Re: [PATCH v2] sched: move h_load calculation to task_h_load

2013-07-16 Thread Peter Zijlstra
On Mon, Jul 15, 2013 at 05:49:19PM +0400, Vladimir Davydov wrote: > The bad thing about update_h_load(), which computes hierarchical load > factor for task groups, is that it is called for each task group in the > system before every load balancer run, and since rebalance can be > triggered very

Re: [PATCH v2] sched: move h_load calculation to task_h_load

2013-07-16 Thread Peter Zijlstra
On Mon, Jul 15, 2013 at 05:49:19PM +0400, Vladimir Davydov wrote: The bad thing about update_h_load(), which computes hierarchical load factor for task groups, is that it is called for each task group in the system before every load balancer run, and since rebalance can be triggered very

[PATCH v2] sched: move h_load calculation to task_h_load

2013-07-15 Thread Vladimir Davydov
The bad thing about update_h_load(), which computes hierarchical load factor for task groups, is that it is called for each task group in the system before every load balancer run, and since rebalance can be triggered very often, this function can eat really a lot of cpu time if there are many cpu

[PATCH v2] sched: move h_load calculation to task_h_load

2013-07-15 Thread Vladimir Davydov
The bad thing about update_h_load(), which computes hierarchical load factor for task groups, is that it is called for each task group in the system before every load balancer run, and since rebalance can be triggered very often, this function can eat really a lot of cpu time if there are many cpu