From mboxrd@z Thu Jan 1 00:00:00 1970 From: Amir Vadai Subject: Re: [PATCH net-next 4/7] net/mlx4_en: Set carrier to off when a port is stopped Date: Thu, 17 Jan 2013 09:04:08 +0200 Message-ID: <50F7A268.1090708@mellanox.com> References: <1358350935-3281-1-git-send-email-amirv@mellanox.com> <1358350935-3281-5-git-send-email-amirv@mellanox.com> <1358352016.2923.15.camel@bwh-desktop.uk.solarflarecom.com> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8"; format=flowed Content-Transfer-Encoding: 7bit Cc: "David S. Miller" , , "Or Gerlitz" , Eugenia Emantayev To: Ben Hutchings Return-path: Received: from eu1sys200aog113.obsmtp.com ([207.126.144.135]:47395 "HELO eu1sys200aog113.obsmtp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1759191Ab3AQHDf (ORCPT ); Thu, 17 Jan 2013 02:03:35 -0500 In-Reply-To: <1358352016.2923.15.camel@bwh-desktop.uk.solarflarecom.com> Sender: netdev-owner@vger.kernel.org List-ID: On 16/01/2013 18:00, Ben Hutchings wrote: > On Wed, 2013-01-16 at 17:42 +0200, Amir Vadai wrote: >> >From: Eugenia Emantayev >> > >> >Under heavy CPU load changing ring size/mtu/etc. could result in transmit >> >timeout, since stop-start port might take more than 10 sec. Set >> >netif_carrier_off to prevent tx queue transmit timeout. > A spurious link change can restart L3 auto-configuration (DHCP, SLAAC, > etc.) netif_device_detach() also inhibits the watchdog and doesn't have > that problem. > > Ben. > Thanks, Ben. I will change it to netif_device_attach(). Since this will need some testing, will resend the patchset without this patch for now. Amir.