Add support for non-IPI task_work
Get series with b4
b4 am [email protected]Versions newest first · linked by author and title
- v4 Latest0 of 5 patches 1 replyIn review
- v30 of 5 patches 0 repliesSuperseded
- v25 patches 0 repliesSuperseded
Earlier versions · 1
| Version | Posted | Patches | Replies | Status |
|---|---|---|---|---|
| v1 | 5 patches | 3 replies | Superseded |
Changes in v4 from the cover letter
- Make SQPOLL incompatible with the IPI flags. It makes no sense for SQPOLL as no IPIs are ever used there anyway, so make that explicit and fail a request to setup a ring like that.
Patches in v4 No applies recorded yet
None of the 5 patches the cover letter announces are in this archive.
Reviews trailers per patch
| Patch | Pavel Begunkov |
|---|---|
| Series | R-b |
Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.
Cover letter [PATCHSET v4 next 0/5] Add support for non-IPI task_work
Hi,
Unless we're using SQPOLL, any task_work queue will result in an IPI to the target task unless it's running in the kernel already. This isn't always needed, particularly not for the common case of not sharing the ring. In certain workloads, this can provide a 5-10% improvement. Some of this is due the cost of the IPI, and some from needlessly interrupting the target task when the work could just get run when completions are being waited for.
Patches 1..4 are prep patches, patch 5 is the actual change, and patch 6 adds support for IORING_SQ_TASKRUN so that applications may use this feature and still rely on io_uring_peek_cqe().
v4:
- Make SQPOLL incompatible with the IPI flags. It makes no sense for SQPOLL as no IPIs are ever used there anyway, so make that explicit and fail a request to setup a ring like that.