<html>
  <head>
    <meta content="text/html; charset=windows-1252"
      http-equiv="Content-Type">
  </head>
  <body text="#000000" bgcolor="#FFFFFF">
    <div class="moz-cite-prefix">On 09/11/2017 06:32 AM, Lukas Larsson
      wrote:<br>
    </div>
    <blockquote
cite="mid:CAP3zBqPJn9rMQhAkxbp3R3tWAE1U3Gqmdk6OB12amSHFGa4h9A@mail.gmail.com"
      type="cite">
      <div dir="ltr">Hello,
        <div><br>
        </div>
        <div>
          <div class="gmail_extra">
            <div class="gmail_quote">On Thu, Aug 31, 2017 at 10:07 AM,
              Mikael Karlsson <span dir="ltr"><<a
                  moz-do-not-send="true"
                  href="mailto:karlsson.rm@gmail.com" target="_blank"><a class="moz-txt-link-abbreviated" href="mailto:karlsson.rm@gmail.com">karlsson.rm@gmail.com</a></a>></span>
              wrote:<br>
              <blockquote class="gmail_quote" style="margin:0px 0px 0px
                0.8ex;border-left:1px solid
                rgb(204,204,204);padding-left:1ex">
                <div dir="ltr">
                  <div>
                    <div>
                      <div>I noticed that the secio emulator flag
                        (scheduler eager check for io) default value has
                        changed from false to true since ERTS 7.0. Could
                        someone explain what this means in practice, I
                        do not quite understand the line: "This,
                        however, also implies that execution of
                        outstanding I/O operation is not prioritized to
                        the same extent as when <span
                          class="gmail-m_-2787486722499859692gmail-code">false</span>
                        is passed."<br>
                      </div>
                    </div>
                  </div>
                </div>
              </blockquote>
              <div><br>
              </div>
              <div>
                <div>The eager check io flag instructs the emulator when
                  it should check for new I/O events (internally called
                  check_io)  in the fds that it is currently interested
                  in.</div>
                <div><br>
                </div>
                <div>Without secio, the schedulers will first finish
                  with all work generated from the previous check_io. If
                  a lot of I/O events where triggered by the check_io,
                  ports may be temporarily prioritized higher than
                  processes in order to be able to do the next check_io
                  sooner.</div>
                <div><br>
                </div>
                <div>With secio, the next check_io can be done before
                  all events of the previous check_io are consumed. When
                  this feature is enabled, the temporary higher
                  prioritization of ports is removed. This is the change
                  in priority that the documentation is trying to
                  explain.</div>
              </div>
              <div> </div>
              <blockquote class="gmail_quote" style="margin:0px 0px 0px
                0.8ex;border-left:1px solid
                rgb(204,204,204);padding-left:1ex">
                <div dir="ltr">
                  <div>Is there any special cases where you would prefer
                    to still have it set to false.<br>
                  </div>
                </div>
              </blockquote>
              <div><br>
              </div>
              <div>I see no reason to not have secio enabled.<br>
              </div>
              <br>
            </div>
          </div>
        </div>
      </div>
    </blockquote>
    I have tested in the past to determine that secio can make Erlang
    source code performance poor, if it isn't utilizing an Erlang port
    type, though the testing was with Erlang/OTP 17.4
(<a class="moz-txt-link-freetext" href="https://github.com/CloudI/loadtests/raw/master/tests/http_req/loadtest/results_v1_4_0/201412_summary.pdf">https://github.com/CloudI/loadtests/raw/master/tests/http_req/loadtest/results_v1_4_0/201412_summary.pdf</a>).<br>
    <br>
    Best Regards,<br>
    Michael<br>
  </body>
</html>