MCE Analysis Help

[idata]

Any ideas where I can get some help with the analysis of the MCEs below? Using an "unqualified" OS (CentOS), which my OEM vendor doesn't support and therefore doesn't have the support pack tools that hook into the OS for analysis. They suggested I "ask Intel" to provide an analysis of what part of the subsystem may be having the problem. OEM vendor is suggesting this is potentially not strictly a hardware error despite what the MCE says, and might actually be an interop problem between the OS and the hardware. These are IA64 systems, and I'm seeing them occur regularly on multiple machines.

Thanks in advance,

-Rob

HARDWARE ERROR. This is NOT a software problem!

Please contact your hardware vendorMCE 12CPU 0 BANK 8 MISC 14a6688000011080 ADDR 8e41d65c0 TIME 1340190061 Wed Jun 20 11:01:01 2012MCG status:MCi status:MCi_MISC register validMCi_ADDR register validMCA: MEMORY CONTROLLER RD_CHANNELunspecified_ERRTransaction: Memory read errorSTATUS 8c0000400001009f MCGSTATUS 0MCGCAP 1c09 APICID 0 SOCKETID 0 CPUID Vendor Intel Family 6 Model 44

HARDWARE ERROR. This is NOT a software problem!

Please contact your hardware vendorMCE 0CPU 1 BANK 8 MISC 4702108000016000 TIME 1340154061 Wed Jun 20 01:01:01 2012MCG status:MCi status:MCi_MISC register validMCA: MEMORY CONTROLLER MS_CHANNELunspecified_ERRTransaction: Memory scrubbing errorSTATUS 88000040000200cf MCGSTATUS 0MCGCAP 1c09 APICID 20 SOCKETID 1 CPUID Vendor Intel Family 6 Model 44

HARDWARE ERROR. This is NOT a software problem!

Please contact your hardware vendorMCE 31CPU 0 BANK 8 MISC d847010400011287 ADDR 87bc2aac0 TIME 1340215261 Wed Jun 20 18:01:01 2012MCG status:MCi status:MCi_MISC register validMCi_ADDR register validMCA: MEMORY CONTROLLER RD_CHANNELunspecified_ERRTransaction: Memory read errorSTATUS 8c0000400001009f MCGSTATUS 0MCGCAP 1c09 APICID 0 SOCKETID 0 CPUID Vendor Intel Family 6 Model 44

[Adolfo_S_Intel2]

Please let me know what is the Kernel that you are using?

Also let me know the processor model that you are using, and if possible the system configuration itself (hardware components)

Please bear in mind that Intel desktop motherboards do not support Linux operating systems, so we should check for this type of issues on Linux forums.

[idata]

Adolfo,

Thanks for your response. I'm getting the exact Kernel version info on the CentOS build now, and will reply with that shortly. The system is an HP Proliant DL360cG7 with the Itanium IA64 (Westmere) processor; so not a desktop motherboard. Red Hat Linux is a supported OS on this box, and CentOS is essentially an open-source version of it, but not one that HP officially supports, which is why I'm posting here. I'll have more information on the exact configuration of the box shortly.

I did find the following document on IA64 MCE codes, and am attempting to understand it now: http://www.intel.com/Assets/ja_JP/PDF/manual/253668.pdf http://www.intel.com/Assets/ja_JP/PDF/manual/253668.pdf

Regards,

-Rob