view tests/tinyproxy.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
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Tue, 11 Feb 2020 11:18:52 +0100
parents 2372284d9457
children c102b704edb5
line wrap: on
line source

#!/usr/bin/env python

from __future__ import absolute_import, print_function

__doc__ = """Tiny HTTP Proxy.

This module implements GET, HEAD, POST, PUT and DELETE methods
on BaseHTTPServer, and behaves as an HTTP proxy.  The CONNECT
method is also implemented experimentally, but has not been
tested yet.

Any help will be greatly appreciated.           SUZUKI Hisao
"""

__version__ = "0.2.1"

import optparse
import os
import select
import socket
import sys

from mercurial import (
    pycompat,
    util,
)

httpserver = util.httpserver
socketserver = util.socketserver
urlreq = util.urlreq

if os.environ.get('HGIPV6', '0') == '1':
    family = socket.AF_INET6
else:
    family = socket.AF_INET


class ProxyHandler(httpserver.basehttprequesthandler):
    __base = httpserver.basehttprequesthandler
    __base_handle = __base.handle

    server_version = "TinyHTTPProxy/" + __version__
    rbufsize = 0  # self.rfile Be unbuffered

    def handle(self):
        (ip, port) = self.client_address
        allowed = getattr(self, 'allowed_clients', None)
        if allowed is not None and ip not in allowed:
            self.raw_requestline = self.rfile.readline()
            if self.parse_request():
                self.send_error(403)
        else:
            self.__base_handle()

    def log_request(self, code='-', size='-'):
        xheaders = [h for h in self.headers.items() if h[0].startswith('x-')]
        self.log_message(
            '"%s" %s %s%s',
            self.requestline,
            str(code),
            str(size),
            ''.join([' %s:%s' % h for h in sorted(xheaders)]),
        )
        # Flush for Windows, so output isn't lost on TerminateProcess()
        sys.stdout.flush()
        sys.stderr.flush()

    def _connect_to(self, netloc, soc):
        i = netloc.find(':')
        if i >= 0:
            host_port = netloc[:i], int(netloc[i + 1 :])
        else:
            host_port = netloc, 80
        print("\t" "connect to %s:%d" % host_port)
        try:
            soc.connect(host_port)
        except socket.error as arg:
            try:
                msg = arg[1]
            except (IndexError, TypeError):
                msg = arg
            self.send_error(404, msg)
            return 0
        return 1

    def do_CONNECT(self):
        soc = socket.socket(family, socket.SOCK_STREAM)
        try:
            if self._connect_to(self.path, soc):
                self.log_request(200)
                self.wfile.write(
                    pycompat.bytestr(self.protocol_version)
                    + b" 200 Connection established\r\n"
                )
                self.wfile.write(
                    b"Proxy-agent: %s\r\n"
                    % pycompat.bytestr(self.version_string())
                )
                self.wfile.write(b"\r\n")
                self._read_write(soc, 300)
        finally:
            print("\t" "bye")
            soc.close()
            self.connection.close()

    def do_GET(self):
        (scm, netloc, path, params, query, fragment) = urlreq.urlparse(
            self.path, 'http'
        )
        if scm != 'http' or fragment or not netloc:
            self.send_error(400, "bad url %s" % self.path)
            return
        soc = socket.socket(family, socket.SOCK_STREAM)
        try:
            if self._connect_to(netloc, soc):
                self.log_request()
                url = urlreq.urlunparse(('', '', path, params, query, ''))
                soc.send(
                    b"%s %s %s\r\n"
                    % (
                        pycompat.bytestr(self.command),
                        pycompat.bytestr(url),
                        pycompat.bytestr(self.request_version),
                    )
                )
                self.headers['Connection'] = 'close'
                del self.headers['Proxy-Connection']
                for key, val in self.headers.items():
                    soc.send(
                        b"%s: %s\r\n"
                        % (pycompat.bytestr(key), pycompat.bytestr(val))
                    )
                soc.send(b"\r\n")
                self._read_write(soc)
        finally:
            print("\t" "bye")
            soc.close()
            self.connection.close()

    def _read_write(self, soc, max_idling=20):
        iw = [self.connection, soc]
        ow = []
        count = 0
        while True:
            count += 1
            (ins, _, exs) = select.select(iw, ow, iw, 3)
            if exs:
                break
            if ins:
                for i in ins:
                    if i is soc:
                        out = self.connection
                    else:
                        out = soc
                    try:
                        data = i.recv(8192)
                    except socket.error:
                        break
                    if data:
                        out.send(data)
                        count = 0
            else:
                print("\t" "idle", count)
            if count == max_idling:
                break

    do_HEAD = do_GET
    do_POST = do_GET
    do_PUT = do_GET
    do_DELETE = do_GET


class ThreadingHTTPServer(socketserver.ThreadingMixIn, httpserver.httpserver):
    def __init__(self, *args, **kwargs):
        httpserver.httpserver.__init__(self, *args, **kwargs)
        a = open("proxy.pid", "w")
        a.write(str(os.getpid()) + "\n")
        a.close()


def runserver(port=8000, bind=""):
    server_address = (bind, port)
    ProxyHandler.protocol_version = "HTTP/1.0"
    httpd = ThreadingHTTPServer(server_address, ProxyHandler)
    sa = httpd.socket.getsockname()
    print("Serving HTTP on", sa[0], "port", sa[1], "...")
    try:
        httpd.serve_forever()
    except KeyboardInterrupt:
        print("\nKeyboard interrupt received, exiting.")
        httpd.server_close()
        sys.exit(0)


if __name__ == '__main__':
    argv = sys.argv
    if argv[1:] and argv[1] in ('-h', '--help'):
        print(argv[0], "[port [allowed_client_name ...]]")
    else:
        if argv[2:]:
            allowed = []
            for name in argv[2:]:
                client = socket.gethostbyname(name)
                allowed.append(client)
                print("Accept: %s (%s)" % (client, name))
            ProxyHandler.allowed_clients = allowed
            del argv[2:]
        else:
            print("Any clients will be served...")

        parser = optparse.OptionParser()
        parser.add_option(
            '-b',
            '--bind',
            metavar='ADDRESS',
            help='Specify alternate bind address ' '[default: all interfaces]',
            default='',
        )
        (options, args) = parser.parse_args()
        port = 8000
        if len(args) == 1:
            port = int(args[0])
        runserver(port, options.bind)