From: Dave Jiang <dave.jiang@intel.com>
To: John Groves <john@jagalactic.com>, John Groves <John@Groves.net>,
Miklos Szeredi <miklos@szeredi.hu>,
Dan Williams <dan.j.williams@intel.com>,
Bernd Schubert <bschubert@ddn.com>,
Alison Schofield <alison.schofield@intel.com>
Cc: John Groves <jgroves@micron.com>,
John Groves <jgroves@fastmail.com>,
Jonathan Corbet <corbet@lwn.net>,
Vishal Verma <vishal.l.verma@intel.com>,
Matthew Wilcox <willy@infradead.org>, Jan Kara <jack@suse.cz>,
Alexander Viro <viro@zeniv.linux.org.uk>,
David Hildenbrand <david@kernel.org>,
Christian Brauner <brauner@kernel.org>,
"Darrick J . Wong" <djwong@kernel.org>,
Randy Dunlap <rdunlap@infradead.org>,
Jeff Layton <jlayton@kernel.org>,
Amir Goldstein <amir73il@gmail.com>,
Jonathan Cameron <Jonathan.Cameron@huawei.com>,
Stefan Hajnoczi <shajnocz@redhat.com>,
Joanne Koong <joannelkoong@gmail.com>,
Josef Bacik <josef@toxicpanda.com>,
Bagas Sanjaya <bagasdotme@gmail.com>,
James Morse <james.morse@arm.com>, Fuad Tabba <tabba@google.com>,
Sean Christopherson <seanjc@google.com>,
Shivank Garg <shivankg@amd.com>,
Ackerley Tng <ackerleytng@google.com>,
Gregory Price <gourry@gourry.net>,
Aravind Ramesh <arramesh@micron.com>,
Ajay Joshi <ajayjoshi@micron.com>,
"venkataravis@micron.com" <venkataravis@micron.com>,
"linux-doc@vger.kernel.org" <linux-doc@vger.kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"nvdimm@lists.linux.dev" <nvdimm@lists.linux.dev>,
"linux-cxl@vger.kernel.org" <linux-cxl@vger.kernel.org>,
"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>
Subject: Re: [PATCH V7 18/19] famfs_fuse: Add famfs fmap metadata documentation
Date: Thu, 19 Feb 2026 13:22:36 -0700 [thread overview]
Message-ID: <124bdd0a-c7d8-40e3-9d1d-481d73fd9186@intel.com> (raw)
In-Reply-To: <0100019bd33eab0d-e982dfea-fdc0-4f02-b60f-9d4897fdcb7d-000000@email.amazonses.com>
On 1/18/26 3:34 PM, John Groves wrote:
> From: John Groves <John@Groves.net>
>
> This describes the fmap metadata - both simple and interleaved
>
> Signed-off-by: John Groves <john@groves.net>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
> ---
> fs/fuse/famfs_kfmap.h | 73 +++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 73 insertions(+)
>
> diff --git a/fs/fuse/famfs_kfmap.h b/fs/fuse/famfs_kfmap.h
> index 0fff841f5a9e..970ad802b492 100644
> --- a/fs/fuse/famfs_kfmap.h
> +++ b/fs/fuse/famfs_kfmap.h
> @@ -7,6 +7,79 @@
> #ifndef FAMFS_KFMAP_H
> #define FAMFS_KFMAP_H
>
> +/* KABI version 43 (aka v2) fmap structures
> + *
> + * The location of the memory backing for a famfs file is described by
> + * the response to the GET_FMAP fuse message (defined in
> + * include/uapi/linux/fuse.h
> + *
> + * There are currently two extent formats: Simple and Interleaved.
> + *
> + * Simple extents are just (devindex, offset, length) tuples, where devindex
> + * references a devdax device that must be retrievable via the GET_DAXDEV
> + * message/response.
> + *
> + * The extent list size must be >= file_size.
> + *
> + * Interleaved extents merit some additional explanation. Interleaved
> + * extents stripe data across a collection of strips. Each strip is a
> + * contiguous allocation from a single devdax device - and is described by
> + * a simple_extent structure.
> + *
> + * Interleaved_extent example:
> + * ie_nstrips = 4
> + * ie_chunk_size = 2MiB
> + * ie_nbytes = 24MiB
> + *
> + * ┌────────────┐────────────┐────────────┐────────────┐
> + * │Chunk = 0 │Chunk = 1 │Chunk = 2 │Chunk = 3 │
> + * │Strip = 0 │Strip = 1 │Strip = 2 │Strip = 3 │
> + * │Stripe = 0 │Stripe = 0 │Stripe = 0 │Stripe = 0 │
> + * │ │ │ │ │
> + * └────────────┘────────────┘────────────┘────────────┘
> + * │Chunk = 4 │Chunk = 5 │Chunk = 6 │Chunk = 7 │
> + * │Strip = 0 │Strip = 1 │Strip = 2 │Strip = 3 │
> + * │Stripe = 1 │Stripe = 1 │Stripe = 1 │Stripe = 1 │
> + * │ │ │ │ │
> + * └────────────┘────────────┘────────────┘────────────┘
> + * │Chunk = 8 │Chunk = 9 │Chunk = 10 │Chunk = 11 │
> + * │Strip = 0 │Strip = 1 │Strip = 2 │Strip = 3 │
> + * │Stripe = 2 │Stripe = 2 │Stripe = 2 │Stripe = 2 │
> + * │ │ │ │ │
> + * └────────────┘────────────┘────────────┘────────────┘
> + *
> + * * Data is laid out across chunks in chunk # order
> + * * Columns are strips
> + * * Strips are contiguous devdax extents, normally each coming from a
> + * different memory device
> + * * Rows are stripes
> + * * The number of chunks is (int)((file_size + chunk_size - 1) / chunk_size)
> + * (and obviously the last chunk could be partial)
> + * * The stripe_size = (nstrips * chunk_size)
> + * * chunk_num(offset) = offset / chunk_size //integer division
> + * * strip_num(offset) = chunk_num(offset) % nchunks
> + * * stripe_num(offset) = offset / stripe_size //integer division
> + * * ...You get the idea - see the code for more details...
> + *
> + * Some concrete examples from the layout above:
> + * * Offset 0 in the file is offset 0 in chunk 0, which is offset 0 in
> + * strip 0
> + * * Offset 4MiB in the file is offset 0 in chunk 2, which is offset 0 in
> + * strip 2
> + * * Offset 15MiB in the file is offset 1MiB in chunk 7, which is offset
> + * 3MiB in strip 3
> + *
> + * Notes about this metadata format:
> + *
> + * * For various reasons, chunk_size must be a multiple of the applicable
> + * PAGE_SIZE
> + * * Since chunk_size and nstrips are constant within an interleaved_extent,
> + * resolving a file offset to a strip offset within a single
> + * interleaved_ext is order 1.
> + * * If nstrips==1, a list of interleaved_ext structures degenerates to a
> + * regular extent list (albeit with some wasted struct space).
> + */
> +
> /*
> * The structures below are the in-memory metadata format for famfs files.
> * Metadata retrieved via the GET_FMAP response is converted to this format
next prev parent reply other threads:[~2026-02-19 20:22 UTC|newest]
Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20260118222911.92214-1-john@jagalactic.com>
2026-01-18 22:29 ` [PATCH BUNDLE v7] famfs: Fabric-Attached Memory File System John Groves
2026-01-18 22:30 ` [PATCH V7 00/19] famfs: port into fuse John Groves
2026-01-18 22:31 ` [PATCH V7 01/19] dax: move dax_pgoff_to_phys from [drivers/dax/] device.c to bus.c John Groves
2026-02-11 14:23 ` Ira Weiny
2026-02-18 23:00 ` Dave Jiang
2026-01-18 22:31 ` [PATCH V7 02/19] dax: Factor out dax_folio_reset_order() helper John Groves
2026-02-13 21:24 ` Ira Weiny
2026-02-18 23:04 ` Dave Jiang
2026-02-24 3:00 ` Ackerley Tng
2026-03-02 15:06 ` John Groves
2026-03-09 6:27 ` Ackerley Tng
2026-01-18 22:31 ` [PATCH V7 03/19] dax: add fsdev.c driver for fs-dax on character dax John Groves
2026-02-13 21:05 ` Ira Weiny
2026-02-17 17:56 ` John Groves
2026-03-19 15:11 ` Jonathan Cameron
2026-01-18 22:31 ` [PATCH V7 04/19] dax: Save the kva from memremap John Groves
2026-02-13 21:23 ` Ira Weiny
2026-02-18 23:33 ` Dave Jiang
2026-01-18 22:31 ` [PATCH V7 05/19] dax: Add dax_operations for use by fs-dax on fsdev dax John Groves
2026-02-13 21:23 ` Ira Weiny
2026-02-18 0:38 ` John Groves
2026-02-14 16:10 ` Ira Weiny
2026-02-18 0:49 ` John Groves
2026-01-18 22:32 ` [PATCH V7 06/19] dax: Add dax_set_ops() for setting dax_operations at bind time John Groves
2026-02-19 15:41 ` Dave Jiang
2026-01-18 22:32 ` [PATCH V7 07/19] dax: Add fs_dax_get() func to prepare dax for fs-dax usage John Groves
2026-02-19 16:07 ` Dave Jiang
2026-02-26 23:20 ` John Groves
2026-01-18 22:32 ` [PATCH V7 08/19] dax: export dax_dev_get() John Groves
2026-02-19 16:18 ` Dave Jiang
2026-01-18 22:32 ` [PATCH V7 09/19] famfs_fuse: magic.h: Add famfs magic numbers John Groves
2026-02-19 16:21 ` Dave Jiang
2026-01-18 22:32 ` [PATCH V7 10/19] famfs_fuse: Update macro s/FUSE_IS_DAX/FUSE_IS_VIRTIO_DAX/ John Groves
2026-02-19 16:33 ` Dave Jiang
2026-01-18 22:32 ` [PATCH V7 11/19] famfs_fuse: Basic fuse kernel ABI enablement for famfs John Groves
2026-02-19 16:57 ` Dave Jiang
2026-01-18 22:33 ` [PATCH V7 12/19] famfs_fuse: Plumb the GET_FMAP message/response John Groves
2026-02-19 17:12 ` Dave Jiang
2026-02-26 0:24 ` John Groves
2026-01-18 22:33 ` [PATCH V7 13/19] famfs_fuse: Create files with famfs fmaps John Groves
2026-02-19 18:31 ` Dave Jiang
2026-02-25 21:30 ` John Groves
2026-01-18 22:33 ` [PATCH V7 14/19] famfs_fuse: GET_DAXDEV message and daxdev_table John Groves
2026-02-19 18:51 ` Dave Jiang
2026-02-25 23:51 ` John Groves
2026-01-18 22:33 ` [PATCH V7 15/19] famfs_fuse: Plumb dax iomap and fuse read/write/mmap John Groves
2026-01-18 22:33 ` [PATCH V7 16/19] famfs_fuse: Add holder_operations for dax notify_failure() John Groves
2026-01-18 22:33 ` [PATCH V7 17/19] famfs_fuse: Add DAX address_space_operations with noop_dirty_folio John Groves
2026-01-30 23:13 ` Joanne Koong
2026-01-18 22:34 ` [PATCH V7 18/19] famfs_fuse: Add famfs fmap metadata documentation John Groves
2026-02-19 20:22 ` Dave Jiang [this message]
2026-01-18 22:34 ` [PATCH V7 19/19] famfs_fuse: Add documentation John Groves
2026-02-19 21:39 ` Dave Jiang
2026-02-26 0:29 ` John Groves
2026-01-18 22:34 ` [PATCH V7 0/3] libfuse: add basic famfs support to libfuse John Groves
2026-01-18 22:35 ` [PATCH V7 1/3] fuse_kernel.h: bring up to baseline 6.19 John Groves
2026-01-30 22:53 ` Joanne Koong
2026-01-31 0:41 ` Darrick J. Wong
2026-01-31 1:18 ` Joanne Koong
2026-01-18 22:35 ` [PATCH V7 2/3] fuse_kernel.h: add famfs DAX fmap protocol definitions John Groves
2026-01-18 22:35 ` [PATCH V7 3/3] fuse: add famfs DAX fmap support John Groves
2026-01-18 22:36 ` [PATCH V4 0/2] ndctl: Add daxctl support for the new "famfs" mode of devdax John Groves
2026-01-18 22:36 ` [PATCH V4 1/2] daxctl: Add support for famfs mode John Groves
2026-02-19 21:47 ` Dave Jiang
2026-02-27 2:00 ` Alison Schofield
2026-01-18 22:36 ` [PATCH V4 2/2] Add test/daxctl-famfs.sh to test famfs mode transitions: John Groves
2026-02-19 22:02 ` Dave Jiang
2026-01-20 17:01 ` [PATCH V4 0/2] ndctl: Add daxctl support for the new "famfs" mode of devdax Alireza Sanaee
2026-01-20 17:05 ` John Groves
2026-02-09 23:13 ` Alison Schofield
2026-02-11 14:31 ` John Groves
2026-01-20 9:12 ` [PATCH BUNDLE v7] famfs: Fabric-Attached Memory File System Alireza Sanaee
2026-01-20 15:13 ` John Groves
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=124bdd0a-c7d8-40e3-9d1d-481d73fd9186@intel.com \
--to=dave.jiang@intel.com \
--cc=John@Groves.net \
--cc=Jonathan.Cameron@huawei.com \
--cc=ackerleytng@google.com \
--cc=ajayjoshi@micron.com \
--cc=alison.schofield@intel.com \
--cc=amir73il@gmail.com \
--cc=arramesh@micron.com \
--cc=bagasdotme@gmail.com \
--cc=brauner@kernel.org \
--cc=bschubert@ddn.com \
--cc=corbet@lwn.net \
--cc=dan.j.williams@intel.com \
--cc=david@kernel.org \
--cc=djwong@kernel.org \
--cc=gourry@gourry.net \
--cc=jack@suse.cz \
--cc=james.morse@arm.com \
--cc=jgroves@fastmail.com \
--cc=jgroves@micron.com \
--cc=jlayton@kernel.org \
--cc=joannelkoong@gmail.com \
--cc=john@jagalactic.com \
--cc=josef@toxicpanda.com \
--cc=linux-cxl@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=miklos@szeredi.hu \
--cc=nvdimm@lists.linux.dev \
--cc=rdunlap@infradead.org \
--cc=seanjc@google.com \
--cc=shajnocz@redhat.com \
--cc=shivankg@amd.com \
--cc=tabba@google.com \
--cc=venkataravis@micron.com \
--cc=viro@zeniv.linux.org.uk \
--cc=vishal.l.verma@intel.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