STAR: Scaling Transactions through Asymmetrical Replication

11/05/2018
by   Yi Lu, et al.
0

In this paper, we present STAR, a new distributed and replicated in-memory database. By employing a single-node non-partitioned architecture for some replicas and a partitioned architecture for other replicas, STAR is able to efficiently run both highly partitionable workloads and workloads that involve cross-partition transactions. The key idea is a new phase-switching algorithm where the execution of single-partition and cross-partition transactions are separated. In the partitioned phase, single-partition transactions are run on multiple machines in parallel to exploit more concurrency. In the single-master phase, mastership for the entire database is switched to a designated coordinator node, which can execute these transactions without the use of expensive coordination protocols like two-phase commit. Because the coordinator node has a full copy of the database, this phase-switching can be done at negligible cost. Our experiments on two popular benchmarks (YCSB and TPC-C) show that high availability via replication can coexist with fast serializable transaction execution in distributed in-memory databases, with STAR outperforming systems that employ conventional concurrency control and replication algorithms by up to one order of magnitude.

READ FULL TEXT
research
11/05/2018

STAR: Scaling Transactions through Asymmetric Replication

In this paper, we present STAR, a new distributed in-memory database wit...
research
04/03/2021

Zeus: Locality-aware Distributed Transactions

State-of-the-art distributed in-memory datastores (FaRM, FaSST, DrTM) pr...
research
04/19/2023

GeoGauss: Strongly Consistent and Light-Coordinated OLTP for Geo-Replicated SQL Database

Multinational enterprises conduct global business that has a demand for ...
research
03/01/2019

SCAR: Strong Consistency using Asynchronous Replication with Minimal Coordination

Data replication is crucial in modern distributed systems as a means to ...
research
03/16/2020

Hihooi: A Database Replication Middleware for Scaling Transactional Databases Consistently

With the advent of the Internet and Internet-connected devices, modern b...
research
11/29/2018

Chiller: Contention-centric Transaction Execution and Data Partitioning for Fast Networks

Distributed transactions on high-overhead TCP/IP-based networks were con...
research
07/06/2022

C5: Cloned Concurrency Control that Always Keeps Up

Asynchronously replicated primary-backup databases are commonly deployed...

Please sign up or login with your details

Forgot password? Click here to reset