Scsi problems with MPT-Fusion-based HBA

[Matthew Jacob]

Wrong mailing list. The messsages indicate that you are runnning Linux.

Perhaps you should install FreeBSD instead.


On 6/13/05, paw <paul.wisniewski at icecube.wisc.edu> wrote:
> Hi,
> 
> I am hoping that the experts on the list may be able to give me some
> insight with an a scsi-related problem I am experiencing. I am simply
> looking for an interpretation of what this I/O means, or what I might be
> able to try to solve the problem.  The equipment is in a remote
> location, and spare parts are not available to try swapping things out.
> Thanks in advance for all your help,  --paw
> 
> 
> Kernel:  2.4
> Server:   HP Proliant 380DL
> Scsi:   (HP Part # 268351-B21, LSI Logic / Symbios Logic 53c1030 PCI-X
> Fusion-MPT Dual Ultra320
> Device:  Western Scientific EonStor A16F/A16U Disk Array  16-disk, 6TB
> RAID divvied into 2TB partitions
> Connection: Single 3 foot scsi cable rated to U320.
> 
> Problems:
> Extremly poor throughput, and intermittant,  debilitating Scsi errors
> causing lockups. Server reboots necessary to clear error conditions
> 
> Example of errors:
> 
> scsi : aborting command due to timeout : pid 541102, scsi0, channel 0,
> id 0, lun 0 Write (10) 00 51 05 14 80 00 01 40 00
> mptscsih: OldAbort scheduling ABORT SCSI IO (sc=c6c06e00)
> scsi : aborting command due to timeout : pid 541099, scsi0, channel 0,
> id 0, lun 0 Write (10) 00 51 05 11 f0 00 00 10 00
> mptscsih: OldAbort scheduling ABORT SCSI IO (sc=c6c48200)
> SCSI host 0 abort (pid 541097) timed out - resetting
> SCSI bus is being reset for host 0 channel 0.
> mptscsih: OldReset scheduling BUS_RESET (sc=c6c07200)
> SCSI host 0 abort (pid 541095) timed out - resetting
> SCSI bus is being reset for host 0 channel 0.
> mptscsih: OldReset scheduling BUS_RESET (sc=c6d04200)
> scsi : aborting command due to timeout : pid 541100, scsi0, channel 0,
> id 0, lun 0 Write (10) 00 51 05 12 00 00 01 40 00
> mptscsih: OldAbort scheduling ABORT SCSI IO (sc=c6c59200)
> scsi : aborting command due to timeout : pid 541103, scsi0, channel 0,
> id 0, lun 0 Write (10) 00 51 05 15 c0 00 01 38 00
> mptscsih: OldAbort scheduling ABORT SCSI IO (sc=c6c48e00)
> scsi : aborting command due to timeout : pid 541098, scsi0, channel 0,
> id 0, lun 0 Write (10) 00 51 05 11 48 00 00 a8 00
> mptscsih: OldAbort scheduling ABORT SCSI IO (sc=c6c06c00)
> SCSI host 0 abort (pid 541096) timed out - resetting
> SCSI bus is being reset for host 0 channel 0.
> mptscsih: OldReset scheduling BUS_RESET (sc=c6c48400)
> scsi : aborting command due to timeout : pid 541101, scsi0, channel 0,
> id 0, lun 0 Write (10) 00 51 05 13 40 00 01 40 00
> mptscsih: OldAbort scheduling ABORT SCSI IO (sc=c6d04400)
> scsi : aborting command due to timeout : pid 541102, scsi0, channel 0,
> id 0, lun 0 Write (10) 00 51 05 14 80 00 01 40 00
> mptscsih: OldAbort scheduling ABORT SCSI IO (sc=c6c06e00)
> scsi : aborting command due to timeout : pid 541099, scsi0, channel 0,
> id 0, lun 0 Write (10) 00 51 05 11 f0 00 00 10 00
> mptscsih: OldAbort scheduling ABORT SCSI IO (sc=c6c48200)
> SCSI host 0 abort (pid 541097) timed out - resetting
> SCSI bus is being reset for host 0 channel 0.
> 
> ---------------------------
> 
> Flushing ide devices: hda
> mptbase: Initiating ioc0 recovery
> mptbase: ioc0: WARNING - Unexpected doorbell active
> mptbase: ioc0: ERROR - Doorbell ACK timeout (count=4999), IntStatus =
>                ffffffff!
> 
> 
> _______________________________________________
> freebsd-scsi at freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-scsi
> To unsubscribe, send any mail to "freebsd-scsi-unsubscribe at freebsd.org"
>