From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ingo Oeser Subject: Re: [PATCH 3/3] chelsio: more rx speedup Date: Wed, 10 Jan 2007 09:34:45 +0100 Message-ID: <200701100934.46203.netdev@axxeo.de> References: <20061215190716.956791000@osdl.org> <20070109102647.05d92861@freekitty> <45A44A87.7070202@chelsio.com> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Cc: Stephen Hemminger , Jeff Garzik , netdev@vger.kernel.org Return-path: Received: from mail.axxeo.de ([82.100.226.146]:36808 "EHLO mail.axxeo.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S964785AbXAJIfF (ORCPT ); Wed, 10 Jan 2007 03:35:05 -0500 To: Divy Le Ray In-Reply-To: <45A44A87.7070202@chelsio.com> Content-Disposition: inline Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Divy Le Ray schrieb: > Stephen Hemminger wrote: > > On Tue, 9 Jan 2007 09:42:03 +0100 > > Ingo Oeser wrote: > >> Stephen Hemminger schrieb: > >>> - if (fl->credits < drop_thres) { > >>> +use_orig_buf: > >>> + if (fl->credits < 2) { > >>> > >> Why 2? What does this magic number mean? > > No idea, it was there in the original. (as a parameter). > The T2 HW behaves nicely when it is guaranteed to have 2 available > entries in the rx free list. Can we have a #define for this? That would help people understand this issue more. And don't be shy about errata, all hardware and software out there has them like the humans that made them :-) Regards Ingo Oeser