xfs: merged io completions
Get series with b4
b4 am 155529406249.243484.1307333973877627694.stgit@magnoliaVersions newest first · linked by author and title
- v2 Latest3 patches 13 repliesIn review
- v1 RFC1 patch 3 repliesSuperseded
Patches in v2 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/3 | xfs: implement per-inode writeback completion queuesfs/ fs/ fs/ +1 more | +47 | 10 replies | |
| 1/3 | xfs: implement per-inode writeback completion queuesfs/ fs/ fs/ +1 more | +47 | 1 reply | |
| 2/3 | xfs: remove unused m_data_workqueuefs/ fs/ | +1 | 1 reply | |
| 3/3 | xfs: merge adjacent io completions of the same typefs/ | +86 | 1 reply |
Reviews trailers per patch
All 4 patches have a Reviewed-by or Acked-by.
| Patch | Brian Foster |
|---|---|
| 1/3 | R-b |
| 1/3 | R-b |
| 2/3 | R-b |
| 3/3 | R-b |
Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.
Cover letter [PATCH v2 0/3] xfs: merged io completions
Hi all,
Here's a quick patchset reworking writeback ioend completion processing into per-inode completion queues so that we don't have a thundering herd of unwritten/cow completion kworkers contending for the ILOCK that then tie up log reservation space and cause deadlocks. The third patch combines adjacent ioends when possible to reduce the overhead further.
If you're going to start using this mess, you probably ought to just pull from my git trees, which are linked below.
This is an extraordinary way to destroy everything. Enjoy! Comments and questions are, as always, welcome.
--D
kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=merged-completions