From mboxrd@z Thu Jan  1 00:00:00 1970
From: "Michael S. Tsirkin" <mst@redhat.com>
Subject: Re: Having troubles binding an SR-IOV VF to
 uio_pci_generic on Amazon instance
Date: Wed, 30 Sep 2015 23:36:58 +0300
Message-ID: <20150930232841-mutt-send-email-mst@redhat.com>
References: <560ABF25.9030300@cloudius-systems.com>
 <20150929235122-mutt-send-email-mst@redhat.com>
 <20150929144616.4e70b44c@urahara>
 <20150930004714-mutt-send-email-mst@redhat.com>
 <560BBB62.3050502@cloudius-systems.com>
 <20150930102807.6e681bca@urahara>
 <20150930203712-mutt-send-email-mst@redhat.com>
 <20150930104304.7a8c8e56@urahara>
 <20150930212553-mutt-send-email-mst@redhat.com>
 <20150930200049.GC27881@scylladb.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: "dev@dpdk.org" <dev@dpdk.org>
To: Gleb Natapov <gleb@scylladb.com>
Return-path: <dev-bounces@dpdk.org>
Received: from mx1.redhat.com (mx1.redhat.com [209.132.183.28])
 by dpdk.org (Postfix) with ESMTP id 17AF4282
 for <dev@dpdk.org>; Wed, 30 Sep 2015 22:37:03 +0200 (CEST)
Content-Disposition: inline
In-Reply-To: <20150930200049.GC27881@scylladb.com>
List-Id: patches and discussions about DPDK <dev.dpdk.org>
List-Unsubscribe: <http://dpdk.org/ml/options/dev>,
 <mailto:dev-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://dpdk.org/ml/archives/dev/>
List-Post: <mailto:dev@dpdk.org>
List-Help: <mailto:dev-request@dpdk.org?subject=help>
List-Subscribe: <http://dpdk.org/ml/listinfo/dev>,
 <mailto:dev-request@dpdk.org?subject=subscribe>
Errors-To: dev-bounces@dpdk.org
Sender: "dev" <dev-bounces@dpdk.org>

On Wed, Sep 30, 2015 at 11:00:49PM +0300, Gleb Natapov wrote:
> > You are increasing interrupt latency by a huge factor by channeling
> > interrupts through a scheduler.  Let user install an
> > interrupt handler function, and be done with it.
> > 
> Interrupt latency is not always hugely important. If you enter interrupt
> mode only when idle hundred more us on a first packet will not kill you.

It certainly affects worst-case latency.  And if you lower interupt
latency, you can go idle faster, so it affects power too.

> If
> interrupt latency is important then uio may be not the right solution,
> but then neither is vfio.

That's what I'm saying, if you don't need memory isolation you can do
better than just slightly tweak existing drivers.

> --
> 			Gleb.