From: Jens Axboe Date: Fri, 26 Jul 2019 15:53:43 +0000 (-0600) Subject: Document io_uring feature X-Git-Tag: fio-3.16~47 X-Git-Url: https://git.kernel.dk/?p=fio.git;a=commitdiff_plain;h=029b42ace698eae477c5e261d2f82b191507526b Document io_uring feature This was released with Linux 5.1, so we can document it now as the API won't change. Signed-off-by: Jens Axboe --- diff --git a/HOWTO b/HOWTO index 142b83e5..81244064 100644 --- a/HOWTO +++ b/HOWTO @@ -1805,6 +1805,11 @@ I/O engine **pvsync2** Basic :manpage:`preadv2(2)` or :manpage:`pwritev2(2)` I/O. + **io_uring** + Fast Linux native asynchronous I/O. Supports async IO + for both direct and buffered IO. + This engine defines engine specific options. + **libaio** Linux native asynchronous I/O. Note that Linux may only support queued behavior with non-buffered I/O (set ``direct=1`` or @@ -2002,6 +2007,35 @@ In addition, there are some parameters which are only valid when a specific with the caveat that when used on the command line, they must come after the :option:`ioengine` that defines them is selected. +.. option:: hipri : [io_uring] + + If this option is set, fio will attempt to use polled IO completions. + Normal IO completions generate interrupts to signal the completion of + IO, polled completions do not. Hence they are require active reaping + by the application. The benefits are more efficient IO for high IOPS + scenarios, and lower latencies for low queue depth IO. + +.. option:: fixedbufs : [io_uring] + + If fio is asked to do direct IO, then Linux will map pages for each + IO call, and release them when IO is done. If this option is set, the + pages are pre-mapped before IO is started. This eliminates the need to + map and release for each IO. This is more efficient, and reduces the + IO latency as well. + +.. option:: sqthread_poll : [io_uring] + + Normally fio will submit IO by issuing a system call to notify the + kernel of available items in the SQ ring. If this option is set, the + act of submitting IO will be done by a polling thread in the kernel. + This frees up cycles for fio, at the cost of using more CPU in the + system. + +.. option:: sqthread_poll_cpu : [io_uring] + + When :option:`sqthread_poll` is set, this option provides a way to + define which CPU should be used for the polling thread. + .. option:: userspace_reap : [libaio] Normally, with the libaio engine in use, fio will use the diff --git a/fio.1 b/fio.1 index 156201ad..2966d9d5 100644 --- a/fio.1 +++ b/fio.1 @@ -1762,6 +1762,29 @@ In addition, there are some parameters which are only valid when a specific with the caveat that when used on the command line, they must come after the \fBioengine\fR that defines them is selected. .TP +.BI (io_uring)hipri +If this option is set, fio will attempt to use polled IO completions. Normal IO +completions generate interrupts to signal the completion of IO, polled +completions do not. Hence they are require active reaping by the application. +The benefits are more efficient IO for high IOPS scenarios, and lower latencies +for low queue depth IO. +.TP +.BI (io_uring)fixedbufs +If fio is asked to do direct IO, then Linux will map pages for each IO call, and +release them when IO is done. If this option is set, the pages are pre-mapped +before IO is started. This eliminates the need to map and release for each IO. +This is more efficient, and reduces the IO latency as well. +.TP +.BI (io_uring)sqthread_poll +Normally fio will submit IO by issuing a system call to notify the kernel of +available items in the SQ ring. If this option is set, the act of submitting IO +will be done by a polling thread in the kernel. This frees up cycles for fio, at +the cost of using more CPU in the system. +.TP +.BI (io_uring)sqthread_poll_cpu +When `sqthread_poll` is set, this option provides a way to define which CPU +should be used for the polling thread. +.TP .BI (libaio)userspace_reap Normally, with the libaio engine in use, fio will use the \fBio_getevents\fR\|(3) system call to reap newly returned events. With