From mboxrd@z Thu Jan 1 00:00:00 1970 From: Juan Quintela Subject: Re: [PATCHv2] virtio: put last seen used index into ring itself Date: Tue, 18 May 2010 13:26:36 +0200 Message-ID: References: <20100518021315.GA22852@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Rusty Russell , Jiri Pirko , Shirley Ma , Amit Shah , Mark McLoughlin , netdev@vger.kernel.org, linux-kernel@vger.kernel.org, alex.williamson@redhat.com To: "Michael S. Tsirkin" Return-path: Received: from mx1.redhat.com ([209.132.183.28]:1250 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752271Ab0ERL07 (ORCPT ); Tue, 18 May 2010 07:26:59 -0400 In-Reply-To: <20100518021315.GA22852@redhat.com> (Michael S. Tsirkin's message of "Tue, 18 May 2010 05:13:15 +0300") Sender: netdev-owner@vger.kernel.org List-ID: "Michael S. Tsirkin" wrote: > Generally, the Host end of the virtio ring doesn't need to see where > Guest is up to in consuming the ring. However, to completely understand > what's going on from the outside, this information must be exposed. > For example, host can reduce the number of interrupts by detecting > that the guest is currently handling previous buffers. > > Fortunately, we have room to expand: the ring is always a whole number > of pages and there's hundreds of bytes of padding after the avail ring > and the used ring, whatever the number of descriptors (which must be a > power of 2). > > We add a feature bit so the guest can tell the host that it's writing > out the current value there, if it wants to use that. > > This is based on a patch by Rusty Russell, with the main difference > being that we dedicate a feature bit to guest to tell the host it is > writing the used index. This way we don't need to force host to publish > the last available index until we have a use for it. > > Another difference is that while the feature helps virtio-net, > there have been conflicting reports wrt virtio-blk. > The reason is unknown, it could be due to the fact that > virtio-blk does not bother to disable interrupts at all. > So for now, this patch only acks this feature for -net. > > Signed-off-by: Rusty Russell > Signed-off-by: Michael S. Tsirkin It looks good. Later, Juan.