From: Andrew Morton <akpm@linux-foundation.org>
To: Gavin Shan <gshan@redhat.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
alexander.h.duyck@linux.intel.com, david@redhat.com,
shan.gavin@gmail.com
Subject: Re: [RFC PATCH] mm/page_reporting: Adjust threshold according to MAX_ORDER
Date: Tue, 1 Jun 2021 17:03:47 -0700 [thread overview]
Message-ID: <20210601170347.d78ec4af51b1522305deef4a@linux-foundation.org> (raw)
In-Reply-To: <20210601033319.100737-1-gshan@redhat.com>
On Tue, 1 Jun 2021 11:33:19 +0800 Gavin Shan <gshan@redhat.com> wrote:
> The PAGE_REPORTING_MIN_ORDER is equal to @pageblock_order, taken as
> minimal order (threshold) to trigger page reporting. The page reporting
> is never triggered with the following configurations and settings on
> aarch64. In the particular scenario, the page reporting won't be triggered
> until the largest (2 ^ (MAX_ORDER-1)) free area is achieved from the
> page freeing. The condition is very hard, or even impossible to be met.
>
> CONFIG_ARM64_PAGE_SHIFT: 16
> CONFIG_HUGETLB_PAGE: Y
> CONFIG_HUGETLB_PAGE_SIZE_VARIABLE: N
> pageblock_order: 13
> CONFIG_FORCE_MAX_ZONEORDER: 14
> MAX_ORDER: 14
>
> The issue can be reproduced in VM, running kernel with above configurations
> and settings. The 'memhog' is used inside the VM to access 512MB anonymous
> area. The QEMU's RSS doesn't drop accordingly after 'memhog' exits.
>
> /home/gavin/sandbox/qemu.main/build/qemu-system-aarch64 \
> -accel kvm -machine virt,gic-version=host \
> -cpu host -smp 8,sockets=2,cores=4,threads=1 -m 4096M,maxmem=64G \
> -object memory-backend-ram,id=mem0,size=2048M \
> -object memory-backend-ram,id=mem1,size=2048M \
> -numa node,nodeid=0,cpus=0-3,memdev=mem0 \
> -numa node,nodeid=1,cpus=4-7,memdev=mem1 \
> : \
> -device virtio-balloon-pci,id=balloon0,free-page-reporting=yes
>
> This tries to fix the issue by adjusting the threshold to the smaller value
> of @pageblock_order and (MAX_ORDER/2). With this applied, the QEMU's RSS
> drops after 'memhog' exits.
>
Sounds promising, but...
> --- a/mm/page_reporting.h
> +++ b/mm/page_reporting.h
> @@ -10,9 +10,10 @@
> #include <linux/pgtable.h>
> #include <linux/scatterlist.h>
>
> -#define PAGE_REPORTING_MIN_ORDER pageblock_order
> -
> #ifdef CONFIG_PAGE_REPORTING
> +#define PAGE_REPORTING_MIN_ORDER \
> + min_t(unsigned int, pageblock_order, (MAX_ORDER / 2))
> +
> DECLARE_STATIC_KEY_FALSE(page_reporting_enabled);
> void __page_reporting_notify(void);
Could you please redo this as a regular old static function in
page_reporting.c? Bonus points for commenting its design ;)
prev parent reply other threads:[~2021-06-02 0:03 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-01 3:33 Gavin Shan
2021-06-01 8:01 ` David Hildenbrand
[not found] ` <0c0eb8c8-463d-d6f1-3cec-bbc0af0a229c@redhat.com>
2021-06-14 11:03 ` David Hildenbrand
2021-06-15 2:26 ` Alexander Duyck
2021-06-16 9:10 ` Gavin Shan
2021-06-16 8:03 ` David Hildenbrand
2021-06-16 13:16 ` Gavin Shan
2021-06-16 11:20 ` David Hildenbrand
2021-06-16 13:58 ` Gavin Shan
2021-06-16 12:07 ` David Hildenbrand
2021-06-21 5:16 ` Gavin Shan
2021-06-16 14:15 ` Alexander Duyck
2021-06-21 7:03 ` Gavin Shan
2021-06-21 7:52 ` Gavin Shan
2021-06-21 13:43 ` Alexander Duyck
2021-06-16 1:53 ` Gavin Shan
2021-06-16 7:59 ` David Hildenbrand
2021-06-16 12:59 ` Gavin Shan
2021-06-16 11:15 ` David Hildenbrand
2021-06-02 0:03 ` Andrew Morton [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=20210601170347.d78ec4af51b1522305deef4a@linux-foundation.org \
--to=akpm@linux-foundation.org \
--cc=alexander.h.duyck@linux.intel.com \
--cc=david@redhat.com \
--cc=gshan@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=shan.gavin@gmail.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