<div dir="ltr"><div><div>Yes, the bug was found in gfapi and is under review at <a href="http://review.gluster.org/14854" target="_blank">http://review.gluster.org/14854</a>.<br></div>This codepath is never exercised with a FUSE mount.<br><br></div>-Krutika<br></div><div class="gmail_extra"><br><div class="gmail_quote">On Thu, Jul 7, 2016 at 12:35 PM, Lindsay Mathieson <span dir="ltr"><<a href="mailto:lindsay.mathieson@gmail.com" target="_blank">lindsay.mathieson@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="">On 7 July 2016 at 16:32, Lindsay Mathieson <<a href="mailto:lindsay.mathieson@gmail.com">lindsay.mathieson@gmail.com</a>> wrote:<br>
> ut I had a<br>
> couple of VM's that refused to work on fuse due to access issues. It<br>
> was quite odd. I'll revisit one.<br>
<br>
<br>
</span>Ah, I figured that one out - VM's in question had caching turned off,<br>
which required aio support. There's a similary issue with ZFS. Setting<br>
the cache to writeback or writethrough (safer) solves the problem.<br>
<br>
I'll reconsider running 3.7.12 with fuse - is the developer consensus<br>
that the issues are just with libgfapi and that fuse should be as<br>
reliable as 3.7.11 for now?<br>
<br>
thanks,<br>
<span class="HOEnZb"><font color="#888888"><br>
--<br>
Lindsay<br>
</font></span></blockquote></div><br></div>