From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:36094) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ajMRq-0003Pt-L5 for qemu-devel@nongnu.org; Fri, 25 Mar 2016 03:46:23 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1ajMRo-0006FC-9Y for qemu-devel@nongnu.org; Fri, 25 Mar 2016 03:46:22 -0400 Received: from mx1.redhat.com ([209.132.183.28]:41877) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ajMRo-0006F5-4J for qemu-devel@nongnu.org; Fri, 25 Mar 2016 03:46:20 -0400 Received: from int-mx14.intmail.prod.int.phx2.redhat.com (int-mx14.intmail.prod.int.phx2.redhat.com [10.5.11.27]) by mx1.redhat.com (Postfix) with ESMTPS id A59CD7F6B1 for ; Fri, 25 Mar 2016 07:46:19 +0000 (UTC) References: <1458537955-8032-1-git-send-email-jasowang@redhat.com> <1458537955-8032-3-git-send-email-jasowang@redhat.com> <56F44F45.7000405@redhat.com> From: Jason Wang Message-ID: <56F4ECC8.7060303@redhat.com> Date: Fri, 25 Mar 2016 15:46:16 +0800 MIME-Version: 1.0 In-Reply-To: <56F44F45.7000405@redhat.com> Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH 2/2] tap: vhost busy polling support List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Eric Blake , mst@redhat.com, qemu-devel@nongnu.org On 03/25/2016 04:34 AM, Eric Blake wrote: > On 03/20/2016 11:25 PM, Jason Wang wrote: >> This patch add the capability of basic vhost net busy polling which is >> supported by recent kernel. User could configure the maximum number of >> us that could be spent on busy polling through a new property of tap >> "vhost_poll_us". >> >> Signed-off-by: Jason Wang >> --- >> +++ b/qapi-schema.json >> @@ -2532,7 +2532,8 @@ >> '*vhostfd': 'str', >> '*vhostfds': 'str', >> '*vhostforce': 'bool', >> - '*queues': 'uint32'} } >> + '*queues': 'uint32', >> + '*vhost_poll_us': 'uint32'} } > Missing documentation. Right. > > New interfaces should prefer '-' over '_'; but this is an existing > interface where we already have 'vnet_hdr', so intra-command consistency > makes your naming okay. > Will change to use '-'. Thanks