Linux EXT4 FS development
 help / color / mirror / Atom feed
* Implementation plan for a dedicated block cache for ext4
@ 2026-11-20 15:21 Theodore Tso
  0 siblings, 0 replies; only message in thread
From: Theodore Tso @ 2026-11-20 15:21 UTC (permalink / raw)
  To: Ext4 Developers List

As I had discussed on the ext4 conference call, I've been toying with
the idea of creating a dedicated block cache for ext4.  With the help
of AI --- I won't say AI Overlords; I'm conficed the AI Intern, or
perhaps AI PFY is more appropriate :-) --- I've come up with a
high-level design and implementation doc:

   https://github.com/tytso/ext4-artifacts/blob/main/jbuf/implementation-plan.md

I'd appreciate comments.  I'd suggest reading sections 1 (Goals), 3
(Architectural Decisions and Hazards), and 7 (Block-Device Superblock
Coherency) first.

Nothing here is locked down.  One of the things that I am still unsure
about is how nasty including support for data=journal mode is going to
be, and whether we will want to drop support before proceeding.

I expect we'll be doing several rounds of design reviews before I ask
the AI to create the patch series.  For people who prefer to look at
code first, feel free to wait until later.  But I do think this is one
place where debating things at the detail level of the implementation
plan is more efficient than having reading throguh 37 iterations of a
20 patch series.  :-)

						- Ted

^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2026-11-20 15:21 UTC | newest]

Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-11-20 15:21 Implementation plan for a dedicated block cache for ext4 Theodore Tso

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox