view mercurial/hgweb/wsgicgi.py @ 49658:523cacdfd324

delta-find: set the default candidate chunk size to 10 I ran performance and storage tests on repositories of various sizes and shapes for the following values of the config : 5, 10, 20, 50, 100, no-chunking The performance tests do not show any statistical impact on computation times for large pushes and pulls. For searching for an individual delta, this can provide a significant performance improvement with a minor degradation of space-quality on the result. (see data at the end of the commit). For overall store size, the change : - does not have any impact on many small repositories, - has an observable, but very negligible impact on most larger repositories. - One private repository we use for testing sees a small increase in size (1%) in the narrower version. We will try to get more numbers on a larger version of that repository to make sure nothing pathological happens. We pick "10" as the limit as "5" seems a bit more risky. There are room to improve the current code, by using more aggressive filtering and better (i.e any) sorting of the candidates. However this is already a large improvement for pathological cases, with little impact in the common situations. The initial motivation for this change is to fix performance of delta computation for a file where the previous code ended up testing 20 000 possible candidate-bases in one go, which is… slow. This affected about ½ of the file revisions leading to atrocious performance, especially during some push/pull operations. Details about individual delta finding timing: ---------------------------------------------- The vast majority of benchmark cases are unchanged but the three below. The first two do not see any impact on the final delta. The last one sees a change in delta-size that is negligible compared to the full text size. ### data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog # benchmark.name = perf-delta-find # benchmark.variants.rev = manifest-snapshot-many-tries-a (revision 756096) ∞: 5.844783 5: 4.473523 (-23.46%) 10: 4.970053 (-14.97%) 20: 5.770386 (-1.27%) 50 5.821358 100: 5.834887 MANIFESTLOG: rev = 756096: (no-limit) delta-base = 301840 search-rounds = 6 try-count = 60 delta-type = snapshot snap-depth = 7 delta-size = 179 MANIFESTLOG: rev=756096: (limit = 10) delta-base=301840 search-rounds=9 try-count=51 delta-type=snapshot snap-depth=7 delta-size=179 ### data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog # benchmark.name = perf-delta-find # benchmark.variants.rev = manifest-snapshot-many-tries-d (revision 754060) ∞: 5.017663 5: 3.655931 (-27.14%) 10: 4.095436 (-18.38%) 20: 4.828949 (-3.76%) 50 4.987574 100: 4.994889 MANIFESTLOG: rev=754060: (no limit) delta-base=301840 search-rounds=5 try-count=53 delta-type=snapshot snap-depth=7 delta-size = 179 MANIFESTLOG: rev=754060: (limite = 10) delta-base=301840 search-rounds=8 try-count=45 delta-type=snapshot snap-depth=7 delta-size = 179 ### data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog # benchmark.name = perf-delta-find # bin-env-vars.hg.flavor = rust # benchmark.variants.rev = manifest-snapshot-many-tries-e (revision 693368) ∞: 4.869282 5: 2.039732 (-58.11%) 10: 2.413537 (-50.43%) 20: 4.449639 (-8.62%) 50 4.865863 100: 4.882649 MANIFESTLOG: rev=693368: delta-base=693336 search-rounds=6 try-count=53 delta-type=snapshot snap-depth=6 full-test-size=131065 delta-size=199 MANIFESTLOG: rev=693368: delta-base=278023 search-rounds=5 try-count=21 delta-type=snapshot snap-depth=4 full-test-size=131065 delta-size=278 Raw data for store size (in bytes) for various chunk size value below: ---------------------------------------------------------------------- 440 134 384 5 pypy/.hg/store/ 440 134 384 10 pypy/.hg/store/ 440 134 384 20 pypy/.hg/store/ 440 134 384 50 pypy/.hg/store/ 440 134 384 100 pypy/.hg/store/ 440 134 384 ... pypy/.hg/store/ 666 987 471 5 netbsd-xsrc-2022-11-15/.hg/store/ 666 987 471 10 netbsd-xsrc-2022-11-15/.hg/store/ 666 987 471 20 netbsd-xsrc-2022-11-15/.hg/store/ 666 987 471 50 netbsd-xsrc-2022-11-15/.hg/store/ 666 987 471 100 netbsd-xsrc-2022-11-15/.hg/store/ 666 987 471 ... netbsd-xsrc-2022-11-15/.hg/store/ 852 844 884 5 netbsd-pkgsrc-2022-11-15/.hg/store/ 852 844 884 10 netbsd-pkgsrc-2022-11-15/.hg/store/ 852 844 884 20 netbsd-pkgsrc-2022-11-15/.hg/store/ 852 844 884 50 netbsd-pkgsrc-2022-11-15/.hg/store/ 852 844 884 100 netbsd-pkgsrc-2022-11-15/.hg/store/ 852 844 884 ... netbsd-pkgsrc-2022-11-15/.hg/store/ 1 504 227 981 5 netbeans-2018-08-01-sparse-zstd/.hg/store/ 1 504 227 871 10 netbeans-2018-08-01-sparse-zstd/.hg/store/ 1 504 227 813 20 netbeans-2018-08-01-sparse-zstd/.hg/store/ 1 504 227 813 50 netbeans-2018-08-01-sparse-zstd/.hg/store/ 1 504 227 813 100 netbeans-2018-08-01-sparse-zstd/.hg/store/ 1 504 227 813 ... netbeans-2018-08-01-sparse-zstd/.hg/store/ 3 875 801 068 5 netbsd-src-2022-11-15/.hg/store/ 3 875 696 767 10 netbsd-src-2022-11-15/.hg/store/ 3 875 696 757 20 netbsd-src-2022-11-15/.hg/store/ 3 875 696 653 50 netbsd-src-2022-11-15/.hg/store/ 3 875 696 653 100 netbsd-src-2022-11-15/.hg/store/ 3 875 696 653 ... netbsd-src-2022-11-15/.hg/store/ 4 531 441 314 5 mozilla-central/.hg/store/ 4 531 435 157 10 mozilla-central/.hg/store/ 4 531 432 045 20 mozilla-central/.hg/store/ 4 531 429 119 50 mozilla-central/.hg/store/ 4 531 429 119 100 mozilla-central/.hg/store/ 4 531 429 119 ... mozilla-central/.hg/store/ 4 875 861 390 5 mozilla-unified/.hg/store/ 4 875 855 155 10 mozilla-unified/.hg/store/ 4 875 852 027 20 mozilla-unified/.hg/store/ 4 875 848 851 50 mozilla-unified/.hg/store/ 4 875 848 851 100 mozilla-unified/.hg/store/ 4 875 848 851 ... mozilla-unified/.hg/store/ 11 498 764 601 5 mozilla-try/.hg/store/ 11 497 968 858 10 mozilla-try/.hg/store/ 11 497 958 730 20 mozilla-try/.hg/store/ 11 497 927 156 50 mozilla-try/.hg/store/ 11 497 925 963 100 mozilla-try/.hg/store/ 11 497 923 428 ... mozilla-try/.hg/store/ 10 047 914 031 5 private-repo 9 969 132 101 10 private-repo 9 944 745 015 20 private-repo 9 939 756 703 50 private-repo 9 939 833 016 100 private-repo 9 939 822 035 ... private-repo
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Wed, 23 Nov 2022 19:08:27 +0100
parents f254fc73d956
children 18c8c18993f0 04bfcb416745
line wrap: on
line source

# hgweb/wsgicgi.py - CGI->WSGI translator
#
# Copyright 2006 Eric Hopper <hopper@omnifarious.org>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
#
# This was originally copied from the public domain code at
# http://www.python.org/dev/peps/pep-0333/#the-server-gateway-side


import os

from ..pycompat import getattr
from .. import pycompat

from ..utils import procutil

from . import common


def launch(application):
    procutil.setbinary(procutil.stdin)
    procutil.setbinary(procutil.stdout)

    environ = dict(os.environ.items())  # re-exports
    environ.setdefault('PATH_INFO', '')
    if environ.get('SERVER_SOFTWARE', '').startswith('Microsoft-IIS'):
        # IIS includes script_name in PATH_INFO
        scriptname = environ['SCRIPT_NAME']
        if environ['PATH_INFO'].startswith(scriptname):
            environ['PATH_INFO'] = environ['PATH_INFO'][len(scriptname) :]

    stdin = procutil.stdin
    if environ.get('HTTP_EXPECT', '').lower() == '100-continue':
        stdin = common.continuereader(stdin, procutil.stdout.write)

    environ['wsgi.input'] = stdin
    environ['wsgi.errors'] = procutil.stderr
    environ['wsgi.version'] = (1, 0)
    environ['wsgi.multithread'] = False
    environ['wsgi.multiprocess'] = True
    environ['wsgi.run_once'] = True

    if environ.get('HTTPS', 'off').lower() in ('on', '1', 'yes'):
        environ['wsgi.url_scheme'] = 'https'
    else:
        environ['wsgi.url_scheme'] = 'http'

    headers_set = []
    headers_sent = []
    out = procutil.stdout

    def write(data):
        if not headers_set:
            raise AssertionError(b"write() before start_response()")

        elif not headers_sent:
            # Before the first output, send the stored headers
            status, response_headers = headers_sent[:] = headers_set
            out.write(b'Status: %s\r\n' % pycompat.bytesurl(status))
            for hk, hv in response_headers:
                out.write(
                    b'%s: %s\r\n'
                    % (pycompat.bytesurl(hk), pycompat.bytesurl(hv))
                )
            out.write(b'\r\n')

        out.write(data)
        out.flush()

    def start_response(status, response_headers, exc_info=None):
        if exc_info:
            try:
                if headers_sent:
                    # Re-raise original exception if headers sent
                    raise exc_info[0](exc_info[1], exc_info[2])
            finally:
                del exc_info  # avoid dangling circular ref
        elif headers_set:
            raise AssertionError(b"Headers already set!")

        headers_set[:] = [status, response_headers]
        return write

    content = application(environ, start_response)
    try:
        for chunk in content:
            write(chunk)
        if not headers_sent:
            write(b'')  # send headers now if body was empty
    finally:
        getattr(content, 'close', lambda: None)()