Skip to content

Redfs ubuntu noble writethrough split#182

Closed
hbirth wants to merge 2 commits into
redfs-ubuntu-noble-6.8.0-58.60from
redfs-ubuntu-noble-writethrough-split
Closed

Redfs ubuntu noble writethrough split#182
hbirth wants to merge 2 commits into
redfs-ubuntu-noble-6.8.0-58.60from
redfs-ubuntu-noble-writethrough-split

Conversation

@hbirth

@hbirth hbirth commented Jun 12, 2026

Copy link
Copy Markdown
Collaborator

No description provided.

hbirth added 2 commits June 12, 2026 13:05
Writes that already match the alignment advertised via
FUSE_ALIGN_PG_ORDER gain nothing from the writeback cache and can
degrade into page-sized WRITE requests under dirty throttling.  Send
them through fuse_perform_write() instead, which packs requests up to
max_write and keeps them stripe-aligned for the backend.  They create
no dirty pages, so no DLM write lock needs to be cached for them.
Unaligned writes keep using the writeback cache.

Also clarify in the uapi header that align_page_order is the log2 of
the alignment in bytes, not in pages.

Signed-off-by: Horst Birthelmer <hbirthelmer@ddn.com>
Signed-off-by: Horst Birthelmer <hbirthelmer@ddn.com>
@hbirth hbirth requested review from bsbernd, cding-ddn and yongzech June 12, 2026 11:12
Comment thread fs/fuse/file.c
Comment thread fs/fuse/file.c
}

align = fc->alignment_pages ?
(u64)fc->alignment_pages << PAGE_SHIFT : PAGE_SIZE;

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why enforcing alignment on page size if fc->alignment_pages is not set?

Comment thread fs/fuse/file.c
@hbirth

hbirth commented Jun 15, 2026

Copy link
Copy Markdown
Collaborator Author

@bernd I have to close this PR because I cannot update it ... and open a new one with the requesteed changes ... just so you know

@hbirth hbirth closed this Jun 15, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants