From: Steve Capper <steve.capper@linaro.org>
To: Joern Engel <joern@logfs.org>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [PATCH 1/2] hugetlb: properly account rss
Date: Wed, 3 Jul 2013 14:41:19 +0100 [thread overview]
Message-ID: <20130703134118.GA4978@linaro.org> (raw)
In-Reply-To: <1371581225-27535-2-git-send-email-joern@logfs.org>
On Tue, Jun 18, 2013 at 02:47:04PM -0400, Joern Engel wrote:
> When moving a program from mmap'ing small pages to mmap'ing huge pages,
> a remarkable drop in rss ensues. For some reason hugepages were never
> accounted for in rss, which in my book is a clear bug. Sadly this bug
> has been present in hugetlbfs since it was merged back in 2002. There
> is every chance existing programs depend on hugepages not being counted
> as rss.
>
> I think the correct solution is to fix the bug and wait for someone to
> complain. It is just as likely that noone cares - as evidenced by the
> fact that noone seems to have noticed for ten years.
>
> Signed-off-by: Joern Engel <joern@logfs.org>
> ---
> mm/hugetlb.c | 4 ++++
> 1 file changed, 4 insertions(+)
>
Hi,
This patch has caused a few warnings for me today when it was integrated into
linux-next. The libhugetlbfs test suite gave me:
[ 94.320661] BUG: Bad rss-counter state mm:ffff880119461040 idx:1 val:-512
[ 94.330346] BUG: Bad rss-counter state mm:ffff880119460680 idx:1 val:-2560
[ 94.341746] BUG: Bad rss-counter state mm:ffff880119460d00 idx:1 val:-512
[ 94.347518] BUG: Bad rss-counter state mm:ffff880119460d00 idx:1 val:-512
[ 94.415203] BUG: Bad rss-counter state mm:ffff8801194f9040 idx:1 val:-1024
[ ...]
I think I've found the cause; MAP_SHARED mappings.
alloc_huge_page and __unmap_hugepage_range are called for shared pages. Also,
__unmap_hugepage_range is called more times than alloc_huge_page (which makes
sense as multiple views of a shared mapping are unmapped) leading to negative
counter values.
Excluding VM_SHARED VMAs from the counter increment/decrement stopped the
warnings for me. Although this may not be the best way to address the issue.
Cheers,
--
Steve
--
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: Steve Capper <steve.capper@linaro.org>
To: Joern Engel <joern@logfs.org>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [PATCH 1/2] hugetlb: properly account rss
Date: Wed, 3 Jul 2013 14:41:19 +0100 [thread overview]
Message-ID: <20130703134118.GA4978@linaro.org> (raw)
In-Reply-To: <1371581225-27535-2-git-send-email-joern@logfs.org>
On Tue, Jun 18, 2013 at 02:47:04PM -0400, Joern Engel wrote:
> When moving a program from mmap'ing small pages to mmap'ing huge pages,
> a remarkable drop in rss ensues. For some reason hugepages were never
> accounted for in rss, which in my book is a clear bug. Sadly this bug
> has been present in hugetlbfs since it was merged back in 2002. There
> is every chance existing programs depend on hugepages not being counted
> as rss.
>
> I think the correct solution is to fix the bug and wait for someone to
> complain. It is just as likely that noone cares - as evidenced by the
> fact that noone seems to have noticed for ten years.
>
> Signed-off-by: Joern Engel <joern@logfs.org>
> ---
> mm/hugetlb.c | 4 ++++
> 1 file changed, 4 insertions(+)
>
Hi,
This patch has caused a few warnings for me today when it was integrated into
linux-next. The libhugetlbfs test suite gave me:
[ 94.320661] BUG: Bad rss-counter state mm:ffff880119461040 idx:1 val:-512
[ 94.330346] BUG: Bad rss-counter state mm:ffff880119460680 idx:1 val:-2560
[ 94.341746] BUG: Bad rss-counter state mm:ffff880119460d00 idx:1 val:-512
[ 94.347518] BUG: Bad rss-counter state mm:ffff880119460d00 idx:1 val:-512
[ 94.415203] BUG: Bad rss-counter state mm:ffff8801194f9040 idx:1 val:-1024
[ ...]
I think I've found the cause; MAP_SHARED mappings.
alloc_huge_page and __unmap_hugepage_range are called for shared pages. Also,
__unmap_hugepage_range is called more times than alloc_huge_page (which makes
sense as multiple views of a shared mapping are unmapped) leading to negative
counter values.
Excluding VM_SHARED VMAs from the counter increment/decrement stopped the
warnings for me. Although this may not be the best way to address the issue.
Cheers,
--
Steve
next prev parent reply other threads:[~2013-07-03 13:41 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-06-18 18:47 [PATCH 0/2] hugetlb fixes Joern Engel
2013-06-18 18:47 ` Joern Engel
2013-06-18 18:47 ` [PATCH 1/2] hugetlb: properly account rss Joern Engel
2013-06-18 18:47 ` Joern Engel
2013-06-28 22:03 ` Andrew Morton
2013-06-28 22:03 ` Andrew Morton
2013-07-03 13:41 ` Steve Capper [this message]
2013-07-03 13:41 ` Steve Capper
2013-07-03 14:55 ` Steve Capper
2013-07-03 14:55 ` Steve Capper
2013-06-18 18:47 ` [PATCH 2/2] mmap: allow MAP_HUGETLB for hugetlbfs files Joern Engel
2013-06-18 18:47 ` Joern Engel
2013-06-19 1:22 ` Jianguo Wu
2013-06-19 1:22 ` Jianguo Wu
2013-06-19 16:25 ` [PATCH] mmap: allow MAP_HUGETLB for hugetlbfs files v2 Jörn Engel
2013-06-19 16:25 ` Jörn Engel
2013-06-20 1:31 ` Jianguo Wu
2013-06-20 1:31 ` Jianguo Wu
2013-06-19 16:25 ` [PATCH 2/2] mmap: allow MAP_HUGETLB for hugetlbfs files Jörn Engel
2013-06-19 16:25 ` Jörn Engel
2013-06-18 18:50 ` [PATCH 0/2] hugetlb fixes Jörn Engel
2013-06-18 18:50 ` Jörn Engel
2013-06-18 20:27 ` Andrew Morton
2013-06-18 20:27 ` Andrew Morton
2013-06-18 20:04 ` Jörn Engel
2013-06-18 20:04 ` Jörn Engel
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=20130703134118.GA4978@linaro.org \
--to=steve.capper@linaro.org \
--cc=akpm@linux-foundation.org \
--cc=joern@logfs.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
/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.