System control structure of the IBM eServer z900

Abstract

System control structure of the IBM eServer z900 As computer systems become more complex, the use of embedded controllers for initializing and maintaining system operation is becoming increasingly prevalent. In the IBM eServer z900, a new control approach was introduced. This paper discusses why its introduction was necessary and outlines its associated, key technological and economic innovations. In particular, the following topics are addressed: service subsystem topology, hardware elements for performing system control, hardware abstraction, object-oriented framework for control, and inter-networking of system control microprocessors.

Innovations in infrastructure firmware for the IBM z13

“…For compatibility with older controller hardware Internet Protocol (IP) v4 addressing is used within the service network. In order to maintain communication capabilities even in case of a failure of one of the involved components, this network has been designed as a redundant network consisting of two subnets with separate Ethernet switches [4]. Communication between the otherwise separated subnets is established via trunk cables between the two switches.…”

“…It communicates with all FSPs via a service network. Both the SEs, the FSPs, and the service network are configured redundantly for RAS reasons [4]. We start our discussion by describing the virtual self-boot engine (vSBE) on the FSPs.…”

Redundant I/O interconnect

“…During the HOM self-configuration, i.e., during system power-on, these connections are sensed by the flexible support processor (FSP) [11]. All functional units in the I/O cages maintain an STI connection object.…”

Hyper-acceleration and HW/SW co-verification as an essential part of IBM eServer z900 verification

“…At the beginning of initial machine load (IML) for a z900 machine, all of the code resides on a laptop computer called the service element (SE), which is connected to the machine via a network and communicates finally with the clock-control chip that is part of the system model [7]. The goal of the simulation effort using the CoBALT system is to ensure that the microcode, which is one portion of the IML code, can be loaded into a simulated version of the machine.…”