Description of problem: On a two node cluster, one of the nodes was removed from the cluster. When it attempted to rejoin the cluster, the kernel paniced due to an NMI watchdog lockup. Version-Release number of selected component (if applicable): How reproducible: First time this problem has been seen. Steps to Reproduce: 1. Remove one node from two node cluster 2. Rejoin node to cluster 3. Actual results: Kernel panic Expected results: Normal operation Additional info: This problem may be related to bug #166701 as it occurred in low memory and a spinlock was involved.
Created attachment 118323 [details] KDB info from failed node including dmesg, ps,sr t, etc.
Let me know if this issue shows up again, while running the U2 gfs code.
Doesn't actually block RHEL4NFSFailover