I meant the other way. I meant to say that 3.2.0 must also have the issue (since you mentioned 3.3.0 in the subject)<div><br></div><div>Avati<br><br><div class="gmail_quote">On Tue, Sep 11, 2012 at 6:27 AM, Manhong Dai <span dir="ltr"><<a href="mailto:daimh@umich.edu" target="_blank">daimh@umich.edu</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Hi Avati,<br>
<br>
<br>
Thanks a lot for your help! It is good to know that 3.2.x doesn't have<br>
this problem. So the worst scenario for me is to re-install it with the<br>
latest 3.2.*. I hope my life won't be that miserable.<br>
<br>
<br>
Best,<br>
Manhong<br>
<div><div class="h5">On Mon, 2012-09-10 at 20:53 -0700, Anand Avati wrote:<br>
> Also, I find it very suspect that 3.2.x did not have the same<br>
> behavior!<br>
><br>
><br>
> Avati<br>
><br>
> On Mon, Sep 10, 2012 at 8:53 PM, Anand Avati <<a href="mailto:anand.avati@gmail.com">anand.avati@gmail.com</a>><br>
> wrote:<br>
> This is a limitation of the 'handle' nature of FUSE<br>
> filesystems. You will have to set a lower entry-timeout (mount<br>
> option) to fix this problem.<br>
><br>
><br>
> Avati<br>
><br>
><br>
> On Mon, Sep 10, 2012 at 5:13 PM, Dai, Manhong<br>
> <<a href="mailto:daimh@umich.edu">daimh@umich.edu</a>> wrote:<br>
> Hi Avati,<br>
><br>
><br>
> Thanks a lot! In my case, the application that<br>
> tries to create a new file is not inside the folder.<br>
><br>
><br>
> I write a simple bash scrip to demo this problem.<br>
><br>
> #!/bin/bash<br>
> FOLDER=/home/mengf_lab/daimh/temp/testdir<br>
> for ((i=0; i<100; i++))<br>
> do<br>
> echo "###$i###"<br>
> ssh mengf-n1 "rm -r $FOLDER; mkdir $FOLDER"<br>
> seq 10 |split -l 1 - $FOLDER/a.<br>
> done<br>
><br>
><br>
> And its output is<br>
> ###0###<br>
> ###1###<br>
> split: /home/mengf_lab/daimh/temp/testdir/a.aa: No<br>
> such file or directory<br>
> ###2###<br>
> split: /home/mengf_lab/daimh/temp/testdir/a.aa: No<br>
> such file or directory<br>
> ###3###<br>
> ###4###<br>
><br>
><br>
> Best,<br>
> Manhong<br>
><br>
><br>
><br>
><br>
><br>
><br>
</div></div>> ______________________________________________________<br>
<div class="HOEnZb"><div class="h5">> From: Anand Avati [<a href="mailto:anand.avati@gmail.com">anand.avati@gmail.com</a>]<br>
> Sent: Monday, September 10, 2012 5:25 PM<br>
> To: Dai, Manhong<br>
> Cc: <a href="mailto:gluster-users@gluster.org">gluster-users@gluster.org</a><br>
> Subject: Re: [Gluster-users] A problem with gluster<br>
> 3.3.0 and Sun Grid Engine<br>
><br>
><br>
><br>
><br>
><br>
> On Mon, Sep 10, 2012 at 8:30 AM, Manhong Dai<br>
> <<a href="mailto:daimh@umich.edu">daimh@umich.edu</a>> wrote:<br>
> Hi,<br>
><br>
><br>
> We got a huge problem on our sun grid engine<br>
> cluster with glusterfs 3.3.0. Could somebody<br>
> help me?<br>
><br>
><br>
> Based on my understanding, if a folder is<br>
> removed and recreated on other client node, a<br>
> program that tries to create a new file under<br>
> the folder fails very often.<br>
><br>
><br>
><br>
><br>
><br>
> Is the directory deleted and recreated by another<br>
> client/mount while the application which attempts to<br>
> create the file stays cd'ed inside the directory? Can<br>
> you try to confirm if this is the pattern?<br>
><br>
><br>
> Avati<br>
><br>
><br>
><br>
><br>
><br>
><br>
<br>
<br>
</div></div></blockquote></div><br></div>