From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: Fwd: a Great Idea - include Kademlia networking protocol in kernel -- REVISITED Date: Sun, 14 Nov 2010 10:39:04 +0100 Message-ID: <1289727544.2743.72.camel@edumazet-laptop> References: <1289724643.2743.58.camel@edumazet-laptop> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: netdev@vger.kernel.org, Stephen Guerin To: Marcos Return-path: Received: from mail-ww0-f44.google.com ([74.125.82.44]:54359 "EHLO mail-ww0-f44.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754279Ab0KNJjL (ORCPT ); Sun, 14 Nov 2010 04:39:11 -0500 Received: by wwb29 with SMTP id 29so335729wwb.1 for ; Sun, 14 Nov 2010 01:39:10 -0800 (PST) In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: Le dimanche 14 novembre 2010 =C3=A0 02:14 -0700, Marcos a =C3=A9crit : > > I have no idea why and how kademlia would be added to "linux kernel= " > > > > Its a protocol based on UDP, and probably already done on userland. > > > > What am I missing ? >=20 > The idea is to tightly couple it to the operating system to create a > sort of "super operating system" that is seamless to the application > layers above. Just like memory stores are tightly integrated as to b= e > unnoticeable.... >=20 But we dont want a "super operating system". We want a good one. Memory stores done in userland are as fast as memory stores done in kernel. Once you need to access files, perform complex searches, timers, logging, and all the stuff, you really want to do it from userland, in high level language that many programmers master, or get something that is too complex/buggy.