CN105786656A - Independent disk redundant array disaster tolerance storage method based on random matrix - Google Patents
Independent disk redundant array disaster tolerance storage method based on random matrix Download PDFInfo
- Publication number
- CN105786656A CN105786656A CN201610089410.7A CN201610089410A CN105786656A CN 105786656 A CN105786656 A CN 105786656A CN 201610089410 A CN201610089410 A CN 201610089410A CN 105786656 A CN105786656 A CN 105786656A
- Authority
- CN
- China
- Prior art keywords
- block
- data block
- matrix
- original data
- redundant
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/2053—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where persistent mass storage functionality or persistent mass storage control functionality is redundant
- G06F11/2094—Redundant storage or storage space
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Techniques For Improving Reliability Of Storages (AREA)
Abstract
Provided is an independent disk redundant array disaster tolerance storage method based on a random matrix.The method comprises the steps that code parameters are built according to the size of a file to be stored; the file to be stored is equally divided into k data blocks, and zero-padding is conducted on insufficient places; a storage region in a storage system is obtained; the storage region is divided into n storage blocks; the first k storage blocks of the storage region are selected to serve as original data storage blocks, and the rest n-k storage blocks serve as redundant data storage blocks; the k data blocks are filled into the first k original data storage blocks column by column; a random code matrix G[n*k] of which the scale is n*k is built on GF(2) according to the code parameters; n-k redundant data blocks of the storage blocks are generated according to the random code matrix G[n*k] and k data blocks; the n-k redundant data blocks are filled into the n-k redundant data storage blocks column by column.According to the independent disk redundant array disaster tolerance storage method based on the random matrix, the disaster tolerance capacity and expansibility of the storage system are improved.
Description
Technical field
The present invention relates to field of data storage, particularly to a kind of RAID disaster tolerance based on random matrix
Storage method.
Background technology
Along with the development of information technology and popularizing of network, data start to present explosive growth, and 2010 complete
Ball data volume has reached ZB magnitude.Increasing data are closely bound up with the life of people, and the storage of these data with
Protection is challenged greatly, has become as one of hot issue of current social discussion, and urgently obtains adequate solution.
Now, main storage system has following three classes: a class is based on the storage system replicated, typical such as Google
File system, this storage system uses the mode of three backups to carry out the storage and disaster tolerance of data, and its advantage is simple to operate, shortcoming
It is that memory area utilization rate is relatively low, causes the waste of great memory area.Another kind of is array code based on XOR storage
System, such as RAID-6, conventional coded method has EVENODD code, Star code, RDP code, X-Code etc., and such stores system
Advantage be use xor operation, there is higher coding and decoding efficiency, additionally the utilization rate of memory area the most relatively copy mode has
The biggest raising, its shortcoming is that coding parameter is limited by prime number, it is impossible to arbitrary extension, it is difficult under the different disaster tolerance demand of reply
Code storage.Also having a class is code storage system based on Reed-Solomon code, such as OceanStore.Such stores system
The advantage of system is that the utilization rate of memory area is higher, and coding parameter has a certain degree of freedom in finite field scale, lacks
Point be coding and decoding computing all on finite field, and currently generally acknowledge, the computation complexity on finite field is the highest, particularly rule
In the case of mould is relatively big, this coding having had a strong impact on this storage system and rebuilding rate, it is impossible to be generalized to actual answering well
In with.
In sum, three main class storage systems are all respectively arranged with quality, it is impossible to meet current extensive number well
According to storage demand.Therefore, build a kind of existing higher coding and decoding speed, and storage size be the most unrestricted, simultaneously, moreover it is possible to
Realize the High Performance Cache and Memory System of code storage under different fault-tolerant demand, be big data age people one that data are stored
Urgent needs.
Summary of the invention
For solving above-mentioned technical problem, the invention provides that a kind of redundancy ability is strong and extensibility is good, reliability is high, deposit
Storage efficiency and space availability ratio high RAID disaster tolerance based on random matrix storage method.
The invention provides a kind of RAID disaster tolerance based on random matrix storage method, including: according to
The size of file to be stored builds coding parameter；Described file to be stored is divided into k according to block, not enough local zero padding；
Obtain one section of memory area in storage system；Described memory area is divided into n memory block；Choose described memory area
Front k memory block is as original data storage block, and remaining n-k memory block is as redundant data storage block；By described k
It is filled into by column in described front k original data storage block according to block；It is n according to described coding parameter structure scale on GF (2)
The random coded matrix G of × kn×k；According to described random coded matrix Gn×kAnd described k generates described n-k storage according to block
The redundant data block of block；Described n-k redundant data block is inserted in described n-k memory block by column.
Preferably, described memory area crosses over multiple different physical store nodes.
Preferably, the redundant digit of described n-k memory block is generated according to described random coded matrix and described k according to block
Include according to block: first, by described random coded matrix Gn×kLast n-k non-unity row in, often data corresponding to 1 in row
Block carries out XOR summation, thus obtains the redundant block that this row is corresponding；Then, the redundant block of described correspondence is filled to this row one
In the redundant data block caused.
Preferably, according to described coding parameter at the random coded matrix G that the upper structure scale of GF (2) is n × kn×kIncluding:
First, it is determined that described random coded matrix Gn×kWhether it is sequency spectrum, if not then reconfiguring described random coded matrix
Gn×k, until constructing the described random coded matrix G of sequency spectrumn×k；Secondly, by described random coded matrix Gn×kUnit turns toFinally, willAs final random coded matrix Gn×k。
Present invention also offers a kind of RAID disaster tolerance reconstructing method based on random matrix, including: obtain
Take RECONFIGURATION REQUEST；Corresponding memory area, the random coded matrix prestored and coding is obtained according to described RECONFIGURATION REQUEST
Parameter；Judge whether each memory block in described memory area lost efficacy, if lost efficacy is original data block, then by its sequence number
Adding in inefficacy original data block sequence, otherwise lost efficacy is redundant block, then its sequence number is added inefficacy redundant data block sequence
In；If there being the original data block of inefficacy, then according to described random coded matrix, described inefficacy original data block sequence and do not lose
First the original data block of described inefficacy is reconstructed by the memory block of effect；Without the original data block lost efficacy, then basis
The redundant data block lost efficacy is entered by described random coded matrix, described inefficacy redundant data block sequence and all of original data block
Line reconstruction.
Preferably, if there being the data block of inefficacy, then according to described random coded matrix, described fail data block sequence and
The data block of described inefficacy is reconstructed and includes by the memory block not lost efficacy: choose all data not lost efficacy in memory area
Block；In described random coded matrix, extract the row corresponding with the described data block not lost efficacy and form new matrix G 's×k；Structure
Build encoding equtions group Gs'×k*αk×1=βs×1, wherein, α represents original data block vector, and β represents non-fail data block vector.Profit
The data of all fail data blocks of this memory area are tried to achieve by Gaussian reduction.
Preferably, without the original data block lost efficacy, then according to described random coded matrix, described inefficacy redundant block
The redundant data block lost efficacy is reconstructed and includes by sequence and all of original data block: directly utilize described random coded matrix
Row and all original data blocks of middle correspondence recompile, and generate all inefficacy redundant data blocks.
Present invention achieves the coding and decoding technology of a kind of novel RAID, be greatly enhanced by the program
The redundancy ability of storage system and autgmentability, improve the reliability of storage system, meanwhile, the storage efficiency of storage system and
Space availability ratio have also been obtained the biggest lifting.
Accompanying drawing explanation
Fig. 1 is the overall response flow chart of RAID storage and disaster tolerance method based on random matrix；
Fig. 2 is the code storage flow chart of RAID storage and disaster tolerance method based on random matrix；
Fig. 3 is the random coded matrix generation figure of RAID storage and disaster tolerance method based on random matrix；
Fig. 4 is the disaster tolerance reconstruct flow chart of RAID storage and disaster tolerance method based on random matrix；
Fig. 5 is the redundant block coding demonstration of RAID storage and disaster tolerance method based on random matrix；
Fig. 6 is the fail data block decoding demonstration of RAID storage and disaster tolerance method based on random matrix；
Fig. 7 is the demonstration of a memory area of RAID storage and disaster tolerance method based on random matrix.
Detailed description of the invention
Some symbols used in the present invention and concept first carry out some illustrate:
Disaster tolerance demand r: in customer requirement storage system, the memory block number of maximum allowable deletion accounts for the ratio of memory area.
Coding parameter: n presentation code informational capacity, k represents raw information amount, and δ represents random redundancy.
Redundancy ability t: the block number of maximum allowable deletion in memory area accounts for the ratio of whole memory area.
Crash rate s: in memory area, fail block number accounts for the ratio of whole memory area,
Memory area (Region): the memory area that file raw information to be deposited and coding redundancy information take altogether.Deposit
Storage area territory both can be on one disk, it is also possible to is on disk array, even by the different common structures of memory node
The one section of memory area built, therefore it is a concept in logic
Block (Block): memory area is divided into n part, every part of occupied memory area is expressed as one piece.There are two kinds of forms
Block, be original data block and redundant data block respectively.
Original data block: k block before in memory area, the initial data of file the to be deposited block filled.
Redundant data block: (n-k) individual block after in memory area, namely the block all filled by redundant data.
The core of the present invention is through encoder matrix G and original file data block, utilizes XOR, it is achieved memory block
The generation of redundant block in territory, and be filled in memory area by column, thus when reconstructing fail block, can be according to whole memory block
The failure conditions in territory, first carries out the reconstruct of inefficacy original data block, then carries out the reconstruct of inefficacy redundant data block, makes whole storage
The reconstruction property of system is fully played, and optimizes the utilization calculating resource, ensures the reliability of data to greatest extent, carry
Rise the reliability of storage system.
Refer to Fig. 1 to 7, the invention provides a kind of RAID disaster tolerance storage side based on random matrix
Method, comprises the following steps: build coding parameter according to the size of file to be stored；Described file to be stored is divided into k
According to block, not enough local zero padding；Obtain one section of memory area in storage system；Described memory area is divided into n storage
Block；Choosing front k the memory block of described memory area as original data storage block, remaining n-k memory block is as redundancy
DSB data store block；Described k is filled in described front k original data storage block by column according to block；According to described coding ginseng
Number is at the random coded matrix G that the upper structure scale of GF (2) is n × kn×k；According to described random coded matrix Gn×kAnd described k
Data block generates the redundant data block of described n-k memory block；Described n-k redundant data block is inserted by column described n-k
In memory block.Preferably, described memory area crosses over multiple different physical store nodes.
In one embodiment, it is assumed that a disk array comprises 20 pieces of hard disks, the file of a 200MB is currently had to need
Want code storage, it is desirable to the fault-tolerant ability of this document is more than 20%, and the most even blocks of files after coding has 100, wherein 20
Individual and when losing efficacy with next blocks of files, remain able to obtain this document.
Therefore, n=280 can be set, k=200, t=60, δ=20, at this moment, the fault-tolerant ability of this document reaches 21%, full
The fault-tolerant demand of foot.In this case, current embodiment require that the memory area of 280MB carries out file storage.
In order to improve the fault-tolerant ability of file substantially, the present embodiment chooses 14 pieces of hard disks, and is drawn by this memory area
Being divided into 280 pieces, each disk stores the data volume of 20MB, namely 20 blocks, every block size 1MB, then we are respectively often
Dividing the memory space of 20 blocks on individual disk, we carry out 1 to 280 numberings respectively to all pieces subsequently.The most whole storage
Region divides complete.
First, according to the coding and storing method of the storage system that the present invention is constructed, the code storage of file to be deposited is carried out.
We construct the 0-1 equally distributed random coded matrix G of 280 × 200 scalesn×k, and it is saved in the volume of this memory area
In code information.The file of this 200MB is divided into 200 parts by us, then chooses front 200 blocks of memory area as data block,
And file data blocks is filled into respectively in their front 200 original data storage blocks.We are subsequently according to random coded square
Battle array Gn×kAnd these 200 data blocks generate the data of rear 80 redundant blocks, finally it is filled in the memory area of correspondence.When all
After redundant block all encodes filling, then process terminates.
Preferably, the redundant digit of described n-k memory block is generated according to described random coded matrix and described k according to block
Include according to block: first, by described random coded matrix Gn×kLast n-k non-unity row in, often data corresponding to 1 in row
Block carries out XOR summation, thus obtains the redundant block that this row is corresponding；Then, the redundant block of described correspondence is filled to this row one
In the redundant data block caused.
Preferably, according to described coding parameter at the random coded matrix G that the upper structure scale of GF (2) is n × kn×kIncluding:
First, it is determined that described random coded matrix Gn×kWhether it is sequency spectrum, if not then reconfiguring described random coded matrix
Gn×k, until constructing the described random coded matrix G of sequency spectrumn×k；Secondly, by described random coded matrix Gn×kUnit turns toFinally, willAs final random coded matrix Gn×k。
Present invention also offers a kind of RAID disaster tolerance reconstructing method based on random matrix, including: obtain
Take RECONFIGURATION REQUEST；Corresponding memory area, the random coded matrix prestored and coding is obtained according to described RECONFIGURATION REQUEST
Parameter；Judge whether each memory block in described memory area lost efficacy, if lost efficacy is original data block, then by its sequence number
Adding in inefficacy original data block sequence, otherwise lost efficacy is redundant data block, then its sequence number is added inefficacy redundant data block
In sequence；If there being the original data block of inefficacy, then according to described random coded matrix, described inefficacy original data block sequence and
First the original data block of described inefficacy is reconstructed by the memory block not lost efficacy；Without the original data block lost efficacy, then
According to described random coded matrix, described inefficacy redundant data block sequence and all of original data block, the redundant block lost efficacy is entered
Line reconstruction.
Preferably, if there being the original data block of inefficacy, then according to described random coded matrix, described inefficacy initial data
The original data block of described inefficacy is reconstructed and includes by block sequence and the memory block not lost efficacy: choose owning in memory area
The data block not lost efficacy；In described random coded matrix, extract the row corresponding with the described data block not lost efficacy and form new
Matrix G 's×k；Build encoding equtions group Gs'×k*αk×1=βs×1, wherein, α represents original data block vector, and β represents non-failure number
According to block vector.Gaussian reduction is utilized to try to achieve the data of all fail data blocks of this memory area.
Preferably, without the original data block lost efficacy, then according to described random coded matrix, described inefficacy redundant digit
According to block sequence and all of original data block the redundant block lost efficacy is reconstructed and includes: directly utilize described random coded matrix
Row and all original data blocks of middle correspondence recompile, and generate all inefficacy redundant blocks.
Present invention achieves the coding and decoding technology of a kind of novel RAID, be greatly enhanced by the program
The redundancy ability of storage system and autgmentability, enhance the reliability of storage system, meanwhile, the storage efficiency of storage system and
Space availability ratio have also been obtained the biggest lifting.
Below in conjunction with Fig. 2 to Fig. 7, the committed step in the present invention is illustrated.
Fig. 2 is constructed the code storage of RAID storage and disaster tolerance method based on random matrix by the present invention
Flow chart.File block can be numbered by this flow process, and is saved in respectively in k original data block of memory area, produces simultaneously
Its corresponding redundant block data raw, it is achieved the disaster tolerance guarantee to file.Wherein, encoder matrix G is utilizedn×kFormer with the k having been filled with
Beginning data block, the step generating residue (n-k) individual redundant block is carried out as shown in Figure 5.
Fig. 5 is the coding demonstration of RAID storage and disaster tolerance method based on random matrix.Wherein equation is left
Limit string vertical bar be to be encoded be original file data block vector, on the right of equation for coding after gained coded data block vector,
Including original data block and redundant block two parts.As it is shown in figure 5, utilize random coded matrix G and the original document of upper unit
As original data block, produce coding redundancy block.Specific form due to random coded matrix so that coding has systematic code side
On the right of formula, namely equation, the front k block of encoding block is original file data, and rear (n-k) block is coding redundancy block.
Fig. 3 is constructed the random coded of RAID storage and disaster tolerance method based on random matrix by the present invention
Matrix generates figure.This flow process can construct the random coded matrix G that the upper scale of GF (2) is n × kn×k。
The disaster tolerance weight of the RAID storage and disaster tolerance method based on random matrix that Fig. 4 is constructed by the present invention
Structure flow chart.This flow process can utilize the block not lost efficacy in memory area, and crash rate s is not higher than the inefficacy feelings of redundancy ability t
Condition, it is achieved the reconstruct of fail block.Wherein, utilizing encoder matrix G, fail data block sequence and non-fail block, to memory area
In the process that is reconstructed of fail data block as shown in Figure 6.
Fig. 6 is the fail data block decoding demonstration of RAID storage and disaster tolerance method based on random matrix.
Assuming that we carry out the reconstruct of fail block in memory area, if all fail blocks are redundant data block, then we are the most sharp
With the original data block in encoder matrix G and memory area, recompile generation inefficacy redundant block.If fail block contains
There is original data block, then our row new matrix G' of composition that in extracting encoder matrix G, non-fail block is corresponding, utilize gaussian elimination
First method obtains all inefficacy original data blocks, and then recycling encoder matrix G and all original data blocks generate all inefficacies
Redundant block.As shown in Figure 6, delete in encoder matrix the row corresponding to fail block on the right of equation, produce new matrix, then
Using fail data block as unknown number, and utilizing non-fail block to build equation group, last solving equation group, solution of equations is mistake
The data block data of effect.
Deposit for one of the RAID storage and disaster tolerance method based on random matrix that Fig. 7 is constructed by the present invention
The demonstration in storage area territory, wherein the right vertical line dish is redundancy dish.This memory area is that individual data file is in whole storage system
Required memory area, it is also possible to regard a Stripe band as.
Claims (7)
1. RAID disaster tolerance based on a random matrix storage method, it is characterised in that including:
Size according to described file to be stored builds coding parameter；
Described file to be stored is divided into k according to block, not enough local zero padding；
Obtain one section of memory space in storage system；
Described memory space is divided into n memory block；
Choosing front k the memory block of described memory space as original data storage block, remaining n-k memory block is as redundancy
DSB data store block；
Described k is filled in described front k original data storage block by column according to block；
According to described coding parameter at the random coded matrix G that the upper structure scale of GF (2) is n × kn×k；
According to described random coded matrix Gn×kAnd described k generates the redundant data block of described n-k memory block according to block；
Described n-k redundant data block is inserted in described n-k memory block by column.
Method the most according to claim 1, it is characterised in that described memory space crosses over multiple different physical store joint
Point.
3. according to the method described in claim 1 and 2, it is characterised in that according to described random coded matrix and described k evidence
Block generates the redundant data block of described n-k memory block and includes:
First, by described random coded matrix Gn×kLast n-k non-unity row in, often in row, data block corresponding to 1 is carried out
XOR is sued for peace, thus obtains the redundant block that this row is corresponding；
Then, the redundant block of described correspondence is filled to the redundant data block consistent with this row.
4. according to the method described in claims 1 to 3, it is characterised in that construct scale according to described coding parameter on GF (2)
Random coded matrix G for n × kn×kIncluding:
First, it is determined that described random coded matrix Gn×kWhether it is sequency spectrum, if not then reconfiguring described random coded square
Battle array Gn×k, until constructing the described random coded matrix G of sequency spectrumn×k；
Secondly, by described random coded matrix Gn×kUnit turns to
Finally, willAs final random coded matrix Gn×k。
5. a RAID disaster tolerance reconstructing method based on random matrix, it is characterised in that
Obtain described RECONFIGURATION REQUEST；
Corresponding memory space, the random coded matrix prestored and coding parameter is obtained according to described RECONFIGURATION REQUEST；
Judge whether each memory block in described memory area lost efficacy, if lost efficacy is original data block, then by its sequence number
Adding in inefficacy original data block sequence, otherwise lost efficacy is redundant data block, then its sequence number is added inefficacy redundant data block
In sequence；
If there being the original data block of inefficacy, then according to described random coded matrix, described inefficacy original data block sequence and not
First the data block of described inefficacy is reconstructed by the memory block lost efficacy；
Without the original data block lost efficacy, then according to described random coded matrix, described inefficacy redundant data block sequence and
The redundant data block lost efficacy is reconstructed by all of original data block.
Method the most according to claim 5, it is characterised in that if there being the original data block of inefficacy, then according to described with
Machine encoder matrix, described inefficacy original data block sequence and the memory block not lost efficacy carry out weight to the original data block of described inefficacy
Structure includes:
Choose all data blocks not lost efficacy in memory space；
In described random coded matrix, extract the row corresponding with the described data block not lost efficacy and form new matrix G 's×k；
Build encoding equtions group G's×k*αk×1=βs×1, wherein, α represent original data block vector, β represent non-fail data block to
Amount.
Gaussian reduction is utilized to try to achieve the data of all inefficacy original data blocks of this memory space.
Method the most according to claim 5, it is characterised in that without the original data block lost efficacy, then according to described
The redundant block lost efficacy is reconstructed and includes by random coded matrix, described inefficacy redundant block sequence and all of original data block:
Directly utilize row corresponding in described random coded matrix and all original data blocks recompile, generate all inefficacies superfluous
Remaining block.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610089410.7A CN105786656B (en) | 2016-02-17 | 2016-02-17 | Redundant array of independent disks disaster tolerance storage method based on random matrix |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610089410.7A CN105786656B (en) | 2016-02-17 | 2016-02-17 | Redundant array of independent disks disaster tolerance storage method based on random matrix |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105786656A true CN105786656A (en) | 2016-07-20 |
| CN105786656B CN105786656B (en) | 2019-08-13 |
Family
ID=56402274
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610089410.7A Active CN105786656B (en) | 2016-02-17 | 2016-02-17 | Redundant array of independent disks disaster tolerance storage method based on random matrix |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105786656B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106339975A (en) * | 2016-10-10 | 2017-01-18 | 中科院成都信息技术股份有限公司 | Digital image secret sharing method, restoration method and devices |
| CN106383669A (en) * | 2016-09-19 | 2017-02-08 | 渤海大学 | Distributed storage method and system based on (n,k,m) coding |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1796001A2 (en) * | 1999-03-03 | 2007-06-13 | Yotta Yotta, Inc. | Method for implementing shared disk array management functions. |
| CN101231891A (en) * | 2007-01-04 | 2008-07-30 | 国际商业机器公司 | Error control method and memory system |
| CN101340193A (en) * | 2008-08-12 | 2009-01-07 | 普天信息技术研究院有限公司 | Constructing method, encoder and decoder of low density check code |
| CN101387975A (en) * | 2008-10-20 | 2009-03-18 | 中科院成都信息技术有限公司 | Magnetic disc array system |
| CN101834898A (en) * | 2010-04-29 | 2010-09-15 | 中科院成都信息技术有限公司 | Method for storing network distributed codes |
| US20130173955A1 (en) * | 2012-01-04 | 2013-07-04 | Xtremlo Ltd | Data protection in a random access disk array |
| JP2013152778A (en) * | 2013-02-28 | 2013-08-08 | Qualcomm Inc | Concurrent multiple-dimension word-addressable memory architecture |
| US20140250269A1 (en) * | 2013-03-01 | 2014-09-04 | Lsi Corporation | Declustered raid pool as backup for raid volumes |
-
2016
- 2016-02-17 CN CN201610089410.7A patent/CN105786656B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1796001A2 (en) * | 1999-03-03 | 2007-06-13 | Yotta Yotta, Inc. | Method for implementing shared disk array management functions. |
| CN101231891A (en) * | 2007-01-04 | 2008-07-30 | 国际商业机器公司 | Error control method and memory system |
| CN101340193A (en) * | 2008-08-12 | 2009-01-07 | 普天信息技术研究院有限公司 | Constructing method, encoder and decoder of low density check code |
| CN101387975A (en) * | 2008-10-20 | 2009-03-18 | 中科院成都信息技术有限公司 | Magnetic disc array system |
| CN101834898A (en) * | 2010-04-29 | 2010-09-15 | 中科院成都信息技术有限公司 | Method for storing network distributed codes |
| US20130173955A1 (en) * | 2012-01-04 | 2013-07-04 | Xtremlo Ltd | Data protection in a random access disk array |
| US8799705B2 (en) * | 2012-01-04 | 2014-08-05 | Emc Corporation | Data protection in a random access disk array |
| JP2013152778A (en) * | 2013-02-28 | 2013-08-08 | Qualcomm Inc | Concurrent multiple-dimension word-addressable memory architecture |
| US20140250269A1 (en) * | 2013-03-01 | 2014-09-04 | Lsi Corporation | Declustered raid pool as backup for raid volumes |
Non-Patent Citations (1)
| Title |
|---|
| 肖宜龙: "《随机化数据冗余方法及其在存储系统中的应用》", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106383669A (en) * | 2016-09-19 | 2017-02-08 | 渤海大学 | Distributed storage method and system based on (n,k,m) coding |
| CN106383669B (en) * | 2016-09-19 | 2019-04-16 | 渤海大学 | Distributed storage method and system of the one kind based on (n, k, m) coding |
| CN106339975A (en) * | 2016-10-10 | 2017-01-18 | 中科院成都信息技术股份有限公司 | Digital image secret sharing method, restoration method and devices |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105786656B (en) | 2019-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106100801B (en) | A kind of non-homogeneous erasure code method of cloud storage system | |
| CN105260259B (en) | A kind of locality based on system minimum memory regeneration code repairs coding method | |
| TWI361348B (en) | Parity engine for use in storage virtualization controller and methods of generating data by parity engine | |
| CN107656832B (en) | A kind of correcting and eleting codes method of low data reconstruction expense | |
| CN101834898B (en) | Method for storing network distributed codes | |
| CN109643258B (en) | Multi-node repair using high-rate minimal storage erase code | |
| Li et al. | A generic transformation for optimal repair bandwidth and rebuilding access in MDS codes | |
| CN103746774B (en) | The fault-tolerant coding method that a kind of efficient data is read | |
| CN107844272A (en) | A kind of cross-packet coding and decoding method for improving error correcting capability | |
| US20210271557A1 (en) | Data encoding, decoding and recovering method for a distributed storage system | |
| US20120023362A1 (en) | System and method for exact regeneration of a failed node in a distributed storage system | |
| CN106484559A (en) | A kind of building method of check matrix and the building method of horizontal array correcting and eleting codes | |
| CN110089035B (en) | Storage controller, data processing chip and data processing method | |
| CN103412799B (en) | Data reconstruction method, data recovery apparatus and distributed memory system | |
| CN103761171B (en) | A kind of low bandwidth data reconstructing method for binary coding redundant storage system | |
| CN104052576A (en) | Data recovery method based on error correcting codes in cloud storage | |
| CN106776129A (en) | A kind of restorative procedure of the multinode data file based on minimum memory regeneration code | |
| CN102012792A (en) | Quick reconfigurable RAID-6 coding and reconfiguration method | |
| CN110383251A (en) | Storage system, computer readable recording medium, the control method of system | |
| CN107689983B (en) | Cloud storage system and method based on low repair bandwidth | |
| CN103593260B (en) | The guard method of a kind of metadata and device | |
| CN102843212B (en) | Coding and decoding processing method and device | |
| CN103106124A (en) | Intersection reconstruction method based on erasure code cluster memory system | |
| CN113391946B (en) | Coding and decoding method for erasure codes in distributed storage | |
| CN108228382A (en) | A kind of data reconstruction method for EVENODD code single-deck failures |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |