Hiperdispatch - IBM z13s Technical Manual

Operating system
Linux on z Systems
The new resources are immediately made available to the operating system and, in the case
of z/VM, to its guests. The dynamic PU add function is not supported for zAware-mode
LPARs.

7.3.16 HiperDispatch

The HIPERDISPATCH=YES/NO parameter in the IEAOPTxx member of SYS1.PARMLIB and on
the SET OPT=xx command controls whether HiperDispatch is enabled or disabled for a z/OS
image. It can be changed dynamically, without an IPL or any outage.
The default is that HiperDispatch is disabled on all releases, from z/OS V1R10 (requires PTFs
for zIIP support) through z/OS V1R12.
Beginning with z/OS V1R13, when running on a z13, z13s, zEC12, zBC12, z196, or z114
server, the IEAOPTxx keyword HIPERDISPATCH defaults to YES. If HIPERDISPATCH=NO is
specified, the specification is accepted as it was on previous z/OS releases.
The use of SMT in the z13s requires that HiperDispatch is enabled on the operating system
(z/OS V2R1/z/OS V2R2 or z/VM V6R3).
Additionally, with z/OS V1R12 or later, any LPAR running with more than 64 logical
processors is required to operate in HiperDispatch Management Mode.
The following rules control this environment:
If an LPAR is defined at IPL with more than 64 logical processors, the LPAR automatically
operates in HiperDispatch Management Mode, regardless of the HIPERDISPATCH=
specification.
If more logical processors are added to an LPAR that has 64 or fewer logical processors
and the additional logical processors raise the number of logical processors to more than
64, the LPAR automatically operates in HiperDispatch Management Mode regardless of
the HIPERDISPATCH=YES/NO specification. That is, even if the LPAR has the
HIPERDISPATCH=NO specification, that LPAR is converted to operate in HiperDispatch
Management Mode.
An LPAR with more than 64 logical processors running in HiperDispatch Management
Mode cannot be reverted to run in non-HiperDispatch Management Mode.
HiperDispatch in the z13s uses a new chip and CPC drawer configuration to improve the
access cache performance. Beginning with z/OS V1R13, HiperDispatch changed to use the
new node cache structure of z13s. The base support is provided by PTFs identified by
IBM.device.server.z13s-2965.requiredservice.
The PR/SM in the System z9 EC to zEC12 servers stripes the memory across all books in the
system to take advantage of the fast book interconnection and spread memory controller
work. The PR/SM in the z13s seeks to assign all memory in one drawer striped across the
two nodes to take advantage of the lower latency memory access in a drawer and smooth
performance variability across nodes in the drawer.
254
IBM z13s Technical Guide
Support requirements
SUSE Linux Enterprise Server 12
SUSE Linux Enterprise Server 11
Red Hat RHEL 7
Red Hat RHEL 6