The Community for Technology Leaders
Green Image
Issue No. 09 - Sept. (2017 vol. 28)
ISSN: 1045-9219
pp: 2514-2526
Yunxiang Wu , Ministry of Education of China, Wuhan National Lab for Optoelectronics, Key Laboratory of Data Storage Systems (School of Computer Science and Technology, Huazhong University of Science and Technology), Wuhan, China
Fang Wang , Ministry of Education of China, Wuhan National Lab for Optoelectronics, Key Laboratory of Data Storage Systems (School of Computer Science and Technology, Huazhong University of Science and Technology), Wuhan, China
Yu Hua , Ministry of Education of China, Wuhan National Lab for Optoelectronics, Key Laboratory of Data Storage Systems (School of Computer Science and Technology, Huazhong University of Science and Technology), Wuhan, China
Dan Feng , Ministry of Education of China, Wuhan National Lab for Optoelectronics, Key Laboratory of Data Storage Systems (School of Computer Science and Technology, Huazhong University of Science and Technology), Wuhan, China
Yuchong Hu , Ministry of Education of China, Wuhan National Lab for Optoelectronics, Key Laboratory of Data Storage Systems (School of Computer Science and Technology, Huazhong University of Science and Technology), Wuhan, China
Wei Tong , Ministry of Education of China, Wuhan National Lab for Optoelectronics, Key Laboratory of Data Storage Systems (School of Computer Science and Technology, Huazhong University of Science and Technology), Wuhan, China
Jingning Liu , Ministry of Education of China, Wuhan National Lab for Optoelectronics, Key Laboratory of Data Storage Systems (School of Computer Science and Technology, Huazhong University of Science and Technology), Wuhan, China
Dan He , Ministry of Education of China, Wuhan National Lab for Optoelectronics, Key Laboratory of Data Storage Systems (School of Computer Science and Technology, Huazhong University of Science and Technology), Wuhan, China
ABSTRACT
Due to the high complexity in software hierarchy and the shared queue & lock mechanism for synchronized access, existing I/O stack for accessing the FCoE based SAN storage becomes a performance bottleneck, thus leading to a high I/O overhead and limited scalability in multi-core servers. In order to address this performance bottleneck, we propose a synergetic and efficient solution that consists of three optimization strategies for accessing the FCoE based SAN storage: (1) We use private per-CPU structures and disabling kernel preemption method to process I/Os, which significantly improves the performance of parallel I/O in multi-core servers; (2) We directly map the requests from the block-layer to the FCoE frames, which efficiently translates I/O requests into network messages; (3) We adopt a low latency I/O completion scheme, which substantially reduces the I/O completion latency. We have implemented a prototype (called FastFCoE, a protocol stack for accessing the FCoE based SAN storage). Experimental results demonstrate that FastFCoE achieves efficient and scalable I/O throughput, obtaining 1132.1K/836K IOPS (6.6/5.4 times as much as original Linux Open-FCoE stack) for read/write requests.
INDEX TERMS
Servers, Scalability, Throughput, Synchronization, Multicore processing, Optimization, Protocols
CITATION

Y. Wu et al., "I/O Stack Optimization for Efficient and Scalable Access in FCoE-Based SAN Storage," in IEEE Transactions on Parallel & Distributed Systems, vol. 28, no. 9, pp. 2514-2526, 2017.
doi:10.1109/TPDS.2017.2685139
924 ms
(Ver 3.3 (11022016))