Decentralizing MVCC by Leveraging Visibility
Xuan Zhou, Xin Zhou, Zhengtai Yu, Hua Guo, Kian-Lee Tan

TL;DR
This paper proposes ViCC, a decentralized MVCC mechanism that enables transactions to autonomously determine timestamps, improving scalability and performance in parallel database systems.
Contribution
It introduces a novel visibility-based concurrency control method that removes centralized timestamp allocation, enhancing scalability for multicore and MPP database platforms.
Findings
ViCC outperforms existing MVCC approaches in scalability.
Experimental results show improved transaction throughput.
ViCC maintains consistency without centralized coordination.
Abstract
Multiversion Concurrency Control (MVCC) is a widely adopted concurrency control mechanism in database systems, which usually utilizes timestamps to resolve conflicts between transactions. However, centralized allocation of timestamps is a potential bottleneck for parallel transaction management. This bottleneck is becoming increasingly visible with the rapidly growing degree of parallelism of today's computing platforms. This paper introduces Visibility based Concurrency Control (ViCC), a series of CC mechanisms that allow transactions to determine their timestamps autonomously, without relying on centralized coordination. As such, ViCC can scale well, rendering it suitable for various multicore and MPP platforms. Extensive experiments are conducted to demonstrate its advantage over existing approaches.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDistributed systems and fault tolerance · Advanced Database Systems and Queries · Advanced Data Storage Technologies
