Re: [PATCH V2] mm/hugetlb: Avoid soft lockup in set_max_huge_pages()
From: Naoya Horiguchi
Date: Thu Jul 28 2016 - 02:44:00 EST
On Thu, Jul 28, 2016 at 10:54:02AM +0800, Jia He wrote:
> In powerpc servers with large memory(32TB), we watched several soft
> lockups for hugepage under stress tests.
> The call trace are as follows:
> This patch is to fix such soft lockups. It is safe to call cond_resched()
> there because it is out of spin_lock/unlock section.
> Signed-off-by: Jia He <hejianet@xxxxxxxxx>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
> Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
> Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
> Cc: Michal Hocko <mhocko@xxxxxxxx>
> Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
> Cc: Paul Gortmaker <paul.gortmaker@xxxxxxxxxxxxx>
Looks good to me.
Reviewed-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
> Changes in V2: move cond_resched to a common calling site in set_max_huge_pages
> mm/hugetlb.c | 4 ++++
> 1 file changed, 4 insertions(+)
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index abc1c5f..9284280 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -2216,6 +2216,10 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
> * and reducing the surplus.
> + /* yield cpu to avoid soft lockup */
> + cond_resched();
> if (hstate_is_gigantic(h))
> ret = alloc_fresh_gigantic_page(h, nodes_allowed);