On 24/10/13 10:18, Vladimir Melnik wrote: > Dear colleagues, > > I'll be very grateful for any clue or advice. I have a cluster (GFS2/DLM on > iSCSI). Something happened today, so one node has stopped working in cluster > and all operations with the filesystem was giving "input/output errors". > Other nodes are working okay. > > I unmounted the filesystem and stopped all services (gfs2, clvmd, cman, > iscsi, iscsid), but I can't start cman again. That's what I have in > log-files: > fenced[2801]: found uncontrolled entry > /sys/fs/gfs2/ckvm1_pod1:vg_psv4 > gfs_controld[2878]: found uncontrolled gfs2 fs ckvm1_pod1:vg_psv4 > > Yes, I really have this "uncontrolled entry", how to get rid of it without > rebooting the node? > > Thank you very much for any ideas and hints. I've not seen that particular error before. Can you paste your cluster.conf and the log files from the effected node, starting just before the event occured? Please also look at the logs from other node(s) at the same time and paste how they responded to the node failure. -- Digimer Papers and Projects: https://alteeve.ca/w/ What if the cure for cancer is trapped in the mind of a person without access to education? -- Linux-cluster mailing list Linux-cluster@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/linux-cluster
