Messages in this thread | | | Date | Fri, 30 Jan 2009 08:04:01 -0800 (PST) | From | Linus Torvalds <> | Subject | Re: [PATCH -v3] use per cpu data for single cpu ipi calls |
| |
On Fri, 30 Jan 2009, Peter Zijlstra wrote: > > Signed-off-by: Steven Rostedt <srostedt@redhat.com> > Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
My only question is whetherr we might even drop the kmalloc() some day: I suspect that the CSD_FLAG_LOCK is essentially never a contention point, and the cost (and occasional synchronization) of kmalloc() quite possibly overwhelms any theoretical scaling ability.
If another CPU hasn't even received its IPI before the same CPU sends the next one, I'm not sure we _want_ to send one, in fact.
But that's a secondary issue, and isn't a correctness thing, just a "do we really need three different allocations?" musing..
Linus
| |