Re: [memcg] 0f12156dff: will-it-scale.per_process_ops -33.6% regression

[Tejun Heo]

On Tue, Sep 07, 2021 at 11:18:21AM -0600, Jens Axboe wrote:
> A purely time based approach might be problematic, as you can allocate a
> LOT of data in a short amount of time. Heuristics probably need to be a
> hybrid of "time much time has passed" OR "we're over the front cache
> threshold in terms of deferred accounting". But yes, I don't see why
> we'd necessarily need different approaches for short vs long life times.

Yeah, it'd need some heuristics to guard against the cache exploding and a
lot of laziness in expiration logic but none of those should be too
complicated.

Thanks.

-- 
tejun