Bad memory

Justin M. Forbes jmforbes at
Fri Jan 18 18:05:02 UTC 2013

On Thu, Jan 17, 2013 at 09:18:40AM -0800, Chuck Forsberg WA7KGX N2469R wrote:
> Recently I discovered the motherboard that had been running
> had an undetected bad memory chip.   This is a real confidence builder.
> Currently, running a definitive memory test requires hours of down time.
> The user mode memory tester has serious limitations.
> I propose kernel support for a user mode program similar to memtest86
> to allow such a program to request a hardware block of memory and
> relocate whatever was in that block to another memory area.  This way
> all of the memory can be checked in the background of a running system.

There are a lof of reasons that this isn't feasible on a running system.
You just don't have access to all of the memory for a full check.


More information about the test mailing list