On Fri, May 27, 2022 at 12:24:03PM +0530, Kanchan Joshi wrote: > On Thu, May 26, 2022 at 08:18:06PM +0530, Ankit Kumar wrote: > > .B libaio > > Linux native asynchronous I/O. Note that Linux may only support > > queued behavior with non-buffered I/O (set `direct=1' or > > @@ -2045,6 +2054,15 @@ 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,io_uring_cmd)nonvectored > > +With this option, fio will use non-vectored read/write commands, where address > > +must contain the address directly. > > +.TP > > +.BI (io_uring,io_uring_cmd)force_async > > +Normal operation for io_uring is to try and issue an sqe as non-blocking first, > > +and if that fails, execute it in an async manner. With this option set to N, > > +then every N request fio will ask sqe to be issued in an async manner. > > +.TP > > .BI (io_uring,xnvme)hipri > > io_uring_cmd should be added here? And same for fixedbufs too. > Agreed, will be done in v3 > > 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 > > @@ -2052,22 +2070,26 @@ 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)registerfiles > > +.BI (io_uring,io_uring_cmd)registerfiles > > With this option, fio registers the set of files being used with the kernel. > > This avoids the overhead of managing file counts in the kernel, making the > > submission and completion part more lightweight. Required for the below > > sqthread_poll option. > > .TP > > -.BI (io_uring,xnvme)sqthread_poll > > +.BI (io_uring,io_uring_cmd,xnvme)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 > > +.BI (io_uring,io_uring_cmd)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 (io_uring_cmd)cmd_type \fR=\fPstr > > +Specifies the type of uring passthrough command to be used. Supported > > +value is nvme. > > Seems that is default value too. So that part needs to be mentioned > here. Yes, will add it in v3
