view mercurial/hgweb/server.py @ 30451:41a8106789ca

util: implement zstd compression engine Now that zstd is vendored and being built (in some configurations), we can implement a compression engine for zstd! The zstd engine is a little different from existing engines. Because it may not always be present, we have to defer load the module in case importing it fails. We facilitate this via a cached property that holds a reference to the module or None. The "available" method is implemented to reflect reality. The zstd engine declares its ability to handle bundles using the "zstd" human name and the "ZS" internal name. The latter was chosen because internal names are 2 characters (by only convention I think) and "ZS" seems reasonable. The engine, like others, supports specifying the compression level. However, there are no consumers of this API that yet pass in that argument. I have plans to change that, so stay tuned. Since all we need to do to support bundle generation with a new compression engine is implement and register the compression engine, bundle generation with zstd "just works!" Tests demonstrating this have been added. How does performance of zstd for bundle generation compare? On the mozilla-unified repo, `hg bundle --all -t <engine>-v2` yields the following on my i7-6700K on Linux: engine CPU time bundle size vs orig size throughput none 97.0s 4,054,405,584 100.0% 41.8 MB/s bzip2 (l=9) 393.6s 975,343,098 24.0% 10.3 MB/s gzip (l=6) 184.0s 1,140,533,074 28.1% 22.0 MB/s zstd (l=1) 108.2s 1,119,434,718 27.6% 37.5 MB/s zstd (l=2) 111.3s 1,078,328,002 26.6% 36.4 MB/s zstd (l=3) 113.7s 1,011,823,727 25.0% 35.7 MB/s zstd (l=4) 116.0s 1,008,965,888 24.9% 35.0 MB/s zstd (l=5) 121.0s 977,203,148 24.1% 33.5 MB/s zstd (l=6) 131.7s 927,360,198 22.9% 30.8 MB/s zstd (l=7) 139.0s 912,808,505 22.5% 29.2 MB/s zstd (l=12) 198.1s 854,527,714 21.1% 20.5 MB/s zstd (l=18) 681.6s 789,750,690 19.5% 5.9 MB/s On compression, zstd for bundle generation delivers: * better compression than gzip with significantly less CPU utilization * better than bzip2 compression ratios while still being significantly faster than gzip * ability to aggressively tune compression level to achieve significantly smaller bundles That last point is important. With clone bundles, a server can pre-generate a bundle file, upload it to a static file server, and redirect clients to transparently download it during clone. The server could choose to produce a zstd bundle with the highest compression settings possible. This would take a very long time - a magnitude longer than a typical zstd bundle generation - but the result would be hundreds of megabytes smaller! For the clone volume we do at Mozilla, this could translate to petabytes of bandwidth savings per year and faster clones (due to smaller transfer size). I don't have detailed numbers to report on decompression. However, zstd decompression is fast: >1 GB/s output throughput on this machine, even through the Python bindings. And it can do that regardless of the compression level of the input. By the time you have enough data to worry about overhead of decompression, you have plenty of other things to worry about performance wise. zstd is wins all around. I can't wait to implement support for it on the wire protocol and in revlogs.
author Gregory Szorc <gregory.szorc@gmail.com>
date Fri, 11 Nov 2016 01:10:07 -0800
parents dd3dd80fca10
children d524c88511a7
line wrap: on
line source

# hgweb/server.py - The standalone hg web server.
#
# Copyright 21 May 2005 - (c) 2005 Jake Edge <jake@edge2.net>
# Copyright 2005-2007 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import errno
import os
import socket
import sys
import traceback

from ..i18n import _

from .. import (
    error,
    util,
)

httpservermod = util.httpserver
socketserver = util.socketserver
urlerr = util.urlerr
urlreq = util.urlreq

from . import (
    common,
)

def _splitURI(uri):
    """Return path and query that has been split from uri

    Just like CGI environment, the path is unquoted, the query is
    not.
    """
    if '?' in uri:
        path, query = uri.split('?', 1)
    else:
        path, query = uri, ''
    return urlreq.unquote(path), query

class _error_logger(object):
    def __init__(self, handler):
        self.handler = handler
    def flush(self):
        pass
    def write(self, str):
        self.writelines(str.split('\n'))
    def writelines(self, seq):
        for msg in seq:
            self.handler.log_error("HG error:  %s", msg)

class _httprequesthandler(httpservermod.basehttprequesthandler):

    url_scheme = 'http'

    @staticmethod
    def preparehttpserver(httpserver, ui):
        """Prepare .socket of new HTTPServer instance"""
        pass

    def __init__(self, *args, **kargs):
        self.protocol_version = 'HTTP/1.1'
        httpservermod.basehttprequesthandler.__init__(self, *args, **kargs)

    def _log_any(self, fp, format, *args):
        fp.write("%s - - [%s] %s\n" % (self.client_address[0],
                                       self.log_date_time_string(),
                                       format % args))
        fp.flush()

    def log_error(self, format, *args):
        self._log_any(self.server.errorlog, format, *args)

    def log_message(self, format, *args):
        self._log_any(self.server.accesslog, format, *args)

    def log_request(self, code='-', size='-'):
        xheaders = []
        if util.safehasattr(self, 'headers'):
            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 do_write(self):
        try:
            self.do_hgweb()
        except socket.error as inst:
            if inst[0] != errno.EPIPE:
                raise

    def do_POST(self):
        try:
            self.do_write()
        except Exception:
            self._start_response("500 Internal Server Error", [])
            self._write("Internal Server Error")
            self._done()
            tb = "".join(traceback.format_exception(*sys.exc_info()))
            self.log_error("Exception happened during processing "
                           "request '%s':\n%s", self.path, tb)

    def do_GET(self):
        self.do_POST()

    def do_hgweb(self):
        path, query = _splitURI(self.path)

        env = {}
        env['GATEWAY_INTERFACE'] = 'CGI/1.1'
        env['REQUEST_METHOD'] = self.command
        env['SERVER_NAME'] = self.server.server_name
        env['SERVER_PORT'] = str(self.server.server_port)
        env['REQUEST_URI'] = self.path
        env['SCRIPT_NAME'] = self.server.prefix
        env['PATH_INFO'] = path[len(self.server.prefix):]
        env['REMOTE_HOST'] = self.client_address[0]
        env['REMOTE_ADDR'] = self.client_address[0]
        if query:
            env['QUERY_STRING'] = query

        if self.headers.typeheader is None:
            env['CONTENT_TYPE'] = self.headers.type
        else:
            env['CONTENT_TYPE'] = self.headers.typeheader
        length = self.headers.getheader('content-length')
        if length:
            env['CONTENT_LENGTH'] = length
        for header in [h for h in self.headers.keys()
                       if h not in ('content-type', 'content-length')]:
            hkey = 'HTTP_' + header.replace('-', '_').upper()
            hval = self.headers.getheader(header)
            hval = hval.replace('\n', '').strip()
            if hval:
                env[hkey] = hval
        env['SERVER_PROTOCOL'] = self.request_version
        env['wsgi.version'] = (1, 0)
        env['wsgi.url_scheme'] = self.url_scheme
        if env.get('HTTP_EXPECT', '').lower() == '100-continue':
            self.rfile = common.continuereader(self.rfile, self.wfile.write)

        env['wsgi.input'] = self.rfile
        env['wsgi.errors'] = _error_logger(self)
        env['wsgi.multithread'] = isinstance(self.server,
                                             socketserver.ThreadingMixIn)
        env['wsgi.multiprocess'] = isinstance(self.server,
                                              socketserver.ForkingMixIn)
        env['wsgi.run_once'] = 0

        self.saved_status = None
        self.saved_headers = []
        self.sent_headers = False
        self.length = None
        self._chunked = None
        for chunk in self.server.application(env, self._start_response):
            self._write(chunk)
        if not self.sent_headers:
            self.send_headers()
        self._done()

    def send_headers(self):
        if not self.saved_status:
            raise AssertionError("Sending headers before "
                                 "start_response() called")
        saved_status = self.saved_status.split(None, 1)
        saved_status[0] = int(saved_status[0])
        self.send_response(*saved_status)
        self.length = None
        self._chunked = False
        for h in self.saved_headers:
            self.send_header(*h)
            if h[0].lower() == 'content-length':
                self.length = int(h[1])
        if (self.length is None and
            saved_status[0] != common.HTTP_NOT_MODIFIED):
            self._chunked = (not self.close_connection and
                             self.request_version == "HTTP/1.1")
            if self._chunked:
                self.send_header('Transfer-Encoding', 'chunked')
            else:
                self.send_header('Connection', 'close')
        self.end_headers()
        self.sent_headers = True

    def _start_response(self, http_status, headers, exc_info=None):
        code, msg = http_status.split(None, 1)
        code = int(code)
        self.saved_status = http_status
        bad_headers = ('connection', 'transfer-encoding')
        self.saved_headers = [h for h in headers
                              if h[0].lower() not in bad_headers]
        return self._write

    def _write(self, data):
        if not self.saved_status:
            raise AssertionError("data written before start_response() called")
        elif not self.sent_headers:
            self.send_headers()
        if self.length is not None:
            if len(data) > self.length:
                raise AssertionError("Content-length header sent, but more "
                                     "bytes than specified are being written.")
            self.length = self.length - len(data)
        elif self._chunked and data:
            data = '%x\r\n%s\r\n' % (len(data), data)
        self.wfile.write(data)
        self.wfile.flush()

    def _done(self):
        if self._chunked:
            self.wfile.write('0\r\n\r\n')
            self.wfile.flush()

class _httprequesthandlerssl(_httprequesthandler):
    """HTTPS handler based on Python's ssl module"""

    url_scheme = 'https'

    @staticmethod
    def preparehttpserver(httpserver, ui):
        try:
            from .. import sslutil
            sslutil.modernssl
        except ImportError:
            raise error.Abort(_("SSL support is unavailable"))

        certfile = ui.config('web', 'certificate')

        # These config options are currently only meant for testing. Use
        # at your own risk.
        cafile = ui.config('devel', 'servercafile')
        reqcert = ui.configbool('devel', 'serverrequirecert')

        httpserver.socket = sslutil.wrapserversocket(httpserver.socket,
                                                     ui,
                                                     certfile=certfile,
                                                     cafile=cafile,
                                                     requireclientcert=reqcert)

    def setup(self):
        self.connection = self.request
        self.rfile = socket._fileobject(self.request, "rb", self.rbufsize)
        self.wfile = socket._fileobject(self.request, "wb", self.wbufsize)

try:
    import threading
    threading.activeCount() # silence pyflakes and bypass demandimport
    _mixin = socketserver.ThreadingMixIn
except ImportError:
    if util.safehasattr(os, "fork"):
        _mixin = socketserver.ForkingMixIn
    else:
        class _mixin(object):
            pass

def openlog(opt, default):
    if opt and opt != '-':
        return open(opt, 'a')
    return default

class MercurialHTTPServer(_mixin, httpservermod.httpserver, object):

    # SO_REUSEADDR has broken semantics on windows
    if os.name == 'nt':
        allow_reuse_address = 0

    def __init__(self, ui, app, addr, handler, **kwargs):
        httpservermod.httpserver.__init__(self, addr, handler, **kwargs)
        self.daemon_threads = True
        self.application = app

        handler.preparehttpserver(self, ui)

        prefix = ui.config('web', 'prefix', '')
        if prefix:
            prefix = '/' + prefix.strip('/')
        self.prefix = prefix

        alog = openlog(ui.config('web', 'accesslog', '-'), ui.fout)
        elog = openlog(ui.config('web', 'errorlog', '-'), ui.ferr)
        self.accesslog = alog
        self.errorlog = elog

        self.addr, self.port = self.socket.getsockname()[0:2]
        self.fqaddr = socket.getfqdn(addr[0])

class IPv6HTTPServer(MercurialHTTPServer):
    address_family = getattr(socket, 'AF_INET6', None)
    def __init__(self, *args, **kwargs):
        if self.address_family is None:
            raise error.RepoError(_('IPv6 is not available on this system'))
        super(IPv6HTTPServer, self).__init__(*args, **kwargs)

def create_server(ui, app):

    if ui.config('web', 'certificate'):
        handler = _httprequesthandlerssl
    else:
        handler = _httprequesthandler

    if ui.configbool('web', 'ipv6'):
        cls = IPv6HTTPServer
    else:
        cls = MercurialHTTPServer

    # ugly hack due to python issue5853 (for threaded use)
    try:
        import mimetypes
        mimetypes.init()
    except UnicodeDecodeError:
        # Python 2.x's mimetypes module attempts to decode strings
        # from Windows' ANSI APIs as ascii (fail), then re-encode them
        # as ascii (clown fail), because the default Python Unicode
        # codec is hardcoded as ascii.

        sys.argv # unwrap demand-loader so that reload() works
        reload(sys) # resurrect sys.setdefaultencoding()
        oldenc = sys.getdefaultencoding()
        sys.setdefaultencoding("latin1") # or any full 8-bit encoding
        mimetypes.init()
        sys.setdefaultencoding(oldenc)

    address = ui.config('web', 'address', '')
    port = util.getport(ui.config('web', 'port', 8000))
    try:
        return cls(ui, app, (address, port), handler)
    except socket.error as inst:
        raise error.Abort(_("cannot start server at '%s:%d': %s")
                         % (address, port, inst.args[1]))