view tests/wireprotosimplecache.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 9d2b2df2c2ba
line wrap: on
line source

# wireprotosimplecache.py - Extension providing in-memory wire protocol cache
#
# Copyright 2018 Gregory Szorc <gregory.szorc@gmail.com>
#
# 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 mercurial import (
    extensions,
    registrar,
    util,
    wireprotoserver,
    wireprototypes,
    wireprotov2server,
)
from mercurial.interfaces import (
    repository,
    util as interfaceutil,
)
from mercurial.utils import stringutil

CACHE = None

configtable = {}
configitem = registrar.configitem(configtable)

configitem(b'simplecache', b'cacheapi', default=False)
configitem(b'simplecache', b'cacheobjects', default=False)
configitem(b'simplecache', b'redirectsfile', default=None)

# API handler that makes cached keys available.
def handlecacherequest(rctx, req, res, checkperm, urlparts):
    if rctx.repo.ui.configbool(b'simplecache', b'cacheobjects'):
        res.status = b'500 Internal Server Error'
        res.setbodybytes(b'cacheobjects not supported for api server')
        return

    if not urlparts:
        res.status = b'200 OK'
        res.headers[b'Content-Type'] = b'text/plain'
        res.setbodybytes(b'simple cache server')
        return

    key = b'/'.join(urlparts)

    if key not in CACHE:
        res.status = b'404 Not Found'
        res.headers[b'Content-Type'] = b'text/plain'
        res.setbodybytes(b'key not found in cache')
        return

    res.status = b'200 OK'
    res.headers[b'Content-Type'] = b'application/mercurial-cbor'
    res.setbodybytes(CACHE[key])


def cachedescriptor(req, repo):
    return {}


wireprotoserver.API_HANDLERS[b'simplecache'] = {
    b'config': (b'simplecache', b'cacheapi'),
    b'handler': handlecacherequest,
    b'apidescriptor': cachedescriptor,
}


@interfaceutil.implementer(repository.iwireprotocolcommandcacher)
class memorycacher(object):
    def __init__(
        self, ui, command, encodefn, redirecttargets, redirecthashes, req
    ):
        self.ui = ui
        self.encodefn = encodefn
        self.redirecttargets = redirecttargets
        self.redirecthashes = redirecthashes
        self.req = req
        self.key = None
        self.cacheobjects = ui.configbool(b'simplecache', b'cacheobjects')
        self.cacheapi = ui.configbool(b'simplecache', b'cacheapi')
        self.buffered = []

        ui.log(b'simplecache', b'cacher constructed for %s\n', command)

    def __enter__(self):
        return self

    def __exit__(self, exctype, excvalue, exctb):
        if exctype:
            self.ui.log(b'simplecache', b'cacher exiting due to error\n')

    def adjustcachekeystate(self, state):
        # Needed in order to make tests deterministic. Don't copy this
        # pattern for production caches!
        del state[b'repo']

    def setcachekey(self, key):
        self.key = key
        return True

    def lookup(self):
        if self.key not in CACHE:
            self.ui.log(b'simplecache', b'cache miss for %s\n', self.key)
            return None

        entry = CACHE[self.key]
        self.ui.log(b'simplecache', b'cache hit for %s\n', self.key)

        redirectable = True

        if not self.cacheapi:
            redirectable = False
        elif not self.redirecttargets:
            redirectable = False
        else:
            clienttargets = set(self.redirecttargets)
            ourtargets = set(t[b'name'] for t in loadredirecttargets(self.ui))

            # We only ever redirect to a single target (for now). So we don't
            # need to store which target matched.
            if not clienttargets & ourtargets:
                redirectable = False

        if redirectable:
            paths = self.req.dispatchparts[:-3]
            paths.append(b'simplecache')
            paths.append(self.key)

            url = b'%s/%s' % (self.req.baseurl, b'/'.join(paths))

            # url = b'http://example.com/%s' % self.key
            self.ui.log(
                b'simplecache',
                b'sending content redirect for %s to ' b'%s\n',
                self.key,
                url,
            )
            response = wireprototypes.alternatelocationresponse(
                url=url, mediatype=b'application/mercurial-cbor'
            )

            return {b'objs': [response]}

        if self.cacheobjects:
            return {
                b'objs': entry,
            }
        else:
            return {
                b'objs': [wireprototypes.encodedresponse(entry)],
            }

    def onobject(self, obj):
        if self.cacheobjects:
            self.buffered.append(obj)
        else:
            self.buffered.extend(self.encodefn(obj))

        yield obj

    def onfinished(self):
        self.ui.log(b'simplecache', b'storing cache entry for %s\n', self.key)
        if self.cacheobjects:
            CACHE[self.key] = self.buffered
        else:
            CACHE[self.key] = b''.join(self.buffered)

        return []


def makeresponsecacher(
    orig,
    repo,
    proto,
    command,
    args,
    objencoderfn,
    redirecttargets,
    redirecthashes,
):
    return memorycacher(
        repo.ui,
        command,
        objencoderfn,
        redirecttargets,
        redirecthashes,
        proto._req,
    )


def loadredirecttargets(ui):
    path = ui.config(b'simplecache', b'redirectsfile')
    if not path:
        return []

    with open(path, 'rb') as fh:
        s = fh.read()

    return stringutil.evalpythonliteral(s)


def getadvertisedredirecttargets(orig, repo, proto):
    return loadredirecttargets(repo.ui)


def extsetup(ui):
    global CACHE

    CACHE = util.lrucachedict(10000)

    extensions.wrapfunction(
        wireprotov2server, b'makeresponsecacher', makeresponsecacher
    )
    extensions.wrapfunction(
        wireprotov2server,
        b'getadvertisedredirecttargets',
        getadvertisedredirecttargets,
    )