Re: ata(4) and NCQ

[Jonathan Stone <kiwi_jonathan%yahoo.com@localhost>]

--- On Tue, 4/19/11, Thor Lancelot Simon <tls%panix.com@localhost> wrote:

> From: Thor Lancelot Simon <tls%panix.com@localhost>
> Subject: Re: ata(4) and NCQ
> To: "Jonathan A. Kollasch" <jakllsch%kollasch.net@localhost>
> Cc: tech-kern%NetBSD.org@localhost, bouyer%NetBSD.org@localhost
> Date: Tuesday, April 19, 2011, 1:13 PM
> On Tue, Apr 19, 2011 at 07:57:56PM
> +0000, Jonathan A. Kollasch wrote:

[....]

> 
> I believe FreeBSD ultimately ended up faking up ATA disks
> to look like
> SCSI ones, and using their existing SCSI midlayer to manage
> tags.

And so, of course, does Linux.

> It would be good to avoid that.  The SCSI code is
> really large.
> 
> However, it does do what's wanted, so perhaps a careful
> examination of
> how it manages tags and openings would be a good first
> step.
> 
> I believe the NCQ rules are much like the SCSI tag ordering
> rules: 

[[ discussion of scsi tags and NCQ]]

Yes, I  believe they NCQ rules are deliberatly like SCSI tagged-queue rules.

> How this maps onto ATA drives and NCQ, I don't know, but
> the overall
> issues and history are worth keeping in mind.

Also that both FreeBSD and Linux took the plunge and handle ATA drives through 
their SCSI mid-layer.  I agree, that code is big; but maybe that alternative is 
worth examiining, too.

--Jonathan