* Peter Zijlstra <[email protected]> [2018-10-24 12:03:23]: > It appears to me the for_each_online_node() iteration in > task_numa_migrate() needs an addition test to see if the selected node > has any CPUs in the relevant sched_domain _at_all_. >
Yes, this should work. Yi Wang does this extra check a little differently. http://lkml.kernel.org/r/[email protected] However the last time I had posted you didn't like that approach. http://lkml.kernel.org/r/[email protected] Further, I would think the number of times, we would be calling sched_setaffinity would be far less than task_numa_migrate(). In the regular case, where we never have isolcpus, we add this extra check. Also what does it mean for a task to have its cpu affinity set to a mix of isolcpus and non isolcpus. Also should we be updating update_numa_stats accordingly? While the problem may not be apparent there but we are counting the load and compute capacity of isolcpus. -- Thanks and Regards Srikar Dronamraju
