view mercurial/statichttprepo.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

# statichttprepo.py - simple http repository class for mercurial
#
# This provides read-only repo access to repositories exported via static http
#
# Copyright 2005-2007 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from i18n import _
import changelog, byterange, url, error
import localrepo, manifest, util, scmutil, store
import urllib, urllib2, errno

class httprangereader(object):
    def __init__(self, url, opener):
        # we assume opener has HTTPRangeHandler
        self.url = url
        self.pos = 0
        self.opener = opener
        self.name = url
    def seek(self, pos):
        self.pos = pos
    def read(self, bytes=None):
        req = urllib2.Request(self.url)
        end = ''
        if bytes:
            end = self.pos + bytes - 1
        req.add_header('Range', 'bytes=%d-%s' % (self.pos, end))

        try:
            f = self.opener.open(req)
            data = f.read()
            if hasattr(f, 'getcode'):
                # python 2.6+
                code = f.getcode()
            elif hasattr(f, 'code'):
                # undocumented attribute, seems to be set in 2.4 and 2.5
                code = f.code
            else:
                # Don't know how to check, hope for the best.
                code = 206
        except urllib2.HTTPError, inst:
            num = inst.code == 404 and errno.ENOENT or None
            raise IOError(num, inst)
        except urllib2.URLError, inst:
            raise IOError(None, inst.reason[1])

        if code == 200:
            # HTTPRangeHandler does nothing if remote does not support
            # Range headers and returns the full entity. Let's slice it.
            if bytes:
                data = data[self.pos:self.pos + bytes]
            else:
                data = data[self.pos:]
        elif bytes:
            data = data[:bytes]
        self.pos += len(data)
        return data
    def __iter__(self):
        return iter(self.read().splitlines(1))
    def close(self):
        pass

def build_opener(ui, authinfo):
    # urllib cannot handle URLs with embedded user or passwd
    urlopener = url.opener(ui, authinfo)
    urlopener.add_handler(byterange.HTTPRangeHandler())

    class statichttpopener(scmutil.abstractopener):
        def __init__(self, base):
            self.base = base

        def __call__(self, path, mode="r", atomictemp=None):
            if mode not in ('r', 'rb'):
                raise IOError('Permission denied')
            f = "/".join((self.base, urllib.quote(path)))
            return httprangereader(f, urlopener)

    return statichttpopener

class statichttprepository(localrepo.localrepository):
    def __init__(self, ui, path):
        self._url = path
        self.ui = ui

        self.root = path
        u = util.url(path.rstrip('/') + "/.hg")
        self.path, authinfo = u.authinfo()

        opener = build_opener(ui, authinfo)
        self.opener = opener(self.path)

        # find requirements
        try:
            requirements = self.opener.read("requires").splitlines()
        except IOError, inst:
            if inst.errno != errno.ENOENT:
                raise
            # check if it is a non-empty old-style repository
            try:
                fp = self.opener("00changelog.i")
                fp.read(1)
                fp.close()
            except IOError, inst:
                if inst.errno != errno.ENOENT:
                    raise
                # we do not care about empty old-style repositories here
                msg = _("'%s' does not appear to be an hg repository") % path
                raise error.RepoError(msg)
            requirements = []

        # check them
        for r in requirements:
            if r not in self.supported:
                raise error.RequirementError(
                        _("requirement '%s' not supported") % r)

        # setup store
        self.store = store.store(requirements, self.path, opener)
        self.spath = self.store.path
        self.sopener = self.store.opener
        self.sjoin = self.store.join

        self.manifest = manifest.manifest(self.sopener)
        self.changelog = changelog.changelog(self.sopener)
        self._tags = None
        self.nodetagscache = None
        self._branchcache = None
        self._branchcachetip = None
        self.encodepats = None
        self.decodepats = None
        self.capabilities = self.capabilities.difference(["pushkey"])

    def url(self):
        return self._url

    def local(self):
        return False

    def lock(self, wait=True):
        raise util.Abort(_('cannot lock static-http repository'))

def instance(ui, path, create):
    if create:
        raise util.Abort(_('cannot create new static-http repository'))
    return statichttprepository(ui, path[7:])