Skip to main navigation Skip to search Skip to main content

An efficient snapshot indexing method for block-level backup data in replication system

  • Guangjun Wu*
  • , Binxing Fang
  • , Xiangzhan Yu
  • , Xiaochun Yun
  • , Shupeng Wang
  • *Corresponding author for this work
  • Harbin Institute of Technology
  • CAS - Institute of Computing Technology

Research output: Contribution to journalArticlepeer-review

Abstract

Snapshot query can provide a clean copy for restoration in replication system. Current backup techniques produce large volume of backup data. Up till now, there was no efficient indexing method to retrieve a snapshot from updating log in block-level replication system. In this paper, we present a novel indexing method that is capable of querying any version of historical snapshot without introducing additional backup operations. A detailed mathematical model is used to analyze the complexity of our implementation. Under the guide of mathematical analysis, we present Hierarchical Clustering Snapshot Indexing Method (HCSIM). HCSIM includes snapshot query algorithm, version deleting rules and concurrency control policy. Extensive experiments have been carried out to show that the new indexing method can support snapshot query at low cost, both in theory and practice. Performance evaluation of the novel indexing method indicates that the implementation is optimal in current snapshot indexing methods. ICIC International

Original languageEnglish
Pages (from-to)915-925
Number of pages11
JournalInternational Journal of Innovative Computing, Information and Control
Volume7
Issue number2
StatePublished - Feb 2011

Keywords

  • Block-level
  • Indexing
  • Snapshot
  • Storage
  • Version management

Fingerprint

Dive into the research topics of 'An efficient snapshot indexing method for block-level backup data in replication system'. Together they form a unique fingerprint.

Cite this