[ovs-dev] [PATCH 2/5] dpif-netdev: Implement the API functions to allow multiple handler threads read upcall.

[Alex Wang]

Hey Yamamoto,

I discussed this with Ben, we want to give it a try.  If there is fairness
issue, we will address it.

Also, there should not be a hard priority of DPIF_UC_MISS over
DPIF_UC_ACTION.
The find_nonempty_queue() should return in a round-robin fashion if both
queues
are non-empty.

Thanks,
Alex Wang,


On Thu, Feb 27, 2014 at 8:06 PM, YAMAMOTO Takashi <yamamoto at valinux.co.jp>wrote:

> > @@ -1452,32 +1507,18 @@ dpif_netdev_queue_to_priority(const struct dpif
> *dpif OVS_UNUSED,
> >      return 0;
> >  }
> >
> > -static struct dp_netdev_queue *
> > -find_nonempty_queue(struct dp_netdev *dp)
> > -    OVS_REQUIRES(dp->queue_mutex)
> > -{
> > -    int i;
> > -
> > -    for (i = 0; i < N_QUEUES; i++) {
> > -        struct dp_netdev_queue *q = &dp->queues[i];
> > -        if (q->head != q->tail) {
> > -            return q;
> > -        }
> > -    }
> > -    return NULL;
> > -}
>
> what's the rationale to remove DPIF_UC_MISS's precedence over
> DPIF_UC_ACTION?
> (just a curious question)
>
> YAMAMOTO Takashi
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.openvswitch.org/pipermail/ovs-dev/attachments/20140228/e71a381f/attachment-0005.html>