Low-bandwidth data reconstruction method for binary coding redundancy storage system

A binary encoding, redundant storage technology, applied in the field of data disaster recovery and low-bandwidth reconstruction of lost data, to reduce the amount of data transmission, reduce pressure, and reduce the number of reads

Active Publication Date: 2014-04-30
山东骑风电子科技有限公司
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Since it is necessary to transmit any s unlost data blocks to a new node for decoding when recovering the lost data blocks, when the amount of data is large, using th

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Low-bandwidth data reconstruction method for binary coding redundancy storage system
  • Low-bandwidth data reconstruction method for binary coding redundancy storage system
  • Low-bandwidth data reconstruction method for binary coding redundancy storage system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] When a node is damaged inside the storage system, for a storage system constructed by traditional (n,k) MDS erasure codes, when ≤n-k nodes in the system are damaged, the system needs to call the data pairs on k nodes It recovers, and the erasure codes that are usually constructed have n-k≤k.

[0059] If the check matrix of the (6,3) Vandermonde system erasure code constructed on binary is as follows image 3 As shown, due to β.H (k+r)·r= 0, where β represents the original file block and verification data block stored in the storage system, and [D 1 ,D 2 ,D 3 ,D 4 ,L,D 10 ,L,D (k+r)·r ]express. If the first storage node in the storage system is damaged, the storage file will be divided into blocks [D 1 ,D 2 ,D 3 ] is lost, then β=[X 1 , X 2 , X 3 ,D 4 ,L,D 10 ,L,D 18 ], where [X 1 , X 2 , X 3 ] corresponds to the data block that has been lost, and [D 10 ,L,D 18 ] is the checksum data block. Apparently, no matter whether any three-column vector in th...

Embodiment 2

[0067] In order to further illustrate the effectiveness of the present invention, the present invention performs low-bandwidth optimization on the decoding process of the STAR code according to the method proposed by the present invention. In this embodiment, the information size of the STAR code is m=5, and the check column size is 3. According to the construction process of the STAR code, when the information scale of the STAR code is m=5, its generation matrix can be expressed as: G = I P , Then P can be expressed as:

[0068] P = 1 0 0 0 1 0 0 ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a low-bandwidth data reconstruction method for a binary coding redundancy storage system. The low-bandwidth data reconstruction method for the binary coding redundancy storage system comprises the steps that (1) the corresponding relation between a lost data block and row vectors of a data check matrix is established, and low-bandwidth check matrixes are determined according to sub-matrixes composed of column vectors of the data check matrix corresponding to data blocks which are not lost in the storage system; (2) whether the number of the low-bandwidth check matrixes is larger than one is judged; (3) if yes, whether the I/O pressures, caused by the fact that the lost data block is recovered through all the low-bandwidth check matrixes, on each storage node are equal or not is judged; (4) if not, the low-bandwidth check matrix exerting the smallest I/O pressure is selected to conduct data reconstruction on the lost data block. Compared with the prior art, the low-bandwidth check matrixes are determined, the storage node with the smallest I/O reading pressure is found for recovery of the lost data block, and therefore the network bandwidth consumption caused by data reading of the system storage nodes can be reduced in the process of data block reconstruction.

Description

technical field [0001] The invention relates to the technical field of coded storage of electronic information data, in particular to data disaster recovery and low-bandwidth reconstruction technology of lost data on a distributed basic storage architecture. Background technique [0002] With the rapid development of wired network technology and wireless network technology, it has become a trend to use the network to build a distributed storage system. However, logically, the network covers a wide range, and any node may cause permanent loss or damage of some important data stored on the distributed system due to some unpredictable accidental changes, such as human error, equipment component failure , earthquakes, floods, fires, typhoons, and even malicious theft, etc., which may cause incalculable losses; especially for sensor network nodes used for field monitoring, due to the large changes in the field environment, some extreme environments are relatively harsh, data acqu...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F11/14
Inventor 蒋海波陈建中李娜周星梅王晓京蒋小强陈怡李范
Owner 山东骑风电子科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products