Paper Info
Title
A comparison of approaches to large-scale data analysis
Abstract
There is currently considerable enthusiasm around the MapReduce (MR) paradigm for large-scale data analysis [17]. Although the basic control flow of this framework has existed in parallel SQL database management systems (DBMS) for over 20 years, some have called MR a dramatically new computing model [8, 17]. In this paper, we describe and compare both paradigms. Furthermore, we evaluate both kinds of systems in terms of performance and development complexity. To this end, we define a benchmark consisting of a collection of tasks that we have run on an open source version of MR as well as on two parallel DBMSs. For each task, we measure each system's performance for various degrees of parallelism on a cluster of 100 nodes. Our results reveal some interesting trade-offs. Although the process to load data into and tune the execution of parallel DBMSs took much longer than the MR system, the observed performance of these DBMSs was strikingly better. We speculate about the causes of the dramatic performance difference and consider implementation concepts that future systems should take from both kinds of architectures.
Year
DOI
Venue
2009
10.1145/1559845.1559865
SIGMOD Conference
Keywords
Field
DocType
observed performance,parallel sql database management,dramatic performance difference,basic control flow,large-scale data analysis,mr system,parallel dbmss,development complexity,future system,considerable enthusiasm,database management system,computer model,data analysis,control flow
Data mining,Parallel database,Computer science,Parallel computing,Control flow,Sql database,Management system,Database
Conference
Citations 
PageRank 
References 
515
62.74
12
Authors
7
Search Limit
100515
Name
Order
Citations
PageRank
Andrew Pavlo11614122.03
Erik Paulson281481.47
Alexander Rasin32950209.48
Daniel J. Abadi46163367.24
David J. DeWitt5129433559.25
Samuel Madden6161011176.38
Michael Stonebraker7124634310.17