From mboxrd@z Thu Jan  1 00:00:00 1970
From: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Subject: Re: [PATCH net-next] virtio_net: force_napi_tx module param.
Date: Wed, 1 Aug 2018 11:56:14 -0400
Message-ID: <CAF=yD-Ja-qpQ1BCzdxbg2ZAw4LR62i3wCL6gkspnGyLSohC8Yg@mail.gmail.com>
References: <20180723231119.142904-1-caleb.raitto@gmail.com>
 <20180729.090027.1373538625446665385.davem@davemloft.net> <CAF=yD-+XnL=TowYwdaww7hBkPQek4_cDMSiqo02UaJhKy5PrTA@mail.gmail.com>
 <20180731153204-mutt-send-email-mst@kernel.org> <CAF=yD-JVj9SLNBftB=ut2-duhi4HQdLBByOHJaZDdavLabD+OA@mail.gmail.com>
Mime-Version: 1.0
Content-Type: text/plain; charset="UTF-8"
Cc: David Miller <davem@davemloft.net>, caleb.raitto@gmail.com,
        Jason Wang <jasowang@redhat.com>,
        Network Development <netdev@vger.kernel.org>,
        Caleb Raitto <caraitto@google.com>
To: "Michael S. Tsirkin" <mst@redhat.com>
Return-path: <netdev-owner@vger.kernel.org>
Received: from mail-it0-f65.google.com ([209.85.214.65]:40819 "EHLO
        mail-it0-f65.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S2389682AbeHARnM (ORCPT
        <rfc822;netdev@vger.kernel.org>); Wed, 1 Aug 2018 13:43:12 -0400
Received: by mail-it0-f65.google.com with SMTP id h23-v6so9989196ita.5
        for <netdev@vger.kernel.org>; Wed, 01 Aug 2018 08:56:50 -0700 (PDT)
In-Reply-To: <CAF=yD-JVj9SLNBftB=ut2-duhi4HQdLBByOHJaZDdavLabD+OA@mail.gmail.com>
Sender: netdev-owner@vger.kernel.org
List-ID: <netdev.vger.kernel.org>

> > > > Just distribute across the available cpus evenly, and be done with it.
> > >
> > > Sounds good to me.
> >
> > So e.g. we could set an affinity hint to a group of CPUs that
> > might transmit to this queue.
>
> We also want to set the xps mask for all cpus in the group to this queue.
>
> Is there a benefit over explicitly choosing one cpu from the set, btw?
> I assumed striping. Something along the lines of
>
>   int stripe = max_t(int, num_online_cpus() / vi->curr_queue_pairs, 1);
>   int vq = 0;
>
>   cpumask_clear(xps_mask);
>
>   for_each_online_cpu(cpu) {
>       cpumask_set_cpu(cpu, xps_mask);
>
>       if ((i + 1) % stripe == 0) {
>           virtqueue_set_affinity(vi->rq[vq].vq, cpu);
>           virtqueue_set_affinity(vi->sq[vq].vq, cpu);
>           netif_set_xps_queue(vi->dev, xps_mask, vq);
>           cpumask_clear(xps_mask);
>           vq++;
>      }
>       i++;
>   }

.. but handling edge cases correctly, such as #cpu not being a perfect
multiple of #vq.