linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Yang Shi <yang@os.amperecomputing.com>
To: Vlastimil Babka <vbabka@suse.cz>,
	Andrew Morton <akpm@linux-foundation.org>,
	"Liam R. Howlett" <Liam.Howlett@oracle.com>,
	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Jann Horn <jannh@google.com>,
	Thorsten Leemhuis <regressions@leemhuis.info>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	Petr Tesarik <ptesarik@suse.com>, Michael Matz <matz@suse.de>,
	Gabriel Krisman Bertazi <gabriel@krisman.be>,
	Matthias Bodenbinder <matthias@bodenbinder.de>,
	stable@vger.kernel.org, Rik van Riel <riel@surriel.com>
Subject: Re: [PATCH hotfix 6.12] mm, mmap: limit THP aligment of anonymous mappings to PMD-aligned sizes
Date: Thu, 24 Oct 2024 11:32:57 -0700	[thread overview]
Message-ID: <e11629d6-c2dd-45fa-9ca6-7a6e38882560@os.amperecomputing.com> (raw)
In-Reply-To: <20241024151228.101841-2-vbabka@suse.cz>



On 10/24/24 8:12 AM, Vlastimil Babka wrote:
> Since commit efa7df3e3bb5 ("mm: align larger anonymous mappings on THP
> boundaries") a mmap() of anonymous memory without a specific address
> hint and of at least PMD_SIZE will be aligned to PMD so that it can
> benefit from a THP backing page.
>
> However this change has been shown to regress some workloads
> significantly. [1] reports regressions in various spec benchmarks, with
> up to 600% slowdown of the cactusBSSN benchmark on some platforms. The
> benchmark seems to create many mappings of 4632kB, which would have
> merged to a large THP-backed area before commit efa7df3e3bb5 and now
> they are fragmented to multiple areas each aligned to PMD boundary with
> gaps between. The regression then seems to be caused mainly due to the
> benchmark's memory access pattern suffering from TLB or cache aliasing
> due to the aligned boundaries of the individual areas.
>
> Another known regression bisected to commit efa7df3e3bb5 is darktable
> [2] [3] and early testing suggests this patch fixes the regression there
> as well.
>
> To fix the regression but still try to benefit from THP-friendly
> anonymous mapping alignment, add a condition that the size of the
> mapping must be a multiple of PMD size instead of at least PMD size. In
> case of many odd-sized mapping like the cactusBSSN creates, those will
> stop being aligned and with gaps between, and instead naturally merge
> again.

Thanks for debugging this. The fix makes sense to me. Reviewed-by: Yang 
Shi <yang@os.amperecomputing.com>

>
> Reported-by: Michael Matz <matz@suse.de>
> Debugged-by: Gabriel Krisman Bertazi <gabriel@krisman.be>
> Closes: https://bugzilla.suse.com/show_bug.cgi?id=1229012 [1]
> Reported-by: Matthias Bodenbinder <matthias@bodenbinder.de>
> Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219366 [2]
> Closes: https://lore.kernel.org/all/2050f0d4-57b0-481d-bab8-05e8d48fed0c@leemhuis.info/ [3]
> Fixes: efa7df3e3bb5 ("mm: align larger anonymous mappings on THP boundaries")
> Cc: <stable@vger.kernel.org>
> Cc: Rik van Riel <riel@surriel.com>
> Cc: Yang Shi <yang@os.amperecomputing.com>
> Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
> ---
>   mm/mmap.c | 3 ++-
>   1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/mm/mmap.c b/mm/mmap.c
> index 9c0fb43064b5..a5297cfb1dfc 100644
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -900,7 +900,8 @@ __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
>   
>   	if (get_area) {
>   		addr = get_area(file, addr, len, pgoff, flags);
> -	} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
> +	} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)
> +		   && IS_ALIGNED(len, PMD_SIZE)) {
>   		/* Ensures that larger anonymous mappings are THP aligned. */
>   		addr = thp_get_unmapped_area_vmflags(file, addr, len,
>   						     pgoff, flags, vm_flags);



      parent reply	other threads:[~2024-10-24 18:33 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-24  7:45 darktable performance regression on AMD systems caused by "mm: align larger anonymous mappings on THP boundaries" Thorsten Leemhuis
2024-10-24  9:58 ` Vlastimil Babka
2024-10-24 10:23   ` Vlastimil Babka
2024-10-24 10:49     ` Petr Tesarik
2024-10-24 10:56       ` Vlastimil Babka
2024-10-24 11:13         ` Petr Tesarik
2024-10-24 13:29           ` Vlastimil Babka
2024-10-24 14:14             ` Petr Tesarik
2024-10-24 11:20     ` Matthias Bodenbinder
2024-10-24 15:12 ` [PATCH hotfix 6.12] mm, mmap: limit THP aligment of anonymous mappings to PMD-aligned sizes Vlastimil Babka
2024-10-24 15:47   ` Lorenzo Stoakes
2024-10-24 16:00     ` Lorenzo Stoakes
2024-10-24 16:04     ` Vlastimil Babka
2024-10-24 16:17       ` Lorenzo Stoakes
2024-10-28 13:45     ` Michael Matz
2024-10-24 18:32   ` Yang Shi [this message]

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=e11629d6-c2dd-45fa-9ca6-7a6e38882560@os.amperecomputing.com \
    --to=yang@os.amperecomputing.com \
    --cc=Liam.Howlett@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=gabriel@krisman.be \
    --cc=jannh@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=matthias@bodenbinder.de \
    --cc=matz@suse.de \
    --cc=ptesarik@suse.com \
    --cc=regressions@leemhuis.info \
    --cc=riel@surriel.com \
    --cc=stable@vger.kernel.org \
    --cc=vbabka@suse.cz \
    /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