Re: [PATCH] sched:Prefer numa hotness over cache hotness

[Rik van Riel <riel@redhat.com>]

On 06/10/2015 03:03 AM, Srikar Dronamraju wrote:
> The current load balancer may not try to prevent a task from moving out
> of a preferred node to a less preferred node. The reason for this being:
> 
> - Since sched features NUMA and NUMA_RESIST_LOWER are disabled by
>   default, migrate_degrades_locality() always returns false.
> 
> - Even if NUMA_RESIST_LOWER were to be enabled, if its cache hot,
>   migrate_degrades_locality() never gets called.
> 
> The above behaviour can mean that tasks can move out of their preferred
> node but they may be eventually be brought back to their preferred node
> by numa balancer (due to higher numa faults).
> 
> To avoid the above, this commit merges migrate_degrades_locality() and
> migrate_improves_locality(). It also replaces 3 sched features NUMA,
> NUMA_FAVOUR_HIGHER and NUMA_RESIST_LOWER by a single sched feature NUMA.

I had been looking at merging the two at well, but ran
into a dead end because I failed to reorder NUMA and
cache_hot testing.  Nice work.

> Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>

Acked-by: Rik van Riel <riel@redhat.com>

-- 
All rights reversed