Re: strace of io_uring events?

On 15/07/2020 23:09, Miklos Szeredi wrote:

On Wed, Jul 15, 2020 at 9:43 PM Pavel Begunkov [off-list ref] wrote:

quoted

To clear details for those who are not familiar with io_uring:

io_uring has a pair of queues, submission (SQ) and completion queues (CQ),
both shared between kernel and user spaces. The userspace submits requests
by filling a chunk of memory in SQ. The kernel picks up SQ entries in
(syscall io_uring_enter) or asynchronously by polling SQ.

CQ entries are filled by the kernel completely asynchronously and
in parallel. Some users just poll CQ to get them, but also have a way
to wait for them.

quoted

quoted

quoted

What do people think?

From what I can tell, listing the submitted requests on
io_uring_enter() would not be hard.  Request completion is
asynchronous, however, and may not require  io_uring_enter() syscall.
Am I correct?

Both, submission and completion sides may not require a syscall.

Okay.

quoted

quoted

quoted

quoted

Is there some existing tracing infrastructure that strace could use to
get async completion events?  Should we be introducing one?

There are static trace points covering all needs.

This needs to be unprivileged, or its usefulness is again compromized.

quoted

And if not used the whole thing have to be zero-overhead. Otherwise
there is perf, which is zero-overhead, and this IMHO won't fly.

Obviously it needs to be zero overhead if not tracing.

What won't fly?

Any approach that is not "zero-overhead if not used". 

-- 
Pavel Begunkov