From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tariq Toukan Subject: Re: [PATCH net-next 9/9] mlx4: add page recycling in receive path Date: Wed, 8 Feb 2017 12:27:05 +0200 Message-ID: <1486a0fa-b098-6990-2246-3a634dfd0a61@gmail.com> References: <20170207030240.31357-1-edumazet@google.com> <20170207030240.31357-10-edumazet@google.com> <92a6e32b-6f0a-88a6-52d3-6ca352c26b22@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Cc: "David S . Miller" , netdev , Tariq Toukan , Martin KaFai Lau , Willem de Bruijn , Jesper Dangaard Brouer , Brenden Blanco , Alexei Starovoitov , Eric Dumazet To: Eric Dumazet Return-path: Received: from mail-wm0-f68.google.com ([74.125.82.68]:33225 "EHLO mail-wm0-f68.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754404AbdBHMXY (ORCPT ); Wed, 8 Feb 2017 07:23:24 -0500 Received: by mail-wm0-f68.google.com with SMTP id v77so32853732wmv.0 for ; Wed, 08 Feb 2017 04:22:37 -0800 (PST) In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: On 07/02/2017 6:34 PM, Eric Dumazet wrote: > On Tue, Feb 7, 2017 at 8:20 AM, Tariq Toukan wrote: >> >> On 07/02/2017 5:02 AM, Eric Dumazet wrote: >>> Same technique than some Intel drivers, for arches where PAGE_SIZE = 4096 >>> >>> In most cases, pages are reused because they were consumed >>> before we could loop around the RX ring. >> This might not be true when multiple streams are handled in the same ring. >> As the process time in stack will be longer. >> We will test this scenario as well. > Sure thing. I already did ;) > > I had a local patch adding a new "ethtool -S ... | grep > rx_page_allocs" counter. > > I could probably add it to the series. I'd always like to have this kind of counters. They make performance analysis much easier. > (I noticed that > rx_alloc_failed was a dead counter) Yes indeed... I'll take care of it. Thanks! > > Thanks.