RXIO: Design and implementation of high performance RDMA-capable GridFTP

被引:2
作者
Tian, Yuan [1 ]
Yu, Weikuan [1 ,2 ]
Vetter, Jeffrey S. [2 ]
机构
[1] Auburn Univ, Dept Comp Sci, Auburn, AL 36849 USA
[2] Oak Ridge Natl Lab, Oak Ridge, TN 37831 USA
基金
美国国家科学基金会;
关键词
41;
D O I
10.1016/j.compeleceng.2011.11.008
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
For its low-latency, high bandwidth, and low CPU utilization, Remote Direct Memory Access (RDMA) has established itself as an effective data movement technology in many networking environments. However, the transport protocols of grid run-time systems, such as GridFTP in Globus, are not yet capable of utilizing RDMA. In this study, we examine the architecture of GridFTP for the feasibility of enabling RDMA. An RDMA-capable XIO (RXIO) framework is designed and implemented to extend its XIO system and match the characteristics of RDMA. Our experimental results demonstrate that RDMA can significantly improve the performance of GridETP, reducing the latency by 32% and increasing the bandwidth by more than three times. In achieving such performance improvements, RDMA dramatically cuts down CPU utilization of GridFTP clients and servers. These results demonstrate that RXIO can effectively exploit the benefits of RDMA for GridFTP. It offers a good prototype to further leverage GridFTP on wide-area RDMA networks. (C) 2011 Elsevier Ltd. All rights reserved.
引用
收藏
页码:772 / 784
页数:13
相关论文
共 32 条
[1]  
Allcock WE, 2005, IPDPS
[2]  
[Anonymous], 2005, Proceedings of the 2005 ACM/IEEE conference on Supercomputing, DOI DOI 10.1109/SC.2005.72
[3]  
[Anonymous], P INT WORKSH PROT LO
[4]  
Bresnahan J, 2009, P 2 INT WORKSH PROT
[5]  
Callaghan Brent., 2003, P ACM SIGCOMM WORKSH, p196.208
[6]  
Carns PH, 2000, USENIX ASSOCIATION PROCEEDINGS OF THE 4TH ANNUAL LINUX SHOWCASE AND CONFERENCE, ATLANTA, P317
[7]  
Cater S, 2008, HIGH PERF COMP S HPC
[8]  
Chadalapaka M., 2003, P ACM SIGCOMM WORKSH, P209, DOI DOI 10.1145/944747.944754
[9]   iSER storage target for object-based storage devices [J].
Dalessandro, Dennis ;
Devulapalli, Ananth ;
Wyckoff, Pete .
SNAPI 2007: FOURTH INTERNATIONAL WORKSHOP ON STORAGE NETWORK ARCHITECTURE AND PARALLEL I/OS, PROCEEDINGS, 2007, :107-113
[10]  
DeBergalis M., 2003, P 2 USENIX C FIL STO