Oze: Decentralized Graph-based Concurrency Control for Real-world Long Transactions on BoM Benchmark
share
In this paper, we propose Oze, a new concurrency control protocol that handles heterogeneous workloads which include long-running update transactions. Oze explores a large scheduling space using a fully precise multi-version serialization graph to reduce false positives. Oze manages the graph in a decentralized manner to exploit many cores in modern servers. We also propose a new OLTP benchmark, BoMB (Bill of Materials Benchmark), based on a use case in an actual manufacturing company. BoMB consists of one long-running update transaction and five short transactions that conflict with each other. Experiments using BoMB show that Oze keeps the abort rate of the long-running update transaction at zero while reaching up to 1.7 Mtpm for short transactions with near linear scalability, whereas state-of-the-art protocols cannot commit the long transaction or experience performance degradation in short transaction throughput.
READ FULL TEXT