> Bill - if we're running in Basic mode at the DR site (and this appears to > be the case based on what the First level VM perfkit told us) then the SIE > penalty shouldn't be affecting us, correct? I had conversation offlist > with David Boyse at sine-nominee off list and it was very enlightening.
No, Bill is correct (as usual). The machine may be in basic mode, but you have two layers of CP involved, and your Linux guests buried deep at 3rd level, so they're easily in the "hurting" category no matter what the basic machine is doing. The LPAR layer just makes it one step worse. > Would you consider WebSphere in particular and Java in general CPU bound > work and/or traditionally a low interrupt workload? Don't know about Bill, but I do. There's a lot of real CPU cycles that go into implementing a single Java instruction, and there are a LOT of Java instructions in a package as general as Websphere. -- db ---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
