On Sat, Dec 18, 2010 at 11:20 PM, Alan Stern <stern@xxxxxxxxxxxxxxxxxxx> wrote: >> They would also gain deterministic and controllable behavior that we >> can't guarantee when we rely on a context switch, because obviously >> the latter yields different results for different platforms and >> workloads (for the exact same subsystem). > > Like I said before, it's a trade-off. There are arguments for both > sides, and which is better is unclear. Rafael has to make a judgment > call. This calls for power measurements and analysis which may demonstrate whether such a change is beneficial or not (and if yes, how much, and under which workloads/setups). Sadly I don't have the equipment to perform those measurements, which I think are imperative to justify such a patch: IMHO the commit log must include numbers... Again, Rafael and Alan, thanks for your time and attention. Ohad. _______________________________________________ linux-pm mailing list linux-pm@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linux-foundation.org/mailman/listinfo/linux-pm
