view mercurial/httpconnection.py @ 42121:6578654916ae

branchcache: lazily validate nodes from the branchmap

On my personal hg-repository with 365 entries in .hg/cache/branch2, following
are the numbers for perfbranchmapload.

Before this patch:

! wall 0.000866 comb 0.000000 user 0.000000 sys 0.000000 (best of 2680)
! wall 0.001525 comb 0.000000 user 0.000000 sys 0.000000 (max of 2680)
! wall 0.001107 comb 0.001097 user 0.001086 sys 0.000011 (avg of 2680)
! wall 0.001104 comb 0.000000 user 0.000000 sys 0.000000 (median of 2680)

With this patch:

! wall 0.000530 comb 0.000000 user 0.000000 sys 0.000000 (best of 4240)
! wall 0.001078 comb 0.000000 user 0.000000 sys 0.000000 (max of 4240)
! wall 0.000696 comb 0.000693 user 0.000677 sys 0.000017 (avg of 4240)
! wall 0.000690 comb 0.000000 user 0.000000 sys 0.000000 (median of 4240)

On our internal repository with ~20k entries in branchcache, I see improvement
from 0.125 sec to 0.066 sec which is 47% speed up.

The above are the numbers of perfbranchmapload which shows how much time we
saved by not validating the nodes. But we need to validate some nodes. Following
are timings of some mercurial operations which have speed up because of this
lazy validation of nodes:

No-op `hg update` on our internal repository (Avg on 4 runs):

Before: 0.540 secs
After: 0.430 secs

Setting a branch name which already exists without --force (Avg of 4 runs):

Before: 0.510 secs
After: 0.250 secs

I ran the ASV performance suite and was unable to see any improvements except
there was improvement of perfdirstatewrite() on netbeans which I think was not
related.

I looked into the commit code, the command which I am trying to speedup, it
looks like it uses revbranchcache to update the branchcache.

Differential Revision: https://phab.mercurial-scm.org/D6208

# httpconnection.py - urllib2 handler for new http support
#
# Copyright 2005, 2006, 2007, 2008 Matt Mackall <[e-mail]>
# Copyright 2006, 2007 Alexis S. L. Carvalho <[e-mail]>
# Copyright 2006 Vadim Gelfer <[e-mail]>
# 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.

from __future__ import absolute_import

import os

from .i18n import _
from . import (
    pycompat,
    util,
)

urlerr = util.urlerr
urlreq = util.urlreq

# moved here from url.py to avoid a cycle
class httpsendfile(object):
    """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
        # 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%.
        self._progress = ui.makeprogress(_('sending'), unit=_('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('auth'):
        if key in ('cookiefile',):
            continue

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

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

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