Re: [PATCH v1 2/3] mm/memory_hotplug: don't shuffle complete zone when onlining memory

From: David Hildenbrand <david@redhat.com>
To: Dan Williams <dan.j.williams@intel.com>,
	Michal Hocko <mhocko@kernel.org>
Cc: Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Linux MM <linux-mm@kvack.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Alexander Duyck <alexander.h.duyck@linux.intel.com>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Kees Cook <keescook@chromium.org>,
	Mel Gorman <mgorman@techsingularity.net>
Subject: Re: [PATCH v1 2/3] mm/memory_hotplug: don't shuffle complete zone when onlining memory
Date: Tue, 16 Jun 2020 20:24:15 +0200	[thread overview]
Message-ID: <02eedfb6-6048-c6bb-df1c-59405ad3ab30@redhat.com> (raw)
In-Reply-To: <CAPcyv4gTTVaGAKt91DcgW=t3PgWFioZA7XQrCAU_gAXhcxBe1w@mail.gmail.com>

On 16.06.20 19:03, Dan Williams wrote:
> On Tue, Jun 16, 2020 at 10:00 AM Dan Williams <dan.j.williams@intel.com> wrote:
>>
>> On Tue, Jun 16, 2020 at 5:51 AM Michal Hocko <mhocko@kernel.org> wrote:
>>>
>>> On Tue 16-06-20 13:52:12, David Hildenbrand wrote:
>>>> Commit e900a918b098 ("mm: shuffle initial free memory to improve
>>>> memory-side-cache utilization") introduced shuffling of free pages
>>>> during system boot and whenever we online memory blocks.
>>>>
>>>> However, whenever we online memory blocks, all pages that will be
>>>> exposed to the buddy end up getting freed via __free_one_page(). In the
>>>> general case, we free these pages in MAX_ORDER - 1 chunks, which
>>>> corresponds to the shuffle order.
>>>>
>>>> Inside __free_one_page(), we will already shuffle the newly onlined pages
>>>> using "to_tail = shuffle_pick_tail();". Drop explicit zone shuffling on
>>>> memory hotplug.
> 
> This was already explained in the initial patch submission. The
> shuffle_pick_tail() shuffling at run time is only sufficient for
> maintaining the shuffle. It's not sufficient for effectively
> randomizing the free list.

Thanks for pointing that out. Something like that should definitely
belong into the code in form of a comment. I'll think of something.

Tow things:

1. The "shuffle when onlining" is really sub-optimal. Assume you hotplug
a 64GB DIMM. With 128MB memory blocks you get 512 zone shuffles. I guess
something better would have been to schedule a reshuffle some ms in the
future.

2. You'll run into the same issue whenever you free a bigger,
consecutive range. Like free_contig_rang()'ing one or more multiple
gigantic pages. We might want to reshuffle (or schedule a reshuffle)
here as well.

-- 
Thanks,

David / dhildenb