* Frederic Weisbecker <fweisbec@xxxxxxxxx> wrote: > I missed this one. because i just posted it :) > Wouldn't your previous idea of a cmpxchg global clock be > better? Perhaps it would scale better while tracing on many > cpus. a cmpxchg global clock has exactly the same cacheline-bouncing properties as the lock here, so there's no real difference. Ingo -- To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html