<div dir="ltr"><br><div class="gmail_extra"><br><div class="gmail_quote">On Thu, Jun 21, 2018 at 8:41 PM, Pat Haley <span dir="ltr">&lt;<a href="mailto:phaley@mit.edu" target="_blank">phaley@mit.edu</a>&gt;</span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
  
    
  
  <div text="#000000" bgcolor="#FFFFFF">
    <br>
    Hi Raghavendra,<br>
    <br>
    Thanks for the suggestions.  Our technician will be in on Monday. 
    We&#39;ll test then and let you know the results.<br>
    <br>
    One question I have, is the &quot;group metadata-cache&quot; option supposed
    to directly impact the performance or is it to help collect data? 
    If the latter, where will the data be located?<br></div></blockquote><div><br></div><div>It impacts performance.</div><div> <br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div text="#000000" bgcolor="#FFFFFF">
    <br>
    Thanks again.<span class="HOEnZb"><font color="#888888"><br>
    <br>
    Pat</font></span><div><div class="h5"><br>
    <br>
    <br>
    <div class="m_-4085817742671750663moz-cite-prefix">On 06/21/2018 01:01 AM, Raghavendra
      Gowdappa wrote:<br>
    </div>
    <blockquote type="cite">
      
      <div dir="ltr"><br>
        <div class="gmail_extra"><br>
          <div class="gmail_quote">On Thu, Jun 21, 2018 at 10:24 AM,
            Raghavendra Gowdappa <span dir="ltr">&lt;<a href="mailto:rgowdapp@redhat.com" target="_blank">rgowdapp@redhat.com</a>&gt;</span>
            wrote:<br>
            <blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
              <div dir="ltr">
                <div>
                  <div>
                    <div>
                      <div>
                        <div>
                          <div>
                            <div>For the case of writes to glusterfs
                              mount,<br>
                              <br>
                            </div>
                            I saw in earlier conversations that there
                            are too many lookups, but small number of
                            writes. Since writes cached in write-behind
                            would invalidate metadata cache, lookups
                            won&#39;t be absorbed by md-cache. I am
                            wondering what would results look like if we
                            turn off performance.write-behind.<br>
                            <br>
                          </div>
                          @Pat,<br>
                          <br>
                        </div>
                        Can you set,<br>
                        <br>
                      </div>
                      # gluster volume set &lt;volname&gt;
                      performance.write-behind off<br>
                    </div>
                  </div>
                </div>
              </div>
            </blockquote>
            <div><br>
            </div>
            <div>Please turn on &quot;group metadata-cache&quot; for write tests
              too.</div>
            <div> <br>
            </div>
            <blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
              <div dir="ltr">
                <div>
                  <div>
                    <div><br>
                    </div>
                    and redo the tests writing to glusterfs mount? Let
                    us know about the results you see.<br>
                    <br>
                  </div>
                  regards,<br>
                </div>
                Raghavendra<br>
              </div>
              <div class="m_-4085817742671750663HOEnZb">
                <div class="m_-4085817742671750663h5">
                  <div class="gmail_extra"><br>
                    <div class="gmail_quote">On Thu, Jun 21, 2018 at
                      8:33 AM, Raghavendra Gowdappa <span dir="ltr">&lt;<a href="mailto:rgowdapp@redhat.com" target="_blank">rgowdapp@redhat.com</a>&gt;</span>
                      wrote:<br>
                      <blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
                        <div dir="ltr"><br>
                          <div class="gmail_extra"><br>
                            <div class="gmail_quote"><span>On Thu, Jun
                                21, 2018 at 8:32 AM, Raghavendra
                                Gowdappa <span dir="ltr">&lt;<a href="mailto:rgowdapp@redhat.com" target="_blank">rgowdapp@redhat.com</a>&gt;</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>For the case of reading from
                                        Glusterfs mount, read-ahead
                                        should help. However, we&#39;ve
                                        known issues with
                                        read-ahead[1][2]. To work around
                                        these, can you try with,<br>
                                        <br>
                                      </div>
                                      1. Turn off
                                      performance.open-behind<br>
                                    </div>
                                    #gluster volume set &lt;volname&gt;
                                    performance.open-behind off<br>
                                    <br>
                                    <div>2. enable group meta
                                      metadata-cache<br>
                                      # gluster volume set
                                      &lt;volname&gt; group
                                      metadata-cache</div>
                                  </div>
                                </blockquote>
                                <div><br>
                                </div>
                              </span>
                              <div>[1]  <a href="https://bugzilla.redhat.com/show_bug.cgi?id=1084508" target="_blank">https://bugzilla.redhat.com/sh<wbr>ow_bug.cgi?id=1084508</a></div>
                              <div>[2] <a href="https://bugzilla.redhat.com/show_bug.cgi?id=1214489" target="_blank">https://bugzilla.redhat.com/sh<wbr>ow_bug.cgi?id=1214489</a></div>
                              <span>
                                <div><br>
                                </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>
                                      <div>
                                        <div class="m_-4085817742671750663m_-7085830777103976589m_-1104802400275053683gmail-m_5499637752699686457h5"><br>
                                          <br>
                                          <div>
                                            <div>
                                              <div>
                                                <div class="gmail_extra"><br>
                                                  <div class="gmail_quote">On
                                                    Thu, Jun 21, 2018 at
                                                    5:00 AM, Pat Haley <span dir="ltr">&lt;<a href="mailto:phaley@mit.edu" target="_blank">phaley@mit.edu</a>&gt;</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"><br>
                                                      Hi,<br>
                                                      <br>
                                                      We were recently
                                                      revisiting our
                                                      problems with the
                                                      slowness of
                                                      gluster writes (<a href="http://lists.gluster.org/pipermail/gluster-users/2017-April/030529.html" rel="noreferrer" target="_blank">http://lists.gluster.org/pipe<wbr>rmail/gluster-users/2017-April<wbr>/030529.html</a>).
                                                      Specifically we
                                                      were testing the
                                                      suggestions in a
                                                      recent post (<a href="http://lists.gluster.org/pipermail/gluster-users/2018-March/033699.html" rel="noreferrer" target="_blank">http://lists.gluster.org/pipe<wbr>rmail/gluster-users/2018-March<wbr>/033699.html</a>).
                                                      The first two
                                                      suggestions
                                                      (specifying a
                                                      negative-timeout
                                                      in the mount
                                                      settings or adding
rpc-auth-allow-insecure to glusterd.vol) did not improve our
                                                      performance, while
                                                      setting
                                                      &quot;disperse.eager-lock
                                                      off&quot; provided a
                                                      tiny (5%)
                                                      speed-up.<br>
                                                      <br>
                                                      Some of the
                                                      various tests we
                                                      have tried earlier
                                                      can be seen in the
                                                      links below.  Do
                                                      any of the above
                                                      observations
                                                      suggest what we
                                                      could try next to
                                                      either improve the
                                                      speed or debug the
                                                      issue?  Thanks<br>
                                                      <br>
                                                      <a href="http://lists.gluster.org/pipermail/gluster-users/2017-June/031565.html" rel="noreferrer" target="_blank">http://lists.gluster.org/piper<wbr>mail/gluster-users/2017-June/0<wbr>31565.html</a><br>
                                                      <a href="http://lists.gluster.org/pipermail/gluster-users/2017-May/030937.html" rel="noreferrer" target="_blank">http://lists.gluster.org/piper<wbr>mail/gluster-users/2017-May/03<wbr>0937.html</a><br>
                                                      <br>
                                                      Pat<br>
                                                      <br>
                                                      -- <br>
                                                      <br>
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=<wbr>-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=<wbr>-=-=-<br>
                                                      Pat Haley         
                                                                     
                                                      Email:  <a href="mailto:phaley@mit.edu" target="_blank">phaley@mit.edu</a><br>
                                                      Center for Ocean
                                                      Engineering     
                                                       Phone:  (617)
                                                      253-6824<br>
                                                      Dept. of
                                                      Mechanical
                                                      Engineering   
                                                      Fax:    (617)
                                                      253-8125<br>
                                                      MIT, Room 5-213   
                                                                      <a href="http://web.mit.edu/phaley/www/" rel="noreferrer" target="_blank">http://web.mit.edu/phaley/www/</a><br>
                                                      77 Massachusetts
                                                      Avenue<br>
                                                      Cambridge, MA 
                                                      02139-4301<br>
                                                      <br>
______________________________<wbr>_________________<br>
                                                      Gluster-users
                                                      mailing list<br>
                                                      <a href="mailto:Gluster-users@gluster.org" target="_blank">Gluster-users@gluster.org</a><br>
                                                      <a href="http://lists.gluster.org/mailman/listinfo/gluster-users" rel="noreferrer" target="_blank">http://lists.gluster.org/mailm<wbr>an/listinfo/gluster-users</a></blockquote>
                                                  </div>
                                                  <br>
                                                </div>
                                              </div>
                                            </div>
                                          </div>
                                        </div>
                                      </div>
                                    </div>
                                  </div>
                                </blockquote>
                              </span></div>
                            <br>
                          </div>
                        </div>
                      </blockquote>
                    </div>
                    <br>
                  </div>
                </div>
              </div>
            </blockquote>
          </div>
          <br>
        </div>
      </div>
    </blockquote>
    <br>
    <pre class="m_-4085817742671750663moz-signature" cols="72">-- 

-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=<wbr>-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=<wbr>-=-=-
Pat Haley                          Email:  <a class="m_-4085817742671750663moz-txt-link-abbreviated" href="mailto:phaley@mit.edu" target="_blank">phaley@mit.edu</a>
Center for Ocean Engineering       Phone:  (617) 253-6824
Dept. of Mechanical Engineering    Fax:    (617) 253-8125
MIT, Room 5-213                    <a class="m_-4085817742671750663moz-txt-link-freetext" href="http://web.mit.edu/phaley/www/" target="_blank">http://web.mit.edu/phaley/www/</a>
77 Massachusetts Avenue
Cambridge, MA  02139-4301
</pre>
  </div></div></div>

<br>______________________________<wbr>_________________<br>
Gluster-users mailing list<br>
<a href="mailto:Gluster-users@gluster.org">Gluster-users@gluster.org</a><br>
<a href="http://lists.gluster.org/mailman/listinfo/gluster-users" rel="noreferrer" target="_blank">http://lists.gluster.org/<wbr>mailman/listinfo/gluster-users</a><br></blockquote></div><br></div></div>