WO2017041670A1

WO2017041670A1 - Data recovery method and apparatus

Info

Publication number: WO2017041670A1
Application number: PCT/CN2016/097953
Authority: WO
Inventors: 罗庆超
Original assignee: 华为技术有限公司
Priority date: 2015-09-09
Filing date: 2016-09-02
Publication date: 2017-03-16
Also published as: CN105242985A; CN105242985B

Abstract

Provided are a data recovery method and apparatus, which fall within the field of computers. The method comprises: receiving fault notification information about a magnetic head, wherein the fault notification information about the magnetic head carries identification of a faulty magnetic head (201); based on the identification of the faulty magnetic head, determining a backup position of target metadata, wherein metadata of the faulty magnetic head is stored at the backup position of the target metadata, and each of the magnetic heads is provided with a metadata backup position in advance (202); acquiring metadata corresponding to the faulty magnetic head from the backup position of the target metadata, wherein the metadata is used to describe a data address and attribute information about data stored in a target disk sheet, and the target disk sheet is a disk sheet which is accessed by the faulty magnetic head (203); and based on the attribute information described by the acquired metadata, recovering the data stored in the target disk sheet (204).By means of metadata stored in a backup position of target metadata, data stored in a target disk sheet corresponding to a faulty magnetic head can be rapidly recovered, thereby reducing the cost of recovering data of an upper layer system, and improving the efficiency of data recovery.

Description

Data repair method and device

Technical field

The present invention relates to the field of computers, and in particular, to a data repair method and apparatus.

Background technique

The magnetic head and the disc are the most basic components of the magnetic disk, and in order to meet the capacity requirement of the magnetic disk, the magnetic disk may include a plurality of magnetic heads and a plurality of optical discs, and one magnetic head can access data stored in one disc, that is, The head is a key component of disk access data. When the head fails, the data stored on the corresponding disk of the head cannot be accessed. Therefore, it is especially important to repair the data stored in the corresponding disk of the head.

At present, the data repair process may be: when receiving the head fault information, determining the entire disk fault where the fault head is located. At this time, all the data stored in the entire fault disk may be directly backed up to other disks, and the The failed disk is formatted to repair the data in the failed disk, and the failed disk can continue to be used later.

In the process of implementing the present invention, the inventors have found that the prior art has at least the following problems:

Since a head is faulty, other heads in the disk where the head is located can also normally access the data stored in the corresponding disk. Therefore, formatting the entire disk not only increases the cost of data repair, but also increases the time for data repair. , reducing the efficiency of data repair.

Summary of the invention

In order to solve the problem of the prior art, an embodiment of the present invention provides a data repair method and apparatus. The technical solution is as follows:

In a first aspect, a data repair method is provided, the method comprising:

Receiving a head failure notification information, wherein the head failure notification information carries a fault head identifier;

Determining, according to the faulty magnetic head identifier, a target metadata backup location, where the target metadata backup location stores metadata of the faulty magnetic head, and each of the magnetic heads is provided with a metadata backup location in advance;

Obtaining, from the target metadata backup location, metadata corresponding to the faulty magnetic head, where the metadata is used to describe a data address and attribute information of data stored in a target disc, where the target disc is Describe the disk accessed by the faulty head;

The data stored in the target disc is repaired based on the attribute information described by the acquired metadata.

With reference to the first aspect, in the first possible implementation manner of the foregoing first aspect, the obtaining, before the acquiring the metadata corresponding to the faulty head from the target metadata backup location, the method further includes:

Obtaining mapping information of the target disk, where the mapping information is used to identify address information accessed by the plurality of magnetic heads included in the target disk, where the target disk is the target disk and the disk where the faulty head is located;

Obtaining metadata of a plurality of disks included in the target disk;

Determining, for each of the plurality of metadata, a metadata backup location of the metadata corresponding to the head based on the data address and the mapping information described by the metadata;

The metadata is written into the determined metadata backup location to back up the metadata.

With reference to the first possible implementation manner of the first aspect, in the second possible implementation manner of the foregoing first aspect, the acquiring the mapping information of the target disk includes:

Sending a mapping information obtaining instruction to the target disk, so that the target disk returns address information accessed by the plurality of magnetic heads included in the target disk respectively;

When the address information accessed by the plurality of magnetic heads returned by the target disk is received, the head identifiers of the plurality of magnetic heads and the address information respectively accessed by the plurality of magnetic heads are stored in the head identification and address The correspondence between the information.

With reference to the first possible implementation of the first aspect or the second possible implementation of the first aspect, in a third possible implementation manner of the foregoing first aspect, the described based on the metadata Determining, by the data address and the mapping information, a metadata backup location of the metadata corresponding to the magnetic head, including:

Determining address information of the data address based on the data address described by the metadata;

Determining, according to the determined address information, a corresponding head identifier from a correspondence between the stored head identifier and the address information;

Based on the acquired head identification, the metadata backup location of the metadata corresponding to the head is determined.

With reference to the first aspect, in the fourth possible implementation manner of the foregoing first aspect, after the repairing the data stored in the target disk based on the attribute information described by the acquired metadata, the method further includes:

The failed head is marked to identify that the failed head has failed.

With reference to the first aspect, or the fourth possible implementation manner of the first aspect, in the fifth possible implementation manner of the foregoing first aspect, the attribute information that is described based on the acquired metadata, is related to the target disk After the data stored in the slice is repaired, it also includes:

Sending a capacity refresh command to the target disk, so that the target disk determines a new capacity of the target disk to refresh the capacity of the target disk, and the target disk new capacity is the capacity of the target disk after the refresh.

In a second aspect, a data repair apparatus is provided, the apparatus comprising:

a receiving module, configured to receive a magnetic head failure notification information, where the magnetic head failure notification information carries a faulty magnetic head identifier;

a first determining module, configured to determine, according to the faulty magnetic head identifier, a target metadata backup location, where the target metadata backup location stores metadata of the faulty magnetic head, and each of the magnetic heads is preset with a metadata backup location;

a first obtaining module, configured to acquire metadata corresponding to the faulty magnetic head from the target metadata backup location, where the metadata is used to describe a data address and attribute information of data stored in a target disk, The target disk is a disk accessed by the faulty magnetic head;

And a repairing module, configured to repair data stored in the target disc based on the attribute information described by the acquired metadata.

With reference to the second aspect, in a first possible implementation manner of the foregoing second aspect, the device further includes:

a second obtaining module, configured to acquire mapping information of the target disk, where the mapping information is used to identify address information accessed by the plurality of magnetic heads included in the target disk, where the target disk is the target disk and the The disk where the faulty head is located;

a third obtaining module, configured to acquire metadata of multiple disks included in the target disk;

a second determining module, configured to determine, for each metadata of the plurality of metadata, a metadata backup location of the metadata corresponding to the magnetic head based on the data address and the mapping information described by the metadata;

And a backup module, configured to write the metadata into the determined metadata backup location to back up the metadata.

With reference to the first possible implementation of the second aspect, in the second possible implementation manner of the foregoing second aspect, the second acquiring module includes:

a sending unit, configured to send a mapping information obtaining instruction to the target disk, so that the target disk returns address information accessed by the plurality of magnetic heads included in the target disk respectively;

a storage unit, configured to: when receiving the address information accessed by the plurality of magnetic heads returned by the target disk, the head identifiers of the plurality of magnetic heads and the address letters respectively accessed by the plurality of magnetic heads The information is stored in the correspondence between the head identification and the address information.

With reference to the first possible implementation of the second aspect or the second possible implementation of the second aspect, in a third possible implementation manner of the foregoing second aspect, the second determining module includes:

a first determining unit, configured to determine address information of the data address based on the data address described by the metadata;

An obtaining unit, configured to acquire, according to the determined address information, a corresponding head identifier from a correspondence between the stored head identifier and the address information;

And a second determining unit, configured to determine, according to the acquired head identifier, a metadata backup location of the metadata corresponding to the magnetic head.

With reference to the second aspect, in a fourth possible implementation manner of the foregoing second aspect, the device further includes:

a marking module for marking the faulty head to identify that the faulty head has failed.

In conjunction with the second aspect, or the fourth possible implementation of the second aspect, in the fifth possible implementation manner of the foregoing second aspect, the device further includes:

And a sending module, configured to send a capacity refresh command to the target disk, so that the target disk determines a new capacity of the target disk to refresh the capacity of the target disk, where the target disk new capacity is a capacity of the target disk after the refresh.

The technical solution provided by the embodiment of the present invention has the beneficial effects that, in the embodiment of the present invention, when the upper layer system receives the head fault information, the metadata corresponding to the fault head can be obtained from the target metadata backup location, and based on The acquired metadata quickly repairs the data stored in the target disk corresponding to the faulty head, so that the target disk can continue to be used without formatting the target disk, which reduces the cost of data recovery of the upper system and reduces data repair. Time to improve the efficiency of data recovery.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present invention. Other drawings may also be obtained from those of ordinary skill in the art in light of the inventive work.

1 is a structural diagram of a data repair system according to an embodiment of the present invention;

2 is a flowchart of a data repair method according to an embodiment of the present invention;

3 is a flowchart of another data repair method according to an embodiment of the present invention;

4 is a schematic structural diagram of a data repair apparatus according to an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of another data repair apparatus according to an embodiment of the present invention; FIG.

6 is a schematic structural diagram of a second acquiring module device according to an embodiment of the present invention;

7 is a schematic structural diagram of a second determining module device according to an embodiment of the present invention;

FIG. 8 is a schematic structural diagram of a data repair device according to an embodiment of the present invention.

detailed description

The embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

Before explaining the embodiments of the present invention in detail, the system architecture of the embodiment of the present invention is first introduced. FIG. 1 is a structural diagram of a data repair system according to an embodiment of the present invention. As shown in FIG. 1 , the data repair system includes an upper layer system and a plurality of disks, and the upper layer system is respectively connected to the plurality of disks. The plurality of disks may respectively include a plurality of disks for storing data, and the plurality of disks for respectively accessing data stored on the plurality of disks, the upper layer system It is used to repair data stored in a disk corresponding to a magnetic head that has failed in the plurality of magnetic heads.

2 is a flowchart of a data repair method according to an embodiment of the present invention. Referring to FIG. 2, the data repair method is used in an upper layer system, and the method includes:

Step 201: Receive a head failure notification information, where the head failure notification information carries a fault head identifier.

Step 202: Determine, according to the fault head identifier, a target metadata backup location, where the target metadata backup location stores metadata of the faulty head, and each of the magnetic heads is preset with a metadata backup location.

Step 203: Obtain metadata corresponding to the fault head from the target metadata backup location, where the metadata is used to describe data address and attribute information of data stored in the target disc, where the target disc is the fault The disc accessed by the head.

Step 204: Repair the data stored in the target disc based on the attribute information described by the acquired metadata.

In the embodiment of the present invention, after receiving the head fault information, the upper layer system may obtain the metadata corresponding to the fault head from the target metadata backup position, and quickly repair the data based on the acquired metadata. The barrier head corresponds to the data stored in the target disc, so that the target disk can still be used without formatting the target disk, which reduces the cost of data recovery of the upper system, reduces the time for data repair, and improves data repair. effectiveness.

Optionally, before obtaining the metadata corresponding to the faulty head from the target metadata backup location, the method further includes:

Obtaining metadata of a plurality of disks included in the target disk;

For each of the plurality of metadata, determining, according to the data address and the mapping information described by the metadata, a metadata backup location of the metadata corresponding to the magnetic head;

The metadata is written to the determined metadata backup location to back up the metadata.

Optionally, the obtaining mapping information of the target disk includes:

When the address information accessed by the plurality of magnetic heads returned by the target disk is received, the head identifiers of the plurality of magnetic heads and the address information respectively accessed by the plurality of magnetic heads are stored between the head identification and the address information. Corresponding relationship.

Optionally, determining, according to the data address and mapping information described by the metadata, a metadata backup location of the metadata corresponding to the magnetic head, including:

Optionally, after the repairing the data stored in the target disc based on the attribute information described by the acquired metadata, the method further includes:

The failed head is marked to identify that the failed head has failed.

Optionally, after the data stored in the target disk is repaired based on the attribute information described by the acquired metadata, the method further includes:

Sending a capacity refresh command to the target disk, so that the target disk determines the new capacity of the target disk to refresh the capacity of the target disk, and the new capacity of the target disk is the capacity of the target disk after the refresh.

The optional embodiments of the present invention may be used in any combination to form an optional embodiment of the present invention.

FIG. 3 is a flowchart of a data repair method according to an embodiment of the present invention. Referring to FIG. 3, the method includes:

Step 301: Obtain mapping information of the target disk, where the mapping information is used to identify address information accessed by the plurality of magnetic heads included in the target disk, where the target disk is the target disk and the disk where the faulty head is located, the target disk The slice is the disk accessed by the failed head.

In order to back up the data stored in the disk accessed by the plurality of magnetic heads included in the target disk, the metadata of the data stored in the disk accessed by the plurality of disks needs to be backed up, and before the metadata is backed up, the upper layer system further Need to get the mapping information of the target disk. The operation of the upper layer system to obtain the target disk mapping information may be: the upper layer system sends a mapping information acquisition instruction to the target disk, so that the target disk returns address information accessed by the plurality of magnetic heads included in the target disk; when the upper layer system receives When the address information of the plurality of magnetic heads returned by the target disk is respectively stored, the head identifier of the plurality of magnetic heads and the address information respectively accessed by the plurality of magnetic heads are stored in a correspondence relationship between the head identifier and the address information. .

It should be noted that the upper layer system may be an operating system installed on the device, or may be an application running on the device, and the device may be a terminal or a server. In addition, the upper layer system may be located in the same device as the target disk. Of course, the upper layer system may also be located in a different device from the target disk, which is not specifically limited in this embodiment of the present invention.

The mapping information obtaining instruction is configured to obtain the address information accessed by the plurality of magnetic heads included in the target disk from the target disk, where the mapping information obtaining instruction may be set in the upper layer system in advance, and the mapping information obtaining instruction may be set. A new instruction may be obtained by extending an existing instruction. For example, the inquiry (inquiry) instruction or the report area (reporting area) instruction may be extended, which is not specifically limited in the embodiment of the present invention.

In addition, the address information respectively accessed by the plurality of magnetic heads is a storage address of data stored in the discs accessed by the plurality of magnetic heads, and the address information accessed by the plurality of magnetic heads respectively may include a starting address and a partial offset. The address of the address may also include an address range, which is not specifically limited in this embodiment of the present invention.

It should be noted that one magnetic head can correspond to one address information, and can also correspond to multiple address information, that is, one magnetic head can access a range of addresses on the disc, and can also access multiple address ranges on the disc. No specific restrictions.

When the address information accessed by the plurality of magnetic heads respectively includes a start address and an offset address, the operation of acquiring the target disk mapping information by the upper layer system may be: the upper layer system sends a mapping information acquisition instruction to the target disk, when the target disk receives the When the mapping information acquisition instruction is obtained, the target disk acquires a starting address and an offset address respectively accessed by the plurality of magnetic heads, and sends a starting address and an offset address respectively accessed by the plurality of magnetic heads to the upper layer system, when When the upper layer system receives the start address and the offset address respectively accessed by the plurality of magnetic heads sent by the target disk, storing the plurality of head identifiers, the start address and the offset address respectively accessed by the plurality of magnetic heads, and storing the start address and the offset address respectively accessed by the plurality of magnetic heads In the correspondence between the head identification, the starting address and the offset address.

For example, the target disk includes three magnetic heads, namely a magnetic head 1, a magnetic head 2 and a magnetic head 3. The upper layer system sends a mapping information acquisition instruction to the target disk, and when the target disk receives the mapping information obtaining instruction, the target disk acquires the magnetic head. The starting address of 1 access is 1000H, the offset address is 0040H, the starting address accessed by head 2 is 2000H, the offset address is 0040H, the starting address accessed by head 3 is 3000H, and the offset address is 0040H. The target disk sends the start address and the offset address respectively accessed by the three magnetic heads to the upper layer system, and when the upper layer system receives the start address and the offset address respectively accessed by the three magnetic heads sent by the target disk respectively The magnetic head ID 1 of the magnetic head 1, the start address and the offset address accessed by the magnetic head 1 are stored in a correspondence relationship between the head identification, the start address, and the offset address shown in Table 1 below, and the magnetic head is The head identification ID2 of 2, the start address and the offset address accessed by the magnetic head 2 are stored in the correspondence relationship between the head identification, the start address and the offset address shown in Table 1 below, and the magnetic The magnetic head 3 correspondence between the identifier of the ID3, the start address and offset address accessed by the magnetic head 3, the head identification is stored in the following table 1, the start address and offset address.

Table 1

磁头标识Head identification	起始地址initial address	偏移地址Offset address
ID1ID1	1000H1000H	0040H0040H
ID2ID2	2000H2000H	0040H0040H
ID3ID3	3000H3000H	0040H0040H
……......	……......	……......

It should be noted that, in the embodiment of the present invention, the correspondence relationship between the head identifier, the start address, and the offset address shown in Table 1 is taken as an example, and the above Table 1 does not limit the embodiment of the present invention. .

Similarly, when the address information accessed by the plurality of magnetic heads respectively includes an address range, the upper layer system obtains The operation of the target disk mapping information may be: the upper layer system sends a mapping information obtaining instruction to the target disk, and when the target disk receives the mapping information obtaining instruction, the target disk acquires an address range accessed by the plurality of magnetic heads respectively, and Sending the address range accessed by the plurality of magnetic heads to the upper layer system respectively, when the upper layer system receives the address range accessed by the plurality of magnetic heads respectively sent by the target magnetic disk, respectively, the plurality of magnetic head identifiers and the plurality of magnetic heads respectively The range of addresses accessed is stored in the correspondence between the head identification and the address range.

For example, the target disk includes three magnetic heads, namely a magnetic head 1, a magnetic head 2 and a magnetic head 3. The upper layer system sends a mapping information acquisition instruction to the target disk, and when the target disk receives the mapping information obtaining instruction, the target disk acquires the magnetic head. The address range accessed by 1 is 1000H to 1040H, the address range accessed by the magnetic head 2 is 2000H to 2040H, and the address range accessed by the magnetic head 3 is 3000H to 3040H. The target disk sends the address range accessed by the three magnetic heads respectively. When the upper layer system receives the address range accessed by the three magnetic heads sent by the target disk, the head identifier ID1 of the magnetic head 1 and the address range accessed by the magnetic head 1 are stored in the following Table 2. In the correspondence between the head identification and the address range, the head identification ID2 of the magnetic head 2 and the address range accessed by the magnetic head 2 are stored in the correspondence relationship between the head identification and the address range shown in Table 2 below, and The head ID ID3 of the magnetic head 3 and the address range accessed by the magnetic head 3 are stored in the correspondence relationship between the head identification and the address range as shown in Table 2 below. .

Table 2

磁头标识Head identification	地址范围Address range
ID1ID1	1000H～1040H1000H～1040H
ID2ID2	2000H～2040H2000H～2040H
ID3ID3	3000H～3040H3000H～3040H
……......	……......

It should be noted that in the embodiment of the present invention, the correspondence relationship between the head identifier and the address range shown in Table 2 above is taken as an example, and the above Table 2 does not limit the embodiment of the present invention.

In addition, different types of disks have different types of data addresses, that is, different types of disks, and the types of address information accessed by the heads are different, for example, when the type of the disk is HDD (Hard Disk Drive). The type of address information accessed by the head may be LBA (Logical Block Address), and when the type of the disk is SMR (Shingled Magnetic Recording), the address information accessed by the head The type may be an LBA or a ZONE. The embodiment of the present invention does not specifically limit this.

After the upper layer system obtains the mapping information of the target disk, the upper layer system may back up the metadata of the plurality of disks included in the target disk, as follows.

Step 302: Obtain metadata of a plurality of disks included in the target disk, and determine, for each metadata in the plurality of metadata, a metadata corresponding to the metadata address and the mapping information. The metadata backup location of the head.

In order to back up the metadata, the upper layer system needs to determine the metadata backup location of the metadata corresponding to the head based on the data address and mapping information described by the metadata. The upper layer system determines, according to the data address and the mapping information described by the metadata, the operation of the metadata backup location of the metadata corresponding to the magnetic head: determining an address of the data address based on the data address described by the metadata And determining, according to the determined address information, a corresponding head identifier from the stored correspondence between the head identifier and the address information; and determining, according to the acquired head identifier, a metadata backup position of the metadata corresponding to the head.

When the upper layer system obtains the metadata of the plurality of disks included in the target disk, the upper layer system may generate the valid data stored in the plurality of disks included in the target disk, thereby obtaining the target disk. The metadata of each disc, the metadata of each disc is used to describe the data address and attribute information of the data stored in the disc. Thus, since the metadata is generated based on the valid data stored in the disc, the data address described by the metadata is the storage address of the valid data stored in the disc.

The address information mentioned in the above step 301 may include a start address and an offset address, and may further include an address range. Therefore, when the address information is different, the upper layer system determines the data address based on the data address described by the metadata. The operation of the address information is also different. The following describes the operation of determining the address information of the data address in two cases:

The first type, when the address information includes the start address and the offset address, the upper layer system may obtain the start address and the offset address included in the correspondence between the stored head identifier, the start address, and the offset address, and obtain And a plurality of start addresses and an offset address corresponding to the plurality of start addresses, and selecting, from the plurality of start addresses and the offset addresses corresponding to the plurality of start addresses, the data address described by the metadata The start address and the offset address determine the selected start address and offset address as the address information of the data address.

The operation of selecting, by the upper layer system, the start address and the offset address of the data address described by the metadata from the multiple start addresses and the offset addresses corresponding to the multiple start addresses may be: Each of the plurality of start addresses, the offset corresponding to the start address and the start address Adding addresses, obtaining an end address, comparing the data address described by the metadata with the start address, and comparing the data address described by the metadata with the end address, when the data address is greater than or equal to When the start address is less than or equal to the end address, the start address and the offset address corresponding to the start address are determined as the start address and the offset address where the data address described by the metadata is located.

Or, for each of the plurality of start addresses, subtracting the start address from the data address described by the metadata to obtain an address difference, if the address difference is a positive number and less than or equal to The offset address corresponding to the start address is determined by the start address and the offset address corresponding to the start address as the start address and the offset address where the data address described by the metadata is located.

For example, the data address described by the metadata is 1040H, and the upper layer system obtains the start address and the offset address included in the correspondence between the stored head identifier, the start address, and the offset address, and obtains multiple start addresses. 1000H, 2000H, 3000H, and the offset addresses corresponding to the three start addresses are 0040H, and the three start addresses 1000H, 2000H, and 3000H are respectively added to the corresponding offset addresses 0040H, and the corresponding addresses are obtained. The end addresses are 1040H, 2040H, 3040H, respectively, and the data address 1040H described by the metadata is compared with the start address 1000H, and the data address 1040H described by the metadata is compared with the end address 1040H to determine the data address. 1040H is greater than the start address 1000H and equal to the end address 1040H; the data address 1040H described by the metadata is compared with the start address 2000H, and the data address 1040H described by the metadata is compared with the end address 2040H to obtain data. The address 1040H is smaller than the start address 2000H and smaller than the end address 2040H; the data address 1040H and the start address 3000H described by the metadata Comparing, and comparing the data address 1040H described by the metadata with the end address 3040H, obtaining that the data address 1040H is smaller than the start address 3000H and smaller than the end address 3040H; therefore, the start address 1000H corresponds to the start address The offset address 0040H is determined as the start address and offset address where the data address 1040H described by the metadata is located.

Or, for the starting address 1000H, 2000H, 3000H, the data address 1040H described by the metadata is subtracted from the starting address 1000H, and the address difference is 0040H, and the address difference is a positive number and is equal to the starting address 1000H. Offset address 0040H; the data address 1040H described by the metadata is subtracted from the start address 2000H, and the address difference is -0960H, the address difference is negative and less than the offset address 0040H corresponding to the start address 2000H; The data address 1040H described by the metadata is subtracted from the start address 3000H, and the address difference is -1960H, and the address difference is a negative number and is smaller than the offset address 0040H corresponding to the start address 1000H; therefore, the start The address 1000H and the offset address 0040H corresponding to the start address are determined to be the data address described by the metadata. Start address and offset address.

Second, when the address information includes the address range, the upper layer system may obtain the address range included in the correspondence between the stored head identifier and the address range, and obtain multiple address ranges, and select the multiple address ranges from the multiple address ranges. The address range in which the data address described by the metadata is located determines the selected address range as the address information of the data address.

The operation of the upper layer system from the address range to select the address range in which the data address described by the metadata is located may be: for each address range in the multiple address ranges, the upper layer system of the address range The start address is compared with the data address described by the metadata, and the end address of the address range is compared with the data address described by the metadata, when the data address is greater than or equal to the start address of the address range and When the end address of the address range is less than or equal to, the address range is determined as the address range in which the data address described by the metadata is located.

For example, the data address described by the metadata is 1040H, and each of the multiple address ranges is 1000H-1040H, 2000-2040H, 3000H-3040H, and the upper layer system starts the address range 1000H-1040H. The address 1000H is compared with the data address 1040H, and the end address 1040H of the address range 1000H-1040H is compared with the data address 1040H, and it is determined that the data address 1040H is greater than the start address 1000H and equal to 1040H; the start of the address range 2000H-2040H The address 2000H is compared with the data address 1040H, and the end address 2040H of the address range 2000H-2040H is compared with the data address 1040H, and it is determined that the data address 1040H is smaller than the start address 2000H and smaller than the end address 2040H; and the address range is 3000H to 3040H. The start address 3000H is compared with the data address 3040H, and the end address 3040H of the address range 3000H to 3040H is compared with the data address 1040H, and it is determined that the data address 1040H is smaller than the start address 3000H and smaller than the end address 3040H, and therefore, the address can be The range 1000H to 1040H is determined as the data address 10 described by the metadata. The address range in which 40H is located.

In addition, the upper layer system determines, according to the obtained head identifier, that the metadata corresponding to the metadata backup position of the magnetic head may be: the upper layer system queries the metadata backup strategy based on the acquired head identifier, thereby determining the metadata corresponding to the head of the metadata. The data backup location, wherein the metadata backup policy may include a correspondence between the head identification and the metadata backup location.

It should be noted that the metadata backup policy is used to determine the metadata backup location, and the metadata backup policy may be set in advance. For example, the metadata backup policy may be to back up the metadata to other disks in the disk where the metadata corresponding to the head is located. The embodiment of the present invention does not specifically limit the slice, other disks, and other storable media.

Step 303: Write the metadata into the determined metadata backup location to back up the metadata.

Further, when the upper layer system writes the metadata to the determined metadata backup location, the upper layer system may further determine the metadata corresponding to the head identifier, and write the metadata to the disk corresponding to the head identifier in the target disk. In the film.

Wherein, since the metadata is data describing the data stored in the disc, for each of the plurality of discs included in the target disk, when the data stored in the disc changes, the disc The corresponding metadata also changes, so the upper layer system can update the metadata in the corresponding metadata backup location of the disc. The operation of updating the metadata in the corresponding metadata backup location of the disk may be: the upper layer system receives a metadata update instruction sent by the target disk, where the metadata update instruction carries the updated head identifier and the updated metadata, The upper layer system determines, based on the updated head identifier, the metadata backup location of the updated metadata corresponding to the head, and replaces the metadata stored in the metadata backup location with the updated metadata.

It should be noted that the metadata update instruction is used to update the changed metadata, update the identifier of the head corresponding to the changed metadata of the head, and the updated head identifier may be the number, name, etc. of the magnetic head, and the present invention. The embodiment does not specifically limit this.

Step 304: Receive magnetic head failure notification information, and the magnetic head failure notification information carries a faulty magnetic head identifier.

When a head of the target disk fails, the target disk where the fault head is located sends a head fault notification information to the upper layer system, and the head fault notification information is used to notify the upper system that the head is faulty, and the upper layer system is based on the head fault information. Determine the faulty head.

Wherein, when the target disk determines that the magnetic head cannot access the data stored in the corresponding target disk, it is determined that the magnetic head is faulty, and the faulty magnetic head is identified as an identifier of the faulty magnetic head, and the faulty magnetic head identifier may be the number of the faulty magnetic head, the fault The name of the magnetic head and the like are not specifically limited in the embodiment of the present invention.

It should be noted that when the target disk sends the head fault information to the upper layer system, it may be sent through an instruction in the upper layer system. For example, the instruction may be a command such as Read or Write, or may be an instruction such as Test Unit Ready or Inquiry. This embodiment of the present invention does not specifically limit this.

Step 305: Determine, according to the fault head identifier, a target metadata backup location, where the target metadata backup location stores metadata of the faulty head, and each of the magnetic heads is previously provided with a metadata backup location.

In order to quickly repair the data stored in the target disk corresponding to the faulty head, the upper layer system needs to acquire the metadata of the data stored in the target disk, and before the metadata is acquired, the target metadata backup location needs to be determined based on the faulty head identifier. And the upper layer system determines, according to the fault head identifier, the operation of the target metadata backup location: the upper layer system queries the metadata backup policy based on the fault head identifier, thereby determining a metadata backup location of the fault head, and the fault head is The metadata backup location is determined as the target metadata backup location.

Step 306: Obtain metadata corresponding to the faulty magnetic head from the target metadata backup location, where the metadata is used to describe data address and attribute information of data stored in the target disk.

Specifically, the upper layer system can read the data stored in the target metadata backup location, and determine the read data as the metadata corresponding to the faulty head.

Step 307: Repair the data stored in the target disc based on the attribute information described by the acquired metadata.

Specifically, the upper layer system reconstructs the data stored in the target disk based on the attribute information described by the acquired metadata, determines the data repair location of the target disk, and writes the reconstructed data to the data repair location. , thereby completing the repair of the data stored in the target disc.

The operation of the upper layer system to determine the data repair location of the target disk may be: the upper layer system may obtain the corresponding data repair location from the corresponding relationship between the stored disk identifier and the data repair location based on the target disk identifier. , the obtained repair location is determined as the data repair location of the target disc.

It should be noted that the target disc is identified as the identifier of the target disc, and the target disc identifier may be the number, the name, and the like of the target disc, which is not specifically limited in this embodiment of the present invention.

Further, after the upper layer system repairs the data stored in the target disk, the upper layer system can mark the faulty head to identify that the faulty head has failed.

The operation of marking the faulty magnetic head in the upper layer system may be: releasing the address information accessed by the faulty magnetic head, or shielding the address information accessed by the faulty magnetic head, which is not specifically limited in this embodiment of the present invention.

In addition, in order to achieve further management of the target disk by the upper layer system, after the upper layer system repairs the data stored in the target disk, the upper layer system may further send a capacity refresh instruction to the target disk, so that the target disk determines the new capacity of the target disk, The capacity of the target disk is refreshed, and the new capacity of the target disk is the capacity of the target disk after the refresh.

Specifically, the upper layer system may send a capacity refresh instruction to the target disk, when the target disk receives When the capacity refresh command is executed, the total disk capacity can be subtracted from the target disk capacity to obtain the new capacity of the target disk.

Further, after the target disk determines the new capacity of the target disk, the target disk can also send the new capacity of the target disk to the upper layer system, so that the upper layer system can manage the capacity of the target disk.

In the embodiment of the present invention, after acquiring the mapping information of the target disk, the upper layer system backs up the metadata in the target disk according to the metadata backup strategy. When the head fails, the upper layer system may be based on the mapping information and target metadata of the target disk. The backup location quickly repairs the data stored in the target disk corresponding to the failed head, that is, when the head fails, the upper system can repair only the data stored in the corresponding disk of the failed head without storing the entire disk. The data is repaired, so that the target disk can still be used without formatting the target disk, which reduces the cost of data recovery of the upper system, reduces the time for data repair, and improves the efficiency of data repair.

FIG. 4 is a schematic structural diagram of a data repair apparatus according to an exemplary embodiment. Referring to FIG. 4, the apparatus includes a receiving module 401, a first determining module 402, a first obtaining module 403, and a repairing module 404.

The receiving module 401 is configured to receive a magnetic head failure notification information, where the magnetic head failure notification information carries a faulty magnetic head identifier;

The first determining module 402 is configured to determine, according to the faulty magnetic head identifier, a target metadata backup location, where the target metadata backup location stores metadata of the faulty magnetic head, and each of the magnetic heads is preset with a metadata backup location;

The first obtaining module 403 is configured to obtain, from the target metadata backup location, metadata corresponding to the faulty magnetic head, where the metadata is used to describe a data address and attribute information of data stored in the target disk. The target disc is a disc accessed by the faulty head;

The repairing module 404 is configured to repair the data stored in the target disc based on the attribute information described by the acquired metadata.

Optionally, referring to FIG. 5, the apparatus further includes:

The second obtaining module 405 is configured to obtain mapping information of the target disk, where the mapping information is used to identify address information accessed by the plurality of magnetic heads included in the target disk, where the target disk is the target disk and the fault head is located Disk

a third obtaining module 406, configured to acquire metadata of multiple disks included in the target disk;

a second determining module 407, configured to calculate, according to the metadata for each of the plurality of metadata Determining, according to the described data address and the mapping information, a metadata backup location of the metadata corresponding to the magnetic head;

The backup module 408 is configured to write the metadata into the determined metadata backup location to back up the metadata.

Optionally, referring to FIG. 6, the second obtaining module 405 includes:

The sending unit 4051 is configured to send a mapping information obtaining instruction to the target disk, so that the target disk returns address information accessed by the plurality of magnetic heads included in the target disk respectively;

The storage unit 4052 is configured to: when receiving the address information accessed by the plurality of magnetic heads returned by the target disk, storing the head identifier of the plurality of magnetic heads and the address information accessed by the plurality of magnetic heads respectively in the head identifier In the correspondence with the address information.

Optionally, referring to FIG. 7, the second determining module 407 includes:

The first determining unit 4071 is configured to determine address information of the data address based on the data address described by the metadata;

The obtaining unit 4072 is configured to obtain, according to the determined address information, a corresponding head identifier from a correspondence between the stored head identifier and the address information;

The second determining unit 4073 is configured to determine, according to the acquired head identifier, a metadata backup location of the metadata corresponding to the magnetic head.

Optionally, the device further includes:

The sending module is configured to send a capacity refresh command to the target disk, so that the target disk determines a new capacity of the target disk to refresh the capacity of the target disk, and the new capacity of the target disk is the capacity of the target disk after the refresh.

In summary, in the embodiment of the present invention, when the upper layer system receives the head fault information, the metadata corresponding to the fault head can be obtained from the target metadata backup position, and the fault head is quickly repaired based on the acquired metadata. The data stored in the target platter, so that the target disk can continue to be used without formatting the target disk, which reduces the cost of data recovery of the upper layer system, reduces the time for data repair, and improves the efficiency of data repair.

It should be noted that, in the data repairing apparatus provided by the foregoing embodiment, only the division of each functional module described above is performed when performing repair data, and in actual application, the above-mentioned work may be performed as needed. The allocation can be done by different functional modules, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the embodiment of the data repair apparatus and the data repair method provided by the foregoing embodiments are the same concept, and the specific implementation process is described in detail in the method embodiment, and details are not described herein again.

Referring to FIG. 8, an embodiment of the present invention provides a data repair device, which includes: a processor 801, a memory 802, a bus 803, and a communication interface 808;

The memory 802 is configured to store a computer execution instruction 8021 through which the processor 801 and the memory 802 are connected. When the data storage device is in operation, the processor 801 executes a computer execution instruction stored in the memory 802 to cause the instruction processing device to execute the following data. Repair methods, including:

Optionally, before the obtaining the metadata corresponding to the faulty head from the target metadata backup location, the method further includes:

Obtaining metadata of a plurality of disks included in the target disk;

Optionally, the acquiring mapping information of the target disk includes:

When receiving the address information accessed by the plurality of magnetic heads returned by the target disk, respectively The head identification of the plurality of magnetic heads and the address information respectively accessed by the plurality of magnetic heads are stored in a correspondence relationship between the head identification and the address information.

Optionally, the determining, according to the data address and the mapping information described by the metadata, the metadata backup location of the metadata corresponding to the magnetic head, including:

Optionally, after the repairing the data stored in the target disk based on the attribute information described by the acquired metadata, the method further includes:

The failed head is marked to identify that the failed head has failed.

In summary, in the embodiment of the present invention, after receiving the head fault information, the upper layer system can obtain the metadata corresponding to the fault head through the target metadata backup position, and quickly repair the fault head corresponding to the fault based on the acquired metadata. The data stored in the target platter, so that the target disk can continue to be used without formatting the target disk, which reduces the cost of data recovery of the upper layer system, reduces the time for data repair, and improves the efficiency of data repair.

A person skilled in the art may understand that all or part of the steps of implementing the above embodiments may be completed by hardware, or may be instructed by a program to execute related hardware, and the program may be stored in a computer readable storage medium. The storage medium mentioned may be a read only memory, a magnetic disk or an optical disk or the like.

The above are only the preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalents, improvements, etc., which are within the spirit and scope of the present invention, should be included in the protection of the present invention. Within the scope.

Claims

A data repair method, characterized in that the method comprises:

Receiving a head failure notification information, wherein the head failure notification information carries a fault head identifier;

Determining, according to the faulty magnetic head identifier, a target metadata backup location, where the target metadata backup location stores metadata of the faulty magnetic head, and each of the magnetic heads is provided with a metadata backup location in advance;

Obtaining, from the target metadata backup location, metadata corresponding to the faulty magnetic head, where the metadata is used to describe a data address and attribute information of data stored in a target disc, where the target disc is Describe the disk accessed by the faulty head;

The data stored in the target disc is repaired based on the attribute information described by the acquired metadata.
The method of claim 1, wherein the obtaining, before the obtaining the metadata corresponding to the faulty head from the target metadata backup location, the method further comprises:

Obtaining mapping information of the target disk, where the mapping information is used to identify address information accessed by the plurality of magnetic heads included in the target disk, where the target disk is the target disk and the disk where the faulty head is located;

Obtaining metadata of a plurality of disks included in the target disk;

Determining, for each of the plurality of metadata, a metadata backup location of the metadata corresponding to the head based on the data address and the mapping information described by the metadata;

The metadata is written into the determined metadata backup location to back up the metadata.
The method of claim 2, wherein the obtaining mapping information of the target disk comprises:

Sending a mapping information obtaining instruction to the target disk, so that the target disk returns address information accessed by the plurality of magnetic heads included in the target disk respectively;

When the address information accessed by the plurality of magnetic heads returned by the target disk is received, the head identifiers of the plurality of magnetic heads and the address information respectively accessed by the plurality of magnetic heads are stored in the head identification and address The correspondence between the information.
The method according to claim 2 or 3, wherein the determining, based on the data address and the mapping information described by the metadata, the metadata backup location of the metadata corresponding to the magnetic head comprises:

Determining address information of the data address based on the data address described by the metadata;

Determining, according to the determined address information, a corresponding head identifier from a correspondence between the stored head identifier and the address information;

Based on the acquired head identification, the metadata backup location of the metadata corresponding to the head is determined.
The method according to claim 1, wherein the repairing the data stored in the target disc based on the attribute information described by the acquired metadata further comprises:

The failed head is marked to identify that the failed head has failed.
The method according to claim 1 or 5, wherein after the repairing the data stored in the target disc based on the attribute information described by the acquired metadata, the method further includes:

Sending a capacity refresh command to the target disk, so that the target disk determines a new capacity of the target disk to refresh the capacity of the target disk, and the target disk new capacity is the capacity of the target disk after the refresh.
A data repair device, characterized in that the device comprises:

a receiving module, configured to receive a magnetic head failure notification information, where the magnetic head failure notification information carries a faulty magnetic head identifier;

a first determining module, configured to determine, according to the faulty magnetic head identifier, a target metadata backup location, where the target metadata backup location stores metadata of the faulty magnetic head, and each of the magnetic heads is preset with a metadata backup location;

a first obtaining module, configured to acquire metadata corresponding to the faulty magnetic head from the target metadata backup location, where the metadata is used to describe a data address and attribute information of data stored in a target disk, The target disk is a disk accessed by the faulty magnetic head;

a repair module for using the attribute information described by the acquired metadata for the target disk The data stored in the slice is repaired.
The device of claim 7 wherein said device further comprises:

a second obtaining module, configured to acquire mapping information of the target disk, where the mapping information is used to identify address information accessed by the plurality of magnetic heads included in the target disk, where the target disk is the target disk and the The disk where the faulty head is located;

a third obtaining module, configured to acquire metadata of multiple disks included in the target disk;

a second determining module, configured to determine, for each metadata of the plurality of metadata, a metadata backup location of the metadata corresponding to the magnetic head based on the data address and the mapping information described by the metadata;

And a backup module, configured to write the metadata into the determined metadata backup location to back up the metadata.
The device of claim 8, wherein the second obtaining module comprises:

a sending unit, configured to send a mapping information obtaining instruction to the target disk, so that the target disk returns address information accessed by the plurality of magnetic heads included in the target disk respectively;

a storage unit, configured to store, when receiving the address information accessed by the plurality of magnetic heads returned by the target disk, address information of the plurality of magnetic heads and address information accessed by the plurality of magnetic heads respectively In the correspondence between the head identification and the address information.
The device according to claim 8 or 9, wherein the second determining module comprises:

a first determining unit, configured to determine address information of the data address based on the data address described by the metadata;

An obtaining unit, configured to acquire, according to the determined address information, a corresponding head identifier from a correspondence between the stored head identifier and the address information;

And a second determining unit, configured to determine, according to the acquired head identifier, a metadata backup location of the metadata corresponding to the magnetic head.
The device of claim 7 wherein said device further comprises:

a marking module, configured to mark the faulty magnetic head to identify the faulty magnetic head barrier.
The device according to claim 7 or 11, wherein the device further comprises:

And a sending module, configured to send a capacity refresh command to the target disk, so that the target disk determines a new capacity of the target disk to refresh the capacity of the target disk, where the target disk new capacity is a capacity of the target disk after the refresh.