From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bruce Richardson Subject: Re: segmented recv ixgbevf Date: Thu, 30 Oct 2014 11:09:57 +0000 Message-ID: <20141030110956.GA8456@bricha3-MOBL3> References: Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: "dev-VfR2kkLFssw@public.gmane.org" To: Alex Markuze Return-path: Content-Disposition: inline In-Reply-To: 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 Thu, Oct 30, 2014 at 12:23:09PM +0200, Alex Markuze wrote: > Hi, > I'm seeing an unwanted behaviour in the receive flow of ixgbevf. While > using Jumbo frames and sending 4k+ bytes , the receive side breaks up the > packets into 2K buffers, and I receive 3 mbuffs per packet. > > Im setting the .max_rx_pkt_len to 4.5K and the mempoll has 5K sized > elements? > > Anything else I'm missing here. The purpose is to have all 4k+ bytes in one > single continuous buffer. > That should be working, I think. Does it work with the plain ixgbe driver on the host? Is there anything in the output of the driver initialization saying something like "forcing scatter mode"?