DISK - I/O request failed.

[Dave Cast]

>------------ Event Monitoring Service Event Notification ------------<

Notification Time: Sun May 11 04:34:20 2008

xxx sent Event Monitor notification information:

/storage/events/disks/default/6_0_8_1_0.0.0 is >= 3.
Its current value is CRITICAL(5).



Event data from monitor:

Event Time..........: Sun May 11 04:34:20 2008
Severity............: CRITICAL
Monitor.............: disk_em
Event #.............: 13
System..............: xxx.xxx.com

Summary:
Disk at hardware path 6/0/8/1/0.0.0 : I/O request failed.


Description of Error:

As part of the polling functionality, the monitor periodically requests
data from the device. The monitor's I/O request failed in this case. The
monitor was requesting data for Inquiry command.

Probable Cause / Recommended Action:

The monitor could not finish the requested I/O operation to the device.
Check /etc/opt/resmon/log/api.log file for an entry logged by
tl_scsi_dev_io request.

Additional Event Data:
System IP Address...: xxx.xxx.xxx.xxx
Event Id............: 0x4826af8c00000000
Monitor Version.....: B.01.01
Event Class.........: I/O
Client Configuration File...........:
/var/stm/config/tools/monitor/default_disk_em.clcfg
Client Configuration File Version...: A.01.00
Qualification criteria met.
Number of events..: 1
Associated OS error log entry id(s):
None
Additional System Data:
System Model Number.............: ia64 hp superdome server SD32B
OS Version......................: B.11.31
STM Version.....................: D.02.00
EMS Version.....................: A.04.20
Latest information on this event:
http://docs.hp.com/hpux/content/hardware/ems/disk_em.htm#13

v-v-v-v-v-v-v-v-v-v-v-v-v D E T A I L S v-v-v-v-v-v-v-v-v-v-v-v-v



Component Data:
Physical Device Path...: 6/0/8/1/0.0.0
Device Class...........: Disk
Inquiry Vendor ID......: COMPAQ
Inquiry Product ID.....: BF1468A4CC
Firmware Version.......: HPB5
Serial Number..........: 3KN2TH2G00009719T6B7

Product/Device Identification Information:

Logger ID.........: disc30; sdisk
Product Identifier: Disk
Product Qualifier.: COMPAQ BF1468A4CC
SCSI Target ID....: 0x00
SCSI LUN..........: 0x00

SCSI Command Data Block:

Command Data Block Contents:
0x0000: 12 00 00 00 FF 00

Command Data Block Fields (6-byte fmt):
Command Operation Code...(0x12)..: INQUIRY
Logical Unit Number..............: 0
EVPD Bit.........................: 0
Page Code........................: 0 (0x00)
Allocation Length................: 255 (0xFF)

Hardware Status: (not present in log record).

SCSI Sense Data: (not present in log record)


>---------- End Event Monitoring Service Event Notification ----------<
***********************************************

Can someone please give me the 'skinny' on this error message? Is it anything to be concerned about? (please don't refer me to the documentation, as I have already read it! and it was not helpful)

TIA
Dave

[TTr · Accepted solution]

Check the disk at 6/0/8/1/0.0.0 path.

If it exists and has failed you need to replace it. If it was removed recently you need to update EMS so that it does not poll at the 6/0/8/1/0.0.0 path.

[Tim Nelson]

Looks to me like you have a disk that is failed/failing.

Run some dd's to the disk to confirm. Otherwise be prepared to replace it.

[Asif Sharif]

Hi Dave,

What is the LED status of disk? If its showing red light then disk is failed.

Regards,
Asif Sharif

[Dave Cast]

This is a production system, using dd in the way that you specified is destructive is it not? I did notice some diags available in stm - however once again, how safe are these to use?

[Dave Cast]

All lights green...this same thing happened about a week ago -

[Tim Nelson]

dd if=/dev/rdsk/cxtxdx of=/dev/null

is simple a non-destructive read of the entire specific disk.

If you encounter an IO error then the disk is failed/failing and requires replacement.

You can also use online diags with a hp code word to review the logs on the disk. If write errors or un-correctable erros then this also indicates the device is failed/failing and needs replacement.

[Mridul Shrivastava]

Have you checked the ouput of ioscan?
check the output of diskinfo and pvdisplay -v
If it shows any stale extents then I would suggest you to get the disk replaced asap.

You could also try running info log for this disk under cstm and it is purely safe.