All of lore.kernel.org
 help / color / mirror / Atom feed
From: Chao Yu via Linux-f2fs-devel <linux-f2fs-devel@lists.sourceforge.net>
To: Jeuk Kim <jeuk20.kim@gmail.com>, jaegeuk@kernel.org
Cc: linux-kernel@vger.kernel.org,
	linux-f2fs-devel@lists.sourceforge.net,
	Jeuk Kim <jeuk20.kim@samsung.com>
Subject: Re: [f2fs-dev] Question: batching block allocation in f2fs DIO path
Date: Tue, 30 Dec 2025 17:27:26 +0800	[thread overview]
Message-ID: <c28020f1-e2f2-42e8-9c0c-0ff70ec219cd@kernel.org> (raw)
In-Reply-To: <CAPjHTeSsvb7UOAn9mWoqXwWTw1J9SEEDo1k=8KVcAxwVsys+Og@mail.gmail.com>

Hi Jeuk,

On 12/29/2025 2:33 PM, Jeuk Kim wrote:
> Hi F2FS maintainers,
> 
> Sorry for the duplicate — I’m resending this because the previous
> message was sent in HTML format.
> 
> I’ve been looking into the DIO allocation path in f2fs, specifically
> when a DIO write needs to allocate new blocks (e.g., hole-filling).
>  From f2fs_map_blocks() through __allocate_data_block() →
> f2fs_allocate_data_block(), it seems each block allocation is handled
> one-by-one, taking curseg_lock/curseg_mutex and the SIT sentry lock
> per block.
> 
> I’m wondering whether batching allocations (a bounded batch, e.g., a
> small run within the current segment) could be feasible in the DIO
> path. My intuition is that with multiple threads doing DIO, reducing
> per-block lock contention and improving sequentiality could help
> throughput.

I agree w/ you.

> 
> Questions:
> 
> Is there a technical or correctness reason that makes batching for DIO
> infeasible (e.g., LFS/SSR/GC interactions, summary/SIT update
> ordering, etc.)?
> 
> Or is this simply an optimization that hasn’t been implemented?

I've implemented a prototype of multiple block allocation for any potential
use cases: pinfile fallocation, direct IO and buffered IO. I can see benefits
from my previous test.

I plan to upstream all implementations, but I think I need more time to clean
up the draft codes and check all corner cases.

You can check the MBA implementation for pinfile use case in below link, I
guess this version is close to upstream.

https://github.com/chaseyu/f2fs-dev/commits/feature/inbatch_write

Thanks,

> 
> If this seems acceptable, would you consider patches in this direction?
> 
> If there are prior discussions or known issues on this, I’d appreciate pointers.
> 
> Thanks for your time.
> 
> Best regards,
> Jeuk Kim



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

WARNING: multiple messages have this Message-ID (diff)
From: Chao Yu <chao@kernel.org>
To: Jeuk Kim <jeuk20.kim@gmail.com>, jaegeuk@kernel.org
Cc: chao@kernel.org, Jinyoung Choi <j-young.choi@samsung.com>,
	Jeuk Kim <jeuk20.kim@samsung.com>,
	linux-kernel@vger.kernel.org,
	linux-f2fs-devel@lists.sourceforge.net
Subject: Re: Question: batching block allocation in f2fs DIO path
Date: Tue, 30 Dec 2025 17:27:26 +0800	[thread overview]
Message-ID: <c28020f1-e2f2-42e8-9c0c-0ff70ec219cd@kernel.org> (raw)
In-Reply-To: <CAPjHTeSsvb7UOAn9mWoqXwWTw1J9SEEDo1k=8KVcAxwVsys+Og@mail.gmail.com>

Hi Jeuk,

On 12/29/2025 2:33 PM, Jeuk Kim wrote:
> Hi F2FS maintainers,
> 
> Sorry for the duplicate — I’m resending this because the previous
> message was sent in HTML format.
> 
> I’ve been looking into the DIO allocation path in f2fs, specifically
> when a DIO write needs to allocate new blocks (e.g., hole-filling).
>  From f2fs_map_blocks() through __allocate_data_block() →
> f2fs_allocate_data_block(), it seems each block allocation is handled
> one-by-one, taking curseg_lock/curseg_mutex and the SIT sentry lock
> per block.
> 
> I’m wondering whether batching allocations (a bounded batch, e.g., a
> small run within the current segment) could be feasible in the DIO
> path. My intuition is that with multiple threads doing DIO, reducing
> per-block lock contention and improving sequentiality could help
> throughput.

I agree w/ you.

> 
> Questions:
> 
> Is there a technical or correctness reason that makes batching for DIO
> infeasible (e.g., LFS/SSR/GC interactions, summary/SIT update
> ordering, etc.)?
> 
> Or is this simply an optimization that hasn’t been implemented?

I've implemented a prototype of multiple block allocation for any potential
use cases: pinfile fallocation, direct IO and buffered IO. I can see benefits
from my previous test.

I plan to upstream all implementations, but I think I need more time to clean
up the draft codes and check all corner cases.

You can check the MBA implementation for pinfile use case in below link, I
guess this version is close to upstream.

https://github.com/chaseyu/f2fs-dev/commits/feature/inbatch_write

Thanks,

> 
> If this seems acceptable, would you consider patches in this direction?
> 
> If there are prior discussions or known issues on this, I’d appreciate pointers.
> 
> Thanks for your time.
> 
> Best regards,
> Jeuk Kim


  reply	other threads:[~2025-12-30  9:27 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-12-29  6:33 [f2fs-dev] Question: batching block allocation in f2fs DIO path Jeuk Kim
2025-12-29  6:33 ` Jeuk Kim
2025-12-30  9:27 ` Chao Yu via Linux-f2fs-devel [this message]
2025-12-30  9:27   ` Chao Yu
2025-12-30 13:25   ` [f2fs-dev] " Jeuk Kim
2025-12-30 13:25     ` Jeuk Kim

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=c28020f1-e2f2-42e8-9c0c-0ff70ec219cd@kernel.org \
    --to=linux-f2fs-devel@lists.sourceforge.net \
    --cc=chao@kernel.org \
    --cc=jaegeuk@kernel.org \
    --cc=jeuk20.kim@gmail.com \
    --cc=jeuk20.kim@samsung.com \
    --cc=linux-kernel@vger.kernel.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.