IBM to improve RS/6000 clustering software
Users will be able to cluster up to 32 RS/6000s
Boston, MA -- While Sun Microsystems is expected to announce a new server cluster in late October, IBM also plans to upgrade clustering software for its RS/6000s. The software will enable users to cluster more machines, as well as spread out machine availability over long distances, according to a company official.
One initiative, code-named Phoenix, will expand the number of RS/6000s that can be clustered from eight to 32 and, next year, to 128, according to David Turek, director of Scalable Powerparallel (SP) Systems in IBM's RS/6000 division.
Phoenix, to be announced in October, will first ship as a feature on the SP later this year, Turek said. Early next year, IBM's High Availability Clustering Multiprocessing (HACMP) software for SP systems and general purpose RS/6000s will be upgraded to include the Phoenix capabilities, Turek said. HACMP will still have the same interface as it does now, he said.
Phoenix will be able to handle operating system, middleware, and application failures, not just hardware failures, Turek said. IBM is also working with OS, middleware, and application software vendors to develop standardized APIs for Phoenix, Turek said.
"Everybody thinks of [availability] in terms of hardware," Turek said. "We've built an infrastructure capable of handling arbitrarily defined software and hardware events."
Also in October, IBM plans to introduce a new HACMP-derived product that will allow geographic availability clustering, Turek said. For example, if a machine fails in Manhattan a recovery script could transfer work to a machine in Boston. IBM is already testing systems over a 1,500 mile range, Turek said.
Geographic availability will be limited to eight-machine clusters
initially, Turek said.
--Sari Kalin, IDG News Service, Boston Bureau
If you have technical problems with this magazine, contact email@example.com