From mboxrd@z Thu Jan 1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:40381)
by lists.gnu.org with esmtp (Exim 4.71)
(envelope-from
) id 1ZzOAB-0000XL-LJ
for qemu-devel@nongnu.org; Thu, 19 Nov 2015 07:18:11 -0500
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
(envelope-from ) id 1ZzOA6-0007fG-M2
for qemu-devel@nongnu.org; Thu, 19 Nov 2015 07:18:07 -0500
Received: from mailout4.w1.samsung.com ([210.118.77.14]:46386)
by eggs.gnu.org with esmtp (Exim 4.71)
(envelope-from ) id 1ZzOA6-0007ex-GS
for qemu-devel@nongnu.org; Thu, 19 Nov 2015 07:18:02 -0500
Received: from eucpsbgm1.samsung.com (unknown [203.254.199.244])
by mailout4.w1.samsung.com
(Oracle Communications Messaging Server 7.0.5.31.0 64bit (built May 5
2014)) with ESMTP id <0NY2003IRA5ZOX00@mailout4.w1.samsung.com> for
qemu-devel@nongnu.org; Thu, 19 Nov 2015 12:17:59 +0000 (GMT)
From: Pavel Fedin
References: <011b01d122af$c60f7ce0$522e76a0$@samsung.com>
<20151119125348-mutt-send-email-mst@redhat.com>
<014b01d122bf$ab73dc90$025b95b0$@samsung.com>
<20151119135725-mutt-send-email-mst@redhat.com>
<564DBB39.3010207@redhat.com>
In-reply-to: <564DBB39.3010207@redhat.com>
Date: Thu, 19 Nov 2015 15:17:57 +0300
Message-id: <014e01d122c4$54073d30$fc15b790$@samsung.com>
MIME-version: 1.0
Content-type: text/plain; charset=us-ascii
Content-transfer-encoding: 7bit
Content-language: ru
Subject: Re: [Qemu-devel] [PATCH] virtio: Implement userspace forwarding for
host notifiers
List-Id:
List-Unsubscribe: ,
List-Archive:
List-Post:
List-Help:
List-Subscribe: ,
To: 'Paolo Bonzini' , "'Michael S. Tsirkin'"
Cc: 'Cornelia Huck' , 'Christian Borntraeger' , qemu-devel@nongnu.org
Hello!
> > Paolo, do you see anything wrong with making
> > memory_region_add_eventfd work (slowly) without kvm ioeventfd support?
> >
>
> Sure, it's even been on the todo list for a while. Stefan Hajnoczi had
> a patch, the only ugly thing was that it slowed down a little all
> non-ioeventfd accesses, but I guess that's okay because it's probably
> not measurable.
>
> http://lists.nongnu.org/archive/html/qemu-devel/2015-07/msg04710.html
Ok, good. So, this has already been tested. Ok, i think i can further extend this patch by:
1. Add a flag to disable memory_region_dispatch_write_ioeventfds(), to be set by KVM code for example. So that with KVM we have even
smaller performance degradation.
2. Issue a one-shot warning, like in my current patch, so that the user knows that his/her kernel prevents from getting the best
performance.
Will it be OK then?
Cc'ed also Cornelia because he's taking part in CCW discussion. And the same kind of generic event forwarding could be implemented
for CCW then.
Kind regards,
Pavel Fedin
Expert Engineer
Samsung Electronics Research center Russia