On Tue, 20 Sep 2016 11:19:46 +0300 Tariq Toukan <ttoukan.li...@gmail.com> wrote:
> Hi Jesper, > > On 20/09/2016 10:46 AM, Jesper Dangaard Brouer wrote: > > On Mon, 19 Sep 2016 16:58:59 +0300 > > Tariq Toukan <tar...@mellanox.com> wrote: > > > >> From: Saeed Mahameed <sae...@mellanox.com> > >> > >> Previously we rang XDP SQ doorbell on every forwarded XDP packet. > >> > >> Here we introduce a xmit more like mechanism that will queue up more > >> than one packet into SQ (up to RX napi budget) w/o notifying the hardware. > >> > >> Once RX napi budget is consumed and we exit napi RX loop, we will > >> flush (doorbell) all XDP looped packets in case there are such. > > I've already raised strong concerns with this approach on the RFC > > patchset. Of not really taking advantage of RX bulking. > > Please do not ignore this! > > Sure. Your approach can fit with our plans to split the RX completion > poll loop into several stages. > I will try it when we get there. > > > If you can promise, that we/you will also try to other approach I'm > > suggesting, then I'm fine with this patch. I'll take the above as a promise that there are plans to work in the direction I'm requesting. Thanks! Acked-by: Jesper Dangaard Brouer <bro...@redhat.com> -- Best regards, Jesper Dangaard Brouer MSc.CS, Principal Kernel Engineer at Red Hat Author of http://www.iptv-analyzer.org LinkedIn: http://www.linkedin.com/in/brouer
