Re: [PATCH 2/2] sched/numa: Apply remote socket distance averaging for Hygon 7447V

[Ingo Molnar]

* Chaohong Guo <guochaohong@xxxxxxxxxxxxxx> wrote:

> The following diagram illustrates the node topology (two packages, six
> nodes each):
> 
>              package 0                        package 1
> 
>            ----------------------------------------------
>            |            --------------------            |
>            |            |                  |            |
>         ------       -------             ------       ------
>         |  0  |------|  3  |             | 6  |-------| 9  |
>         ------       -------             -----        -----
>            |            |                  |            |
>         -------      -------             -----        ------
>         |  5  |------|  2  |             | 11 |-------| 8  |
>         -------      -------             -----        -----
>            |            |                  |            |
>         -------      -------             -----        ------
>         |  4  |------|  1  |             | 10 |-------| 7  |
>         ------       -------             -----        ------
>            |            |                  |            |
>            |            --------------------            |
>            ----------------------------------------------
> 
> From the perspective of CPUs in node 0, sched domains:
>   numa-level 1 : [0]  [3] [5]
>   numa-level 2:  [0, 3, 5], [2], [4]
>   numa-level 3:  [0, 2, 3, 4, 5], [1, 2, 3, 4, 5]
>   numa-level 4:  [0-5], [9]
>   numa-level 5:  [0-5, 9], [6], [8]
>   numa-level 6:  [0-6, 8, 9], [7], [11]
>   numa-level 7:  [0-9], [2-11]
> 
> NUMA level 5-7， nodes in different socket are grouped together,which
> caused CPUs in remote socket are chosen while load balancing.
> 
> For better perfornace, we do the same as Intel is doing on intel GNR/CWF.

Could you please include the before/after sched domains topology
in the changelog. Looks good otherwise.

Thanks,

	Ingo