Bug 128995

Summary: kernel hangs after floating-point assist faults
Product: Red Hat Enterprise Linux 3 Reporter: Gary Hade <garyhade>
Component: kernelAssignee: Geoff Gustafson <grgustaf>
Status: CLOSED WORKSFORME QA Contact: Brian Brock <bbrock>
Severity: high Docs Contact:
Priority: medium    
Version: 3.0CC: acjohnso, gone, jbaron, lcm, peterm, petrides, riel
Target Milestone: ---   
Target Release: ---   
Hardware: ia64   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: 2005-09-12 20:29:39 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 Gary Hade 2004-08-02 20:17:28 UTC
From Bugzilla Helper:
User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 4.0)

Description of problem:
We've seen the kernel hang twice while running stress tests on a two 
node IBM x455.  In both cases a series of "floating-point assist 
fault" messages had been previously written to the console.  It is 
not clear whether the hang is associated with the floating-point 
errors.  The following messages are from the most recent failure.

float_exp_log(17776): floating-point assist fault at ip 
200000000008f7b2
float_exp_log(17780): floating-point assist fault at ip 
200000000008f7b2
float_exp_log(17769): floating-point assist fault at ip 
200000000008f7b2
float_exp_log(17771): floating-point assist fault at ip 
200000000008f7b2
float_exp_log(17771): floating-point assist fault at ip 
200000000008f7b2
float_exp_log(17781): floating-point assist fault at ip 
200000000008f7b2
float_exp_log(17783): floating-point assist fault at ip 
200000000008f7b2
float_exp_log(17785): floating-point assist fault at ip 
200000000008f7b2


Version-Release number of selected component (if applicable):
kernel-2.4.21-18.EL

How reproducible:
Sometimes

Steps to Reproduce:
1. We encountered the problem while subjecting the system to heavy 
test load.
2.
3.
    

Actual Results:  kernel hang

Expected Results:  no kernel hang

Additional info:

Comment 1 Jason Baron 2005-03-10 04:03:36 UTC
hmmm, there isn't much to go on here. Is it possible to get an
alt-sysrq-t at the time of the hang?

Comment 2 Ernie Petrides 2005-09-12 19:32:33 UTC
Gary, are you going to follow up on this at some point?

Comment 3 Gary Hade 2005-09-12 20:29:39 UTC
Ernie, thanks for pinging me on this.  I somehow missed Jason's 6 month old
request for more information.  One reason I neglected to respond was probably
due to the lack of subsequent problem occurrences that would have provided
reminders.  Since the problem was not reproducible this bug can be closed.