Re: [LKP] [mm] ac5b2c1891: vm-scalability.throughput -61.3% regression

[Michal Hocko]

On Wed 12-12-18 12:00:16, Andrea Arcangeli wrote:
[...]
> Adding MADV_THISNODE/MADV_NODE_RECLAIM, will guarantee his proprietary
> software binary will run at maximum performance without cache
> interference, and he's happy to accept the risk of massive slowdown in
> case the local node is truly OOM. The fallback, despite very
> inefficient, will still happen without OOM killer triggering.

I believe this fits much better into a MPOL_$FOO rather than MADV_$FOO.
But other than that I full agree. There are reasonable usecases for the
node reclaim like behavior. As a bonus you do not get local node only
but all nodes within reclaim distance as well.
-- 
Michal Hocko
SUSE Labs