On Wed, 2014-05-07 at 15:00 +0200, Peter Zijlstra wrote: > On Tue, May 06, 2014 at 07:33:07PM -0700, Davidlohr Bueso wrote: > > > So I've been running benchmarks (mostly aim7, which nicely exercises our > > locks) comparing my recent v4 for rwsem optimistic spinning against > > previous implementation ideas for the anon-vma lock, mostly: > > > - rwlock_t > > - qrwlock_t > > Which reminds me; can you provide the numbers for rwlock_t vs qrwlock_t > in a numeric form so I can include them in the qrwlock_t changelog. Ah, right. I was lazy and just showed you the graphs. > That way I can queue those patches for inclusion, I think we want a fair > rwlock_t if we can show (and you graphs do iirc) that it doesn't cost us > performance. I agree, fairness is much welcome here. And I agree that despite my good numbers, and that we should keep the anon vma lock as a rwsem, its still worth merging the qrwlock stuff. I'll cookup my regular numeric table today. Thanks, Davidlohr -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>