TY - GEN
T1 - Middleware support for RDMA-based data transfer in cloud computing
AU - Ren, Yufei
AU - Li, Tan
AU - Yu, Dantong
AU - Jin, Shudong
AU - Robertazzi, Thomas
N1 - Copyright:
Copyright 2012 Elsevier B.V., All rights reserved.
PY - 2012
Y1 - 2012
N2 - Providing high-speed data transfer is vital to various data-intensive applications in cloud computing systems. We design a middleware layer of high-speed communication based on Remote Direct Memory Access (RDMA) that serves as the common substrate to accelerate various data transfer applications in cloud computing, such as FTP, HTTP, file copy, sync and remote file I/O. This middleware offers higher end-to-end bandwidth than the traditional TCP-based alternatives, while it hides the heterogeneity of the underlying high-speed architecture. In this paper, we describe the design of this middleware, including resource abstraction, and task synchronization and scheduling. We provide a reference implementation of the file-transfer protocol over this RDMA based middleware. Our experimental results show that it outperforms several TCP-based FTP tools, such as GridFTP, while maintaining very low CPU consumption on a variety of platforms. Furthermore, these results confirm that our middleware achieves near line-speed performance in both LAN and MAN, and scales consistently from 10Gbps Ethernet to 40Gbps Ethernet and InfiniBand environments.
AB - Providing high-speed data transfer is vital to various data-intensive applications in cloud computing systems. We design a middleware layer of high-speed communication based on Remote Direct Memory Access (RDMA) that serves as the common substrate to accelerate various data transfer applications in cloud computing, such as FTP, HTTP, file copy, sync and remote file I/O. This middleware offers higher end-to-end bandwidth than the traditional TCP-based alternatives, while it hides the heterogeneity of the underlying high-speed architecture. In this paper, we describe the design of this middleware, including resource abstraction, and task synchronization and scheduling. We provide a reference implementation of the file-transfer protocol over this RDMA based middleware. Our experimental results show that it outperforms several TCP-based FTP tools, such as GridFTP, while maintaining very low CPU consumption on a variety of platforms. Furthermore, these results confirm that our middleware achieves near line-speed performance in both LAN and MAN, and scales consistently from 10Gbps Ethernet to 40Gbps Ethernet and InfiniBand environments.
KW - Data Center Networks
KW - Middleware
KW - Protocol offloading
KW - Remote Direct Memory Access
UR - http://www.scopus.com/inward/record.url?scp=84867407447&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84867407447&partnerID=8YFLogxK
U2 - 10.1109/IPDPSW.2012.133
DO - 10.1109/IPDPSW.2012.133
M3 - Conference contribution
AN - SCOPUS:84867407447
SN - 9780769546766
T3 - Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012
SP - 1095
EP - 1103
BT - Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012
T2 - 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012
Y2 - 21 May 2012 through 25 May 2012
ER -