I also tend to leave my thresholds at a low value such as 90% or lower to
then allow me to order more disk and get that in and installed. Not at
98% to then say "oh crud! What stuff can I remove from this system in
this emergency situation? Do they really need payroll history from last
With guesting and a lot of space still available on my hosting partitions
I may rethink this. Still having time to think avoids the knee jerk
reaction of just assigning another storage space.
IBM is still trying to determine the effect of so many storage spaces.
Good? Bad? Indifferent? SSD vs spinny? More data required? From a
currently open pmr:
With regards to the NWSDs - there are in essence 68 Network Storage
Spaces (virtual drives) and there are 32 actual physical drives. In
that environment it is very possible to drive the workload so that it
can overwhelm the physical drives, however - due to the other
bottlenecks we're seeing here (CPU/memory on the host) this isn't the
problem at this time. It is possible that it could be a problem once
the CPU/Memory issues are resolved. We have asked some additional
developers to review this portion and update with their response. I'll
update you when I have some info from them.
This mailing list archive is Copyright 1997-2019 by midrange.com and David Gibbs as a compilation work. Use of the archive is restricted to research of a business or technical nature. Any other uses are prohibited. Full details are available on our policy page. If you have questions about this, please contact