Messages in this thread | | | Date | Fri, 13 Jun 2014 11:34:39 -0500 (CDT) | From | Christoph Lameter <> | Subject | Re: [PATCH -mm v2 8/8] slab: make dead memcg caches discard free slabs immediately |
| |
On Thu, 12 Jun 2014, Joonsoo Kim wrote:
> BTW, I have a question about cache_reap(). If there are many kmemcg > users, we would have a lot of slab caches and just to traverse slab > cache list could take some times. Is it no problem?
Its a big problem and one of the reasons that SLUB was developed. Cache reaping caused noticable random delays to processing which was significantly impacting HPC loads of SGI.
| |