This message is from the T13 list server.

I can firmly state that there are at least two host controllers on the
market that support command queuing for ATA devices in hardware. 

-----Original Message-----
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Hale
Landis
Sent: Tuesday, December 07, 2004 2:40 PM
To: [EMAIL PROTECTED]
Subject: Re: [t13] ATAPI Overlap and Queuing

This message is from the T13 list server.


Mark Overby wrote:
> I object to removing queuing. Overlap I don't object to.

Hmmm... Just to make sure we are talking about the same thing and 
because there has been a long-standing confusion...

There are two versions of "overlap"... One version is when a device 
supports queing but the queue depth is only one - this can work on both 
ATA and ATAPI devices. The other version is defined only for ATAPI 
devices and it uses the DSC bit with "immediate" commands.

I say that all forms of queuing (including the case of queuing with a 
queue depth of one) for both ATA and ATAPI devices can/should be made 
obsolete (because I don't think anyone is currently shipping a host 
controller product that can support any form of queuing as defined by 
ATA/ATAPI-x, x=4, 5, 6 or 7). I do not think the non-queuing version of 
overlap (using the DSC bit on ATAPI devices) should be made obsolete.

Hale

-- 

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

Reply via email to