Re: [PATCH v4] mm, compaction: Skip all non-migratable pages during scan

From: John Hubbard <jhubbard@nvidia.com>
To: David Hildenbrand <david@redhat.com>,
	Matthew Wilcox <willy@infradead.org>
Cc: Khalid Aziz <khalid.aziz@oracle.com>,
	Steven Sistare <steven.sistare@oracle.com>,
	<akpm@linux-foundation.org>, <ying.huang@intel.com>,
	<mgorman@techsingularity.net>, <baolin.wang@linux.alibaba.com>,
	<linux-mm@kvack.org>, <linux-kernel@vger.kernel.org>,
	Khalid Aziz <khalid@kernel.org>
Subject: Re: [PATCH v4] mm, compaction: Skip all non-migratable pages during scan
Date: Fri, 26 May 2023 19:11:05 -0700	[thread overview]
Message-ID: <846b770c-9f63-90a2-0435-ec82484e3f74@nvidia.com> (raw)
In-Reply-To: <e31cd404-56ce-4cad-fcc3-3a6695f750fa@redhat.com>

On 5/26/23 11:50, David Hildenbrand wrote:
> On 26.05.23 20:46, Matthew Wilcox wrote:
>> On Fri, May 26, 2023 at 06:46:15PM +0200, David Hildenbrand wrote:
>>> On 26.05.23 18:44, Matthew Wilcox wrote:
>>>> On Fri, May 26, 2023 at 09:44:34AM -0600, Khalid Aziz wrote:
>>>>>> Oh, I think I found it!  pin_user_pages_remote() is called by
>>>>>> vaddr_get_pfns().  If these are the pages you're concerned about,
>>>>>> then the efficient way to do what you want is simply to call
>>>>>> folio_maybe_dma_pinned().  Far more efficient than the current mess
>>>>>> of total_mapcount().
>>>>>
>>>>> vfio pinned pages triggered this change. Wouldn't checking refcounts against
>>>>> mapcount provide a more generalized way of detecting non-migratable pages?
>>>>
>>>> Well, you changed the comment to say that we were concerned about
>>>> long-term pins.  If we are, than folio_maybe_dma_pinned() is how to test
>>>> for long-term pins.  If we want to skip pages which are short-term pinned,
>>>> then we need to not change the comment, and keep using mapcount/refcount
>>>> differences.
>>>>
>>>
>>> folio_maybe_dma_pinned() is all about FOLL_PIN, not FOLL_LONGTERM.
>>
>> But according to our documentation, FOLL_LONGTERM implies FOLL_PIN.
> 
> Yes. But folio_maybe_dma_pinned() will indicate both, long-term pins and short-term pins. There really is no way to distinguish both, unfortunately.

Not yet, anyway. :)

> 
>> Anyway, right now, the code skips any pages which are merely FOLL_GET,
>> so we'll skip fewer pages if we do only skip the FOLL_PIN ones,
>> regardless if we'd prefer to only skip the FOLL_LONGTERM ones.
>>
>>> folio_maybe_dma_pinned() would skip migrating any page that has more than
>>> 1024 references. (shared libraries?)
>>
>> True, but maybe we should be skipping any page with that many mappings,
>> given how disruptive it is to the rest of the system to unmap a page
>> from >1024 processes.
>>
> 
> So any user with 1024 processes can fragment physical memory? :/
> 
> Sorry, I'd like to minimize the usage of folio_maybe_dma_pinned().
> 

I was actually thinking that we should minimize any more cases of
fragile mapcount and refcount comparison, which then leads to
Matthew's approach here!

thanks,
-- 
John Hubbard
NVIDIA