Hi Tejun,
Sorry it took some time to respond. I went away for
th holidays and just returned yesterday.
We were using linux 2.6.14. I saw a message on one of
the forums that suggested moving to linux 2.6.18
because of improved error handling to fix this
problem. I tried that by moving the entire SCSI
framework from 2.6.18 into 2.6.14 (The full 2.6.18 is
not stable on our platform).
Anyhow, after doing this difficult task I managed to
get rid of the lockups but I still get error messages
and drive 'stalls'. Unfortunately, I don't have them
recorded anywhere because the error messages don't
seem to hurt anything. The drive locks for about 30
seconds, the driver does a 'soft reset' and then the
drive comes back alive. It's far from optimal but at
least the system is usable.
I will try to repeat the test and get the error
messages again so I can send them to you but if you
have any ideas before then please let me know.
Cheers,
Steve...
--- Tejun Heo <htejun@xxxxxxxxx> wrote:
> Hello,
>
> Steve Graham wrote:
> > My name is Steve Graham and I work for a small
> > startup. Our company is developing a server board
> > with the Silicon Images 3512 and we are getting
> some
> > strange lockups during high levels of disk
> activity.
> > The test I'm currently running to cause the
> problem is
> > to run the following concurrently: 'nbench',
> > 'tiobench', and an 'scp' of a 200Meg file to the
> sata
> > drive. Every so often I will get the following
> > message:
> >
> > ata1: status=0x51 { DriveReady SeekComplete Error
> }
> > ata1: error=0x04 { DriveStatusError }
>
> Which kernel version are you running?
>
> > This doesn't mean the drive is locked up and
> doesn't
> > appear to have any side effects on its own but
> > eventually I will get the above message that is
> > immediately followed by the next block of messages
> > that do result in a lockup:
> >
> > ata1: command 0x35 timeout, stat 0xd1 host_stat
> 0x1
> > ata1: status=0xd1 { Busy }
> > sd 0:0:0:0: SCSI error: return code = 0x8000002
> > sda: Current: sense key=0xb
> > ASC=0x47 ASCQ=0x0
> > end_request: I/O error, dev sda, sector 17033103
> > ata1: Abnormal status 0xD1 on port 0xC001E087
> > ata1: Alternate status 0xD1 on port 0xC001E08A
> > ata1: Error 0xd1
> > ata1: Abnormal status 0xD1 on port 0xC001E087
> > ata1: Alternate status 0xD1 on port 0xC001E08A
> > ata1: Error 0xd1
> > ata1: Abnormal status 0xD1 on port 0xC001E087
> > ata1: Alternate status 0xD1 on port 0xC001E08A
>
> This is message from old error handling and doesn't
> really contain much
> useful info. Even if you have to use previous
> kernel in production
> system, providing error messages from 2.6.19 will
> help chasing down the
> cause.
>
> --
> tejun
>
__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
-
To unsubscribe from this list: send the line "unsubscribe linux-ide" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
