Rethinking Eventual Consistency

• consistency 1
• concurrency 5

http://research.microsoft.com/pubs/192621/sigtt611-bernstein.pdf sigmod'13, 2015/12/12 02:33:36, cited 16

• 1. INTRODUCTION
• 2. RETHINKING CONSISTENCY
• 4. CONCLUDING REMARKS

Keywords

Eventual consistency, replication.

Categories and Subject Descriptors

H.3.4 [Information Storage and Retrieval]

Systems and Software — Distributed systems.

ABSTRACT There has been a resurgence of work on replicated, distributed database systems to meet the demands of intermittently-connected clients and of disaster-tolerant databases that span data centers. Many systems weaken the criteria for replica-consistency or isolation, and in some cases add new mechanisms, to improve partition-tolerance, availability, and performance. We present a framework for comparing these criteria and mechanisms, to help architects navigate through this complex design space.

1. INTRODUCTION

Data replication

spreading read and write load across servers and improving availability.

Ideally, replication is transparent to the clients. This is captured in two well-known correctness criteria: one-copy serializability (1SR) [1] and linearizability [13].

The three basic techniques for synchronizing replicated data are primary copy [1,25], multi-master, and quorum consensus.

2. RETHINKING CONSISTENCY

three classic approaches to replicated data

primary copy, multi-master, and quorum consensus.

In all approaches, a client update arrives at one copy, is processed there, and is forwarded as downstream updates to the other copies.

4. CONCLUDING REMARKS