From mboxrd@z Thu Jan 1 00:00:00 1970 From: Alexander Duyck Subject: Re: [net-next 05/10] igb: Update igb to use a path similar to ixgbe to determine when to stop Tx Date: Fri, 08 Feb 2013 12:19:29 -0800 Message-ID: <51155DD1.8030500@intel.com> References: <1360319958-10497-6-git-send-email-jeffrey.t.kirsher@intel.com> <1360326369.28557.95.camel@edumazet-glaptop> <511531AE.8030807@intel.com> <20130208.141854.2122874496462368419.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: eric.dumazet@gmail.com, jeffrey.t.kirsher@intel.com, netdev@vger.kernel.org, gospo@redhat.com, sassmann@redhat.com To: David Miller Return-path: Received: from mga09.intel.com ([134.134.136.24]:6742 "EHLO mga09.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S964813Ab3BHUTb (ORCPT ); Fri, 8 Feb 2013 15:19:31 -0500 In-Reply-To: <20130208.141854.2122874496462368419.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: On 2/8/2013 11:18 AM, David Miller wrote: > From: Alexander Duyck > Date: Fri, 08 Feb 2013 09:11:10 -0800 > >> For igb the IGB_MAX_DATA_PER_TXD is 32K as well. So if I am not >> mistaken we should be fine. The only time we risk exceeding that is >> if we have 64K page size. It sounds like we may need to work in the >> ixgbe driver though since I believe the limit for it is only 16K per >> descriptor. >> >> I will also submit an update for this patch that replaces PAGE_SIZE >> with NETDEV_FRAG_PAGE_MAX_SIZE in order to keep the two in sync. > I therefore expect a respin of this series from Jeff once the > update of this patch is resolved. > > Thanks. I will work with Jeff to get that resolved. Also I will be submitting one patch directly it looks like since NETDEV_FRAG_PAGE_MAX_SIZE turns out to be defined in skbuff.c so I will need to pull it into skbuff.h most likely. Thanks, Alex