CN103384550A - Data storage method and device - Google Patents

Abstract

The embodiment of the invention discloses a data storage method and device, belonging to the technical field of electronic information, which can store data in multiple resource pools to reduce the probability of completely damaging the data and improve the security of data. The data storage method is used for the storage system, the resource pools in the storage system are logically divided into at least 2 sub resource pools, each sub resource pool comprises adjacent N storage apparatus, N being larger than and equal to 2. The data storage method comprises the following steps: dividing the data to be stored into R slices, distributing the slices into the divided sub resource pools, wherein the number of the desirably generated copies of the data to be stored is small than N, R being larger than and equal to 2; generating a copy slice of each slice distributed in each sub resource pool and storing the copy slice in the sub resource pool corresponding to the slice, wherein the copy slice is corresponded to the same slice of the data to be stored.

Description

Method and device for storing data

technical field

The invention relates to the technical field of electronic information, in particular to a method and device for storing data.

Background technique

Distributed storage technology is a commonly used data storage technology. In the distributed storage scenario, all hard disks in the system can be managed as a storage resource pool in a unified manner. When the system reads, writes and stores data, it uses the The entire storage resource pool is used as a storage area for data interaction. For example:

The distributed storage system can map a virtual volume to all hard disks in the storage resource pool, and divide the space on the volume into several 1M data blocks, and each data block corresponds to one of all the hard disks in the resource pool. The block stores the logical partition unit Partition. When a Partition has multiple copies, all data in a Partition will be saved in multiple copies. For example, in a double-copy scenario, each data block corresponds to two Partitions in all hard disks in the resource pool, and the two The content of Partition is exactly the same. According to the commonly used allocation algorithm, the same two Partitions, such as: P1 and P1', are often allocated on two different hard disks, such as: P1 is on hard disk 1, and P1' is on hard disk 2, so that the Partition can be evenly allocated In the entire resource pool, because this method of allocating Partitions can maximize the read and write speed of hard disks in the resource pool, it is widely used.

When any hard disk in the distributed storage system is damaged, data reconstruction can be performed. For example, if hard disk 1 is damaged, P1, P4', P5, and P8' on hard disk 1 have corresponding copies on hard disks 2, 3, and 4. , then the data on hard disk 1 can be restored through the corresponding copies on hard disks 2, 3, and 4.

In the existing distributed storage system, if any hard disk is damaged, data reconstruction will be performed. During the data reconstruction process, if other hard disks in the storage resource pool fail again, the data of the entire virtual volume will be damaged. For example: As shown in Figure 1, when the hard disk 1 is damaged and the data recovery starts, if the hard disk 2 is damaged, the corresponding copy P1' for repairing the hard disk 1 stored on the hard disk 2 will be damaged, so that the data cannot be repaired, resulting in Data corruption of the entire virtual volume reduces data security.

Contents of the invention

Embodiments of the present invention provide a method and device for storing data, which can divide all storage devices in the storage system into at least two resource pools, and store data in the divided resource pools. Since each resource pool The data in the resource pool is independent, and the data will be completely damaged only if two storage devices in the same resource pool are damaged, thereby reducing the probability of complete data damage and improving data security.

In order to achieve the above object, embodiments of the present invention adopt the following technical solutions:

In the first aspect, an embodiment of the present invention provides a method for storing data, which is used in a storage system. The storage system includes a resource pool for storing data, and the resource pool is logically divided into at least two sub-resource pools. , each sub-resource pool includes adjacent N storage devices, N≥2, and the method includes:

dividing the data to be stored into R slices, and distributing the R slices to the divided sub-resource pools, the number of copies of the data to be stored is expected to be less than N, and R≥2;

Generate a copy slice for each slice distributed to each sub-resource pool, and store the copy slice in the sub-resource pool to which the slice belongs, and the copy slice corresponds to the slice with the same data .

With reference to the first aspect, in a first possible implementation manner of the first aspect, storing the copy in the sub-resource pool corresponding to the slice includes: storing the copy slice in a sub-resource pool corresponding to the slice On the storage device in the sub-resource pool to which each copy slice is stored is different from the storage device corresponding to the slice storage, and copy slices with the same data are stored on different storage devices.

In combination with the first aspect and the first possible implementation of the first aspect, the second possible implementation of the first aspect further includes: dividing the divided sub-resource pool into sub-resources of different levels A pool set, each sub-resource pool set includes at least one sub-resource pool, and the number of duplicate slices expected to be generated for each slice in different levels of sub-resource pool sets is different;

The generating a copy slice for each of the slices distributed to each sub-resource pool includes: according to the number of copy slices expected to be generated for each of the slices corresponding to the level of the sub-resource pool set to which the sub-resource pool belongs, the distribution A corresponding number of duplicate slices are generated for each of the slices in the sub-resource pool.

With reference to the first aspect and the first possible implementation of the first aspect, in the third possible implementation of the first aspect, the copy slice is stored in the sub-resource pool to which the slice belongs After that, also include:

For any of the sub-resource pools, when reducing the number of storage devices in the sub-resource pool, allocate the slices in the reduced storage devices to other storage devices in the sub-resource pool, so The number of remaining storage devices in the sub-resource pool is greater than the number of copies expected to be generated.

With reference to the first aspect and the first possible implementation of the first aspect, in the fourth possible implementation of the first aspect, the copy slice is stored in the sub-resource pool to which the slice belongs After that, also include:

For any one of the sub-resource pools, when the number of storage devices in the sub-resource pool is increased, the copy slices of the slices in the sub-resource pool are reallocated to the storage devices in the sub-resource pool.

In combination with the second possible implementation of the first aspect, in a fifth possible implementation, the distributing the R slices to the pre-divided sub-resource pools includes:

According to the importance of the data in the R slices, the R slices are distributed to sub-resource pools of different levels.

In the second aspect, an embodiment of the present invention provides a device for storing data, which is used in a storage system, and the storage system includes a resource pool for storing data, and the resource pool is logically divided into at least two sub-resource pools , each sub-resource pool includes adjacent N storage devices, N≥2, and the method includes:

A distribution module, configured to divide the data to be stored into R slices, and distribute the R slices to the divided sub-resource pools, the number of copies of the data to be stored is expected to be less than N, and R≥2 ;

A replica generating module, configured to generate replica slices for each of the slices distributed in each sub-resource pool;

A storage module, configured to store the duplicate slice in a sub-resource pool corresponding to the slice, and the duplicate slice corresponds to the slice with the same data.

With reference to the second aspect, in the first possible implementation manner of the second aspect, the storage module further includes: the storage module, further configured to store the copy slice in a storage device corresponding to the sub-resource pool to which the slice belongs , and each of the duplicate slices is stored in a storage device different from the storage device corresponding to the slice, and duplicate slices with the same data are stored in different storage devices.

In combination with the second aspect and the first possible implementation of the second aspect, the second possible implementation of the second aspect further includes:

A dividing module, configured to divide the divided sub-resource pools into different-level sub-resource pool sets, each sub-resource pool set includes at least one sub-resource pool, and each of the slices in the different-level sub-resource pool sets The number of replica slices expected to be generated is different;

The copy generation module is further configured to generate a corresponding number of copy slices distributed to each of the sub-resource pools according to the number of copy slices expected to be generated by each of the slices corresponding to the level of the set of sub-resource pools to which the sub-resource pool belongs. Number of replica slices.

In combination with the second aspect and the first possible implementation of the second aspect, the third possible implementation of the second aspect further includes:

A negative adjustment module, configured to reduce the number of storage devices in the sub-resource pool for any one of the sub-resource pools;

A data allocation module, configured to allocate the slices in the reduced storage device to other storage devices in the sub-resource pool, where the number of remaining storage devices in the sub-resource pool is greater than the desired copy number.

In combination with the second aspect and the first possible implementation of the second aspect, the fourth possible implementation of the second aspect further includes:

A positive adjustment module, configured to increase the number of storage devices in the sub-resource pool for any one of the sub-resource pools;

The data allocation module is further configured to reallocate the copy slices of the slices in the sub-resource pool to the storage devices in the sub-resource pool when the number of storage devices in the sub-resource pool is increased.

In combination with the second possible implementation of the second aspect, the fifth possible implementation also includes:

The distribution module is further configured to distribute the R slices to sub-resource pools of different levels according to the importance of data in the R slices.

In the third aspect, the embodiment of the present invention provides a storage system for storing data. The storage system includes a resource pool for storing data. The resource pool is logically divided into at least two sub-resource pools, and each sub-resource The pool includes adjacent N storage devices, N≥2, the storage system includes: a processor, a communication interface, a bus, and is characterized in that it also includes a storage device, the processor, the communication interface and all storage devices The devices communicate with each other through the bus, wherein:

The processor is configured to divide the data to be stored into R slices, distribute the R slices to the divided sub-resource pools through the communication interface, and the data to be stored is expected to generate a copy The number is less than N, R≥2;

The processor is further configured to generate a copy slice for each of the slices distributed in each sub-resource pool, and store the copy slice in the sub-resource pool corresponding to the slice, and the copy slice and The slices having the same data correspond to each other.

In combination with the third aspect, the first possible implementation of the third aspect includes:

The processor is further configured to store the copy slice on a storage device corresponding to the sub-resource pool to which the slice belongs, and each storage device stored in the copy slice is the same as the storage device corresponding to the slice stored Different, replica slices with the same data are stored on different storage devices.

With reference to the third aspect and the first possible implementation manner of the third aspect, in a second possible implementation manner of the third aspect, the processor is further configured to divide the divided sub-resource pools again It is a set of sub-resource pools at different levels, each sub-resource pool set includes at least one sub-resource pool, and the number of duplicate slices expected to be generated for each slice in the sub-resource pool sets of different levels is different;

The processor is further configured to generate a corresponding number of duplicate slices distributed to each of the sub-resource pools according to the number of duplicate slices expected to be generated by each of the slices corresponding to the level of the set of sub-resource pools to which the sub-resource pool belongs. A copy slice of .

With reference to the third aspect, and the first possible implementation manner of the third aspect, in a third possible implementation manner of the third aspect, the processor is further configured to store the copy slice in the corresponding After the sub-resource pool to which the slice belongs, for any one of the sub-resource pools, when reducing the number of storage devices in the sub-resource pool, transfer the slices in the reduced storage devices through the communication interface allocated to other storage devices in the sub-resource pool, and the number of remaining storage devices in the sub-resource pool is greater than the expected number of copies to be generated.

With reference to the third aspect and the first possible implementation manner of the third aspect, in a fourth possible implementation manner of the third aspect, the processor is further configured to store the copy slice in the corresponding After the sub-resource pool to which the slice belongs, for any one of the sub-resource pools, when the number of storage devices in the sub-resource pool is increased, the The replica slices are reallocated to the storage devices in the sub-resource pool.

In combination with the second possible implementation of the third aspect, in a fifth possible implementation, the processor is further configured to distribute the R slices to different levels of in the sub-resource pool.

In a fourth aspect, an embodiment of the present invention provides a computer program product for storing data, which is used in a storage system, and the storage system includes a resource pool for storing data, wherein the resource pool is logically divided It is at least 2 sub-resource pools, each sub-resource pool includes adjacent N storage devices, N≥2, the computer program product includes a computer-readable storage medium storing program codes, and the instructions included in the program codes are used At:

dividing the data to be stored into R slices, and distributing the R slices to the divided sub-resource pools, the number of copies of the data to be stored is expected to be less than N, and R≥2;

Generate a copy slice for each slice distributed to each sub-resource pool, and store the copy slice in the sub-resource pool to which the slice belongs, and the copy slice corresponds to the slice with the same data .

The method, device, storage system, and computer program product for repairing data provided by the embodiments of the present invention can divide all storage devices in the storage system into at least two sub-resource pools, and store data in the divided sub-resource pools In , since the data in each sub-resource pool is independent, the data will be completely damaged only if two storage devices in the same sub-resource pool are damaged. In the prior art, when there is only one resource pool, damage to two storage devices will result in complete data damage. Since the embodiment of the present invention can divide multiple sub-resource pools, and store data in the multiple sub-resource pools divided In a sub-resource pool, only when two storage devices in the same sub-resource pool are damaged, the data will be completely damaged, because the probability of damage to two storage devices in the same sub-resource pool is less than that in the prior art when there is only one resource In the case of a pool, there is a probability of damaging two storage devices, so that the embodiment of the present invention can reduce the probability of complete data damage compared with the prior art, thereby improving data security.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings that need to be used in the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For Those of ordinary skill in the art can also obtain other drawings based on these drawings without making creative efforts.

FIG. 1 is a flow chart of a method for storing data provided by an embodiment of the present invention;

Fig. 1a is a schematic diagram of a specific example of a method for storing data provided by an embodiment of the present invention;

Fig. 1b is a schematic diagram of another specific example of a method for storing data provided by an embodiment of the present invention;

FIG. 2 is a flow chart of another method for storing data provided by an embodiment of the present invention;

Fig. 3a is a flowchart of another method for storing data provided by an embodiment of the present invention;

Fig. 3a1 is a schematic diagram of a specific example of another method for storing data provided by an embodiment of the present invention;

Fig. 3b is another flow chart of another method for storing data provided by an embodiment of the present invention;

FIG. 3b1 is a schematic diagram of another specific example of another method for storing data provided by an embodiment of the present invention;

Fig. 4a is a flowchart of another method for storing data provided by an embodiment of the present invention;

Fig. 4b is another flow chart of another method for storing data provided by an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of a device for storing data provided by an embodiment of the present invention;

FIG. 6 is a schematic structural diagram of another device for storing data provided by an embodiment of the present invention;

FIG. 7 is a schematic diagram of a network architecture of a storage system for storing data provided by an embodiment of the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

On the one hand, an embodiment of the present invention provides a method for storing data, as shown in FIG. 1 , including:

It should be noted that the embodiment of the present invention can be used in a storage system, and the storage system includes a resource pool for storing data, wherein the resource pool is logically divided into at least two sub-resource pools, and each sub-resource The pool includes N adjacent storage devices, where N≥2. Moreover, the embodiments of the present invention may be implemented by devices with data transmission, processing, and storage functions, for example, devices such as management servers and mobile workstations used to manage hard disk arrays in a distributed storage system.

101. Divide data to be stored into R slices, and distribute the R slices to the divided sub-resource pools.

Wherein, the expected number of copies of the data to be stored is less than N, that is, the expected number of copies of the data to be stored is smaller than the number of storage devices in the sub-resource pool, and R≥2. For example: a technical method that can distribute data slices in a distributed storage architecture. For example, the slices allocated to sub-resource pool 1 are P1, P2, and P3, and the number of copies expected to be generated is 2. Then the management server can allocate The slices in the sub-resource pool 1 are P1, P2, and P3, and the duplicate slices P1', P2', P3' of the first copy and the duplicate slices P1'', P2'', P3'' of the second copy are generated. And store P1, P2, P3, P1', P2', P3', P1'', P2'', P3'' on the storage device in the sub-resource pool 1 through the technical means of distribution and dispersal.

In this embodiment, the management server can divide the data to be stored into multiple data slices through common technical means, for example: the management server can divide the data to be stored into multiple The data is divided into at least two data slices, and the divided data slices are distributed on the sub-resource pools. Moreover, in this embodiment, there may be multiple specific implementations for distributing data slices on the sub-resource pools. For example, the management server may distribute data slices to the divided sub-resources in a way of distributing in RAID technology. On the resource pool, the data slices can also be evenly distributed on the divided sub-resource pools.

Further, in this embodiment, the management server can logically divide the storage devices in the system into multiple sub-resource pools, and each sub-resource pool consists of multiple storage devices, for example:

There are a total of 24 hard disks in the distributed storage system. The management server can divide these 24 hard disks into 3 sub-resource pools through MDC (MetadataController). Each sub-resource pool includes 8 hard disks, which can form The architecture of multiple sub-resource pools is shown in Figure 1a.

In practical applications, the commonly used LBA (LogicalBlock Addressing, Logical Block Addressing) in the process of addressing stored data can be mapped to different sub-resource pools, and each sub-resource pool and block storage logical partition unit Partition can be Allocation is done through the cluster management node of MDC. For example, if there are n Partitions in each sub-resource pool, and each hard disk in each sub-resource pool can have multiple Partitions, then the PartitionID in each sub-resource pool can be recorded in MDC (The block stores the logical partition unit ID) and the sub-resource pool ID, and identifies each Partition in the entire hard disk array in the form of "[sub-resource pool ID.PartitionID]", so that each Partition has a unique identification information; other devices in the system can access the Partition in the sub-resource pool by using common technical means according to the identification information of each Partition.

102. Generate a duplicate slice for each slice distributed to each sub-resource pool, and store the duplicate slice in the sub-resource pool to which the corresponding slice belongs.

In this embodiment, at least two identical copies of the data to be stored are expected to be generated, and the number of copies of the data to be stored is expected to be less than N. Moreover, the duplicate slices correspond to the same slices of the data to be stored, and the duplicate slices stored in one sub-resource pool are the same as the duplicate slices stored in other sub-resource pools. That is, the replica slices in one subresource pool are different from the replica slices in other subresource pools. For example: as shown in Figure 1b, the replica slices in the first replica can be divided into P1-P8 by the management server, the replica slices in the second replica can be divided into P1'-P8', and the first replica and the second replica The content is the same, that is, P1 is the same as P1', P2 is the same as P2', until P8 is the same as P8'.

In sub-resource pool 1, hard disk 1 carries P1, P2', P5, and P6', and hard disk 2 carries P1', P2, P5', and P6. The content of the copy in sub-resource pool 1 is the same, and similarly, the content of the first copy in sub-resource pool 2 is the same as that of the second copy in sub-resource pool 2 .

Further, for example: both P1 and P1' are in sub-resource pool 1, that is, the same Partition as P1 only exists in sub-resource pool 1. Similarly, the same Partition is in the same sub-resource pool, so that a sub-resource The data in a pool is content independent of other child resource pools. When the hard disk is damaged, for example: hard disk 1 is damaged, P1, P2', and P5 in hard disk 1 can be repaired only according to P1', P2, P5', and P6 in hard disk 2 that are also in sub-resource pool 1 , P6', so that when a hard disk in a sub-resource pool is damaged, the management server can repair the data in the damaged hard disk only according to the data in other hard disks in the sub-resource pool, so that the data in the sub-resource pool Independent in content from other sub-resource pools.

It should be noted that, in this embodiment of the present invention, since the copy slices in one sub-resource pool are different from those in other sub-resource pools, the data in the sub-resource pool is independent of other sub-resource pools in terms of content, and The copies generated according to the data to be stored are stored in multiple sub-resource pools, and the condition for the entire copy data to be completely damaged is that two storage devices in one sub-resource pool are damaged at the same time, for example: as shown in Figure 1b In the double-copy scenario, the conditions for the entire copy data to be completely damaged are: hard disk 1 and hard disk 2 in sub-resource pool 1 are damaged at the same time, or hard disk 3 and hard disk 4 in sub-resource pool 2 are damaged at the same time. If only one hard disk in sub-resource pool 1 is damaged, and only one hard disk in sub-resource pool 2 is damaged at the same time, the replica data can still be repaired, that is, only when two hard disks in a sub-resource pool are damaged at the same time, The copy data will be corrupted. Since the damage probability of the hard disk is basically the same, if the damage probability of the hard disk is A, then if the prior art scheme is adopted, for example: the prior art scheme is that hard disks 1, 2, 3, and 4 in Fig. In a resource pool, the probability of copy data damage (that is, the probability of two hard disks being damaged at the same time) is A ² , or it can be understood that the probability of copy data damage in the distributed storage system within the time window of data reconstruction is A; while this In the scheme of the embodiment of the invention, hard disks 1 and 2 in Fig. 1b are in sub-resource pool 1, hard disks 3 and 4 are in sub-resource pool 4, and since the data in sub-resource pool 1 is independent of sub-resource pool 2 in content , then the probability of replica data damage (that is, the probability that two hard disks in the same sub-resource pool must be damaged at the same time) is 0.5A ² , or it can be understood that the probability of replica data damage in the distributed storage system within the data reconstruction time window is 0.5A; it can be seen that, in the solution of the embodiment of the present invention, the more sub-resource pools are divided, the lower the probability of copy data damage. For example, if 100 sub-resource pools are divided, the time window for data reconstruction The probability of internal copy data damage is 0.01A. If exactly one hard disk is damaged in each sub-resource pool, the solution provided by the embodiment of the present invention can deal with the extreme situation that a maximum of 100 hard disks are damaged. The data is independent of each other, and it is also possible to repair the data.

Further, for example, in practical applications, the failure rate of storage devices such as hard disks is generally 4%, and considering the influence of performance parameters of some commonly used storage devices on the failure rate of hard disks, according to the solutions of the embodiments of the present invention, the following can be obtained: Data shown in Table 1:

Total number of hard disks: 180 disks data corruption rate single drive failure rate Existing solution: 1 sub-resource pool (180 hard disks per pool) 0.997066418 4% The solution of the present invention: 90 sub-resource pools (2 hard disks per pool) 0.999983563 4% Other commonly used data storage schemes in this field 0.996077775 4%

Table I

It can be seen that, compared with the prior art, the embodiment of the present invention includes N adjacent storage devices in the sub-resource pool, and the probability of adjacent storage devices being damaged at the same time is very small, so the damaged storage devices are not in the same sub-resource pool The chances are very high, and when the data in a sub-resource pool is damaged, it can be recovered through the data on other storage devices in the sub-resource pool, which increases the fault tolerance of the distributed storage system and reduces data damage probability, thereby improving data security.

The method for repairing data provided by the embodiment of the present invention can divide all storage devices into at least two sub-resource pools, and store data in the divided sub-resource pools, because the data in each sub-resource pool is independent , for example: as shown in Figure 1b, the data slices stored in sub-resource pool 1 are P1', P2, P5', P6, P1, P2', P5, and P6', and none of the data slices is related to sub-resource pool 2 The stored data slices are the same, so whether the data in sub-resource pool 2 is damaged or not will not affect the data in sub-resource pool 1, and there is no need to extract the data in sub-resource pool 1 to participate in repairing sub-resource pool 2 data, so the data in each sub-resource pool is independent. Since the data in each sub-resource pool is independent, whether the data in one sub-resource pool is damaged or not, data repair and other processes will not affect the data in other sub-resource pools, there are only two sub-resource pools in the same sub-resource pool The data will be completely damaged only if the storage device is damaged. In the prior art, storage devices storing mutually repairable data may be damaged at the same time, resulting in complete data damage. Since the embodiment of the present invention can divide multiple sub-resource pools, each sub-resource pool includes N adjacent storage device, and store the data in multiple sub-resource pools. Only when the storage devices where the mutually repairable data in the same sub-resource pool are located are all damaged, the data will be completely damaged. Because the same sub-resource pool The probability that the adjacent storage devices are all damaged is very small, so that the embodiment of the present invention can reduce the probability of complete data damage compared with the prior art, thereby improving data security.

Optionally, the embodiment of the present invention also provides a method for storing data, as shown in Figure 2, which may also include:

201. Divide data to be stored into R slices, and distribute the R slices to the sub-resource pools containing storage devices of a specified type.

Wherein, a sub-resource pool may include at least two adjacent storage devices, and the storage devices are used to store data.

In addition, the obtained sub-resource pool includes a specified type of storage device, and the type of the storage device includes but is not limited to: hard disk, solid state disk SSD.

202. Generate a duplicate slice for each slice distributed to each sub-resource pool, and store the duplicate slice in the sub-resource pool to which the corresponding slice belongs.

In this embodiment, the management server can determine the type of storage device to be used, and store the slices of the data to be stored in the sub-resource pool containing the storage device of this type, and then distribute to each sub-resource pool The slice generates a copy slice, and stores the copy slice in the sub-resource pool corresponding to the slice, for example:

The mapping relationship between the type of data and the type of storage device shown in Table 2 can be pre-stored in the management server, and the type of storage device to be used can be determined according to the type of data to be stored, and then the storage device containing this type can be obtained. The sub-resource pool of the storage device, and finally store the data to be stored in the sub-resource pool containing this type of storage device.

type of data storage device type The sub-resource pool where the storage device resides picture mechanical hard drive Sub-resource pool 1 Word SSD Sub-resource pool 2 video mechanical hard drive Sub-resource pool 3

Table II

Another example:

The mapping relationship between the size of data and the type of storage device as shown in Table 3 can be pre-stored in the management server, and the type of storage device to be used can be determined according to the size of the data to be stored, and then the storage device containing this type can be obtained The sub-resource pool of the storage device, and finally store the data to be stored in the sub-resource pool containing this type of storage device.

data size storage device type The sub-resource pool where the storage device resides 100M SSD Sub-resource pool 1 1G mechanical hard drive Sub-resource pool 2 1T mechanical hard drive Sub-resource pool 3

Table three

That is to say, in this embodiment, the management server can determine the type of the storage device to be used in various specific implementation means. In practical applications, those skilled in the art can also determine The type of storage device to use. Because the security of different types of storage devices is also different, for example, many solid state drives are less likely to be damaged than mechanical hard drives. Therefore, the management server can select a corresponding type of storage device according to the importance of the data, thereby further improving the security of important data.

Further optionally, an embodiment of the present invention provides a method for storing data, as shown in FIG. 3a, including:

301. Divide data to be stored into R slices, and distribute the R slices to the divided sub-resource pools.

302. Generate a duplicate slice for each slice distributed to each sub-resource pool, and store the duplicate slice on a storage device corresponding to the sub-resource pool to which the slice belongs.

Wherein, the copy slice corresponds to the same slice of the data to be stored. The storage device for storing each of the duplicate slices is different from the storage device for storing the corresponding slices, and the duplicate slices with the same data are stored on different storage devices. For example:

As shown in Figure 1b, the copy slices of the first copy are P1-P8, the copy slices of the second copy are P1'-P8', and P1 is the same as P1', P2 is the same as P2', until P8 is the same as P8'. In sub-resource pool 1, hard disk 1 carries P1, P2', P5, and P6', and hard disk 2 carries P1', P2, P5', and P6. The content of the copy in sub-resource pool 1 is the same, and similarly, the content of the first copy in sub-resource pool 2 is the same as that of the second copy in sub-resource pool 2 .

Further, both P1 and P1' are in sub-resource pool 1, that is, the same Partition as P1 only exists in sub-resource pool 1. Similarly, the same Partition is in the same sub-resource pool, so that a sub-resource pool The data of is independent in content from other sub-resource pools. Moreover, the hard disk stored in each copy slice is different from the hard disk stored in the corresponding slice. For example, a copy slice in sub-resource pool 1 is different from any slice in any copy in sub-resource pool 2. And the copy slices with the same data are stored on different storage devices, for example: P1 and P1' are on different hard disks.

303a. For any one of the sub-resource pools, reduce the number of storage devices in the sub-resource pool.

In this embodiment, the management server can implement hot plugging/removing of storage devices in the sub-resource pool by common technical means, that is, the number of storage devices in the sub-resource pool can be increased or decreased while the sub-resource pool is running. quantity. For example: when a hard disk in a sub-resource pool fails and needs to be reconstructed by common technical means, the management server can rebuild and restore the data on the failed hard disk in this sub-resource pool, as shown in Figure 3a1. When hard disk 1 in sub-resource pool x fails, the Partitions on hard disk 1 can all be migrated to the other three hard disks in the sub-resource pool according to the rules set in advance. In this way, the number of storage devices in the sub-resource pool can be reduced while the sub-resource pool is running.

304a. Allocate the slices in the reduced storage device to other storage devices in the sub-resource pool.

Parallel, as shown in Figure 3b, may also include:

303b. For any one of the sub-resource pools, increase the number of storage devices in the sub-resource pool.

For example: as shown in Figure 3b1. When the management server adds hard disk 4 to the sub-resource pool x, the Partition on hard disk 1-3 can be evenly distributed among the 4 fast hard disks of hard disk 1-4 according to the rule set in advance, so that hard disk 1-3 Part of the content on the network has been migrated to hard disk 4. In this way, the number of storage devices in the sub-resource pool can be increased while the sub-resource pool is running.

304b. Reallocate the copy slice of the slice in the sub-resource pool to the storage device in the sub-resource pool.

In this embodiment, the management server can reallocate slices in the sub-resource pool after adding storage devices in the sub-resource pool, for example: as shown in Figure 3b1, all data slices on hard disks 1-3 , re-distribute and break up on hard disks 1-4.

The embodiments of the present invention can also realize hot plugging/removing of storage devices in the sub-resource pools, so that each sub-resource pool can be guaranteed to be stored in the sub-resource pools when abnormal operation conditions such as storage device damage and storage device shutdown maintenance occur. The data is not lost, so that the distributed storage system can exclude unusable storage devices at any time while ensuring data stability during operation, thereby further improving data security.

The method for repairing data provided by the embodiment of the present invention can divide all storage devices into at least two sub-resource pools, and store data in the divided sub-resource pools, because the data in each sub-resource pool is independent , taking two storage devices included in a sub-resource pool as an example, the data will be completely damaged only if the two storage devices in the same sub-resource pool are damaged. In the prior art, when there is only one resource pool, damage to two storage devices may cause complete data damage. The embodiment of the present invention can divide multiple sub-resource pools and store data in the divided sub-resource pools. In multiple sub-resource pools, only when two storage devices in the same sub-resource pool are damaged, the data will be completely damaged, because the probability of damage to two adjacent storage devices in the same sub-resource pool is smaller than that in the prior art In the case of only one resource pool, the probability of damaging two storage devices that can restore data to each other makes the embodiment of the present invention reduce the probability of complete data damage compared with the prior art, thereby improving data security. sex.

Still further optionally, the embodiment of the present invention also provides a method for storing data, which may further include: subdividing the divided sub-resource pools into sub-resource pool sets of different levels, and each sub-resource pool set includes at least A sub-resource pool, the number of duplicate slices expected to be generated for each slice in different levels of sub-resource pool sets is different; the generation of duplicate slices for each slice distributed to each sub-resource pool includes: The number of duplicate slices expected to be generated by each slice corresponding to the level of the sub-resource pool set to which the sub-resource pool belongs, will generate a corresponding number of duplicate slices for each of the slices distributed to the sub-resource pools. In specific implementation, it can be shown in Figure 4a, including:

401a. Divide the divided sub-resource pools into sub-resource pool sets of different levels.

Wherein, each set of sub-resource pools includes at least one sub-resource pool, and the number of duplicate slices expected to be generated for each slice in the set of sub-resource pools of different levels is different. For example:

Determine Q first-level sub-resource pools, or Q' second-level sub-resource pools. Among them, the number of copies expected to be generated from slices stored in the first-level sub-resource pool is M, and the number of copies expected to be generated from slices stored in the second-level sub-resource pool is O, and M>O≥2, Q≥2, and Q'≥2.

In this embodiment, the management server can use common technical means to set the expected number of copies of the slices stored in the sub-resource pool. The number of copies of is 2, and the number of copies expected to be generated by slices in sub-resource pool y is 3. Then in the sub-resource pool x, after storing the copy slices P1, P2, P3 from copy 1 and the copy slices P1', P2', P3' from copy 2, it cannot store the copy slices from copy 3 any more. Copy slices P1'', P2'', and P3'' of , if you want to store all or part of the content from copies 1, 2, and 3 at the same time, you need to use sub-resource pool y.

In addition, characters used to limit the number of copies can be added to the identification information used to represent the attributes of the sub-resource pool, for example: 010 indicates that the sub-resource pool allows the expected number of copies of stored data to be 2, and 011 indicates that the sub-resource pool allows The desired number of copies of the stored data is three.

402a. According to the number of duplicate slices expected to be generated for each slice corresponding to the level of the sub-resource pool set to which the sub-resource pool belongs, generate a corresponding number of duplicate slices for each of the slices distributed to the sub-resource pools.

In this embodiment, the management server can determine the level of the sub-resource pool used in various ways, for example: the management server can determine the level of the sub-resource pool according to the type of data to be stored, for example: as shown in Table 4 , the management server can pre-store the mapping relationship between the type of data and the level of the sub-resource pool, and determine the level of the sub-resource pool required to store the data to be stored according to the type of data to be stored and the mapping relationship shown in Table 4.

Table four

Since in practical applications, different data have different degrees of importance, the embodiment of the present invention can adopt different levels of storage methods for data with different degrees of importance, and for relatively important data, a storage method with more copies can be used to ensure For data security, relatively unimportant data can be stored with fewer copies to increase the utilization of storage devices in the system, thereby improving the operating efficiency of the distributed storage system, so that the management server can use more The storage device is used to store relatively important data, thereby further improving the security of the important data.

Parallel, as shown in Figure 4b, also includes:

401b. Divide the divided sub-resource pools into sub-resource pool sets of different levels.

Wherein, each set of sub-resource pools includes at least one sub-resource pool, and the number of duplicate slices expected to be generated for each slice in the set of sub-resource pools of different levels is different.

402b. Divide the data to be stored into R slices, and distribute the R slices to sub-resource pools of different levels according to the importance of the data in the R slices.

Among them, R≥2. For example:

In the process of using the virtual machine, the data of the system volume and user volume of the virtual machine need to be stored in the sub-resource pool. Since the data security of the system volume is more important, the management server can Three copies of the slice are generated and stored in the first-level sub-resource pool, and two copies are generated and stored in the second-level sub-resource pool according to the slice corresponding to the data of the user volume, so as to achieve different data storage according to the same copy. Partially generate different numbers of copies and store them in sub-resource pools of corresponding levels.

Since in practical applications, the importance of different parts of the same data is also different, the embodiment of the present invention can adopt different levels of storage methods for the data of different parts of the importance of the data, and the relatively important parts of the data can be The storage method with more copies is used to ensure security. For relatively unimportant parts, the storage method with fewer copies can be used to increase the utilization rate of storage devices in the system, thereby improving the operating efficiency of the distributed storage system. The management server can use more storage devices to store more important parts of the data, thereby further improving the security of the important parts of the data.

The method for repairing data provided by the embodiment of the present invention can divide all storage devices into at least two sub-resource pools, and store data in the divided sub-resource pools, because the data in each sub-resource pool is independent , the data will be completely damaged only if two storage devices in the same sub-resource pool are damaged. In the prior art, when there is only one resource pool, damage to two storage devices will result in complete data damage. Since the embodiment of the present invention can divide multiple sub-resource pools, and store data in the multiple sub-resource pools divided In a sub-resource pool, only when two storage devices in the same sub-resource pool are damaged, the data will be completely damaged. Since the probability of damage to the two storage devices in the same sub-resource pool is very small, the embodiment of the present invention is relatively Because the existing technology can reduce the probability of complete data damage, thereby improving the security of data.

On the other hand, an embodiment of the present invention provides an apparatus for storing data, which is used in a storage system. The storage system includes a resource pool for storing data, and the resource pool is logically divided into at least two sub-resource pools. Each sub-resource pool includes adjacent N storage devices, N≥2, as shown in Figure 5, including:

The distribution module 51 is configured to divide the data to be stored into R slices, and distribute the R slices to the divided sub-resource pools.

Wherein, the number of copies of the data to be stored is expected to be less than N, and R≥2.

The replica generation module 52 is configured to generate a replica slice for each of the slices distributed in each sub-resource pool.

The storage module 53 is configured to store the duplicate slice in a sub-resource pool corresponding to the slice, and the duplicate slice corresponds to the slice with the same data.

The device for repairing data provided by the embodiment of the present invention can divide all storage devices into at least two sub-resource pools, and store data in the divided sub-resource pools, because the data in each sub-resource pool is independent , the data will be completely damaged only if two storage devices in the same sub-resource pool are damaged. In the prior art, when there is only one resource pool, damage to two storage devices will result in complete data damage. Since the embodiment of the present invention can divide multiple sub-resource pools, and store data in the multiple sub-resource pools divided In a sub-resource pool, only when two storage devices in the same sub-resource pool are damaged, the data will be completely damaged, because the probability of damage to two storage devices in the same sub-resource pool is less than that in the prior art when there is only one resource In the case of a pool, there is a probability of damaging two storage devices, so that the embodiment of the present invention can reduce the probability of complete data damage compared with the prior art, thereby improving data security.

Optionally, as shown in Figure 6, the device for storing data provided by the embodiment of the present invention may include:

The distribution module 62 is configured to divide the data to be stored into R slices, and distribute the R slices to the divided sub-resource pools.

Wherein, the number of copies of the data to be stored is expected to be less than N, and R≥2.

A replica generation module 63, configured to generate a replica slice for each of the slices distributed in each sub-resource pool.

The storage module 64 is configured to store the duplicate slice in a sub-resource pool corresponding to the slice, and the duplicate slice corresponds to the slice with the same data.

Further, the storage module 64 is further configured to store the copy slice on a storage device corresponding to the sub-resource pool to which the slice belongs.

In addition, the storage device for storing each of the duplicate slices is different from the storage device for storing the corresponding slices, and the duplicate slices with the same data are stored on different storage devices.

Further optionally, the device for storing data provided in the embodiment of the present invention may also include:

A division module 61, configured to further divide the divided sub-resource pools into sets of sub-resource pools of different levels.

Wherein, each set of sub-resource pools includes at least one sub-resource pool, and the number of duplicate slices expected to be generated for each slice in the set of sub-resource pools of different levels is different.

The copy generation module 63 is further configured to generate each of the slices distributed to the sub-resource pools according to the number of copy slices expected to be generated by each of the slices corresponding to the level of the set of sub-resource pools to which the sub-resource pool belongs. Corresponding number of replica slices.

Since in practical applications, different data have different degrees of importance, the device provided by the embodiment of the present invention can adopt different levels of storage methods for data of different degrees of importance, and for relatively important data, the Storage method to ensure data security. Relatively unimportant data can be stored with fewer copies to increase the utilization of storage devices in the system, thereby improving the operating efficiency of the distributed storage system, so that the management server can More storage devices are used to store more important data, thereby further improving the security of important data.

Still further optionally, the device for storing data provided by the embodiment of the present invention may also include:

The negative adjustment module 65 is configured to, for any one of the sub-resource pools, reduce the number of storage devices in the sub-resource pool.

The positive adjustment module 66 is configured to, for any one of the sub-resource pools, increase the number of storage devices in the sub-resource pool.

The data allocation module 67 is configured to allocate the slices in the reduced storage devices to other storage devices in the sub-resource pool.

Wherein, the number of remaining storage devices in the sub-resource pool is greater than the number of copies expected to be generated.

The data allocation module 67 is further configured to reallocate the copy slices of the slices in the sub-resource pool to the storage devices in the sub-resource pool when increasing the number of storage devices in the sub-resource pool .

Further optionally, the distribution module 62 is further configured to distribute the R slices to sub-resource pools of different levels according to the importance of data in the R slices.

The embodiment of the present invention can also realize the hot plug/unplug of the storage devices in the sub-resource pools, so that when the storage devices in each sub-resource pool are damaged, shut down for maintenance and other abnormal operation conditions, the data stored in the sub-resource pools can be guaranteed Data is not lost, so that the distributed storage system can eliminate unusable storage devices at any time while ensuring data stability during operation, thereby further improving data security. The device for repairing data provided by the embodiment of the present invention can divide all storage devices into at least two sub-resource pools, and store data in the divided sub-resource pools, because the data in each sub-resource pool is independent , the data will be completely damaged only if two storage devices in the same sub-resource pool are damaged. In the prior art, when there is only one resource pool, damage to two storage devices will result in complete data damage. Since the embodiment of the present invention can divide multiple sub-resource pools, and store data in the multiple sub-resource pools divided In a sub-resource pool, only when two storage devices in the same sub-resource pool are damaged, the data will be completely damaged, because the probability of damage to two storage devices in the same sub-resource pool is less than that in the prior art when there is only one resource In the case of a pool, there is a probability of damaging two storage devices, so that the embodiment of the present invention can reduce the probability of complete data damage compared with the prior art, thereby improving data security.

In another aspect, an embodiment of the present invention provides a storage system for storing data. As shown in FIG. 7 , the storage system includes a storage area 74 for storing data, and the storage area 74 is logically divided into at least 2 Sub-resource pools, each sub-resource pool includes adjacent N storage devices, N≥2, the storage system includes: a processor 71, a communication interface 72, a bus 73, the processor 71, the communication interface 72 and all storage devices in the storage area 74 complete mutual communication through the bus 73, wherein:

The processor 71 is configured to divide the data to be stored into R slices, and distribute the R slices to the divided sub-resource pools through the communication interface 72 .

Wherein, the number of copies of the data to be stored is expected to be less than N, and R≥2.

The processor 71 is further configured to generate a duplicate slice for each slice distributed to each sub-resource pool, and store the duplicate slice in the sub-resource pool to which the slice belongs.

Wherein, the copy slice corresponds to the same slice of the data to be stored.

Further, the processor 71 is further configured to store the duplicate slice on a storage device corresponding to the sub-resource pool to which the slice belongs.

Wherein, the storage device for storing each duplicate slice is different from the storage device for corresponding slice storage, and duplicate slices with the same data are stored on different storage devices.

Optionally, the processor 71 is further configured to further divide the divided sub-resource pools into sub-resource pool sets of different levels.

Wherein, each set of sub-resource pools includes at least one sub-resource pool, and the number of duplicate slices expected to be generated for each slice in the set of sub-resource pools of different levels is different.

The processor 71 is further configured to, according to the number of duplicate slices expected to be generated by each slice corresponding to the level of the set of sub-resource pools to which the sub-resource pool belongs, generate corresponding slices distributed to each of the sub-resource pools Number of replica slices.

Further optionally, the processor 71 is further configured to, after storing the copy slice in the sub-resource pool to which the slice belongs, for any one of the sub-resource pools, when reducing the sub-resource pool When the number of storage devices in the sub-resource pool is reduced, the slices in the reduced storage devices are allocated to other storage devices in the sub-resource pool through the communication interface 72 .

Wherein, the number of remaining storage devices in the sub-resource pool is greater than the number of copies expected to be generated.

Optionally in parallel, the processor 71 is further configured to, after storing the copy slice in the sub-resource pool to which the slice belongs, for any one of the sub-resource pools, when adding the sub-resource When the number of storage devices in the pool is equal, the copy slices of the slices in the sub-resource pool are reallocated to the storage devices in the sub-resource pool through the communication interface 72 .

Further optionally, the processor 71 is further configured to distribute the R slices to sub-resource pools of different levels according to the importance of data in the R slices.

The repair data storage system provided by the embodiment of the present invention can divide all storage devices in the storage system into at least two resource pools, and store data in the divided resource pools. Since the data in each resource pool It is independent, and the data will be completely damaged only if two storage devices in the same resource pool are damaged. In the prior art, when there is only one resource pool, damage to two storage devices will result in complete data damage. The embodiment of the present invention can divide multiple resource pools and store data in the divided multiple resource pools. In a resource pool, only when two storage devices in the same resource pool are damaged, the data will be completely damaged, because the probability of two storage devices in the same resource pool being damaged is less than that in the prior art when there is only one resource In the case of a pool, there is a probability of damaging two storage devices, so that the embodiment of the present invention can reduce the probability of complete data damage compared with the prior art, thereby improving data security.

In yet another aspect, an embodiment of the present invention provides a computer program product for repairing data, which is used in a storage system, and the storage system includes a resource pool for storing data, and the resource pool is logically divided into at least two sub-resources A pool, each sub-resource pool includes adjacent N storage devices, N≥2, the computer program product includes a computer-readable storage medium storing program code, and the program code includes instructions for:

The data to be stored is divided into R slices, and the R slices are distributed to the divided sub-resource pools, the number of copies of the data to be stored is expected to be less than N, and R≥2.

Generate a copy slice for each slice distributed to each sub-resource pool, and store the copy slice in the sub-resource pool to which the slice belongs, and the copy slice corresponds to the slice with the same data .

The computer program product for repairing data provided by the embodiments of the present invention can divide all storage devices in the storage system into at least two resource pools, and store data in the divided resource pools. The data is independent, and the data will be completely damaged only if two storage devices in the same resource pool are damaged. In the prior art, when there is only one resource pool, damage to two storage devices will result in complete data damage. The embodiment of the present invention can divide multiple resource pools and store data in the divided multiple resource pools. In a resource pool, only when two storage devices in the same resource pool are damaged, the data will be completely damaged, because the probability of two storage devices in the same resource pool being damaged is less than that in the prior art when there is only one resource In the case of a pool, there is a probability of damaging two storage devices, so that the embodiment of the present invention can reduce the probability of complete data damage compared with the prior art, thereby improving data security.

Each embodiment in this specification is described in a progressive manner, the same and similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for relevant parts, please refer to part of the description of the method embodiment.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. During execution, it may include the processes of the embodiments of the above-mentioned methods. Wherein, the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM) or a random access memory (Random Access Memory, RAM), etc.

The above is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Anyone skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present invention. All should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be determined by the protection scope of the claims.

Claims (19)

1. the method for a storage data, be used for storage system, and described storage system comprises the resource pool for the storage data, it is characterized in that, described resource pool is at least 2 sub-resource pools by logical partitioning, and each child resource pond comprises an adjacent N memory device, N 〉=2, described method comprises:

The data of needs storages are divided into R section, R described section are distributed in the described child resource pond of division, the copy amount that the described data that need storage are expected generation is less than N, R 〉=2;

To being distributed to each the described section ghost section in each child resource pond, and described copy section is stored in child resource pond under corresponding described section, the described copy section described section identical with data is mutually corresponding.

2. the method for storage data according to claim 1, it is characterized in that, the described child resource pond that described copy is stored under corresponding described section comprises: described copy section is stored on memory device in child resource pond under corresponding described section, and the memory device of each described copy section storage is different from the memory device of corresponding described section storage, and the copy section that data are identical is stored on different memory devices.

3. the method for storage data according to claim 1 and 2 is characterized in that:

Also comprise: the child resource pond of described division is divided into the pond set of different stage child resource again, the set of each child resource pond comprises at least one child resource pond, and the copy number of sections that in the child resource pond set of different stage, the expectation of each described section generates is different;

Described to being distributed to each the described section ghost section in each child resource pond, comprise: the copy number of sections that generates according to corresponding each the described section expectation of the rank of child resource pond set under the child resource pond will be distributed to each described section in the child resource pond and generate the copy section of respective amount.

4. the method for storage data according to claim 1 and 2, is characterized in that, in the child resource pond under the section of described copy being stored in corresponding described section after, also comprise:

For any described child resource pond, during the quantity of the memory device in reducing described child resource pond, described section in the memory device that reduces is assigned on other memory devices in described child resource pond the number of copies that the remaining memory device quantity in described child resource pond generates greater than described expectation.

5. the method for storage data according to claim 1 and 2, is characterized in that, in the child resource pond under the section of described copy being stored in corresponding described section after, also comprise:

For any described child resource pond, during the quantity of the memory device in increasing described child resource pond, the copy section of the described section in this child resource pond is re-assigned on memory device in this child resource pond.

6. the method for storage data according to claim 3, is characterized in that, describedly R section is distributed in advance the child resource pond of dividing comprises:

According to the significance level of data in R section, in R the child resource pond that is distributed to different stage of cutting into slices.

7. the device of a storage data, be used for storage system, and described storage system comprises the resource pool for the storage data, it is characterized in that, described resource pool is at least 2 sub-resource pools by logical partitioning, and each child resource pond comprises an adjacent N memory device, N 〉=2, described method comprises:

Distribution module, the data that are used for needing to store are divided into R section, R described section are distributed in the described child resource pond of division, and the copy amount that the described data that need storage are expected generation is less than N, R 〉=2;

The copy generation module is used for being distributed to each described section ghost section in each child resource pond;

Storage module is used for described copy section is stored in child resource pond under corresponding described section, and the described copy section described section identical with data is mutually corresponding.

8. the device of storage data according to claim 7, it is characterized in that, also comprise: described storage module, also be used for described copy section is stored into the memory device in the child resource pond under corresponding described section, and the memory device of each described copy section storage is different from the memory device of corresponding described section storage, and the copy section that data are identical is stored on different memory devices.

9. the device of according to claim 7 or 8 described storage datas, is characterized in that, also comprises:

Divide module, be used for the child resource pond of described division is divided into the pond set of different stage child resource again, the set of each child resource pond comprises at least one child resource pond, and the copy number of sections that in the child resource pond set of different stage, the expectation of each described section generates is different;

Described copy generation module also is used for the copy number of sections that corresponding each the described section expectation of rank according to child resource pond set under the child resource pond generates, and will be distributed to each described section in the child resource pond and generate the copy section of respective amount.

10. the device of according to claim 7 or 8 described storage datas, is characterized in that, also comprises:

The negative regulator module is used for for any described child resource pond, reduces the quantity of the memory device in described child resource pond;

Data allocations module, the described section that is used for the memory device that will reduce are assigned to other memory devices in described child resource pond, the number of copies that the remaining memory device quantity in described child resource pond generates greater than described expectation.

11. the device of storage data according to claim 10 is characterized in that, also comprises:

Positive adjustment module is used for for any described child resource pond, increases the quantity of the memory device in described child resource pond;

Described data allocations module, when also being used for the quantity when the memory device that increases described child resource pond, the copy of the described section in this child resource pond is cut into slices to be re-assigned on memory device in this child resource pond.

12. the device of storage data according to claim 9 is characterized in that, also comprises:

Described distribution module also is used for the significance level according to R section data, in R the child resource pond that is distributed to different stage of cutting into slices.

13. the storage system of a storage data, described storage system comprises the resource pool for the storage data, it is characterized in that, described resource pool is at least 2 sub-resource pools by logical partitioning, and each child resource pond comprises an adjacent N memory device, N 〉=2, described storage system comprises: processor, communication interface, bus characterized by further comprising memory device, described processor, described communication interface and all memory devices, complete mutual communication by described bus, wherein:

Described processor, the data that are used for needing to store are divided into R section, by described communication interface, R described section are distributed in the described child resource pond of division, and the copy amount that the described data that need storage are expected generation is less than N, R 〉=2;

Described processor also is used for being distributed to each described section ghost section in each child resource pond, and described copy section is stored in child resource pond under corresponding described section, and the described copy section described section identical with data is mutually corresponding.

14. the storage system of storage data according to claim 13 is characterized in that, comprising:

Described processor, also be used for described copy section is stored into the memory device in the child resource pond under corresponding described section, and the memory device of each described copy section storage is different from the memory device of corresponding described section storage, and the copy section that data are identical is stored on different memory devices.

15. the storage system of according to claim 13 or 14 described storage datas, it is characterized in that, described processor, also be used for the child resource pond of described division is divided into the pond set of different stage child resource again, the set of each child resource pond comprises at least one child resource pond, and the copy number of sections that in the child resource pond set of different stage, the expectation of each described section generates is different;

Described processor also is used for the copy number of sections that corresponding each the described section expectation of rank according to child resource pond set under the child resource pond generates, and will be distributed to each described section in the child resource pond and generate the copy section of respective amount.

16. the storage system of according to claim 13 or 14 described storage datas, it is characterized in that, described processor, also be used for behind the child resource pond that described copy section is stored under corresponding described section, for any described child resource pond, during the quantity of the memory device in reducing described child resource pond, by described communication interface, the described section in the memory device that reduces is assigned on other memory devices in described child resource pond the number of copies that the remaining memory device quantity in described child resource pond generates greater than described expectation.

17. the storage system of according to claim 13 or 14 described storage datas, it is characterized in that, described processor, also be used for behind the child resource pond that described copy section is stored under corresponding described section, for any described child resource pond, during the quantity of the memory device in increasing described child resource pond, by described communication interface, the copy section of the described section in this child resource pond is re-assigned on memory device in this child resource pond.

18. the storage system of storage data according to claim 15 is characterized in that, described processor also is used for the significance level according to R section data, in R the child resource pond that is distributed to different stage of cutting into slices.

19. the computer program of a repair data, be used for storage system, described storage system comprises the resource pool for the storage data, it is characterized in that, described resource pool is at least 2 sub-resource pools by logical partitioning, and each child resource pond comprises N adjacent memory device, N 〉=2, described computer program comprises the computer-readable recording medium of having stored program code, and the instruction that described program code comprises is used for carrying out described method as arbitrary in claim 1-6.

Images