Method for dispersing and recovering storage data on dynamically changed storage medium

A storage medium, dynamic change technology, applied in the direction of protecting storage content from loss, can solve problems such as large computational load, low read and write efficiency, data loss, etc., to solve dependencies and bottlenecks, improve acquisition speed, and ensure integrity. Effect

Inactive Publication Date: 2012-11-28
HANGZHOU CLOUDUOLC NETWORK TECHOLOGY
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] But the RAID technology also has obvious deficiencies: one, need to increase expensive hardware RAID and use the same hard disk, its controllability can basically meet the read and write requirements, need to increase additional costs; two, RAID storage scalability is poor, The hard disk bundled usage mode of RAID makes it very difficult to increase or decrease the hard disk capacity; third, if the hard disk in the hard disk array is damaged and the new disk is not replaced in time, the security of data storage cannot be guaranteed at this time; for multiple hard drives, not multiple servers
[0013] Although RAID 1 technology adopts hard disk mirroring, which can guarantee the instant recovery of data, but because it is mirroring, the storage locations of the same data on the two disks are completely corresponding. If the track of the disk is damaged, the mirroring will lose its meaning and the data cannot be stored safely; and Because it is a mirroring technology, an even number of disks is required to achieve it, and if the damaged hard disk cannot be replaced in time, the security of the data will be affected; when reading data, the mirrored disk is often idle, and only one disk provides data , the reading and writing efficiency is low
[0014] For RAID 3 to 6 technologies, the data needs to be distributed and stored and the verification data to be calculated. The calculation of the verification is huge. After the disk is damaged, the rebuild of the RAID usually takes more than ten to twenty hours to complete, which affects the system. Normal operation, during this period, if another disk failure occurs, it will completely cause data loss

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
  • Method for dispersing and recovering storage data on dynamically changed storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] An image file is divided into two groups, the first group is numbered 1, and the second group is numbered 2, (when the data is not divisible by 2, that is, the data cannot be equally divided, the data can be filled with 0 ), the purpose of this grouping is to increase the granularity of files and facilitate the speed of subsequent processing. This grouping can be carried out according to actual requirements, and there is no strict requirement. Generally, integer division is appropriate, but the present invention can also be realized without integer division.

[0044] For each set of data, if the redundancy mode of 10+5 is adopted, (also in the block, when the data is not divisible by 10, that is, the data cannot be equally divided, the data can be filled with 0), then The numbers of the first group of data blocks are 1.1, 1.2..., 1.15; the numbers of the second group of data blocks are 2.1, 2.2..., 2.15; if the number of all storage devices is 4, the device numbers are r...

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 method for dispersing and recovering storage data on a dynamically changed storage medium. The method comprises the following steps: firstly, equally dividing data required to be stored into J groups, numbering each group of data and setting the groups from 1 to J; secondly, secondarily and equally dividing each group of data into N blocks, adding corresponding X checking blocks, wherein X is greater than 0, numbering the equally divided data and setting the data into 1.1, 1.2 until 1.N+X, 2.1, 2.2 until 2.N+X till J.1, J.2 until J.N+X; numbering all storage equipment on the network and setting the storage equipment from 1 to M, wherein M is greater than 0; distributing data of T blocks on M storage equipment; when partial M equipment is online, acquiring serial numbers of the current online storage equipment, obtaining T storage equipment which are most approximate to the serial numbers of each group and distributing and storing the data of T blocks on the T storage equipment; monitoring whether the storage equipment carries out online or offline change or not at regular time; and if the data are changed due to offline or damage of the storage equipment, restoring original data blocks or checking blocks and redistributing the data blocks according to the steps.

Description

technical field [0001] The invention relates to a method for dispersely storing data on a dynamically changing storage medium and restoring it. Background technique [0002] The safe storage of data is a very important task, especially for some special industries, the safety, reliability, and stability of data storage even exceed the requirements for functionality, and even require that damaged data can be recovered in the shortest possible time. Recovery, in order to realize the timely reading of data and ensure that the work performed by the computer system is not interrupted. For example, the storage device used for the video server of a TV station is required to ensure that the stored program data is safe and reliable, and even if the data is damaged, it can be restored immediately, especially during the broadcasting process. Restoring data on the premise of broadcasting the program shall not affect the normal broadcasting of the program. This puts high demands on the ...

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): G06F12/16
Inventor 黄旭涛李家川
Owner HANGZHOU CLOUDUOLC NETWORK TECHOLOGY
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