view mercurial/wireprototypes.py @ 49658:523cacdfd324

delta-find: set the default candidate chunk size to 10 I ran performance and storage tests on repositories of various sizes and shapes for the following values of the config : 5, 10, 20, 50, 100, no-chunking The performance tests do not show any statistical impact on computation times for large pushes and pulls. For searching for an individual delta, this can provide a significant performance improvement with a minor degradation of space-quality on the result. (see data at the end of the commit). For overall store size, the change : - does not have any impact on many small repositories, - has an observable, but very negligible impact on most larger repositories. - One private repository we use for testing sees a small increase in size (1%) in the narrower version. We will try to get more numbers on a larger version of that repository to make sure nothing pathological happens. We pick "10" as the limit as "5" seems a bit more risky. There are room to improve the current code, by using more aggressive filtering and better (i.e any) sorting of the candidates. However this is already a large improvement for pathological cases, with little impact in the common situations. The initial motivation for this change is to fix performance of delta computation for a file where the previous code ended up testing 20 000 possible candidate-bases in one go, which is… slow. This affected about ½ of the file revisions leading to atrocious performance, especially during some push/pull operations. Details about individual delta finding timing: ---------------------------------------------- The vast majority of benchmark cases are unchanged but the three below. The first two do not see any impact on the final delta. The last one sees a change in delta-size that is negligible compared to the full text size. ### data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog # benchmark.name = perf-delta-find # benchmark.variants.rev = manifest-snapshot-many-tries-a (revision 756096) ∞: 5.844783 5: 4.473523 (-23.46%) 10: 4.970053 (-14.97%) 20: 5.770386 (-1.27%) 50 5.821358 100: 5.834887 MANIFESTLOG: rev = 756096: (no-limit) delta-base = 301840 search-rounds = 6 try-count = 60 delta-type = snapshot snap-depth = 7 delta-size = 179 MANIFESTLOG: rev=756096: (limit = 10) delta-base=301840 search-rounds=9 try-count=51 delta-type=snapshot snap-depth=7 delta-size=179 ### data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog # benchmark.name = perf-delta-find # benchmark.variants.rev = manifest-snapshot-many-tries-d (revision 754060) ∞: 5.017663 5: 3.655931 (-27.14%) 10: 4.095436 (-18.38%) 20: 4.828949 (-3.76%) 50 4.987574 100: 4.994889 MANIFESTLOG: rev=754060: (no limit) delta-base=301840 search-rounds=5 try-count=53 delta-type=snapshot snap-depth=7 delta-size = 179 MANIFESTLOG: rev=754060: (limite = 10) delta-base=301840 search-rounds=8 try-count=45 delta-type=snapshot snap-depth=7 delta-size = 179 ### data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog # benchmark.name = perf-delta-find # bin-env-vars.hg.flavor = rust # benchmark.variants.rev = manifest-snapshot-many-tries-e (revision 693368) ∞: 4.869282 5: 2.039732 (-58.11%) 10: 2.413537 (-50.43%) 20: 4.449639 (-8.62%) 50 4.865863 100: 4.882649 MANIFESTLOG: rev=693368: delta-base=693336 search-rounds=6 try-count=53 delta-type=snapshot snap-depth=6 full-test-size=131065 delta-size=199 MANIFESTLOG: rev=693368: delta-base=278023 search-rounds=5 try-count=21 delta-type=snapshot snap-depth=4 full-test-size=131065 delta-size=278 Raw data for store size (in bytes) for various chunk size value below: ---------------------------------------------------------------------- 440 134 384 5 pypy/.hg/store/ 440 134 384 10 pypy/.hg/store/ 440 134 384 20 pypy/.hg/store/ 440 134 384 50 pypy/.hg/store/ 440 134 384 100 pypy/.hg/store/ 440 134 384 ... pypy/.hg/store/ 666 987 471 5 netbsd-xsrc-2022-11-15/.hg/store/ 666 987 471 10 netbsd-xsrc-2022-11-15/.hg/store/ 666 987 471 20 netbsd-xsrc-2022-11-15/.hg/store/ 666 987 471 50 netbsd-xsrc-2022-11-15/.hg/store/ 666 987 471 100 netbsd-xsrc-2022-11-15/.hg/store/ 666 987 471 ... netbsd-xsrc-2022-11-15/.hg/store/ 852 844 884 5 netbsd-pkgsrc-2022-11-15/.hg/store/ 852 844 884 10 netbsd-pkgsrc-2022-11-15/.hg/store/ 852 844 884 20 netbsd-pkgsrc-2022-11-15/.hg/store/ 852 844 884 50 netbsd-pkgsrc-2022-11-15/.hg/store/ 852 844 884 100 netbsd-pkgsrc-2022-11-15/.hg/store/ 852 844 884 ... netbsd-pkgsrc-2022-11-15/.hg/store/ 1 504 227 981 5 netbeans-2018-08-01-sparse-zstd/.hg/store/ 1 504 227 871 10 netbeans-2018-08-01-sparse-zstd/.hg/store/ 1 504 227 813 20 netbeans-2018-08-01-sparse-zstd/.hg/store/ 1 504 227 813 50 netbeans-2018-08-01-sparse-zstd/.hg/store/ 1 504 227 813 100 netbeans-2018-08-01-sparse-zstd/.hg/store/ 1 504 227 813 ... netbeans-2018-08-01-sparse-zstd/.hg/store/ 3 875 801 068 5 netbsd-src-2022-11-15/.hg/store/ 3 875 696 767 10 netbsd-src-2022-11-15/.hg/store/ 3 875 696 757 20 netbsd-src-2022-11-15/.hg/store/ 3 875 696 653 50 netbsd-src-2022-11-15/.hg/store/ 3 875 696 653 100 netbsd-src-2022-11-15/.hg/store/ 3 875 696 653 ... netbsd-src-2022-11-15/.hg/store/ 4 531 441 314 5 mozilla-central/.hg/store/ 4 531 435 157 10 mozilla-central/.hg/store/ 4 531 432 045 20 mozilla-central/.hg/store/ 4 531 429 119 50 mozilla-central/.hg/store/ 4 531 429 119 100 mozilla-central/.hg/store/ 4 531 429 119 ... mozilla-central/.hg/store/ 4 875 861 390 5 mozilla-unified/.hg/store/ 4 875 855 155 10 mozilla-unified/.hg/store/ 4 875 852 027 20 mozilla-unified/.hg/store/ 4 875 848 851 50 mozilla-unified/.hg/store/ 4 875 848 851 100 mozilla-unified/.hg/store/ 4 875 848 851 ... mozilla-unified/.hg/store/ 11 498 764 601 5 mozilla-try/.hg/store/ 11 497 968 858 10 mozilla-try/.hg/store/ 11 497 958 730 20 mozilla-try/.hg/store/ 11 497 927 156 50 mozilla-try/.hg/store/ 11 497 925 963 100 mozilla-try/.hg/store/ 11 497 923 428 ... mozilla-try/.hg/store/ 10 047 914 031 5 private-repo 9 969 132 101 10 private-repo 9 944 745 015 20 private-repo 9 939 756 703 50 private-repo 9 939 833 016 100 private-repo 9 939 822 035 ... private-repo
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Wed, 23 Nov 2022 19:08:27 +0100
parents 642e31cb55f0
children 93b0de7f13ca
line wrap: on
line source

# 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 .node import (
    bin,
    hex,
)
from .i18n import _
from .pycompat import getattr
from .thirdparty import attr
from . import (
    error,
    util,
)
from .interfaces import util as interfaceutil
from .utils import compression

# Names of the SSH protocol implementations.
SSHV1 = b'ssh-v1'

NARROWCAP = b'exp-narrow-1'
ELLIPSESCAP1 = b'exp-ellipses-1'
ELLIPSESCAP = b'exp-ellipses-2'
SUPPORTED_ELLIPSESCAP = (ELLIPSESCAP1, ELLIPSESCAP)

# All available wire protocol transports.
TRANSPORTS = {
    SSHV1: {
        b'transport': b'ssh',
        b'version': 1,
    },
    b'http-v1': {
        b'transport': b'http',
        b'version': 1,
    },
}


class bytesresponse:
    """A wire protocol response consisting of raw bytes."""

    def __init__(self, data):
        self.data = data


class ooberror:
    """wireproto reply: failure of a batch of operation

    Something failed during a batch call. The error message is stored in
    `self.message`.
    """

    def __init__(self, message):
        self.message = message


class pushres:
    """wireproto reply: success with simple integer return

    The call was successful and returned an integer contained in `self.res`.
    """

    def __init__(self, res, output):
        self.res = res
        self.output = output


class pusherr:
    """wireproto reply: failure

    The call failed. The `self.res` attribute contains the error message.
    """

    def __init__(self, res, output):
        self.res = res
        self.output = output


class streamres:
    """wireproto reply: binary stream

    The call was successful and the result is a stream.

    Accepts a generator containing chunks of data to be sent to the client.

    ``prefer_uncompressed`` indicates that the data is expected to be
    uncompressable and that the stream should therefore use the ``none``
    engine.
    """

    def __init__(self, gen=None, prefer_uncompressed=False):
        self.gen = gen
        self.prefer_uncompressed = prefer_uncompressed


class streamreslegacy:
    """wireproto reply: uncompressed binary stream

    The call was successful and the result is a stream.

    Accepts a generator containing chunks of data to be sent to the client.

    Like ``streamres``, but sends an uncompressed data for "version 1" clients
    using the application/mercurial-0.1 media type.
    """

    def __init__(self, gen=None):
        self.gen = gen


# list of nodes encoding / decoding
def decodelist(l, sep=b' '):
    if l:
        return [bin(v) for v in l.split(sep)]
    return []


def encodelist(l, sep=b' '):
    try:
        return sep.join(map(hex, l))
    except TypeError:
        raise


# batched call argument encoding


def escapebatcharg(plain):
    return (
        plain.replace(b':', b':c')
        .replace(b',', b':o')
        .replace(b';', b':s')
        .replace(b'=', b':e')
    )


def unescapebatcharg(escaped):
    return (
        escaped.replace(b':e', b'=')
        .replace(b':s', b';')
        .replace(b':o', b',')
        .replace(b':c', b':')
    )


# mapping of options accepted by getbundle and their types
#
# Meant to be extended by extensions. It is the extension's responsibility to
# ensure such options are properly processed in exchange.getbundle.
#
# supported types are:
#
# :nodes: list of binary nodes, transmitted as space-separated hex nodes
# :csv:   list of values, transmitted as comma-separated values
# :scsv:  set of values, transmitted as comma-separated values
# :plain: string with no transformation needed.
GETBUNDLE_ARGUMENTS = {
    b'heads': b'nodes',
    b'bookmarks': b'boolean',
    b'common': b'nodes',
    b'obsmarkers': b'boolean',
    b'phases': b'boolean',
    b'bundlecaps': b'scsv',
    b'listkeys': b'csv',
    b'cg': b'boolean',
    b'cbattempted': b'boolean',
    b'stream': b'boolean',
    b'includepats': b'csv',
    b'excludepats': b'csv',
}


class baseprotocolhandler(interfaceutil.Interface):
    """Abstract base class for wire protocol handlers.

    A wire protocol handler serves as an interface between protocol command
    handlers and the wire protocol transport layer. Protocol handlers provide
    methods to read command arguments, redirect stdio for the duration of
    the request, handle response types, etc.
    """

    name = interfaceutil.Attribute(
        """The name of the protocol implementation.

        Used for uniquely identifying the transport type.
        """
    )

    def getargs(args):
        """return the value for arguments in <args>

        For version 1 transports, returns a list of values in the same
        order they appear in ``args``. For version 2 transports, returns
        a dict mapping argument name to value.
        """

    def getprotocaps():
        """Returns the list of protocol-level capabilities of client

        Returns a list of capabilities as declared by the client for
        the current request (or connection for stateful protocol handlers)."""

    def getpayload():
        """Provide a generator for the raw payload.

        The caller is responsible for ensuring that the full payload is
        processed.
        """

    def mayberedirectstdio():
        """Context manager to possibly redirect stdio.

        The context manager yields a file-object like object that receives
        stdout and stderr output when the context manager is active. Or it
        yields ``None`` if no I/O redirection occurs.

        The intent of this context manager is to capture stdio output
        so it may be sent in the response. Some transports support streaming
        stdio to the client in real time. For these transports, stdio output
        won't be captured.
        """

    def client():
        """Returns a string representation of this client (as bytes)."""

    def addcapabilities(repo, caps):
        """Adds advertised capabilities specific to this protocol.

        Receives the list of capabilities collected so far.

        Returns a list of capabilities. The passed in argument can be returned.
        """

    def checkperm(perm):
        """Validate that the client has permissions to perform a request.

        The argument is the permission required to proceed. If the client
        doesn't have that permission, the exception should raise or abort
        in a protocol specific manner.
        """


class commandentry:
    """Represents a declared wire protocol command."""

    def __init__(
        self,
        func,
        args=b'',
        transports=None,
        permission=b'push',
        cachekeyfn=None,
        extracapabilitiesfn=None,
    ):
        self.func = func
        self.args = args
        self.transports = transports or set()
        self.permission = permission
        self.cachekeyfn = cachekeyfn
        self.extracapabilitiesfn = extracapabilitiesfn

    def _merge(self, func, args):
        """Merge this instance with an incoming 2-tuple.

        This is called when a caller using the old 2-tuple API attempts
        to replace an instance. The incoming values are merged with
        data not captured by the 2-tuple and a new instance containing
        the union of the two objects is returned.
        """
        return commandentry(
            func,
            args=args,
            transports=set(self.transports),
            permission=self.permission,
        )

    # Old code treats instances as 2-tuples. So expose that interface.
    def __iter__(self):
        yield self.func
        yield self.args

    def __getitem__(self, i):
        if i == 0:
            return self.func
        elif i == 1:
            return self.args
        else:
            raise IndexError(b'can only access elements 0 and 1')


class commanddict(dict):
    """Container for registered wire protocol commands.

    It behaves like a dict. But __setitem__ is overwritten to allow silent
    coercion of values from 2-tuples for API compatibility.
    """

    def __setitem__(self, k, v):
        if isinstance(v, commandentry):
            pass
        # Cast 2-tuples to commandentry instances.
        elif isinstance(v, tuple):
            if len(v) != 2:
                raise ValueError(b'command tuples must have exactly 2 elements')

            # It is common for extensions to wrap wire protocol commands via
            # e.g. ``wireproto.commands[x] = (newfn, args)``. Because callers
            # doing this aren't aware of the new API that uses objects to store
            # command entries, we automatically merge old state with new.
            if k in self:
                v = self[k]._merge(v[0], v[1])
            else:
                # Use default values from @wireprotocommand.
                v = commandentry(
                    v[0],
                    args=v[1],
                    transports=set(TRANSPORTS),
                    permission=b'push',
                )
        else:
            raise ValueError(
                b'command entries must be commandentry instances '
                b'or 2-tuples'
            )

        return super(commanddict, self).__setitem__(k, v)

    def commandavailable(self, command, proto):
        """Determine if a command is available for the requested protocol."""
        assert proto.name in TRANSPORTS

        entry = self.get(command)

        if not entry:
            return False

        if proto.name not in entry.transports:
            return False

        return True


def supportedcompengines(ui, role):
    """Obtain the list of supported compression engines for a request."""
    assert role in (compression.CLIENTROLE, compression.SERVERROLE)

    compengines = compression.compengines.supportedwireengines(role)

    # Allow config to override default list and ordering.
    if role == compression.SERVERROLE:
        configengines = ui.configlist(b'server', b'compressionengines')
        config = b'server.compressionengines'
    else:
        # This is currently implemented mainly to facilitate testing. In most
        # cases, the server should be in charge of choosing a compression engine
        # because a server has the most to lose from a sub-optimal choice. (e.g.
        # CPU DoS due to an expensive engine or a network DoS due to poor
        # compression ratio).
        configengines = ui.configlist(
            b'experimental', b'clientcompressionengines'
        )
        config = b'experimental.clientcompressionengines'

    # No explicit config. Filter out the ones that aren't supposed to be
    # advertised and return default ordering.
    if not configengines:
        attr = (
            b'serverpriority' if role == util.SERVERROLE else b'clientpriority'
        )
        return [
            e for e in compengines if getattr(e.wireprotosupport(), attr) > 0
        ]

    # If compression engines are listed in the config, assume there is a good
    # reason for it (like server operators wanting to achieve specific
    # performance characteristics). So fail fast if the config references
    # unusable compression engines.
    validnames = {e.name() for e in compengines}
    invalidnames = {e for e in configengines if e not in validnames}
    if invalidnames:
        raise error.Abort(
            _(b'invalid compression engine defined in %s: %s')
            % (config, b', '.join(sorted(invalidnames)))
        )

    compengines = [e for e in compengines if e.name() in configengines]
    compengines = sorted(
        compengines, key=lambda e: configengines.index(e.name())
    )

    if not compengines:
        raise error.Abort(
            _(
                b'%s config option does not specify any known '
                b'compression engines'
            )
            % config,
            hint=_(b'usable compression engines: %s')
            % b', '.sorted(validnames),  # pytype: disable=attribute-error
        )

    return compengines


@attr.s
class encodedresponse:
    """Represents response data that is already content encoded.

    Wire protocol version 2 only.

    Commands typically emit Python objects that are encoded and sent over the
    wire. If commands emit an object of this type, the encoding step is bypassed
    and the content from this object is used instead.
    """

    data = attr.ib()


@attr.s
class alternatelocationresponse:
    """Represents a response available at an alternate location.

    Instances are sent in place of actual response objects when the server
    is sending a "content redirect" response.

    Only compatible with wire protocol version 2.
    """

    url = attr.ib()
    mediatype = attr.ib()
    size = attr.ib(default=None)
    fullhashes = attr.ib(default=None)
    fullhashseed = attr.ib(default=None)
    serverdercerts = attr.ib(default=None)
    servercadercerts = attr.ib(default=None)


@attr.s
class indefinitebytestringresponse:
    """Represents an object to be encoded to an indefinite length bytestring.

    Instances are initialized from an iterable of chunks, with each chunk being
    a bytes instance.
    """

    chunks = attr.ib()