view mercurial/setdiscovery.py @ 20528:1a9ebc83a74c

win32: improve the performance of win32.unlink() over CIFS

Emulating POSIX unlink() behavior with os.rename() and os.unlink() is often slow
especially over CIFS from Windows clients due to its protocol overhead. This
patch changes win32.unlink() to try first an exclusive open with the Win32
delete-on-close flag, and if a sharing violation is detected, to fall back to
the original emulation.

This patch also removes a test with os.path.isdir() since we expect opening a
directory shall fail as os.unlink() would.

Example measurements (repeated 3-times after 1-time calibration):

(Without this patch: hg update from null to default)
127 files updated, 0 files merged, 0 files removed, 0 files unresolved
time: real 19.871 secs (user 0.328+0.000 sys 1.794+0.000)
time: real 19.622 secs (user 0.312+0.000 sys 2.044+0.000)
time: real 19.138 secs (user 0.250+0.000 sys 1.872+0.000)

(Without this patch: hg update from default to null)
0 files updated, 0 files merged, 127 files removed, 0 files unresolved
time: real 35.158 secs (user 0.156+0.000 sys 2.512+0.000)
time: real 35.272 secs (user 0.250+0.000 sys 2.512+0.000)
time: real 36.569 secs (user 0.203+0.000 sys 2.387+0.000)

(With this patch: hg update from null to default)
127 files updated, 0 files merged, 0 files removed, 0 files unresolved
time: real 17.893 secs (user 0.328+0.000 sys 1.700+0.000)
time: real 18.512 secs (user 0.265+0.000 sys 1.529+0.000)
time: real 20.238 secs (user 0.312+0.000 sys 1.685+0.000)

(With this patch: hg update from default to null)
0 files updated, 0 files merged, 127 files removed, 0 files unresolved
time: real 12.312 secs (user 0.250+0.000 sys 0.811+0.000)
time: real 12.471 secs (user 0.156+0.000 sys 0.889+0.000)
time: real 9.727 secs (user 0.125+0.000 sys 0.858+0.000)

# setdiscovery.py - improved discovery of common nodeset for mercurial
#
# Copyright 2010 Benoit Boissinot <[e-mail]>
# and Peter Arrenbrecht <[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 node import nullid
from i18n import _
import random
import util, dagutil

def _updatesample(dag, nodes, sample, always, quicksamplesize=0):
    # if nodes is empty we scan the entire graph
    if nodes:
        heads = dag.headsetofconnecteds(nodes)
    else:
        heads = dag.heads()
    dist = {}
    visit = util.deque(heads)
    seen = set()
    factor = 1
    while visit:
        curr = visit.popleft()
        if curr in seen:
            continue
        d = dist.setdefault(curr, 1)
        if d > factor:
            factor *= 2
        if d == factor:
            if curr not in always: # need this check for the early exit below
                sample.add(curr)
                if quicksamplesize and (len(sample) >= quicksamplesize):
                    return
        seen.add(curr)
        for p in dag.parents(curr):
            if not nodes or p in nodes:
                dist.setdefault(p, d + 1)
                visit.append(p)

def _setupsample(dag, nodes, size):
    if len(nodes) <= size:
        return set(nodes), None, 0
    always = dag.headsetofconnecteds(nodes)
    desiredlen = size - len(always)
    if desiredlen <= 0:
        # This could be bad if there are very many heads, all unknown to the
        # server. We're counting on long request support here.
        return always, None, desiredlen
    return always, set(), desiredlen

def _takequicksample(dag, nodes, size, initial):
    always, sample, desiredlen = _setupsample(dag, nodes, size)
    if sample is None:
        return always
    if initial:
        fromset = None
    else:
        fromset = nodes
    _updatesample(dag, fromset, sample, always, quicksamplesize=desiredlen)
    sample.update(always)
    return sample

def _takefullsample(dag, nodes, size):
    always, sample, desiredlen = _setupsample(dag, nodes, size)
    if sample is None:
        return always
    # update from heads
    _updatesample(dag, nodes, sample, always)
    # update from roots
    _updatesample(dag.inverse(), nodes, sample, always)
    assert sample
    if len(sample) > desiredlen:
        sample = set(random.sample(sample, desiredlen))
    elif len(sample) < desiredlen:
        more = desiredlen - len(sample)
        sample.update(random.sample(list(nodes - sample - always), more))
    sample.update(always)
    return sample

def findcommonheads(ui, local, remote,
                    initialsamplesize=100,
                    fullsamplesize=200,
                    abortwhenunrelated=True):
    '''Return a tuple (common, anyincoming, remoteheads) used to identify
    missing nodes from or in remote.
    '''
    roundtrips = 0
    cl = local.changelog
    dag = dagutil.revlogdag(cl)

    # early exit if we know all the specified remote heads already
    ui.debug("query 1; heads\n")
    roundtrips += 1
    ownheads = dag.heads()
    sample = ownheads
    if remote.local():
        # stopgap until we have a proper localpeer that supports batch()
        srvheadhashes = remote.heads()
        yesno = remote.known(dag.externalizeall(sample))
    elif remote.capable('batch'):
        batch = remote.batch()
        srvheadhashesref = batch.heads()
        yesnoref = batch.known(dag.externalizeall(sample))
        batch.submit()
        srvheadhashes = srvheadhashesref.value
        yesno = yesnoref.value
    else:
        # compatibility with pre-batch, but post-known remotes during 1.9
        # development
        srvheadhashes = remote.heads()
        sample = []

    if cl.tip() == nullid:
        if srvheadhashes != [nullid]:
            return [nullid], True, srvheadhashes
        return [nullid], False, []

    # start actual discovery (we note this before the next "if" for
    # compatibility reasons)
    ui.status(_("searching for changes\n"))

    srvheads = dag.internalizeall(srvheadhashes, filterunknown=True)
    if len(srvheads) == len(srvheadhashes):
        ui.debug("all remote heads known locally\n")
        return (srvheadhashes, False, srvheadhashes,)

    if sample and util.all(yesno):
        ui.note(_("all local heads known remotely\n"))
        ownheadhashes = dag.externalizeall(ownheads)
        return (ownheadhashes, True, srvheadhashes,)

    # full blown discovery

    # own nodes where I don't know if remote knows them
    undecided = dag.nodeset()
    # own nodes I know we both know
    common = set()
    # own nodes I know remote lacks
    missing = set()

    # treat remote heads (and maybe own heads) as a first implicit sample
    # response
    common.update(dag.ancestorset(srvheads))
    undecided.difference_update(common)

    full = False
    while undecided:

        if sample:
            commoninsample = set(n for i, n in enumerate(sample) if yesno[i])
            common.update(dag.ancestorset(commoninsample, common))

            missinginsample = [n for i, n in enumerate(sample) if not yesno[i]]
            missing.update(dag.descendantset(missinginsample, missing))

            undecided.difference_update(missing)
            undecided.difference_update(common)

        if not undecided:
            break

        if full:
            ui.note(_("sampling from both directions\n"))
            sample = _takefullsample(dag, undecided, size=fullsamplesize)
        elif common:
            # use cheapish initial sample
            ui.debug("taking initial sample\n")
            sample = _takefullsample(dag, undecided, size=fullsamplesize)
        else:
            # use even cheaper initial sample
            ui.debug("taking quick initial sample\n")
            sample = _takequicksample(dag, undecided, size=initialsamplesize,
                                      initial=True)

        roundtrips += 1
        ui.progress(_('searching'), roundtrips, unit=_('queries'))
        ui.debug("query %i; still undecided: %i, sample size is: %i\n"
                 % (roundtrips, len(undecided), len(sample)))
        # indices between sample and externalized version must match
        sample = list(sample)
        yesno = remote.known(dag.externalizeall(sample))
        full = True

    result = dag.headsetofconnecteds(common)
    ui.progress(_('searching'), None)
    ui.debug("%d total queries\n" % roundtrips)

    if not result and srvheadhashes != [nullid]:
        if abortwhenunrelated:
            raise util.Abort(_("repository is unrelated"))
        else:
            ui.warn(_("warning: repository is unrelated\n"))
        return (set([nullid]), True, srvheadhashes,)

    anyincoming = (srvheadhashes != [nullid])
    return dag.externalizeall(result), anyincoming, srvheadhashes