From: Johannes Weiner <hannes@cmpxchg.org>
To: Zi Yan <ziy@nvidia.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Vlastimil Babka <vbabka@suse.cz>,
Mel Gorman <mgorman@techsingularity.net>,
Miaohe Lin <linmiaohe@huawei.com>,
Kefeng Wang <wangkefeng.wang@huawei.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 3/6] mm: page_alloc: move free pages when converting block during isolation
Date: Mon, 11 Sep 2023 16:47:51 -0400 [thread overview]
Message-ID: <20230911204751.GA134811@cmpxchg.org> (raw)
In-Reply-To: <23206152-6E36-453B-B118-6BBAA913441B@nvidia.com>
On Mon, Sep 11, 2023 at 04:17:07PM -0400, Zi Yan wrote:
> On 11 Sep 2023, at 15:41, Johannes Weiner wrote:
>
> > When claiming a block during compaction isolation, move any remaining
> > free pages to the correct freelists as well, instead of stranding them
> > on the wrong list. Otherwise, this encourages incompatible page mixing
> > down the line, and thus long-term fragmentation.
> >
> > Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
> > ---
> > mm/page_alloc.c | 5 ++++-
> > 1 file changed, 4 insertions(+), 1 deletion(-)
> >
> > diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> > index 3db405414174..f6f658c3d394 100644
> > --- a/mm/page_alloc.c
> > +++ b/mm/page_alloc.c
> > @@ -2548,9 +2548,12 @@ int __isolate_free_page(struct page *page, unsigned int order)
> > * Only change normal pageblocks (i.e., they can merge
> > * with others)
> > */
> > - if (migratetype_is_mergeable(mt))
> > + if (migratetype_is_mergeable(mt)) {
> > set_pageblock_migratetype(page,
> > MIGRATE_MOVABLE);
> > + move_freepages_block(zone, page,
> > + MIGRATE_MOVABLE, NULL);
> > + }
> > }
> > }
> >
> > --
> > 2.42.0
>
> Is this needed?
Yes, the problem is if we e.g. isolate half a block, then we'll
convert the type of the whole block but strand the half we're not
isolating. This can be a couple of hundred pages on the wrong list.
> And is this correct?
>
> __isolate_free_page() removes the free page from a free list, but the added
> move_freepages_block() puts the page back to another free list, making
> __isolate_free_page() not do its work. OK. the for loop is going through
> the pages within the pageblock, so move_freepages_block() should be used
> on the rest of the pages on the pageblock.
>
> So to make this correct, the easies change might be move
> del_page_from_free_list(page, zone, order) below this code chunk.
There is a del_page_from_freelist() just above this diff hunk. That
takes the page off the list and clears its PageBuddy.
move_freepages_block() will then move only the remainder of the block
that's still on the freelist with a mismatched type (move_freepages()
only moves buddies).
next prev parent reply other threads:[~2023-09-11 20:47 UTC|newest]
Thread overview: 83+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-09-11 19:41 [PATCH V2 0/6] mm: page_alloc: freelist migratetype hygiene Johannes Weiner
2023-09-11 19:41 ` [PATCH 1/6] mm: page_alloc: remove pcppage migratetype caching Johannes Weiner
2023-09-11 19:59 ` Zi Yan
2023-09-11 21:09 ` Andrew Morton
2023-09-12 13:47 ` Vlastimil Babka
2023-09-12 14:50 ` Johannes Weiner
2023-09-13 9:33 ` Vlastimil Babka
2023-09-13 13:24 ` Johannes Weiner
2023-09-13 13:34 ` Vlastimil Babka
2023-09-12 15:03 ` Johannes Weiner
2023-09-14 7:29 ` Vlastimil Babka
2023-09-14 9:56 ` Mel Gorman
2023-09-27 5:42 ` Huang, Ying
2023-09-27 14:51 ` Johannes Weiner
2023-09-30 4:26 ` Huang, Ying
2023-10-02 14:58 ` Johannes Weiner
2023-09-11 19:41 ` [PATCH 2/6] mm: page_alloc: fix up block types when merging compatible blocks Johannes Weiner
2023-09-11 20:01 ` Zi Yan
2023-09-13 9:52 ` Vlastimil Babka
2023-09-14 10:00 ` Mel Gorman
2023-09-11 19:41 ` [PATCH 3/6] mm: page_alloc: move free pages when converting block during isolation Johannes Weiner
2023-09-11 20:17 ` Zi Yan
2023-09-11 20:47 ` Johannes Weiner [this message]
2023-09-11 20:50 ` Zi Yan
2023-09-13 14:31 ` Vlastimil Babka
2023-09-14 10:03 ` Mel Gorman
2023-09-11 19:41 ` [PATCH 4/6] mm: page_alloc: fix move_freepages_block() range error Johannes Weiner
2023-09-11 20:23 ` Zi Yan
2023-09-13 14:40 ` Vlastimil Babka
2023-09-14 13:37 ` Johannes Weiner
2023-09-14 10:03 ` Mel Gorman
2023-09-11 19:41 ` [PATCH 5/6] mm: page_alloc: fix freelist movement during block conversion Johannes Weiner
2023-09-13 19:52 ` Vlastimil Babka
2023-09-14 14:47 ` Johannes Weiner
2023-09-11 19:41 ` [PATCH 6/6] mm: page_alloc: consolidate free page accounting Johannes Weiner
2023-09-13 20:18 ` Vlastimil Babka
2023-09-14 4:11 ` Johannes Weiner
2023-09-14 23:52 ` [PATCH V2 0/6] mm: page_alloc: freelist migratetype hygiene Mike Kravetz
2023-09-15 14:16 ` Johannes Weiner
2023-09-15 15:05 ` Mike Kravetz
2023-09-16 19:57 ` Mike Kravetz
2023-09-16 20:13 ` Andrew Morton
2023-09-18 7:16 ` Vlastimil Babka
2023-09-18 14:52 ` Johannes Weiner
2023-09-18 17:40 ` Mike Kravetz
2023-09-19 6:49 ` Johannes Weiner
2023-09-19 12:37 ` Zi Yan
2023-09-19 15:22 ` Zi Yan
2023-09-19 18:47 ` Mike Kravetz
2023-09-19 20:57 ` Zi Yan
2023-09-20 0:32 ` Mike Kravetz
2023-09-20 1:38 ` Zi Yan
2023-09-20 6:07 ` Vlastimil Babka
2023-09-20 13:48 ` Johannes Weiner
2023-09-20 16:04 ` Johannes Weiner
2023-09-20 17:23 ` Zi Yan
2023-09-21 2:31 ` Zi Yan
2023-09-21 10:19 ` David Hildenbrand
2023-09-21 14:47 ` Zi Yan
2023-09-25 21:12 ` Zi Yan
2023-09-26 17:39 ` Johannes Weiner
2023-09-28 2:51 ` Zi Yan
2023-10-03 2:26 ` Zi Yan
2023-10-10 21:12 ` Johannes Weiner
2023-10-11 15:25 ` Johannes Weiner
2023-10-11 15:45 ` Johannes Weiner
2023-10-11 15:57 ` Zi Yan
2023-10-13 0:06 ` Zi Yan
2023-10-13 14:51 ` Zi Yan
2023-10-16 13:35 ` Zi Yan
2023-10-16 14:37 ` Johannes Weiner
2023-10-16 15:00 ` Zi Yan
2023-10-16 18:51 ` Johannes Weiner
2023-10-16 19:49 ` Zi Yan
2023-10-16 20:26 ` Johannes Weiner
2023-10-16 20:39 ` Johannes Weiner
2023-10-16 20:48 ` Zi Yan
2023-09-26 18:19 ` David Hildenbrand
2023-09-28 3:22 ` Zi Yan
2023-10-02 11:43 ` David Hildenbrand
2023-10-03 2:35 ` Zi Yan
2023-09-18 7:07 ` Vlastimil Babka
2023-09-18 14:09 ` Johannes Weiner
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=20230911204751.GA134811@cmpxchg.org \
--to=hannes@cmpxchg.org \
--cc=akpm@linux-foundation.org \
--cc=linmiaohe@huawei.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@techsingularity.net \
--cc=vbabka@suse.cz \
--cc=wangkefeng.wang@huawei.com \
--cc=ziy@nvidia.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.