From: Vlastimil Babka <vbabka@suse.cz>
To: Heesub Shin <heesub.shin@samsung.com>,
Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
Mel Gorman <mgorman@suse.de>, Dongjun Shin <d.j.shin@samsung.com>,
Sunghwan Yun <sunghwan.yun@samsung.com>
Subject: Re: [PATCH 2/2] mm/compaction: fix to initialize free scanner properly
Date: Mon, 07 Apr 2014 16:46:12 +0200 [thread overview]
Message-ID: <5342BA34.8050006@suse.cz> (raw)
In-Reply-To: <1396515424-18794-2-git-send-email-heesub.shin@samsung.com>
On 04/03/2014 10:57 AM, Heesub Shin wrote:
> Free scanner does not works well on systems having zones which do not
> span to pageblock-aligned boundary.
>
> zone->compact_cached_free_pfn is reset when the migration and free
> scanner across or compaction restarts. After the reset, if end_pfn of
> the zone was not aligned to pageblock_nr_pages, free scanner tries to
> isolate free pages from the middle of pageblock to the end, which can
> be very small range.
Hm good catch. I think that the same problem can happen (at least
theoretically) through zone->compact_cached_free_pfn with
CONFIG_HOLES_IN_ZONE enabled. Then compact_cached_free_pfn could be set
to a non-aligned-to-pageblock pfn and spoil scans. I'll send a patch
that solves it on isolate_freepages() level, which allows further
simplification of the function.
Vlastimil
> Signed-off-by: Heesub Shin <heesub.shin@samsung.com>
> Cc: Dongjun Shin <d.j.shin@samsung.com>
> Cc: Sunghwan Yun <sunghwan.yun@samsung.com>
> ---
> mm/compaction.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/mm/compaction.c b/mm/compaction.c
> index 1ef9144..fefe1da 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -983,7 +983,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
> */
> cc->migrate_pfn = zone->compact_cached_migrate_pfn;
> cc->free_pfn = zone->compact_cached_free_pfn;
> - if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) {
> + if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) {
> cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1);
> zone->compact_cached_free_pfn = cc->free_pfn;
> }
>
--
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: Vlastimil Babka <vbabka@suse.cz>
To: Heesub Shin <heesub.shin@samsung.com>,
Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
Mel Gorman <mgorman@suse.de>, Dongjun Shin <d.j.shin@samsung.com>,
Sunghwan Yun <sunghwan.yun@samsung.com>
Subject: Re: [PATCH 2/2] mm/compaction: fix to initialize free scanner properly
Date: Mon, 07 Apr 2014 16:46:12 +0200 [thread overview]
Message-ID: <5342BA34.8050006@suse.cz> (raw)
In-Reply-To: <1396515424-18794-2-git-send-email-heesub.shin@samsung.com>
On 04/03/2014 10:57 AM, Heesub Shin wrote:
> Free scanner does not works well on systems having zones which do not
> span to pageblock-aligned boundary.
>
> zone->compact_cached_free_pfn is reset when the migration and free
> scanner across or compaction restarts. After the reset, if end_pfn of
> the zone was not aligned to pageblock_nr_pages, free scanner tries to
> isolate free pages from the middle of pageblock to the end, which can
> be very small range.
Hm good catch. I think that the same problem can happen (at least
theoretically) through zone->compact_cached_free_pfn with
CONFIG_HOLES_IN_ZONE enabled. Then compact_cached_free_pfn could be set
to a non-aligned-to-pageblock pfn and spoil scans. I'll send a patch
that solves it on isolate_freepages() level, which allows further
simplification of the function.
Vlastimil
> Signed-off-by: Heesub Shin <heesub.shin@samsung.com>
> Cc: Dongjun Shin <d.j.shin@samsung.com>
> Cc: Sunghwan Yun <sunghwan.yun@samsung.com>
> ---
> mm/compaction.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/mm/compaction.c b/mm/compaction.c
> index 1ef9144..fefe1da 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -983,7 +983,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
> */
> cc->migrate_pfn = zone->compact_cached_migrate_pfn;
> cc->free_pfn = zone->compact_cached_free_pfn;
> - if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) {
> + if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) {
> cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1);
> zone->compact_cached_free_pfn = cc->free_pfn;
> }
>
next prev parent reply other threads:[~2014-04-07 14:46 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-04-03 8:57 [PATCH 1/2] mm/compaction: clean up unused code lines Heesub Shin
2014-04-03 8:57 ` Heesub Shin
2014-04-03 8:57 ` [PATCH 2/2] mm/compaction: fix to initialize free scanner properly Heesub Shin
2014-04-03 8:57 ` Heesub Shin
2014-04-07 14:46 ` Vlastimil Babka [this message]
2014-04-07 14:46 ` Vlastimil Babka
2014-04-15 9:18 ` [PATCH 1/2] mm/compaction: make isolate_freepages start at pageblock boundary Vlastimil Babka
2014-04-15 9:18 ` Vlastimil Babka
2014-04-15 9:18 ` [PATCH 2/2] mm/compaction: cleanup isolate_freepages() Vlastimil Babka
2014-04-15 9:18 ` Vlastimil Babka
2014-04-16 1:53 ` Joonsoo Kim
2014-04-16 1:53 ` Joonsoo Kim
2014-04-16 15:49 ` Rik van Riel
2014-04-16 15:49 ` Rik van Riel
2014-04-17 0:07 ` Minchan Kim
2014-04-17 0:07 ` Minchan Kim
2014-04-21 19:41 ` Andrew Morton
2014-04-21 19:41 ` Andrew Morton
2014-04-21 21:43 ` Vlastimil Babka
2014-04-21 21:43 ` Vlastimil Babka
2014-04-21 23:53 ` Minchan Kim
2014-04-21 23:53 ` Minchan Kim
2014-04-22 6:33 ` Vlastimil Babka
2014-04-22 6:33 ` Vlastimil Babka
2014-04-22 6:52 ` Minchan Kim
2014-04-22 6:52 ` Minchan Kim
2014-04-22 13:17 ` Vlastimil Babka
2014-04-22 13:17 ` Vlastimil Babka
2014-04-23 2:58 ` Joonsoo Kim
2014-04-23 2:58 ` Joonsoo Kim
2014-04-23 7:30 ` Vlastimil Babka
2014-04-23 7:30 ` Vlastimil Babka
2014-04-23 13:54 ` Joonsoo Kim
2014-04-23 13:54 ` Joonsoo Kim
2014-04-23 14:31 ` Vlastimil Babka
2014-04-23 14:31 ` Vlastimil Babka
2014-04-25 8:29 ` Joonsoo Kim
2014-04-25 8:29 ` Joonsoo Kim
2014-04-29 8:40 ` Vlastimil Babka
2014-04-29 8:40 ` Vlastimil Babka
2014-05-01 1:58 ` Michal Nazarewicz
2014-04-16 1:52 ` [PATCH 1/2] mm/compaction: make isolate_freepages start at pageblock boundary Joonsoo Kim
2014-04-16 1:52 ` Joonsoo Kim
2014-04-16 15:47 ` Rik van Riel
2014-04-16 15:47 ` Rik van Riel
2014-04-16 23:43 ` Minchan Kim
2014-04-16 23:43 ` Minchan Kim
2014-04-07 14:40 ` [PATCH 1/2] mm/compaction: clean up unused code lines Vlastimil Babka
2014-04-07 14:40 ` Vlastimil Babka
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=5342BA34.8050006@suse.cz \
--to=vbabka@suse.cz \
--cc=akpm@linux-foundation.org \
--cc=d.j.shin@samsung.com \
--cc=heesub.shin@samsung.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=sunghwan.yun@samsung.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.