view hgext/zeroconf/__init__.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 eecc005229ff
children d4ba4d51f85f
line wrap: on
line source

# zeroconf.py - zeroconf support for Mercurial
#
# 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.
'''discover and advertise repositories on the local network

The zeroconf extension will advertise :hg:`serve` instances over
DNS-SD so that they can be discovered using the :hg:`paths` command
without knowing the server's IP address.

To allow other people to discover your repository using run
:hg:`serve` in your repository::

  $ cd test
  $ hg serve

You can discover Zeroconf-enabled repositories by running
:hg:`paths`::

  $ hg paths
  zc-test = http://example.com:8000/test
'''
from __future__ import absolute_import

import os
import socket
import time

from . import Zeroconf
from mercurial import (
    dispatch,
    encoding,
    extensions,
    hg,
    pycompat,
    rcutil,
    ui as uimod,
)
from mercurial.hgweb import server as servermod

# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = b'ships-with-hg-core'

# publish

server = None
localip = None


def getip():
    # finds external-facing interface without sending any packets (Linux)
    try:
        s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
        s.connect(('1.0.0.1', 0))
        ip = s.getsockname()[0]
        return ip
    except socket.error:
        pass

    # Generic method, sometimes gives useless results
    try:
        dumbip = socket.gethostbyaddr(socket.gethostname())[2][0]
        if ':' in dumbip:
            dumbip = '127.0.0.1'
        if not dumbip.startswith('127.'):
            return dumbip
    except (socket.gaierror, socket.herror):
        dumbip = '127.0.0.1'

    # works elsewhere, but actually sends a packet
    try:
        s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
        s.connect(('1.0.0.1', 1))
        ip = s.getsockname()[0]
        return ip
    except socket.error:
        pass

    return dumbip


def publish(name, desc, path, port):
    global server, localip
    if not server:
        ip = getip()
        if ip.startswith('127.'):
            # if we have no internet connection, this can happen.
            return
        localip = socket.inet_aton(ip)
        server = Zeroconf.Zeroconf(ip)

    hostname = socket.gethostname().split('.')[0]
    host = hostname + ".local"
    name = "%s-%s" % (hostname, name)

    # advertise to browsers
    svc = Zeroconf.ServiceInfo(
        b'_http._tcp.local.',
        pycompat.bytestr(name + '._http._tcp.local.'),
        server=host,
        port=port,
        properties={b'description': desc, b'path': b"/" + path},
        address=localip,
        weight=0,
        priority=0,
    )
    server.registerService(svc)

    # advertise to Mercurial clients
    svc = Zeroconf.ServiceInfo(
        b'_hg._tcp.local.',
        pycompat.bytestr(name + '._hg._tcp.local.'),
        server=host,
        port=port,
        properties={b'description': desc, b'path': b"/" + path},
        address=localip,
        weight=0,
        priority=0,
    )
    server.registerService(svc)


def zc_create_server(create_server, ui, app):
    httpd = create_server(ui, app)
    port = httpd.port

    try:
        repos = app.repos
    except AttributeError:
        # single repo
        with app._obtainrepo() as repo:
            name = app.reponame or os.path.basename(repo.root)
            path = repo.ui.config(b"web", b"prefix", b"").strip(b'/')
            desc = repo.ui.config(b"web", b"description")
            if not desc:
                desc = name
        publish(name, desc, path, port)
    else:
        # webdir
        prefix = app.ui.config(b"web", b"prefix", b"").strip(b'/') + b'/'
        for repo, path in repos:
            u = app.ui.copy()
            if rcutil.use_repo_hgrc():
                u.readconfig(os.path.join(path, b'.hg', b'hgrc'))
            name = os.path.basename(repo)
            path = (prefix + repo).strip(b'/')
            desc = u.config(b'web', b'description')
            if not desc:
                desc = name
            publish(name, desc, path, port)
    return httpd


# listen


class listener(object):
    def __init__(self):
        self.found = {}

    def removeService(self, server, type, name):
        if repr(name) in self.found:
            del self.found[repr(name)]

    def addService(self, server, type, name):
        self.found[repr(name)] = server.getServiceInfo(type, name)


def getzcpaths():
    ip = getip()
    if ip.startswith('127.'):
        return
    server = Zeroconf.Zeroconf(ip)
    l = listener()
    Zeroconf.ServiceBrowser(server, b"_hg._tcp.local.", l)
    time.sleep(1)
    server.close()
    for value in l.found.values():
        name = value.name[: value.name.index(b'.')]
        url = "http://%s:%s%s" % (
            socket.inet_ntoa(value.address),
            value.port,
            value.properties.get("path", "/"),
        )
        yield b"zc-" + name, pycompat.bytestr(url)


def config(orig, self, section, key, *args, **kwargs):
    if section == b"paths" and key.startswith(b"zc-"):
        for name, path in getzcpaths():
            if name == key:
                return path
    return orig(self, section, key, *args, **kwargs)


def configitems(orig, self, section, *args, **kwargs):
    repos = orig(self, section, *args, **kwargs)
    if section == b"paths":
        repos += getzcpaths()
    return repos


def configsuboptions(orig, self, section, name, *args, **kwargs):
    opt, sub = orig(self, section, name, *args, **kwargs)
    if section == b"paths" and name.startswith(b"zc-"):
        # We have to find the URL in the zeroconf paths.  We can't cons up any
        # suboptions, so we use any that we found in the original config.
        for zcname, zcurl in getzcpaths():
            if zcname == name:
                return zcurl, sub
    return opt, sub


def defaultdest(orig, source):
    for name, path in getzcpaths():
        if path == source:
            return name.encode(encoding.encoding)
    return orig(source)


def cleanupafterdispatch(orig, ui, options, cmd, cmdfunc):
    try:
        return orig(ui, options, cmd, cmdfunc)
    finally:
        # we need to call close() on the server to notify() the various
        # threading Conditions and allow the background threads to exit
        global server
        if server:
            server.close()


extensions.wrapfunction(dispatch, b'_runcommand', cleanupafterdispatch)

extensions.wrapfunction(uimod.ui, b'config', config)
extensions.wrapfunction(uimod.ui, b'configitems', configitems)
extensions.wrapfunction(uimod.ui, b'configsuboptions', configsuboptions)
extensions.wrapfunction(hg, b'defaultdest', defaultdest)
extensions.wrapfunction(servermod, b'create_server', zc_create_server)