<div dir="ltr"><div><div><div><div><div><div>There are two things you need to change for o-direct to be handled properly in gluster stack:<br><br></div>1) gluster volume set <volname> performance.strict-o-direct on<br></div>on nfs this option is gluster volume set <volname> performance.nfs.strict-o-direct on<br><br></div>2) gluster volume set <volname> network.remote-dio off<br><br></div>Please note that we found a bug in o-direct reads which happen sometime, which is fixed by <a href="http://review.gluster.org/14639">http://review.gluster.org/14639</a><br><br></div>Without this patch you may get EINVAL for reads sometimes.<br><br></div>Pranith<br></div><div class="gmail_extra"><br><div class="gmail_quote">On Fri, Jun 17, 2016 at 7:04 PM, Keiviw <span dir="ltr"><<a href="mailto:keiviw@163.com" target="_blank">keiviw@163.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div style="line-height:1.7;color:#000000;font-size:14px;font-family:Arial">By "mount -t glusterfs XXXX:/testvol -o direct-io-mode=true mountpoint",the GlusterFS client will enable the direct io, and the file will not cached in the GlusterFS client,but it won't work in the GlusterFS server. By defalut,the GlusterFS will ignore the direct io flag. How to make the server work in direct-io-mode??</div><br><br><span title="neteasefooter"><p> </p></span><br>_______________________________________________<br>
Gluster-devel mailing list<br>
<a href="mailto:Gluster-devel@gluster.org">Gluster-devel@gluster.org</a><br>
<a href="http://www.gluster.org/mailman/listinfo/gluster-devel" rel="noreferrer" target="_blank">http://www.gluster.org/mailman/listinfo/gluster-devel</a><br></blockquote></div><br><br clear="all"><br>-- <br><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr">Pranith<br></div></div>
</div>