view mercurial/treediscovery.py @ 40628:29e4a77b5305

shelve: use matcher to restrict prefetch to just the modified files

Shelve currently operates by:
- make a temp commit
- identify all the bases necessary to shelve, put them in the bundle
- use exportfile to export the temp commit to the bundle ('file' here means
  "export to this fd", not "export this file")
- remove the temp commit

exportfile calls prefetchfiles, and prefetchfiles uses a matcher to restrict
what files it's going to prefetch; if it's not provided, it's alwaysmatcher.
This means that `hg shelve` in a remotefilelog repo can possibly download the
file contents of everything in the repository, even when it doesn't need to. It
luckily is restricted to the narrowspec (if there is one), but this is still a
lot of downloading that's just unnecessary, especially if there's a "smart"
VCS-aware filesystem involved.

exportfile is called with exactly one revision to emit, so we're just
restricting it to prefetching the files from that revision. The base revisions
having separate files should not be a concern since they're handled already;
example:

commit 10 is draft and modifies foo/a.txt and foo/b.txt
commit 11 is draft and modifies foo/a.txt
my working directory that I'm shelving modifies foo/b.txt

By the time we get to exportfile, commit 10 and 11 are already handled, so the
matcher only specifying foo/b.txt does not cause any problems. I verified this
by doing an `hg unbundle` on the bundle that shelve produces, and getting the
full contents of those commits back out, instead of just the files that were
modified in the shelve.

Differential Revision: https://phab.mercurial-scm.org/D5268

# discovery.py - protocol changeset discovery functions
#
# Copyright 2010 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import collections

from .i18n import _
from .node import (
    nullid,
    short,
)
from . import (
    error,
    pycompat,
)

def findcommonincoming(repo, remote, heads=None, force=False):
    """Return a tuple (common, fetch, heads) used to identify the common
    subset of nodes between repo and remote.

    "common" is a list of (at least) the heads of the common subset.
    "fetch" is a list of roots of the nodes that would be incoming, to be
      supplied to changegroupsubset.
    "heads" is either the supplied heads, or else the remote's heads.
    """

    knownnode = repo.changelog.hasnode
    search = []
    fetch = set()
    seen = set()
    seenbranch = set()
    base = set()

    if not heads:
        with remote.commandexecutor() as e:
            heads = e.callcommand('heads', {}).result()

    if repo.changelog.tip() == nullid:
        base.add(nullid)
        if heads != [nullid]:
            return [nullid], [nullid], list(heads)
        return [nullid], [], heads

    # assume we're closer to the tip than the root
    # and start by examining the heads
    repo.ui.status(_("searching for changes\n"))

    unknown = []
    for h in heads:
        if not knownnode(h):
            unknown.append(h)
        else:
            base.add(h)

    if not unknown:
        return list(base), [], list(heads)

    req = set(unknown)
    reqcnt = 0
    progress = repo.ui.makeprogress(_('searching'), unit=_('queries'))

    # search through remote branches
    # a 'branch' here is a linear segment of history, with four parts:
    # head, root, first parent, second parent
    # (a branch always has two parents (or none) by definition)
    with remote.commandexecutor() as e:
        branches = e.callcommand('branches', {'nodes': unknown}).result()

    unknown = collections.deque(branches)
    while unknown:
        r = []
        while unknown:
            n = unknown.popleft()
            if n[0] in seen:
                continue

            repo.ui.debug("examining %s:%s\n"
                          % (short(n[0]), short(n[1])))
            if n[0] == nullid: # found the end of the branch
                pass
            elif n in seenbranch:
                repo.ui.debug("branch already found\n")
                continue
            elif n[1] and knownnode(n[1]): # do we know the base?
                repo.ui.debug("found incomplete branch %s:%s\n"
                              % (short(n[0]), short(n[1])))
                search.append(n[0:2]) # schedule branch range for scanning
                seenbranch.add(n)
            else:
                if n[1] not in seen and n[1] not in fetch:
                    if knownnode(n[2]) and knownnode(n[3]):
                        repo.ui.debug("found new changeset %s\n" %
                                      short(n[1]))
                        fetch.add(n[1]) # earliest unknown
                    for p in n[2:4]:
                        if knownnode(p):
                            base.add(p) # latest known

                for p in n[2:4]:
                    if p not in req and not knownnode(p):
                        r.append(p)
                        req.add(p)
            seen.add(n[0])

        if r:
            reqcnt += 1
            progress.increment()
            repo.ui.debug("request %d: %s\n" %
                        (reqcnt, " ".join(map(short, r))))
            for p in pycompat.xrange(0, len(r), 10):
                with remote.commandexecutor() as e:
                    branches = e.callcommand('branches', {
                        'nodes': r[p:p + 10],
                    }).result()

                for b in branches:
                    repo.ui.debug("received %s:%s\n" %
                                  (short(b[0]), short(b[1])))
                    unknown.append(b)

    # do binary search on the branches we found
    while search:
        newsearch = []
        reqcnt += 1
        progress.increment()

        with remote.commandexecutor() as e:
            between = e.callcommand('between', {'pairs': search}).result()

        for n, l in zip(search, between):
            l.append(n[1])
            p = n[0]
            f = 1
            for i in l:
                repo.ui.debug("narrowing %d:%d %s\n" % (f, len(l), short(i)))
                if knownnode(i):
                    if f <= 2:
                        repo.ui.debug("found new branch changeset %s\n" %
                                          short(p))
                        fetch.add(p)
                        base.add(i)
                    else:
                        repo.ui.debug("narrowed branch search to %s:%s\n"
                                      % (short(p), short(i)))
                        newsearch.append((p, i))
                    break
                p, f = i, f * 2
            search = newsearch

    # sanity check our fetch list
    for f in fetch:
        if knownnode(f):
            raise error.RepoError(_("already have changeset ")
                                  + short(f[:4]))

    base = list(base)
    if base == [nullid]:
        if force:
            repo.ui.warn(_("warning: repository is unrelated\n"))
        else:
            raise error.Abort(_("repository is unrelated"))

    repo.ui.debug("found new changesets starting at " +
                 " ".join([short(f) for f in fetch]) + "\n")

    progress.complete()
    repo.ui.debug("%d total queries\n" % reqcnt)

    return base, list(fetch), heads