From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758466Ab2DYMqZ (ORCPT ); Wed, 25 Apr 2012 08:46:25 -0400 Received: from mail-ey0-f174.google.com ([209.85.215.174]:36822 "EHLO mail-ey0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757239Ab2DYMqW (ORCPT ); Wed, 25 Apr 2012 08:46:22 -0400 Subject: Re: many rx packets dropped since 2.6.37 From: Eric Dumazet To: Chris Cc: linux-kernel@vger.kernel.org In-Reply-To: References: <1335353427.3274.103.camel@edumazet-glaptop> Content-Type: text/plain; charset="UTF-8" Date: Wed, 25 Apr 2012 14:46:15 +0200 Message-ID: <1335357975.3274.187.camel@edumazet-glaptop> Mime-Version: 1.0 X-Mailer: Evolution 2.28.3 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 2012-04-25 at 14:34 +0200, Chris wrote: > Are you sure that these packets are really dropped? I see a lot of > more packets dropped with virtio_net instead of e1000. (KVM > environments) > Yep, we are sure packets are dropped, just read the patch and you'll can see this. > Why do we see dropped packets only in virtual environments and bonded > network interfaces and not on real network interfaces? This has to be investigated, eventually. About the bond, if you are in active-backup mode, a frame coming to inactive device is going to be dropped, or you could have duplication of logical frames. You can use tcpdump to get a copy of these frames.