view mercurial/wireprototypes.py @ 42044:bb271ec2fbfb

compression: introduce a `storage.revlog.zstd.level` configuration This option control the zstd compression level used when compressing revlog chunk. The usage of zstd for revlog compression has not graduated from experimental yet, but we intend to fix that soon. The option name for the compression level is more straight forward to pick, so this changesets comes first. Having a dedicated option for each compression engine is useful because they don't support the same range of values. I ran the same measurement as for the zlib compression level (in the parent changesets). The variation in repository size is stay mostly in the same (small) range. The "read/write" performance see smallish variation, but are overall much better than zlib. Write performance show the same tend of having better write performance for when reaching high-end compression. Again, we don't intend to change the default zstd compression level (currently: 3) in this series. However this is worth investigating in the future. The Performance comparison of zlib vs zstd is quite impressive. The repository size stay in the same range, but the performance are much better in all situations. Comparison summary ================== We are looking at: - performance range for zlib - performance range for zstd - comparison of default zstd (level-3) to default zlib (level 6) - comparison of the slowest zstd time to the fastest zlib time Read performance: ----------------- | zlib | zstd | cmp | f2s mercurial | 0.170159 - 0.189219 | 0.144127 - 0.149624 | 80% | 88% pypy | 2.679217 - 2.768691 | 1.532317 - 1.705044 | 60% | 63% netbeans | 122.477027 - 141.620281 | 72.996346 - 89.731560 | 58% | 73% mozilla | 147.867662 - 170.572118 | 91.700995 - 105.853099 | 56% | 71% Write performance: ------------------ | zlib | zstd | cmp | f2s mercurial | 53.250304 - 56.2936129 | 40.877025 - 45.677286 | 75% | 86% pypy | 460.721984 - 476.589918 | 270.545409 - 301.002219 | 63% | 65% netbeans | 520.560316 - 715.930400 | 370.356311 - 428.329652 | 55% | 82% mozilla | 739.803002 - 987.056093 | 505.152906 - 591.930683 | 57% | 80% Raw data -------- repo alg lvl .hg/store size 00manifest.d read write mercurial zlib 1 49,402,813 5,963,475 0.170159 53.250304 mercurial zlib 6 47,197,397 5,875,730 0.182820 56.264320 mercurial zlib 9 47,121,596 5,849,781 0.189219 56.293612 mercurial zstd 1 49,737,084 5,966,355 0.144127 40.877025 mercurial zstd 3 48,961,867 5,895,208 0.146376 42.268142 mercurial zstd 5 48,200,592 5,938,676 0.149624 43.162875 mercurial zstd 10 47,833,520 5,913,353 0.145185 44.012489 mercurial zstd 15 47,314,604 5,728,679 0.147686 45.677286 mercurial zstd 20 47,330,502 5,830,539 0.145789 45.025407 mercurial zstd 22 47,330,076 5,830,539 0.143996 44.690460 pypy zlib 1 370,830,572 28,462,425 2.679217 460.721984 pypy zlib 6 340,112,317 27,648,747 2.768691 467.537158 pypy zlib 9 338,360,736 27,639,003 2.763495 476.589918 pypy zstd 1 362,377,479 27,916,214 1.532317 270.545409 pypy zstd 3 354,137,693 27,905,988 1.686718 294.951509 pypy zstd 5 342,640,043 27,655,774 1.705044 301.002219 pypy zstd 10 334,224,327 27,164,493 1.567287 285.186239 pypy zstd 15 329,000,363 26,645,965 1.637729 299.561332 pypy zstd 20 324,534,039 26,199,547 1.526813 302.149827 pypy zstd 22 324,530,595 26,198,932 1.525718 307.821218 netbeans zlib 1 1,281,847,810 165,495,457 122.477027 520.560316 netbeans zlib 6 1,205,284,353 159,161,207 139.876147 715.930400 netbeans zlib 9 1,197,135,671 155,034,586 141.620281 678.297064 netbeans zstd 1 1,259,581,737 160,840,613 72.996346 370.356311 netbeans zstd 3 1,232,978,122 157,691,551 81.622317 396.733087 netbeans zstd 5 1,208,034,075 160,246,880 83.080549 364.342626 netbeans zstd 10 1,188,624,176 156,083,417 79.323935 403.594602 netbeans zstd 15 1,176,973,589 153,859,477 89.731560 428.329652 netbeans zstd 20 1,162,958,258 151,147,535 82.842667 392.335349 netbeans zstd 22 1,162,707,029 151,150,220 82.565695 402.840655 mozilla zlib 1 2,775,497,186 298,527,987 147.867662 751.263721 mozilla zlib 6 2,596,856,420 286,597,671 170.572118 987.056093 mozilla zlib 9 2,587,542,494 287,018,264 163.622338 739.803002 mozilla zstd 1 2,723,159,348 286,617,532 91.700995 570.042751 mozilla zstd 3 2,665,055,001 286,152,013 95.240155 561.412805 mozilla zstd 5 2,607,819,817 288,060,030 101.978048 505.152906 mozilla zstd 10 2,558,761,085 283,967,648 104.113481 497.771202 mozilla zstd 15 2,526,216,060 275,581,300 105.853099 591.930683 mozilla zstd 20 2,485,114,806 266,478,859 95.268795 576.515389 mozilla zstd 22 2,484,869,080 266,456,505 94.429282 572.785537
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Wed, 27 Mar 2019 18:35:59 +0100
parents 3e47d1ec9da5
children c767e655ffda
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 __future__ import absolute_import

from .node import (
    bin,
    hex,
)
from .i18n import _
from .thirdparty import (
    attr,
)
from . import (
    error,
    util,
)
from .utils import (
    compression,
    interfaceutil,
)

# Names of the SSH protocol implementations.
SSHV1 = 'ssh-v1'
# These are advertised over the wire. Increment the counters at the end
# to reflect BC breakages.
SSHV2 = 'exp-ssh-v2-0003'
HTTP_WIREPROTO_V2 = 'exp-http-v2-0003'

NARROWCAP = 'exp-narrow-1'
ELLIPSESCAP = 'exp-ellipses-1'

# All available wire protocol transports.
TRANSPORTS = {
    SSHV1: {
        'transport': 'ssh',
        'version': 1,
    },
    SSHV2: {
        'transport': 'ssh',
        # TODO mark as version 2 once all commands are implemented.
        'version': 1,
    },
    'http-v1': {
        'transport': 'http',
        'version': 1,
    },
    HTTP_WIREPROTO_V2: {
        'transport': 'http',
        'version': 2,
    }
}

class bytesresponse(object):
    """A wire protocol response consisting of raw bytes."""
    def __init__(self, data):
        self.data = data

class ooberror(object):
    """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(object):
    """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(object):
    """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(object):
    """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(object):
    """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=' '):
    if l:
        return [bin(v) for v in  l.split(sep)]
    return []

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

# batched call argument encoding

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

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

# mapping of options accepted by getbundle and their types
#
# Meant to be extended by extensions. It is extensions responsibility to ensure
# such options are properly processed in exchange.getbundle.
#
# supported types are:
#
# :nodes: list of binary nodes
# :csv:   list of comma-separated values
# :scsv:  list of comma-separated values return as set
# :plain: string with no transformation needed.
GETBUNDLE_ARGUMENTS = {
    'heads':  'nodes',
    'bookmarks': 'boolean',
    'common': 'nodes',
    'obsmarkers': 'boolean',
    'phases': 'boolean',
    'bundlecaps': 'scsv',
    'listkeys': 'csv',
    'cg': 'boolean',
    'cbattempted': 'boolean',
    'stream': 'boolean',
    'includepats': 'csv',
    'excludepats': '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(object):
    """Represents a declared wire protocol command."""
    def __init__(self, func, args='', transports=None,
                 permission='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('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('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='push')
        else:
            raise ValueError('command entries must be commandentry instances '
                             '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('server', 'compressionengines')
        config = '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('experimental',
                                      'clientcompressionengines')
        config = 'experimental.clientcompressionengines'

    # No explicit config. Filter out the ones that aren't supposed to be
    # advertised and return default ordering.
    if not configengines:
        attr = 'serverpriority' if role == util.SERVERROLE else '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 = set(e.name() for e in compengines)
    invalidnames = set(e for e in configengines if e not in validnames)
    if invalidnames:
        raise error.Abort(_('invalid compression engine defined in %s: %s') %
                          (config, ', '.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(_('%s config option does not specify any known '
                            'compression engines') % config,
                          hint=_('usable compression engines: %s') %
                          ', '.sorted(validnames))

    return compengines

@attr.s
class encodedresponse(object):
    """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(object):
    """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(object):
    """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()