Uncorrectable memory error and CPU bus error - IBM System x3530 M4 (7160) and System x3630 M4 (7158)

Resolving The Problem

Source

RETAIN tip: H213778

Symptom

System x3630M4/x3530M4 may report uncorrectable bus error on Central Processing Unit (CPU) and uncorrectable error on memory while performing excessive memory usage application or memory diagnostic.

The error from the Integrated Management Module (IMM) chassis event log is as follows and results in a system restart.

The symptom can only be observed by the Three (3) DIMMs for One (1) CPU or Six (6) DIMMs for Two (2) CPUs ( One DIMM per channel ) configuration.

Affected configurations

The system may be any of the following IBM servers:

• System x3530 M4, type 7160 E5-xxxxV2, any model
• System x3630 M4, type 7158 E5-xxxxV2, any model

This tip is not software specific.

This tip is not option specific.

The following system BIOS/UEFI level(s) are affected: UEFI version 1.60/1.70/1.71 are affected.

Solution

The issue has been addressed by the UEFI firmware code version 2.12 or later.

The file is or will be available by selecting the appropriate Product Group, type of System, Product name, Product machine type, and operating system on IBM Support's Fix Central web page, at the following URL:

http://www.ibm.com/support/fixcentral/

Workaround

This issue can be worked around by changing the UEFI setting to lower memory speed from default 1600 MT/s to 1333 MT/s.

In UEFI setup menu, Select 'System Settings' --> 'Operating Modes' --> Choose Operating Mode: 'Custom Mode' --> Change Memory Speed to 'Balanced'.

Additional information

The system mistakenly triggers the failure symptom. The UEFI firmware will address this issue in next release.