Serval: A Wait-free Multi-version Deterministic Concurrency Control Scheme

Caracal is a multi-version deterministic concurrency control protocol designed to handle contention efficiently. During its initialization phase, Caracal appends pending versions of the same data item from the same core simultaneously using dynamically allocated buffers when contention occurs. However, Caracal still requires latches when performing remote writes on the global version array. This paper introduces Serval, a novel method aimed at optimizing Caracal’s limitations. Serval incorporates two types of bitmaps to indicate the information of update operations and adopts dynamic local version arrays instead of global version arrays for contended data items. These enhancements enable Serval to ensure wait-free conditions during the initialization phase and provide more efficiency in the execution phase under contention.

Authors

Institutions

Publication Details

Published
2024-11-26
DOI
https://doi.org/10.1109/candar64496.2024.00028
Primary Topic
Distributed systems and fault tolerance
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Serval: A Wait-free Multi-version Deterministic Concurrency Control Scheme

Rina Onishi, Haowen Li, Hideyuki Kawashima
Distributed systems and fault tolerance
article

Serval: A Wait-free Multi-version Deterministic Concurrency Control Scheme

Rina Onishi, Haowen Li, Hideyuki Kawashima
article en

Abstract

Caracal is a multi-version deterministic concurrency control protocol designed to handle contention efficiently. During its initialization phase, Caracal appends pending versions of the same data item from the same core simultaneously using dynamically allocated buffers when contention occurs. However, Caracal still requires latches when performing remote writes on the global version array. This paper introduces Serval, a novel method aimed at optimizing Caracal’s limitations. Serval incorporates two types of bitmaps to indicate the information of update operations and adopts dynamic local version arrays instead of global version arrays for contended data items. These enhancements enable Serval to ensure wait-free conditions during the initialization phase and provide more efficiency in the execution phase under contention.

Keio University Shonan Fujisawa (JP)
Research and Development
Openalex Percentile: Top 72%
Distributed systems and fault tolerance
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.