Messages in this thread | | | Date | Sat, 10 Apr 1999 13:30:36 -0400 (EDT) | From | Chuck Lever <> | Subject | Re: more on hash functions |
| |
On Sat, 10 Apr 1999, Alan Cox wrote: > > thanks for the information. the missing piece, though, is how expensive > > is a multiplication operation relative to a couple of memory references? > > that's the direct trade-off when tuning these hash tables. > > Van Jacobson uses a 2K lookup table for his CBQ code on the sun4c. I trust Van's > optimising knowledge..
yes, there are several important hash tables in Linux that are 1024 buckets or smaller, and i believe that has some effect on system throughput, even on the smallest machines. do you know what VJ's hash function is?
agreed that multiplication should be avoided. however, in some cases nothing else works.
- 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/
| |