Messages in this thread | | | Date | Thu, 20 May 1999 20:03:45 +0100 (GMT) | From | Matthew Kirkwood <> | Subject | Re: andrea buffer code (2.2.9-C.gz) |
| |
On Wed, 19 May 1999, Manfred Spraul wrote:
> > You know: to scale better you need to waste > > more memory :-).
> Then you have NT: They prove that if you decide everywhere 'scale' > instead of 'effective', the result becomes bloated & not much faster.
Indeed. In cases like these, might it make some sense to have some fixed number of spinlocks and choose which to use with some reductive function? You'd probably want something with a little less overhead than the usual hash functions, of course, but 1K locks or so might well perform better that one or 32K of them.
Matthew.
- 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/
| |