Hard cap the test system, soft cap the production system?  Then the
test system can't exceed its percent, even if the CPU is not 100%.
The soft cap would allow the production system to get extra cycles if
the test system isn't using its full share.
On Tue, Aug 28, 2018 at 4:13 PM Martin Packer <[email protected]> wrote:
>
>
> Then the two WLMs can’t cooperate - and aren’t even aware of each other’s
> state. :-(
>
> Manual shifting the weights - via BCPii - might be doable.
>
> Cheers, Martin
>
> Sent from my iPad
>
> > On 28 Aug 2018, at 22:11, Pommier, Rex <[email protected]> wrote:
> >
> > Hi Martin,
> >
> > Sorry, no sysplex.
> >
> > Rex
> >
> > -----Original Message-----
> > From: IBM Mainframe Discussion List [mailto:[email protected]] On
> Behalf Of Martin Packer
> > Sent: Tuesday, August 28, 2018 3:59 PM
> > To: [email protected]
> > Subject: [External] Re: cross LPAR priority and cycle stealing
> >
> >
> >
> > Are these LPARs in the same Sysplex? Two beneficial effects if they are:
> >
> > 1) You could - with IRD Weight Management - have weights shifted between
> > the LPARs.
> >
> > 2) Sysplex PI for important works comes into play.
> >
> > Cheers, Martin
> >
> > Sent from my iPad
> >
> >> On 28 Aug 2018, at 21:52, Pommier, Rex <[email protected]> wrote:
> >>
> >> Hello list,
> >>
> >> Hypothetical scenario is a single machine with 2 LPARs on it, each LPAR
> > is defined as having 50% of the capacity of the entire machine, uncapped
> > across the board.  In this scenario, if both LPAR1 and LPAR2 are running
> > flat out, each LPAR will take 50% of the machine.  If one of the LPARs is
> > busy and the other isn't doing anything, the busy LPAR will "steal"
> cycles
> > from the not busy one.  That's the easy part.  Here's where my thoughts
> get
> > fuzzy.  Is there a way to differentiate between high priority work on one
> > LPAR and low priority work on the other LPAR.  Here's what I'd like to
> do:
> > Say I'm running a bunch of production on one LPAR and a bunch of test
> work
> > on the other one.  I'd like to be able to steal cycles from the test LPAR
> > and give them to the production one.  I know WLM handles this within an
> > LPAR, making sure the high priority work gets the cycles it needs, but is
> > there a mechanism where I can do this across multiple LPARs?  If there
> is,
> > can somebody point me to the right place for learning how to configure
> this
> > to happen automatically?
> >>
> >> I have higher and lower priority work alternating between multiple LPARs
> > and would like the machine to be able to better balance the workloads so
> > that regardless of which LPAR the high priority work is on, it gets the
> CPU
> > necessary.
> >>
> >> TIA,
> >>
> >> Rex
> >>
> >>
> >> The information contained in this message is confidential, protected
> from
> > disclosure and may be legally privileged.  If the reader of this message
> is
> > not the intended recipient or an employee or agent responsible for
> > delivering this message to the intended recipient, you are hereby
> notified
> > that any disclosure, distribution, copying, or any action taken or action
> > omitted in reliance on it, is strictly prohibited and may be unlawful.
> If
> > you have received this communication in error, please notify us
> immediately
> > by replying to this message and destroy the material in its entirety,
> > whether in electronic or hard copy format.  Thank you.
> >>
> >> ----------------------------------------------------------------------
> >> For IBM-MAIN subscribe / signoff / archive access instructions,
> >> send email to [email protected] with the message: INFO IBM-MAIN
> >> Unless stated otherwise above:
> > IBM United Kingdom Limited - Registered in England and Wales with number
> 741598.
> > Registered office: PO Box 41, North Harbour, Portsmouth, Hampshire PO6
> 3AU
> >
> >
> > ----------------------------------------------------------------------
> > For IBM-MAIN subscribe / signoff / archive access instructions,
> > send email to [email protected] with the message: INFO IBM-MAIN
> >
> > The information contained in this message is confidential, protected from
> disclosure and may be legally privileged.  If the reader of this message is
> not the intended recipient or an employee or agent responsible for
> delivering this message to the intended recipient, you are hereby notified
> that any disclosure, distribution, copying, or any action taken or action
> omitted in reliance on it, is strictly prohibited and may be unlawful.  If
> you have received this communication in error, please notify us immediately
> by replying to this message and destroy the material in its entirety,
> whether in electronic or hard copy format.  Thank you.
> >
> >
> > ----------------------------------------------------------------------
> > For IBM-MAIN subscribe / signoff / archive access instructions,
> > send email to [email protected] with the message: INFO 
> > IBM-MAINUnless stated otherwise above:
> IBM United Kingdom Limited - Registered in England and Wales with number 
> 741598.
> Registered office: PO Box 41, North Harbour, Portsmouth, Hampshire PO6 3AU
>
>
> ----------------------------------------------------------------------
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to [email protected] with the message: INFO IBM-MAIN



-- 
Mike A Schwab, Springfield IL USA
Where do Forest Rangers go to get away from it all?

----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [email protected] with the message: INFO IBM-MAIN

Reply via email to