SIGMOD '88 Proceedings of the 1988 ACM SIGMOD international conference on Management of data
Principles of distributed database systems
Principles of distributed database systems
SIGMOD '91 Proceedings of the 1991 ACM SIGMOD international conference on Management of data
Parallel database systems: the future of high performance database systems
Communications of the ACM
Parallel database systems: open problems and new issues
Distributed and Parallel Databases - Special issue: Research topics in distributed and parallel databases
Two techniques for on-line index modification in shared nothing parallel databases
SIGMOD '96 Proceedings of the 1996 ACM SIGMOD international conference on Management of data
Towards self-tuning data placement in parallel database systems
SIGMOD '00 Proceedings of the 2000 ACM SIGMOD international conference on Management of data
SC '97 Proceedings of the 1997 ACM/IEEE conference on Supercomputing
Prototyping Bubba, A Highly Parallel Database System
IEEE Transactions on Knowledge and Data Engineering
Adaptive Load Balancing in Disk Arrays
FODO '93 Proceedings of the 4th International Conference on Foundations of Data Organization and Algorithms
Principles of Transaction-Based On-Line Reorganization
VLDB '92 Proceedings of the 18th International Conference on Very Large Data Bases
Fat-Btree: An Update-Conscious Parallel Directory Structure
ICDE '99 Proceedings of the 15th International Conference on Data Engineering
ICDE '05 Proceedings of the 21st International Conference on Data Engineering
Dynamic Data Migration Policies for Query-Intensive Distributed Data Environments
APWeb/WAIM '09 Proceedings of the Joint International Conferences on Advances in Data and Web Management
DEXA'10 Proceedings of the 21st international conference on Database and expert systems applications: Part II
Hi-index | 0.00 |
In shared-nothing environments, data is typically declustered and indexed across the system processing elements (PEs) to achieve efficient processing. However access patterns are inherently dynamic and skewed, thus, data reorganization based on the data access history (heat) is essential and should be done online. While the data is being reorganized, indexes need to be modified too, therefore, reorganization should additionally deal with the index modification. Based on minimization of index modification, we propose a data reorganization technique over a shared-nothing parallel system. By finding the exact work that should be done, the technique can smoothly balance a given heat across the PEs as fast as possible, if it is required. By tuning its parameters, it can cover a wide range of balancing requirements. We evaluate its performance through simulation studies. Its effectiveness is clarified quantitatively.