I did say to do it only if the system is otherwise idle: say if no-one
has used the CPU for two time slices, then check a single page. When
looking for random bit errors, there is no need to race through
memory, since they don't happen very often. This would not noticably
impact performance.
> The main problem with it, from a technical standpoint, is that unlike
> ECC all you know is that a page was corrupted, so you have to throw it
> out. If it was dirty, or in use, what do you do?
Nothing. This scheme is *only* for clean pages in the page cache (i.e.
those that should be identical to what on disc). For people with lots
of RAM, most of which is taken up by page cache, this scheme should
work quite well.
Regards,
Richard....