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

Jeff Garzik jgarzik at pobox.com
Thu Jun 10 16:49:15 PDT 2004


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 simulator.

	Jeff





More information about the T10 mailing list