tests/sshprotoext.py

match: convert O(n) to O(log n) in exactmatcher.visitchildrenset

When using narrow, during rebase this is called (at least) once per directory in
the set of files in the commit being rebased. Every time it's called, we did the
set arithmetic (now extracted and cached), which was probably pretty cheap but
not necessary to repeat each time, looped over every item in the matcher and
kept things that started with the directory we were querying.

With very large narrowspecs, and a commit that touched a file in a large number
of directories, this was slow. In a pathological repo, the rebase of a single
commit (that touched over 17k files, I believe in approximately as many
directories) with a narrowspec that had >32k entries took 8,246s of profiled
time, with 5,007s of that spent in visitchildrenset (transitively). With this
change, the time spent in visitchildrenset is less than 34s (which is where my
profile cut off). Most of the remaining time was network access due to our
custom remotefilelog-based setup not properly prefetching.

Differential Revision: https://phab.mercurial-scm.org/D10294

# sshprotoext.py - Extension to test behavior of SSH protocol
#
# 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.

# This extension replaces the SSH server started via `hg serve --stdio`.
# The server behaves differently depending on environment variables.

from __future__ import absolute_import

from mercurial import (
    error,
    extensions,
    registrar,
    sshpeer,
    wireprotoserver,
    wireprotov1server,
)

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

configitem(b'sshpeer', b'mode', default=None)
configitem(b'sshpeer', b'handshake-mode', default=None)


class bannerserver(wireprotoserver.sshserver):
    """Server that sends a banner to stdout."""

    def serve_forever(self):
        for i in range(10):
            self._fout.write(b'banner: line %d\n' % i)

        super(bannerserver, self).serve_forever()


class prehelloserver(wireprotoserver.sshserver):
    """Tests behavior when connecting to <0.9.1 servers.

    The ``hello`` wire protocol command was introduced in Mercurial
    0.9.1. Modern clients send the ``hello`` command when connecting
    to SSH servers. This mock server tests behavior of the handshake
    when ``hello`` is not supported.
    """

    def serve_forever(self):
        l = self._fin.readline()
        assert l == b'hello\n'
        # Respond to unknown commands with an empty reply.
        wireprotoserver._sshv1respondbytes(self._fout, b'')
        l = self._fin.readline()
        assert l == b'between\n'
        proto = wireprotoserver.sshv1protocolhandler(
            self._ui, self._fin, self._fout
        )
        rsp = wireprotov1server.dispatch(self._repo, proto, b'between')
        wireprotoserver._sshv1respondbytes(self._fout, rsp.data)

        super(prehelloserver, self).serve_forever()


def performhandshake(orig, ui, stdin, stdout, stderr):
    """Wrapped version of sshpeer._performhandshake to send extra commands."""
    mode = ui.config(b'sshpeer', b'handshake-mode')
    if mode == b'pre-no-args':
        ui.debug(b'sending no-args command\n')
        stdin.write(b'no-args\n')
        stdin.flush()
        return orig(ui, stdin, stdout, stderr)
    elif mode == b'pre-multiple-no-args':
        ui.debug(b'sending unknown1 command\n')
        stdin.write(b'unknown1\n')
        ui.debug(b'sending unknown2 command\n')
        stdin.write(b'unknown2\n')
        ui.debug(b'sending unknown3 command\n')
        stdin.write(b'unknown3\n')
        stdin.flush()
        return orig(ui, stdin, stdout, stderr)
    else:
        raise error.ProgrammingError(b'unknown HANDSHAKECOMMANDMODE: %s' % mode)


def extsetup(ui):
    # It's easier for tests to define the server behavior via environment
    # variables than config options. This is because `hg serve --stdio`
    # has to be invoked with a certain form for security reasons and
    # `dummyssh` can't just add `--config` flags to the command line.
    servermode = ui.environ.get(b'SSHSERVERMODE')

    if servermode == b'banner':
        wireprotoserver.sshserver = bannerserver
    elif servermode == b'no-hello':
        wireprotoserver.sshserver = prehelloserver
    elif servermode:
        raise error.ProgrammingError(b'unknown server mode: %s' % servermode)

    peermode = ui.config(b'sshpeer', b'mode')

    if peermode == b'extra-handshake-commands':
        extensions.wrapfunction(sshpeer, '_performhandshake', performhandshake)
    elif peermode:
        raise error.ProgrammingError(b'unknown peer mode: %s' % peermode)