Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Local repair coding method of cross circular convolutional codes capable of multi-fault tolerance

A technology of cross loop and encoding method, applied in the field of partial repair encoding, which can solve the problems of high bandwidth overhead, high disk I/O overhead, and high storage cost

Active Publication Date: 2018-10-19
CHANGAN UNIV
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the explosive growth of stored data, the scale of the storage system has also doubled, which means that the storage nodes have become massive. In order to ensure the availability and reliability of the stored data, the storage system usually adopts "replication" and "erasure code" strategies. However, The storage cost of the "replication" strategy is high, and a large amount of copy data needs to be stored to ensure the high reliability of the system. The bandwidth overhead of the "erasure code" strategy is too large during the node repair process, and the storage system needs to have a high network bandwidth.
Aiming at the shortcomings of the "replication" and "erasure code" strategies, a regenerative code is proposed, but the regenerative code connects a large number of nodes in the process of repairing the faulty node, which has high disk I / O overhead, and the faulty node repair The solution is single, which cannot meet the requirements of the current massive storage nodes, and the fault tolerance of the system is low, which limits the repair of faulty nodes in the storage system

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
  • Local repair coding method of cross circular convolutional codes capable of multi-fault tolerance
  • Local repair coding method of cross circular convolutional codes capable of multi-fault tolerance
  • Local repair coding method of cross circular convolutional codes capable of multi-fault tolerance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0088] Present embodiment is for constructing (5,4) MDS sign indicating number in finite field GF (8), and the file size of note storage is M=1000M, and file is divided into k=4 information data block, uses m=[m 1 m 2 m 3 m 4 ] means file information data, where m 1 ,m 2 ,...,m 4 Indicates information data block; c=[c 1 c 2 ... c 5 ] represents the generated code word of the MDS code stored in the distributed storage node, and c=m G MDS , where the generator matrix G of the (5,4)MDS code MDS =[I|P] 4×5 , where I is a 4×4 identity matrix, and P is a 4×1-dimensional sub-matrix. (5,4) MDS code can be expressed as

[0089] c=m·G MDS =m·[I|P] 4×5

[0090] The n=5 encoded data blocks generated by the (5,4) MDS code are copied twice respectively, and stored in the selected n=5(N 1 , N 2 , N 3 , N 4 , N 5 ) in the data node, each node stores three data blocks, through the triangular structure diagram of the node coded data block, cross generates n check data blocks ...

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 discloses a local repair coding method of cross circular convolutional codes capable of multi-fault tolerance. The amount of data stored in a storage system is large, and the number of storage nodes is increased. If a conventional partial repetition code is used to construct local repair coding, when the fault of a node occurs, the faulty node repair scheme is single, the disk I / O cost in the repair process is large, and the fault tolerance capability of the system is low. Therefore, in a distributed storage system, the codes capable of multi-fault tolerance are used, a pluralityof repair schemes are provided in a process of repairing the faulty node, the disk I / O cost is low, and the fault tolerance capability of the system is improved.

Description

technical field [0001] The invention belongs to the field of computers, and relates to a local repair coding method for multi-error tolerant cross-circular convolutional codes. Background technique [0002] With the explosive growth of stored data, the scale of the storage system has also doubled, which means that the storage nodes have become massive. In order to ensure the availability and reliability of the stored data, the storage system usually adopts "replication" and "erasure code" strategies. However, The "replication" strategy has a high storage cost and needs to store a large amount of copy data to ensure high system reliability. The "erasure code" strategy has too much bandwidth overhead during the node repair process, requiring the storage system to have a high network bandwidth. Aiming at the shortcomings of the "replication" and "erasure code" strategies, a regenerative code is proposed, but the regenerative code connects a large number of nodes in the process ...

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): H03M13/11H04L29/08
CPCH03M13/1148H04L67/1097
Inventor 王静张雪飞贺书磊王淑霞王甜甜
Owner CHANGAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products