Re: [PATCH v4] memcg: expose socket memory pressure in a cgroup

[Matyas Hurtik <matyas.hurtik@cdn77.com>]

Hello,

On 8/20/25 9:03 PM, Tejun Heo wrote:
> On Wed, Aug 20, 2025 at 06:51:07PM +0200, Matyas Hurtik wrote:
>> And the read side:   total_duration = 0;   for (; 
>> !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg))     
>> total_duration += atomic_long_read(&memcg->socket_pressure_duration); 
>> Would that work? 
> This doesn't make sense to me. Why would a child report the numbers 
> from its ancestors?

Result of mem_cgroup_under_socket_pressure() depends on
whether self or any ancestors have had socket_pressure set.

So any duration of an ancestor being throttled would also
mean the child was being throttled.

By summing our and our ancestors socket_pressure_duration
we should get our total time being throttled
(possibly more because of overlaps).

Thanks,
Matyas