mercurial/peer.py

revset: speed up '_matchfiles'

File matching is done by applying the matcher to all elements in the 'file'
field of all changesets in the repository. This requires to read/parse all
changesets in the repository and do a lot of matching. However about 1/3 of the
time of the function is used to create 'changectx' object and retrieve their
'file' field.

This is far too much overhead so we are skipping the changectx layer and
directly access the data from the changelog. This provide use significant speed
up:

repository: mozilla central 252524 revisions
command: hg perfrevset '_matchfiles("p:browser")'
Before: 15.899687s
After:  10.011705s

Slowdown is even more significant if you have a lot of namespace that slowdown
lookup.

The time is now spent with this approximate repartition:

  Matcher: 20%
    regexp matching: 10%
  changelog.read: 80%
    reading revision: 60%
      checking hash: 15%
      decompression: 15%
      reading chunk: 30%
    changelog parsing: 20%
      decoding to local: 10%

The next easy win is probably to have more of the changelog stack implemented
using the CPython api.

# 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):
        pass

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))

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 = batchable.next()
        if not encresref:
            return encargsorres # a local result in this case
        self = args[0]
        encresref.set(self._submitone(f.func_name, encargsorres))
        return batchable.next()
    setattr(plain, 'batchable', f)
    return plain

class peerrepository(object):

    def batch(self):
        return localbatch(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