Re: [PATCH] mm-vmscan-dont-mess-with-pgdat-flags-in-memcg-reclaim-v2-fix

[Johannes Weiner]

On Fri, Apr 06, 2018 at 04:52:15PM +0300, Andrey Ryabinin wrote:
> On 04/06/2018 05:13 AM, Shakeel Butt wrote:
> > Question: Should this 'flags' be per-node? Is it ok for a congested
> > memcg to call wait_iff_congested for all nodes?
> 
> Indeed, congestion state should be pre-node. If memcg on node A is
> congested, there is no point is stalling memcg reclaim from node B.
> 
> Make congestion state per-cgroup-per-node and record it in
> 'struct mem_cgroup_per_node'.
> 
> Signed-off-by: Andrey Ryabinin <aryabinin@xxxxxxxxxxxxx>

Thanks for fixing this, Andrey. This is great.

For the combined patch and this fix:

Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>