view mercurial/peer.py @ 29304:5e32852fa4bd

revset: make filteredset.__nonzero__ respect the order of the filteredset

This fix allows __nonzero__ to respect the direction of iteration of the
whole filteredset. Here's the case when it matters. Imagine that we have a
very large repository and we want to execute a command like:

    $ hg log --rev '(tip:0) and user(ikostia)' --limit 1

(we want to get the latest commit by me).

Mercurial will evaluate a filteredset lazy data structure, an
instance of the filteredset class, which will know that it has to iterate
in a descending order (isdescending() will return True if called). This
means that when some code iterates over the instance of this filteredset,
the 'and user(ikostia)' condition will be first checked on the latest
revision, then on the second latest and so on, allowing Mercurial to
print matches as it founds them. However, cmdutil.getgraphlogrevs
contains the following code:

    revs = _logrevs(repo, opts)
    if not revs:
        return revset.baseset(), None, None

The "not revs" expression is evaluated by calling filteredset.__nonzero__,
which in its current implementation will try to iterate the filteredset
in ascending order until it finds a revision that matches the 'and user(..'
condition. If the condition is only true on late revisions, a lot of
useless iterations will be done. These iterations could be avoided if
__nonzero__ followed the order of the filteredset, which in my opinion
is a sensible thing to do here.

The problem gets even worse when instead of 'user(ikostia)' some more
expensive check is performed, like grepping the commit diff.


I tested this fix on a very large repo where tip is my commit and my very
first commit comes fairly late in the revision history. Results of timing
of the above command on that very large repo.

-with my fix:
real    0m1.795s
user    0m1.657s
sys     0m0.135s

-without my fix:
real    1m29.245s
user    1m28.223s
sys     0m0.929s

I understand that this is a very specific kind of problem that presents
itself very rarely, only on very big repositories and with expensive
checks and so on. But I don't see any disadvantages to this kind of fix
either.

# 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