On 24/05/2016 05:04, Fam Zheng wrote: > On Mon, 05/23 14:54, Paolo Bonzini wrote: > > scsi-block will be able to do FUA just by passing the request through > > to the LUN (which is also more efficient); there is no need to emulate > > it like we do for scsi-disk. > > Even for scsi-disk, shall we just use the block layer FUA fallback already by > passing BDRV_REQ_FUA in blk_aio_pwritev and simply the code in this series?
That's a good idea but it should be done separately, I think. Thanks, Paolo
