Messages in this thread | | | Date | Wed, 15 Jun 2016 06:42:18 +0800 | From | Yuyang Du <> | Subject | Re: [rfc patch] sched/fair: Use instantaneous load for fork/exec balancing |
| |
On Tue, Jun 14, 2016 at 09:58:31AM +0200, Mike Galbraith wrote: > SUSE's regression testing noticed that... > > 0905f04eb21f sched/fair: Fix new task's load avg removed from source CPU in wake_up_new_task() > > ...introduced a hackbench regression, and indeed it does. I think this > regression has more to do with randomness than anything else, but in > general... > > While averaging calms down load balancing, helping to keep migrations > down to a dull roar, it's not completely wonderful when it comes to > things that live in the here and now, hackbench being one such. > > time sh -c 'for i in `seq 1000`; do hackbench -p -P > /dev/null; done' > > real 0m55.397s > user 0m8.320s > sys 5m40.789s > > echo LB_INSTANTANEOUS_LOAD > /sys/kernel/debug/sched_features > > real 0m48.049s > user 0m6.510s > sys 5m6.291s > > Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com>
I am entirely for giving it a "clear unadulterated reality", and even more for it an option.
Reviewed-by: Yuyang Du <yuyang.du@intel.com>
| |