Messages in this thread | | | Date | Wed, 31 Mar 1999 23:53:53 -0500 (EST) | From | Chuck Lever <> | Subject | Re: buffer cache behavior on memory-constrained systems (fwd) |
| |
On Wed, 31 Mar 1999, Ricardo Galli Granada wrote: > > >also, i think the page LRU approach is a clever way to solve the buffer > > >reclamation problem. do you know how close to optimal (in terms of > > >keeping the most used buffers in memory, and expelling the least used > > >ones) it is? > > > > It should be optimal according to my instinct, but I didn't do math on > > it... > > According to empirical results (I doubt there is any analytic > demonstration) that you can find in any good OS book, LRU is the > algorithm which is most closed the OPT algorithm (select the page wich > will be used more far away in the future) for page replacement.
the reason i asked "how optimal" is because the LRU algorithm Andrea added was for *pages*, not for buffers. i'm curious how close to LRU buffer replacement we can get with LRU *page* replacement.
- Chuck Lever -- corporate: <chuckl@netscape.com> personal: <chucklever@netscape.net> or <cel@monkey.org>
The Linux Scalability project: http://www.citi.umich.edu/projects/citi-netscape/
- 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/
| |