From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:56893) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1al6ZU-0000CJ-0t for qemu-devel@nongnu.org; Tue, 29 Mar 2016 23:13:29 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1al6ZQ-00024M-Ns for qemu-devel@nongnu.org; Tue, 29 Mar 2016 23:13:27 -0400 Received: from e37.co.us.ibm.com ([32.97.110.158]:35308) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1al6ZQ-00024I-Fv for qemu-devel@nongnu.org; Tue, 29 Mar 2016 23:13:24 -0400 Received: from localhost by e37.co.us.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Tue, 29 Mar 2016 21:13:23 -0600 Received: from b03cxnp07028.gho.boulder.ibm.com (b03cxnp07028.gho.boulder.ibm.com [9.17.130.15]) by d03dlp02.boulder.ibm.com (Postfix) with ESMTP id 2BC7D3E4087F for ; Tue, 29 Mar 2016 21:04:45 -0600 (MDT) Received: from d03av04.boulder.ibm.com (d03av04.boulder.ibm.com [9.17.195.170]) by b03cxnp07028.gho.boulder.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id u2U34iPg38273038 for ; Tue, 29 Mar 2016 20:04:44 -0700 Received: from d03av04.boulder.ibm.com (loopback [127.0.0.1]) by d03av04.boulder.ibm.com (8.14.4/8.14.4/NCO v10.0 AVout) with ESMTP id u2U34hwa030152 for ; Tue, 29 Mar 2016 21:04:44 -0600 References: <1459258923-10319-1-git-send-email-mst@redhat.com> <56FAADE8.2070708@de.ibm.com> From: tu bo Message-ID: <56FB4248.2030700@linux.vnet.ibm.com> Date: Wed, 30 Mar 2016 11:04:40 +0800 MIME-Version: 1.0 In-Reply-To: <56FAADE8.2070708@de.ibm.com> Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH 0/2] dataplane: fix start/stop races List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Christian Borntraeger , "Michael S. Tsirkin" , qemu-devel@nongnu.org Cc: Cornelia Huck , pbonzini@redhat.com, tubo@cn.ibm.com Hi Christian: On 03/30/2016 12:31 AM, Christian Borntraeger wrote: > On 03/29/2016 03:42 PM, Michael S. Tsirkin wrote: >> This works around races that data plane introduces >> simply by exiting immediately if we detect >> that dataplane is active. >> >> It's a small but ugly patch, it's only justification >> is that it's minimally intrusive, and that it clearly >> has no chance to break non data plane users. >> >> The idea is to rework it all post 2.6. >> >> Michael S. Tsirkin (2): >> virtio: add aio handler >> virtio-blk: use aio handler for data plane >> >> include/hw/virtio/virtio-blk.h | 2 ++ >> include/hw/virtio/virtio.h | 4 ++++ >> hw/block/dataplane/virtio-blk.c | 13 +++++++++++++ >> hw/block/virtio-blk.c | 28 ++++++++++++++++++---------- >> hw/virtio/virtio.c | 36 ++++++++++++++++++++++++++++++++---- >> 5 files changed, 69 insertions(+), 14 deletions(-) >> > > This also seems to help on my setup.Tu Bo, would be good if you > can double check this patch set as well on your setup? With qemu master + [PATCH 0/2] dataplane: fix start/stop races, I did NOT see any crash, result is good in my box. thanks > > Christian > >