mercurial/httpconnection.py
author Gregory Szorc <gregory.szorc@gmail.com>
Mon, 20 Jan 2020 23:51:25 -0800
changeset 44118 f81c17ec303c
parent 43106 d783f945a701
child 44298 0e8b28fb751b
permissions -rw-r--r--
hgdemandimport: apply lazy module loading to sys.meta_path finders Python's `sys.meta_path` finders are the primary objects whose job it is to find a module at import time. When `import` is called, Python iterates objects in this list and calls `o.find_spec(...)` to find a `ModuleSpec` (or None if the module couldn't be found by that finder). If no meta path finder can find a module, import fails. One of the default meta path finders is `PathFinder`. Its job is to import modules from the filesystem and is probably the most important importer. This finder looks at `sys.path` and `sys.path_hooks` to do its job. The `ModuleSpec` returned by `MetaPathImporter.find_spec()` has a `loader` attribute, which defines the concrete module loader to use. `sys.path_hooks` is a hook point for teaching `PathFinder` to instantiate custom loader types. Previously, we injected a custom `sys.path_hook` that told `PathFinder` to wrap the default loaders with a loader that creates a module object that is lazy. This approach worked. But its main limitation was that it only applied to the `PathFinder` meta path importer. There are other meta path importers that are registered. And in the case of PyOxidizer loading modules from memory, `PathFinder` doesn't come into play since PyOxidizer's own meta path importer was handling all imports. This commit changes our approach to lazy module loading by proxying all meta path importers. Specifically, we overload the `find_spec()` method to swap in a wrapped loader on the `ModuleSpec` before it is returned. The end result of this is all meta path importers should be lazy. As much as I would have loved to utilize .__class__ manipulation to achieve this, some meta path importers are implemented in C/Rust in such a way that they cannot be monkeypatched. This is why we use __getattribute__ to define a proxy. Also, this change could theoretically open us up to regressions in meta path importers whose loader is creating module objects which can't be monkeypatched. But I'm not aware of any of these in the wild. So I think we'll be safe. According to hyperfine, this change yields a decent startup time win of 5-6ms: ``` Benchmark #1: ~/.pyenv/versions/3.6.10/bin/python ./hg version Time (mean ? ?): 86.8 ms ? 0.5 ms [User: 78.0 ms, System: 8.7 ms] Range (min ? max): 86.0 ms ? 89.1 ms 50 runs Time (mean ? ?): 81.1 ms ? 2.7 ms [User: 74.5 ms, System: 6.5 ms] Range (min ? max): 77.8 ms ? 90.5 ms 50 runs Benchmark #2: ~/.pyenv/versions/3.7.6/bin/python ./hg version Time (mean ? ?): 78.9 ms ? 0.6 ms [User: 70.2 ms, System: 8.7 ms] Range (min ? max): 78.1 ms ? 81.2 ms 50 runs Time (mean ? ?): 73.4 ms ? 0.6 ms [User: 65.3 ms, System: 8.0 ms] Range (min ? max): 72.4 ms ? 75.7 ms 50 runs Benchmark #3: ~/.pyenv/versions/3.8.1/bin/python ./hg version Time (mean ? ?): 78.1 ms ? 0.6 ms [User: 70.2 ms, System: 7.9 ms] Range (min ? max): 77.4 ms ? 80.9 ms 50 runs Time (mean ? ?): 72.1 ms ? 0.4 ms [User: 64.4 ms, System: 7.6 ms] Range (min ? max): 71.4 ms ? 74.1 ms 50 runs ``` Differential Revision: https://phab.mercurial-scm.org/D7954

# httpconnection.py - urllib2 handler for new http support
#
# Copyright 2005, 2006, 2007, 2008 Matt Mackall <mpm@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.

from __future__ import absolute_import

import os

from .i18n import _
from .pycompat import open
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(
            _(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 pycompat.iteritems(groups):
        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 = 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(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