On 01/15/2013 05:56 PM, Alex Paschal wrote: > Are those 40mil spread across several filespaces? I've seen situations > on TSM-classic (i.e. pre-6) where doing smaller workloads, like deleting > one filespace at a time, worked better than deleting the whole node. > Would that be practical in this case?
Thanks, I experimented after your suggestion: objects deleted wasn't particularly different doing the whole node vs. one FS at a time. I've addressed the prompt issue; no more thrashing on a "quiesced" instance. It'll be interesting to see if it happens again. At least I'll be sensitized; I don't really have a clear idea how long that has been getting in the way of normal operations. - Allen S. Rout
