contrib/hgperf

hgweb: parse WSGI request into a data structure

Currently, our WSGI applications (hgweb_mod and hgwebdir_mod) process
the raw WSGI request instance themselves. This means they have to
talk in terms of system strings. And they need to know details
about what's in the WSGI request. And in the case of hgweb_mod, it
is doing some very funky things with URL parsing to impact
dispatching. The code is difficult to read and maintain.

This commit introduces parsing of the WSGI request into a higher-level
and easier-to-reason-about data structure.

To prove it works, we hook it up to hgweb_mod and use it for populating
the relative URL on the request instance.

We hold off on using it in more places because the logic in hgweb_mod
is crazy and I don't want to involve those changes with review of
the parsing code.

The URL construction code has variations that use the HTTP: Host header
(the canonical WSGI way of reconstructing the URL) and with the use
of SERVER_NAME. We need to differentiate because hgweb is currently
using SERVER_NAME for URL construction.

Differential Revision: https://phab.mercurial-scm.org/D2734

#!/usr/bin/env python
#
# hgperf - measure performance of Mercurial commands
#
# Copyright 2014 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''measure performance of Mercurial commands

Using ``hgperf`` instead of ``hg`` measures performance of the target
Mercurial command. For example, the execution below measures
performance of :hg:`heads --topo`::

    $ hgperf heads --topo

All command output via ``ui`` is suppressed, and just measurement
result is displayed: see also "perf" extension in "contrib".

Costs of processing before dispatching to the command function like
below are not measured::

    - parsing command line (e.g. option validity check)
    - reading configuration files in

But ``pre-`` and ``post-`` hook invocation for the target command is
measured, even though these are invoked before or after dispatching to
the command function, because these may be required to repeat
execution of the target command correctly.
'''

import os
import sys

libdir = '@LIBDIR@'

if libdir != '@' 'LIBDIR' '@':
    if not os.path.isabs(libdir):
        libdir = os.path.join(os.path.dirname(os.path.realpath(__file__)),
                              libdir)
        libdir = os.path.abspath(libdir)
    sys.path.insert(0, libdir)

# enable importing on demand to reduce startup time
try:
    from mercurial import demandimport; demandimport.enable()
except ImportError:
    import sys
    sys.stderr.write("abort: couldn't find mercurial libraries in [%s]\n" %
                     ' '.join(sys.path))
    sys.stderr.write("(check your install and PYTHONPATH)\n")
    sys.exit(-1)

from mercurial import (
    dispatch,
    util,
)

def timer(func, title=None):
    results = []
    begin = util.timer()
    count = 0
    while True:
        ostart = os.times()
        cstart = util.timer()
        r = func()
        cstop = util.timer()
        ostop = os.times()
        count += 1
        a, b = ostart, ostop
        results.append((cstop - cstart, b[0] - a[0], b[1]-a[1]))
        if cstop - begin > 3 and count >= 100:
            break
        if cstop - begin > 10 and count >= 3:
            break
    if title:
        sys.stderr.write("! %s\n" % title)
    if r:
        sys.stderr.write("! result: %s\n" % r)
    m = min(results)
    sys.stderr.write("! wall %f comb %f user %f sys %f (best of %d)\n"
                     % (m[0], m[1] + m[2], m[1], m[2], count))

orgruncommand = dispatch.runcommand

def runcommand(lui, repo, cmd, fullargs, ui, options, d, cmdpats, cmdoptions):
    ui.pushbuffer()
    lui.pushbuffer()
    timer(lambda : orgruncommand(lui, repo, cmd, fullargs, ui,
                                 options, d, cmdpats, cmdoptions))
    ui.popbuffer()
    lui.popbuffer()

dispatch.runcommand = runcommand

dispatch.run()