view mercurial/statichttprepo.py @ 50338:81c7d04f4722 stable

match: match explicit file using a set The matcher as all the logic to do quick comparison against explicit patterns, however the pattern matcher was shadowing the code using that set and used the compiled regex pattern in all cases, which is quite slow. We restore the usage of the set based matching to boost performance. Building the regexp is still consuming a large amount of time (actually, the majority of the time), which is still silly. Maybe using re2 would help that, but this is a quest for another adventure. Another path to improve this is to have a pattern type dedicated to match the exact path to a file only (not a directory). This pattern could use the set matching only and be skipped in the regex all together. Benchmarks ========== In the following benchmark we are comparing the `hg cat` and `hg files` run time when matching against all files in the repository. They are run: - without the rust extensions - with the standard python engine (so without re2) Performance improvement in this series -------------------------------------- ###### hg files ############################################################### ### mercurial-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.230092 seconds prev-changeset: 0.230069 seconds this-changeset: 0.211425 seconds (-8.36%) ### mercurial-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.234235 seconds prev-changeset: 0.231165 seconds (-1.38%) this-changeset: 0.212300 seconds (-9.43%) ### pypy-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.613567 seconds prev-changeset: 0.616799 seconds this-changeset: 0.510852 seconds (-16.82%) ### pypy-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.801880 seconds prev-changeset: 0.616393 seconds (-23.22%) this-changeset: 0.511903 seconds (-36.23%) ### netbeans-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 21.541828 seconds prev-changeset: 21.586773 seconds this-changeset: 13.648347 seconds (-36.76%) ### netbeans-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 172.759857 seconds prev-changeset: 21.908197 seconds (-87.32%) this-changeset: 13.945110 seconds (-91.93%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 62.474221 seconds prev-changeset: 61.279490 seconds (-1.22%) this-changeset: 29.529469 seconds (-52.40%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 1364.180218 seconds prev-changeset: 62.473549 seconds (-95.40%) this-changeset: 30.625249 seconds (-97.75%) ###### hg cat ################################################################# ### mercurial-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.764407 seconds prev-changeset: 0.763883 seconds this-changeset: 0.737326 seconds (-3.68%) ### mercurial-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.768924 seconds prev-changeset: 0.765848 seconds this-changeset: 0.174d0b seconds (-4.44%) ### pypy-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 2.065220 seconds prev-changeset: 2.070498 seconds this-changeset: 1.939482 seconds (-6.08%) ### pypy-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 2.276388 seconds prev-changeset: 2.069197 seconds (-9.15%) this-changeset: 1.931746 seconds (-15.19%) ### netbeans-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 40.967983 seconds prev-changeset: 41.392423 seconds this-changeset: 32.181681 seconds (-22.20%) ### netbeans-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 216.388709 seconds prev-changeset: 41.648689 seconds (-80.88%) this-changeset: 32.580817 seconds (-85.04%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 105.228510 seconds prev-changeset: 103.315670 seconds (-1.23%) this-changeset: 69.416118 seconds (-33.64%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 1448.722784 seconds prev-changeset: 104.369358 seconds (-92.80%) this-changeset: 70.554789 seconds (-95.13%) Different way to list the same data with this revision ------------------------------------------------------ ###### hg files ############################################################### ### mercurial-2018-08-01-zstd-sparse-revlog root: 0.119182 seconds glob: 0.120697 seconds (+1.27%) sorted: 0.211425 seconds (+77.40%) shuffled: 0.212300 seconds (+78.13%) ### pypy-2018-08-01-zstd-sparse-revlog root: 0.121986 seconds glob: 0.124822 seconds (+2.32%) sorted: 0.510852 seconds (+318.78%) shuffled: 0.511903 seconds (+319.64%) ### netbeans-2018-08-01-zstd-sparse-revlog root: 0.173984 seconds glob: 0.227203 seconds (+30.59%) sorted: 13.648347 seconds (+7744.59%) shuffled: 13.945110 seconds (+7915.16%) ### mozilla-central-2018-08-01-zstd-sparse-revlog root: 0.366463 seconds glob: 0.491030 seconds (+33.99%) sorted: 29.529469 seconds (+7957.96%) shuffled: 30.625249 seconds (+8256.97%) ###### hg cat ################################################################# ### mercurial-2018-08-01-zstd-sparse-revlog glob: 0.647471 seconds root: 0.643120 seconds shuffled: 0.174d0b seconds (+13.92%) sorted: 0.737326 seconds (+13.88%) ### mozilla-central-2018-08-01-zstd-sparse-revlog glob: 40.596983 seconds root: 40.129136 seconds shuffled: 70.554789 seconds (+73.79%) sorted: 69.416118 seconds (+70.99%) ### netbeans-2018-08-01-zstd-sparse-revlog glob: 18.777924 seconds root: 18.613905 seconds shuffled: 32.580817 seconds (+73.51%) sorted: 32.181681 seconds (+71.38%) ### pypy-2018-08-01-zstd-sparse-revlog glob: 1.555319 seconds root: 1.536534 seconds shuffled: 1.931746 seconds (+24.20%) sorted: 1.939482 seconds (+24.70%)
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Sat, 01 Apr 2023 05:58:59 +0200
parents 2f60cd6442fd
children ebf1a07539b9
line wrap: on
line source

# statichttprepo.py - simple http repository class for mercurial
#
# This provides read-only repo access to repositories exported via static http
#
# Copyright 2005-2007 Olivia Mackall <olivia@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.


import errno

from .i18n import _
from .node import sha1nodeconstants
from . import (
    branchmap,
    changelog,
    error,
    localrepo,
    manifest,
    namespaces,
    pathutil,
    pycompat,
    requirements as requirementsmod,
    url,
    util,
    vfs as vfsmod,
)
from .utils import (
    urlutil,
)

urlerr = util.urlerr
urlreq = util.urlreq


class httprangereader:
    def __init__(self, url, opener):
        # we assume opener has HTTPRangeHandler
        self.url = url
        self.pos = 0
        self.opener = opener
        self.name = url

    def __enter__(self):
        return self

    def __exit__(self, exc_type, exc_value, traceback):
        self.close()

    def seek(self, pos):
        self.pos = pos

    def read(self, bytes=None):
        req = urlreq.request(pycompat.strurl(self.url))
        end = b''
        if bytes:
            end = self.pos + bytes - 1
        if self.pos or end:
            req.add_header('Range', 'bytes=%d-%s' % (self.pos, end))

        try:
            f = self.opener.open(req)
            data = f.read()
            code = f.code
        except urlerr.httperror as inst:
            num = inst.code == 404 and errno.ENOENT or None
            # Explicitly convert the exception to str as Py3 will try
            # convert it to local encoding and with as the HTTPResponse
            # instance doesn't support encode.
            raise IOError(num, str(inst))
        except urlerr.urlerror as inst:
            raise IOError(None, inst.reason)

        if code == 200:
            # HTTPRangeHandler does nothing if remote does not support
            # Range headers and returns the full entity. Let's slice it.
            if bytes:
                data = data[self.pos : self.pos + bytes]
            else:
                data = data[self.pos :]
        elif bytes:
            data = data[:bytes]
        self.pos += len(data)
        return data

    def readlines(self):
        return self.read().splitlines(True)

    def __iter__(self):
        return iter(self.readlines())

    def close(self):
        pass


# _RangeError and _HTTPRangeHandler were originally in byterange.py,
# which was itself extracted from urlgrabber. See the last version of
# byterange.py from history if you need more information.
class _RangeError(IOError):
    """Error raised when an unsatisfiable range is requested."""


class _HTTPRangeHandler(urlreq.basehandler):
    """Handler that enables HTTP Range headers.

    This was extremely simple. The Range header is a HTTP feature to
    begin with so all this class does is tell urllib2 that the
    "206 Partial Content" response from the HTTP server is what we
    expected.
    """

    def http_error_206(self, req, fp, code, msg, hdrs):
        # 206 Partial Content Response
        r = urlreq.addinfourl(fp, hdrs, req.get_full_url())
        r.code = code
        r.msg = msg
        return r

    def http_error_416(self, req, fp, code, msg, hdrs):
        # HTTP's Range Not Satisfiable error
        raise _RangeError(b'Requested Range Not Satisfiable')


def build_opener(ui, authinfo):
    # urllib cannot handle URLs with embedded user or passwd
    urlopener = url.opener(ui, authinfo)
    urlopener.add_handler(_HTTPRangeHandler())

    class statichttpvfs(vfsmod.abstractvfs):
        def __init__(self, base):
            self.base = base
            self.options = {}

        def __call__(self, path, mode=b'r', *args, **kw):
            if mode not in (b'r', b'rb'):
                raise IOError(b'Permission denied')
            f = b"/".join((self.base, urlreq.quote(path)))
            return httprangereader(f, urlopener)

        def join(self, path):
            if path:
                return pathutil.join(self.base, path)
            else:
                return self.base

    return statichttpvfs


class statichttppeer(localrepo.localpeer):
    def local(self):
        return None

    def canpush(self):
        return False


class statichttprepository(
    localrepo.localrepository, localrepo.revlogfilestorage
):
    supported = localrepo.localrepository._basesupported

    def __init__(self, ui, path):
        self._url = path
        self.ui = ui

        self.root = path
        u = urlutil.url(path.rstrip(b'/') + b"/.hg")
        self.path, authinfo = u.authinfo()

        vfsclass = build_opener(ui, authinfo)
        self.vfs = vfsclass(self.path)
        self.cachevfs = vfsclass(self.vfs.join(b'cache'))
        self._phasedefaults = []

        self.names = namespaces.namespaces()
        self.filtername = None
        self._extrafilterid = None
        self._wanted_sidedata = set()
        self.features = set()

        try:
            requirements = set(self.vfs.read(b'requires').splitlines())
        except FileNotFoundError:
            requirements = set()

            # check if it is a non-empty old-style repository
            try:
                fp = self.vfs(b"00changelog.i")
                fp.read(1)
                fp.close()
            except FileNotFoundError:
                # we do not care about empty old-style repositories here
                msg = _(b"'%s' does not appear to be an hg repository") % path
                raise error.RepoError(msg)
        if requirementsmod.SHARESAFE_REQUIREMENT in requirements:
            storevfs = vfsclass(self.vfs.join(b'store'))
            requirements |= set(storevfs.read(b'requires').splitlines())

        supportedrequirements = localrepo.gathersupportedrequirements(ui)
        localrepo.ensurerequirementsrecognized(
            requirements, supportedrequirements
        )
        localrepo.ensurerequirementscompatible(ui, requirements)
        self.nodeconstants = sha1nodeconstants
        self.nullid = self.nodeconstants.nullid

        # setup store
        self.store = localrepo.makestore(requirements, self.path, vfsclass)
        self.spath = self.store.path
        self.svfs = self.store.opener
        self.sjoin = self.store.join
        self._filecache = {}
        self.requirements = requirements

        rootmanifest = manifest.manifestrevlog(self.nodeconstants, self.svfs)
        self.manifestlog = manifest.manifestlog(
            self.svfs, self, rootmanifest, self.narrowmatch()
        )
        self.changelog = changelog.changelog(self.svfs)
        self._tags = None
        self.nodetagscache = None
        self._branchcaches = branchmap.BranchMapCache()
        self._revbranchcache = None
        self.encodepats = None
        self.decodepats = None
        self._transref = None
        self._dirstate = None

    def _restrictcapabilities(self, caps):
        caps = super(statichttprepository, self)._restrictcapabilities(caps)
        return caps.difference([b"pushkey"])

    def url(self):
        return self._url

    def local(self):
        return False

    def peer(self, path=None):
        return statichttppeer(self, path=path)

    def wlock(self, wait=True):
        raise error.LockUnavailable(
            0,
            _(b'lock not available'),
            b'lock',
            _(b'cannot lock static-http repository'),
        )

    def lock(self, wait=True):
        raise error.LockUnavailable(
            0,
            _(b'lock not available'),
            b'lock',
            _(b'cannot lock static-http repository'),
        )

    def _writecaches(self):
        pass  # statichttprepository are read only


def make_peer(ui, path, create, intents=None, createopts=None):
    if create:
        raise error.Abort(_(b'cannot create new static-http repository'))
    url = path.loc[7:]
    return statichttprepository(ui, url).peer(path=path)