Scsi Bus error - RP3440 with DS2300 split bus mode 14 Drives

[nibble]

Everyone,

We're receiving a lot of scsi reset errors from the external drives of our 3440. EMS reported this to all the drives of the DS2300 but not simultaneously. Some reports on 1 drive, then the next day to another drive and so on. I've attached the EMS output for the drive 13 at this point. and Ive pasted the other one below:

Description of Error:

The hardware did not respond to the request by the driver. The I/O request
was not completed.

Probable Cause / Recommended Action:

The I/O request that the monitor made to this device failed because the
device timed-out. Check cables, power supply, ensure the drive is powered
ON, and if needed contact your HP support representative to check the
drive.

The possible causes as indicated by the EMS have been checked out for both errors and there's nothing that matches on it, except if the drive is really faulty and we were able to replaced it.


The 3440 which is running on UX11.23 with SAP. IT has 1 Dual channel Ultra160 LVD SCSI adapter board where the 2 BCCs of the DS2300 are connected.

The DS2300 is configured to have split bus mode, with 14 x 73Gb drives as shown below. The second set of 7 drives is a mirror to the 1st set using UX mirroring. Proper termination, cables and the like are already checked. The machine is running SAP. Its been noticed also that an intermittent high I/O wait (as high as 100) happens and anytime of the day, at least 10 times for about 10 seconds then drops down -- this high io possibly related to the scsi bus error/reset.

... ioscan

ba 5 0/6 lba CLAIMED BUS_NEXUS Local PCI-X Bus Adapter (783)
ext_bus 6 0/6/1/0 c8xx CLAIMED INTERFACE SCSI C1010 Ultra160 Wide LVD A6829-60101
target 16 0/6/1/0.7 tgt CLAIMED DEVICE
ctl 8 0/6/1/0.7.0 sctl CLAIMED DEVICE Initiator
/dev/rscsi/c6t7d0
target 17 0/6/1/0.8 tgt CLAIMED DEVICE
disk 16 0/6/1/0.8.0 sdisk CLAIMED DEVICE HP 73.4GST373454LC
/dev/dsk/c6t8d0 /dev/rdsk/c6t8d0
target 18 0/6/1/0.9 tgt CLAIMED DEVICE
disk 17 0/6/1/0.9.0 sdisk CLAIMED DEVICE HP 73.4GST373454LC
/dev/dsk/c6t9d0 /dev/rdsk/c6t9d0
target 19 0/6/1/0.10 tgt CLAIMED DEVICE
disk 18 0/6/1/0.10.0 sdisk CLAIMED DEVICE HP 73.4GMAU3073NC
/dev/dsk/c6t10d0 /dev/rdsk/c6t10d0
target 20 0/6/1/0.11 tgt CLAIMED DEVICE
disk 19 0/6/1/0.11.0 sdisk CLAIMED DEVICE HP 73.4GST373454LC
/dev/dsk/c6t11d0 /dev/rdsk/c6t11d0
target 21 0/6/1/0.12 tgt CLAIMED DEVICE
disk 20 0/6/1/0.12.0 sdisk CLAIMED DEVICE HP 73.4GMAU3073NC
/dev/dsk/c6t12d0 /dev/rdsk/c6t12d0
target 22 0/6/1/0.14 tgt CLAIMED DEVICE
disk 21 0/6/1/0.13.0 sdisk CLAIMED DEVICE HP 73.4GST373454LC
/dev/dsk/c6t14d0 /dev/rdsk/c6t14d0
target 23 0/6/1/0.14 tgt CLAIMED DEVICE
disk 24 0/6/1/0.14.0 sdisk CLAIMED DEVICE HP 73.4GST373454LC
/dev/dsk/c6t14d0 /dev/rdsk/c6t14d0
target 24 0/6/1/0.15 tgt CLAIMED DEVICE
ctl 10 0/6/1/0.15.0 sctl CLAIMED DEVICE HP A6491A
/dev/rscsi/c6t15d0
ext_bus 7 0/6/1/1 c8xx CLAIMED INTERFACE SCSI C1010 Ultra160 Wide LVD A6829-60101
target 4 0/6/1/1.0 tgt CLAIMED DEVICE
disk 11 0/6/1/1.0.0 sdisk CLAIMED DEVICE HP 73.4GST373454LC
/dev/dsk/c7t0d0 /dev/rdsk/c7t0d0
target 6 0/6/1/1.1 tgt CLAIMED DEVICE
disk 12 0/6/1/1.1.0 sdisk CLAIMED DEVICE HP 73.4GST373454LC
/dev/dsk/c7t1d0 /dev/rdsk/c7t1d0
target 7 0/6/1/1.2 tgt CLAIMED DEVICE
disk 13 0/6/1/1.2.0 sdisk CLAIMED DEVICE HP 73.4GST373454LC
/dev/dsk/c7t2d0 /dev/rdsk/c7t2d0
target 8 0/6/1/1.3 tgt CLAIMED DEVICE
disk 14 0/6/1/1.3.0 sdisk CLAIMED DEVICE HP 73.4GST373454LC
/dev/dsk/c7t3d0 /dev/rdsk/c7t3d0
target 9 0/6/1/1.4 tgt CLAIMED DEVICE
disk 15 0/6/1/1.4.0 sdisk CLAIMED DEVICE HP 73.4GST373454LC
/dev/dsk/c7t4d0 /dev/rdsk/c7t4d0
target 10 0/6/1/1.5 tgt CLAIMED DEVICE
disk 21 0/6/1/1.5.0 sdisk CLAIMED DEVICE HP 73.4GST373454LC
/dev/dsk/c7t5d0 /dev/rdsk/c7t5d0
target 11 0/6/1/1.6 tgt CLAIMED DEVICE
disk 22 0/6/1/1.6.0 sdisk CLAIMED DEVICE HP 73.4GST373454LC
/dev/dsk/c7t6d0 /dev/rdsk/c7t6d0
target 12 0/6/1/1.7 tgt CLAIMED DEVICE
ctl 7 0/6/1/1.7.0 sctl CLAIMED DEVICE Initiator
/dev/rscsi/c7t7d0
target 22 0/6/1/1.15 tgt CLAIMED DEVICE
ctl 9 0/6/1/1.15.0 sctl CLAIMED DEVICE HP A6491A
/dev/rscsi/c7t15d0

Any comments are highly appreciated.

[nibble]

Its an RP3440 (A7137A), not RP4440 as previously stated. the drives for the DS2300 are hotswap-ultra 320 LVD 15K

[Khairy]

hi nibble,

post the following output. May i warned u its a lengthy output. Its from cstm diagnostic tools.

I'm suspecting something but need to be sure...

# echo "map selall information;wait infolog quit ok" | cstm > /tmp/cstm.txt

Rgds

[nibble]

Hi K, ive attached the output

[Khairy]

hi n,

seems no errors on the DS2300. But its worth to narrow down to scsi cables and scsi adapter.

Based on the cstm, the scsi adapter attached to DS is a dual channel adapter. Means if the adapter fail, your server won't be able to access DS2300 (yeah,the adapter is the single point of failure).

I've encountered a non stop scsi bus errors from DS and SC JBOD storage long time ago due to different firmware at controller level and another case due to bad C1016 scsi adapter.

In your case, you're saying it happen to disk1 (in separate bus) and then it happen in disk2 on next day and it continues. And this time it occured to disk13 (I assume its on diff bus). I've ruled out scsi cable.

Backup your disks in DS2300 regularly. I suspect it may indicate a soon problematic scsi adapter.

Rgds

[Andrew Merritt_2]

Hi,
It's almost certainly not the cause of the errors, but you should look at upgrading your OnlineDiags to a currently supported version. You have the C.48.00 version, which was released in May 2005. The current version is C.58.00, released in December 2007. See http://www.docs.hp.com/en/diag/stm/stm_upd.htm#table for the versions, and http://www.software.hp.com/portal/swdepot/displayProductInfo.do?productNumber=B6191AAE to download the latest.

Andrew