FAB: Building distributed enterprise disk arrays from commodity components

被引:36
作者
Saito, Y [1 ]
Frolund, S [1 ]
Veitch, A [1 ]
Merchant, A [1 ]
Spence, S [1 ]
机构
[1] Hewlett Packard Labs, Palo Alto, CA 94304 USA
关键词
algorithms; management; performance; reliability; storage; disk array; replication; erasure coding; voting; consensus;
D O I
10.1145/1037187.1024400
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
This paper describes the design, implementation, and evaluation of a Federated Array of Bricks (FAB), a distributed disk array that provides the reliability of traditional enterprise arrays with lower cost and better scalability. FAB is built from a collection of bricks, small storage appliances containing commodity disks, CPU, NVRAM, and network interface cards. FAB deploys a new majority-voting-based algorithm to replicate or erasure-code logical blocks across bricks and a reconfiguration algorithm to move data in the background when bricks are added or decommissioned. We argue that voting is practical and necessary for reliable, high-throughput storage systems such as FAB. We have implemented a FAB prototype on a 22-node Linux cluster. This prototype sustains 85MB/second of throughput for a database workload, and 270MB/second for a bulk-read workload. In addition, it can outperform traditional master-slave replication through performance decoupling and can handle brick failures and recoveries smoothly without disturbing client requests.
引用
收藏
页码:48 / 58
页数:11
相关论文
共 34 条
[1]  
ADYA A, 2002, 5 S OP SYS DES IMPL
[2]  
Aguilera Marcos K., 2003, Technical Report HPL- 2003-241
[3]  
ANDERSON D, 2003, USENIX C FIL STOR TE
[4]  
ASAMI S, 2000, UCBCSD001100
[5]   SHARING MEMORY ROBUSTLY IN MESSAGE-PASSING SYSTEMS [J].
ATTIYA, H ;
BARNOY, A ;
DOLEV, D .
JOURNAL OF THE ASSOCIATION FOR COMPUTING MACHINERY, 1995, 42 (01) :124-142
[6]   THE TICKERTAIP PARALLEL RAID ARCHITECTURE [J].
CAO, P ;
LIM, SB ;
VENKATARAMAN, S ;
WILKES, J .
ACM TRANSACTIONS ON COMPUTER SYSTEMS, 1994, 12 (03) :236-269
[7]   RAID - HIGH-PERFORMANCE, RELIABLE SECONDARY STORAGE [J].
CHEN, PM ;
LEE, EK ;
GIBSON, GA ;
KATZ, RH ;
PATTERSON, DA .
ACM COMPUTING SURVEYS, 1994, 26 (02) :145-185
[8]  
CHRISTIN F, 1995, CSE95428 UC SAN DIEG
[9]  
Frolund S, 2004, 2004 INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS AND NETWORKS, PROCEEDINGS, P125
[10]  
FROLUND S, 2003, 8 WORKSH HOT TOP OP, P169