On 02/24/2010 03:11 PM, Andrew Morton wrote:
On Sun, 21 Feb 2010 15:10:45 +0100 aarcange@xxxxxxxxxx wrote:
Add khugepaged to relocate fragmented pages into hugepages if new hugepages
become available. (this is indipendent of the defrag logic that will have to
make new hugepages available)
What does this mean? What are the user-visible effects if (when) this
kernel thread fails to keep up?
The result will be that applications use small pages, instead of
large ones, and potentially run slightly slower.
The same kind of slowdowns that memory pressure can already cause
to userland processes.
Generally it seems like a bad idea to do this sort of thing
asynchronously. Because it reduces repeatability across runs and
across machines - system behaviour becomes more dependent on the size
of the machine and the amount of activity in unrelated jobs?
Isn't system performance already dependent on the size of
the machine and the amount of activity in unrelated jobs?
Using hugepages is a performance enhancement only and
otherwise transparent to userspace.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>