From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Loke, Chetan" Subject: RE: Netconf2011 slides... Date: Fri, 17 Jun 2011 14:09:47 -0400 Message-ID: References: <20110615.145937.1748734114172641662.davem@davemloft.net> <4DF9D644.708@linux.vnet.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: "David Miller" , To: "Changli Gao" , "Srinivasa T N" Return-path: Received: from exprod6og107.obsmtp.com ([64.18.1.208]:48800 "HELO exprod6og107.obsmtp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S932104Ab1FQSQ6 convert rfc822-to-8bit (ORCPT ); Fri, 17 Jun 2011 14:16:58 -0400 Content-class: urn:content-classes:message In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: > -----Original Message----- > From: netdev-owner@vger.kernel.org [mailto:netdev- > owner@vger.kernel.org] On Behalf Of Changli Gao > Sent: June 17, 2011 9:22 AM > To: Srinivasa T N > Cc: David Miller; netdev@vger.kernel.org > Subject: Re: Netconf2011 slides... >=20 > On Thu, Jun 16, 2011 at 6:09 PM, Srinivasa T N > wrote: > > =A0 =A0 =A0 =A0Were there some interesting topics which is useful f= or the > community? > > (Few lines on each such topic would do). > > >=20 > netmap was mentioned by Tom. It is interesting for me. >=20 > http://info.iet.unipi.it/~luigi/netmap/ http://lists.openwall.net/netdev/2011/06/08/7 Just curious is there anything that we can do to enhance TPACKET_V3 (ig= nore the memcpy)? Not selling it because I have proposed the patch but anyone who is seri= ous about online/offline packet mining for multiple ports would have hard t= ime scaling with tpacket_v1[2] to begin with. At the very least, one needs block abstraction + timeout mechanism. Sim= ple. One just can't retire data - packet-by-packet. We have boxes capable of mining ~40G with similar approach. Now we can also think about rolling it into a separate driver but then = that's something that is open for discussion. Benefits of a driver are as follows: 1) Folks can customize block/packet headers according to their needs wi= thout having to recompile the kernel. 2) No core network bloat. 3) Smaller NPU/FPGA shops can churn out a new driver patchset relativel= y quickly. >=20 > -- > Regards, > Changli Gao(xiaosuo@gmail.com) Regards Chetan Loke