view mercurial/wireprototypes.py @ 37631:2f626233859b

wireproto: implement batching on peer executor interface

This is a bit more complicated than non-batch requests because we
need to buffer sends until the last request arrives *and* we need
to support resolving futures as data arrives from the remote.

In a classical concurrent.futures executor model, the future
"starts" as soon as it is submitted. However, we have nothing to
start until the last command is submitted.

If we did nothing, calling result() would deadlock, since the future
hasn't "started." So in the case where we queue the command, we return
a special future type whose result() will trigger sendcommands().
This eliminates the deadlock potential. It also serves as a check
against callers who may be calling result() prematurely, as it will
prevent any subsequent callcommands() from working. This behavior
is slightly annoying and a bit restrictive. But it's the world
that half duplex connections forces on us.

In order to support streaming responses, we were previously using
a generator. But with a futures-based API, we're using futures
and not generators. So in order to get streaming, we need a
background thread to read data from the server.

The approach taken in this patch is to leverage the ThreadPoolExecutor
from concurrent.futures for managing a background thread. We create
an executor and future that resolves when all response data is
processed (or an error occurs). When exiting the context manager,
we wait on that background reading before returning.

I was hoping we could manually spin up a threading.Thread and this
would be simple. But I ran into a few deadlocks when implementing.
After looking at the source code to concurrent.futures, I figured
it would just be easier to use a ThreadPoolExecutor than implement
all the code needed to manually manage a thread.

To prove this works, a use of the batch API in discovery has been
updated.

Differential Revision: https://phab.mercurial-scm.org/D3269

# Copyright 2018 Gregory Szorc <[e-mail]>
#
# 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 .thirdparty.zope import (
    interface as zi,
)

# 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-v2-0001'
HTTPV2 = 'exp-http-v2-0001'

# 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,
    },
    HTTPV2: {
        '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

class cborresponse(object):
    """Encode the response value as CBOR."""
    def __init__(self, v):
        self.value = v

# 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',
}

class baseprotocolhandler(zi.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 = zi.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.
        """