Re: [linux-next:master] [vmalloc] 60ced5818f: stress-ng.shm.ops_per_sec 7.2% regression

Hi David,

[...]
 
> Looking at the original results, I spotted
> 
>     354997 ± 14%    +111.6%     751255 ±  4%  meminfo.PageTables
> 
> So we consumed twice the (process) page tables. Did you also manage to reproduce
> that or do you have an explanation for that?

Unfortunately not, When I tried with the reproduce scripts and see the
peek usage of meminfo for Pagetable, it's almost the same (from 90000KB ~
100,000KB), I couldn't observe the this drasmatic usage increase via
this testcase. So I think this is not for this patch.

> 
> > 
> > Given that the regression appears to be driven by a synthetic workload that
> > combines frequent shmem page faults with repeated stack allocation/free operations,
> > I do not think this is a significant concern for typical real-world workloads.
> 
> Yeah, if it's "we have less fragmentation", I agree. Using order-2 folios for
> shmem would likely similarly mitigate the problem I assume.
> 

Agree. Thanks!

-- 
Sincerely,
Yeoreum Yun