An Efficient Binary Locally Repairable Code for Hadoop Distributed File System

In the Hadoop distributed file systems (HDFSs), to lower costly communication traffic for data recovery, the concept of locally repairable codes (LRCs) has been recently proposed. With regard to the immense size of modern energy-hungry HDFS, computational complexity reduction can be attractive. In t...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE communications letters Ročník 18; číslo 8; s. 1287 - 1290
Hlavní autoři: Shahabinejad, Mostafa, Khabbazian, Majid, Ardakani, Masoud
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York, NY IEEE 01.08.2014
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Applied sciences
Coding, codes
Computational complexity
Decoding
Encoding
Exact sciences and technology
Information theory
Information, signal and communications theory
Maintenance engineering
Reliability
Signal and communications theory
Systematics
Telecommunications and information theory
locally repairable codes
hadoop distributed file system
Erasure coding
Finite field
Multiplication
Coding
Data recovery
Minimal distance
Distributed system
Reliability
Binary code
Computational complexity
ISSN:1089-7798, 1558-2558
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In the Hadoop distributed file systems (HDFSs), to lower costly communication traffic for data recovery, the concept of locally repairable codes (LRCs) has been recently proposed. With regard to the immense size of modern energy-hungry HDFS, computational complexity reduction can be attractive. In this letter, to avoid finite field multiplications, which are the major source of complexity, we put forward the idea of designing binary locally repairable codes (BLRCs). More specifically, we design a BLRC with a length of 15, rate of 2/3, and minimum distance of 4, which has the minimum possible locality among its type. We show that our code has lower complexity than most recent non-binary LRC in the literature while meeting other desirable requirements in HDFS such as storage overhead and reliability.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1089-7798
1558-2558
DOI:10.1109/LCOMM.2014.2332491