RE: [t13] Queued DMA Command

[Tony Goodfellow]

Note: Only commands in the “Overlapped/Queued Command Set” may be sent to a device without causing the queue to be aborted. This includes the 00h (NOP) command with any sub-command in the range 01h to FFh.   -----Original Message----- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Eschmann, Michael K Sent: Friday, 22 April, 2005 10:38 To: forum@t13.org Subject: RE: [t13] Queued DMA Command   In d1532v1r4b, volume 1, look at the first paragraph in section 4.20 ("Queued feature set").  It says "If a queue exists when a non-queued command is received, the non-queued command shall be command aborted and the commands in the queue shall be discarded."    The sentence has been there since ATA4.   Happy reading, MKE.     From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Yamini Shastry Sent: Friday, April 22, 2005 9:37 AM To: 'John Masiewicz' Cc: forum@t13.org Subject: [t13] Queued DMA Command   Hello,   On a SATA link with devices that support command queuing, can a DMA QUEUED command (read or write) and a DMA non-queued command be pending at the same time? In other words, Can a SATA Host send a READ DMA QUEUED followed by a READ DMA while the first command is pending?   If not, can anyone point me to the spec that says so?   Thanks, Yamini