Kevin Littlejohn wrote:
> I'm not sure how you achieve this - given the request pattern is random?
Reads are random, but elevator seeking eleminates many stupid seeks.
Yes, there still is some randomness, but with a non-random pattern.
Elevator seeking takes into account that disks are fast for requests on
the same or a adjacent track, but slow on longer seeks. The cyclic
nature also guarantees that no request starves. Elevator cycle time is
also a good measure on how loaded the disk is.
It may be possible to cluster related objects and use intelligent
prefetching for hits to further minimize seeks on cache hits by
sacrifying some memory. In a FIFO cache chances are high that related
objects are close to each other.
/Henrik
Received on Tue Jul 29 2003 - 13:15:56 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:12:02 MST