> > Out of curiosity, do you have any statistics on how much of a performance impact scanning may have? > > We've reached the point where we've finally been able to show previous admonitions to not enable THP due to a negative performance impact no longer hold true, and I'd hate to see systems on which enabling THP now would cause a performance hit due to this scanner. There are no noticeable performance issues from running the scanner itself from our experiments. As written, we check 256 pfn s at a time every second, which does not appear to be an issue.
