linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Zi Yan <ziy@nvidia.com>
To: Shivank Garg <shivankg@amd.com>
Cc: linux-mm@kvack.org, David Rientjes <rientjes@google.com>,
	Aneesh Kumar <AneeshKumar.KizhakeVeetil@arm.com>,
	David Hildenbrand <david@redhat.com>,
	John Hubbard <jhubbard@nvidia.com>,
	Kirill Shutemov <k.shutemov@gmail.com>,
	Matthew Wilcox <willy@infradead.org>,
	Mel Gorman <mel.gorman@gmail.com>,
	"Rao, Bharata Bhasker" <bharata@amd.com>,
	Rik van Riel <riel@surriel.com>,
	RaghavendraKT <Raghavendra.KodsaraThimmappa@amd.com>,
	Wei Xu <weixugc@google.com>, Suyeon Lee <leesuyeon0506@gmail.com>,
	Lei Chen <leillc@google.com>,
	"Shukla, Santosh" <santosh.shukla@amd.com>,
	"Grimm, Jon" <jon.grimm@amd.com>,
	sj@kernel.org, shy828301@gmail.com,
	Liam Howlett <liam.howlett@oracle.com>,
	Gregory Price <gregory.price@memverge.com>,
	"Huang, Ying" <ying.huang@linux.alibaba.com>
Subject: Re: [RFC PATCH 3/5] mm/migrate: add migrate_folios_batch_move to batch the folio move operations
Date: Thu, 09 Jan 2025 09:08:59 -0500	[thread overview]
Message-ID: <12C61EDE-43B9-46C1-BADA-F299AF394F62@nvidia.com> (raw)
In-Reply-To: <97ed042a-fe70-46cf-80f1-59e7add66860@amd.com>

On 9 Jan 2025, at 6:47, Shivank Garg wrote:

> On 1/3/2025 10:54 PM, Zi Yan wrote:
>> This is a preparatory patch that enables batch copying for folios
>> undergoing migration. By enabling batch copying the folio content, we can
>> efficiently utilize the capabilities of DMA hardware or multi-threaded
>> folio copy. It also adds MIGRATE_NO_COPY back to migrate_mode, so that
>> folio copy will be skipped during metadata copy process and performed
>> in a batch later.
>>
>> Currently, the folio move operation is performed individually for each
>> folio in sequential manner:
>> for_each_folio() {
>>         Copy folio metadata like flags and mappings
>>         Copy the folio content from src to dst
>>         Update page tables with dst folio
>> }
>>
>> With this patch, we transition to a batch processing approach as shown
>> below:
>> for_each_folio() {
>>         Copy folio metadata like flags and mappings
>> }
>> Batch copy all src folios to dst
>> for_each_folio() {
>>         Update page tables with dst folios
>> }
>>
>> dst->private is used to store page states and possible anon_vma value,
>> thus needs to be cleared during metadata copy process. To avoid additional
>> memory allocation to store the data during batch copy process, src->private
>> is used to store the data after metadata copy process, since src is no
>> longer used.
>>
>> Originally-by: Shivank Garg <shivankg@amd.com>
>> Signed-off-by: Zi Yan <ziy@nvidia.com>
>> ---
>
> Hi Zi,
>
> Please retain my Signed-off-by for future posting of batch page migration
> patchset.
>
> I think we can separate out the MIGRATE_NO_COPY support into separate patch.

Sure. Will change them in the next version.

Best Regards,
Yan, Zi


  reply	other threads:[~2025-01-09 14:09 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-01-03 17:24 [RFC PATCH 0/5] Accelerate page migration with batching and multi threads Zi Yan
2025-01-03 17:24 ` [RFC PATCH 1/5] mm: separate move/undo doing on folio list from migrate_pages_batch() Zi Yan
2025-01-03 17:24 ` [RFC PATCH 2/5] mm/migrate: factor out code in move_to_new_folio() and migrate_folio_move() Zi Yan
2025-01-03 17:24 ` [RFC PATCH 3/5] mm/migrate: add migrate_folios_batch_move to batch the folio move operations Zi Yan
2025-01-09 11:47   ` Shivank Garg
2025-01-09 14:08     ` Zi Yan [this message]
2025-01-03 17:24 ` [RFC PATCH 4/5] mm/migrate: introduce multi-threaded page copy routine Zi Yan
2025-01-06  1:18   ` Hyeonggon Yoo
2025-01-06  2:01     ` Zi Yan
2025-02-13 12:44   ` Byungchul Park
2025-02-13 15:34     ` Zi Yan
2025-02-13 21:34       ` Byungchul Park
2025-01-03 17:24 ` [RFC PATCH 5/5] test: add sysctl for folio copy tests and adjust NR_MAX_BATCHED_MIGRATION Zi Yan
2025-01-03 22:21   ` Gregory Price
2025-01-03 22:56     ` Zi Yan
2025-01-03 19:17 ` [RFC PATCH 0/5] Accelerate page migration with batching and multi threads Gregory Price
2025-01-03 19:32   ` Zi Yan
2025-01-03 22:09 ` Yang Shi
2025-01-06  2:33   ` Zi Yan
2025-01-09 11:47 ` Shivank Garg
2025-01-09 15:04   ` Zi Yan
2025-01-09 18:03     ` Shivank Garg
2025-01-09 19:32       ` Zi Yan
2025-01-10 17:05         ` Zi Yan
2025-01-10 19:51           ` Zi Yan
2025-01-16  4:57             ` Shivank Garg
2025-01-21  6:15               ` Shivank Garg
2025-02-13  8:17 ` Byungchul Park
2025-02-13 15:36   ` Zi Yan

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=12C61EDE-43B9-46C1-BADA-F299AF394F62@nvidia.com \
    --to=ziy@nvidia.com \
    --cc=AneeshKumar.KizhakeVeetil@arm.com \
    --cc=Raghavendra.KodsaraThimmappa@amd.com \
    --cc=bharata@amd.com \
    --cc=david@redhat.com \
    --cc=gregory.price@memverge.com \
    --cc=jhubbard@nvidia.com \
    --cc=jon.grimm@amd.com \
    --cc=k.shutemov@gmail.com \
    --cc=leesuyeon0506@gmail.com \
    --cc=leillc@google.com \
    --cc=liam.howlett@oracle.com \
    --cc=linux-mm@kvack.org \
    --cc=mel.gorman@gmail.com \
    --cc=riel@surriel.com \
    --cc=rientjes@google.com \
    --cc=santosh.shukla@amd.com \
    --cc=shivankg@amd.com \
    --cc=shy828301@gmail.com \
    --cc=sj@kernel.org \
    --cc=weixugc@google.com \
    --cc=willy@infradead.org \
    --cc=ying.huang@linux.alibaba.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