"Dmesg" reply errors

[RuyiLuo]

Hello all.

When I use "Dmesg" command,it replies with errors such like "LPMC type : I-Cache Parity Error."

In syslog.log I see two lines about "Cache":
Dec 5 22:19:19 xgjf1 vmunix: LPMC type : I-Cache Parity Error.
Dec 5 22:19:19 xgjf1 vmunix: LPMC type : I-Cache Parity Error.
But no more information is finded.

MODEL--9000/800/L2000-5X

So what can i do now?Thanks to anyone who gives a advisement

[Michael Tully · Accepted solution]

It;s likely your encountering a processor problem. Another place to look is in the GSP logs. Here is a similar discussion to yours.

http://forums1.itrc.hp.com/service/forums/questionanswer.do?threadId=692543

[Steven E. Protter]

This is a Low Priority Machine Check

It needs to be dealt with before it becomes a High Priority Machine Check(HPMC)

If that happens its instant crash. In this situation you may come back up with no system due to a system board issue, or short a processor.

This should be dealth with via a hardware call as soon as practical.

SEP

[A. Clay Stephenson]

Because these two events happened at the same time, for our purposes let's call them the same event. Yours is a Low Priority Machine Check in the Instruction Cache. This is really only of concern if you see it freequently. I'll loosely define frequently as more than about 1 per week. This type of event can literally be the result of comsic or other background radiation although, in general, unless you are in an unusual environment only cosmic radiation is energetic enough to cause this. If you begin to see these events often then it is time to call your HP Mr. Goodwrench and have a processor board replaced.

[RuyiLuo]

I am sorry that i have ignored the information follows:

Dec 5 22:19:19 xgjf1 vmunix: Parity Error.^M
Dec 5 22:19:19 xgjf1 vmunix: LPMC type : I-Cache Parity Error.^M
Dec 5 22:10:25 xgjf1 cmcld: Warning: cmcld process was unable to run for the last 3 seconds
Dec 5 22:19:19 xgjf1 vmunix: LPMC type : I-Cache Parity Error.^M
Dec 5 22:39:19 xgjf1 above message repeats 80 times
Dec 5 22:10:30 xgjf1 cmcld: Warning: cmcld process was unable to run for the last 3 seconds

It seems terrible.I have made a hardware call,and the result they give me is a problem of Memory.They promise me replacement of Memory.

But i still want to know how to deal with this situation.

[Hoang Chi Cong_1]

Hi guru
Here is good link:
http://www5.itrc.hp.com/service/cki/docDisplay.do?docLocale=en_US&docId=200000065556468

(You have to type username/password to login)


And here is good thread, it may help you:
http://forums1.itrc.hp.com/service/forums/questionanswer.do?threadId=105608


Hope this helps

Regard,

Jimkery

[Hoang Chi Cong_1]

Oops, click 'submit' a bit prematurely...

You can check in the syslog.log file for the even ID. Then check in this site:
http://www.docs.hp.com/en/diag/ems/lpmc_em.htm

regard,
Jimkery

[Saurav_1]

Confirm that Diagnostics and Patches are updated in your system to latest.

MDT. Memory Deallocation table. and Page deallocation table. Keeps the track of faulty pages in memory. Those pages once locked will not be used again by system.

memlogd is the daemon for this.

Cheers
Saurav