<html>
  <head>
    <meta content="text/html; charset=windows-1252"
      http-equiv="Content-Type">
  </head>
  <body bgcolor="#FFFFFF" text="#000000">
    <div class="moz-cite-prefix">Hi Leonardo, <br>
      <br>
      I am aware that sequential IO is routed directly to the backing
      device. And I also played with the parameters like
      sequential_threshold and the write_promote_adjustment introduced
      in 3.14. <br>
      To test this i ran ./fio --name=test
      --filename=/dev/mapper/dmcache  --rw=randwrite  --filesize=16G 
      --bs=64k --ioengine=libaio --direct=1 --iodepth=1000 in a endless
      loop. <br>
      <br>
      Regards <br>
      <br>
      Christoph<br>
      <br>
      <br>
      Am 08.07.2015 um 19:55 schrieb Leonardo Santos:<br>
    </div>
    <blockquote
cite="mid:CAEZ+n-hF2EUPAHYC98ao0x_Q2nWXFodaxXkBqjg8ZvpqNviVKQ@mail.gmail.com"
      type="cite">
      <div dir="ltr">
        <div class="gmail_extra">
          <div class="gmail_quote">
            <pre style="color:rgb(0,0,0)"><font face="arial, sans-serif">Are you using sequential or random workload? </font></pre>
            <pre style="color:rgb(0,0,0)"><span style="font-family:arial,sans-serif">It's important, since DMCache bypasses sequential I/O based on theshold.</span></pre>
          </div>
        </div>
      </div>
      <br>
      <fieldset class="mimeAttachmentHeader"></fieldset>
      <br>
      <pre wrap="">--
dm-devel mailing list
<a class="moz-txt-link-abbreviated" href="mailto:dm-devel@redhat.com">dm-devel@redhat.com</a>
<a class="moz-txt-link-freetext" href="https://www.redhat.com/mailman/listinfo/dm-devel">https://www.redhat.com/mailman/listinfo/dm-devel</a></pre>
    </blockquote>
    <br>
  </body>
</html>