From: Arnd Bergmann Subject: Re: [PATCH 0/21]: powerpc/cell spidernet bugfixes, etc. Date: Wed, 11 Oct 2006 18:02:42 +0200 Message-ID: <200610111802.43996.arnd@arndb.de> References: <20061010204946.GW4381@austin.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: akpm@osdl.org, jeff@garzik.org, James K Lewis , netdev@vger.kernel.org, linux-kernel@vger.kernel.org, linuxppc-dev@ozlabs.org Return-path: Received: from moutng.kundenserver.de ([212.227.126.177]:47297 "EHLO moutng.kundenserver.de") by vger.kernel.org with ESMTP id S1161094AbWJKQDU convert rfc822-to-8bit (ORCPT ); Wed, 11 Oct 2006 12:03:20 -0400 To: Linas Vepstas In-Reply-To: <20061010204946.GW4381@austin.ibm.com> Content-Disposition: inline Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Tuesday 10 October 2006 22:49, Linas Vepstas wrote: > Andrew, please apply/forward upstream. >=20 > The following set of 21 patches (!) are all aimed at the the=20 > spidernet ethernet device driver. The spidernet is an etherenet > controller built into the Toshiba southbridge for the PowerPC Cell > processor. (This is the only device in existance that with this > ethernet hardware in it). >=20 > These patches re-package/re-order/re-cleanup a previous > set of patches I've previously mailed. Thus, some have > been previously Acked-by lines, most do not. Most of > these patches are tiny, and handle problems that cropped > up during testing. Sorry about there being so many of them. >=20 > The first set of 12 patches fix a large variety of mostly=20 > minor bugs.=20 >=20 > The important patches are 13 through 17: these overcome a=20 > debilitating performance problem on transmit (6 megabits > per second !!) on transmit of patches 500 bytes or larger. > After applying these, I am able to get the following: >=20 > pkt sz =A0 speed (100K buffs) =A0 =A0 =A0 speed (4M buffs) > ------ =A0 ----------------- =A0 =A0 =A0 =A0---------------- > 1500 =A0 =A0 700 Mbits/sec =A0 =A0 =A0 =A0 =A0 =A0951 Mbits/sec > 1000 =A0 =A0 658 Mbits/sec =A0 =A0 =A0 =A0 =A0 =A0770 > 800 =A0 =A0 =A0600 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0648 > 500 =A0 =A0 =A0500 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0500 > 300 =A0 =A0 =A0372 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0372 > 60 =A0 =A0 =A0 =A070 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 70 >=20 > Above buf size refers to /proc/sys/net/core/wmem_default Excellent work! I guess this the best tx performance we've seen so far on this hardware. Consider this as an Acked-by: for all the patches, I'll save the effort of replying to each one of them separately. Jeff, do you plan on merging these fixes for 2.6.19? Arnd <><