view tests/test-wsgirequest.py @ 44363:f7459da77f23

nodemap: introduce an option to use mmap to read the nodemap mapping

The performance and memory benefit is much greater if we don't have to copy all
the data in memory for each information. So we introduce an option (on by
default) to read the data using mmap.

This changeset is the last one definition the API for index support nodemap
data. (they have to be able to use the mmaping).

Below are some benchmark comparing the best we currently have in 5.3 with the
final step of this series (using the persistent nodemap implementation in
Rust). The benchmark run `hg perfindex` with various revset and the following
variants:

Before:

 * do not use the persistent nodemap
 * use the CPython implementation of the index for nodemap
 * use mmapping of the changelog index

After:

 * use the MixedIndex Rust code, with the NodeTree object for nodemap access
   (still in review)
 * use the persistent nodemap data from disk
 * access the persistent nodemap data through mmap
 * use mmapping of the changelog index

The persistent nodemap greatly speed up  most operation on very large
repositories. Some of the previously very fast lookup end up a bit slower because
the persistent nodemap has to be setup. However the absolute slowdown is very
small and won't matters in the big picture.

Here are some numbers (in seconds) for the reference copy of mozilla-try:

Revset            Before   After     abs-change speedup

-10000:           0.004622 0.005532   0.000910  ×   0.83
-10:              0.000050 0.000132   0.000082  ×   0.37
tip               0.000052 0.000085   0.000033  ×   0.61
0 + (-10000:)     0.028222 0.005337  -0.022885  ×   5.29
0                 0.023521 0.000084  -0.023437  × 280.01
(-10000:) + 0     0.235539 0.005308  -0.230231  ×  44.37
(-10:) + :9       0.232883 0.000180  -0.232703  ×1293.79
(-10000:) + (:99) 0.238735 0.005358  -0.233377  ×  44.55
:99 + (-10000:)   0.317942 0.005593  -0.312349  ×  56.84
:9 + (-10:)       0.313372 0.000179  -0.313193  ×1750.68
:9                0.316450 0.000143  -0.316307  ×2212.93


On smaller repositories, the cost of nodemap related operation is not as big, so
the win is much more modest. Yet it helps shaving a handful of millisecond here
and there.

Here are some numbers (in seconds) for the reference copy of mercurial:

Revset            Before   After     abs-change speedup
-10:              0.000065 0.000097   0.000032  × 0.67
tip               0.000063 0.000078   0.000015  × 0.80
0                 0.000561 0.000079  -0.000482  × 7.10
-10000:           0.004609 0.003648  -0.000961  × 1.26
0 + (-10000:)     0.005023 0.003715  -0.001307  × 1.35
(-10:) + :9       0.002187 0.000108  -0.002079  ×20.25
(-10000:) + 0     0.006252 0.003716  -0.002536  × 1.68
(-10000:) + (:99) 0.006367 0.003707  -0.002660  × 1.71
:9 + (-10:)       0.003846 0.000110  -0.003736  ×34.96
:9                0.003854 0.000099  -0.003755  ×38.92
:99 + (-10000:)   0.007644 0.003778  -0.003866  × 2.02

Differential Revision: https://phab.mercurial-scm.org/D7894

from __future__ import absolute_import, print_function

import unittest

from mercurial.hgweb import request as requestmod
from mercurial import error

DEFAULT_ENV = {
    'REQUEST_METHOD': 'GET',
    'SERVER_NAME': 'testserver',
    'SERVER_PORT': '80',
    'SERVER_PROTOCOL': 'http',
    'wsgi.version': (1, 0),
    'wsgi.url_scheme': 'http',
    'wsgi.input': None,
    'wsgi.errors': None,
    'wsgi.multithread': False,
    'wsgi.multiprocess': True,
    'wsgi.run_once': False,
}


def parse(env, reponame=None, altbaseurl=None, extra=None):
    env = dict(env)
    env.update(extra or {})

    return requestmod.parserequestfromenv(
        env, reponame=reponame, altbaseurl=altbaseurl
    )


class ParseRequestTests(unittest.TestCase):
    def testdefault(self):
        r = parse(DEFAULT_ENV)
        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.method, b'GET')
        self.assertIsNone(r.remoteuser)
        self.assertIsNone(r.remotehost)
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)
        self.assertIsNone(r.reponame)
        self.assertEqual(r.querystring, b'')
        self.assertEqual(len(r.qsparams), 0)
        self.assertEqual(len(r.headers), 0)

    def testcustomport(self):
        r = parse(DEFAULT_ENV, extra={'SERVER_PORT': '8000',})

        self.assertEqual(r.url, b'http://testserver:8000')
        self.assertEqual(r.baseurl, b'http://testserver:8000')
        self.assertEqual(r.advertisedurl, b'http://testserver:8000')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver:8000')

        r = parse(
            DEFAULT_ENV,
            extra={'SERVER_PORT': '4000', 'wsgi.url_scheme': 'https',},
        )

        self.assertEqual(r.url, b'https://testserver:4000')
        self.assertEqual(r.baseurl, b'https://testserver:4000')
        self.assertEqual(r.advertisedurl, b'https://testserver:4000')
        self.assertEqual(r.advertisedbaseurl, b'https://testserver:4000')

    def testhttphost(self):
        r = parse(DEFAULT_ENV, extra={'HTTP_HOST': 'altserver',})

        self.assertEqual(r.url, b'http://altserver')
        self.assertEqual(r.baseurl, b'http://altserver')
        self.assertEqual(r.advertisedurl, b'http://testserver')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')

    def testscriptname(self):
        r = parse(DEFAULT_ENV, extra={'SCRIPT_NAME': '',})

        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)

        r = parse(DEFAULT_ENV, extra={'SCRIPT_NAME': '/script',})

        self.assertEqual(r.url, b'http://testserver/script')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver/script')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'/script')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)

        r = parse(DEFAULT_ENV, extra={'SCRIPT_NAME': '/multiple words',})

        self.assertEqual(r.url, b'http://testserver/multiple%20words')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver/multiple%20words')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'/multiple words')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)

    def testpathinfo(self):
        r = parse(DEFAULT_ENV, extra={'PATH_INFO': '',})

        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [])
        self.assertEqual(r.dispatchpath, b'')

        r = parse(DEFAULT_ENV, extra={'PATH_INFO': '/pathinfo',})

        self.assertEqual(r.url, b'http://testserver/pathinfo')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver/pathinfo')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [b'pathinfo'])
        self.assertEqual(r.dispatchpath, b'pathinfo')

        r = parse(DEFAULT_ENV, extra={'PATH_INFO': '/one/two/',})

        self.assertEqual(r.url, b'http://testserver/one/two/')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver/one/two/')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [b'one', b'two'])
        self.assertEqual(r.dispatchpath, b'one/two')

    def testscriptandpathinfo(self):
        r = parse(
            DEFAULT_ENV,
            extra={'SCRIPT_NAME': '/script', 'PATH_INFO': '/pathinfo',},
        )

        self.assertEqual(r.url, b'http://testserver/script/pathinfo')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver/script/pathinfo')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'/script')
        self.assertEqual(r.dispatchparts, [b'pathinfo'])
        self.assertEqual(r.dispatchpath, b'pathinfo')

        r = parse(
            DEFAULT_ENV,
            extra={
                'SCRIPT_NAME': '/script1/script2',
                'PATH_INFO': '/path1/path2',
            },
        )

        self.assertEqual(
            r.url, b'http://testserver/script1/script2/path1/path2'
        )
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(
            r.advertisedurl, b'http://testserver/script1/script2/path1/path2'
        )
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'/script1/script2')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')

        r = parse(
            DEFAULT_ENV,
            extra={
                'HTTP_HOST': 'hostserver',
                'SCRIPT_NAME': '/script',
                'PATH_INFO': '/pathinfo',
            },
        )

        self.assertEqual(r.url, b'http://hostserver/script/pathinfo')
        self.assertEqual(r.baseurl, b'http://hostserver')
        self.assertEqual(r.advertisedurl, b'http://testserver/script/pathinfo')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'/script')
        self.assertEqual(r.dispatchparts, [b'pathinfo'])
        self.assertEqual(r.dispatchpath, b'pathinfo')

    if not getattr(unittest.TestCase, 'assertRaisesRegex', False):
        # Python 3.7 deprecates the regex*p* version, but 2.7 lacks
        # the regex version.
        assertRaisesRegex = (  # camelcase-required
            unittest.TestCase.assertRaisesRegexp
        )

    def testreponame(self):
        """repository path components get stripped from URL."""

        with self.assertRaisesRegex(
            error.ProgrammingError, 'reponame requires PATH_INFO'
        ):
            parse(DEFAULT_ENV, reponame=b'repo')

        with self.assertRaisesRegex(
            error.ProgrammingError, 'PATH_INFO does not begin with repo ' 'name'
        ):
            parse(
                DEFAULT_ENV,
                reponame=b'repo',
                extra={'PATH_INFO': '/pathinfo',},
            )

        with self.assertRaisesRegex(
            error.ProgrammingError, 'reponame prefix of PATH_INFO'
        ):
            parse(
                DEFAULT_ENV,
                reponame=b'repo',
                extra={'PATH_INFO': '/repoextra/path',},
            )

        r = parse(
            DEFAULT_ENV,
            reponame=b'repo',
            extra={'PATH_INFO': '/repo/path1/path2',},
        )

        self.assertEqual(r.url, b'http://testserver/repo/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://testserver/repo/path1/path2')
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'/repo')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertEqual(r.reponame, b'repo')

        r = parse(
            DEFAULT_ENV,
            reponame=b'prefix/repo',
            extra={'PATH_INFO': '/prefix/repo/path1/path2',},
        )

        self.assertEqual(r.url, b'http://testserver/prefix/repo/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(
            r.advertisedurl, b'http://testserver/prefix/repo/path1/path2'
        )
        self.assertEqual(r.advertisedbaseurl, b'http://testserver')
        self.assertEqual(r.apppath, b'/prefix/repo')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertEqual(r.reponame, b'prefix/repo')

    def testaltbaseurl(self):
        # Simple hostname remap.
        r = parse(DEFAULT_ENV, altbaseurl=b'http://altserver')

        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://altserver')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)
        self.assertIsNone(r.reponame)

        # With a custom port.
        r = parse(DEFAULT_ENV, altbaseurl=b'http://altserver:8000')
        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://altserver:8000')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver:8000')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)
        self.assertIsNone(r.reponame)

        # With a changed protocol.
        r = parse(DEFAULT_ENV, altbaseurl=b'https://altserver')
        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'https://altserver')
        self.assertEqual(r.advertisedbaseurl, b'https://altserver')
        # URL scheme is defined as the actual scheme, not advertised.
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)
        self.assertIsNone(r.reponame)

        # Need to specify explicit port number for proper https:// alt URLs.
        r = parse(DEFAULT_ENV, altbaseurl=b'https://altserver:443')
        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'https://altserver')
        self.assertEqual(r.advertisedbaseurl, b'https://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)
        self.assertIsNone(r.reponame)

        # With only PATH_INFO defined.
        r = parse(
            DEFAULT_ENV,
            altbaseurl=b'http://altserver',
            extra={'PATH_INFO': '/path1/path2',},
        )
        self.assertEqual(r.url, b'http://testserver/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://altserver/path1/path2')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertIsNone(r.reponame)

        # Path on alt URL.
        r = parse(DEFAULT_ENV, altbaseurl=b'http://altserver/altpath')
        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://altserver/altpath')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'/altpath')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)
        self.assertIsNone(r.reponame)

        # With a trailing slash.
        r = parse(DEFAULT_ENV, altbaseurl=b'http://altserver/altpath/')
        self.assertEqual(r.url, b'http://testserver')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://altserver/altpath/')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'/altpath/')
        self.assertEqual(r.dispatchparts, [])
        self.assertIsNone(r.dispatchpath)
        self.assertIsNone(r.reponame)

        # PATH_INFO + path on alt URL.
        r = parse(
            DEFAULT_ENV,
            altbaseurl=b'http://altserver/altpath',
            extra={'PATH_INFO': '/path1/path2',},
        )
        self.assertEqual(r.url, b'http://testserver/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(
            r.advertisedurl, b'http://altserver/altpath/path1/path2'
        )
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'/altpath')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertIsNone(r.reponame)

        # PATH_INFO + path on alt URL with trailing slash.
        r = parse(
            DEFAULT_ENV,
            altbaseurl=b'http://altserver/altpath/',
            extra={'PATH_INFO': '/path1/path2',},
        )
        self.assertEqual(r.url, b'http://testserver/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(
            r.advertisedurl, b'http://altserver/altpath//path1/path2'
        )
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'/altpath/')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertIsNone(r.reponame)

        # Local SCRIPT_NAME is ignored.
        r = parse(
            DEFAULT_ENV,
            altbaseurl=b'http://altserver',
            extra={'SCRIPT_NAME': '/script', 'PATH_INFO': '/path1/path2',},
        )
        self.assertEqual(r.url, b'http://testserver/script/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(r.advertisedurl, b'http://altserver/path1/path2')
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertIsNone(r.reponame)

        # Use remote's path for script name, app path
        r = parse(
            DEFAULT_ENV,
            altbaseurl=b'http://altserver/altroot',
            extra={'SCRIPT_NAME': '/script', 'PATH_INFO': '/path1/path2',},
        )
        self.assertEqual(r.url, b'http://testserver/script/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(
            r.advertisedurl, b'http://altserver/altroot/path1/path2'
        )
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.urlscheme, b'http')
        self.assertEqual(r.apppath, b'/altroot')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertIsNone(r.reponame)

        # reponame is factored in properly.
        r = parse(
            DEFAULT_ENV,
            reponame=b'repo',
            altbaseurl=b'http://altserver/altroot',
            extra={'SCRIPT_NAME': '/script', 'PATH_INFO': '/repo/path1/path2',},
        )

        self.assertEqual(r.url, b'http://testserver/script/repo/path1/path2')
        self.assertEqual(r.baseurl, b'http://testserver')
        self.assertEqual(
            r.advertisedurl, b'http://altserver/altroot/repo/path1/path2'
        )
        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
        self.assertEqual(r.apppath, b'/altroot/repo')
        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
        self.assertEqual(r.dispatchpath, b'path1/path2')
        self.assertEqual(r.reponame, b'repo')


if __name__ == '__main__':
    import silenttestrunner

    silenttestrunner.main(__name__)