Bug 633196

Summary:	testing NMI watchdog ... <4>WARNING: CPU#0: NMI appears to be stuck (62->62)!
Product:	Red Hat Enterprise Linux 5	Reporter:	Eryu Guan <eguan>
Component:	kernel	Assignee:	Don Zickus <dzickus>
Status:	CLOSED ERRATA	QA Contact:	Han Pingtian <phan>
Severity:	medium	Docs Contact:
Priority:	low
Version:	5.5.z	CC:	jhunt, jwilson, pvn, qcai
Target Milestone:	rc
Target Release:	---
Hardware:	All
OS:	Linux
Whiteboard:
Fixed In Version:		Doc Type:	Bug Fix
Doc Text:		Story Points:	---
Clone Of:		Environment:
Last Closed:	2011-07-21 10:25:05 UTC	Type:	---
Regression:	---	Mount Type:	---
Documentation:	---	CRM:
Verified Versions:		Category:	---
oVirt Team:	---	RHEL 7.3 requirements from Atomic Host:
Cloudforms Team:	---	Target Upstream Version:
Embargoed:

Description Eryu Guan 2010-09-13 08:11:29 UTC

Description of problem:
When booting RHEL5.5 I got these messages on specific host:
testing NMI watchdog ... <4>WARNING: CPU#0: NMI appears to be stuck (62->62)!

The host is hp-dl385g7-01.rhts.eng.bos.redhat.com.

And here is more test results
http://rhts.redhat.com/cgi-bin/rhts/jobs.cgi?id=174249&type=single


Version-Release number of selected component (if applicable):
kernel-2.6.18-194.15.1.el5

How reproducible:
always

Steps to Reproduce:
1. Boot rhel5 on host hp-dl385g7-01.rhts.eng.bos.redhat.com.
2. Check dmesg
3.
  
Actual results:
AMD Opteron(tm) Processor 6128 stepping 01
Brought up 16 CPUs
testing NMI watchdog ... <4>WARNING: CPU#0: NMI appears to be stuck (62->62)!
time.c: Using 14.318180 MHz WALL HPET GTOD HPET/TSC timer.
time.c: Detected 1424.953 MHz processor.

Expected results:
No such warning

Additional info:
bug 500892 is a similar one for rhel4

Comment 1 Jacob Hunt 2010-12-24 00:03:53 UTC

System with the same issues, I get the following when the server boots up.

AMD Opteron(tm) Processor 6174 stepping 01
Brought up 24 CPUs
testing NMI watchdog ... <4>WARNING: CPU#0: NMI appears to be stuck (177->177)!
time.c: Using 14.318180 MHz WALL HPET GTOD HPET/TSC timer.
time.c: Detected 2200.011 MHz processor.


Information:

RHEL 5.4
kernel 2.6.18-164.el5
HP ProLiant BL465c G7

Comment 2 Don Zickus 2011-01-03 14:25:06 UTC

This maybe due to the BIOS using the same performance counters the nmi watchdog is using.  HP has suggested the following to disable some monitoring to allow the nmi watchdog to work.  [This only affects AMD G7s AFAIK]

(when the BIOS loads during a restart)
- Press "F9" during POST to go into RBSU
- Hit "control-a"
- you will then see a new "service options" menu
- go into it, and disable the following:
1) memory pre-failure notification
2) processor power utilization monitoring

If this works, I will dup this bug over to another bug I am working on to address this issue.

Cheers,
Don

Comment 7 RHEL Program Management 2011-03-21 22:49:23 UTC

This request was evaluated by Red Hat Product Management for inclusion in a Red
Hat Enterprise Linux maintenance release.  Product Management has requested
further review of this request by Red Hat Engineering, for potential
inclusion in a Red Hat Enterprise Linux Update release for currently deployed
products.  This request is not yet committed for inclusion in an Update
release.

Comment 9 Jarod Wilson 2011-03-28 18:37:17 UTC

Patch(es) available in kernel-2.6.18-252.el5
You can download this test kernel (or newer) from http://people.redhat.com/jwilson/el5
Detailed testing feedback is always welcomed.

Comment 11 Han Pingtian 2011-05-16 03:31:08 UTC

Verified with 2.6.18-256.el5PAE.

Comment 12 errata-xmlrpc 2011-07-21 10:25:05 UTC

An advisory has been issued which should help the problem
described in this bug report. This report is therefore being
closed with a resolution of ERRATA. For more information
on therefore solution and/or where to find the updated files,
please follow the link below. You may reopen this bug report
if the solution does not work for you.

http://rhn.redhat.com/errata/RHSA-2011-1065.html