From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760003AbXHXPid (ORCPT ); Fri, 24 Aug 2007 11:38:33 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1757282AbXHXPiL (ORCPT ); Fri, 24 Aug 2007 11:38:11 -0400 Received: from netops-testserver-4-out.sgi.com ([192.48.171.29]:43712 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1758721AbXHXPiJ (ORCPT ); Fri, 24 Aug 2007 11:38:09 -0400 From: akepner@sgi.com Date: Fri, 24 Aug 2007 08:37:03 -0700 To: Jan-Bernd Themann Cc: netdev , Christoph Raisch , Jan-Bernd Themann , linux-kernel , linux-ppc , Marcus Eder , Thomas Klein , Stefan Roscher Subject: Re: RFC: issues concerning the next NAPI interface Message-ID: <20070824153703.GN5592@sgi.com> References: <200708241559.17055.ossthema@de.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <200708241559.17055.ossthema@de.ibm.com> User-Agent: Mutt/1.4.1i Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Aug 24, 2007 at 03:59:16PM +0200, Jan-Bernd Themann wrote: > ....... > 3) On modern systems the incoming packets are processed very fast. Especially >    on SMP systems when we use multiple queues we process only a few packets >    per napi poll cycle. So NAPI does not work very well here and the interrupt >    rate is still high. What we need would be some sort of timer polling mode >    which will schedule a device after a certain amount of time for high load >    situations. With high precision timers this could work well. Current >    usual timers are too slow. A finer granularity would be needed to keep the > latency down (and queue length moderate). > We found the same on ia64-sn systems with tg3 a couple of years ago. Using simple interrupt coalescing ("don't interrupt until you've received N packets or M usecs have elapsed") worked reasonably well in practice. If your h/w supports that (and I'd guess it does, since it's such a simple thing), you might try it. -- Arthur