cancel
Showing results for 
Search instead for 
Did you mean: 

GSP Event

 
SOLVED
Go to solution
Andrew_247
Occasional Visitor

GSP Event

Hi All,

I found the following in my GSP "chassis log" while troubleshooting a server hang. Would I be correct in assuming that possible causes are:

1./ Hardware-related issue (memory/cpu)
2./ Running old firmware on GSP card
3./ Possible software issue (OS/application).

Can anyone shed more light on what these events mean ? I don't have cclogview installed.
I issued "TC" at the GSP to force a crash dump but it seems I didn't wait long enough before doing an "RS" as no crash dump was produced. Oh well, better luck next time...

Log Entry # 0 :
SYSTEM NAME: server1lancons
DATE: 07/21/2004 TIME: 07:29:44
ALERT LEVEL: 13 = System hang detected via timer popping

SOURCE: 1 = processor
SOURCE DETAIL: 1 = processor general SOURCE ID: 0
PROBLEM DETAIL: 4 = timeout

CALLER ACTIVITY: F = display_activity() update STATUS: 0
CALLER SUBACTIVITY: 00 = implementation dependent
REPORTING ENTITY TYPE: E = HP-UX REPORTING ENTITY ID: 00

0x78E000D41100F000 00000003 00000001 type 15 = Activity Level/Timeout
0x58E008D41100F000 00006806 15071D2C type 11 = Timestamp 07/21/2004 07:29:44
Type CR for next entry, Q CR to quit.

Log Entry # 1 :
SYSTEM NAME: server1lancons
DATE: 07/21/2004 TIME: 07:29:49
ALERT LEVEL: 2 = Non-Urgent operator attention required

SOURCE: 0 = unknown, no source stated
SOURCE DETAIL: 0 = unknown, no source stated SOURCE ID: FF
PROBLEM DETAIL: 0 = no problem detail

CALLER ACTIVITY: 6 = machine check STATUS: 2
CALLER SUBACTIVITY: 10 = implementation dependent
REPORTING ENTITY TYPE: 0 = system firmware REPORTING ENTITY ID: 00

0x0000002000FF6102 00000000 00000000 type 0 = Data Field Unused
0x5800082000FF6102 00006806 15071D31 type 11 = Timestamp 07/21/2004 07:29:49
Type CR for next entry, - CR for previous entry, Q CR to quit.
6 REPLIES 6
Bharat Katkar
Honored Contributor

Re: GSP Event

HI,
One possible cause i see is your Processor. It may not be getting hanged after sometime. Check for the Processor and it's respective PSM's also. Check whether the heatsink is getting too HOT. See if you are able to isolate the processor by removing one at a time and server comes up succesfully.

hope that helps.
Regards,
You need to know a lot to actually know how little you know
Andrew_247
Occasional Visitor

Re: GSP Event

Hi,

Thanks for that. Unfortunately it is a single-cpu machine, and installed in a remote location so it's not so easy to check.

I'm wondering if there is an equivalent to Tru64's /var/adm/binary.errlog where hardware events are logged for future analysis ?

Cheers.

Bharat Katkar
Honored Contributor

Re: GSP Event

Hi Andrew,
Then you can look into /var/tombstones
directory.
You will find the list of files starting with ts.
Refer file "ts99"

Regards,
You need to know a lot to actually know how little you know
Ron Thompson
Advisor

Re: GSP Event

We have had this GSP log entry "System hang detected by timer popping" many times and it has always turned out to be the "Platform Monitor" circuit. Have this circuit board replaced. This problem will not go away by its self and usually just gets worse.
Jim Thomas_5
Advisor
Solution

Re: GSP Event

Andrew. This is a known problem. Your GSP signature is that of a problem fixed by updating to the latest PDC code for your system. The System Timer Popped error was simply a result of the HPMC while the OS was up. The HPMC event GSP Entry matches that of a problem fixed by updating PDC to current latest revision.

Andrew_247
Occasional Visitor

Re: GSP Event

Hi Jim,

Thank you very much for your response. I will request that the PDC firmware be updated on this machine. The same message was logged 6 months ago so I am treating this as a recurring problem that must be resolved.

Thanks again,

Andrew.