[Bulk] [CentOS] hda dma seek errors

Johnny Hughes mailing-lists at hughesjr.com
Wed Aug 3 13:24:03 UTC 2005


On Wed, August 3, 2005 8:01 am, BRUCE STANLEY said:
>
>
>
> --- Rohan Walsh <rohan_walsh at yahoo.com.au> wrote:
>
>> On Tue, 2005-08-02 at 23:58 -0400, Kanwar Ranbir Sandhu wrote:
>> > On Tue, 2005-02-08 at 19:57 -0700, BRUCE STANLEY wrote:
>> > > I am getting occasional seek error on my boot drive.
>> > > The messages are as follows:
>> > >
>> > > pshda: dma_intr: status = 0x51 { Drive ReadySeekComplete Error }
>> > >   hda: dma_intr: error= 0x84 { DriveStatusError BadCRC }
>> > >   ide: failed opcode was: unknown
>> >
>> > I've recently seen similar errors on an old server here, and all my
>> > Googling seems to indicate an early sign of imminent drive failure.
>> >
>> > Some people reported resolving the issue by making changes to DMA
>> > settings with hdparm, or changing something in the BIOS.  However, in
>> > most cases, the recommendations were:
>> >
>> > 1. Backup data, ASAP, and wait for failure before moving to new disk
>> > 2. Use fdisk to map out the bad sectors.
>> > 3. Get a new HD, ASAP.
>>
>> I used these errors as a good reason to buy a bigger drive and the new
>> drive had the same error messages. After testing with seagates tool, I
>> can find no problem with either drive. I disable dma as a temporary
>> solution, but I think it is not a drive fault in my case. Do back up :)
>>
>
>
> How did you go about disabling dma?
>
>

You only want to do that as a last resort, it makes your disk IO very slow.

You would change it using hdparm ... the option would be:

hdparm -d0

You can make it happen every reboot by editing the file:

/etc/sysconfig/harddisks

set:

USE_DMA=0

and remove the # in front of it.

AGAIN ... only if absolutely necessary, because it greatly slows down disk
I/O.


-- 
Johnny Hughes
<http://www.HughesJR.com/>




More information about the CentOS mailing list