view mercurial/httpconnection.py @ 51592:24844407fa0d

perf: clear vfs audit_cache before each run When generating a stream clone, we spend a large amount of time auditing path. Before this changes, the first run was warming the vfs cache for the other runs, leading to a large runtime difference and a "faulty" reported timing for the operation. We now clear this important cache between run to get a more realistic timing. Below are some example of median time change when clearing these cases. The maximum time for a run did not changed significantly. ### data-env-vars.name = mozilla-central-2018-08-01-zstd-sparse-revlog # benchmark.name = hg.perf.exchange.stream.generate # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.version = latest no-clearing: 17.289905 cache-clearing: 21.587965 (+24.86%, +4.30) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog no-clearing: 32.670748 cache-clearing: 40.467095 (+23.86%, +7.80) ## data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog no-clearing: 37.838858 cache-clearing: 46.072749 (+21.76%, +8.23) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog no-clearing: 32.969395 cache-clearing: 39.646209 (+20.25%, +6.68) In addition, this significantly reduce the timing difference between the performance command, from the perf extensions and a `real `hg bundle` call producing a stream bundle. Some significant differences remain especially on the "mozilla-try" repositories, but they are now smaller. Note that some of that difference will actually not be attributable to the stream generation (like maybe phases or branch map computation). Below are some benchmarks done on a currently draft changeset fixing some unrelated slowness in `hg bundle` (34a78972af409d1ff37c29e60f6ca811ad1a457d) ### data-env-vars.name = mozilla-central-2018-08-01-zstd-sparse-revlog # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default hg.perf.exchange.stream.generate: 21.587965 hg.command.bundle: 24.301799 (+12.57%, +2.71) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog hg.perf.exchange.stream.generate: 40.467095 hg.command.bundle: 44.831317 (+10.78%, +4.36) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog hg.perf.exchange.stream.generate: 39.646209 hg.command.bundle: 45.395258 (+14.50%, +5.75) ## data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog hg.perf.exchange.stream.generate: 46.072749 hg.command.bundle: 55.882608 (+21.29%, +9.81) ## data-env-vars.name = mozilla-try-2023-03-22-zlib-general-delta hg.perf.exchange.stream.generate: 334.716708 hg.command.bundle: 377.856767 (+12.89%, +43.14) ## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog hg.perf.exchange.stream.generate: 302.972301 hg.command.bundle: 326.098755 (+7.63%, +23.13)
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Sat, 13 Apr 2024 23:40:28 +0200
parents 642e31cb55f0
children 493034cc3265
line wrap: on
line source

# httpconnection.py - urllib2 handler for new http support
#
# Copyright 2005, 2006, 2007, 2008 Olivia Mackall <olivia@selenic.com>
# Copyright 2006, 2007 Alexis S. L. Carvalho <alexis@cecm.usp.br>
# Copyright 2006 Vadim Gelfer <vadim.gelfer@gmail.com>
# Copyright 2011 Google, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.


import os

from .i18n import _
from .pycompat import open
from . import (
    pycompat,
    util,
)
from .utils import (
    urlutil,
)


urlerr = util.urlerr
urlreq = util.urlreq

# moved here from url.py to avoid a cycle
class httpsendfile:
    """This is a wrapper around the objects returned by python's "open".

    Its purpose is to send file-like objects via HTTP.
    It do however not define a __len__ attribute because the length
    might be more than Py_ssize_t can handle.
    """

    def __init__(self, ui, *args, **kwargs):
        self.ui = ui
        self._data = open(*args, **kwargs)
        self.seek = self._data.seek
        self.close = self._data.close
        self.write = self._data.write
        self.length = os.fstat(self._data.fileno()).st_size
        self._pos = 0
        self._progress = self._makeprogress()

    def _makeprogress(self):
        # We pass double the max for total because we currently have
        # to send the bundle twice in the case of a server that
        # requires authentication. Since we can't know until we try
        # once whether authentication will be required, just lie to
        # the user and maybe the push succeeds suddenly at 50%.
        return self.ui.makeprogress(
            _(b'sending'), unit=_(b'kb'), total=(self.length // 1024 * 2)
        )

    def read(self, *args, **kwargs):
        ret = self._data.read(*args, **kwargs)
        if not ret:
            self._progress.complete()
            return ret
        self._pos += len(ret)
        self._progress.update(self._pos // 1024)
        return ret

    def __enter__(self):
        return self

    def __exit__(self, exc_type, exc_val, exc_tb):
        self.close()


# moved here from url.py to avoid a cycle
def readauthforuri(ui, uri, user):
    uri = pycompat.bytesurl(uri)
    # Read configuration
    groups = {}
    for key, val in ui.configitems(b'auth'):
        if key in (b'cookiefile',):
            continue

        if b'.' not in key:
            ui.warn(_(b"ignoring invalid [auth] key '%s'\n") % key)
            continue
        group, setting = key.rsplit(b'.', 1)
        gdict = groups.setdefault(group, {})
        if setting in (b'username', b'cert', b'key'):
            val = util.expandpath(val)
        gdict[setting] = val

    # Find the best match
    scheme, hostpath = uri.split(b'://', 1)
    bestuser = None
    bestlen = 0
    bestauth = None
    for group, auth in groups.items():
        if user and user != auth.get(b'username', user):
            # If a username was set in the URI, the entry username
            # must either match it or be unset
            continue
        prefix = auth.get(b'prefix')
        if not prefix:
            continue

        prefixurl = urlutil.url(prefix)
        if prefixurl.user and prefixurl.user != user:
            # If a username was set in the prefix, it must match the username in
            # the URI.
            continue

        # The URI passed in has been stripped of credentials, so erase the user
        # here to allow simpler matching.
        prefixurl.user = None
        prefix = bytes(prefixurl)

        p = prefix.split(b'://', 1)
        if len(p) > 1:
            schemes, prefix = [p[0]], p[1]
        else:
            schemes = (auth.get(b'schemes') or b'https').split()
        if (
            (prefix == b'*' or hostpath.startswith(prefix))
            and (
                len(prefix) > bestlen
                or (
                    len(prefix) == bestlen
                    and not bestuser
                    and b'username' in auth
                )
            )
            and scheme in schemes
        ):
            bestlen = len(prefix)
            bestauth = group, auth
            bestuser = auth.get(b'username')
            if user and not bestuser:
                auth[b'username'] = user
    return bestauth