view tests/get-with-headers.py @ 29787:80df04266a16

hgweb: profile HTTP requests

Currently, running `hg serve --profile` doesn't yield anything useful:
when the process is terminated the profiling output displays results
from the main thread, which typically spends most of its time in
select.select(). Furthermore, it has no meaningful results from
mercurial.* modules because the threads serving HTTP requests don't
actually get profiled.

This patch teaches the hgweb wsgi applications to profile individual
requests. If profiling is enabled, the profiler kicks in after
HTTP/WSGI environment processing but before Mercurial's main request
processing.

The profile results are printed to the configured profiling output.
If running `hg serve` from a shell, they will be printed to stderr,
just before the HTTP request line is logged. If profiling to a file,
we only write a single profile to the file because the file is not
opened in append mode. We could add support for appending to files
in a future patch if someone wants it.

Per request profiling doesn't work with the statprof profiler because
internally that profiler collects samples from the thread that
*initially* requested profiling be enabled. I have plans to address
this by vendoring Facebook's customized statprof and then improving
it.

#!/usr/bin/env python

"""This does HTTP GET requests given a host:port and path and returns
a subset of the headers plus the body of the result."""

from __future__ import absolute_import, print_function

import json
import os
import sys

from mercurial import (
    util,
)

httplib = util.httplib

try:
    import msvcrt
    msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
    msvcrt.setmode(sys.stderr.fileno(), os.O_BINARY)
except ImportError:
    pass

twice = False
if '--twice' in sys.argv:
    sys.argv.remove('--twice')
    twice = True
headeronly = False
if '--headeronly' in sys.argv:
    sys.argv.remove('--headeronly')
    headeronly = True
formatjson = False
if '--json' in sys.argv:
    sys.argv.remove('--json')
    formatjson = True

tag = None
def request(host, path, show):
    assert not path.startswith('/'), path
    global tag
    headers = {}
    if tag:
        headers['If-None-Match'] = tag

    conn = httplib.HTTPConnection(host)
    conn.request("GET", '/' + path, None, headers)
    response = conn.getresponse()
    print(response.status, response.reason)
    if show[:1] == ['-']:
        show = sorted(h for h, v in response.getheaders()
                      if h.lower() not in show)
    for h in [h.lower() for h in show]:
        if response.getheader(h, None) is not None:
            print("%s: %s" % (h, response.getheader(h)))
    if not headeronly:
        print()
        data = response.read()

        # Pretty print JSON. This also has the beneficial side-effect
        # of verifying emitted JSON is well-formed.
        if formatjson:
            # json.dumps() will print trailing newlines. Eliminate them
            # to make tests easier to write.
            data = json.loads(data)
            lines = json.dumps(data, sort_keys=True, indent=2).splitlines()
            for line in lines:
                print(line.rstrip())
        else:
            sys.stdout.write(data)

        if twice and response.getheader('ETag', None):
            tag = response.getheader('ETag')

    return response.status

status = request(sys.argv[1], sys.argv[2], sys.argv[3:])
if twice:
    status = request(sys.argv[1], sys.argv[2], sys.argv[3:])

if 200 <= status <= 305:
    sys.exit(0)
sys.exit(1)