Re: [PATCH] mm, memcg: reclaim more aggressively before high allocator throttling

[Chris Down]

Shakeel Butt writes:
> What was the initial reason to have different behavior in the first place?

This differing behaviour is simply a mistake, it was never intended to be this 
deviate from what happens elsewhere. To that extent this patch is as much a bug 
fix as it is an improvement.

> >  static void high_work_func(struct work_struct *work)
> > @@ -2378,16 +2384,20 @@ void mem_cgroup_handle_over_high(void)
> >  {
> >         unsigned long penalty_jiffies;
> >         unsigned long pflags;
> > +       unsigned long nr_reclaimed;
> >         unsigned int nr_pages = current->memcg_nr_pages_over_high;
>
> Is there any benefit to keep current->memcg_nr_pages_over_high after
> this change? Why not just use SWAP_CLUSTER_MAX?

I don't feel strongly either way, but current->memcg_nr_pages_over_high can be 
very large for large allocations.

That said, maybe we should just reclaim `max(SWAP_CLUSTER_MAX, current - high)` 
for each loop? I agree that with this design it looks like perhaps we don't 
need it any more.

Johannes, what do you think?