RING: a strategy for minimizing the cost of online data placement reorganization for B-tree indexed database over shared-nothing parallel machines
Hisham Feelifl, Masaru Kitsuregawa · 2001
Proposes a new strategy called RING that utilizes a ring configuration of the range partition strategy to achieve efficient online data placement reorganization in shared-nothing environments. In the event of reorganization, it has been observed that the range partition strategy in its well-known linear configuration can lead to two main drawbacks: high reorganization costs and performance dependence on hotspot locations in a system. Thus, we modify the configuration into a ring, seeking to minimize the effect of these drawbacks. We also introduce a new standalone heat-balancing algorithm to support the ring configuration, where its migration decisions are deduced by taking into account reorganization costs while balancing a system. RING is based on simple but effective approaches that incur little overhead, so that performance is almost optimized for free. Our simulation results indicate that, under a wide range of requirements, performance can be considerably improved by modifying the underlying structure to support the ring configuration.