Escalated to Bugzilla from IssueTracker
From User-Agent: XML-RPC uname -a: Linux paamd6.us.oracle.com 2.4.21-34.ELsmp #1 SMP Thu Jul 28 23:28:35 EDT 2005 x86_64 x86_64 x86_64 GNU/Linux This is with latest RHEL3U6 beta x86_64 on the Quartet hardware. On booting with numa=off the kernel panics. As reported by the SA: First reboot will have CPU 0 error, second reboot will have CPU 1 error, and so forth. The errors from the console are as follows CPU 0: Machine Check Exception: 0000000000000004 Northbridge Machine Check exception b60000010005001b 0 Uncorrectable condition Uncorrectable condition Address: 0000000037ff0000 Kernel panic This event sent from IssueTracker by lwang issue 78580
From User-Agent: XML-RPC However, The system boots with numa=off and acpi=off. numa=off alone doesn't work. With RHEL3 U5 on the same hardware, numa=off used to work. So this is a regression. Status set to: Waiting on Tech This event sent from IssueTracker by lwang issue 78580
From User-Agent: XML-RPC From what I can tell, this panic is actually a Machine Check exception rather than a panic. Can you include the kernel bootline so I can see if ACPI is on or off? Larry Woodman This event sent from IssueTracker by lwang issue 78580
Fixing "product" and "hardware" fields.
There was a potentially relevant fix already committed to the 2nd respin of RHEL3 U6 (built on 19-Aug-2005): - fix x86_64 machine check regression from -32.10.EL (Brian Maly) Could we please get verification on whether the most recently available U6 beta kernel (2.4.21-35.EL) still panics while booting with numa=off? Thanks in advance.
From User-Agent: XML-RPC With the latest kernel 2.4.21-35.EL, the system does not panic with numa=off. It comes up successfully. This event sent from IssueTracker by martinez issue 78580
Fixing bug status/disposition and propagating acks from bug 165841. The fix for this problem was committed to the RHEL3 U6 patch pool on 19-Aug-2005 (in kernel version 2.4.21-35.EL). *** This bug has been marked as a duplicate of 165841 ***
I'm linking in Issue Tracker 78590 to this bug as well, because the symptom appears to be identical. Could we please get an update to IT 78590 to confirm whether the problem is resolved in 2.4.21-35.EL? Thanks in advance.
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 the 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-2005-663.html