From mboxrd@z Thu Jan 1 00:00:00 1970 From: Daniel Borkmann Subject: Re: [PATCH net-next] virtio_net: migrate mergeable rx buffers to page frag allocators Date: Tue, 29 Oct 2013 08:30:53 +0100 Message-ID: <526F642D.5010706@redhat.com> References: <1383000258-1458-1-git-send-email-mwdalton@google.com> <1383002389.4344.7.camel@edumazet-glaptop.roam.corp.google.com> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Cc: Michael Dalton , "David S. Miller" , netdev@vger.kernel.org, Eric Dumazet , Rusty Russell , "Michael S. Tsirkin" , virtualization@lists.linux-foundation.org, Francesco Fusco To: Eric Dumazet Return-path: Received: from mx1.redhat.com ([209.132.183.28]:26163 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751476Ab3J2HbG (ORCPT ); Tue, 29 Oct 2013 03:31:06 -0400 In-Reply-To: <1383002389.4344.7.camel@edumazet-glaptop.roam.corp.google.com> Sender: netdev-owner@vger.kernel.org List-ID: On 10/29/2013 12:19 AM, Eric Dumazet wrote: > On Mon, 2013-10-28 at 15:44 -0700, Michael Dalton wrote: >> The virtio_net driver's mergeable receive buffer allocator >> uses 4KB packet buffers. For MTU-sized traffic, SKB truesize >> is > 4KB but only ~1500 bytes of the buffer is used to store >> packet data, reducing the effective TCP window size >> substantially. This patch addresses the performance concerns >> with mergeable receive buffers by allocating MTU-sized packet >> buffers using page frag allocators. If more than MAX_SKB_FRAGS >> buffers are needed, the SKB frag_list is used. >> >> Signed-off-by: Michael Dalton >> --- > > Signed-off-by: Eric Dumazet > > Daniel & Francesco, this should address the performance problem you > tried to address with ("tcp: rcvbuf autotuning improvements") That's awesome, thanks everyone ! > ( http://www.spinics.net/lists/netdev/msg252642.html ) > > Thanks !