[Bulk] [CentOS] hda dma seek errors

Bryan J. Smith b.j.smith at ieee.org
Wed Aug 3 13:22:04 UTC 2005


BRUCE STANLEY wrote:
> How did you go about disabling dma?

Typically it's:  
  # hdparm -d 0 /dev/hdX

Manuel BERTRAND <manuel.bertrand at lif.univ-mrs.fr> wrote:
> Change your IDE cable, be happy.
> (old IDE have fewer wire)

Well, it all depends.

Normally during POST, if the BIOS detects an UltraDMA Mode
3** (50MBps**) or higher** signaling, and the cable is not
augmented with 40 ground wires (the 80-conductor type), it is
supposed to reduce the signaling to UltraDMA Mode 2 (33MBps).
 But the OS and/or drive might optimize its signaling to a
higher rate once the kernel loads, or at boot-time
optimization.

[ **NOTE:  UltraDMA mode 3 (50MBps) and 4 (66MBps) are
commonly referred to as Ultra66 ]

But it could be a variety of problems:  
- Cable used (40-pin v. 40-pin+40-ground aka "Ultra66 cable")
- Multiple ATA devices on a channel conflicting
- Hdparm optimizing the ATA channel and IDE disk incorrectly
- Many, many others

But in every case I had, when the drive _had_ worked prior
without issue, it was a kernel upgrade and that ATA driver. 
As I mentioned before, there have been many documented cases
of this, as well as the politics of the ATA code in the
kernel (around 2.4.18-19 IIRC).


-- 
Bryan J. Smith                | Sent from Yahoo Mail
mailto:b.j.smith at ieee.org     |  (please excuse any
http://thebs413.blogspot.com/ |   missing headers)



More information about the CentOS mailing list