From mboxrd@z Thu Jan 1 00:00:00 1970 From: Arnd Bergmann Subject: Re: [PATCH 1/2]: powerpc/cell spidernet bottom half Date: Thu, 17 Aug 2006 01:03:20 +0200 Message-ID: <200608170103.21097.arnd@arndb.de> References: <44E34825.2020105@garzik.org> <200608162324.47235.arnd@arndb.de> <20060816225558.GM20551@austin.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Cc: Linas Vepstas , akpm@osdl.org, jeff@garzik.org, netdev@vger.kernel.org, jklewis@us.ibm.com, linux-kernel@vger.kernel.org, Jens.Osterkamp@de.ibm.com, David Miller Return-path: Received: from moutng.kundenserver.de ([212.227.126.187]:61660 "EHLO moutng.kundenserver.de") by vger.kernel.org with ESMTP id S932323AbWHPXDY (ORCPT ); Wed, 16 Aug 2006 19:03:24 -0400 To: linuxppc-dev@ozlabs.org In-Reply-To: <20060816225558.GM20551@austin.ibm.com> Content-Disposition: inline Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Am Thursday 17 August 2006 00:55 schrieb Linas Vepstas: > > it only > > seems to be hard to make it go fast using any of them. > > Last round of measurements seemed linear for packet sizes between > 60 and 600 bytes, suggesting that the hardware can handle a > maximum of 120K descriptors/second, independent of packet size. > I don't know why this is. Could well be related to latencies when going to the remote node for descriptor DMAs. Have you tried if the hch's NUMA patch or using numactl makes a difference here? > > sounds like the right approach to simplify the code. > > Its not a big a driver. 'wc' says its 2.3 loc, which > is 1/3 or 1/5 the size of tg3.c or the e1000*c files. Right, I was thinking of removing a lock or another, not throwing out half of the driver ;-) Arnd <><