Re: mm/hugetlb.c/alloc_fresh_huge_page(): slow division on NUMA

From: Andreas Mohr
Date: Thu Mar 23 2006 - 06:53:14 EST


On Thu, Mar 23, 2006 at 03:47:50AM -0800, Andrew Morton wrote:
> Andreas Mohr <andi@xxxxxxxxxxxxxxxxxxxxxxx> wrote:
> >
> > on NUMA there
> > indeed is an idiv opcode in the mm/hugetlb.o output:
> >
> > 138: e8 fc ff ff ff call 139 <alloc_fresh_huge_page+0x32>
> Stop looking at ancient 2.6.16 kernels. That code isn't there any more ;)
Hrmpf. I had just gotten some awful suspicion when looking at 2.6.16-mm1
changelog mentioning hugemem changes. Oh well...

I'm going to hunt for similar modulo cases in the future.

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at
Please read the FAQ at