optimise registered buffer/file updates
Status from this message: Applied, thanks!
Get series with b4
b4 am [email protected]Versions newest first · linked by author and title
- v2 Latest13 patches 2 repliesApplied
- v1 RFC11 patches 11 repliesSuperseded
Patches in v2 Applied
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/13 | io_uring/rsrc: use non-pcpu refcounts for nodesio_uring/ io_uring/ | +9 | 0 replies | |
| 2/13 | io_uring/rsrc: keep cached refs per nodeinclude/ io_uring/ io_uring/ | +18 | 0 replies | |
| 3/13 | io_uring: don't put nodes under spinlocksio_uring/ io_uring/ | +8 | 0 replies | |
| 4/13 | io_uring: io_free_req() via twio_uring/ | +7 | 0 replies | |
| 5/13 | io_uring/rsrc: protect node refs with uring_lockio_uring/ io_uring/ io_uring/ | +21 | 0 replies | |
| 6/13 | io_uring/rsrc: kill rsrc_ref_lockinclude/ io_uring/ io_uring/ | +1 | 0 replies | |
| 7/13 | io_uring/rsrc: rename rsrc_listio_uring/ io_uring/ | +10 | 0 replies | |
| 8/13 | io_uring/rsrc: optimise io_rsrc_put allocationio_uring/ io_uring/ | +36 | 0 replies | |
| 9/13 | io_uring/rsrc: don't offload node freeinclude/ io_uring/ io_uring/ | +4 | 0 replies | |
| 10/13 | io_uring/rsrc: cache struct io_rsrc_nodeinclude/ io_uring/ io_uring/ +1 more | +32 | 0 replies | |
| 11/13 | io_uring/rsrc: add lockdep sanity checksio_uring/ io_uring/ io_uring/ | +7 | 0 replies | |
| 12/13 | io_uring/rsrc: optimise io_rsrc_data refcountingio_uring/ io_uring/ | +19 | 0 replies | |
| 13/13 | io_uring/rsrc: add custom limit for node cachinginclude/ io_uring/ io_uring/ +1 more | +13 | 0 replies |
Reviews trailers per patch
No Reviewed-by, Acked-by or Tested-by trailers for v2 yet.
Cover letter [PATCH v2 00/13] optimise registered buffer/file updates
The patchset optimises registered files and buffers updates / removals, The rsrc-update-bench test showes 11x improvement (1040K -> 11468K updates / sec). It also improves latency by eliminating rcu grace period waiting and bouncing it to another worker, and reduces memory footprint by removing percpu refs.
That's quite important for apps updating files/buffers with medium or higher frequency as updates are slow and expensive, and it currently takes quite a number of IO requests per update to make using fixed files/buffers worthwhile.
Another upside is that it makes it simpler, patch 9 removes very convoluted synchronisation via flush_delayed_work() from the quiesce path.
v2: rebase, add patches 12 and 13 to remove the last pair atomics out
of the path and to limit caching.
Pavel Begunkov (13):
io_uring/rsrc: use non-pcpu refcounts for nodes io_uring/rsrc: keep cached refs per node
io_uring: don't put nodes under spinlocks
io_uring: io_free_req() via tw io_uring/rsrc: protect node refs with uring_lock io_uring/rsrc: kill rsrc_ref_lock io_uring/rsrc: rename rsrc_list io_uring/rsrc: optimise io_rsrc_put allocation io_uring/rsrc: don't offload node free io_uring/rsrc: cache struct io_rsrc_node io_uring/rsrc: add lockdep sanity checks io_uring/rsrc: optimise io_rsrc_data refcounting io_uring/rsrc: add custom limit for node caching
include/linux/io_uring_types.h | 8 +- io_uring/alloc_cache.h | 6 +- io_uring/io_uring.c | 54 ++++++---- io_uring/rsrc.c | 176 ++++++++++++--------------------- io_uring/rsrc.h | 58 +++++------ 5 files changed, 136 insertions(+), 166 deletions(-)
Signature · 1 line
2.39.1