From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stephen Hemminger Subject: Re: [PATCH v2 0/6] link bonding Date: Tue, 2 Sep 2014 11:15:28 -0700 Message-ID: <20140902111528.74aa7928@urahara> References: <1408456313-28812-1-git-send-email-declan.doherty@intel.com> <1409560289-29558-1-git-send-email-declan.doherty@intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: dev-VfR2kkLFssw@public.gmane.org To: Declan Doherty Return-path: In-Reply-To: <1409560289-29558-1-git-send-email-declan.doherty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org> List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces-VfR2kkLFssw@public.gmane.org Sender: "dev" On Mon, 1 Sep 2014 09:31:23 +0100 Declan Doherty wrote: > This patch set adds support for link status interrupt in the link bonding > pmd. It also contains some patches to tidy up the code structure and to > of the link bonding code and to fix bugs relating to transmission > failures in the under lying slave pmd which could lead to leaked mbufs. Does this work when interfaces being bonded do not support link state like VF's and some other virtual devices (like vmxnet3?). I am concerned that the flag to say whether device support LSC or not is in drv_flags which is normally invariant. So either bond has to simulate link state if slave devices do not support (by polling) or provide another mechanism for application to determine availablity of link state.