From mboxrd@z Thu Jan 1 00:00:00 1970 From: Daniel Borkmann Subject: Re: [PATCH net-next] packet: respect devices with LLTX flag in direct xmit Date: Fri, 28 Mar 2014 22:13:40 +0100 Message-ID: <5335E604.4020105@redhat.com> References: <1395934710-29182-1-git-send-email-dborkman@redhat.com> <20140328.165058.1610297081920676758.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, brouer@redhat.com To: David Miller Return-path: Received: from mx1.redhat.com ([209.132.183.28]:15702 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753192AbaC1VNn (ORCPT ); Fri, 28 Mar 2014 17:13:43 -0400 In-Reply-To: <20140328.165058.1610297081920676758.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: On 03/28/2014 09:50 PM, David Miller wrote: > From: Daniel Borkmann > Date: Thu, 27 Mar 2014 16:38:30 +0100 > >> Quite often it can be useful to test with dummy or similar >> devices as a blackhole sink for skbs. Such devices are only >> equipped with a single txq, but marked as NETIF_F_LLTX as >> they do not require locking their internal queues on xmit >> (or implement locking themselves). Therefore, rather use >> HARD_TX_{UN,}LOCK API, so that NETIF_F_LLTX will be respected. >> >> trafgen mmap/TX_RING example against dummy device with config >> foo: { fill(0xff, 64) } results in the following performance >> improvements for such scenarios on an ordinary Core i7/2.80GHz: > ... >> Signed-off-by: Daniel Borkmann >> Cc: Jesper Dangaard Brouer > > Applied, nice work. > > The only remaining issue is that Eric seems to suggest that a tx > dropped counter bump should be added. Please submit that as a > follow-on if my reading of his feedback is accurate. Yes, will do next week. I think at time of submission we didn't have that yet. :)