> In 2Q, when a page is present in LRU queue, you move it to the front of
> LRU queue as usual. Otherwise, if it is in memory, it must be in A1 queue
> (the FIFO one), so you DON'T do anything. When the page is NOT in memory,
> you load it conditionally to Am LRU queue (if it is present in A1out
> queue) or to A1 queue (FIFO), if not.
>
> It gets interesting when you need to swap out a page from memory. When the
> size of A1 FIFO is greater than limit (e.g., 10% of buffer space), a page
> from A1 is swapped out (and put into A1out list), otherwise a page from Am
> LRU is swapped out (and NOT put into A1out, since it hasn't been accessed
> for long time).
This description has me horribly confused. Do you have
any pointers to state diagrams of this thing? ;)
regards,
Rik
-- Executive summary of a recent Microsoft press release: "we are concerned about the GNU General Public License (GPL)"
http://www.surriel.com/ http://www.conectiva.com/ http://distro.conectiva.com/
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/