From mboxrd@z Thu Jan 1 00:00:00 1970 From: Nicolas Ferre Subject: Re: [PATCH 3/3 v3] net/macb: Try to optimize struct macb layout Date: Tue, 28 May 2013 10:08:40 +0200 Message-ID: <51A46608.2020906@atmel.com> References: Mime-Version: 1.0 Content-Type: text/plain; charset="windows-1252"; format=flowed Content-Transfer-Encoding: 7bit Cc: , , Jean-Christophe PLAGNIOL-VILLARD , , , , , Havard Skinnemoen , Ben Hutchings To: David Laight , "David S. Miller" , Return-path: In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On 15/05/2013 11:37, David Laight : >> From: Havard Skinnemoen > >> Move the NAPI struct below that since it is used >> from the interrupt handler. This field is also marked as >> ___cacheline_aligned_in_smp. > > Is that a good idea if the cache line size is 256 bytes? > Indeed is that ever sane - except for a few special structures > that really need it, and are guaranteed to be allocated > with that much alignment. I do not know if that was really needed, it was a recommendation by Ben. (previous email here: https://patchwork.kernel.org/patch/1887101/ ) Anyway, it seems that this patch needs more work whereas the others of the series are not commented. So maybe, I can resend patches 1, 2 for making this big enhancement go forward (as it is in review process for quite a long time...). David, do you want me to resend or can you retrieve these v3 patches in patchwork? Best regards, -- Nicolas Ferre