Mainframe Propeller Head

Jun 30 2009   4:56PM GMT

Hybrid mainframe computing

Mark Fontecchio Mark Fontecchio Profile: Mark Fontecchio

Expect IBM to talk up the concept of “hybrid mainframe computing” over the next year.

The idea is allowing easier, more fluid connections between mainframe hardware and other platforms. First on the list: blade servers.

Earlier this year, you may remember Karl Freund, IBM System z VP of strategy, talking about being able to run your blade servers like they’re a mainframe LPAR.

Though there is little comparison between the hardware of a mainframe and an Intel blade, Freund said management will be easier, being able to handle one systems management console, and having failover going to the same sysplex, rather than using different backup platforms.

Presumably this would make it easier for your front-end apps on your blade servers to communicate and get along with back-end database and ERP applications on the mainframe.

At the time, Freund wouldn’t divulge when this kind of technology would come out, but the details are starting to trickle out now. I just spoke with Jim Porell, the chief architect of System z software, and he said the company expected to be beta testing the technology by the end of this year, with it coming out in general availability sometime next year.

Porell also described in some detail how the connection would work. He said one feature engineers are working on is a data warehouse capability. Let’s say a user does transaction processing on the mainframe and writes to a DB2 database, also on the mainframe. Well, if you add query processing on top of that, “everything gets expensive.”

So let’s say the user wants to extract that query processing capability to a distributed platform. Currently what they’ll probably do is burn mainframe MIPS by building a copy of the DB2 database, burn MIPS by transferring, and even then, the database is “never completely up to date,” Porell said.

With the new capability, the BladeCenter would be connected to the mainframe in such a way that the query processing could happen on the blade servers, which could tap directly into the DB2 database on the mainframe.

“We want to change it so the customer is getting the benefit right out of the box,” Porell said. “Right now the customers would have to do it themselves, and I’m not sure they would have the capability to do it.”

 Comment on this Post

There was an error processing your information. Please try again later.
Thanks. We'll let you know when a new response is added.
Send me notifications when other members comment.

Forgot Password

No problem! Submit your e-mail address below. We'll send you an e-mail containing your password.

Your password has been sent to:

Share this item with your network: