From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: Regarding Routing cache Date: Thu, 17 Nov 2011 08:26:58 +0100 Message-ID: <1321514818.3274.37.camel@edumazet-laptop> References: <1321511214.3274.25.camel@edumazet-laptop> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: netdev To: Ajith Adapa Return-path: Received: from mail-wy0-f174.google.com ([74.125.82.174]:42108 "EHLO mail-wy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752732Ab1KQH1D (ORCPT ); Thu, 17 Nov 2011 02:27:03 -0500 Received: by wyh11 with SMTP id 11so1575893wyh.19 for ; Wed, 16 Nov 2011 23:27:01 -0800 (PST) In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: Please, no private mails on this discussion. I added back netdev on CC. Le jeudi 17 novembre 2011 =C3=A0 12:09 +0530, Ajith Adapa a =C3=A9crit = : > Hi, >=20 > Sorry about my naive post regarding the issue. >=20 > > IPv6 has no routing cache, and wont have one, since we are trying t= o > > remove IPv4 routing cache :) >=20 > But it would have performance issues right as we always check fib > table for destination route ? >=20 > Is there any references or posts or material which takes about the > reason for removing the ipv6 and ipv4 routing caches ? >=20 routing cache doesnt scale and was difficult to tune in some situations= =2E It uses a lot of memory, and doesnt fit in CPU caches. It was a good solution in the past, but better is to get scalable algo in the first place. http://vger.kernel.org/netconf2011.html http://vger.kernel.org/netconf2011_slides/davem_netconf2011.pdf