On Thu, Jan 07, 2021 at 11:33:25AM +0100, Vincent Guittot wrote: > Active balance is triggered for a number of voluntary cases like misfit > or pinned tasks cases but also after that a number of load balance > attempts failed to migrate a task. There is no need to use active load > balance when the group is overloaded because an overloaded state means > that there is at least one waiting task. Nevertheless, the waiting task > is not selected and detached until the threshold becomes higher than its > load. This threshold increases with the number of failed lb (see the > condition if ((load >> env->sd->nr_balance_failed) > env->imbalance) in > detach_tasks()) and the waiting task will end up to be selected after a > number of attempts. > > Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org>
I didn't see major problems so. Acked-by: Mel Gorman <mgor...@suse.de> Like you, I do not see significant performance differences, either positive or negative (minor gains and losses that are borderline). However, I didn't track the stats necessary to see what impact it had on alb_* stats which is an oversight but schedstat tracking interferes with results on its own. It would have been nice to see how often this case is even hit in the overloaded case. -- Mel Gorman SUSE Labs
