions. This normalizes
    # the wire data to that format.
    #
    # This loop also aggregates non-revision metadata, such as phase
    # data.
    def iterrevisions():
        for cset in objs:
            node = cset[b'node']

            if b'phase' in cset:
                nodesbyphase[cset[b'phase']].add(node)

            # Some entries might only be metadata only updates.
            if b'revisionsize' not in cset:
                continue

            data = next(objs)

            yield (
                node,
                cset[b'parents'][0],
                cset[b'parents'][1],
                # Linknode is always itself for changesets.
                cset[b'node'],
                # We always send full revisions. So delta base is not set.

    progress.complete()

    return {
        'added': added,
        'nodesbyphase': nodesbyphase,
    }