Re: [RFC][PATCHv3 2/7] zsmalloc: partial page ordering within a fullness_list

From: Sergey Senozhatsky
Date: Mon Jun 29 2015 - 19:41:10 EST


Hello,

Sorry for long reply.

On (06/29/15 15:52), Minchan Kim wrote:
[..]
> > head = &class->fullness_list[fullness];
> > - if (*head)
> > - list_add_tail(&page->lru, &(*head)->lru);
> > + if (*head) {
> > + /*
> > + * We want to see more ZS_FULL pages and less almost
> > + * empty/full. Put pages with higher ->inuse first.
> > + */
> > + if (page->inuse < (*head)->inuse)
> > + list_add_tail(&page->lru, &(*head)->lru);
> > + else
> > + list_add(&page->lru, &(*head)->lru);
> > + }
>
> >
> > *head = page;
>
> Why do you want to always put @page in the head?
> How about this?


Yeah, right. Looks OK to me. How do we want to handle it? Do you want
to submit it with Suggested-by: ss (I'm fine) or you want me to submit
it later today with Suggested-by: Minchan Kim?

-ss

> diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
> index e8cb31c..1c5fde9 100644
> --- a/mm/zsmalloc.c
> +++ b/mm/zsmalloc.c
> @@ -658,21 +658,25 @@ static void insert_zspage(struct page *page, struct size_class *class,
> if (fullness >= _ZS_NR_FULLNESS_GROUPS)
> return;
>
> + zs_stat_inc(class, fullness == ZS_ALMOST_EMPTY ?
> + CLASS_ALMOST_EMPTY : CLASS_ALMOST_FULL, 1);
> +
> head = &class->fullness_list[fullness];
> - if (*head) {
> - /*
> - * We want to see more ZS_FULL pages and less almost
> - * empty/full. Put pages with higher ->inuse first.
> - */
> - if (page->inuse < (*head)->inuse)
> - list_add_tail(&page->lru, &(*head)->lru);
> - else
> - list_add(&page->lru, &(*head)->lru);
> + if (!*head) {
> + *head = page;
> + return;
> }
>
> - *head = page;
> - zs_stat_inc(class, fullness == ZS_ALMOST_EMPTY ?
> - CLASS_ALMOST_EMPTY : CLASS_ALMOST_FULL, 1);
> + /*
> + * We want to see more ZS_FULL pages and less almost
> + * empty/full. Put pages with higher ->inuse first.
> + */
> + list_add_tail(&page->lru, &(*head)->lru);
> + if (page->inuse >= (*head)->inuse)
> + *head = page;
> }
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/