How to Analyze Memory Errors on x86 or x64 Servers Using HERD
(Doc ID 1019683.1)
Last updated on JANUARY 30, 2022
Applies to:
Sun Blade X6240 Server Module - Version Not Applicable to Not Applicable [Release N/A]Sun Fire X2100 Server - Version Not Applicable to Not Applicable [Release N/A]
Sun Fire X2200 M2 Server - Version Not Applicable to Not Applicable [Release N/A]
Sun Fire X4100 M2 Server - Version Not Applicable to Not Applicable [Release N/A]
Sun Fire X4100 Server - Version Not Applicable to Not Applicable [Release N/A]
Red Hat Enterprise Linux Advanced Server x86-64 (AMD Opteron Architecture)
Microsoft Windows (32-bit)
Microsoft Windows x64 (64-bit)
All Platforms
Goal
Memory errors on x86_64 (x64) systems running Linux or Windows will give rise to Machine Check Exceptions (MCE). This document will tell you how to analyze these MCEs using HERD.
Symptoms:
- Silent Northbridge MCE
- Panic
- Performance Reduction
- Memory Capacity Reduction
- Reset
Purpose/Scope:
This document describes which troubleshooting steps to take when trying to resolve memory errors on x64 systems running the Linux and Windows operating systems. A memory error will give rise to a machine check exception (MCE).
In the case of correctable memory errors, the MCE will be reported on the console and in the system log files /var/log/messages on Linux and the Event Log on Windows.
In the case of an uncorrectable memory error, the platform will reset, and a MCE entry may appear in the system log file /var/log/messages after a reboot occurs.
The presence of this log entry is not always guaranteed as the severity of the platform crash dictates the platforms ability to report errors.
Solution
To view full details, sign in with your My Oracle Support account. |
|
Don't have a My Oracle Support account? Click to get started! |