HRSF: Single Disk Failure Recovery for Liberation Code Based Storage Systems
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Storage system often applies erasure codes to protect against disk failure and ensure system reliability andavailability. Liberation code that is a type of coding scheme has been widely used in many storage systemsbecause its encoding and modifying operations are efficient. However, it cannot effectively achieve fast recoveryfrom single disk failure in storage systems, and has great influence on recovery performance as well as responsetime of client requests. To solve this problem, in this paper, we present HRSF, a Hybrid Recovery method forsolving Single disk Failure. We present the optimal algorithm to accelerate failure recovery process. Theoreticalanalysis proves that our scheme consumes approximately 25% less amount of data read than the conventionalmethod. In the evaluation, we perform extensive experiments by setting different number of disks and chunksizes. The results show that HRSF outperforms conventional method in terms of the amount of data read andfailure recovery time.
Abstract
Storage system often applies erasure codes to protect against disk failure and ensure system reliability andavailability. Liberation code that is a type of coding scheme has been widely used in many storage systemsbecause its encoding and modifying operations are efficient. However, it cannot effectively achieve fast recoveryfrom single disk failure in storage systems, and has great influence on recovery performance as well as responsetime of client requests. To solve this problem, in this paper, we present HRSF, a Hybrid Recovery method forsolving Single disk Failure. We present the optimal algorithm to accelerate failure recovery process. Theoreticalanalysis proves that our scheme consumes approximately 25% less amount of data read than the conventionalmethod. In the evaluation, we perform extensive experiments by setting different number of disks and chunksizes. The results show that HRSF outperforms conventional method in terms of the amount of data read andfailure recovery time.
참고문헌 (25)
- M. Deng, "Erasure codes in big data era", Proceedings of International Conference on Control, Automation and Information Sciences (ICCAIS), pp.218~223 (2014)
- X. Pei, "A decentralized redundancy generation scheme for codes with locality in distributed storage systems", Concurrency and Computation: Practice and Experience, 29(8) (2017)
- P. Corbett, "Row-diagonal parity for double disk failure correction", Proceeding of the 3rd USENIX Conference on File and Storage Technologies, pp.1~14 (2004)
- M. Blaum, "EVENODD : an efficient scheme for tolerating double disk failures in RAID architectures", IEEE Transactions on Computers, 44(2), pp.192~202 (1995)
- C. Huang, "STAR : an efficient coding scheme for correcting triple storage node failures", IEEE Transactions on Computers, 57(7), pp.889~901 (2008)
- Y. Fu, "Short code : an efficient RAID-6 MDS code for optimizing degraded reads and partial stripe writes", IEEE Transactions on Computers, 66(1), pp.127~137 (2017)
- P. M. Chen, "RAID : high-performance, reliable secondary storage", ACM Computing Surveys(CSUR), 26(2), pp.145~185 (1994)
- L. Xiang, "Optimal recovery of single disk failure in RDP code storage", ACM SIGMETRICS Performance Evaluation Review, 38(1), pp.119~130 (2010)
- Z. Wang, "Rebuilding for array codes in distributed storage systems", Proceedings of 2010 IEEE Globecom Workshops, pp.1905~1909 (2010)
- Z. Shen, "Seek-efficient I", O optimization in single failure recovery for XOR-coded storage systems, 2017, pp.28(3), 877~890
- Z. Shen, "Encoding-aware data placement for efficient degraded reads in XORcoded storage systems", Proceedings of IEEE 35th Symposium on Reliable Distributed Systems, pp.239~248 (2016)
- P. Nakkiran, "Optimal systematic distributed storage codes with fast encoding", Proceedings of IEEE International Symposium on Information Theory, pp.430~434 (2016)
- M. Itani, "Practical single node failure recovery using fractional repetition codes in data centers", Proceedings of IEEE 30th International Conference on Advanced Information Networking and Applications (AINA), pp.762~768 (2016)
- B. Sung, "Fast reconstruction for degraded reads and recovery process in primary array storage systems", IEICE Transactions on Information and Systems, 100(2), pp.294~303 (2017)
- O. Khan, "Rethinking erasure codes for cloud file systems:minimizing I", O for recovery and degraded reads, 2012, ~
- O. Khan, "In search of I", O optimal recovery from disk failures, 2011, ~
- Y. Zhu, "Boosting degraded reads in heterogeneous erasure-coded storage systems", IEEE Transaction on Computers, 64(8), pp.2145~2157 (2015)
- K. V. Rashmi, "A solution to the network challenges of data recovery in erasure-coded distributed storage systems: a study on the Facebook warehouse cluster", Proceedings of the 5th USENIX Conference on Hot Topics in Storage and File System, pp.8~13 (2013)
- K. V. Rashmi, "A "hitchhiker's" guide to fast and efficient data reconstruction in erasure-coded data centers", ACM SIGCOMM Computer Communication Review, 44(4), pp.331~342 (2015)
- Z. Shen, "Reconsidering single failure recovery in clustered file systems", Proceedings of 2016 46th Annual IEEE, 2016, 323~334
- M. Sathiamoorthy, "XORing elephants : novel erasure codes for big data", Proceedings of the VLDB Endowment, 6(5), pp.325~336 (2013)
- J. S. Plank, "The RAID-6 Liber8Tion Code", The International Journal of High Performance Computing Applications, 23(3), pp.242~251 (2009)
- D. Narayanan, "Write off-loading: practical power management for enterprise storage", Proceedings of the 6th USENIX Conference on File and Storage Technologies (FAST), pp.253~267 (2008)
- S. Wu, "Workout: I", O workload outsourcing for boosting RAID reconstruction performance, 2009, 239~252
- "The DiskSim simulation environment (v4.0)"[URL]