[gentoo-server] Drive issues or overload

[gentoo-server] Drive issues or overload

[Brett Curtis]

I have several IBM x series servers at work and one of my machines  
drives seem to be acting up a bit. I get a major loss in system time  
and performance.

My dmesg tailed..

hda: dma_timer_expiry: dma status == 0x61
hda: DMA timeout error
hda: dma timeout error: status=0xd0 { Busy }

ide: failed opcode was: unknown
hda: DMA disabled
hdb: DMA disabled
ide0: reset: success
hda: dma_timer_expiry: dma status == 0x21
hda: DMA timeout error
hda: dma timeout error: status=0xd0 { Busy }

ide: failed opcode was: unknown
hda: DMA disabled
ide0: reset: success
hda: dma_timer_expiry: dma status == 0x21
hda: DMA timeout error
hda: dma timeout error: status=0xd0 { Busy }

ide: failed opcode was: unknown
hda: DMA disabled
ide0: reset: success
hda: dma_timer_expiry: dma status == 0x21
hda: DMA timeout error
hda: dma timeout error: status=0xd0 { Busy }

ide: failed opcode was: unknown
hda: DMA disabled
ide0: reset: success
Losing too many ticks!
TSC cannot be used as a timesource.
Possible reasons for this are:
   You're running with Speedstep,
   You don't have DMA enabled for your hard disk (see hdparm),
   Incorrect TSC synchronization on an SMP system (see dmesg).
Falling back to a sane timesource now.
hda: dma_timer_expiry: dma status == 0x21
hda: DMA timeout error
hda: dma timeout error: status=0xd0 { Busy }

ide: failed opcode was: unknown
hda: DMA disabled
ide0: reset: success
spurious 8259A interrupt: IRQ7.


This machine is our continues build environment that builds out  
several instances of our app and is under extreme load at times. I am  
wondering if this is a sign of a bad drive or if this has something  
to do with overload.

I am able to enable dma after the fact with hdparm.  I do not run any  
special hdparm option at boot. The only thing I do is build the ide /  
drive options in to my kernel.

Any suggestions would be great.

Thanks,
Brett
-- 
gentoo-server@gentoo.org mailing list

Re: [gentoo-server] Drive issues or overload

[Ian P. Christian]

[-- Attachment #1: Type: text/plain, Size: 236 bytes --]

On Monday 12 September 2005 14:19, Brett Curtis wrote:
> Any suggestions would be great.

Have you tried using SMART tools to get information from, and test the drive?

Kind Regards,

-- 
Ian P. Christian ~ http://pookey.co.uk

[-- Attachment #2: Type: application/pgp-signature, Size: 189 bytes --]

Re: [gentoo-server] Drive issues or overload

[Brett Curtis]

I emerged ide-smart ran some tests all test seemed to pass.

ide-smart -d /dev/hda

Id=  1  Status=11  {Prefailure  Online }  Value=100  Threshold= 60   
Passed
Id=  2  Status= 5  {Prefailure  OffLine}  Value=100  Threshold= 50   
Passed
Id=  3  Status= 7  {Prefailure  Online }  Value=100  Threshold= 24   
Passed
Id=  4  Status=18  {Advisory    Online }  Value=100  Threshold=  0   
Passed
Id=  5  Status=51  {Prefailure  Online }  Value=100  Threshold=  5   
Passed
Id=  7  Status=11  {Prefailure  Online }  Value=100  Threshold= 67   
Passed
Id=  8  Status= 5  {Prefailure  OffLine}  Value=128  Threshold= 20   
Passed
Id=  9  Status=18  {Advisory    Online }  Value= 99  Threshold=  0   
Passed
Id= 10  Status=19  {Prefailure  Online }  Value=100  Threshold= 60   
Passed
Id= 12  Status=50  {Advisory    Online }  Value=100  Threshold=  0   
Passed
Id=192  Status=50  {Advisory    Online }  Value=100  Threshold= 50   
Passed
Id=193  Status=18  {Advisory    Online }  Value=100  Threshold= 50   
Passed
Id=194  Status= 2  {Advisory    Online }  Value=141  Threshold=  0   
Passed
Id=196  Status=50  {Advisory    Online }  Value=100  Threshold=  0   
Passed
Id=197  Status=34  {Advisory    Online }  Value=100  Threshold=  0   
Passed
Id=198  Status= 8  {Advisory    OffLine}  Value=100  Threshold=  0   
Passed
Id=199  Status=10  {Advisory    Online }  Value=200  Threshold=  0   
Passed
OffLineStatus=132 {Suspended}, AutoOffLine=Yes, OffLineTimeout=24  
minutes
OffLineCapability=91 {Immediate Auto SuspendOnCmd}
SmartRevision=16, CheckSum=46, SmartCapability=3 {SaveOnStandBy  
AutoSave}

ide-smart -i -d /dev/hda

does not report anything.

I am new to this tool but according to the man it looks like I am ok  
as far as it reports.

I also set up smartmontools to run weekly

and a smartctl -a /dev/hda reports things as OK.

a smartctl -t short /dev/hda ran ok, a long is in process.

I need to learn a bit more on these tools but should prove to be  
handy when I do.

Thanks for the tip on these tools I will be running them on all my  
servers now.

So it looks like an overload problem I guess the only thing to do now  
is move some services onto a different machine.

Thanks Again

Brett

On Sep 12, 2005, at 9:26 AM, Ian P. Christian wrote:


> On Monday 12 September 2005 14:19, Brett Curtis wrote:
>
>
>> Any suggestions would be great.
>>
>>
>
> Have you tried using SMART tools to get information from, and test  
> the drive?
>
> Kind Regards,
>
> -- 
> Ian P. Christian ~ http://pookey.co.uk
>
>


-- 
gentoo-server@gentoo.org mailing list

Re: [gentoo-server] Drive issues or overload

[Matthew Lange]

Sounds like an imminent drive failure to me :(
You might try smartmontools to see if there are any pare-indicators to
it's failure.

http://smartmontools.sourceforge.net/


Matt

-- 
gentoo-server@gentoo.org mailing list