CN106528342A - Disk array fault tolerance apparatus with cloud server backup function - Google Patents
Disk array fault tolerance apparatus with cloud server backup function Download PDFInfo
- Publication number
- CN106528342A CN106528342A CN201610992459.3A CN201610992459A CN106528342A CN 106528342 A CN106528342 A CN 106528342A CN 201610992459 A CN201610992459 A CN 201610992459A CN 106528342 A CN106528342 A CN 106528342A
- Authority
- CN
- China
- Prior art keywords
- unit
- band
- disk
- data
- disk array
- 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.)
- Pending
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
- G06F11/14—Error detection or correction of the data by redundancy in operation
- G06F11/1402—Saving, restoring, recovering or retrying
- G06F11/1446—Point-in-time backing up or restoration of persistent data
- G06F11/1456—Hardware arrangements for backup
-
- 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
- G06F11/14—Error detection or correction of the data by redundancy in operation
- G06F11/1402—Saving, restoring, recovering or retrying
- G06F11/1446—Point-in-time backing up or restoration of persistent data
- G06F11/1448—Management of the data involved in backup or backup restore
-
- 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
- G06F11/14—Error detection or correction of the data by redundancy in operation
- G06F11/1402—Saving, restoring, recovering or retrying
- G06F11/1446—Point-in-time backing up or restoration of persistent data
- G06F11/1458—Management of the backup or restore process
- G06F11/1464—Management of the backup or restore process for networked environments
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)
Abstract
The present invention discloses a disk array fault tolerance apparatus with a cloud server backup function. The apparatus comprises a replacement unit, a rebuilding unit, a recording unit, a processing unit, a repairing unit, and a recovering unit. The recording unit is connected with the rebuilding unit, the processing unit, the repairing unit, and the recovering unit. The recording unit is connected with a cloud server backup storage by using a connection device. The rebuilding unit is connected with the replacement unit. A rebuilding read error of a strip is repaired by using a write method, and the redundancy of the disk array is recovered as soon as possible, so that failure of the whole disk array due to faults of multiple disks in rebuilding is prevented. The apparatus has the cloud server backup function. When a local disk has an irreparable fault, backup data can be recovered from the storage of the cloud server.
Description
Technical field：
The present invention relates to it is related to disk storage system field, specifically a kind of fault-tolerant dress of disk array with Cloud Server backup
Put.
Background technology：
RAID, abbreviation disk array, multiple independent disks are combined into an array by which, there is provided well
Redundancy and the storage performance higher than single disk.In field of storage, by the redundancy of disk array itself by data
Directly or indirectly it is stored on multiple single disks, to reach the mesh that the data when one or more disk failures are not lost
, that is, realize data fault-tolerant.
Wherein, when because disk failure in some reasons such as disk array etc. causes disk array to lose redundancy
When, the disk array can be in degrading state.Make so that the disk failure in disk array causes disk array to lose redundancy
The disk array as a example by degrading state, then in the prior art, is to recover this because disk failure is in degrading state
The redundancy of disk array, conventional mode are to increase the mode that HotSpare disk is rebuild, specially：The magnetic of failure is replaced with HotSpare disk
Disk.But, in the process of reconstruction, and if there occurs that disk rebuilds read error, wherein, reconstruction read error is process of reconstruction
In, rebuild I/O cause disk occur read error, then, and stop rebuild, now the disk array can only rest on degrading state without
Method returns to redundant state.When other disks in the disk array are broken down again, whole disk array will be unsuccessfully
I/O passages are closed, this does not only result in the disk array and stops offer business, also results in the data stored before the disk array
Lose.
In addition, when business reading is carried out to the disk array in degrading state, in the event of business read error, wherein industry
Business misreads and is mistaken for：During business read-write, business I/O causes the read error that disk occurs, then now the disk array fails, i.e.,
I/O passages are closed, this causes the disk array to stop offer business, and causes the loss of data for storing before.
And the popularization of country's big city network and high speed fibre causes to back up using Cloud Server at set intervals at present
Data are possibly realized, for the very high enterprise of security request data can preserve needs by way of Cloud Server is backed up
Data.
The content of the invention：
It is an object of the invention to provide a kind of disk array fault tolerance facility with Cloud Server backup, it is to avoid in degrading state
Disk array due to the problem for occurring to rebuild read error or business read error and cause；And energy is backed up by Cloud Server
Enough restoring datas.
The technical solution used in the present invention is：
A kind of disk array fault tolerance facility with Cloud Server backup：Including replacement unit, reconstruction unit, recording unit, place
Reason unit, reparation unit and recovery unit；Recording unit is connected respectively to reconstruction unit, processing unit, repairs unit and recovery
Unit, recording unit are connected to Cloud Server backup of memory by connection equipment, and reconstruction unit is connected to replacement unit；Institute
Replacement unit is stated, when the disk failures in disk array, increases HotSpare disk in the disk array, to replace this
The disk of raw failure；The reconstruction unit, the disk array to increased HotSpare disk in units of band are rebuild；The note
Record unit, when the current band rebuild by the reconstruction unit occurs to rebuild read error, will deserve the identification record of preceding article band
To in Nonvolatile memory, and trigger the reconstruction unit and skip current band, continue to rebuild from next band, until completing
The reconstruction of disk array；The processing unit, when needs are to band institute corresponding with stripe markings in the Nonvolatile memory
When the HotSpare disk of occupancy reads data, read command is not issued, using other disks in addition to HotSpare disk shared by the band
In data calculate need from HotSpare disk read data；When needing to corresponding with stripe markings in the Nonvolatile memory
Band shared by other disks in addition to HotSpare disk when reading data, to this, other disks issue read command, with basis
Data are read in the read command；The reparation unit, for each stripe markings recorded in the Nonvolatile memory, by writing
Mode repairs the reconstruction read error of band corresponding with the stripe markings, and after completing to repair from the Nonvolatile memory
Delete the stripe markings；The recovery unit, when mistake occurs in disk repair data or deletes mark mistake, by the data
Return to the data before repairing.
The reparation unit is repaired and the stripe markings by writing data to whole band corresponding with the stripe markings
The business read error of corresponding band；Or, it is determined that the significance level of band institute corresponding with stripe markings data storage, such as
Fruit determines that the significance level of the data less than given threshold, then repairs band corresponding with the stripe markings by following operation
Business read error：To the disk write setting data shared by band corresponding with the stripe markings.
Compared with prior art, the beneficial effects of the present invention is：
The present invention repairs the reconstruction read error of the band by WriteMode, recovers the redundancy of disk array as early as possible, it is to avoid rebuild
During multiple disks break down and cause the situation of whole disk array failure to occur.There is business in current band to misread
Mistake, the identification record of preceding article band can be deserved in Nonvolatile memory, and control the disk array and the reading of offer business is provided
Write, not only ensure that business continuance but also avoid the risk that data are lost.Cloud Server backup functionality is provided simultaneously,
The data of backup when the catastrophe failure that cannot be repaired occurs in local disk, can be recovered from the memory of Cloud Server.
Description of the drawings：
Fig. 1 is schematic structural view of the invention.
Specific embodiment：
Below in conjunction with the accompanying drawings, the present invention is described in further detail by embodiment：
A kind of disk array fault tolerance facility with Cloud Server backup：Including replacement unit, reconstruction unit, recording unit, place
Reason unit, reparation unit and recovery unit；Recording unit is connected respectively to reconstruction unit, processing unit, repairs unit and recovery
Unit, recording unit are connected to Cloud Server backup of memory by connection equipment, and reconstruction unit is connected to replacement unit；Institute
Replacement unit is stated, when the disk failures in disk array, increases HotSpare disk in the disk array, to replace this
The disk of raw failure；The reconstruction unit, the disk array to increased HotSpare disk in units of band are rebuild；The note
Record unit, when the current band rebuild by the reconstruction unit occurs to rebuild read error, will deserve the identification record of preceding article band
To in Nonvolatile memory, and trigger the reconstruction unit and skip current band, continue to rebuild from next band, until completing
The reconstruction of disk array；The processing unit, when needs are to band institute corresponding with stripe markings in the Nonvolatile memory
When the HotSpare disk of occupancy reads data, read command is not issued, using other disks in addition to HotSpare disk shared by the band
In data calculate need from HotSpare disk read data；When needing to corresponding with stripe markings in the Nonvolatile memory
Band shared by other disks in addition to HotSpare disk when reading data, to this, other disks issue read command, with basis
Data are read in the read command；The reparation unit, for each stripe markings recorded in the Nonvolatile memory, by writing
Mode repairs the reconstruction read error of band corresponding with the stripe markings, and after completing to repair from the Nonvolatile memory
Delete the stripe markings；The recovery unit, when mistake occurs in disk repair data or deletes mark mistake, by the data
Return to the data before repairing.
The reparation unit is repaired and the stripe markings by writing data to whole band corresponding with the stripe markings
The business read error of corresponding band；Or, it is determined that the significance level of band institute corresponding with stripe markings data storage, such as
Fruit determines that the significance level of the data less than given threshold, then repairs band corresponding with the stripe markings by following operation
Business read error：To the disk write setting data shared by band corresponding with the stripe markings.
Embodiment of the present invention is only the description carried out to the preferred embodiment of the present invention, not to the present invention
Spirit and scope are defined, and on the premise of without departing from design philosophy of the present invention, in this area, engineers and technicians are to this
Various modifications and improvement that bright technical scheme is made, all should fall into protection scope of the present invention, the skill that the present invention is claimed
Art content, has all recorded in detail in the claims.
Claims (2)
1. it is a kind of with Cloud Server backup disk array fault tolerance facility, it is characterised in that：Including replacement unit, rebuild single
Unit, recording unit, processing unit, reparation unit and recovery unit；Recording unit be connected respectively to reconstruction unit, processing unit,
Unit and recovery unit are repaired, recording unit is connected to Cloud Server backup of memory by connection equipment, and reconstruction unit connects again
It is connected to replacement unit；The replacement unit, when the disk failures in disk array, increases heat in the disk array
Standby disk, to replace the disk for breaking down；The reconstruction unit, to increased the disk array of HotSpare disk in units of band
Rebuild；The recording unit, it is when the current band rebuild by the reconstruction unit occurs to rebuild read error, this is current
The identification record of band is in Nonvolatile memory, and triggers the reconstruction unit and skip current band, from next band after
It is continuous to rebuild, until completing the reconstruction of disk array；The processing unit, when need to band mark in the Nonvolatile memory
When knowing HotSpare disk shared by corresponding band and reading data, do not issue read command, using shared by the band except HotSpare disk
Outside other disks in data calculate need from HotSpare disk read data；When need to the Nonvolatile memory
When other disks in addition to HotSpare disk shared by the corresponding band of middle stripe markings read data, to this, other disks are issued
Read command, to read data according to the read command；The reparation unit, for each recorded in the Nonvolatile memory
Tape identification, by the reconstruction read error of WriteMode reparation band corresponding with the stripe markings, and from described after completing to repair
The stripe markings are deleted in Nonvolatile memory；The recovery unit, when mistake occurs in disk repair data or deletes mark
During mistake, by data of the data recovery to before repairing.
2. it is according to claim 1 with Cloud Server backup disk array fault tolerance facility, it is characterised in that：It is described to repair
Multiple unit repairs the industry of band corresponding with the stripe markings by writing data to whole band corresponding with the stripe markings
Business read error；Or, it is determined that the significance level of band institute corresponding with stripe markings data storage, if it is determined that go out the data
Significance level be less than given threshold, then the business read error of corresponding with stripe markings band is repaired by following operation：
To the disk write setting data shared by band corresponding with the stripe markings.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610992459.3A CN106528342A (en) | 2016-11-11 | 2016-11-11 | Disk array fault tolerance apparatus with cloud server backup function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610992459.3A CN106528342A (en) | 2016-11-11 | 2016-11-11 | Disk array fault tolerance apparatus with cloud server backup function |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106528342A true CN106528342A (en) | 2017-03-22 |
Family
ID=58351067
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610992459.3A Pending CN106528342A (en) | 2016-11-11 | 2016-11-11 | Disk array fault tolerance apparatus with cloud server backup function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106528342A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108334280A (en) * | 2017-12-28 | 2018-07-27 | 创新科存储技术（深圳）有限公司 | A kind of RAID5 disks group fast reconstructing method and device |
| CN109445708A (en) * | 2018-11-02 | 2019-03-08 | 南方电网调峰调频发电有限公司 | A kind of transparent fault transfer method based on the privately owned cloud platform of database |
| CN116149576A (en) * | 2023-04-20 | 2023-05-23 | 北京大学 | Method and system for reconstructing disk redundant array oriented to server non-perception calculation |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184129A (en) * | 2011-04-27 | 2011-09-14 | 杭州华三通信技术有限公司 | Fault tolerance method and device for disk arrays |
| CN105183589A (en) * | 2015-08-31 | 2015-12-23 | 安徽欧迈特数字技术有限责任公司 | Disk array fault tolerance apparatus |
| CN105959356A (en) * | 2016-04-26 | 2016-09-21 | 华中科技大学 | Method of realizing multi-cloud storage fault-tolerance conversion mechanism |
-
2016
- 2016-11-11 CN CN201610992459.3A patent/CN106528342A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184129A (en) * | 2011-04-27 | 2011-09-14 | 杭州华三通信技术有限公司 | Fault tolerance method and device for disk arrays |
| CN105183589A (en) * | 2015-08-31 | 2015-12-23 | 安徽欧迈特数字技术有限责任公司 | Disk array fault tolerance apparatus |
| CN105959356A (en) * | 2016-04-26 | 2016-09-21 | 华中科技大学 | Method of realizing multi-cloud storage fault-tolerance conversion mechanism |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108334280A (en) * | 2017-12-28 | 2018-07-27 | 创新科存储技术（深圳）有限公司 | A kind of RAID5 disks group fast reconstructing method and device |
| CN108334280B (en) * | 2017-12-28 | 2021-01-08 | 深圳创新科技术有限公司 | RAID5 disk group fast reconstruction method and device |
| CN109445708A (en) * | 2018-11-02 | 2019-03-08 | 南方电网调峰调频发电有限公司 | A kind of transparent fault transfer method based on the privately owned cloud platform of database |
| CN116149576A (en) * | 2023-04-20 | 2023-05-23 | 北京大学 | Method and system for reconstructing disk redundant array oriented to server non-perception calculation |
| CN116149576B (en) * | 2023-04-20 | 2023-07-25 | 北京大学 | Method and system for reconstructing disk redundant array oriented to server non-perception calculation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102012847B (en) | Improved disk array reconstruction method | |
| CN102184129B (en) | Fault tolerance method and device for disk arrays | |
| CN103970481B (en) | The method and apparatus rebuilding memory array | |
| US9009526B2 (en) | Rebuilding drive data | |
| CN102023815B (en) | RAID is realized in solid-state memory | |
| CN104484251B (en) | A kind of processing method and processing device of hard disk failure | |
| CN100504795C (en) | Computer RAID array early-warning system and method | |
| CN101887351B (en) | Fault-tolerance method and system for redundant array of independent disk | |
| CN103309775A (en) | Fault-tolerance method for high-reliability disk array | |
| CN102508620B (en) | Method for processing RAID5 (Redundant Array of Independent Disks) bad sector | |
| CN102508733B (en) | A kind of data processing method based on disk array and disk array manager | |
| CN104035830A (en) | Method and device for recovering data | |
| CN105302667A (en) | Cluster architecture based high-reliability data backup and recovery method | |
| CN103699457A (en) | Method and device for restoring disk arrays based on stripping | |
| CN104407821B (en) | A kind of method and device for realizing RAID reconstruction | |
| US20120084610A1 (en) | Method and device for reading and writing a memory card | |
| CN103019894B (en) | Reconstruction method for redundant array of independent disks | |
| CN110399247A (en) | A kind of data reconstruction method, device, equipment and computer readable storage medium | |
| CN106528342A (en) | Disk array fault tolerance apparatus with cloud server backup function | |
| US8886993B2 (en) | Storage device replacement method, and storage sub-system adopting storage device replacement method | |
| CN100462931C (en) | Method, system and computer program product for recovery of formatting in repair of bad sectors in disk drives | |
| CN108874312B (en) | Data storage method and storage device | |
| US8423776B2 (en) | Storage systems and data storage method | |
| CN102999399A (en) | Method and device of automatically restoring storage of JBOD (just bundle of disks) array | |
| CN105183590A (en) | Disk array fault tolerance processing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170322 |
|
| RJ01 | Rejection of invention patent application after publication |