[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <875y8k3o60.fsf@yhuang6-desk2.ccr.corp.intel.com>
Date: Mon, 22 May 2023 13:55:51 +0800
From: "Huang, Ying" <ying.huang@...el.com>
To: David Hildenbrand <david@...hat.com>
Cc: Khalid Aziz <khalid.aziz@...cle.com>, akpm@...ux-foundation.org,
willy@...radead.org, steven.sistare@...cle.com,
mgorman@...hsingularity.net, khalid@...nel.org, linux-mm@...ck.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH v3] mm, compaction: Skip all non-migratable pages during
scan
David Hildenbrand <david@...hat.com> writes:
> On 18.05.23 03:09, Huang, Ying wrote:
>> David Hildenbrand <david@...hat.com> writes:
>>
>>> On 17.05.23 18:15, Khalid Aziz wrote:
>>>> Pages pinned in memory through extra refcounts can not be migrated.
>>>> Currently as isolate_migratepages_block() scans pages for
>>>> compaction, it skips any pinned anonymous pages. All non-migratable
>>>> pages should be skipped and not just the anonymous pinned pages.
>>>> This patch adds a check for extra refcounts on a page to determine
>>>> if the page can be migrated. This was seen as a real issue on a
>>>> customer workload where a large number of pages were pinned by vfio
>>>> on the host and any attempts to allocate hugepages resulted in
>>>> significant amount of cpu time spent in either direct compaction or
>>>> in kcompactd scanning vfio pinned pages over and over again that can
>>>> not be migrated.
>>>
>>> How will this change affect alloc_contig_range(), such as used for CMA
>>> allocations or virtio-mem? alloc_contig_range() ends up calling
>>> isolate_migratepages_range() -> isolate_migratepages_block().
>> IIUC, cc->alloc_contig can be used to distinguish contiguous
>> allocation
>> and compaction. And, from the original commit which introduced
>> anonymous pages skipping (commit 119d6d59dcc0 ("mm, compaction: avoid
>> isolating pinned pages ")) and this patch, large number of migration
>> failure during compaction causes real issue too. So, I suggest to use
>> cc->alloc_contig here.
>
> Agreed. I further wonder if we want to special-case the !alloc_contig
> case also for MIGRATE_CMA and ZONE_MOVABLE, where we cannot have
> longterm page pinnings (e.g., vfio pinned pages).
This makes sense. The skipping is more accurate in this way.
Best Regards,
Huang, Ying
Powered by blists - more mailing lists