Having spent some time on a rack mounted server yesterday afternoon we are now trying to determine the most probable cause of two DDR2 modules failing on an IBM server simultaneously.
The server would boot with either both modules, and with one at a time, but failed at the 12% mark on MEMTEST86+.
Some replacement memory is working perfectly, it just seems odd that both sticks would fail at the same time and have the exact same problem in a certain area of memory.
Does anyone know what would cause this?
If its a known issue with some vendors this is a relatively new IBM rack server.
The memory likely came from one chip vendor and one module vendor. The manufacturing batch(es) may have even been the same. Perhaps this batch of chips and/or modules was prone to failure. Alternatively, physical damage to both modules upon system build/configuration.
Are you certain that the modules themselves have failed (i.e. do they stay 'bad' in another server?) as I've recently seen a similar issue where it was the fault of the CPU and/or motherboard memory traces that was affecting more than one module.
The modules might have been defunctive from the beginning and you only noticed, after using more RAM than in the beginngin. I've had such a case myself once!
Improper handling could be the cause. See http://www.kingston.com/tools/umg/umg07.asp:
"Electro-Static Discharge (ESD) is a frequent causes of damage to the memory module. ESD is the result of handling the module without first properly grounding yourself and thereby dissipating static electricity from your body or clothing. If you have a grounded wrist strap, wear it. If you don't, before touching electronic components - especially your new memory module - make sure you first touch an unpainted, grounded metal object. Most convenient is the metal frame inside the computer. In addition, always handle the module by the edges. If ESD damages memory, problems may not show up immediately and may be difficult to diagnose."