On Fri, 21 Apr 2000, Andrea Arcangeli wrote:
> On Fri, 21 Apr 2000, Rik van Riel wrote:
>
> >Doing this will give the pages a shorter life span in the
> >LRU queue, which may be good or wrong, depending on the
>
> Doing this will give a longer life to pages that had a cache hit.
>
> The new inserted pages don't need the reference bit since their
> age is just honoured by the initial position in the LRU.
Ahh, but you're forgetting that it is usually not
relevant to keep around unmapped pages from which
somebody did a read() because the data is copied
somewhere else now.
If that page would be the primary place where the
data is stored, then the page would have been mapped
into a process' address space, to be unmapped by
swap_out() as soon as the process hasn't used the page
for one swap_out() scan.
regards,
Rik
-- The Internet is not a network of computers. It is a network of people. That is its real strength.Wanna talk about the kernel? irc.openprojects.net / #kernelnewbies http://www.conectiva.com/ http://www.surriel.com/
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sun Apr 23 2000 - 21:00:19 EST