mercurial/peer.py

rebase: use matcher to optimize manifestmerge

The old merge code would call manifestmerge and calculate the complete diff
between the source to the destination. In many cases, like rebase, the vast
majority of differences between the source and destination are irrelevant
because they are differences between the destination and the common ancestor
only, and therefore don't affect the merge. Since most actions are 'keep', all
the effort to compute them is wasted.

Instead, let's compute the difference between the source and the common ancestor
and only perform the diff of those files against the merge destination. When
using treemanifest, this lets us avoid loading almost the entire tree when
rebasing from a very old ancestor. This speeds up rebase of an old stack of 27
commits by 20x.

In mozilla-central, without treemanifest, when rebasing a commit from
default~100000 to default, this speeds up the manifestmerge step from 2.6s to
1.2s.  However, the additional diff adds an overhead to all manifestmerge calls,
especially for flat manifests. When rebasing a commit from default~1 to default
it appears to add 100ms in mozilla-central. While we could put this optimization
behind a flag, I think the fact that it makes merge O(number of changes being
applied) instead of O(number of changes between X and Y) justifies it.

# peer.py - repository base classes for mercurial
#
# Copyright 2005, 2006 Matt Mackall <[e-mail]>
# Copyright 2006 Vadim Gelfer <[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

from .i18n import _
from . import (
    error,
    util,
)

# abstract batching support

class future(object):
    '''placeholder for a value to be set later'''
    def set(self, value):
        if util.safehasattr(self, 'value'):
            raise error.RepoError("future is already set")
        self.value = value

class batcher(object):
    '''base class for batches of commands submittable in a single request

    All methods invoked on instances of this class are simply queued and
    return a a future for the result. Once you call submit(), all the queued
    calls are performed and the results set in their respective futures.
    '''
    def __init__(self):
        self.calls = []
    def __getattr__(self, name):
        def call(*args, **opts):
            resref = future()
            self.calls.append((name, args, opts, resref,))
            return resref
        return call
    def submit(self):
        raise NotImplementedError()

class iterbatcher(batcher):

    def submit(self):
        raise NotImplementedError()

    def results(self):
        raise NotImplementedError()

class localbatch(batcher):
    '''performs the queued calls directly'''
    def __init__(self, local):
        batcher.__init__(self)
        self.local = local
    def submit(self):
        for name, args, opts, resref in self.calls:
            resref.set(getattr(self.local, name)(*args, **opts))

class localiterbatcher(iterbatcher):
    def __init__(self, local):
        super(iterbatcher, self).__init__()
        self.local = local

    def submit(self):
        # submit for a local iter batcher is a noop
        pass

    def results(self):
        for name, args, opts, resref in self.calls:
            yield getattr(self.local, name)(*args, **opts)

def batchable(f):
    '''annotation for batchable methods

    Such methods must implement a coroutine as follows:

    @batchable
    def sample(self, one, two=None):
        # Handle locally computable results first:
        if not one:
            yield "a local result", None
        # Build list of encoded arguments suitable for your wire protocol:
        encargs = [('one', encode(one),), ('two', encode(two),)]
        # Create future for injection of encoded result:
        encresref = future()
        # Return encoded arguments and future:
        yield encargs, encresref
        # Assuming the future to be filled with the result from the batched
        # request now. Decode it:
        yield decode(encresref.value)

    The decorator returns a function which wraps this coroutine as a plain
    method, but adds the original method as an attribute called "batchable",
    which is used by remotebatch to split the call into separate encoding and
    decoding phases.
    '''
    def plain(*args, **opts):
        batchable = f(*args, **opts)
        encargsorres, encresref = next(batchable)
        if not encresref:
            return encargsorres # a local result in this case
        self = args[0]
        encresref.set(self._submitone(f.func_name, encargsorres))
        return next(batchable)
    setattr(plain, 'batchable', f)
    return plain

class peerrepository(object):

    def batch(self):
        return localbatch(self)

    def iterbatch(self):
        """Batch requests but allow iterating over the results.

        This is to allow interleaving responses with things like
        progress updates for clients.
        """
        return localiterbatcher(self)

    def capable(self, name):
        '''tell whether repo supports named capability.
        return False if not supported.
        if boolean capability, return True.
        if string capability, return string.'''
        caps = self._capabilities()
        if name in caps:
            return True
        name_eq = name + '='
        for cap in caps:
            if cap.startswith(name_eq):
                return cap[len(name_eq):]
        return False

    def requirecap(self, name, purpose):
        '''raise an exception if the given capability is not present'''
        if not self.capable(name):
            raise error.CapabilityError(
                _('cannot %s; remote repository does not '
                  'support the %r capability') % (purpose, name))

    def local(self):
        '''return peer as a localrepo, or None'''
        return None

    def peer(self):
        return self

    def canpush(self):
        return True

    def close(self):
        pass