Updating starcluster when spot instances go down
This archive was generated by
Hi all - So I've had on a few occasions nodes on my cluster get terminated
due to spikes in spot prices. When this happens, if I try to readd nodes
to my cluster, SGE (and StarCluster) and confused....ie jobs are left in
the queue, nodes can't be added or perform nfs mounts, etc, etc.
Right now, the only option I have is to re-create the cluster. I think
this is overkill. Is there a way, or would people find it beneficial, if
there was a command to sync starcluster with what nodes are actually
running and update config files on the master node?
Received on Mon Jul 29 2013 - 11:35:51 EDT