We're having the same problem --- the underlying bricks seem fine and the problem appears to be that ls is reporting the wrong thing rather than there are actually duplicate files.
We are using gluster 3.6.1-1 on machines running Scientific Linux 6.3 (we're use the glusterfs-epel packages). The underlying bricks are all ext3.
Different client machines report different duplicate files. There doesn't seem to be pattern to why files duplicated -- some bricks seem to have more files that are listed as duplicates than others but no obvious pattern.
Some other oddities. We have a directory called dm512 that contains some duplicate files.
If I do ls dm512, the duplicate files appear -- one of which is called restart.12
But if I say "ls restart.36", the file appears only once
But if I say "ls restart.36*", the file appears twice. And using, find
find . -iname "restart.36" -exec echo "<{}>" \;
gives
<./restart.36>
<./restart.36>
We upgraded from 3.5 to 3.6 about two weeks ago and user only reported the problem about a week ago. I don't think this necessarily means the problem didn't occur before -- our gluster file system is a storage area for us for relatively infrequently but important large data sets.
It's a bit unnerving for the user and causes some scripts to break, e.g., "for x in `ls dm512`; do"
Scott
<table width="100%" border="0" cellspacing="0" cellpadding="0" style="width:100%;">
<tr>
<td align="left" style="text-align:justify;"><font face="arial,sans-serif" size="1" color="#999999"><span style="font-size:11px;">This communication is intended for the addressee only. It is confidential. If you have received this communication in error, please notify us immediately and destroy the original message. You may not copy or disseminate this communication without the permission of the University. Only authorised signatories are competent to enter into agreements on behalf of the University and recipients are thus advised that the content of this message may not be legally binding on the University and may contain the personal views and opinions of the author, which are not necessarily the views and opinions of The University of the Witwatersrand, Johannesburg. All agreements between the University and outsiders are subject to South African Law unless the University agrees in writing to the contrary. </span></font></td>
</tr>
</table>
_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
http://www.gluster.org/mailman/listinfo/gluster-users
