On Wed, 2014-07-23 at 08:57 +0200, Peter Zijlstra wrote: > On Wed, Jul 23, 2014 at 06:55:03AM +0200, Mike Galbraith wrote: > > On Mon, 2014-07-21 at 09:42 -0700, Andi Kleen wrote: > > > > > FWIW the main problem is currently that switch-through-idle is so > > > slow. I think improving that would give a boost to far more > > > situations. > > > > Two high frequency idle enter/exit suckage spots: > > > > 1) nohz (tick) - it's expensive to start/stop tick on every micro-idle, > > throttle it or something. > > Yeah, so the idea was to use the cpuidle idle guestimator to control > this, and now that we've moved it somewhat closer to the scheduler that > might become possible. > > > 2) ondemand governor - tweak silly default settings to reflect the > > reality that we routinely schedule communicating threads cross core. > > Yeah, so the plan is to shoot cpufreq in the head and base the > replacement on smp aware metrics ;-) Its on a todo list somewhere.. It never ceases to amaze me that people aren't screaming bloody murder about those two spots. Watching performance of lightly loaded boxen is enough to make a grown man cry. SUSE (and I in all of my many regression testing trees) puts tourniquets on both of these blood spurting gashes, laptops be damned. I also resurrect mwait_idle(), as while you may consider it obsolete, I still love my lovely little Q6600 box (power sucking pig) dearly :) -Mike -- To unsubscribe from this list: send the line "unsubscribe linux-api" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
