Re: [Qemu-devel] [PATCH v2 2/4] nvdimm: warn if the backend is not a DAX device

2017-06-11 Thread Michael S. Tsirkin
On Mon, Jun 12, 2017 at 11:18:21AM +0800, Haozhong Zhang wrote: > On 06/08/17 15:51 +0300, Michael S. Tsirkin wrote: > > On Tue, Jun 06, 2017 at 03:22:27PM +0800, Haozhong Zhang wrote: > > > Applications in Linux guest that use device-dax never trigger flush > > > that can be trapped by KVM/QEMU.

Re: [Qemu-devel] [PATCH v2 2/4] nvdimm: warn if the backend is not a DAX device

2017-06-11 Thread Haozhong Zhang
On 06/08/17 15:51 +0300, Michael S. Tsirkin wrote: > On Tue, Jun 06, 2017 at 03:22:27PM +0800, Haozhong Zhang wrote: > > Applications in Linux guest that use device-dax never trigger flush > > that can be trapped by KVM/QEMU. Meanwhile, if the host backend is not > > device-dax, QEMU cannot

Re: [Qemu-devel] [PATCH v2 2/4] nvdimm: warn if the backend is not a DAX device

2017-06-08 Thread Michael S. Tsirkin
On Tue, Jun 06, 2017 at 03:22:27PM +0800, Haozhong Zhang wrote: > Applications in Linux guest that use device-dax never trigger flush > that can be trapped by KVM/QEMU. Meanwhile, if the host backend is not > device-dax, QEMU cannot guarantee the persistence of guest writes. > Before solving this

Re: [Qemu-devel] [PATCH v2 2/4] nvdimm: warn if the backend is not a DAX device

2017-06-07 Thread Haozhong Zhang
On 06/07/17 16:14 +0100, Stefan Hajnoczi wrote: > On Tue, Jun 06, 2017 at 03:22:27PM +0800, Haozhong Zhang wrote: > > diff --git a/util/osdep.c b/util/osdep.c > > index a2863c8e53..02881f96bc 100644 > > --- a/util/osdep.c > > +++ b/util/osdep.c > > @@ -471,3 +471,64 @@ writev(int fd, const struct

Re: [Qemu-devel] [PATCH v2 2/4] nvdimm: warn if the backend is not a DAX device

2017-06-07 Thread Haozhong Zhang
On 06/06/17 10:59 -0700, Dan Williams wrote: > On Tue, Jun 6, 2017 at 12:22 AM, Haozhong Zhang > wrote: > > Applications in Linux guest that use device-dax never trigger flush > > that can be trapped by KVM/QEMU. Meanwhile, if the host backend is not > > device-dax, QEMU

Re: [Qemu-devel] [PATCH v2 2/4] nvdimm: warn if the backend is not a DAX device

2017-06-07 Thread Stefan Hajnoczi
On Tue, Jun 06, 2017 at 03:22:27PM +0800, Haozhong Zhang wrote: > diff --git a/util/osdep.c b/util/osdep.c > index a2863c8e53..02881f96bc 100644 > --- a/util/osdep.c > +++ b/util/osdep.c > @@ -471,3 +471,64 @@ writev(int fd, const struct iovec *iov, int iov_cnt) > return readv_writev(fd, iov,

Re: [Qemu-devel] [PATCH v2 2/4] nvdimm: warn if the backend is not a DAX device

2017-06-06 Thread Dan Williams
On Tue, Jun 6, 2017 at 12:22 AM, Haozhong Zhang wrote: > Applications in Linux guest that use device-dax never trigger flush > that can be trapped by KVM/QEMU. Meanwhile, if the host backend is not > device-dax, QEMU cannot guarantee the persistence of guest writes. >

[Qemu-devel] [PATCH v2 2/4] nvdimm: warn if the backend is not a DAX device

2017-06-06 Thread Haozhong Zhang
Applications in Linux guest that use device-dax never trigger flush that can be trapped by KVM/QEMU. Meanwhile, if the host backend is not device-dax, QEMU cannot guarantee the persistence of guest writes. Before solving this flushing problem, QEMU should warn users if the host backend is not