Project Description
OpenSwap combines disaster recovery and continuous availability for IBM AIX servers by integrating storage subsystem synchronous mirroring, multi-path disk I/O driver, and Tivoli replication management. These products were combined to provide seamless failover to remote replica volumes when a storage subsystem failure was detected or planned maintenance was required at the primary site. It also does not impact the traditional use of synchronous replication as a Disaster Recovery solution. This project was an IBM CEO Milestone in 2007 and increased reliability and scalability were added to the prototype in 2008. Working with technical leaders in software, storage, and server hardware, we were able to provide a solution that met the needs of all concerned. This project combined system software development, predictive failure analysis, and replication management for varied and interesting set of problems to solve.
Selected Publications
- Lanyue Lu, Prasenjit Sarkar, Dinesh Subhraveti, Soumitra Sarkar, Mark Seaman, Reshu Jain, Ahmed Bashir, " CARP: Handling silent data errors and site failures in an integrated program and storage replication mechanism", in Proceedings of the 29th International Conference on Distributed Computing Systems (ICDCS), June 2009.
People
- Prasenjit Sarkar
- Reshu Jain
- Mark Seaman
