[Gluster-users] Question about file anomalies and copying to gluster failing

DUPRE, LANCE DUPREL at mailbox.sc.edu
Thu Jul 10 15:46:25 UTC 2014


I seem to be having trouble with our servers running the red hat gluster appliance v 3.2.5. We have 3 distributed bricks part of the cluster and it is shared out using glusters native NFS support to Mac OSX Clients. Currently I am unable to copy large (20GB) files to the cluster. Also, I was able to create an empty test folder through the NFS share but when I delete it, it will reappear after a few seconds. I have took a look at the gluster logs and see about 20 of these this in the nfs.log file:

[dht-layout.c:581:dht_layout_normalize] 0-archive-dht: found anomalies in /archival/MVTN_C6089_Pres1. holes=1 overlaps=0   

I assume there has been some file corruption. but shouldn’t gluster self heal? If not how do I trigger the self heal to start?

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20140710/3e364fdc/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 495 bytes
Desc: Message signed with OpenPGP using GPGMail
URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20140710/3e364fdc/attachment.sig>

More information about the Gluster-users mailing list