view tests/test-wireproto.py @ 34824:e2ad93bcc084

revlog: introduce an experimental flag to slice chunks reads when too sparse

Delta chains can become quite sparse if there is a lot of unrelated data between
relevant pieces. Right now, revlog always reads all the necessary data for the
delta chain in one single read. This can lead to a lot of unrelated data to be
read (see issue5482 for more details).
One can use the `experimental.maxdeltachainspan` option with a large value
(or -1) to easily produce a very sparse delta chain.

This change introduces the ability to slice the chunks retrieval into  multiple
reads, skipping large sections of unrelated data. Preliminary testing shows
interesting results. For example the peak memory consumption to read a manifest
on a large repository is reduced from 600MB to 250MB (200MB without
maxdeltachainspan). However, the slicing itself and the multiple reads can have
an negative impact on performance. This is why the new feature is hidden behind
an experimental flag.

Future changesets will add various parameters to control the slicing heuristics.
We hope to experiment a wide variety of repositories during 4.4 and hopefully
turn the feature on by default in 4.5.
As a first try, the algorithm itself is prone to deep changes. However, we wish
to define APIs and have a baseline to work on.

from __future__ import absolute_import, print_function

from mercurial import (
    util,
    wireproto,
)
stringio = util.stringio

class proto(object):
    def __init__(self, args):
        self.args = args
    def getargs(self, spec):
        args = self.args
        args.setdefault('*', {})
        names = spec.split()
        return [args[n] for n in names]

class clientpeer(wireproto.wirepeer):
    def __init__(self, serverrepo):
        self.serverrepo = serverrepo

    @property
    def ui(self):
        return self.serverrepo.ui

    def url(self):
        return 'test'

    def local(self):
        return None

    def peer(self):
        return self

    def canpush(self):
        return True

    def close(self):
        pass

    def capabilities(self):
        return ['batch']

    def _call(self, cmd, **args):
        return wireproto.dispatch(self.serverrepo, proto(args), cmd)

    def _callstream(self, cmd, **args):
        return stringio(self._call(cmd, **args))

    @wireproto.batchable
    def greet(self, name):
        f = wireproto.future()
        yield {'name': mangle(name)}, f
        yield unmangle(f.value)

class serverrepo(object):
    def greet(self, name):
        return "Hello, " + name

    def filtered(self, name):
        return self

def mangle(s):
    return ''.join(chr(ord(c) + 1) for c in s)
def unmangle(s):
    return ''.join(chr(ord(c) - 1) for c in s)

def greet(repo, proto, name):
    return mangle(repo.greet(unmangle(name)))

wireproto.commands['greet'] = (greet, 'name',)

srv = serverrepo()
clt = clientpeer(srv)

print(clt.greet("Foobar"))
b = clt.iterbatch()
map(b.greet, ('Fo, =;:<o', 'Bar'))
b.submit()
print([r for r in b.results()])