<div dir="ltr"><br><div class="gmail_extra"><br><div class="gmail_quote">On Tue, Jun 19, 2018 at 5:07 PM, Udit agarwal <span dir="ltr"><<a href="mailto:dev.madaari@gmail.com" target="_blank">dev.madaari@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Hi all,<br>We've managed to run fio on RTEMS. Currently, the following IOengines are working: psync, vsync ,sync, null, filecreate, ftruncate. Following are the rough sd card(with FAT fs) benchmarking results i got:<br>During a read operation:<br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><br>IOPS=201, BW=804KiB/s</blockquote><div>And during a write operation:<br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">IOPS=56, BW=224KiB/s</blockquote><div><a href="https://gist.github.com/madaari/54a6c43c69a95e7b7d7a61632c8dfda6" target="_blank">Here</a> are the complete results. I''ve documented the procedure on my <a href="http://uditagarwal.in/" target="_blank">blog</a> and updated the ticket <a href="https://devel.rtems.org/ticket/3429" target="_blank">#3429</a> with the leftovers.<br></div><div>Immediate goal after this is to get the generated code merged upstream to fio's main repository, i'm working on that, but that can move in parallel with phase 2 objectives.<br></div></div></div></blockquote><div><br></div><div>It's great that you got results! How does this compare to Linux or FreeBSD</div><div>on the same hardware configuration?</div><div><br></div><div>And now to the next phase. :)</div><div><br></div><div>Good job!</div><div><br></div><div>--joel </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div><div><br></div><div>Regards,<br></div><div>Udit AGarwal<br></div></div></div>
</blockquote></div><br></div></div>