<div dir="ltr"><div>Hi Xavier,</div><div><br></div>Thanks for your reply. When can we expect the 3.7.1 release?<div><br></div><div>cheers</div><div>Backer<br><div class="gmail_extra"><br><div class="gmail_quote">On Wed, May 27, 2015 at 1:22 PM, Xavier Hernandez <span dir="ltr"><<a href="mailto:xhernandez@datalab.es" target="_blank">xhernandez@datalab.es</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Hi,<br>
<br>
some Input/Output error issues have been identified and fixed. These fixes will be available on 3.7.1.<br>
<br>
Xavi<div><div class="h5"><br>
<br>
On 05/26/2015 10:15 AM, Mohamed Pakkeer wrote:<br>
</div></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div><div class="h5">
Hi Glusterfs Experts,<br>
<br>
We are testing glusterfs 3.7.0 tarball on our 10 Node glusterfs cluster.<br>
Each node has 36 dirves and please find the volume info below<br>
<br>
Volume Name: vaulttest5<br>
Type: Distributed-Disperse<br>
Volume ID: 68e082a6-9819-4885-856c-1510cd201bd9<br>
Status: Started<br>
Number of Bricks: 36 x (8 + 2) = 360<br>
Transport-type: tcp<br>
Bricks:<br>
Brick1: 10.1.2.1:/media/disk1<br>
Brick2: 10.1.2.2:/media/disk1<br>
Brick3: 10.1.2.3:/media/disk1<br>
Brick4: 10.1.2.4:/media/disk1<br>
Brick5: 10.1.2.5:/media/disk1<br>
Brick6: 10.1.2.6:/media/disk1<br>
Brick7: 10.1.2.7:/media/disk1<br>
Brick8: 10.1.2.8:/media/disk1<br>
Brick9: 10.1.2.9:/media/disk1<br>
Brick10: 10.1.2.10:/media/disk1<br>
Brick11: 10.1.2.1:/media/disk2<br>
Brick12: 10.1.2.2:/media/disk2<br>
Brick13: 10.1.2.3:/media/disk2<br>
Brick14: 10.1.2.4:/media/disk2<br>
Brick15: 10.1.2.5:/media/disk2<br>
Brick16: 10.1.2.6:/media/disk2<br>
Brick17: 10.1.2.7:/media/disk2<br>
Brick18: 10.1.2.8:/media/disk2<br>
Brick19: 10.1.2.9:/media/disk2<br>
Brick20: 10.1.2.10:/media/disk2<br>
...<br>
....<br>
Brick351: 10.1.2.1:/media/disk36<br>
Brick352: 10.1.2.2:/media/disk36<br>
Brick353: 10.1.2.3:/media/disk36<br>
Brick354: 10.1.2.4:/media/disk36<br>
Brick355: 10.1.2.5:/media/disk36<br>
Brick356: 10.1.2.6:/media/disk36<br>
Brick357: 10.1.2.7:/media/disk36<br>
Brick358: 10.1.2.8:/media/disk36<br>
Brick359: 10.1.2.9:/media/disk36<br>
Brick360: 10.1.2.10:/media/disk36<br>
Options Reconfigured:<br>
performance.readdir-ahead: on<br>
<br>
We did some performance testing and simulated the proactive self healing<br>
for Erasure coding. Disperse volume has been created across nodes.<br>
<br></div></div>
_*Description of problem*_<br>
<br>
I disconnected the *network of two nodes* and tried to write some video<br>
files and *glusterfs* *wrote the video files on balance 8 nodes<br>
perfectly*. I tried to download the uploaded file and it was downloaded<span class=""><br>
perfectly. Then i enabled the network of two nodes, the pro active self<br>
healing mechanism worked perfectly and wrote the unavailable junk of<br>
data to the recently enabled node from the other 8 nodes. But when i<br>
tried to download the same file node, it showed Input/Output error. I<br>
couldn't download the file. I think there is an issue in pro active self<br>
healing.<br>
<br>
Also we tried the simulation with one node network failure. We faced<br>
same I/O error issue while downloading the file<br>
<br>
<br></span>
_Error while downloading file _<br>
_<br>
_<span class=""><br>
<br>
root@master02:/home/admin# rsync -r --progress /mnt/gluster/file13_AN<br>
./1/file13_AN-2<br>
<br>
sending incremental file list<br>
<br>
file13_AN<br>
<br>
3,342,355,597 100% 4.87MB/s 0:10:54 (xfr#1, to-chk=0/1)<br>
<br>
rsync: read errors mapping "/mnt/gluster/file13_AN": Input/output error (5)<br>
<br>
WARNING: file13_AN failed verification -- update discarded (will try again).<br>
<br>
root@master02:/home/admin# cp /mnt/gluster/file13_AN ./1/file13_AN-3<br>
<br>
cp: error reading ‘/mnt/gluster/file13_AN’: Input/output error<br>
<br></span>
cp: failed to extend ‘./1/file13_AN-3’: Input/output error_<span class=""><br>
_<br>
<br>
<br>
We can't conclude the issue with glusterfs 3.7.0 or our glusterfs<br>
configuration.<br>
<br>
Any help would be greatly appreciated<br>
<br>
--<br>
Cheers<br>
Backer<br>
<br>
<br>
<br></span>
_______________________________________________<br>
Gluster-users mailing list<br>
<a href="mailto:Gluster-users@gluster.org" target="_blank">Gluster-users@gluster.org</a><br>
<a href="http://www.gluster.org/mailman/listinfo/gluster-users" target="_blank">http://www.gluster.org/mailman/listinfo/gluster-users</a><br>
<br>
</blockquote>
</blockquote></div><br><br clear="all"><div><br></div><div class="gmail_signature"><br><br></div>
</div></div></div>