linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Usama Arif <usamaarif642@gmail.com>
To: Andrew Morton <akpm@linux-foundation.org>,
	david@redhat.com, linux-mm@kvack.org
Cc: hannes@cmpxchg.org, shakeel.butt@linux.dev, riel@surriel.com,
	ziy@nvidia.com, baolin.wang@linux.alibaba.com,
	lorenzo.stoakes@oracle.com, Liam.Howlett@oracle.com,
	npache@redhat.com, ryan.roberts@arm.com, dev.jain@arm.com,
	hughd@google.com, linux-kernel@vger.kernel.org,
	linux-doc@vger.kernel.org, kernel-team@meta.com,
	Breno Leitao <leitao@debian.org>
Subject: Re: [RFC] mm: khugepaged: use largest enabled hugepage order for min_free_kbytes
Date: Fri, 6 Jun 2025 16:01:28 +0100	[thread overview]
Message-ID: <a179fd65-dc3f-4769-9916-3033497188ba@gmail.com> (raw)
In-Reply-To: <20250606143700.3256414-1-usamaarif642@gmail.com>



On 06/06/2025 15:37, Usama Arif wrote:
> On arm64 machines with 64K PAGE_SIZE, the min_free_kbytes and hence the
> watermarks are evaluated to extremely high values, for e.g. a server with
> 480G of memory, only 2M mTHP hugepage size set to madvise, with the rest
> of the sizes set to never, the min, low and high watermarks evaluate to
> 11.2G, 14G and 16.8G respectively.
> In contrast for 4K PAGE_SIZE of the same machine, with only 2M THP hugepage
> size set to madvise, the min, low and high watermarks evaluate to 86M, 566M
> and 1G respectively.
> This is because set_recommended_min_free_kbytes is designed for PMD
> hugepages (pageblock_order = min(HPAGE_PMD_ORDER, PAGE_BLOCK_ORDER)).
> Such high watermark values can cause performance and latency issues in
> memory bound applications on arm servers that use 64K PAGE_SIZE, eventhough
> most of them would never actually use a 512M PMD THP.
> 
> Instead of using HPAGE_PMD_ORDER for pageblock_order use the highest large
> folio order enabled in set_recommended_min_free_kbytes.
> With this patch, when only 2M THP hugepage size is set to madvise for the
> same machine with 64K page size, with the rest of the sizes set to never,
> the min, low and high watermarks evaluate to 2.08G, 2.6G and 3.1G

I forgot to change the other pageblock_nr_pages instance, the patch
will need the below fixlet as well. The watermark numbers will then be
the same as when 4K PAGE_SIZE is used.

commit 0c6bb4e5b3aa078949d712ab9c35e7b2a33cd8a4 (HEAD)
Author: Usama Arif <usamaarif642@gmail.com>
Date:   Fri Jun 6 15:43:25 2025 +0100

    [fixlet] mm: khugepaged: replace all instances of pageblock_nr_pages
    
    This will change the 64K page size, 2M THP hugepage madvise  min, low
    and high watermarks to 87M, 575M and 1G.
    
    Signed-off-by: Usama Arif <usamaarif642@gmail.com>

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index e64cba74eb2a..1c643f13135e 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -2650,7 +2650,7 @@ static void set_recommended_min_free_kbytes(void)
        }
 
        /* Ensure 2 pageblocks are free to assist fragmentation avoidance */
-       recommended_min = pageblock_nr_pages * nr_zones * 2;
+       recommended_min = min_thp_pageblock_nr_pages() * nr_zones * 2;
 
        /*
         * Make sure that on average at least two pageblocks are almost free


  reply	other threads:[~2025-06-06 15:01 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-06 14:37 Usama Arif
2025-06-06 15:01 ` Usama Arif [this message]
2025-06-06 15:18 ` Zi Yan
2025-06-06 15:38   ` Usama Arif
2025-06-06 16:10     ` Zi Yan
2025-06-07  8:35       ` Lorenzo Stoakes
2025-06-08  0:04         ` Zi Yan
2025-06-09 11:13       ` Usama Arif
2025-06-09 13:19         ` Zi Yan
2025-06-09 14:11           ` Usama Arif
2025-06-09 14:16             ` Lorenzo Stoakes
2025-06-09 14:37               ` Zi Yan
2025-06-09 14:50                 ` Lorenzo Stoakes
2025-06-09 15:20                   ` Zi Yan
2025-06-09 19:40                     ` Lorenzo Stoakes
2025-06-09 19:49                       ` Zi Yan
2025-06-09 20:03                         ` Usama Arif
2025-06-09 20:24                           ` Zi Yan
2025-06-10 10:41                             ` Usama Arif
2025-06-10 14:03                         ` Lorenzo Stoakes
2025-06-10 14:20                           ` Zi Yan
2025-06-10 15:16                             ` Usama Arif
2025-06-09 15:32             ` Zi Yan
2025-06-06 17:37 ` David Hildenbrand
2025-06-09 11:34   ` Usama Arif
2025-06-09 13:28     ` Zi Yan
2025-06-07  8:18 ` Lorenzo Stoakes
2025-06-07  8:44   ` Lorenzo Stoakes
2025-06-09 12:07   ` Usama Arif
2025-06-09 12:12     ` Usama Arif
2025-06-09 14:58       ` Lorenzo Stoakes
2025-06-09 14:57     ` Lorenzo Stoakes

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=a179fd65-dc3f-4769-9916-3033497188ba@gmail.com \
    --to=usamaarif642@gmail.com \
    --cc=Liam.Howlett@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=david@redhat.com \
    --cc=dev.jain@arm.com \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=kernel-team@meta.com \
    --cc=leitao@debian.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=npache@redhat.com \
    --cc=riel@surriel.com \
    --cc=ryan.roberts@arm.com \
    --cc=shakeel.butt@linux.dev \
    --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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox