GPDS/PPRC HyperSwap™
The GDPS/PPRC HyperSwap function is designed to broaden the continuous availability attributes of GDPS/ PPRC by extending the Parallel Sysplex redundancy to disk subsystems. The HyperSwap function is enabled to mask planned and unplanned disk and site reconfi gura- tions by transparently switching to use the secondary PPRC volumes. The HyperSwap function is designed to be controlled by complete automation, allowing all aspects of the site switch to be controlled via GDPS. Large con-
figurations can be supported, as HyperSwap has been designed to provide capacity and capability to swap large numbers of disk devices very quickly. The important ability to
The planned HyperSwap function provides the ability to transparently switch all primary PPRC disk subsystems with the secondary PPRC disk subsystems for a planned switch confi guration. It enables disk confi guration mainte- nance and planned site maintenance without requiring any applications to be quiesced. The unplanned HyperSwap function contains additional function designed to transpar- ently switch to use secondary PPRC disk subsystems, in the event of unplanned outages of the primary PPRC disk subsystems or a failure of the site containing the primary PPRC disk subsystems. With unplanned HyperSwap func- tion, disk subsystem failures no longer constitute a single point of failure for an entire sysplex. If applications are cloned and exploiting data sharing across the two sites, the GDPS/PPRC unplanned HyperSwap capability, lays the foundation for continuous availability, even in the event of a complete site failure. In the event of a complete failure of the site where the primary disk resides, the systems in the site with the secondary disks can continue to remain active even though workload running on these systems
needs to be restarted. An improvement in the Recovery Time Objective (RTO) can be accomplished.
With the release of GDPS/PPRC V3.2, the HyperSwap function was enhanced to exploit the PPRC Failover/ Failback function. For planned reconfi gurations, PPRC Failover/Failback can help reduce the overall elapsed time to switch the disk subsystems, which can then reduce the time that applications may not be available to users. For unplanned reconfi gurations, PPRC Failover/Failback allows the secondary disks to be confi gured in the suspended state after the switch, thus eliminating the need to per- form a full copy of the data when reestablishing the PPRC mirror in the reverse direction. The window during which critical data is left without PPRC protection following an unplanned reconfi guration is thereby minimized.
GDPS/PPRC management for open systems LUNs (Logi- cal Unit Numbers): 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 defi ned to the z/OS platform. GDPS/PPRC can also provide data consistency across both z/OS and open systems data.
GDPS supports PPRC over Fiber Channel links: GDPS/ PPRC supports Enterprise Storage Server (ESS) PPRC over Fiber Channel Protocol (FCP). It is expected that the distance between sites can be increased while maintain- ing acceptable application performance, since PPRC over FCP requires only one protocol exchange compared to two or three exchanges when using PPRC over ESCON. The effi ciency of the FCP protocol is also expected to help lower the total cost of ownership, since two PPRC FCP links are considered suffi cient for most workloads, which can allow a reduction in
49
