Lune

ICDE2024Top-tier venue

Lion: Minimizing Distributed Transactions Through Adaptive Replica Provision

Qiushi Zheng, Zhanhao Zhao, Wei Lu, Chang Yao, Yuxing Chen, Anqun Pan, Xiaoyong Du

Abstract

Distributed transaction processing often involves multiple rounds of cross-node communications, and therefore, tends to be slow. To improve performance, existing approaches convert distributed transactions into single-node transactions by either migrating co-accessed partitions onto the same nodes or establishing a super node housing replicas of the entire database. However, migration-based methods might cause transactions to be blocked due to waiting for data migration, while the super node can become a bottleneck.

In this paper, we present Lion, a novel transaction processing protocol that utilizes partition-based replication to reduce the occurrence of distributed transactions. Inspired by the fact that modern distributed databases horizontally partition data, with each partition having multiple replicas, Lion aims to assign a node with one replica from each partition involved in a given transaction's read or write operations. To ensure such a node is available, we propose an adaptive replica provision mechanism, enhanced with an LSTM-based workload prediction algorithm, to determine the appropriate node for locating replicas of co-accessed partitions. The adaptation of replica placement is conducted preemptively and asynchronously, thereby minimizing its impact on performance. By employing this adaptive replica placement strategy, we ensure that the majority of transactions can be efficiently processed on a single node without additional overhead. Only a small fraction of transactions will need to be treated as regular distributed transactions when such a node is unavailable. Consequently, Lion effectively minimizes distributed transactions, while avoiding any disruption caused by data migration or the creation of a super node. We conduct extensive experiments to compare Lion against various transaction processing protocols. The results show that Lion achieves up to 2.7x higher throughput and 76.4% better scalability against these state-of-the-art approaches.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Efficient Distributed Transaction Processing in Heterogeneous Networks cites Don't Look Back, Look into the Future: Prescient Data Partitioning and Migration for Deterministic Database Systems
  • Efficient Distributed Transaction Processing in Heterogeneous Networks cites MorphoSys: Automatic Physical Design Metamorphosis for Distributed Database Systems
  • Efficient Distributed Transaction Processing in Heterogeneous Networks cites Caracal: Contention Management with Deterministic Concurrency Control
  • Chimera: Mitigating Ownership Transfers in Multi-Primary Shared-Storage Cloud-Native Databases cites Efficient Distributed Transaction Processing in Heterogeneous Networks
  • Chimera: Mitigating Ownership Transfers in Multi-Primary Shared-Storage Cloud-Native Databases cites Don't Look Back, Look into the Future: Prescient Data Partitioning and Migration for Deterministic Database Systems
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. TxnSails: Achieving Serializable Transaction Scheduling with Self-Adaptive Isolation Level SelectionQiyu Zhuang, Wei Lu, Shuang Liu, Yuxing Chen et al.VLDB 2025 · 1 citation
  2. Chimera: Mitigating Ownership Transfers in Multi-Primary Shared-Storage Cloud-Native DatabasesHuang Chunyue, Shuang Liu, Xinyi Zhang, Wenhao Li et al.VLDB 2025 · 1 citation

Builds on10

  1. Epoch-based Commit and Replication in Distributed OLTP DatabasesYi Lu, Xiangyao Yu, Lei Cao, Samuel MaddenVLDB 2021 · 52 citations
  2. Caracal: Contention Management with Deterministic Concurrency ControlDai Qin, Angela Demke Brown, Ashvin GoelSOSP 2021 · 37 citations
  3. Efficient Distributed Transaction Processing in Heterogeneous NetworksQian Zhang, Jingyao Li, Hongyao Zhao, Quanqing Xu et al.VLDB 2023 · 25 citations
  4. MorphoSys: Automatic Physical Design Metamorphosis for Distributed Database SystemsMichael Abebe, Brad Glasbergen, Khuzaima DaudjeeVLDB 2020 · 18 citations
  5. Don't Look Back, Look into the Future: Prescient Data Partitioning and Migration for Deterministic Database SystemsYu-Shan Lin, Ching Tsai, Tz-Yu Lin, Yun-Sheng Chang et al.SIGMOD 2021 · 17 citations

Related papers

  1. Zeus: locality-aware distributed transactionsAntonios Katsarakis, Yijun Ma, Zhaowei Tan, Andrew Bainbridge et al.EuroSys 2021 · 20 citations
  2. Epoch-based Optimistic Concurrency Control in Geo-replicated DatabasesYunhao Mao, Harunari Takata, Michail Bachras, Yuqiu Zhang et al.SIGMOD 2026
  3. Logos: Robust Sharding Blockchain With Fast Processing and Optimal Cross-Shard OverheadYizhong Liu, Boyu Zhao, Yuxuan Hu, Haojun Tan et al.USENIX Security 2026
  4. DynaMast: Adaptive Dynamic Mastering for Replicated SystemsMichael Abebe, Brad Glasbergen, Khuzaima DaudjeeICDE 2020 · 14 citations
  5. Handling Highly Contended OLTP Workloads Using Fast Dynamic PartitioningGuna Prasaad, Alvin Cheung, Dan SuciuSIGMOD 2020 · 34 citations
Dusk over the sea between two cliffs drawn in fine vertical lines