From: Christoph Hellwig <[email protected]>
To: Dave Chinner <[email protected]>
Cc: Christoph Hellwig <[email protected]>, Pierre Labat <[email protected]>,
Keith Busch <[email protected]>,
Kanchan Joshi <[email protected]>,
Keith Busch <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>,
"[email protected]" <[email protected]>
Subject: Re: [EXT] Re: [PATCHv11 0/9] write hints with nvme fdp and scsi streams
Date: Thu, 14 Nov 2024 07:07:10 +0100 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
On Thu, Nov 14, 2024 at 10:51:09AM +1100, Dave Chinner wrote:
> Specifically to this "stream hint" discussion: go look at the XFS
> filestreams allocator.
Those are rally two different things - file streams is about how to
locate data into a single hardware write streams. SCSI/NVMe streams
including streams 2.0 (FDP) that this thread is about is about telling
the hardware about these streams, and also about allowing the file
systems (or other user of the storage) to pack into the actual
underlying hardware boundaries that matter for deleting/overwriting
this data.
Funnily enough Hans and I were just recently brainstorming on how to
tie both together for the zoned xfs work.
> SGI wrote an entirely new allocator for XFS whose only purpose in
> life is to automatically separate individual streams of user data
> into physically separate regions of LBA space.
One of the interesting quirks of streams/FDP is that they they operate
on (semi-)physical data placement that is completely decoupled from LBA
space. So if a file system or application really wants to track LBA
vs physical allocations separately it gives them a way to do that.
I don't really know what the advantage of having to track both is, but
people smarted than me might have good uses for it.
next prev parent reply other threads:[~2024-11-14 6:07 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-08 19:36 [PATCHv11 0/9] write hints with nvme fdp and scsi streams Keith Busch
2024-11-08 19:36 ` [PATCHv11 1/9] block: use generic u16 for write hints Keith Busch
2024-11-08 19:36 ` [PATCHv11 2/9] block: introduce max_write_hints queue limit Keith Busch
2024-11-08 19:36 ` [PATCHv11 3/9] statx: add write hint information Keith Busch
2024-11-08 19:36 ` [PATCHv11 4/9] block: allow ability to limit partition write hints Keith Busch
2024-11-08 19:36 ` [PATCHv11 5/9] block, fs: add write hint to kiocb Keith Busch
2024-11-08 19:36 ` [PATCHv11 6/9] io_uring: enable per-io hinting capability Keith Busch
2024-11-08 19:36 ` [PATCHv11 7/9] block: export placement hint feature Keith Busch
2024-11-11 10:29 ` [PATCHv11 0/9] write hints with nvme fdp and scsi streams Christoph Hellwig
2024-11-11 16:27 ` Keith Busch
2024-11-11 16:34 ` Christoph Hellwig
2024-11-12 13:26 ` Kanchan Joshi
2024-11-12 13:34 ` Christoph Hellwig
2024-11-12 14:25 ` Keith Busch
2024-11-12 16:50 ` Christoph Hellwig
2024-11-12 17:19 ` Christoph Hellwig
2024-11-12 18:18 ` [EXT] " Pierre Labat
2024-11-13 4:47 ` Christoph Hellwig
2024-11-13 23:51 ` Dave Chinner
2024-11-14 3:09 ` Martin K. Petersen
2024-11-14 6:07 ` Christoph Hellwig [this message]
2024-11-15 16:28 ` Keith Busch
2024-11-15 16:53 ` Christoph Hellwig
2024-11-18 23:37 ` Keith Busch
2024-11-19 7:15 ` Christoph Hellwig
2024-11-20 17:21 ` Darrick J. Wong
2024-11-20 18:11 ` Keith Busch
2024-11-21 7:17 ` Christoph Hellwig
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 \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
/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