RE: [t13] ATA-8 APT Teleconference

[Mark Overby]

Title: Re: [t13] ATA-8 APT Teleconference

As I stated in the telecon call, the draft with those changes will be available by the 21st of November. Descriptions of the feature set and IDENTIFY words are in the ATA8-ACS document. My changes are soley to the ATA8-APT document describing the parallel interface. I suggest you read the latest rev of ATA8-ACS. I believe I already noted to Curtis that the IDENTIFY words were now wrong and he was going to fix in the next rev.

 

We have a joint T13 / T10 meeting in January in Phoenix to go over all of the packet material to ensure that it is accurate and correct with reality.

 

I believe the reason it was obsoleted was to simplify ATA8-ACS for ATAPI, but you'd have to ask Curtis for his reasoning behind it - it was his motion to obsolete.

 

There are discussions ongoing about allowing "NCQ" like functionality for packet devices.

---

From: [EMAIL PROTECTED] on behalf of Hale Landis
Sent: Mon 11/14/2005 1:07 PM
To: forum@t13.org
Subject: Re: [t13] ATA-8 APT Teleconference

This message is from the T13 list server.


Mark Overby wrote:
> Answers inline below:

[...]

> *** The feature set(s) as described in clause 4.19 and 4.20  of
> ATA-7.

This is more than an "editorial change"... When will the marked up
versions of all the changes be available? That is changes to 4.19, 4.20,
IDENTIFY data words, PACKET command, SERVICE command, and protocol
diagrams, etc.

> *** Both are being removed. I agree that removing one made no sense
> without removing the other. This was voted on at the April 05 plenary
> meeting and is recorded in the minutes. Curtis Stevens sat in on an
> MMC meeting in March 05 in Dana Point and there as no objection.

OK. But why remove this just for ATAPI? So what if no one implements it.
If this old PATA attempt at 'tagged command queuing' is OK for disk
drives why is it not OK for ATAPI devices?

> *** I fully disagree that the overlap and queuing feature sets have
> not been implemented at the host level. I know of 3 hosts I
> personally have examined that implement this feature set. Queueing
> and overlap is only being removed for packet command set devices.

Just curious... Why is there no 'NCQ' for ATAPI devices? Is this a
continued attempt to 'force' the ATAPI people out of T13 (and SATAIO?)
and make them move to other interfaces (like USB) by restricting what
they can implement?

Hale

--

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