CN101241453B - Magnetic disc redundant array maintenance method and device - Google Patents
Magnetic disc redundant array maintenance method and device Download PDFInfo
- Publication number
- CN101241453B CN101241453B CN2008100076715A CN200810007671A CN101241453B CN 101241453 B CN101241453 B CN 101241453B CN 2008100076715 A CN2008100076715 A CN 2008100076715A CN 200810007671 A CN200810007671 A CN 200810007671A CN 101241453 B CN101241453 B CN 101241453B
- Authority
- CN
- China
- Prior art keywords
- redundant arrays
- inexpensive disks
- disk
- rebuilding
- synchronously
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Hardware Redundancy (AREA)
Abstract
The present invention provides a maintaining method and device of Redundant Arrays Of Inexpensive Disks. The maintaining method includes following steps: the Redundant Arrays Of Inexpensive Disks starts process synchronization to check conformance, if checking a damage disk, the process synchronization is continuous, at the same time establishing a new process to reconstitute the damaged disk; the synchronization process and the reconstutition process are two individual processes. The synchronization process and the reconstutition process are processed at the same time by using the method and device of the invention in the array type of supporting multiple disk damages. The synchronization process and the reconstutition process operating to the different disks can improve efficiency of the synchronization and reconstutition, shorten average time of the synchronization and reconstutition, enhance the array robustness, greatly keep the user data security.
Description
Technical field
The present invention relates to communication technical field, relate in particular to a kind of maintaining method and device of redundant arrays of inexpensive disks.
Background technology
In the storage system, use a plurality of inexpensive disks to form RAID (Redundant Arrays ofInexpensive Disks, Redundant Array of Inexpensive Disc) usually.Disk array has polytype, and the type that has is just simply for the increase capacity, and the type that has then provides data redundancy to ensure secure user data.Below introduce the data profile and the data protection principle of several array type commonly used:
(1) RAID0: shown in Figure 1A, created by two or more disks, do not have the data redundancy protection, any one disk failures will obliterated data.
(2) RAID1: shown in Figure 1B, can only be created by two disks, same piece of data copies as two parts and deposits, and a tuple is arranged according to redundancy protecting, supports any one disk failures and obliterated data not.
(3) RAID5: shown in Fig. 1 C, create, a tuple is arranged, support any one disk failures and obliterated data not according to redundancy protecting by the above disks of three or three.Data block Pi on each band deposits is the result that all data block Di on each band carry out XOR.Notice that RAID5 is not that direct copy data is deposited, but the XOR value of calculating all data deposits, the disk space effective rate of utilization is higher than RAID1.Any blocks of data Di damages and can recover by other data computation on the band.
(4) RAID6: shown in Fig. 1 D, create, double data redundancy protection is arranged, support any two disk failures and obliterated data not by four or more disk.Data block Pi on each band is the same with RAID5, and that deposit is the result that all data block Di of this band carry out XOR; That data block Qi deposits is the XOR result that all data block Di carry out the Galois Field conversion.Any two blocks of data Di on the single band, Di ' damage and can recover by other data computation on the band.
(5) RAID10: shown in Fig. 1 E; even number disk by four or more is created; one tuple is arranged according to redundancy protecting; any one disk failures can obliterated data; can support half disk failures of array at most and obliterated data not, a plurality of disk failures are lost not obliterated data and are decided on the position of damaging disk.The data protection principle is similar to RAID1, also is to duplicate a deposit data more.
More than in the various array type of Jie Shaoing, the array of band data redundancy protection comprises RAID1, RAID5, RAID6, RAID10.Concrete, for the redundancy protecting of data be according to synchronously or the function of rebuilding realize.
Synchronizing function is called consistency check again, refers to the many piece of data in the redundant array are carried out consistency check.Initialization when being divided into the establishment array is synchronous and the operating timing of array is synchronous.Initialization is used for synchronously guaranteeing that array establishment back array data is initialised to consistent state; Regularly be used for periodically detecting the consistance of the many piece of data in the redundant array synchronously, inconsistent if quantitative check is checked through many piece of data, can select alarm to the user, also can cover other different data with a piece of data according to certain policy selection.One synoptic diagram of synchronizing function is seen Fig. 2 A, is example with RAID1, and two parts of data of depositing are carried out consistency check.
Rebuild function, when having a disk failures to cause the redundance of array to reduce in the redundant array, the user can select to use new blank disc to add array, and recovers the complete deposit data of portion by rebuilding function to blank disc from other normal disks.After reconstruction was finished, the redundance of array will increase.Rebuilding a synoptic diagram of function and see Fig. 2 B, is example with RAID1, and the data in the disk 0 are reconstructed on the new disk 1.
In the prior art, be in from reducing design complexities, simplify software and realize, increase code reuse and be mainly the aspects such as redundant array design of supporting single disk failures and consider, design result in all redundant array types synchronously and rebuild function and all can not carry out simultaneously.And in the redundant array type of supporting a plurality of disk failures, as RAID6, RAID10, synchronous and reconstruction function can occur simultaneously, and scheme synchronous and that reconstruction is carried out simultaneously is more excellent.And it is also unreasonable for the array type of supporting a plurality of disk failures such as RAID6, RAID10 in the prior art to restriction synchronous and that reconstruction can not occur simultaneously.
Summary of the invention
The invention provides a kind of maintaining method and device of redundant arrays of inexpensive disks, be used for maintenance process, realize synchronously and rebuild function simultaneously, improve the maintenance efficiency of disk array at disk array.
For achieving the above object, the invention provides a kind of dimension expanding method of redundant arrays of inexpensive disks, may further comprise the steps:
Redundant arrays of inexpensive disks starts synchronized process and carries out consistency check, if during detect a disk failures;
Continue described synchronized process in other disks in described redundant arrays of inexpensive disks, create a new process simultaneously the disk of described damage is rebuild; The wherein said synchronous process and the process of reconstruction are two separate processes.
Wherein, described redundant arrays of inexpensive disks is specially: the redundant arrays of inexpensive disks of supporting a plurality of disk failures.
Wherein, described synchronously and rebuild in the process of carrying out, to described synchronously and/or the process of rebuilding carry out record.
Wherein, described simultaneously the disk of described damage is rebuild after, also comprise:
After interrupt taking place and restarting, read described synchronously and/or the process record of rebuilding, and continue described synchronously and/or the process of rebuilding.
The present invention also provides a kind of attending device of redundant arrays of inexpensive disks, comprising:
Lock unit is used for redundant arrays of inexpensive disks is carried out synchronously, when in synchronized process, finding disk failures, and the notice control module;
Control module when being used to receive the notice of described lock unit, continues described synchronized process in other disks in described redundant arrays of inexpensive disks, notify reconstruction unit that the disk of described damage is rebuild simultaneously; The wherein said synchronous process and the process of reconstruction are two separate processes;
Reconstruction unit is used for the notice according to described control module, and the disk of described damage is rebuild.
Wherein, also comprise:
The process record cell is used for the synchronized process of described lock unit and the process of rebuilding of described reconstruction unit are carried out record.
Wherein, also comprise:
The process reading unit, be used for when the process of rebuilding of the synchronized process of described lock unit and/or described reconstruction unit is interrupted, from described process record cell, read the process of rebuilding of the synchronized process of described lock unit and/or described reconstruction unit and notify described control module, carry out the recovery of synchronized process and/or process of rebuilding for described control module.
Wherein, described redundant arrays of inexpensive disks is specially: the redundant arrays of inexpensive disks of supporting a plurality of disk failures.
Compared with prior art, the present invention has the following advantages:
Make in the array type of supporting a plurality of disk failures, can carry out simultaneously with the reconstruction function synchronously.That carries out simultaneously operates different disks with rebuilding synchronously, can improve synchronously and the efficient of rebuilding, and shortens synchronously and the averaging time of rebuilding, and increases the array robustness, more effectively ensures secure user data.
Description of drawings
Figure 1A to Fig. 1 E is respectively the array data distribution schematic diagram of RAID0 in the prior art, RAID1, RAID5, RAID6 and RAID10;
Fig. 2 A is the synchronizing function synoptic diagram of array in the prior art;
Fig. 2 B is the reconstruction functional schematic of array in the prior art;
Fig. 3 is the process flow diagram of redundant arrays of inexpensive disks maintaining method among the present invention;
Fig. 4 A is the application scenarios synoptic diagram of redundant arrays of inexpensive disks maintaining method among the present invention;
Fig. 4 B is the Another Application scene synoptic diagram of redundant arrays of inexpensive disks maintaining method among the present invention;
Fig. 5 is the structural representation of redundant arrays of inexpensive disks attending device among the present invention.
Embodiment
The invention provides a kind of redundant arrays of inexpensive disks maintaining method, as shown in Figure 3, may further comprise the steps:
In step s301, the redundant arrays of inexpensive disks synchronized process, find a disk failures.
Step s302, continue this synchronized process, create a new process simultaneously the disk of described damage is rebuild; The wherein synchronous process and the process of reconstruction are two separate processes.
Concrete, for the redundant arrays of inexpensive disks of supporting a plurality of disk failures, as RAID6 and RAID10 etc., synchronizing function and reconstruction function can be carried out simultaneously.In the process that synchronizing function and reconstruction function are carried out simultaneously, synchronizing function is operated different target disks separately with the reconstruction function, and the progress information of record oneself.Synchronously with the process of rebuilding in, if there be and interrupt taking place (as reset, power down etc.), after the End of Interrupt, can read out respectively synchronously and the progress information of rebuilding, and according to progress information continue respectively uncompleted synchronously with rebuild.
Below in conjunction with specific embodiment, embodiments of the present invention are described further.
In the application scenarios of the present invention, the example that is maintained as so that the multiple redundancy array RAID6 that supports a plurality of disk failures is carried out illustrates embodiments of the present invention.
Shown in Fig. 4 A, among the multiple redundancy array RAID6, the user starts a task and begins synchronously (shown in the four-headed arrow among Fig. 4 A), if find that in synchronized process a disk failures is arranged, then proceeds synchronously; If the condition that array satisfy to be rebuild (HotSpare disk is arranged and enable automatic reconstruction or manual beginning of user rebuild), then start the another one task immediately and begin to rebuild (shown in the unidirectional arrow among Fig. 4 A), this is different from needs in the prior art and will just can switch to the method for reconstruction tasks after the synchronous task end.In synchronizing function with rebuild in the process that function carries out simultaneously, synchronously and rebuild the own progress msg of record separately, can realize so synchronously and reconstruction is carried out simultaneously.In addition, rebuild and the destination disk of synchronous operation can be not exclusively the same, shown in Fig. 4 A, for synchronously, D0/D1/P0, D2/P1/Q1 finish synchronously, are carrying out synchronous between P2/Q2/D4; For reconstruction, rebuild Q0 by D0/D1/P0 and finish, carrying out rebuilding D3 by D2/P1/Q1; This maintenance mode that carries out simultaneously and can operate the different target dish can shorten synchronously and rebuilds the time of finishing.
In the further application of the invention scene, the example that is maintained as so that a heavy redundant array RAID10 who supports a plurality of disk failures is carried out illustrates embodiments of the present invention.
Shown in Fig. 4 B, among the multiple redundancy array RAID10, the user starts a task and begins synchronously (shown in the four-headed arrow among Fig. 4 B), if find that in synchronized process a disk failures is arranged, then proceeds synchronously; If the condition that array satisfy to be rebuild (HotSpare disk is arranged and enable automatic reconstruction or manual beginning of user rebuild), then start the another one task immediately and begin to rebuild (shown in the unidirectional arrow among Fig. 4 B), in the process that synchronizing function and reconstruction function are carried out simultaneously, write down the progress msg of oneself synchronously separately with reconstruction.In addition, rebuild and the destination disk of synchronous operation can be not exclusively the same, shown in Fig. 4 B, for synchronously, the finishing synchronously of D0/D0 on the different disk carried out on the different disk synchronous between D2/D2; For reconstruction, carrying out rebuilding the process of the D1 on the new disk 3 by the D1 on the disk 2.This maintenance mode that carries out simultaneously and can operate the different target dish can shorten synchronously and rebuilds the time of finishing.
The present invention also provides a kind of redundant arrays of inexpensive disks attending device, and its structure comprises as shown in Figure 5:
Also comprise:
The method and apparatus that the application of the invention provides makes in the array type of supporting a plurality of disk failures, can carry out simultaneously with the reconstruction function synchronously.Rebuild function the disk that has damaged in the array is rebuild, synchronizing function is carried out consistency check to many piece of data of residue disk simultaneously.That carries out simultaneously operates different disks with rebuilding synchronously, can improve synchronously and the efficient of rebuilding, and shortens synchronously and the averaging time of rebuilding, and increases the array robustness, more effectively ensures secure user data.
Through the above description of the embodiments, those skilled in the art can be well understood to the present invention and can realize by the mode that software adds essential general hardware platform, can certainly pass through hardware, but the former is better embodiment under a lot of situation.Based on such understanding, the part that technical scheme of the present invention contributes to prior art in essence in other words can embody with the form of software product, this computer software product is stored in the storage medium, comprises that some instructions are used so that an equipment is carried out the described method of each embodiment of the present invention.
More than disclosed only be several specific embodiment of the present invention, still, the present invention is not limited thereto, any those skilled in the art can think variation all should fall into protection scope of the present invention.
Claims (8)
1. the maintaining method of a redundant arrays of inexpensive disks is characterized in that, may further comprise the steps:
Redundant arrays of inexpensive disks starts synchronized process and carries out consistency check, if during detect a disk failures;
Continue described synchronized process in other disks in described redundant arrays of inexpensive disks, create a new process simultaneously the disk of described damage is rebuild; The wherein said synchronous process and the process of reconstruction are two separate processes.
2. the maintaining method of redundant arrays of inexpensive disks according to claim 1 is characterized in that described redundant arrays of inexpensive disks is specially: the redundant arrays of inexpensive disks of supporting a plurality of disk failures.
3. the maintaining method of redundant arrays of inexpensive disks according to claim 1 is characterized in that, described synchronously and rebuild in the process of carrying out, to described synchronously and/or the process of rebuilding carry out record.
4. as the maintaining method of redundant arrays of inexpensive disks as described in the claim 3, it is characterized in that, described simultaneously the disk of described damage is rebuild after, also comprise:
After interrupt taking place and restarting, read described synchronously and/or the process record of rebuilding, and continue described synchronously and/or the process of rebuilding.
5. the attending device of a redundant arrays of inexpensive disks is characterized in that, comprising:
Lock unit is used for redundant arrays of inexpensive disks is carried out synchronously, when in synchronized process, finding disk failures, and the notice control module;
Control module when being used to receive the notice of described lock unit, continues described synchronized process in other disks in described redundant arrays of inexpensive disks, notify reconstruction unit that the disk of described damage is rebuild simultaneously; The wherein said synchronous process and the process of reconstruction are two separate processes;
Reconstruction unit is used for the notice according to described control module, and the disk of described damage is rebuild.
6. as the attending device of redundant arrays of inexpensive disks as described in the claim 5, it is characterized in that, also comprise:
The process record cell is used for the synchronized process of described lock unit and the process of rebuilding of described reconstruction unit are carried out record.
7. as the attending device of redundant arrays of inexpensive disks as described in the claim 6, it is characterized in that, also comprise:
The process reading unit, be used for when the process of rebuilding of the synchronized process of described lock unit and/or described reconstruction unit is interrupted, from described process record cell, read the process of rebuilding of the synchronized process of described lock unit and/or described reconstruction unit and notify described control module, carry out the recovery of synchronized process and/or process of rebuilding for described control module.
8. as the attending device of redundant arrays of inexpensive disks as described in the claim 5, it is characterized in that described redundant arrays of inexpensive disks is specially: the redundant arrays of inexpensive disks of supporting a plurality of disk failures.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008100076715A CN101241453B (en) | 2008-03-05 | 2008-03-05 | Magnetic disc redundant array maintenance method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008100076715A CN101241453B (en) | 2008-03-05 | 2008-03-05 | Magnetic disc redundant array maintenance method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101241453A CN101241453A (en) | 2008-08-13 |
| CN101241453B true CN101241453B (en) | 2010-06-16 |
Family
ID=39932998
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2008100076715A Expired - Fee Related CN101241453B (en) | 2008-03-05 | 2008-03-05 | Magnetic disc redundant array maintenance method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101241453B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117213B (en) * | 2009-12-31 | 2015-03-25 | 纬创资通股份有限公司 | Starting method of computer system using redundancy array of independent disks |
| CN101859265B (en) * | 2010-06-02 | 2012-09-26 | 杭州华三通信技术有限公司 | Disk array reconstruction method and device |
| CN102314381A (en) * | 2010-07-02 | 2012-01-11 | 上海宝信软件股份有限公司 | Integration equipment and method for improving availability of information system |
| CN110109773A (en) * | 2019-04-11 | 2019-08-09 | 苏州浪潮智能科技有限公司 | A kind of detection method and system of magnetic disk of virtual machine consistency |
| CN114079616B (en) * | 2021-11-02 | 2023-11-03 | 中国船舶重工集团公司第七0三研究所 | Redundancy method for database of non-hot standby disk array server |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5774643A (en) * | 1995-10-13 | 1998-06-30 | Digital Equipment Corporation | Enhanced raid write hole protection and recovery |
| US20050091452A1 (en) * | 2003-10-28 | 2005-04-28 | Ying Chen | System and method for reducing data loss in disk arrays by establishing data redundancy on demand |
| CN1808365A (en) * | 2005-01-17 | 2006-07-26 | 英业达股份有限公司 | Automatic reconstruction method for disk redundancy array device |
-
2008
- 2008-03-05 CN CN2008100076715A patent/CN101241453B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5774643A (en) * | 1995-10-13 | 1998-06-30 | Digital Equipment Corporation | Enhanced raid write hole protection and recovery |
| US20050091452A1 (en) * | 2003-10-28 | 2005-04-28 | Ying Chen | System and method for reducing data loss in disk arrays by establishing data redundancy on demand |
| CN1808365A (en) * | 2005-01-17 | 2006-07-26 | 英业达股份有限公司 | Automatic reconstruction method for disk redundancy array device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101241453A (en) | 2008-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101387975B (en) | Magnetic disc array system | |
| JP4516846B2 (en) | Disk array system | |
| Xu et al. | Single disk failure recovery for X-code-based parallel storage systems | |
| CN101241453B (en) | Magnetic disc redundant array maintenance method and device | |
| US20130145208A1 (en) | Method for a Plurality of RAID Systems and Data Storage System Thereof | |
| US8464090B2 (en) | Recovery of failed disks in an array of disks | |
| US20080126840A1 (en) | Method for reconstructing data in case of two disk drives of raid failure and system therefor | |
| US7853823B2 (en) | System and method for reconstructing lost data in a storage system | |
| EP2899626B1 (en) | Method and system for service-aware data placement in a storage system | |
| CN101567211A (en) | Method for improving usability of disk and disk array controller | |
| CN101276302A (en) | Magnetic disc fault processing and data restructuring method in magnetic disc array system | |
| CN101916173A (en) | RAID (Redundant Array of Independent Disks) based data reading and writing method and system thereof | |
| WO2016095372A1 (en) | Method and apparatus for realizing image backup of transaction logs | |
| CN103246478A (en) | Disk array system supporting grouping-free overall situation hot standby disks based on flexible redundant array of independent disks (RAID) | |
| CN102226892B (en) | Disk fault tolerance processing method and device thereof | |
| CN102508733A (en) | Disk array based data processing method and disk array manager | |
| CN102750195A (en) | Method for cluster file system data fault tolerance | |
| US11093339B2 (en) | Storage utilizing a distributed cache chain and a checkpoint drive in response to a data drive corruption | |
| CN102799543B (en) | On the storage medium of dynamic change, dispersion stores data and restoration methods | |
| CN101937378A (en) | Method for carrying out back-up protection on data of storage equipment and computer system | |
| CN101794246B (en) | Backup storage system, backup system, data backup method and recovery method | |
| US8938429B1 (en) | Resynchronization of nonactive and active segments | |
| WO2016112824A1 (en) | Storage processing method and apparatus, and storage device | |
| CN110046065A (en) | A kind of storage array method for reconstructing, device, equipment and storage medium | |
| CN101630281B (en) | Image method and device of data storage |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 310052 Binjiang District Changhe Road, Zhejiang, China, No. 466, No. Patentee after: Xinhua three Technology Co., Ltd. Address before: 310053 Hangzhou hi tech Industrial Development Zone, Zhejiang province science and Technology Industrial Park, No. 310 and No. six road, HUAWEI, Hangzhou production base Patentee before: Huasan Communication Technology Co., Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20100616 Termination date: 20200305 |