🤖 AI Summary
To address concurrency control challenges under mixed long/short transaction workloads in manufacturing systems, this paper proposes a decentralized graph-based protocol that guarantees zero aborts for long update transactions, improves short-transaction throughput, and fully exploits multicore parallelism. Our key contributions are: (1) the first decentralized scheduling mechanism based on a full-precision multiversion serialization graph (MVSG), enabling lock-free concurrency and distributed graph maintenance; and (2) BoMB—the first OLTP benchmark tailored to Bill-of-Materials (BOM) scenarios—accurately modeling heterogeneous transaction conflict patterns. Experimental evaluation on BoMB demonstrates 100% commit rate for long transactions, short-transaction throughput of 1.7 Mtpm, and near-linear scalability—substantially outperforming state-of-the-art approaches.
📝 Abstract
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.
