Hi Pavel,
I'm currently trying to prototype for an IORING_POLL_CANCEL_ON_CLOSE
flag that can be passed to POLL_ADD. With that we'll register
the request in &req->file->f_uring_poll (similar to the file->f_ep list for epoll)
Then we only get a real reference to the file during the call to
vfs_poll() otherwise we drop the fget/fput reference and rely on
an io_uring_poll_release_file() (similar to eventpoll_release_file())
to cancel our registered poll request.
Yes, this is a bit tricky as we hold the file ref across the operation. I'd
be interested in seeing your approach to this, and also how it would
interact with registered files...
Not sure I mentioned before but shutdown(2) / IORING_OP_SHUTDOWN
usually helps. Is there anything keeping you from doing that?
The thing is that the tevent backend has no control over what
callers do and there's no way to audit all high level samba code,
everything needs to work exactly as it does with the poll and epoll backends.
Only high level code that actively/directly uses io_uring features could cope
with io_uring specific behavior.
As a side note I recently work on bug related to half closed tcp sockets,
see https://bugzilla.samba.org/show_bug.cgi?id=15202
It seems that shutdown() (even with SHUT_RDWR) behaves differently
for tcp sockets compared to a (final) close().
Do you only poll sockets or pipes as well?
Anything that's supported by poll needs to work.
The key flag is IORING_SETUP_DEFER_TASKRUN. On a different system than above
I'm getting the following numbers:
- epoll: Got 114450.16 pipe events/sec
- poll: Got 105872.52 pipe events/sec
- samba_io_uring_ev-without-defer_taskrun': Got 95564.22 pipe events/sec
- samba_io_uring_ev-with-defer_taskrun': Got 122853.85 pipe events/sec
Any chance you can do a run with just IORING_SETUP_COOP_TASKRUN set? I'm
curious how big of an impact the IPI elimination is, where it slots in
compared to the defer taskrun and the default settings.
And if it doesn't take too much time to test, it would also be interesting
to see if there is any impact from IORING_SETUP_SINGLE_ISSUER alone,
without TASKRUN flags.
See the other mail to Jens.
metze
