From: Nicholas Bellinger
Hi MST, MKP, Paolo & Co,
The following is an initial RFC series for allowing vhost/scsi to
accept T10 protection information (PI) as seperate SGLs along side
existing data payload SGLs from within virtio-scsi guest memory.
In it's current form, both ends are using virti
On Mon, Feb 24, 2014 at 05:32:24AM +, Nicholas A. Bellinger wrote:
> From: Nicholas Bellinger
>
> Hi MST, MKP, Paolo & Co,
>
> The following is an initial RFC series for allowing vhost/scsi to
> accept T10 protection information (PI) as seperate SGLs along side
> existing data payload SGLs f
Il 24/02/2014 06:32, Nicholas A. Bellinger ha scritto:
AFAICT up until this point the ->prio field has been unused, but
I'm certainly open to better ways of signaling (to vhost) that some
number of metadata iovs are to be expected.. Any thoughts..?
Hi nab,
the virtio-scsi side of the patch is
On Mon, 2014-02-24 at 11:23 +0100, Paolo Bonzini wrote:
> Il 24/02/2014 06:32, Nicholas A. Bellinger ha scritto:
> > AFAICT up until this point the ->prio field has been unused, but
> > I'm certainly open to better ways of signaling (to vhost) that some
> > number of metadata iovs are to be expecte
> "nab" == Nicholas A Bellinger writes:
nab> Mmm, at least for PI I don't think a residual field is necessary.
nab> Any time the metadata is not fully read on outgoing WRITEs, or
nab> written on incoming READs the next hop performing a VERIFY
nab> operation will end up failing with a GUARD o