DOI QR코드

DOI QR Code

The Design of Regenerating Codes with a Varying Number of Helper Nodes

다양한 도움 노드의 수를 가지는 재생 부호의 설계

  • Lee, Hyuk (Department of Electrical and Computer Engineering, INMAC, Seoul National University) ;
  • Lee, Jungwoo (Department of Electrical and Computer Engineering, INMAC, Seoul National University)
  • Received : 2016.10.07
  • Accepted : 2016.12.06
  • Published : 2016.12.31

Abstract

Erasure codes have recently been applied to distributed storage systems due to their high storage efficiency. Regenerating codes are a kind of erasure codes, which are optimal in terms of minimum repair bandwidth. An (n,k,d)-regenerating code consists of n storage nodes where a failed node can be recovered with the help of the exactly d numbers of surviving nodes. However, if node failures occur frequently or network connection is unstable, the number of helper nodes that a failed node can contact may be smaller than d. In such cases, regenerating codes cannot repair the failed nodes efficiently since the node repair process of the codes does not work when the number of helper nodes is less than d. In this paper, we propose an operating method of regenerating codes where a failed node can be repaired from ${\bar{d}}$ helper nodes where $$k{\leq_-}{\bar{d}}{\leq_-}d$$.

최근 분산 저장 시스템에 erasure code를 활용하여 저장소 효율성을 높이려는 연구가 활발히 진행되고 있다. 재생 부호(regenerating codes)는 erasure code의 일종으로, 높은 저장소 효율성과 네트워크 효율성을 가지는 코드이다. (n,k,d)-재생 부호는 n개의 저장소 노드를 가지며, 손실된 노드가 발생하였을 때, 해당 노드는 d개의 살아남은 노드로부터 정보를 다운로드받아 복구될 수 있다. 하지만 일반적인 재생 부호는 노드 복구 시 정확히 d개의 도움 노드들을 사용해야 하며, 노드 손실이 빈번하거나, 노드 간 접속이 불안정한 환경에서, d개 이하의 노드들에만 접속 가능할 경우에 유연하게 대처할 수 없다. 본 논문에서는 약간의 복구 대역폭의 희생을 통하여, $$k{\leq_-}{\bar{d}}{\leq_-}d$$의 다양한 도움 노드의 수 ${\bar{d}}$개로 노드를 복구할 수 있는 유연한 코드 운용 방식을 제안하였다.

Keywords

References

  1. D. Borthakur, HDFS architectuure guide, Hadoop apache project(2008), http://hadoop.apache.org/common/docs/current/hdfs_design.pdf
  2. B. Calder, J. Wang, A. Ogus, N. Nilakantan, A. Skjolsvold, S. McKelvie, Y. Xu, S. Srivastav, J. Wu, H. Simitci, J. Haridas, C. Uddaraju, H. Khatri, A. Edwards, V. Bedekar, S. Mainali, R. Abbasi, A. Agarwal, M. F. ul Haq, M. I. ul Haq, D. Bhardwaj, S. Dayanand, A. Adusumilli, M. McNett, S. Sankaran, K. Manivannan, and L. Rigas, "Windows azure storage: A highly available cloud storage service with strong consistency," in Proc. ACM SOSP, pp. 143-157, Oct. 2011.
  3. K. V. Rashmi, N. B. Shah, D. Gu, H. Kuang, D. Borthakur, and K. Ramchandran, "A solution to the network challenges of data recovery in erasure-coded distributed storage systems: A study on the Facebook warehouse cluster," in Proc. USENIX Workshop on Hot Topics in Storage and File Systems, Jun. 2013.
  4. D. S. Papailiopoulos and A. G. Dimakis, "Locally repairable codes," IEEE Trans. Inf. Theory, vol. 60, no. 10, pp. 5843-5855, Oct. 2014. https://doi.org/10.1109/TIT.2014.2325570
  5. J.-H. Kim, M.-Y. Nam, and H.-Y. Song, "Construction of [2^k-1+k, k, 2^k-1+1] codes attaining Griesmer bound and its locality," J. KICS, vol. 40, no. 03, Mar. 2015.
  6. M.-Y. Nam, J.-H. Kim, and H.-Y. Song, "Locally repairable fractional repetition codes," J. KICS, vol. 40, no. 9, pp. 1741-1753. Sept. 2015. https://doi.org/10.7840/kics.2015.40.9.1741
  7. J.-H. Kim, M.-Y. Nam, and H.-Y. Song, "Bianry locally repairable codes from complete multipartite graphs," J. KICS, vol. 40, no. 03, Mar. 2015.
  8. A. G. Dimakis, P. B. Godfrey, Y. Wu, M. J. Wainwright, and K. Ramchandran, "Network coding for distributed storage systems," IEEE Trans. Inf. Theory, vol. 56, no. 9, pp. 4539-4551, Sept. 2010. https://doi.org/10.1109/TIT.2010.2054295
  9. K. V. Rashmi, N. B. Shah, and P. V. Kumar, "Optimal exact-regenerating codes for distributed storage at the MSR and MBR points via a product-matrix construction," IEEE Trans. Inf. Theory, vol. 57, no. 8, pp. 5227-5239, Aug. 2011. https://doi.org/10.1109/TIT.2011.2159049