mercurial/sshserver.py

copies: optimize forward copy detection logic for rebases

Forward copy detection (i.e. detecting what files have been moved/copied in
commit X since ancestor Y) previously required diff'ing the manifests of both X
and Y. This was expensive since it required reading both entire manifests and
doing a set difference (they weren't already in a set because of the
lazymanifest work). This cost almost 1 second on very large repositories, and
happens N times for a rebase of N commits.

This patch optimizes it for the case of rebase. In a rebase, we are comparing a
commit against it's immediate parent, and therefore we can know what files
changed by looking at ctx.files().  This lets us drastically decrease the size
of the set comparison, and makes it O(# of changes) instead of O(size of
manifest). This makes it take 1ms instead of 1000ms.

# 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.

from __future__ import absolute_import

import os
import sys

from . import (
    error,
    hook,
    util,
    wireproto,
)

class sshserver(wireproto.abstractserverproto):
    def __init__(self, ui, repo):
        self.ui = ui
        self.repo = repo
        self.lock = None
        self.fin = ui.fin
        self.fout = ui.fout

        hook.redirect(True)
        ui.fout = repo.ui.fout = ui.ferr

        # 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 error.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):
        write = self.fout.write
        for chunk in source.gen:
            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 sendooberror(self, rsp):
        self.ui.ferr.write('%s\n-\n' % rsp.message)
        self.ui.ferr.flush()
        self.fout.write('\n')
        self.fout.flush()

    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,
        wireproto.ooberror: sendooberror,
    }

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