CN108228382A - A kind of data reconstruction method for EVENODD code single-deck failures - Google Patents
A kind of data reconstruction method for EVENODD code single-deck failures Download PDFInfo
- Publication number
- CN108228382A CN108228382A CN201810027966.2A CN201810027966A CN108228382A CN 108228382 A CN108228382 A CN 108228382A CN 201810027966 A CN201810027966 A CN 201810027966A CN 108228382 A CN108228382 A CN 108228382A
- Authority
- CN
- China
- Prior art keywords
- data
- disk
- redundancy
- fault
- evenodd
- 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
- G06F11/08—Error detection or correction by redundancy in data representation, e.g. by using checking codes
- G06F11/10—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's
- G06F11/1076—Parity data used in redundant arrays of independent storages, e.g. in RAID systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Techniques For Improving Reliability Of Storages (AREA)
- Signal Processing For Digital Recording And Reproducing (AREA)
Abstract
The invention discloses a kind of data reconstruction methods for EVENODD code single-deck failures, belong to computerized information storage and recovery technology field.This method is on the basis of existing EVENODD codings, to including the EVENODD of p data disk, take it is therein beforeA data disk carries out exclusive or calculating, the result of exclusive or is saved in a new redundancy magnetic disk, which is defined as local redundancy disk；When data disk breaks down, then corresponding data recovery is carried out according to the location of data disk；When redundancy magnetic disk breaks down, then corresponding data recovery is carried out according to the type of redundancy magnetic disk.This method utilizes newly-increased local redundancy disk so that number of disks relevant with single data disk is reduced.Data reduce the number of disk reading when restoring, digital independent expense is small, and data recovering efficiency is high, are a kind of better than traditional EVENODD code single-deck failure recovering algorithms.
Description
Technical field
The present invention relates to computerized information storage and recovery technology fields, more particularly to a kind of to be directed to EVENODD code single-decks
The data recovering algorithms of failure.
Background technology
In recent years, with the fast development of society and science and technology, the data volume in database is just increased with astonishing speed,
Therefore the scale of storage system also increasingly increases.And with the increase of scale, the stability problem encountered of storage system
Gradually increase.Being continuously increased with number of disks is mainly manifested in, the probability of loss of data caused by disk failure also exists
Increase.Even and if still remained intact to ensure data after disk failures, it is necessary to which data are restored.Therefore,
Time and the recovery process required data volume read that data are restored just become the key of system stability.
Document【EVENODD:an effcient scheme for tolerating double disk failures
in RAID architectures】The EVENODD codes of proposition are more common a kind of arrays for holding two mistakes in storage system
Code.Its principle is mainly to ensure the integrality of data by increasing by two additional redundancy magnetic disks.EVENODD codes can be in office
Initial data is still correctly recovered after two data disk failures of meaning.For EVENODD codings, advantage exists
In simple in structure, coding and decoding process is based on XOR operation, thus speed is quickly.But one of its major defect is exactly single-deck failure
The overabundance of data read needed for restoring needs to read the former data of all residues, and data read time is longer, data recovering efficiency
It is relatively low.
Invention content
It is extensive the technical problem to be solved by the present invention is to be directed to existing EVENODD codes single-deck fault data based on described above
The multiple time is long, restores the low deficiency of efficiency, provide it is a kind of it is new for EVENODD code single-deck failures when data reconstruction method,
The storage overhead of the algorithm slightly larger than tradition EVENODD encode, but the reading expense of single-deck fault recovery be only about it is existing
The 50% of EVENODD codings, data recovery time is short, restores efficient.
The whole principle of data reconstruction method of the present invention is：On the basis of EVENODD codings, take therein
BeforeA data disk carries out exclusive or calculating, the result of exclusive or is saved in a new redundancy magnetic disk, the new redundancy
Disc Definition is local redundancy disk.When data fault occurs for single disk, phase is carried out according to the position of failed disk or type
The data answered are restored.I.e. if data disk breaks down, then corresponding data are carried out according to the location of data disk
Restore；If redundancy magnetic disk breaks down, then corresponding data recovery is carried out according to the type of redundancy magnetic disk.
Data reconstruction method step of the present invention is：
(1) first to comprising p data disk and two redundancy magnetic disk EVENODD coding, take it is therein beforeIt is a
Data disk carries out exclusive or calculating, wherein, p is the number of data disk, and p values are prime number, and two redundancy magnetic disks are water respectively
Flat redundancy magnetic disk and diagonal redundancy magnetic disk；
(2) result of exclusive or is saved in a new redundancy magnetic disk, which is defined as local redundancy disk,
Calculation formula is as follows：
ai,jFor the data block in the disk array, i, j are the ranks coordinate of the data block；
(3) it when data fault (loss of data) occurs for individual data disk, is carried out according to the position of fault data disk
Fault recovery；
(4) when data fault (loss of data) occurs for single redundancy magnetic disk, event is carried out according to fault redundance disk type
Barrier restores.
Specifically, above-mentioned steps (3) the specific steps are：
1. first determining whether to occur the data disk position of data fault, situation can be divided into before failure is happened atNumber
According to disk with afterA two kinds of situations of data disk；
Before 2. the data disk in case of data fault is located atIn a data disk, then before readingA disk
In the data of intact disk and local redundancy disk, carry out exclusive or calculating, obtained data are that data fault disk occurs
Data, if the data disk of data fault occurs as e, it is as follows that data restore formula；
ai,jFor the data block in the disk array, i, j are the ranks coordinate of the data block；
3. if it happens the data disk of data fault is rearIn a disk, then read rearA data magnetic
The data of intact disk and horizontal redundancy disk and local redundancy magnetic disk in disk, carry out exclusive or calculating, and obtained data are
The data disk of data fault disk occurs, if the data disk that data fault occurs is e, it is as follows that data restore formula：
ai,jFor the data block in the disk array, i, j are the ranks coordinate of the data block
Specifically, above-mentioned steps (4) the specific steps are：
1. first determining whether the redundancy magnetic disk type to break down, it is divided into three kinds of situations：
2. the disk in case of data fault is horizontal redundancy disk, then after readingA data disk and part are superfluous
The data of residual magnetism disk carry out exclusive or calculating, and obtained data are that the horizontal redundancy data in magnetic disk of data fault occurs, and data are extensive
Multiple formula is as follows：
ai,jFor the data block in the disk array, i, j are the ranks coordinate of the data block；
3. what it is in case of data fault is diagonal redundancy magnetic disk, then needs to read the data in all data disks and carry out
Exclusive or calculates, and calculation formula is as follows：
ai,jFor the data block in the disk array, i, j are the ranks coordinate of the data block；
4. what it is in case of data fault is local redundancy disk, then before readingA data disk carries out exclusive or meter
It calculates, obtained data are that the local redundancy data in magnetic disk of data fault occurs, formula in the same above-mentioned steps of calculation formula (2),
Specifically：
ai,jFor the data block in the disk array, i, j are the ranks coordinate of the data block
This method utilizes newly-increased local redundancy disk so that number of disks relevant with single data disk is reduced.It should
Recovery algorithms reduce the number of disk reading, the time and are spatially superior to traditional EVENODD single-deck failure recovering algorithms.
In general, data reconstruction method can read four expense, system stability, correctness sides from storage overhead, recovery
Overall merit is carried out in face.Storage overhead can be obtained by comparing the size needed for encoding, although this algorithm is more compared with existing EVENODD
A redundant columns (local redundancy disk) are increased, but the value of p is often larger in practice, increased storage overhead almost may be used
To ignore；Restore to read the blocks of files number that can read needed for recovery same type mistake of expense index to observe
Go out, since the probability that data disk breaks down is more than the probability that redundancy magnetic disk breaks down, it may be said that be to be far longer than, work as p
When tending to be infinite, single-deck failure expense levels off toTherefore, the present invention, which reads expense and can theoretically reduce by 50% reading, opens
Pin restores efficient.System stability in disk array is often depending on single-deck failure recovery time, and data recovery time gets over
It is short, it is meant that the probability for generating multiple mistakes is lower；Due to reducing the number of data blocks of reading, the recovery time of this algorithm
Also it is minimized, therefore system stability increases；Finally since the preceding p+2 of this algorithm row remain EVENODD codings, because
This can also restore any two mistake, ensure that decoded correctness.Therefore data fault restoration methods proposed by the present invention
It is extremely excellent.
By the above method it is found that the beneficial effects of the invention are as follows：
1st, it is excessively high to solve the problems, such as that expense is read in existing EVENODD codes single-deck fault recovery；The present invention is to be based on
The improvement of EVENODD single-deck fault recoveries, EVENODD coding methods are that a kind of algorithm is simple, and efficiency of the operation based on exclusive or is very
High coding mode.But EVENODD but there are one it is more notable the shortcomings that, for single disk failures, when restoring
It needs to use whole data, it is very big to read expense.Data reconstruction method proposed by the invention, due to adding in local redundancy magnetic
Disk so that the single relevant number of disks of data disks is reduced to half, effectively reduces reading expense.
2nd, the stability of system entirety is improved；Most of disk failure is all single-deck event in array storage system
Barrier, and system stability is dependent on the recovery time of single-deck failure with reading expense.Data recovery side proposed by the invention
Method participates in the disk number of operation due to reducing, not only reduces reading expense, also save operation time, into one
Step improves the efficiency of recovery, and then improves the stability of system entirety indirectly.
Description of the drawings
Fig. 1 is existing EVENODD (5,7) coding disk array model schematics；
Fig. 2 is horizontal redundancy disk and to diagonal redundancy magnetic disk data algorithm schematic diagram in Fig. 1：
Fig. 3 is improved EVENODD (5,7) the coding disk array model schematic of the present invention；
Structure when Fig. 4 is first data disk generation data fault in EVENODD (5,7) coding disk array models
Schematic diagram；
Structure when Fig. 5 is third data disk generation data fault in EVENODD (5,7) coding disk array models
Schematic diagram；
Structural representation when Fig. 6 is horizontal redundancy disk failures in EVENODD (5,7) coding disk array models
Figure；
Specific embodiment
The embodiment of the present invention is described in detail below in conjunction with the accompanying drawings.
Embodiment described in the invention is only the section Example rather than whole embodiments of the present invention.For the ease of
It describes, part related to the present invention rather than full content is only shown in attached drawing.
Data fault described in following embodiments is also referred to as loss of data, all data event that this specification occurs
Barrier, loss of data paraphrase are identical；Similarly, failure is also identical with losing paraphrase.
The present invention is used as reference to illustrate with existing EVENODD (5,7) structure, which contains 5
Data disk, i.e. p=5；2 redundancy magnetic disks, 2 redundancy magnetic disks are horizontal redundancy disk and diagonal redundancy magnetic disk respectively.
In general, p value value is larger, often more than 100, working method of the invention for ease of description, in the present embodiment
Only illustrate by taking p=5 as an example, when p is other values, working method can refer to the embodiment of p=5.
Referring to Fig. 1~2, Fig. 1 is existing EVENODD (5,7) disc array structure schematic diagram, and Fig. 2 is that corresponding algorithm shows
It is intended to；Disk0~Disk4 is the data disk of 5 combination arrays together, and Disk5~Disk6 is really tired out for 2 combinations one
The redundancy magnetic disk risen, wherein, Disk5 is horizontal redundancy disk, and Disk6 is diagonal redundancy magnetic disk.
The data algorithm of horizontal redundancy disk is
Diagonally the data algorithm of redundancy magnetic disk is
Wherein,
I=0,1...3；
ai,jFor the data block in the disk array, i, j are the ranks coordinate of the data block.
Fig. 3 is improved EVENODD (5,7) the disc array structure schematic diagram of the present invention, compared to Figure 1, it is known that, it improves
EVENODD (5,7) disk array afterwards increases a redundancy magnetic disk, i.e., in existing level redundancy magnetic disk and diagonal redundancy magnetic disk
On the basis of increase a local redundancy disk, that is to say the Disk7 shown in Fig. 3.
The data of local redundancy disk carry out exclusive or calculating by the data in preceding 2 data disks, that is to say utilization
Data in Disk0 and Disk1 carry out exclusive or；
Calculation formula is：
I=0,1...3.
Referring to Fig. 4, in the attached drawing, × represent that data fault occurs, Ο represents that data are intact.When first 2 in disk array
First data disk in data disk when data fault occurs for Disk0, then reads second data disk and local redundancy
The data of disk, that is, the data read in Disk1 and Disk7 carry out exclusive or, so as to recover the loss data in Disk0；
Data restore formula：
Referring to Fig. 5, in the attached drawing, × represent that data fault occurs, Ο represents that data are intact.3 after in disk array
Third data disk in data disk when data fault occurs for i.e. Disk2, first reads the data in Disk3, Disk4, so
Data in read level redundancy magnetic disk and local redundancy magnetic disk, i.e. data in Disk5 and Disk7 again afterwards, will be read
Data carry out exclusive or calculating, so as to recover the loss data in Disk2；
Data restore formula：
Referring to Fig. 6, in the attached drawing, × represent that data fault occurs, Ο represents that data are intact, when data occur for redundancy magnetic disk
During failure, first determine whether that the type of the redundancy magnetic disk of data fault occurs；
If data fault occurs for horizontal redundancy disk, i.e. data fault occurs for Disk5,3 data magnetic after first reading
Data in data in disk, i.e. Disk2, Disk3 and Disk4, then read data in local redundancy disk, i.e. number in Disk7
According to by the progress exclusive or calculating of read data.So as to recover the loss data in Disk5；
Data restore formula：
If data fault occurs for diagonal redundancy magnetic disk, i.e. when data fault occurs for Disk6, according to existing EVENODD
(5,7) array structure model carries out exclusive or calculating, due to this part and existing calculating indistinction.Here formula is saved.In general, by
Larger in p value, the probability that data fault occurs for diagonal redundancy magnetic disk is extremely low, and therefore, the situation application which restores is seldom, and one
Denier occurs, and exclusive or calculating is carried out according to existing EVENODD (5,7) model.
If data fault occurs for local redundancy disk, i.e. when data fault occurs for Disk7, then 2 data before reading
Data in data in disk, i.e. Disk0 and Disk1 carry out exclusive or calculating；
Data restore formula：
I=0,1...3
Above-described embodiment shows only the situation of p=5, since the value of p is usually larger, can not enumerate multiple typical cases
Embodiment, it is believed that above-described embodiment is presently preferred embodiments of the present invention and not all embodiments, as long as without wound
The technical solution that the property made labour can be realized on the basis of above-described embodiment, the right for being regarded as falling into patent of the present invention are protected
In the range of shield.
Claims (4)
1. a kind of data reconstruction method for EVENODD code single-deck failures, which is characterized in that include the following steps：
(1), the EVENODD comprising p data disk and two redundancy magnetic disks is encoded, take it is therein beforeA data magnetic
Disk carries out exclusive or calculating, wherein, p is prime number, and two redundancy magnetic disks are horizontal redundancy disk and diagonal redundancy magnetic disk respectively；
(2), the result of step (1) exclusive or is saved in a new redundancy magnetic disk, which is defined as local redundancy magnetic
Disk；
(3), when data fault occurs for individual data disk, data fault recovery is carried out according to the position of fault data disk；
(4), when data fault occurs for single redundancy magnetic disk, data fault recovery is carried out according to the type of fault redundance disk.
A kind of 2. data reconstruction method for EVENODD code single-deck failures as described in claim 1, which is characterized in that institute
It states the probability that data disk breaks down and is more than the probability that redundancy magnetic disk breaks down.
3. a kind of data reconstruction method for EVENODD code single-deck failures as described in claim 1, it is characterised in that：Institute
It states step and (3) includes following sub-step：
1. first determining whether to occur the data disk position of data fault, situation is divided into before data fault is happened atA data
Disk is with afterA two kinds of situations of data disk；
Before 2. the data disk in case of data fault is located atIn a data disk, then before readingA data disk
In the data of intact data disk and local redundancy disk, carry out exclusive or calculating, obtained data are that data fault occurs
The data of disk；
After 3. the data disk in case of data fault is located atIn a data disk, then after readingA data disk
In the data of intact data disk and horizontal redundancy disk and local redundancy magnetic disk, carry out exclusive or calculating, obtained data are i.e.
For the data of data fault disk occur.
4. a kind of data reconstruction method for EVENODD code single-deck failures as described in claim 1, it is characterised in that：Institute
It states step and (4) includes following sub-step：
1. first determine whether the redundancy magnetic disk type to break down, point three kinds of situations；
2. the disk in case of data fault is horizontal redundancy disk, then after readingA data disk and local redundancy
Data in disk carry out exclusive or calculating, and obtained data are that the horizontal redundancy data in magnetic disk of data fault occurs；
3. the disk in case of data fault is diagonal redundancy magnetic disk, then the data read in all data disks carry out exclusive or
It calculates；, obtained data are that the diagonal redundancy magnetic disk data of data fault occur；
4. what it is in case of data fault is local redundancy disk, then before readingA data disk carries out exclusive or calculating, obtains
To data be the local redundancy data in magnetic disk that breaks down.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810027966.2A CN108228382B (en) | 2018-01-11 | 2018-01-11 | Data recovery method for single-disk fault of EVENODD code |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810027966.2A CN108228382B (en) | 2018-01-11 | 2018-01-11 | Data recovery method for single-disk fault of EVENODD code |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108228382A true CN108228382A (en) | 2018-06-29 |
| CN108228382B CN108228382B (en) | 2021-08-10 |
Family
ID=62640197
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810027966.2A Active CN108228382B (en) | 2018-01-11 | 2018-01-11 | Data recovery method for single-disk fault of EVENODD code |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108228382B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111143108A (en) * | 2019-12-09 | 2020-05-12 | 成都信息工程大学 | Encoding and decoding method and device for reducing array code Xcode repair |
| CN111475329A (en) * | 2020-02-25 | 2020-07-31 | 成都信息工程大学 | Method and device for reducing predictive erasure code repair under big data application platform |
| CN111679793A (en) * | 2020-06-16 | 2020-09-18 | 成都信息工程大学 | Single-disk fault rapid recovery method based on STAR code |
| US11038533B2 (en) | 2019-04-25 | 2021-06-15 | International Business Machines Corporation | Expansion for generalized EVENODD codes |
| CN113094213A (en) * | 2021-05-07 | 2021-07-09 | 河北工业大学 | GPyramid-Code layout and data recovery and storage method for single-disk failure of layout |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1454349A (en) * | 2000-06-07 | 2003-11-05 | 处理存储器有限公司 | A method and system for highly-parallel logging and recovery operation in main-memory transaction processing systems |
| CN1670682A (en) * | 2004-03-15 | 2005-09-21 | 华为技术有限公司 | A data reintegration method |
| CN1906592A (en) * | 2003-07-14 | 2007-01-31 | 国际商业机器公司 | Redundancy in array storage system |
| 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 |
| TWI310497B (en) * | 2004-02-06 | 2009-06-01 | Hon Hai Prec Ind Co Ltd | System and method for disk fault tolerance |
| US20100083069A1 (en) * | 2008-06-18 | 2010-04-01 | John Johnson Wylie | Selecting Erasure Codes For A Fault Tolerant System |
| CN101770413A (en) * | 2010-01-07 | 2010-07-07 | 杭州华三通信技术有限公司 | Method and equipment for rebuilding redundant disk array |
| CN101980137A (en) * | 2010-10-19 | 2011-02-23 | 成都市华为赛门铁克科技有限公司 | Method, device and system for reconstructing redundant array of inexpensive disks |
| CN102023819A (en) * | 2010-12-01 | 2011-04-20 | 北京同有飞骥科技股份有限公司 | Method for constructing double-disk fault tolerance horizontal grouping and parallel access disk array |
| CN102081559A (en) * | 2011-01-11 | 2011-06-01 | 成都市华为赛门铁克科技有限公司 | Data recovery method and device for redundant array of independent disks |
| CN103365739A (en) * | 2013-08-02 | 2013-10-23 | 深圳市瑞耐斯技术有限公司 | NAND flash memory equipment and data recovery method thereof |
| CN103744750A (en) * | 2014-01-13 | 2014-04-23 | 杭州华为数字技术有限公司 | Method and device for recovering data |
| CN104765660A (en) * | 2015-04-24 | 2015-07-08 | 中国人民解放军国防科学技术大学 | Single-disc quick recovery method machine based on RAID6 of SSD |
| CN106155847A (en) * | 2016-08-19 | 2016-11-23 | 浪潮(北京)电子信息产业有限公司 | A kind of disk array |
| KR101756136B1 (en) * | 2016-01-22 | 2017-07-26 | 계명대학교 산학협력단 | A fault tolerant method for a hierarchical system |
-
2018
- 2018-01-11 CN CN201810027966.2A patent/CN108228382B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1454349A (en) * | 2000-06-07 | 2003-11-05 | 处理存储器有限公司 | A method and system for highly-parallel logging and recovery operation in main-memory transaction processing systems |
| CN1906592A (en) * | 2003-07-14 | 2007-01-31 | 国际商业机器公司 | Redundancy in array storage system |
| TWI310497B (en) * | 2004-02-06 | 2009-06-01 | Hon Hai Prec Ind Co Ltd | System and method for disk fault tolerance |
| CN1670682A (en) * | 2004-03-15 | 2005-09-21 | 华为技术有限公司 | A data reintegration method |
| US20100083069A1 (en) * | 2008-06-18 | 2010-04-01 | John Johnson Wylie | Selecting Erasure Codes For A Fault Tolerant System |
| 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 |
| CN101770413A (en) * | 2010-01-07 | 2010-07-07 | 杭州华三通信技术有限公司 | Method and equipment for rebuilding redundant disk array |
| CN101980137A (en) * | 2010-10-19 | 2011-02-23 | 成都市华为赛门铁克科技有限公司 | Method, device and system for reconstructing redundant array of inexpensive disks |
| CN102023819A (en) * | 2010-12-01 | 2011-04-20 | 北京同有飞骥科技股份有限公司 | Method for constructing double-disk fault tolerance horizontal grouping and parallel access disk array |
| CN102081559A (en) * | 2011-01-11 | 2011-06-01 | 成都市华为赛门铁克科技有限公司 | Data recovery method and device for redundant array of independent disks |
| CN103365739A (en) * | 2013-08-02 | 2013-10-23 | 深圳市瑞耐斯技术有限公司 | NAND flash memory equipment and data recovery method thereof |
| CN103744750A (en) * | 2014-01-13 | 2014-04-23 | 杭州华为数字技术有限公司 | Method and device for recovering data |
| CN104765660A (en) * | 2015-04-24 | 2015-07-08 | 中国人民解放军国防科学技术大学 | Single-disc quick recovery method machine based on RAID6 of SSD |
| KR101756136B1 (en) * | 2016-01-22 | 2017-07-26 | 계명대학교 산학협력단 | A fault tolerant method for a hierarchical system |
| CN106155847A (en) * | 2016-08-19 | 2016-11-23 | 浪潮(北京)电子信息产业有限公司 | A kind of disk array |
Non-Patent Citations (2)
| Title |
|---|
| 萧枫 等: "一种低单盘故障恢复开销的局部修复码", 《计算机工程与应用》 * |
| 项利萍: "RAID-6 存储系统中故障修复问题研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11038533B2 (en) | 2019-04-25 | 2021-06-15 | International Business Machines Corporation | Expansion for generalized EVENODD codes |
| CN111143108A (en) * | 2019-12-09 | 2020-05-12 | 成都信息工程大学 | Encoding and decoding method and device for reducing array code Xcode repair |
| CN111143108B (en) * | 2019-12-09 | 2023-05-02 | 成都信息工程大学 | Coding and decoding method and device for reducing array code Xcode repair |
| CN111475329A (en) * | 2020-02-25 | 2020-07-31 | 成都信息工程大学 | Method and device for reducing predictive erasure code repair under big data application platform |
| CN111475329B (en) * | 2020-02-25 | 2023-07-18 | 成都信息工程大学 | Method and device for reducing predictive erasure code repair under big data application platform |
| CN111679793A (en) * | 2020-06-16 | 2020-09-18 | 成都信息工程大学 | Single-disk fault rapid recovery method based on STAR code |
| CN111679793B (en) * | 2020-06-16 | 2023-03-14 | 成都信息工程大学 | Single-disk fault rapid recovery method based on STAR code |
| CN113094213A (en) * | 2021-05-07 | 2021-07-09 | 河北工业大学 | GPyramid-Code layout and data recovery and storage method for single-disk failure of layout |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108228382B (en) | 2021-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108228382A (en) | A kind of data reconstruction method for EVENODD code single-deck failures | |
| CN102270161B (en) | Methods for storing, reading and recovering erasure code-based multistage fault-tolerant data | |
| KR100985444B1 (en) | Data storage array | |
| CN102012792B (en) | Quick reconfigurable RAID-6 coding and reconfiguration method | |
| US8489916B2 (en) | Multi-disk fault-tolerant system, method for generating a check block, and method for recovering a data block | |
| CN105956128B (en) | A kind of adaptive coding storage fault-tolerance approach based on simple regeneration code | |
| CN110442535B (en) | Method and system for improving reliability of distributed solid-state disk key value cache system | |
| CN109086000B (en) | Three-fault-tolerant data layout method in RAID storage system | |
| CN103761195B (en) | Storage method utilizing distributed data encoding | |
| KR19990010106A (en) | Method and apparatus for data storage in parity storage and disk failure in external storage subsystem | |
| CN101834898A (en) | Method for storing network distributed codes | |
| CN108347306B (en) | Similar local reconstruction code encoding and node fault repairing method in distributed storage system | |
| CN103593260B (en) | The guard method of a kind of metadata and device | |
| US20100138717A1 (en) | Fork codes for erasure coding of data blocks | |
| CN115080303B (en) | Encoding method, decoding method, device and medium for RAID6 disk array | |
| CN112000512B (en) | Data restoration method and related device | |
| CN104268031B (en) | It is a kind of to be used for the erasure codes collocation method of solid state hard disc in disk array storage system | |
| CN111459710A (en) | Erasure code memory recovery method, device and memory system capable of sensing heat degree and risk | |
| CN104866243A (en) | RAID-6 transverse and oblique check encoding and decoding method for optimizing input/output load | |
| CN116501553B (en) | Data recovery method, device, system, electronic equipment and storage medium | |
| CN105630417A (en) | RAID5 (Redundant Array Of Independent Disks) system and method for continuously writing data after failure of RAID5 system | |
| CN110268397B (en) | Efficient optimized data layout method applied to data warehouse system | |
| CN107977285A (en) | A kind of data modification method, device and the medium of correcting and eleting codes memory mechanism | |
| CN115562594B (en) | Method, system and related device for constructing RAID card | |
| CN106911793B (en) | I/O optimized distributed storage data repair method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |