From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH 2/3] virtio: indirect ring entries (VIRTIO_RING_F_INDIRECT_DESC) Date: Sun, 17 May 2009 18:05:39 +0300 Message-ID: <4A1027C3.3080109@redhat.com> References: <1229620222-22216-1-git-send-email-markmc@redhat.com> <200905171134.31285.rusty@rustcorp.com.au> <4A0FAE35.3040608@redhat.com> <200905172346.14498.rusty@rustcorp.com.au> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Cc: Mark McLoughlin , dlaor@redhat.com, netdev@vger.kernel.org, Dor Laor , virtualization@lists.linux-foundation.org To: Rusty Russell Return-path: Received: from mx2.redhat.com ([66.187.237.31]:38237 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750829AbZEQPFt (ORCPT ); Sun, 17 May 2009 11:05:49 -0400 In-Reply-To: <200905172346.14498.rusty@rustcorp.com.au> Sender: netdev-owner@vger.kernel.org List-ID: Rusty Russell wrote: > On Sun, 17 May 2009 03:57:01 pm Avi Kivity wrote: > >> Rusty Russell wrote: >> >>> +static void adjust_threshold(struct vring_virtqueue *vq, >>> + unsigned int out, unsigned int in) >>> +{ >>> + /* There are really two species of virtqueue, and it matters here. >>> + * If there are no output parts, it's a "normally full" receive queue, >>> + * otherwise it's a "normally empty" send queue. */ >>> >> This comment is true for networking, but not for block. ++overkill with >> a ->adjust_threshold op. >> > > No, it's true for block. It has output parts, so we should reduce threshold > when it's full. Network recvq is an example which should reduce threshold > when it's empty. > You mean the header that contains the sector number? It's a little incidental, but I guess it works. -- error compiling committee.c: too many arguments to function