view mercurial/treediscovery.py @ 48178:f12a19d03d2c

fix: reduce number of tool executions By grouping together (path, ctx) pairs according to the inputs they would provide to fixer tools, we can deduplicate executions of fixer tools to significantly reduce the amount of time spent running slow tools. This change does not handle clean files in the working copy, which could still be deduplicated against the files in the checked out commit. It's a little harder to do that because the filerev is not available in the workingfilectx (and it doesn't exist for added files). Anecdotally, this change makes some real uses cases at Google 10x faster. I think we were originally hesitant to do this because the benefits weren't obvious, and implementing it efficiently is kind of tricky. If we simply memoized the formatter execution function, we would be keeping tons of file content in memory. Also included is a regression test for a corner case that I broke with my first attempt at optimizing this code. Differential Revision: https://phab.mercurial-scm.org/D11280
author Danny Hooper <hooper@google.com>
date Thu, 02 Sep 2021 14:08:45 -0700
parents d55b71393907
children 6000f5b25c9b
line wrap: on
line source

# discovery.py - protocol changeset discovery functions
#
# Copyright 2010 Olivia Mackall <olivia@selenic.com>
#
# 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 short
from . import (
    error,
    pycompat,
)


def findcommonincoming(repo, remote, heads=None, force=False, audit=None):
    """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(b'heads', {}).result()

    if audit is not None:
        audit[b'total-roundtrips'] = 1

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

    # assume we're closer to the tip than the root
    # and start by examining the heads
    repo.ui.status(_(b"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(_(b'searching'), unit=_(b'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(b'branches', {b'nodes': unknown}).result()

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

            repo.ui.debug(b"examining %s:%s\n" % (short(n[0]), short(n[1])))
            if n[0] == repo.nullid:  # found the end of the branch
                pass
            elif n in seenbranch:
                repo.ui.debug(b"branch already found\n")
                continue
            elif n[1] and knownnode(n[1]):  # do we know the base?
                repo.ui.debug(
                    b"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(b"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(
                b"request %d: %s\n" % (reqcnt, b" ".join(map(short, r)))
            )
            for p in pycompat.xrange(0, len(r), 10):
                with remote.commandexecutor() as e:
                    branches = e.callcommand(
                        b'branches',
                        {
                            b'nodes': r[p : p + 10],
                        },
                    ).result()

                for b in branches:
                    repo.ui.debug(
                        b"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(b'between', {b'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(b"narrowing %d:%d %s\n" % (f, len(l), short(i)))
                if knownnode(i):
                    if f <= 2:
                        repo.ui.debug(
                            b"found new branch changeset %s\n" % short(p)
                        )
                        fetch.add(p)
                        base.add(i)
                    else:
                        repo.ui.debug(
                            b"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(_(b"already have changeset ") + short(f[:4]))

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

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

    progress.complete()
    repo.ui.debug(b"%d total queries\n" % reqcnt)
    if audit is not None:
        audit[b'total-roundtrips'] = reqcnt

    return base, list(fetch), heads