From: Johannes Weiner <hannes@cmpxchg.org>
To: "Huang, Ying" <ying.huang@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
"Kirill A. Shutemov" <kirill@shutemov.name>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH -mm -v10 3/3] mm, THP, swap: Enable THP swap optimization only if has compound map
Date: Tue, 25 Apr 2017 17:46:18 -0400 [thread overview]
Message-ID: <20170425214618.GB6841@cmpxchg.org> (raw)
In-Reply-To: <20170425125658.28684-4-ying.huang@intel.com>
On Tue, Apr 25, 2017 at 08:56:58PM +0800, Huang, Ying wrote:
> From: Huang Ying <ying.huang@intel.com>
>
> If there is no compound map for a THP (Transparent Huge Page), it is
> possible that the map count of some sub-pages of the THP is 0. So it
> is better to split the THP before swapping out. In this way, the
> sub-pages not mapped will be freed, and we can avoid the unnecessary
> swap out operations for these sub-pages.
>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
CC Kirill to double check the reasoning here
> ---
> mm/swap_state.c | 16 +++++++++++++---
> 1 file changed, 13 insertions(+), 3 deletions(-)
>
> diff --git a/mm/swap_state.c b/mm/swap_state.c
> index 006d91d8fc53..13f83c6bb1b4 100644
> --- a/mm/swap_state.c
> +++ b/mm/swap_state.c
> @@ -192,9 +192,19 @@ int add_to_swap(struct page *page, struct list_head *list)
> VM_BUG_ON_PAGE(!PageLocked(page), page);
> VM_BUG_ON_PAGE(!PageUptodate(page), page);
>
> - /* cannot split, skip it */
> - if (PageTransHuge(page) && !can_split_huge_page(page, NULL))
> - return 0;
> + if (PageTransHuge(page)) {
> + /* cannot split, skip it */
> + if (!can_split_huge_page(page, NULL))
> + return 0;
> + /*
> + * Split pages without a PMD map right away. Chances
> + * are some or all of the tail pages can be freed
> + * without IO.
> + */
> + if (!compound_mapcount(page) &&
> + split_huge_page_to_list(page, list))
> + return 0;
> + }
>
> retry:
> entry = get_swap_page(page);
> --
> 2.11.0
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Johannes Weiner <hannes@cmpxchg.org>
To: "Huang, Ying" <ying.huang@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
"Kirill A. Shutemov" <kirill@shutemov.name>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH -mm -v10 3/3] mm, THP, swap: Enable THP swap optimization only if has compound map
Date: Tue, 25 Apr 2017 17:46:18 -0400 [thread overview]
Message-ID: <20170425214618.GB6841@cmpxchg.org> (raw)
In-Reply-To: <20170425125658.28684-4-ying.huang@intel.com>
On Tue, Apr 25, 2017 at 08:56:58PM +0800, Huang, Ying wrote:
> From: Huang Ying <ying.huang@intel.com>
>
> If there is no compound map for a THP (Transparent Huge Page), it is
> possible that the map count of some sub-pages of the THP is 0. So it
> is better to split the THP before swapping out. In this way, the
> sub-pages not mapped will be freed, and we can avoid the unnecessary
> swap out operations for these sub-pages.
>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
CC Kirill to double check the reasoning here
> ---
> mm/swap_state.c | 16 +++++++++++++---
> 1 file changed, 13 insertions(+), 3 deletions(-)
>
> diff --git a/mm/swap_state.c b/mm/swap_state.c
> index 006d91d8fc53..13f83c6bb1b4 100644
> --- a/mm/swap_state.c
> +++ b/mm/swap_state.c
> @@ -192,9 +192,19 @@ int add_to_swap(struct page *page, struct list_head *list)
> VM_BUG_ON_PAGE(!PageLocked(page), page);
> VM_BUG_ON_PAGE(!PageUptodate(page), page);
>
> - /* cannot split, skip it */
> - if (PageTransHuge(page) && !can_split_huge_page(page, NULL))
> - return 0;
> + if (PageTransHuge(page)) {
> + /* cannot split, skip it */
> + if (!can_split_huge_page(page, NULL))
> + return 0;
> + /*
> + * Split pages without a PMD map right away. Chances
> + * are some or all of the tail pages can be freed
> + * without IO.
> + */
> + if (!compound_mapcount(page) &&
> + split_huge_page_to_list(page, list))
> + return 0;
> + }
>
> retry:
> entry = get_swap_page(page);
> --
> 2.11.0
next prev parent reply other threads:[~2017-04-25 21:46 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-25 12:56 [PATCH -mm -v10 0/3] THP swap: Delay splitting THP during swapping out Huang, Ying
2017-04-25 12:56 ` Huang, Ying
2017-04-25 12:56 ` [PATCH -mm -v10 1/3] mm, THP, swap: Delay splitting THP during swap out Huang, Ying
2017-04-25 12:56 ` Huang, Ying
[not found] ` <20170425125658.28684-2-ying.huang-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
2017-04-27 5:31 ` Minchan Kim
2017-04-27 5:31 ` Minchan Kim
2017-04-27 5:31 ` Minchan Kim
2017-04-27 7:12 ` Huang, Ying
2017-04-27 7:12 ` Huang, Ying
2017-04-27 7:12 ` Huang, Ying
[not found] ` <87mvb21fz1.fsf-5/hDr2MS57EDqwDYnZuMFFaTQe2KTcn/@public.gmane.org>
2017-04-27 13:37 ` Johannes Weiner
2017-04-27 13:37 ` Johannes Weiner
2017-04-27 13:37 ` Johannes Weiner
2017-04-28 8:40 ` Minchan Kim
2017-04-28 8:40 ` Minchan Kim
2017-04-28 12:21 ` Huang, Ying
2017-04-28 12:21 ` Huang, Ying
[not found] ` <87d1bwvi26.fsf-5/hDr2MS57EDqwDYnZuMFFaTQe2KTcn/@public.gmane.org>
2017-05-10 1:03 ` Minchan Kim
2017-05-10 1:03 ` Minchan Kim
2017-05-10 1:03 ` Minchan Kim
2017-05-01 10:44 ` Johannes Weiner
2017-05-01 10:44 ` Johannes Weiner
2017-05-01 10:44 ` Johannes Weiner
2017-05-01 23:53 ` Minchan Kim
2017-05-01 23:53 ` Minchan Kim
2017-05-01 23:53 ` Minchan Kim
2017-05-10 13:56 ` Johannes Weiner
2017-05-10 13:56 ` Johannes Weiner
[not found] ` <20170510135654.GD17121-druUgvl0LCNAfugRpC6u6w@public.gmane.org>
2017-05-10 23:25 ` Minchan Kim
2017-05-10 23:25 ` Minchan Kim
2017-05-10 23:25 ` Minchan Kim
2017-05-11 0:50 ` Huang, Ying
2017-05-11 0:50 ` Huang, Ying
2017-05-11 0:50 ` Huang, Ying
[not found] ` <87h90sb4jq.fsf-5/hDr2MS57EDqwDYnZuMFFaTQe2KTcn/@public.gmane.org>
2017-05-11 4:31 ` Minchan Kim
2017-05-11 4:31 ` Minchan Kim
2017-05-11 4:31 ` Minchan Kim
2017-05-12 2:21 ` [PATCH 1/2] mm: swap: unify swap slot free functions to put_swap_page Minchan Kim
2017-05-12 2:21 ` Minchan Kim
2017-05-12 2:21 ` [PATCH 2/2] mm: swap: move anonymous THP split logic to vmscan Minchan Kim
2017-05-12 2:21 ` Minchan Kim
2017-05-12 16:48 ` Johannes Weiner
2017-05-12 16:48 ` Johannes Weiner
2017-05-12 16:47 ` [PATCH 1/2] mm: swap: unify swap slot free functions to put_swap_page Johannes Weiner
2017-05-12 16:47 ` Johannes Weiner
2017-05-11 1:22 ` [PATCH -mm -v10 1/3] mm, THP, swap: Delay splitting THP during swap out Minchan Kim
2017-05-11 1:22 ` Minchan Kim
2017-05-11 10:40 ` Johannes Weiner
2017-05-11 10:40 ` Johannes Weiner
2017-05-12 1:34 ` Minchan Kim
2017-05-12 1:34 ` Minchan Kim
2017-04-25 12:56 ` [PATCH -mm -v10 2/3] mm, THP, swap: Check whether THP can be split firstly Huang, Ying
2017-04-25 12:56 ` Huang, Ying
2017-04-25 21:43 ` Johannes Weiner
2017-04-25 21:43 ` Johannes Weiner
2017-04-25 12:56 ` [PATCH -mm -v10 3/3] mm, THP, swap: Enable THP swap optimization only if has compound map Huang, Ying
2017-04-25 12:56 ` Huang, Ying
2017-04-25 21:46 ` Johannes Weiner [this message]
2017-04-25 21:46 ` Johannes Weiner
2017-04-28 13:16 ` Kirill A. Shutemov
2017-04-28 13:16 ` Kirill A. Shutemov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20170425214618.GB6841@cmpxchg.org \
--to=hannes@cmpxchg.org \
--cc=akpm@linux-foundation.org \
--cc=kirill@shutemov.name \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ying.huang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.