On 04/10/2018 09:40 AM, Richard W.M. Jones wrote:
>> When the destination is a block device we cannot avoid zeroing since a block
>> device may contain junk data (we usually get dirty empty images from our
>> local
>> xtremio server).
>
> (Off topic for qemu-block but ...) We don't have enough information
> at our end to know about any of this.
Yep, see my other email about a possible NBD protocol extension to
actually let the client learn up-front if the exported device is known
to start in an all-zero state.
In the future we can report all-zero state in OPTIONS, but since this
info is already known on engine side when creating a disk, I think reporting
it in engine is better.
Nir