×
The internal search function is temporarily non-functional. The current search engine is no longer viable and we are researching alternatives.
As a stop gap measure, we are using Google's custom search engine service.
If you know of an easy to use, open source, search engine ... please contact support@midrange.com.
Ok, for the sake of argument let's say that we've poured over the queries
in question that were running on the guest lpar at this time. We've built
the appropriate indexes, structured the syntax as best we could for
performance and still get the results required and so on and so forth.
All disk for this guest is provided by the host. The host is running all
SSD's
From the host we have two NWSD's defined for this guest. One NWSD serves
up ten 140GB storage spaces, the other NWSD serves up seven 140GB storage
spaces.
Put a recent service pack on iNav and finally got it working for
Management Central again.
There are times with the "Disk Arm Utilization" chart shows 100%
utilization of many of the "arms" on this guest.
At that same time the Host shows CPU utilization of 120-160%.
This host serves up disk for 5 lpars. Four of them are IBM i and one is
AIX.
Disk arm utilization only gets high for this one guest.
We have 0.5CPU allocated to this host. Host is running IBM i 7.2
Power 8.
Does this point to anything in particular? Like:
- Does the host need more CPU?
- Do we need to unload/reload the guest and have more NWSD's, each with
less storage spaces? Like shoot for six NWSD's with six storage spaces
apiece, (just for example)?
Rob Berendt
midrange.com
