Hello,
On (05/09/16 17:07), Minchan Kim wrote:
[..]
> > Depending on the circumstances, OBJ_ALLOCATED can become less
> > than OBJ_USED, which can result in either very high or negative
> > `total_scan' value calculated in do_shrink_slab().
>
> So, do you see pr_err("shrink_slab: %pF negative obj
Hello Sergey,
On Mon, May 09, 2016 at 04:35:33PM +0900, Sergey Senozhatsky wrote:
> zs_can_compact() has two race conditions in its core calculation:
>
> unsigned long obj_wasted = zs_stat_get(class, OBJ_ALLOCATED) -
> zs_stat_get(class, OBJ_USED);
>
> 1) classes ar
2 matches
Mail list logo
