view mercurial/setdiscovery.py @ 36367:043e77f3be09

sshpeer: return framed file object when needed

Currently, wireproto.wirepeer has a default implementation of
_submitbatch() and sshv1peer has a very similar implementation.
The main difference is that sshv1peer is aware of the total amount
of bytes it can read whereas the default implementation reads the
stream until no more data is returned. The default implementation
works for HTTP, since there is a known end to HTTP responses (either
Content-Length or 0 sized chunk).

This commit teaches sshv1peer to use our just-introduced "cappedreader"
class for wrapping a file object to limit the number of bytes that
can be read. We do this by introducing an argument to specify whether
the response is framed. If set, we returned a cappedreader instance
instead of the raw pipe.

_call() always has framed responses. So we set this argument
unconditionally and then .read() the entirety of the result.
Strictly speaking, we don't need to use cappedreader in this case
and can inline frame decoding/read logic. But I like when things
are consistent. The overhead should be negligible.

_callstream() and _callcompressable() are special: whether framing
is used depends on the specific command. So, we define a set
of commands that have framed response. It currently only
contains "batch."

As a result of this change, the one-off implementation of
_submitbatch() in sshv1peer can be removed since it is now
safe to .read() the response's file object until end of stream.
cappedreader takes care of not overrunning the frame.

Differential Revision: https://phab.mercurial-scm.org/D2380

# 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.
"""
Algorithm works in the following way. You have two repository: local and
remote. They both contains a DAG of changelists.

The goal of the discovery protocol is to find one set of node *common*,
the set of nodes shared by local and remote.

One of the issue with the original protocol was latency, it could
potentially require lots of roundtrips to discover that the local repo was a
subset of remote (which is a very common case, you usually have few changes
compared to upstream, while upstream probably had lots of development).

The new protocol only requires one interface for the remote repo: `known()`,
which given a set of changelists tells you if they are present in the DAG.

The algorithm then works as follow:

 - We will be using three sets, `common`, `missing`, `unknown`. Originally
 all nodes are in `unknown`.
 - Take a sample from `unknown`, call `remote.known(sample)`
   - For each node that remote knows, move it and all its ancestors to `common`
   - For each node that remote doesn't know, move it and all its descendants
   to `missing`
 - Iterate until `unknown` is empty

There are a couple optimizations, first is instead of starting with a random
sample of missing, start by sending all heads, in the case where the local
repo is a subset, you computed the answer in one round trip.

Then you can do something similar to the bisecting strategy used when
finding faulty changesets. Instead of random samples, you can try picking
nodes that will maximize the number of nodes that will be
classified with it (since all ancestors or descendants will be marked as well).
"""

from __future__ import absolute_import

import collections
import random

from .i18n import _
from .node import (
    nullid,
    nullrev,
)
from . import (
    dagutil,
    error,
    util,
)

def _updatesample(dag, nodes, sample, quicksamplesize=0):
    """update an existing sample to match the expected size

    The sample is updated with nodes exponentially distant from each head of the
    <nodes> set. (H~1, H~2, H~4, H~8, etc).

    If a target size is specified, the sampling will stop once this size is
    reached. Otherwise sampling will happen until roots of the <nodes> set are
    reached.

    :dag: a dag object from dagutil
    :nodes:  set of nodes we want to discover (if None, assume the whole dag)
    :sample: a sample to update
    :quicksamplesize: optional target size of the sample"""
    # if nodes is empty we scan the entire graph
    if nodes:
        heads = dag.headsetofconnecteds(nodes)
    else:
        heads = dag.heads()
    dist = {}
    visit = collections.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:
            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 _takequicksample(dag, nodes, size):
    """takes a quick sample of size <size>

    It is meant for initial sampling and focuses on querying heads and close
    ancestors of heads.

    :dag: a dag object
    :nodes: set of nodes to discover
    :size: the maximum size of the sample"""
    sample = dag.headsetofconnecteds(nodes)
    if size <= len(sample):
        return _limitsample(sample, size)
    _updatesample(dag, None, sample, quicksamplesize=size)
    return sample

def _takefullsample(dag, nodes, size):
    sample = dag.headsetofconnecteds(nodes)
    # update from heads
    _updatesample(dag, nodes, sample)
    # update from roots
    _updatesample(dag.inverse(), nodes, sample)
    assert sample
    sample = _limitsample(sample, size)
    if len(sample) < size:
        more = size - len(sample)
        sample.update(random.sample(list(nodes - sample), more))
    return sample

def _limitsample(sample, desiredlen):
    """return a random subset of sample of at most desiredlen item"""
    if len(sample) > desiredlen:
        sample = set(random.sample(sample, desiredlen))
    return sample

def findcommonheads(ui, local, remote, heads=None,
                    initialsamplesize=100,
                    fullsamplesize=200,
                    abortwhenunrelated=True,
                    ancestorsof=None):
    '''Return a tuple (common, anyincoming, remoteheads) used to identify
    missing nodes from or in remote.
    '''
    start = util.timer()

    roundtrips = 0
    cl = local.changelog
    localsubset = None
    if ancestorsof is not None:
        rev = local.changelog.rev
        localsubset = [rev(n) for n in ancestorsof]
    dag = dagutil.revlogdag(cl, localsubset=localsubset)

    # early exit if we know all the specified remote heads already
    ui.debug("query 1; heads\n")
    roundtrips += 1
    ownheads = dag.heads()
    sample = _limitsample(ownheads, initialsamplesize)
    # indices between sample and externalized version must match
    sample = list(sample)
    if heads:
        srvheadhashes = heads
        yesno = remote.known(dag.externalizeall(sample))
    else:
        batch = remote.iterbatch()
        batch.heads()
        batch.known(dag.externalizeall(sample))
        batch.submit()
        srvheadhashes, yesno = batch.results()

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

    # full blown discovery

    # own nodes I know we both know
    # treat remote heads (and maybe own heads) as a first implicit sample
    # response
    common = cl.incrementalmissingrevs(srvheads)
    commoninsample = set(n for i, n in enumerate(sample) if yesno[i])
    common.addbases(commoninsample)
    # own nodes where I don't know if remote knows them
    undecided = set(common.missingancestors(ownheads))
    # own nodes I know remote lacks
    missing = set()

    full = False
    while undecided:

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

            undecided.difference_update(missing)

        if not undecided:
            break

        if full or common.hasbases():
            if full:
                ui.note(_("sampling from both directions\n"))
            else:
                ui.debug("taking initial sample\n")
            samplefunc = _takefullsample
            targetsize = fullsamplesize
        else:
            # use even cheaper initial sample
            ui.debug("taking quick initial sample\n")
            samplefunc = _takequicksample
            targetsize = initialsamplesize
        if len(undecided) < targetsize:
            sample = list(undecided)
        else:
            sample = samplefunc(dag, undecided, targetsize)
            sample = _limitsample(sample, targetsize)

        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

        if sample:
            commoninsample = set(n for i, n in enumerate(sample) if yesno[i])
            common.addbases(commoninsample)
            common.removeancestorsfrom(undecided)

    # heads(common) == heads(common.bases) since common represents common.bases
    # and all its ancestors
    result = dag.headsetofconnecteds(common.bases)
    # common.bases can include nullrev, but our contract requires us to not
    # return any heads in that case, so discard that
    result.discard(nullrev)
    elapsed = util.timer() - start
    ui.progress(_('searching'), None)
    ui.debug("%d total queries in %.4fs\n" % (roundtrips, elapsed))
    msg = ('found %d common and %d unknown server heads,'
           ' %d roundtrips in %.4fs\n')
    missing = set(result) - set(srvheads)
    ui.log('discovery', msg, len(result), len(missing), roundtrips,
           elapsed)

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

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