I agree with Ted and Allan, that you really need to look at other values as
well (throughput, queuing, parallel tape mounts, ..), And then you have the
VTS staging/destaging, potential thrashing, ..
What about future growth in your workload, the end of month runs. There are
very many issues to look at.
Bear in mind though, that RMF is showing you average values for an interval.
If you're seeing 90% average, then you've certainly had peaks reaching 100%
already.
John.
----- Original Message -----
From: "Ted MacNEIL" <[EMAIL PROTECTED]>
Newsgroups: bit.listserv.ibm-main
Sent: Monday, September 22, 2008 7:07 PM
Subject: Re: Maximum Channel Busy Recommendation for 3494 VTS ESCON Attached
>So, you think 100% is ok and we probably shouldn't worry about it?
I haven't done any empirical studies of Tape in years.
So, I cannot be 100% sure.
But, remember, there is cache on the supporting disk sub-system and it's
not truly random access like regular disk.
I would check out my tape throughput, and my batch service levels.
If they're good, then I wouldn't worry too much about it.
There haven't been many tape studies done, lately.
The only person I know who was even doing it was Bill Grey of STK (now
Sun), and I haven't seen much from him, lately.
Try the CMG proceedings; they might have something.
But, no I don't think it's a problem (if I'm wrong somebody will correct
me -- hopefully with data).
-
Too busy driving to stop for gas!
----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
