[t13] 04-136r0.pdf SCSI to ATA Command Translations

Eschmann, Michael K michael.k.eschmann at intel.com
Thu Jun 10 17:47:42 PDT 2004

This message is from the T13 list server.

In case you weren't aware, ATA 48-bit "extended" read and write supports
1 to 65536 sectors so the comment about it only supporting 256 sectors
is incorrect.  TTFN, MKE.

-----Original Message-----
From: owner-forum at t13.org [mailto:owner-forum at t13.org] On Behalf Of Jeff
Sent: Thursday, June 10, 2004 4:49 PM
To: Pat LaVarre
Cc: t10 at t10.org; Joerg Schilling; forum at t13.org
Subject: Re: [t13] 04-136r0.pdf SCSI to ATA Command Translations

This message is from the T13 list server.

Pat LaVarre wrote:
> // Jeff G:
>  > My choice in Linux is to simulate MMC-3
>  > version, ...
> Eh?  Linux implements a PDT x00 variation on the MMC-3 that t10.org 
> defines only for PDT x05?

No, I am saying that the libata ATAPI code (some of which you are 
working on :)) will fully simulate an auto-sensing MMC-3 device before I

turn on the code for public use.

>  > For lba28 devices,
>  > Linux limits you to 0xff (actually a tiny bit
>  > less) as expected.
> Linux lba28 max is xFE LBA's per CDB?

ATA lba48 limits you to 256 sectors.

libata limits lba28 devices to 200 sectors, for various reasons.

> Eh??  Read/ write long doesn't work in ATA?

It's no longer defined in the current specs.

>  > > op x88 Read(16) and op x8A Write(16)?
>  >
>  > Linux implements ...
>  > I disagree with the T10 proposal
>  > that it should not be implemented.
> Maybe 64 bit max LBA is happening now in RAID for capacity.

No maybe... it is.  :)

>  > The (12) variants are pointless.
>  > I did not bother to implement them,
>  > since READ/WRITE(16) translation is fully
>  > supported by Linux.
> Pointless why?
> Pointless like the (6) and (10) are pointless because (16) supercedes?
> Pointless because (12) differs from (10) mostly by allowing more 
> LBA/CDB, which merely reduces status/ command overhead, which almost 
> always is already small enough not to matter?

Pointless because (16) exists for when your needs exceed the limits 
provided in (10).

Not enough applications use (12) to justify its support in the


More information about the T10 mailing list