Re: Playing with SATA NCQ

[Jeff Garzik <jgarzik@pobox.com>]

Erik Slagter wrote:
> On Sun, 2005-05-29 at 12:34 -0400, Jeff Garzik wrote:
> 
>>>>Now, this patch is not complete. It should work and work well, but error
>>>>handling isn't really tested or finished yet (by any stretch of the
>>>>imagination). So don't use this on a production machine, it _should_ be
>>>>safe to use on your test boxes and for-fun workstations though (I run it
>>>>here...). I have tested on ich6 and ich7 generation ahci, and with
>>>>Maxtor and Seagate drives.
>>>
>>>Is this supposed to work on ICH7 in legacy mode as well?
>>
>>Nope.  ata_piix does not support NCQ (because the h/w doesn't support).
> 
> 
> If I understand this correctly: NCQ does not work on ICH7 in native mode
> (using ata_piix) because in this mode there is no NCQ available, right?

To be more specific, there are these modes:

	legacy mode		no NCQ
	combined mode		no NCQ
	native mode		no NCQ
	AHCI mode		NCQ


>>>Another question: is there a fundamental problem to have the ICH6/7
>>>enabled AHCI mode by the kernel instead of the BIOS? I know some BIOSes
>>>don't offer the choice to enable AHCI (like mine :-().
>>
>>Not a problem.  You just don't get to use AHCI and such.
> 
> 
> Huh?
> 
> My question was if there is a fundamental reason why the AHCI mode of
> the ICH6/7 must be enabled by the BIOS, is there a reason why the kernel
> doesn't do it, or can't do it?

The BIOS sets up PCI resources necessary to use AHCI mode.

	Jeff