view tests/test-batching.py @ 44363:f7459da77f23

nodemap: introduce an option to use mmap to read the nodemap mapping The performance and memory benefit is much greater if we don't have to copy all the data in memory for each information. So we introduce an option (on by default) to read the data using mmap. This changeset is the last one definition the API for index support nodemap data. (they have to be able to use the mmaping). Below are some benchmark comparing the best we currently have in 5.3 with the final step of this series (using the persistent nodemap implementation in Rust). The benchmark run `hg perfindex` with various revset and the following variants: Before: * do not use the persistent nodemap * use the CPython implementation of the index for nodemap * use mmapping of the changelog index After: * use the MixedIndex Rust code, with the NodeTree object for nodemap access (still in review) * use the persistent nodemap data from disk * access the persistent nodemap data through mmap * use mmapping of the changelog index The persistent nodemap greatly speed up most operation on very large repositories. Some of the previously very fast lookup end up a bit slower because the persistent nodemap has to be setup. However the absolute slowdown is very small and won't matters in the big picture. Here are some numbers (in seconds) for the reference copy of mozilla-try: Revset Before After abs-change speedup -10000: 0.004622 0.005532 0.000910 × 0.83 -10: 0.000050 0.000132 0.000082 × 0.37 tip 0.000052 0.000085 0.000033 × 0.61 0 + (-10000:) 0.028222 0.005337 -0.022885 × 5.29 0 0.023521 0.000084 -0.023437 × 280.01 (-10000:) + 0 0.235539 0.005308 -0.230231 × 44.37 (-10:) + :9 0.232883 0.000180 -0.232703 ×1293.79 (-10000:) + (:99) 0.238735 0.005358 -0.233377 × 44.55 :99 + (-10000:) 0.317942 0.005593 -0.312349 × 56.84 :9 + (-10:) 0.313372 0.000179 -0.313193 ×1750.68 :9 0.316450 0.000143 -0.316307 ×2212.93 On smaller repositories, the cost of nodemap related operation is not as big, so the win is much more modest. Yet it helps shaving a handful of millisecond here and there. Here are some numbers (in seconds) for the reference copy of mercurial: Revset Before After abs-change speedup -10: 0.000065 0.000097 0.000032 × 0.67 tip 0.000063 0.000078 0.000015 × 0.80 0 0.000561 0.000079 -0.000482 × 7.10 -10000: 0.004609 0.003648 -0.000961 × 1.26 0 + (-10000:) 0.005023 0.003715 -0.001307 × 1.35 (-10:) + :9 0.002187 0.000108 -0.002079 ×20.25 (-10000:) + 0 0.006252 0.003716 -0.002536 × 1.68 (-10000:) + (:99) 0.006367 0.003707 -0.002660 × 1.71 :9 + (-10:) 0.003846 0.000110 -0.003736 ×34.96 :9 0.003854 0.000099 -0.003755 ×38.92 :99 + (-10000:) 0.007644 0.003778 -0.003866 × 2.02 Differential Revision: https://phab.mercurial-scm.org/D7894
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Tue, 11 Feb 2020 11:18:52 +0100
parents 2372284d9457
children 89a2afe31e82
line wrap: on
line source

# test-batching.py - tests for transparent command batching
#
# Copyright 2011 Peter Arrenbrecht <peter@arrenbrecht.ch>
#
# 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, print_function

import contextlib

from mercurial import (
    localrepo,
    pycompat,
    wireprotov1peer,
)


def bprint(*bs):
    print(*[pycompat.sysstr(b) for b in bs])


# equivalent of repo.repository
class thing(object):
    def hello(self):
        return b"Ready."


# equivalent of localrepo.localrepository
class localthing(thing):
    def foo(self, one, two=None):
        if one:
            return b"%s and %s" % (one, two,)
        return b"Nope"

    def bar(self, b, a):
        return b"%s und %s" % (b, a,)

    def greet(self, name=None):
        return b"Hello, %s" % name

    @contextlib.contextmanager
    def commandexecutor(self):
        e = localrepo.localcommandexecutor(self)
        try:
            yield e
        finally:
            e.close()


# usage of "thing" interface
def use(it):

    # Direct call to base method shared between client and server.
    bprint(it.hello())

    # Direct calls to proxied methods. They cause individual roundtrips.
    bprint(it.foo(b"Un", two=b"Deux"))
    bprint(it.bar(b"Eins", b"Zwei"))

    # Batched call to a couple of proxied methods.

    with it.commandexecutor() as e:
        ffoo = e.callcommand(b'foo', {b'one': b'One', b'two': b'Two'})
        fbar = e.callcommand(b'bar', {b'b': b'Eins', b'a': b'Zwei'})
        fbar2 = e.callcommand(b'bar', {b'b': b'Uno', b'a': b'Due'})

    bprint(ffoo.result())
    bprint(fbar.result())
    bprint(fbar2.result())


# local usage
mylocal = localthing()
print()
bprint(b"== Local")
use(mylocal)

# demo remoting; mimicks what wireproto and HTTP/SSH do

# shared


def escapearg(plain):
    return (
        plain.replace(b':', b'::')
        .replace(b',', b':,')
        .replace(b';', b':;')
        .replace(b'=', b':=')
    )


def unescapearg(escaped):
    return (
        escaped.replace(b':=', b'=')
        .replace(b':;', b';')
        .replace(b':,', b',')
        .replace(b'::', b':')
    )


# server side

# equivalent of wireproto's global functions
class server(object):
    def __init__(self, local):
        self.local = local

    def _call(self, name, args):
        args = dict(arg.split(b'=', 1) for arg in args)
        return getattr(self, name)(**args)

    def perform(self, req):
        bprint(b"REQ:", req)
        name, args = req.split(b'?', 1)
        args = args.split(b'&')
        vals = dict(arg.split(b'=', 1) for arg in args)
        res = getattr(self, pycompat.sysstr(name))(**pycompat.strkwargs(vals))
        bprint(b"  ->", res)
        return res

    def batch(self, cmds):
        res = []
        for pair in cmds.split(b';'):
            name, args = pair.split(b':', 1)
            vals = {}
            for a in args.split(b','):
                if a:
                    n, v = a.split(b'=')
                    vals[n] = unescapearg(v)
            res.append(
                escapearg(
                    getattr(self, pycompat.sysstr(name))(
                        **pycompat.strkwargs(vals)
                    )
                )
            )
        return b';'.join(res)

    def foo(self, one, two):
        return mangle(self.local.foo(unmangle(one), unmangle(two)))

    def bar(self, b, a):
        return mangle(self.local.bar(unmangle(b), unmangle(a)))

    def greet(self, name):
        return mangle(self.local.greet(unmangle(name)))


myserver = server(mylocal)

# local side

# equivalent of wireproto.encode/decodelist, that is, type-specific marshalling
# here we just transform the strings a bit to check we're properly en-/decoding
def mangle(s):
    return b''.join(pycompat.bytechr(ord(c) + 1) for c in pycompat.bytestr(s))


def unmangle(s):
    return b''.join(pycompat.bytechr(ord(c) - 1) for c in pycompat.bytestr(s))


# equivalent of wireproto.wirerepository and something like http's wire format
class remotething(thing):
    def __init__(self, server):
        self.server = server

    def _submitone(self, name, args):
        req = name + b'?' + b'&'.join([b'%s=%s' % (n, v) for n, v in args])
        return self.server.perform(req)

    def _submitbatch(self, cmds):
        req = []
        for name, args in cmds:
            args = b','.join(n + b'=' + escapearg(v) for n, v in args)
            req.append(name + b':' + args)
        req = b';'.join(req)
        res = self._submitone(b'batch', [(b'cmds', req,)])
        for r in res.split(b';'):
            yield r

    @contextlib.contextmanager
    def commandexecutor(self):
        e = wireprotov1peer.peerexecutor(self)
        try:
            yield e
        finally:
            e.close()

    @wireprotov1peer.batchable
    def foo(self, one, two=None):
        encargs = [(b'one', mangle(one),), (b'two', mangle(two),)]
        encresref = wireprotov1peer.future()
        yield encargs, encresref
        yield unmangle(encresref.value)

    @wireprotov1peer.batchable
    def bar(self, b, a):
        encresref = wireprotov1peer.future()
        yield [(b'b', mangle(b),), (b'a', mangle(a),)], encresref
        yield unmangle(encresref.value)

    # greet is coded directly. It therefore does not support batching. If it
    # does appear in a batch, the batch is split around greet, and the call to
    # greet is done in its own roundtrip.
    def greet(self, name=None):
        return unmangle(self._submitone(b'greet', [(b'name', mangle(name),)]))


# demo remote usage

myproxy = remotething(myserver)
print()
bprint(b"== Remote")
use(myproxy)