Chapter 7. Sysplex functions 173
Draft Document for Review April 7, 2004 6:15 pm 6947ch07.fm
GDPS/PPRC Management for Open Systems LUNs
GDPS/PPRC technology has been extended to manage a heterogeneous environment of
z/OS and Open Systems data. If installations share their disk subsystems between the z/OS
and Open Systems platforms, GDPS/PPRC, running in a z/OS system, can manage the
PPRC status of devices that belong to the other platforms and are not even defined to the
z/OS platform. GDPS/PPRC will also provide data consistency across both z/OS and Open
Systems data.
GDPS/PPRC over Fiber Channel links
The IBM TotalStorage Enterprise Storage Server (ESS) supports PPRC over Fiber Channel
for ESS Model 800. It is designed to improve throughput as compared to PPRC over ESCON
links and reduces cross-site connectivity (two PPRC Fiber Channel links are considered
sufficient for most workloads). The benefit of this support is the opportunity to increase the
distance between sites without losing performance.
GDPS FlashCopy V2 support
Previously source and target volumes needed to reside on the same Logical Subsystem
(LSS) within the disk subsystem. With FlashCopy V2 a flash copy can be created from a
source in one LSS to a target in a different LSS in the same disk subsystem.
Business Continuity for Linux guests
GDPS plans to exploit the HyperSwap function in z/VM V5.1 to provide business continuity for
z/OS and Linux guests. z/VM HyperSwap swaps the virtual device associated with one real
disk to another and can be used to switch to a secondary disk storage subsystem mirrored by
PPRC. This is a useful function for those users that share data and storage subsystems
between z/OS and Linux. A SAP application server running on Linux and a SAP data base
server running on a z/OS is an example of an environment that will benefit from the z/VM
V5.1 HyperSwap functionality.
Much of the functionality is similar to that for z/OS systems and data. The following recovery
actions are designed to support planned and unplanned outages.
򐂰In place re-IPL of failing operating system images.
򐂰Site takeover of a production site.
򐂰Transparent planned and unplanned HyperSwap of disk subsystem.
Near continuous availability and disaster recovery solutions require IBM Tivoli System
Automation for Linux, and z/VM V5.1 in addition to other GDPS/PPRC prerequisites.
GDPS/PPRC Cross-site extended distance for Parallel Sysplex
Via a RPQ the capability to configure GDPS/PPRC or a multi-site Parallel Sysplex up to a
distance of 100 kilometers (62 miles) is made possible. Support for the following has been
extended for up to 100 kilometers from the previous limitation of 50 kilometers (31 miles),
through use of Dense Wavelength Division Multiplexer (DWDM) equipment for:
򐂰External Timer Reference (ETR) links to a Sysplex Timer
򐂰ISC-3 links in peer mode
This support is consistent with other technologies that support the same distance, such as
FICON, Peer-to-Peer Remote Copy (PPRC), and Peer-to-Peer Virtual Tape Server (PtP
VTS).