view tests/tinyproxy.py @ 14365:a8e3931e3fb5

revlog: linearize created changegroups in generaldelta revlogs

This greatly improves the speed of the bundling process, and often reduces the
bundle size considerably. (Although if the repository is already ordered, this
has little effect on both time and bundle size.)

For non-generaldelta clients, the reduced bundle size translates to a reduced
repository size, similar to shrinking the revlogs (which uses the exact same
algorithm). For generaldelta clients the difference is minor.

When the new bundle format comes, reordering will not be necessary since we
can then store the deltaparent relationsships directly. The eventual default
behavior for clients and servers is presented in the table below, where "new"
implies support for GD as well as the new bundle format:

                    old client                    new client
old server          old bundle, no reorder        old bundle, no reorder
new server, non-GD  old bundle, no reorder[1]     old bundle, no reorder[2]
new server, GD      old bundle, reorder[3]        new bundle, no reorder[4]

[1] reordering is expensive on the server in this case, skip it
[2] client can choose to do its own redelta here
[3] reordering is needed because otherwise the pull does a lot of extra
    work on the server
[4] reordering isn't needed because client can get deltabase in bundle
    format

Currently, the default is to reorder on GD-servers, and not otherwise. A new
setting, bundle.reorder, has been added to override the default reordering
behavior. It can be set to either 'auto' (the default), or any true or false
value as a standard boolean setting, to either force the reordering on or off
regardless of generaldelta.


Some timing data from a relatively branch test repository follows. All
bundling is done with --all --type none options.

Non-generaldelta, non-shrunk repo:
-----------------------------------
Size: 276M

Without reorder (default):
Bundle time: 14.4 seconds
Bundle size: 939M

With reorder:
Bundle time: 1 minute, 29.3 seconds
Bundle size: 381M

Generaldelta, non-shrunk repo:
-----------------------------------
Size: 87M

Without reorder:
Bundle time: 2 minutes, 1.4 seconds
Bundle size: 939M

With reorder (default):
Bundle time: 25.5 seconds
Bundle size: 381M

#!/usr/bin/env python

__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 BaseHTTPServer, select, socket, SocketServer, urlparse

class ProxyHandler (BaseHTTPServer.BaseHTTPRequestHandler):
    __base = BaseHTTPServer.BaseHTTPRequestHandler
    __base_handle = __base.handle

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

    def handle(self):
        (ip, port) =  self.client_address
        if hasattr(self, 'allowed_clients') and ip not in self.allowed_clients:
            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)]))

    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, arg:
            try: msg = arg[1]
            except: msg = arg
            self.send_error(404, msg)
            return 0
        return 1

    def do_CONNECT(self):
        soc = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
        try:
            if self._connect_to(self.path, soc):
                self.log_request(200)
                self.wfile.write(self.protocol_version +
                                 " 200 Connection established\r\n")
                self.wfile.write("Proxy-agent: %s\r\n" % self.version_string())
                self.wfile.write("\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) = urlparse.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(socket.AF_INET, socket.SOCK_STREAM)
        try:
            if self._connect_to(netloc, soc):
                self.log_request()
                soc.send("%s %s %s\r\n" % (
                    self.command,
                    urlparse.urlunparse(('', '', path, params, query, '')),
                    self.request_version))
                self.headers['Connection'] = 'close'
                del self.headers['Proxy-Connection']
                for key_val in self.headers.items():
                    soc.send("%s: %s\r\n" % key_val)
                soc.send("\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 1:
            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
                    data = i.recv(8192)
                    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,
                           BaseHTTPServer.HTTPServer): pass

if __name__ == '__main__':
    from sys import 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..."
        BaseHTTPServer.test(ProxyHandler, ThreadingHTTPServer)