| | |
Summary: On the Performance of WideArea Synchronous Database Replication
Yair Amir # Claudiu Danilov # Michal MiskinAmir + Jonathan Stanton #
Ciprian Tutu #
Technical Report
CNDS20024
http://www.cnds.jhu.edu
November 18, 2002
Abstract
A fundamental challenge in database replication is to maintain a low cost of updates while as
suring global system consistency. The di#culty of the problem is magnified for widearea network
settings due to the high latency and the increased likelihood of network partitions. As a conse
quence, most of the research in the area has focused either on improving the performance of local
transaction execution or on replication models with weaker semantics, which rely on application
knowledge to resolve potential conflicts.
In this work we identify the performance bottleneck of the existing synchronous replication
schemes as residing in the update synchronization algorithm. We compare the performance of
several such synchronization algorithms and highlight the large performance gap between various
methods. We design a generic, synchronous replication scheme that uses an enhanced synchro
nization algorithm and demonstrate its practicality by building a prototype that replicates a
PostgreSQL database system. We claim that the use of an optimized synchronization engine is
|