This message is from the T13 list server.

On Tue, 12 Mar 2002 10:42:55 -0800, [EMAIL PROTECTED] wrote:
>This message is from the T13 list server.

>In the ATA RAID1 (disk mirroring) application, R/W Long has been
>used to perform forced error on the rebuild drive in certain LBA
>(when the host cannot get valid data from the corresponding LBA
>in source drive during the mirror rebuild process).

Raymond: I assume in this case the R/W Long command is being sent to
and executed by the RAID controller (and not by one of attached disk
drives)? In this case the host software is using this R/W Long
command code to trigger some function inside the RAID controller
itself? If the answers are "yes" then the R/W Long command is not
being used to test the ECC correction in the RAID controller or in an
attached disk drive.

As Jim said...  ECC implementation is much different now than
even 10 years ago and it is extremely vendor specific.  Unless
you have talked to the disk drive manufacturer you can not know
if any Write Long can be used to absolutely force a drive to
return an error on a read command.  As Jim said...  If the
function of returning an error on a read of an LBA is required
then we should define a new command that can insure that.  There
have been proposals for such a command in the past (I made one of
those proposals via email a few years ago) but nothing has
happened yet.

>Instead of defining "proprietary vendor-specific extension" to
>deliver this function by each manufacturer for above 128GB
>drives, will it make more sense for T13 to "unify" this efforts?

I agree...  It would be real good if the ATA RAID folks would
bring some proposals to T13...  Good for two reasons:  1) it
would standardize some of the functions needed/used by ATA RAID
controllers and 2) get T13 to think about ATA RAID devices (ATA
would probably have 64-bit LBA now if T13 was more aware of these
RAID products).



*** Hale Landis *** www.ata-atapi.com ***



Reply via email to