CN106933707B - Data recovery method and system of data storage device based on raid technology - Google Patents
Data recovery method and system of data storage device based on raid technology Download PDFInfo
- Publication number
- CN106933707B CN106933707B CN201710153658.XA CN201710153658A CN106933707B CN 106933707 B CN106933707 B CN 106933707B CN 201710153658 A CN201710153658 A CN 201710153658A CN 106933707 B CN106933707 B CN 106933707B
- Authority
- CN
- China
- Prior art keywords
- data
- storage device
- recording
- data storage
- data block
- 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
- 238000013500 data storage Methods 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000011084 recovery Methods 0.000 title claims abstract description 37
- 238000005516 engineering process Methods 0.000 title claims abstract description 24
- 230000008569 process Effects 0.000 claims description 21
- 230000003287 optical effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 7
- 238000012545 processing Methods 0.000 description 18
- 238000004364 calculation method Methods 0.000 description 15
- 238000010586 diagram Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000002085 persistent effect Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 238000013021 overheating Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
Images
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
- G06F11/1479—Generic software techniques for error detection or fault masking
- G06F11/1489—Generic software techniques for error detection or fault masking through recovery blocks
Abstract
The invention discloses a data recovery method and a data recovery system of a data storage device based on raid technology, which comprises the following steps: the method comprises the following steps: numbering each data block in the data storage device; when a subdata storage device a in the data storage device is damaged, recording corresponding data block numbers of all data which are not successfully written in a when a is damaged and corresponding data block numbers of all data written in after a is damaged, and generating first recording information; replacing the damaged subdata storage device a with a complete subdata storage device b, copying the data of the subdata storage device a into the subdata storage device b, recording the number information of the data block failed in copying, and generating second recording information; and generating a data block number to be reconstructed through the first recording information and the second recording information, and reconstructing a corresponding data block according to a raid algorithm, thereby realizing the technical effect of efficiently and quickly completing data recovery of the data storage device.
Description
Technical Field
The invention relates to the field of data storage processing, in particular to a data recovery method and a data recovery system of data storage equipment based on raid technology.
Background
Current storage commonly employs raid techniques to avoid data loss due to a single hardware corruption. The damage of the disk is avoided by raid5, raid6, Huashi raid2.0 technology and the like; and avoiding the N + M raid of the cloud storage server fault. After a storage data node (a disk or a server) fails, the raid technology is used, damaged hardware can be directly replaced by new hardware, and then data on the new hardware is recovered through an algorithm.
The technical implementation of raid5 is shown in table 1:
TABLE 1
RAID5 is a storage solution that takes into account storage performance, data security, and storage cost. Taking RAID5 composed of four hard disks as an example, the data storage mode is as shown in fig. 3: in FIG. 3, Ap is the parity information for A1, A2, and A3, and so on. As can be seen in the figure, RAID5 does not back up the stored data, but stores the data and corresponding parity information on the individual disks making up RAID5, and the parity information and corresponding data are stored on different disks, respectively. When a disk of RAID5 is corrupted, the remaining data and corresponding parity information are used to recover the corrupted data.
RAID5 may be understood as a compromise between RAID0 and RAID 1. RAID5 can provide data security guarantee for the system, but the guarantee degree is lower than that of the Mirror and the utilization rate of the disk space is higher than that of the Mirror. RAID5 has a data read rate similar to RAID0, but with one more parity information, and writes data at a slower rate than a single disk write operation. Meanwhile, as a plurality of data correspond to one parity check information, the utilization rate of the disk space of RAID5 is higher than that of RAID1, and the storage cost is relatively low.
When disk3(disk0, disk1, disk2 and other optional disk damage) in FIG. 3 is damaged, the data of disk3 can be calculated by the data of other disks; then, replacing the disk3 with a new blank disk 3'; the data on disk 3' is then recovered through an algorithm.
In FIG. 3, Ap is calculated by A1, A2 and A3, B3 is calculated by B1, B2 and Bp, and C3 and D3 can be calculated by analogy. Thereby recovering the data on disk 3', which is the current reconstruction technique.
It can be seen that the current reconstruction requires reading all data from several other disks and writing it to disk 3'; in the process of reconstruction, the system disk is occupied by the reconstruction process, and external service processing is basically impossible. Or if the reconstruction time is very long, sometimes up to several weeks, during the large external traffic processing. Taking raid5 as an example, other raid algorithms, including but not limited to raid0, raid5, raid6, Huawei raid2.0, raid1, raid10, raid N + M, etc. all have similar problems, and all adopt similar schemes, except that the calculation methods are different.
In summary, in the process of implementing the technical solution of the present invention, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
in the prior art, the data recovery mode of the existing data storage device has the technical problems of large calculation amount, low efficiency and serious reduction of the external service processing capability of the data storage device in the data recovery process.
Disclosure of Invention
The invention provides a data recovery method and a data recovery system of a data storage device based on raid technology, which solve the technical problems that the existing data recovery mode of the data storage device has large calculation amount and low efficiency, and the external service processing capacity of the data storage device is seriously reduced in the data recovery process, realize the high-efficiency and quick completion of the data recovery of the data storage device, and ensure the technical effect of the external service processing capacity of the data storage device.
In order to solve the technical problem, the present application provides a data recovery method for a data storage device based on raid technology, where the method includes:
step 1: numbering each data block in the data storage device, wherein the data storage device comprises N sub data storage devices, and N is a positive integer greater than or equal to 1;
step 2: when a subdata storage device a in the data storage device is damaged, recording corresponding data block numbers (discarding corresponding data) of all data which are not successfully written in a when a is damaged and corresponding data block numbers (discarding corresponding data) of all data written in after a is damaged, and generating first recording information based on the recorded numbers;
and step 3: replacing the damaged subdata storage device a with a complete subdata storage device b, copying the data of the subdata storage device a into the subdata storage device b, recording the number information of the data block failed in copying, and generating second recording information based on the recorded number;
and 4, step 4: and generating a data block number to be reconstructed according to the first recording information and the second recording information, reconstructing a corresponding data block according to a current raid algorithm, and writing the reconstructed data block into the sub-data storage device b.
Among them, the current raid algorithm includes but is not limited to: raid0, raid5, raid6, Huacheng raid2.0, raid1, raid10, raid N + M, and the like.
Further, numbering each data block in the data storage device, specifically: the number is a management number and is determined before the system writes data. For example, 0 to 1000 bytes are block 1, 1001 to 2000 bytes are block 2, and 2001 to 3000 bytes are block 3, … …. In order to manage the numbering which is convenient to carry out, the blocks can be conveniently recorded later when the data change occurs to the blocks.
Further, the specific implementation manner of the first record information includes but is not limited to: tables, logs, bitmaps, databases.
Further, when new data is written into the data block, on one hand, the data of the data block is changed into corresponding data, the data block is recorded to be rewritten, the number information of all rewritten data blocks is recorded, and first recording information is generated.
Further, the sub data storage device includes, but is not limited to: server cluster, server, PC, magnetic disk, tape library, U disk, optical disk and hard disk.
After the step 1, before the step 2, a judging step is further included, wherein the judging step specifically comprises the following steps: judging whether the damage of the data storage device is true or false, and if true, performing subsequent steps; if false, step 3 is skipped to perform the subsequent steps. The disc is kicked by mistake and is automatically recovered later. Only partial data blocks in the false kick process are reconstructed. I.e., the data in the second recording information is empty, and is reconstructed using only the data in the first recording information.
On the other hand, the application also provides a data recovery system of a data storage device based on raid technology, and the system includes:
a numbering module to: numbering each data block in the data storage device, wherein the data storage device comprises N sub data storage devices, and N is a positive integer greater than or equal to 1;
a first recording module to: when a subdata storage device a in the data storage device is damaged, recording the data block numbers of all data which are not successfully written in a when a is damaged and the data block numbers of all data written in after a is damaged, and generating first recording information based on the recorded numbers;
a replacement module for: replacing the damaged subdata storage device a with a complete subdata storage device b;
a second recording module to: copying the data of the sub-data storage device a to the sub-data storage device b, recording the data block failed in copying and the corresponding number information, and generating second recording information;
a data reconstruction module to: and generating data information needing to be reconstructed according to the first recording information and the second recording information, reconstructing a corresponding data block, and writing the reconstructed data block into the sub-data storage device b.
The replacement of the replacement module may be performed automatically (i.e., in a manner of hot-standby), or manually by a user (i.e., in a process of pulling out the a-disc and inserting the b-disc).
Generating data information to be reconstructed through the first recording information and the second recording information, and reconstructing a corresponding data block, specifically including:
merging the first recording information and the second recording information to generate a number set of all data blocks needing to be reconstructed;
and performing data reconstruction on the data block according to a reconstruction algorithm corresponding to the raid, calculating data of the current data block in the sub data storage device b, and writing the data into the data block.
One or more technical solutions provided by the present application have at least the following technical effects or advantages:
the damaged disk is generally damaged by partial equator or sectors, and not all data is damaged, but the method and the system in the application only recover the damaged data block and the data rewritten after the damage, compared with the traditional mode, the efficiency is obviously improved, a large amount of calculation is needed in the traditional mode, and then all data is recovered, the data information needing to be reconstructed is generated through the first recorded information and the second recorded information, and the corresponding data block is reconstructed;
furthermore, when new device data is constructed, the data on the damaged device is used as much as possible, the damaged disk does not participate in external services, the data read from the damaged disk on the IO model is sequential IO, the new device does not participate in the external services at the moment, and the IO is sequential write IO; in the conventional method, reading data and writing data are all random IO (due to external services). The read-write efficiency of the least sequential IO is improved by 5 times compared with that of the random IO, usually 10 times, even 10 times; according to the invention, a large amount of calculation work is omitted in the data construction process, the data does not need to be checked and calculated by a CPU (Central processing Unit), the data can be directly transferred from a bad disk to a new disk by a DMA (direct memory access) technology, and the efficiency is greatly improved.
Furthermore, the idea of the present invention can be utilized to solve the problem of too long reconstruction time caused by non-persistent failures such as vibration, overheating, electromagnetic interference, etc. (these failures can cause that the disk cannot be normally used within a certain time and is kicked out of the raid group, but after the disk is found not to be really damaged, the disk can be rejoined into the raid group and the reconstruction is started). The method can also solve the problem that the reconstruction time is too long because a user mistakenly extracts a normal disk in use (which often happens when the user maintains equipment, when the disk is found to be normal after being hot extracted, and then the disk is hot inserted, the system can carry out full disk reconstruction on the disk).
Further, in the process of traditional algorithm reconstruction, a large amount of reading and writing can be performed on the disk, and the cpu is used for calculation, and at this time, the external service is difficult to acquire corresponding reading and writing and cpu resources, so that the external service efficiency is greatly reduced. In the process of recovering data, the data on the bad disk is used as much as possible, the bad disk does not participate in the service, the new disk does not participate in the service at the moment, and a large amount of calculation work is not needed, so that the new disk basically does not compete with the external service for computer resources. The processing capacity of the external service is ensured.
Therefore, the technical problems that the data recovery mode of the existing data storage device is large in calculation amount and low in efficiency, and the external service processing capacity of the data storage device is seriously reduced in the data recovery process are effectively solved, the data recovery of the data storage device is efficiently and quickly completed, and the technical effect of the external service processing capacity of the data storage device is guaranteed.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention;
FIG. 1 is a schematic flow chart of a data recovery method for a data storage device according to the present application;
FIG. 2 is a schematic diagram of the components of a data recovery system of the data storage device of the present application;
FIG. 3 is a schematic diagram of the raid5 scheme in the present application;
FIG. 4 is a schematic diagram of a raid5 reconstruction calculation method in the present application;
FIG. 5 is a schematic diagram of the data blocks in raid5 being partitioned and numbered in the present application;
FIG. 6 is a schematic diagram of the generation of record Table 1 in the present application;
FIG. 7 is a schematic diagram of the generation of record Table 2 in the present application;
FIG. 8 is a schematic illustration of reconstruction performed according to record Table 1 and record Table 2 in the present application.
Detailed Description
The invention provides a data recovery method and a data recovery system of a data storage device based on raid technology, which solve the technical problems that the existing data recovery mode of the data storage device has large calculation amount and low efficiency, and the external service processing capacity of the data storage device is seriously reduced in the data recovery process, realize the high-efficiency and quick completion of the data recovery of the data storage device, and ensure the technical effect of the external service processing capacity of the data storage device.
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflicting with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described and thus the scope of the present invention is not limited by the specific embodiments disclosed below.
Referring to fig. 1-2, the present application provides a data recovery method for a data storage device based on raid technology, where the method includes:
step 1: numbering each data block in the data storage device, wherein the data storage device comprises N sub data storage devices, and N is a positive integer greater than or equal to 1;
step 2: when a subdata storage device a in the data storage device is damaged, recording corresponding data block numbers (discarding corresponding data) of all data which are not successfully written in a when a is damaged and corresponding data block numbers (discarding corresponding data) of all data written in after a is damaged, and generating first recording information based on the recorded numbers;
and step 3: replacing the damaged subdata storage device a with a complete subdata storage device b, copying the data of the subdata storage device a into the subdata storage device b, recording the number information of the data block failed in copying, and generating second recording information based on the recorded number;
and 4, step 4: and generating a data block number to be reconstructed according to the first recording information and the second recording information, reconstructing a corresponding data block according to a current raid algorithm, and writing the reconstructed data block into the sub-data storage device b.
The system comprises: the device comprises a numbering module, a first recording module, a replacing module, a second recording module and a data reconstruction module.
The present application is described below by way of example with reference to a magnetic disk:
firstly, numbering each data block of a disk; then, when there is a disk3 damaged, the damaged disk is kicked out of raid5, and raid5 is in a degraded state. All blocks that are overwritten are recorded. As shown in fig. 6, when new data is written into block 2, on the one hand, we change the data of block 2 to the corresponding C1 ', Cp ', C2 ', while recording that block 2 was overwritten. In this process, we record all the overwritten disk blocks and call "record table 1".
Then, the data on disk3 'is recovered offline, and we need to change to disk 3' since disk3 has been corrupted. Now disk 3' is a blank disk, we proceed as follows in order to reduce reconstruction time: copy the data on disk3 to disk 3', since disk3 corrupted we assumed that at this time Ap, B3, C3, copy succeeded and D3 copy failed, we recorded the failed data block 3; when copy is completed, we get a disk 3' with incomplete data and a record table with copy failure, and call these data as "record table 2"
Then, disk 3' is put into the system, and the light reconstruction process is started to reconstruct only the data blocks of "recording table 1" + "recording table 2"; by "record table 1" we found that block 2 is to be reconstructed, we calculated C3 'from C1' and Cp 'and C2'. We found by "record Table 2" that block 3 is to be reconstructed, we calculated D3 by Dp and D1 and D2. We have completed the reconstruction process by writing C3 'and D3 to the corresponding locations of Disk 3', respectively.
Compared with the traditional reconstruction algorithm, the light reconstruction method has different modes that all data blocks need to be calculated once by using the algorithm corresponding to the raid, and the light reconstruction method is a reconstruction scheme which only needs to use the algorithm corresponding to the raid for part of necessary data blocks through certain processing; this means that the reconstruction is performed using the partial data of "record table 1" + "record table 2".
In addition, the data storage device is easy to have errors, but the device itself is not damaged, and the method or the system in the application can also be used for processing, specifically:
a false kick (server) scene. And (4) a non-persistent damage scene of the disk. Such as caused by excessive temperature, or by external shock, or by electromagnetic interference. The disc is kicked, and then the disc is found to be undamaged, and then is automatically recovered. Only partial data blocks in the false kick process are reconstructed.
The method comprises the following specific steps:
firstly, numbering each data block of a disk; then, when there is a temporary damage to the disk3, all the overwritten blocks are recorded. As shown in fig. 6, when new data is written into block 2, on the one hand, we change the data of block 2 to the corresponding C1 ', Cp ', C2 ', while recording that block 2 was overwritten. In this process, we record all the overwritten disk blocks and call "record table 1".
Then, we find that disk3 has recovered. Disk3 then directly reengages the light reconstruction process.
Then, starting a light reconstruction process, and reconstructing only the data block of the record table 1; by "record table 1" we found that block 2 is to be reconstructed, we calculated C3 'from C1' and Cp 'and C2'. We write C3' to the corresponding location of Disk3 to complete the reconstruction process.
One or more technical solutions provided by the present application have at least the following technical effects or advantages:
the damaged disk is generally damaged by partial equator or sectors, and not all data is damaged, but the method and the system in the application only recover the damaged data block and the data rewritten after the damage, compared with the traditional mode, the efficiency is obviously improved, a large amount of calculation is needed in the traditional mode, and then all data is recovered, the data information needing to be reconstructed is generated through the first recorded information and the second recorded information, and the corresponding data block is reconstructed;
the idea of the patent can also be utilized to solve the problem that the reconstruction time is too long due to non-persistent faults such as vibration, overheating, electromagnetic interference and the like (the faults can cause that the disk cannot be normally used within a certain time and is kicked out of the raid group, but after the disk is found not to be really damaged, the disk can be added into the raid group again and the reconstruction is started).
The method can also solve the problem that the reconstruction time is too long because a user mistakenly extracts a normal disk in use (which often happens when the user maintains equipment, when the disk is found to be normal after being hot extracted, and then the disk is hot inserted, the system can carry out full disk reconstruction on the disk).
Furthermore, when new device data is constructed, data on damaged devices are used as much as possible, the damaged disks do not participate in external services, reading data from the damaged disks on an IO model is sequential IO reading, the new devices do not participate in the external services at the moment, and the IO is sequential IO writing; in the conventional method, reading data and writing data are all random IO (due to external services). The read-write efficiency of the least sequential IO is improved by 5 times, usually 10 times, even 10 times than that of the random IO. Therefore, IO read-write efficiency can be greatly improved; in addition, a large amount of calculation work is omitted in the data construction process, the data does not need to be checked and calculated through a CPU (Central processing Unit), the data can be directly transferred from a bad disk to a new disk through a DMA (direct memory access) technology, and the efficiency is greatly improved.
Furthermore, the idea of the present invention can be utilized to solve the problem of too long reconstruction time caused by non-persistent failures such as vibration, overheating, electromagnetic interference, etc. (these failures can cause that the disk cannot be normally used within a certain time and is kicked out of the raid group, but after the disk is found not to be really damaged, the disk can be rejoined into the raid group and the reconstruction is started). The method can also solve the problem that the reconstruction time is too long because a user mistakenly extracts a normal disk in use (which often happens when the user maintains equipment, when the disk is found to be normal after being hot extracted, and then the disk is hot inserted, the system can carry out full disk reconstruction on the disk).
Further, in the process of traditional algorithm reconstruction, a large amount of reading and writing can be performed on the disk, and the cpu is used for calculation, and at this time, the external service is difficult to acquire corresponding reading and writing and cpu resources, so that the external service efficiency is greatly reduced. In the process of recovering data, the data on the bad disk is used as much as possible, the bad disk does not participate in the service, the new disk does not participate in the service at the moment, and a large amount of calculation work is not needed, so that the new disk basically does not compete with the external service for computer resources. The processing capacity of the external service is ensured.
Therefore, the technical problems that the data recovery mode of the existing data storage device is large in calculation amount and low in efficiency, and the external service processing capacity of the data storage device is seriously reduced in the data recovery process are effectively solved, the data recovery of the data storage device is efficiently and quickly completed, and the technical effect of the external service processing capacity of the data storage device is guaranteed.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A data recovery method of a data storage device based on raid technology is characterized by comprising the following two situations:
situation one, data storage device corruption;
step 1: numbering each data block in the data storage device, wherein the data storage device comprises N sub data storage devices, and N is a positive integer greater than or equal to 1;
step 2: when a subdata storage device a in the data storage device is damaged, recording corresponding data block numbers of all data which are not successfully written in a when a is damaged and corresponding data block numbers of all data written in after a is damaged, and generating first recording information based on the recorded numbers;
and step 3: replacing the damaged subdata storage device a with a complete subdata storage device b, copying the data of the subdata storage device a into the subdata storage device b, recording the number information of the data block failed in copying, and generating second recording information based on the recorded number;
and 4, step 4: generating a data block number to be reconstructed through the first recording information and the second recording information, reconstructing a corresponding data block according to a raid algorithm, and writing the reconstructed data block into the sub data storage device b;
case two: an error occurs in the data storage device;
s1: numbering each data block of the disk;
s2: when a disk3 is temporarily damaged, recording all the rewritten blocks, recording all the rewritten disk blocks, and calling the data as 'recording table 1';
s3: when the disk3 is recovered, directly participates in the reconstruction process, disk3 reconstructs the data blocks of "recording table 1".
2. The method for recovering data of a data storage device based on raid technology according to claim 1, wherein the step 4 specifically includes:
merging the first recording information and the second recording information to generate a number set of all data blocks needing to be reconstructed;
and performing data reconstruction on the data block according to a reconstruction algorithm corresponding to the raid, calculating data of the current data block in the sub data storage device b, and writing the data into the data block.
3. The method for recovering data of a data storage device based on raid technology according to claim 1, wherein after step 1, before step 2, a determination step is further included, and the determination step specifically is:
judging whether the damage of the data storage device is true or false, and if true, performing subsequent steps; if the record is false, skipping step 3, and setting the second record information as null, and performing the subsequent steps.
4. The method for recovering data of a data storage device based on raid technology according to claim 1, wherein the step 2 specifically includes: when new data is written into the data block, on one hand, the data of the data block is changed into corresponding data, the data block is recorded to be rewritten, the number information of all rewritten data blocks is recorded, and first recording information is generated.
5. The data recovery method of a data storage device based on raid technology according to claim 1, wherein said child data storage devices include but are not limited to: server cluster, server, PC, magnetic disk, tape library, U disk, optical disk and hard disk.
6. A data recovery system of a data storage device based on raid technology is characterized in that according to the damage situation of the data storage device, the system comprises two modes:
when the data storage device is damaged, the system comprises:
a numbering module to: numbering each data block in the data storage device, wherein the data storage device comprises N sub data storage devices, and N is a positive integer greater than or equal to 1;
a first recording module to: when a subdata storage device a in the data storage device is damaged, recording the data block numbers of all data which are not successfully written in a when a is damaged and the data block numbers of all data written in after a is damaged, and generating first recording information based on the recorded numbers;
a replacement module for: replacing the damaged subdata storage device a with a complete subdata storage device b;
a second recording module to: copying the data of the sub-data storage device a to the sub-data storage device b, recording the data block failed in copying and the corresponding number information, and generating second recording information;
a data reconstruction module to: generating data information to be reconstructed through the first recording information and the second recording information, reconstructing a corresponding data block, and writing the reconstructed data block into the sub-data storage device b;
when the data storage device is damaged, the system comprises:
the numbering module is used for numbering each data block of the disk;
a first recording module to: when a disk3 is temporarily damaged, recording all the rewritten blocks, recording all the rewritten disk blocks, and calling the data as 'recording table 1';
a data reconstruction module to: when the disk3 is recovered, directly participates in the reconstruction process, disk3 reconstructs the data blocks of "recording table 1".
7. The data recovery system of a data storage device based on raid technology according to claim 6, wherein the data information to be reconstructed is generated by the first record information and the second record information, and the corresponding data block is reconstructed, specifically including:
merging the first recording information and the second recording information to generate a number set of all data blocks needing to be reconstructed;
and performing data reconstruction on the data block according to a reconstruction algorithm corresponding to the raid, calculating data of the current data block in the sub data storage device b, and writing the data into the data block.
8. The data recovery system of a data storage device based on raid technology according to claim 6, wherein said first record information specifically includes but is not limited to: tables, logs, bitmaps, databases.
9. The data recovery system of a data storage device based on raid technology according to claim 6 wherein when new data is written into a data block, on one hand, the data of the data block is changed to corresponding data, and at the same time, the data block is recorded as being overwritten, and the number information of all overwritten data blocks is recorded, and the first record information is generated.
10. A raid technology based data storage device data recovery system according to claim 6 wherein said child data storage devices include but are not limited to: server cluster, server, PC, magnetic disk, tape library, U disk, optical disk and hard disk.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710153658.XA CN106933707B (en) | 2017-03-15 | 2017-03-15 | Data recovery method and system of data storage device based on raid technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710153658.XA CN106933707B (en) | 2017-03-15 | 2017-03-15 | Data recovery method and system of data storage device based on raid technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106933707A CN106933707A (en) | 2017-07-07 |
| CN106933707B true CN106933707B (en) | 2020-11-06 |
Family
ID=59432629
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710153658.XA Expired - Fee Related CN106933707B (en) | 2017-03-15 | 2017-03-15 | Data recovery method and system of data storage device based on raid technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106933707B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109726036B (en) * | 2018-11-21 | 2021-08-20 | 华为技术有限公司 | Data reconstruction method and device in storage system |
| CN109901953B (en) * | 2019-02-14 | 2022-07-08 | 新华三技术有限公司成都分公司 | Data reconstruction method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN102945141A (en) * | 2012-11-09 | 2013-02-27 | 华为技术有限公司 | System and method for improving storage performance of RAID (redundant array of independent disks) group |
| CN103729268A (en) * | 2014-01-15 | 2014-04-16 | 浪潮电子信息产业股份有限公司 | Data recovery method for RAID5 with two disks lost |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4491330B2 (en) * | 2004-11-08 | 2010-06-30 | 富士通株式会社 | Disk array device, data recovery method and data recovery program |
| WO2014190501A1 (en) * | 2013-05-29 | 2014-12-04 | 华为技术有限公司 | Data recovery method, storage device, and storage system |
| CN105740091B (en) * | 2014-12-10 | 2019-04-26 | 华为技术有限公司 | Data backup, restoration methods and equipment |
-
2017
- 2017-03-15 CN CN201710153658.XA patent/CN106933707B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN102945141A (en) * | 2012-11-09 | 2013-02-27 | 华为技术有限公司 | System and method for improving storage performance of RAID (redundant array of independent disks) group |
| CN103729268A (en) * | 2014-01-15 | 2014-04-16 | 浪潮电子信息产业股份有限公司 | Data recovery method for RAID5 with two disks lost |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106933707A (en) | 2017-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7143308B2 (en) | Apparatus, system, and method for differential rebuilding of a reactivated offline RAID member disk | |
| US8843782B2 (en) | Method and apparatus for reconstructing redundant array of inexpensive disks, and system | |
| US6892276B2 (en) | Increased data availability in raid arrays using smart drives | |
| US20060117216A1 (en) | Program, storage control method, and storage system | |
| JPWO2006123416A1 (en) | Disk failure recovery method and disk array device | |
| US20090210742A1 (en) | Methods, systems and media for data recovery using global parity for multiple independent RAID levels | |
| CN105302667B (en) | High reliability data backup and restoration methods based on aggregated structure | |
| JP2005122338A (en) | Disk array device having spare disk drive, and data sparing method | |
| JP2008539474A (en) | Power safe disk storage device, system and method | |
| CN102521058A (en) | Disk data pre-migration method of RAID (Redundant Array of Independent Disks) group | |
| CN102508733B (en) | A kind of data processing method based on disk array and disk array manager | |
| US7155634B1 (en) | Process for generating and reconstructing variable number of parity for byte streams independent of host block size | |
| WO2020103512A1 (en) | Data reconstruction method and device in storage system | |
| CN104881242A (en) | Data writing method and data writing device | |
| CN106933707B (en) | Data recovery method and system of data storage device based on raid technology | |
| CN116204137B (en) | Distributed storage system, control method, device and equipment based on DPU | |
| US7600151B2 (en) | RAID capacity expansion interruption recovery handling method and system | |
| US20030163757A1 (en) | RAID subsystem and data input/output and recovery method in disk error mode | |
| JP6055262B2 (en) | Video recording apparatus and program thereof | |
| US20190354433A1 (en) | Parity log with by-pass | |
| JP3288724B2 (en) | Method of tracking incomplete writes in a disk array, and disk storage system performing such a method | |
| CN111897676A (en) | File backup method and device based on database index | |
| US7788525B2 (en) | Fault tolerance system and method for multiple failed disks in a disk array | |
| JP2016004356A (en) | Control device for storage device, control method for storage device, and control program for storage device | |
| CN110618897B (en) | VGDA (virtual volume data acquisition) information-based VG data recovery 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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201106 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |