view mercurial/sshserver.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

# sshserver.py - ssh protocol server support for mercurial
#
# Copyright 2005-2007 Matt Mackall <[e-mail]>
# Copyright 2006 Vadim Gelfer <[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.

import util, hook, wireproto, changegroup
import os, sys

class sshserver(object):
    def __init__(self, ui, repo):
        self.ui = ui
        self.repo = repo
        self.lock = None
        self.fin = sys.stdin
        self.fout = sys.stdout

        hook.redirect(True)
        sys.stdout = sys.stderr

        # Prevent insertion/deletion of CRs
        util.setbinary(self.fin)
        util.setbinary(self.fout)

    def getargs(self, args):
        data = {}
        keys = args.split()
        for n in xrange(len(keys)):
            argline = self.fin.readline()[:-1]
            arg, l = argline.split()
            if arg not in keys:
                raise util.Abort("unexpected parameter %r" % arg)
            if arg == '*':
                star = {}
                for k in xrange(int(l)):
                    argline = self.fin.readline()[:-1]
                    arg, l = argline.split()
                    val = self.fin.read(int(l))
                    star[arg] = val
                data['*'] = star
            else:
                val = self.fin.read(int(l))
                data[arg] = val
        return [data[k] for k in keys]

    def getarg(self, name):
        return self.getargs(name)[0]

    def getfile(self, fpout):
        self.sendresponse('')
        count = int(self.fin.readline())
        while count:
            fpout.write(self.fin.read(count))
            count = int(self.fin.readline())

    def redirect(self):
        pass

    def groupchunks(self, changegroup):
        while True:
            d = changegroup.read(4096)
            if not d:
                break
            yield d

    def sendresponse(self, v):
        self.fout.write("%d\n" % len(v))
        self.fout.write(v)
        self.fout.flush()

    def sendstream(self, source):
        for chunk in source.gen:
            self.fout.write(chunk)
        self.fout.flush()

    def sendpushresponse(self, rsp):
        self.sendresponse('')
        self.sendresponse(str(rsp.res))

    def sendpusherror(self, rsp):
        self.sendresponse(rsp.res)

    def serve_forever(self):
        try:
            while self.serve_one():
                pass
        finally:
            if self.lock is not None:
                self.lock.release()
        sys.exit(0)

    handlers = {
        str: sendresponse,
        wireproto.streamres: sendstream,
        wireproto.pushres: sendpushresponse,
        wireproto.pusherr: sendpusherror,
    }

    def serve_one(self):
        cmd = self.fin.readline()[:-1]
        if cmd and cmd in wireproto.commands:
            rsp = wireproto.dispatch(self.repo, self, cmd)
            self.handlers[rsp.__class__](self, rsp)
        elif cmd:
            impl = getattr(self, 'do_' + cmd, None)
            if impl:
                r = impl()
                if r is not None:
                    self.sendresponse(r)
            else: self.sendresponse("")
        return cmd != ''

    def do_lock(self):
        '''DEPRECATED - allowing remote client to lock repo is not safe'''

        self.lock = self.repo.lock()
        return ""

    def do_unlock(self):
        '''DEPRECATED'''

        if self.lock:
            self.lock.release()
        self.lock = None
        return ""

    def do_addchangegroup(self):
        '''DEPRECATED'''

        if not self.lock:
            self.sendresponse("not locked")
            return

        self.sendresponse("")
        cg = changegroup.unbundle10(self.fin, "UN")
        r = self.repo.addchangegroup(cg, 'serve', self._client(),
                                     lock=self.lock)
        return str(r)

    def _client(self):
        client = os.environ.get('SSH_CLIENT', '').split(' ', 1)[0]
        return 'remote:ssh:' + client