Magnetic disc array system

A disk array and disk technology, applied in the direction of response error generation, redundant code error detection, etc., can solve problems such as disk failure, data loss, and low fault tolerance

Inactive Publication Date: 2009-03-18
CAS OF CHENGDU INFORMATION TECH CO LTD
View PDF0 Cites 39 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 1. When the RAID system is faced with natural disasters such as earthquakes and fires, or man-made damage such as terrorist explosions, a large number of disks will fail, and the existing RAID technology will inevitably fail when facing this situation. data loss will occur;
[0006] 2. If the RAID system has a greater fault tolerance, it can safely provide uninterrupted services when a small number of disk errors occur. However, the existing RAID system has a low fault tolerance, and the number of disk errors can easily reach the fault tolerance. At this time, in order to avoid data loss caused by disk errors that may continue to occur, the system has to stop the service for data recovery

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
  • Magnetic disc array system
  • Magnetic disc array system
  • Magnetic disc array system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0081] Construct a disk array system that includes n=32 disks and can tolerate t / 2=6 disks at most. The smallest capacity among all disks is 80G bytes, so the total capacity of the disk array system is 20*80G bytes. The storage space of each disk is divided into sectors with a size of 512 bytes, and sectors with the same number on each disk are grouped into a stripe, and the disk array system performs data read and write operations in units of stripes; each stripe The storage space of the tape, that is, each sector of each disk is evenly divided into 32 blocks, the first 20 blocks store valid information as information blocks, and the last 12 blocks store check information as check blocks; write operations on the stripe When the fault-tolerant coding method is used to produce check information, the valid information is stored in the information block, and the check information is stored in the check block; when a disk error occurs in the disk array system, the error disk recov...

Embodiment 2

[0145] The same place as in Embodiment 1 will not be described again, and the difference is that:

[0146] Construct a disk array system that contains n=32 disks and can tolerate t / 2=10 disks at most. The smallest capacity among all disks is 40G bytes, so the total capacity of the disk array system is 12*40G bytes. Each sector of each disk is evenly divided into 32 blocks, the first 12 blocks store valid information as information blocks, and the last 20 blocks store check information as check blocks.

[0147] The fault-tolerant coding method is as follows:

[0148] Construct a matrix of [12, 31] and set all its elements to 0

[0149]

[0150] Randomly select p=7 elements in the above matrix, and set their values ​​to 1.

[0151] Row and column homogenization is performed on the matrix, and row and column transformations are performed randomly. The result is as follows:

[0152]

[0153] Save all elements with a value of 1 in the above matrix as a set of two-tuples:...

Embodiment 3

[0174] The same place as in Embodiment 1 will not be described again, and the difference is that:

[0175] Construct a disk array system that includes n=4 disks and can tolerate a maximum of t / 2=1 disks. The smallest capacity among all disks is 120G bytes, so the total capacity of the disk array system is 2*120G bytes. Each sector of each disk is evenly divided into 4 blocks, the first 2 blocks store valid information as an information block, and the last 2 blocks store verification information as a check block.

[0176] The fault-tolerant coding method is as follows:

[0177] Construct a matrix of [2, 3] and set all its elements to 0

[0178] 0 0 0 0 0 0

[0179] Randomly select p=2 elements in the above matri...

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 disk array system, which comprises n disks, wherein n is more than 4, and errors in less than or equal to t / 2 disks are allowed. The memory space of each disk is divided into sectors of 512 bytes or 4k bytes, the sectors with same numbers on each disk are organized into a stripe, the disk array system performs data reading and writing in stripes, the memory space of each sector is uniformly divided into n chunks, preliminary n-t chunks storing effective information are used as information blocks, and last t chunks storing parity information are used as parity blocks. Compared with the prior art, the invention provides the disk array system with non-stop service, high reliability and high fault tolerance, the fault tolerance reaches above 10, non-stop service can be supplied in case of less disk errors, and all data can be recovered in case of a great number of errors.

Description

technical field [0001] The invention relates to the field of large-capacity storage, in particular to a high fault-tolerant disk array system with uninterrupted service. Background technique [0002] With the continuous development of human society, information has increasingly become an important resource in people's daily life; for highly electronic modern enterprises, all kinds of information stored in computers directly affect business decisions and even the success or failure of enterprises. However, due to various occasional reasons, people cannot effectively predict and prevent computer system errors and disasters. Hardware failures, personnel operating errors, virus attacks, terrorist attacks, power outages, fires, earthquakes and other natural disasters may also cause computer data Inaccessible or even lost, resulting in immeasurable losses. [0003] In order to meet people's demand for larger storage system capacity, better I / O performance and higher reliability, ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F11/10
Inventor 陈峥张永成唐聃王晓京曹晟万武南孙宣东杨洁孟庆春王一丁周红磊张良志方佳嘉蔡红亮
Owner CAS OF CHENGDU INFORMATION TECH CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap