MIPS
Millions of instructions per second: the common, rough way of describing how much processing capacity a mainframe has.
Also written millions of instructions per second, MSU, million service units, mainframe capacity
MIPS stands for millions of instructions per second. On the mainframe it is used loosely as a size: a site might say it has "a 20,000 MIPS shop" or that a new application "needs 500 MIPS". It describes processing capacity.
It is a rough measure. A real instruction count depends on the type of work, so IBM publishes relative capacity ratings for each machine model, and the industry converts those into MIPS figures. Two sites with the same MIPS number can see different results with different workloads.
A related unit is the MSU, million service units per hour. Much mainframe software is priced on how many MSUs the system uses, often measured as an average over four hours. That is why saving processor time matters on a mainframe: using less can lower the software bill as well as delay a hardware upgrade.
You will hear MIPS in conversations about cost, capacity planning and moving work off or onto the mainframe. Treat it as a size estimate, not an exact number.
Where can I learn this hands-on?
Right here, at ZedBank. You take a junior job at a simulated bank and learn each part of the work by doing it, with Zed beside you. There's nothing to install.
Start at ZedBankRelated
- IBM ZIBM's current family of mainframe hardware, and the brand name you will see on most modern mainframe job adverts.
- MainframeA large, highly reliable computer built to run enormous volumes of transactions and batch work for an entire organisation at once.
- WLMWorkload Manager: the part of z/OS that decides which work gets the processor, memory and disk access first, based on goals the site sets.
- SMFSystem Management Facilities: the z/OS feature that writes a detailed record of what happened on the system, used for billing, performance and security.
- LPARA logical partition: one physical mainframe carved into several independent virtual machines, each running its own operating system.