Chip ponders:
> Thursday afternoon, we peaked at 902 sessions-jobs-etc and suddenly
> we began to get all sorts of strange error messages.  The message
> we locked onto was the ol' out-of-DST-space message. (Shades of MPE-V)
> The fine folks at HP, upon dialin' in, pronounced that the machine was
> registering "extreme" amounts of CM-switching.  ?que?!

First make *sure* that they are talking about switches *to* CM (which are
"bad") as opposed to switches *from* CM (to NM) which are not bad.  Sort of
like bad cholesterol versus good cholesterol.  You want he total number to
be as low as possible, but one kind will kill you whereas the other kind
isn't really bad and may actually be good for you (switching to NM means
that once there things will run faster than in CM, so switching might be
better than not switching).

Switch rates should scale linearly with system activity, and should be
completely unrelated to any non-linear performance degredation, or any
limits you might be hitting.

> Well, all of our business applications are compiled into NMPRGs so I went
> looking elsewhere.

Well, a switch *to* CM has to come from something that has been "compiled
into NMPRGs", with a common cause being a switch stub written to allow all
the new "NM" applications to get back to some routine in an SL that you use
that you don't have the source code or an NM compiler for.

> Besides, the thought of having to fundamentally alter
> thousands of applications makes my toes curl...

Simplest advice is to take several deep breaths and ignore the switching
numbers.

> ...but I did find this.

[:LISTF of NETBASE account CM programs snipped]

First of all, a CM program cannot be the source of a "bad" switch *to* CM
(one way to avoid "bad" switches is to leave all your code in CM!)

> Wha' th' hecks th' deal with NBSPOOL ?!?!?

The NBSPOOL.PUB.NETBASE (and other NB spooling programs) are primarily just
user interface driver programs when run on an MPE/iX system.  All of the
code that does the real work is Native Mode, and stored in an XL (SPOOLXL?)
in PUB.NETBASE.  This will result in seeing some number of "not bad"
switches *from* CM to NM when NBSPOOL is active.

> My bet is that once the analysis comes back, it is likely that our beloved
> Netbase stuff will be the culprit.

Sorry, but I doubt it.

G.