From 10a57a0823789e7fb76f26073edc37200aa356d9 Mon Sep 17 00:00:00 2001 From: Jeff Moyer Date: Thu, 14 Feb 2019 18:20:33 -0500 Subject: io_uring_enter.2: clarify min_complete min_complete means slightly different things depending on how the ring was setup. Signed-off-by: Jeff Moyer Signed-off-by: Jens Axboe --- man/io_uring_enter.2 | 33 ++++++++++++++++++++------------- 1 file changed, 20 insertions(+), 13 deletions(-) (limited to 'man/io_uring_enter.2') diff --git a/man/io_uring_enter.2 b/man/io_uring_enter.2 index 92cc77e..0e6ca61 100644 --- a/man/io_uring_enter.2 +++ b/man/io_uring_enter.2 @@ -37,21 +37,28 @@ the bit is set in .I flags, then the system call will attempt to wait for -.I min_events -I/O completions. Note that it is valid to specify -.B IORING_ENTER_GETEVENTS -in -.I flags -and pass in .I min_complete -as 0 at the same time. This allows the kernel to return already -completed events without waiting. This is useful only when the -io_uring instance was configured for polling (by specifying the +event completions before returning. If the io_uring instance was +configured for polling, by specifying +.B IORING_SETUP_IOPOLL +in the call to +.BR io_uring_setup (2), +then min_complete has a slightly different meaning. Passing a value +of 0 instructs the kernel to return any events which are already complete, +without blocking. If +.I min_complete +is a non-zero value, the kernel will still return immediately if any +completion events are available. If no event completions are +available, then the call will poll either until one or more +completions become available, or until the process has exceeded its +scheduler time slice. + +Note that, for interrupt driven I/O (where .B IORING_SETUP_IOPOLL -flag in -.BR io_uring_setup(2)), -as for IRQ driven I/O, the application can just check the completion -queue without entering the kernel. +was not specified in the call to +.BR io_uring_setup (2)), +an application may check the completion queue for event completions +without entering the kernel at all. .PP When the system call returns that a certain amount of SQEs have been consumed and submitted, it's safe to reuse SQE entries in the ring. This is -- cgit