Description of problem: In the scenario when one of the nodes goes down when the load on client is high any of the below issues are noticed: 1) symlinks get zeroed out and become regular files 2) some of the files become zero byte 3) spurious split-brains are observed But the files related to case 1 and case 2 are not reported in any of the logs. It is absolutely clueless what happened on the files or what was happening. Logs need enhancements to verify things.
Verified on glusterfs 3.4.0.18rhs built on Aug 7 2013 08:02:45 Now the logs look better and I see the logs with information printed on Comment 2
Verified on glusterfs 3.4.0.18rhs built on Aug 7 2013 08:02:45 Now the logs look better and I see the logs with information printed on Comment
Since the problem described in this bug report should be resolved in a recent advisory, it has been closed with a resolution of ERRATA. For information on the advisory, and where to find the updated files, follow the link below. If the solution does not work for you, open a new bug report. http://rhn.redhat.com/errata/RHBA-2013-1262.html