linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Kundan Kumar <kundan.kumar@samsung.com>
Cc: Christoph Hellwig <hch@lst.de>, Brian Foster <bfoster@redhat.com>,
	viro@zeniv.linux.org.uk, brauner@kernel.org, jack@suse.cz,
	willy@infradead.org, mcgrof@kernel.org, clm@meta.com,
	david@fromorbit.com, amir73il@gmail.com, axboe@kernel.dk,
	ritesh.list@gmail.com, djwong@kernel.org, dave@stgolabs.net,
	cem@kernel.org, wangyufei@vivo.com,
	linux-fsdevel@vger.kernel.org, linux-mm@kvack.org,
	linux-xfs@vger.kernel.org, gost.dev@samsung.com,
	anuj20.g@samsung.com, vishak.g@samsung.com, joshi.k@samsung.com
Subject: Re: [PATCH v3 0/6] AG aware parallel writeback for XFS
Date: Tue, 10 Feb 2026 16:38:54 +0100	[thread overview]
Message-ID: <20260210153854.GA2484@lst.de> (raw)
In-Reply-To: <5b11145d-15e2-485c-a978-365b58854371@samsung.com>

On Mon, Feb 09, 2026 at 09:24:49PM +0530, Kundan Kumar wrote:
> - Create a bounded number of bdi wb contexts at mount time (capped,
> e.g. ≤ agcount).

Yeah.  And then optimally map them to CPU cores, similar to the
blk-mq cpumap.

> - Store a per-inode stream/shard id (no per-folio state).

Yes.

> - Assign the stream id once and use it to select the wb context for
> writeback.

Yes.

> - In the delalloc allocator, bias AG selection from the stream id by
> partitioning AG space into per-stream "bands" and rotating the start
> AG within that band; fall back to the existing allocator when
> allocation can't be satisfied.

Yes.

We might also need something that falls back to less helpers if
the free space is distributed unevently, but probably not for the
first prototype.



      reply	other threads:[~2026-02-10 15:39 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20260116101236epcas5p12ba3de776976f4ea6666e16a33ab6ec4@epcas5p1.samsung.com>
2026-01-16 10:08 ` Kundan Kumar
     [not found]   ` <CGME20260116101241epcas5p330f9c335a096aaaefda4b7d3c38d6038@epcas5p3.samsung.com>
2026-01-16 10:08     ` [PATCH v3 1/6] iomap: add write ops hook to attach metadata to folios Kundan Kumar
     [not found]   ` <CGME20260116101245epcas5p30269c6aa35784db67e6d6ca800a683a7@epcas5p3.samsung.com>
2026-01-16 10:08     ` [PATCH v3 2/6] xfs: add helpers to pack AG prediction info for per-folio tracking Kundan Kumar
2026-01-29  0:45       ` Darrick J. Wong
2026-02-03  7:15         ` Kundan Kumar
2026-02-05 16:39           ` Darrick J. Wong
2026-02-04  7:37       ` Nirjhar Roy (IBM)
     [not found]   ` <CGME20260116101251epcas5p1cf5b48f2efb14fe4387be3053b3c3ebc@epcas5p1.samsung.com>
2026-01-16 10:08     ` [PATCH v3 3/6] xfs: add per-inode AG prediction map and dirty-AG bitmap Kundan Kumar
2026-01-29  0:44       ` Darrick J. Wong
2026-02-03  7:20         ` Kundan Kumar
2026-02-05 16:42           ` Darrick J. Wong
2026-02-05  6:44         ` Nirjhar Roy (IBM)
2026-02-05 16:32           ` Darrick J. Wong
2026-02-06  5:41             ` Nirjhar Roy (IBM)
2026-02-05  6:36       ` Nirjhar Roy (IBM)
2026-02-05 16:36         ` Darrick J. Wong
2026-02-06  5:36           ` Nirjhar Roy (IBM)
2026-02-06  5:57             ` Darrick J. Wong
2026-02-06  6:03               ` Nirjhar Roy (IBM)
2026-02-06  7:00       ` Christoph Hellwig
     [not found]   ` <CGME20260116101256epcas5p2d6125a6bcad78c33f737fdc3484aca79@epcas5p2.samsung.com>
2026-01-16 10:08     ` [PATCH v3 4/6] xfs: tag folios with AG number during buffered write via iomap attach hook Kundan Kumar
2026-01-29  0:47       ` Darrick J. Wong
2026-01-29 22:40         ` Darrick J. Wong
2026-02-03  7:32           ` Kundan Kumar
2026-02-03  7:28         ` Kundan Kumar
2026-02-05 15:56           ` Brian Foster
2026-02-06  6:44       ` Nirjhar Roy (IBM)
     [not found]   ` <CGME20260116101259epcas5p1cfa6ab02e5a01f7c46cc78df95c57ce0@epcas5p1.samsung.com>
2026-01-16 10:08     ` [PATCH v3 5/6] xfs: add per-AG writeback workqueue infrastructure Kundan Kumar
2026-01-29 22:21       ` Darrick J. Wong
2026-02-03  7:35         ` Kundan Kumar
2026-02-06  6:46       ` Christoph Hellwig
2026-02-10 11:56       ` Nirjhar Roy (IBM)
     [not found]   ` <CGME20260116101305epcas5p497cd6d9027301853669f1c1aaffbf128@epcas5p4.samsung.com>
2026-01-16 10:08     ` [PATCH v3 6/6] xfs: offload writeback by AG using per-inode dirty bitmap and per-AG workers Kundan Kumar
2026-01-29 22:34       ` Darrick J. Wong
2026-02-03  7:40         ` Kundan Kumar
2026-02-11  9:39       ` Nirjhar Roy (IBM)
2026-01-16 16:13   ` [syzbot ci] Re: AG aware parallel writeback for XFS syzbot ci
2026-01-21 19:54   ` [PATCH v3 0/6] " Brian Foster
2026-01-22 16:15     ` Kundan Kumar
2026-01-23  9:36       ` Pankaj Raghav (Samsung)
2026-01-23 13:26       ` Brian Foster
2026-01-28 18:28         ` Kundan Kumar
2026-02-06  6:25           ` Christoph Hellwig
2026-02-06 10:07             ` Kundan Kumar
2026-02-06 17:42               ` Darrick J. Wong
2026-02-09  6:30               ` Christoph Hellwig
2026-02-09 15:54             ` Kundan Kumar
2026-02-10 15:38               ` Christoph Hellwig [this message]

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=20260210153854.GA2484@lst.de \
    --to=hch@lst.de \
    --cc=amir73il@gmail.com \
    --cc=anuj20.g@samsung.com \
    --cc=axboe@kernel.dk \
    --cc=bfoster@redhat.com \
    --cc=brauner@kernel.org \
    --cc=cem@kernel.org \
    --cc=clm@meta.com \
    --cc=dave@stgolabs.net \
    --cc=david@fromorbit.com \
    --cc=djwong@kernel.org \
    --cc=gost.dev@samsung.com \
    --cc=jack@suse.cz \
    --cc=joshi.k@samsung.com \
    --cc=kundan.kumar@samsung.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=mcgrof@kernel.org \
    --cc=ritesh.list@gmail.com \
    --cc=viro@zeniv.linux.org.uk \
    --cc=vishak.g@samsung.com \
    --cc=wangyufei@vivo.com \
    --cc=willy@infradead.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox