WO2018107828A1

WO2018107828A1 - Method and device for information processing

Info

Publication number: WO2018107828A1
Application number: PCT/CN2017/101221
Authority: WO
Inventors: 曹力; 陈伟; 丁智勇
Original assignee: 杭州海康威视数字技术股份有限公司
Priority date: 2016-12-13
Filing date: 2017-09-11
Publication date: 2018-06-21
Also published as: CN108614670B; CN108614670A

Abstract

A method and a device for information processing, which are applicable to a storage server. The method comprises: acquiring, from a metadata server, first stripe information of at least one damaged stripe, the first stripe information comprising: the identifiers of normal blocks, and streaming object data to which the streaming data stored in the normal blocks belongs (S201); according to the streaming object data to which the streaming data stored in the normal blocks belongs, grouping the normal blocks corresponding to the identifiers of the normal blocks (S202); constructing at least one new normal stripe for each group of data blocks (S203); acquiring second stripe information of the at least one new normal stripe (S204); and sending the second stripe information to the metadata server, so as to add the second stripe information into the metadata server (S205). In the use of the embodiments of the present application, if the normal data block corresponding to the damaged stripe is further damaged, the streaming data stored in the further damaged normal data block can be restored.

Description

Information processing method and device

The present application claims priority to Chinese Patent Application No. PCT Application No. No. No. No. No. No. No. No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No

Technical field

The present application relates to the field of data processing technologies, and in particular, to an information processing method and apparatus.

Background technique

With the popularity and development of the Internet, streaming data, such as video data, plays an increasingly important role in human life. However, in the process of streaming data, streaming data may be lost due to disk corruption, storage node failure, and the like. In order to improve the reliability and security of data, it is necessary to repair the streaming data.

At present, the stream data repair is generally performed based on the erasure code. Specifically, referring to FIG. 1, a stripe may correspond to a plurality of stripe blocks, as shown in FIG. 1, N+M stripe blocks, wherein a part of the strips With a block, as shown in FIG. 1, N stripe blocks are used as data blocks to store streaming data, and another part of stripe blocks, such as M stripe blocks in FIG. 1, as check blocks to store parity data. The check data stored in the check block is obtained by performing erasure coding on the stream data stored in the data block. When the data block corresponding to the strip is damaged, it is referred to as a "bad block", resulting in the bad block. When the streaming data is lost, the erasure code calculation may be performed according to the check data in the check block, and the streaming data in the bad block is repaired.

In the prior art, the number of bad blocks corresponding to the stripe is not greater than the number of check blocks corresponding to the stripe, if the stream type data stored in the bad block corresponding to the stripe is repaired based on the erasure code; If the number of bad blocks corresponding to the strip is greater than the number of check blocks corresponding to the strip, the stream data stored in the bad block corresponding to the strip cannot be repaired. At this time, the strip can be determined to be damaged. Bands. In this case, if the normal data block corresponding to the strip is damaged, which is referred to as "normal block", and the damaged normal block occurs again, the streaming data stored in the re-damaged normal block will no longer be repaired.

Summary of the invention

The purpose of the embodiment of the present application is to provide an information processing method and apparatus, so that when the normal data block corresponding to the damaged strip is damaged again, the streaming data stored in the corrupted normal data block can be repaired. The specific technical solutions are as follows:

In one aspect, the embodiment of the present application discloses an information processing method, which is applied to a storage server. The method includes:

Obtaining strip information of at least one damaged strip from the metadata server, and using the strip information of the at least one damaged strip as the first strip information; the first strip information includes: normal block identifier and normal Streaming object data to which the streaming data stored in the block belongs;

The normal block corresponding to the identifier of the normal block is used as the first data block, and the first data block is grouped according to the streaming object data to which the streaming data stored in the normal block belongs;

Constructing at least one new normal strip for each set of first data blocks;

Obtaining stripe information of the at least one new normal stripe, and using the stripe information of the at least one new normal stripe as the second stripe information;

Transmitting the second stripe information to the metadata server to cause the metadata server to add the second stripe information.

Optionally, before the step of acquiring the strip information of the at least one damaged strip from the metadata server, the method further includes:

Detect whether there is a bad block in the local area;

If yes, the identifier of the bad block is sent to the metadata server, so that the metadata server updates the stripe information of the normal stripe and the stripe information of the damaged strip according to the identifier of the bad block.

Optionally, the step of obtaining the strip information of the at least one damaged strip from the metadata server includes:

Receiving stripe information of a preset number of damaged strips currently stored by the metadata server; or

Receiving stripe information of all currently stored corrupted strips periodically sent by the metadata server.

Optionally, the first strip information further includes: an offset of the streaming data stored in the normal block in the streaming object data;

After the step of grouping the first data block according to the streaming object data to which the streaming data stored in the normal block belongs, the method further includes:

According to the flow data stored in the normal block, the offsets in the streaming object data are in descending order. The first data block in each set of first data blocks is sorted.

Optionally, each stripe corresponds to N data blocks and M check blocks, where N and M are positive integers;

The step of constructing at least one new normal strip for each set of first data blocks includes:

For each first data block of the group, the first data block in the first data block of the group is subjected to erasure coding calculation for the streaming data stored in each of the N first data blocks in order from the front to the back. Check data of M check blocks; constructing a new normal strip by each N first data blocks and M check blocks corresponding to the N first data blocks;

Obtaining NS preset data blocks when the first first data blocks remain in the first data block of the group; and forming the N normal blocks by the S first data blocks and the NS preset data blocks, And performing the erasure code calculation on the stream data stored in the S first data blocks and the data stored in the NS preset data blocks, and obtaining the verification data of the M check blocks, where the S first Constructing a new normal stripe, wherein S is a positive integer, the data block and the M check blocks corresponding to the NS preset data blocks, the S first data blocks, and the NS preset data blocks. S<N.

Optionally, the method further includes:

Refusing to store data in the N-S preset data blocks to the storage server.

On the second aspect, the embodiment of the present application further discloses an information processing method, which is applied to a metadata server, and the method includes:

Transmitting the strip information of the at least one damaged strip to the storage server, so that the storage server uses the strip information of the at least one damaged strip as the first strip information, where the first strip information includes: The identifier of the block and the streaming object data to which the streaming data stored in the normal block belongs; the normal block corresponding to the identifier of the normal block is used as the first data block, and the streaming object belongs to the streaming data stored in the normal block Data, grouping the first data blocks; constructing at least one new normal strip for each set of first data blocks;

Receiving, by the storage server, second strip information; the second strip information is stripe information of the at least one new normal stripe;

The second strip information is stored.

Before the step of transmitting the stripe information of the at least one damaged strip to the storage server, the method further includes:

Receiving an identifier of a bad block sent by the storage server;

Determining strip information of a normal strip corresponding to the identifier of the bad block;

Marking, in the strip information of the normal stripe, a normal block corresponding to the identifier of the bad block as a bad block;

When the number of normal blocks marked as bad blocks in the strip information of the normal strip is greater than M, the strip information of the normal strip is updated to the strip information of the damaged strip.

Optionally, the step of sending the stripe information of the at least one damaged strip to the storage server includes:

When the stripe information of the preset number of damaged strips is currently stored in the metadata server, the stripe information of all the damaged strips is sent to the storage server; or

Timing information of all damaged strips currently stored is periodically sent to the storage server.

Optionally, after the step of storing the second strip information, the method further includes:

Delete the first strip information.

In one aspect, the embodiment of the present application further discloses an information processing apparatus, which is applied to a storage server, where the apparatus includes:

a first information acquiring unit, configured to acquire strip information of at least one damaged strip from the metadata server, and use the strip information of the at least one damaged strip as the first strip information; the first strip information The method includes: an identifier of a normal block and streaming object data to which the streaming data stored in the normal block belongs;

a block grouping unit, configured to use the normal block corresponding to the identifier of the normal block as the first data block, and group the first data block according to the streaming object data to which the streaming data stored in the normal block belongs;

a strip building unit for constructing at least one new normal strip for each set of first data blocks;

a second information acquiring unit, configured to acquire stripe information of the at least one new normal stripe, and use the stripe information of the at least one new normal stripe as the second stripe information;

And an information sending unit, configured to send the second stripe information to the metadata server, so that the metadata server adds the second stripe information.

Optionally, the device further includes:

a block detecting unit, configured to detect whether a local bad block exists before acquiring the stripe information of the at least one damaged stripe from the metadata server;

An identifier sending unit, configured to send, by the block detection unit, an identifier of the bad block to the metadata server, so that the metadata server is configured according to the identifier of the bad block Update the strip information of the normal strip and the strip information of the damaged strip.

Optionally, the first information acquiring unit is specifically configured to:

The device also includes:

a block sorting unit, configured to: after the first data block is grouped according to the streaming object data to which the streaming data stored in the normal block belongs, according to the streaming data stored in the normal block, in the streaming object data The order of the shifts from small to large, the first data block in each set of the first data block is sorted.

The strip building unit is specifically configured to:

Obtaining NS preset data blocks when the first first data blocks remain in the first data block of the group; and forming N normal blocks by the S first data blocks and the NS preset data blocks; The S first And performing the erasure code calculation on the stream data stored in the data block and the data stored in the NS preset data blocks, and obtaining the check data of the M check blocks, where the S first data blocks and the NS are The M parity blocks corresponding to the preset data blocks, the S first data blocks, and the NS preset data blocks construct a new normal stripe, where S is a positive integer, S<N.

Optionally, the device further includes:

And a storage rejecting unit, configured to refuse to store data in the N-S preset data blocks to the storage server.

In an aspect, the embodiment of the present application further discloses an information processing apparatus, which is applied to a metadata server, where the apparatus includes:

An information sending unit, configured to send the strip information of the at least one damaged strip to the storage server, so that the storage server uses the strip information of the at least one damaged strip as the first strip information, the first The stripe information includes: an identifier of a normal block and streaming object data to which the streaming data stored in the normal block belongs; a normal block corresponding to the identifier of the normal block is used as the first data block, and the flow is stored in the normal block. Streaming object data to which the data belongs, grouping the first data block; constructing at least one new normal strip for each set of the first data block;

An information receiving unit, configured to receive second strip information sent by the storage server; the second strip information is stripe information of the at least one new normal stripe;

An information storage unit, configured to store the second strip information.

The device also includes:

An identifier receiving unit, configured to receive an identifier of a bad block sent by the storage server before sending the stripe information of the at least one damaged strip to the storage server;

An information determining unit, configured to determine strip information of a normal stripe corresponding to the identifier of the bad block;

a block marking unit, configured to mark a normal block corresponding to the identifier of the bad block in the strip information of the normal stripe as a bad block;

An information updating unit, configured to: mark a normal block marked as a bad block in the strip information of the normal stripe When the number of the numbers is greater than M, the strip information of the normal strip is updated to the strip information of the damaged strip.

Optionally, the information sending unit is specifically configured to:

Optionally, the device further includes:

And an information deleting unit, configured to delete the first strip information after storing the second strip information.

In five aspects, the embodiment of the present application discloses a storage server, including a processor, a communication interface, a memory, and a communication bus; wherein the processor, the communication interface, and the memory complete communication with each other through the communication bus. ;

The memory is configured to store an application;

The processor, when used to execute an application stored on the memory, implements the above-mentioned information processing method steps applied to the storage server.

In one aspect, the embodiment of the present application discloses a metadata server, including a processor, a communication interface, a memory, and a communication bus; wherein the processor, the communication interface, and the memory complete each other through the communication bus. Communication;

The memory is configured to store an application;

The processor is configured to implement the information processing method step applied to the metadata server when the application stored on the memory is executed.

In the seventh aspect, the embodiment of the present application discloses an application program, which is used to implement the above-mentioned information processing method step applied to the storage server at runtime. .

In one aspect, the embodiment of the present application discloses an application program for implementing the above-mentioned information processing method step applied to the metadata server at runtime.

In nine aspects, the embodiment of the present application discloses a readable storage medium, and the readable storage medium is used. In the storage application, the application is implemented to implement the above-described information processing method steps applied to the storage server.

In ten aspects, the embodiment of the present application discloses a readable storage medium for storing an application, and the application is implemented to implement the above-mentioned information processing method step applied to the metadata server.

An embodiment of the present application provides an information processing method and apparatus, where a storage server obtains first strip information of at least one damaged strip from a metadata server, where the first strip information includes: an identifier of a normal block and a normal block. The streamed object data to which the stored stream data belongs is grouped according to the stream object data to which the stream data stored in the normal block belongs, and the normal blocks corresponding to the identifiers of the normal blocks are grouped, thereby constructing at least one new normal stripe, and The second stripe information is sent to the metadata server, and the metadata server adds the second stripe information. It can be seen that, in the embodiment of the present application, when the normal block corresponding to the damaged strip is damaged again, the normal block corresponding to the damaged strip re-constructs the new normal strip, and the corresponding data block of the new normal strip is Normal block, so the stream data stored in the normal block that is damaged again can be repaired according to the information of the new normal stripe, so that the normal data block corresponding to the damaged strip is damaged again, and the normal data block is damaged again. The streaming data stored in it can be repaired. Of course, implementing any of the products or methods of the present application necessarily does not necessarily require all of the advantages described above to be achieved at the same time.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings to be used in the embodiments or the related art description will be briefly described below. Obviously, the drawings in the following description are only Some embodiments of the application may also be used to obtain other figures from those of ordinary skill in the art without departing from the scope of the invention.

Figure 1 is a schematic view of a strip structure;

2 is a schematic flowchart of an information processing method according to an embodiment of the present application;

FIG. 3 is another schematic flowchart of an information processing method according to an embodiment of the present disclosure;

4 is a schematic diagram of a damaged strip obtained in an embodiment of the present application;

FIG. 5 is a schematic diagram of a new normal strip reconstructed in the embodiment of the present application; FIG.

FIG. 6 is a schematic flowchart diagram of another information processing method according to an embodiment of the present disclosure;

FIG. 7 is another schematic flowchart of another information processing method according to an embodiment of the present disclosure;

FIG. 8 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present disclosure;

FIG. 9 is another schematic structural diagram of an information processing apparatus according to an embodiment of the present disclosure;

FIG. 10 is a schematic structural diagram of another information processing apparatus according to an embodiment of the present disclosure;

FIG. 11 is another schematic structural diagram of another information processing apparatus according to an embodiment of the present application.

detailed description

The technical solutions in the embodiments of the present application are clearly and completely described in the following with reference to the drawings in the embodiments of the present application. It is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

For convenience of description of the present application, the definitions of the words appearing in the embodiments of the present application are described below:

The stripe block can store streaming data as a data block, or can store parity data as a check block;

The normal block is a normal data block, and the storage server can normally read the streaming data from the normal block;

The bad block is a corrupted data block, that is, a damaged normal block, and the storage server cannot read the streaming data from the bad block;

Among them, normal blocks and bad blocks are collectively referred to as data blocks.

The embodiments of the present application are described in detail below through specific embodiments.

Referring to FIG. 2, FIG. 2 is a schematic flowchart of an information processing method according to an embodiment of the present disclosure, which is applied to a storage server, and the method includes:

S201: Obtain at least one stripe information of the damaged strip from the metadata server, and use the stripe information of the at least one damaged strip as the first stripe information;

The first strip information may include: an identifier of the normal block and streaming object data to which the streaming data stored in the normal block belongs. Here, the streaming object data may be all the streaming data from the same terminal, or all the streaming data from the same time period, or some streaming data divided by the user, which is not performed by the embodiment of the present application. limited. In the streaming data loss part of the streaming object data, the user can still read other streaming data in the streaming object data.

In an embodiment of the present application, the stripe information of the damaged stripe acquired by the storage server may be: stripe information of all damaged strips currently stored in the metadata server. Generally, the metadata server may periodically send the stripe information of all the damaged strips currently stored to the storage server, or when the stripe information of the preset number of damaged strips is stored in the metadata server, The stripe information of the preset number of damaged strips currently stored is sent to the storage server.

In an embodiment of the present application, referring to FIG. 3, on the basis of FIG. 2, before the stripe information of the at least one damaged stripe is obtained from the metadata server, the information processing method may further include:

S301: Detect whether there is a bad block locally; if yes, S302;

In general, the storage server can periodically detect whether there is a bad block locally. In an embodiment of the present application, if the streaming data in a normal block fails to be read, the streaming data in the normal block is read again, and if it still fails, the normal block can be determined as a bad block.

S302: Send the identifier of the bad block to the metadata server.

The metadata server may store the metadata of the stripe, and the metadata of the stripe is stripe information, which may include: an identifier of the hard disk, an offset of the data block in the hard disk, an identifier of the data block, and a storage in the data block. The flow object data to which the streaming data belongs, the offset of the streaming data stored in the data block in the streaming object data, and the storage state of the data block are as shown in Table 1.

Table 1

The stripe block is divided into a data block and a check block. In the above table 1, the strip block can be understood as a data block and a strip. A set of strips is a set of data blocks corresponding to one stripe;

The hard disk identifier wwn (World Wide Name) is a unique 48-bit or 64-bit number assigned by an authoritative organization. It is specifically defined as a recognized name authorization, usually assigned to the manufacturer by region to distinguish One or a group of network connections; in order to reduce the probability of occurrence of damaged strips, each strip corresponding to one strip corresponds to one hard disk, for example, one strip corresponds to four strip blocks, and the strip corresponds to four different hard disks. ;

The offset of the sliced block in the streaming object data can be understood as the offset of the streaming data stored in the data block in the streaming object data; by the offset, combined with the stripe block, it can be understood as a data block. The offset in the hard disk can accurately read the streaming data stored in the data block;

The stream object data corresponding to the stripe block can be understood as the stream object data to which the stream data stored in the data block belongs. Generally, the metadata of the streaming object data may be stored in the metadata server, where the metadata of the streaming object data may include: an identifier of a strip corresponding to the data block storing the streaming data, and a size of the streaming object data. Information, as shown in Table 2.

Table 2

字段Field	Key(键)Key (key)	备注Remarks
object_keyObject_key	Primary Key(主键)Primary Key	流式对象数据Streaming object data
strip_id集合Strip_id collection		条带的标识的集合Collection of stripe logos
object_sizeObject_size		流式对象数据的大小Streaming object data size

The set of stripe identifiers is a set of identifiers of strips corresponding to the data blocks storing the stream data.

The status of the stripe block can be understood as the storage state of the data block. Here, the storage state of the data block may include a normal state and a damaged state. Specifically, when streaming data is stored in the data block, the storage state of the data block is set to a normal state, that is, the data block is marked as a normal block; when the data block is damaged, the data block is stored in the data block. When streaming data is lost, the storage state of the data block is set to a corrupted state, that is, the normal block is marked as a bad block.

After receiving the identifier of the bad block sent by the storage server, the metadata server determines the stripe information of the normal stripe corresponding to the identifier of the bad block, and marks the normal block corresponding to the identifier of the bad block in the stripe information of the normal stripe. a bad block, that is, a "strip block" of the normal block corresponding to the identification of the bad block The state is set to a damaged state; if the number of normal blocks marked as bad blocks in the normal strip is greater than the number of check blocks in the normal strip, the strip information of the normal strip is updated to Strip information for damaged strips.

S202: The normal block corresponding to the identifier of the normal block included in the first stripe information is used as the first data block, and the first data block is grouped according to the streaming object data to which the streaming data stored in the normal block belongs.

For example, as shown in FIG. 4, strip information of four damaged strips is acquired, which are strip information of the strip 1, strip information of the strip 2, strip information of the strip 3, and strip 4 Stripe information, wherein the data block 1, the data block 3, the data block 6, the data block 8, the data block 9, the data block 10, the data block 13, and the data block 14 of the four strips are normal blocks, that is, there are 8 The first data block, the streaming data 1 in the data block 1, the streaming data 3 in the data block 3, the streaming data 6 in the data block 6, and the streaming data 8 in the data block 8, The stream data 9 is stored in the data block 9, the stream data 10 is stored in the data block 10, the stream data 13 is stored in the data block 13, and the stream data 14 is stored in the data block 14, where the stream data 1 is stored. The streaming data 3, the streaming data 6, the streaming data 8, the streaming data 9 and the streaming data 10 belong to the streaming object data Object1, and the streaming data 13 and the streaming data 14 belong to the streaming object data Object2; In the case, when the first data block is grouped, the data block 1, the data block 3, the data block 6, the data block 8, the data block 9, and the data may be used. 10 grouped into a group, the data blocks 13 and 14 is divided into a set of data blocks.

S203: Construct at least one new normal strip for each set of the first data block;

In an embodiment of the present application, in order to facilitate data reading, after the plurality of first data blocks are grouped according to the streaming object data to which the streaming data stored in the normal block belongs, the data block may be stored in the data block. The streamed data is sorted in the order of offset from the streamed object data, and the first block of data in each group is sorted, and a new normal strip is constructed according to the sorted first block. Here, the offset of the streaming data stored in the data block in the streaming object data may be included in the stripe information of the acquired corrupted stripe.

For each group of first data blocks, after sorting in the first data block of the group, performing erasure coding calculation on the streaming data stored in each of the N first data blocks in order from the front to the back, and obtaining M check blocks. Check data; construct a new normal strip by each N first data blocks and M check blocks corresponding to the N first data blocks;

When S first data blocks remain in the first data block of the group, acquiring NS preset data blocks; and forming the N normal blocks by the S first data blocks and the NS preset data blocks; The stream data stored in the S first data blocks and the data stored in the NS preset data blocks are subjected to erasure code calculation, and the check data of the M check blocks is obtained, and the S first data blocks are used. The M parity blocks corresponding to the NS preset data blocks, the S first data blocks, and the NS preset data blocks construct a new normal stripe. It should be noted that S is a positive integer, S<N, and the preset data block can be an empty data block, that is, a data block that does not store any data, and can also be a data block of all 0s or other known data. This embodiment of the present application does not limit this.

Still speaking, the example in S202 is described, N=4. For the first data block of the Object1 group, the order of the offset of the streaming data stored in each first data block from the small to the largest in the streaming object data Object1 is: Data 1 - Streaming Data 3 - Streaming Data 6 - Streaming Data 8 - Streaming Data 9 - Streaming Data 10, the ordering of the first data block is: Data Block 1 - Data Block 3 - Data Block 6 - Data block 8 - data block 9 - data block 10, if one strip corresponds to 4 data blocks and 1 check block, the flow data stored in every 4 first data blocks is corrected in order from front to back. The code deletion calculation, that is, the first four normal blocks of the data block 1, the data block 3, the data block 6, and the data block 8, are first obtained, and the erasure code calculation is performed on the stream data stored in the four normal blocks to obtain 1 One test data 1, the one check data 1 is stored in the check block 1, as shown in FIG. 5, and one block is composed of the data block 1, the data block 3, the data block 6, the data block 8, and the check block 1. The new normal strip 5; at this time, the first data block of the Object1 group only has two normal blocks of the data block 9 and the data block 10, that is, S=2. At this time, 2<4, the NS=4 is obtained. -2=2 preset data blocks, which are composed of data block 9, data block 10 and the two preset data blocks, and form 4 normal blocks, and perform erasure code calculation on the data stored in the four data blocks to obtain 1 test data 2, the 1 check data 2 is stored in the check block 2, as shown in FIG. 5, the data block 9, the data block 10, the two preset data blocks and the check block 2 constitute one New normal strip 6.

In an embodiment of the present application, in order to save the storage space of the storage server, the data in the N-S preset data blocks is refused to be stored to the storage server.

S204: Obtain stripe information of at least one new normal stripe, and use stripe information of at least one new normal stripe as the second stripe information.

S205: Send the second stripe information to the metadata server.

The metadata server adds the second stripe information. In this way, when the normal data block is damaged and the streaming data is lost, the streaming data stored in the corrupted normal data block can be repaired.

In addition, in order to ensure that the streamed data stored in the normal data block that is re-damaged can be accurately repaired, the metadata server may delete the first stripe information after receiving the second stripe information.

As an example in S203, if a new normal strip 7 is formed by the data block 13, the data block 14, the two preset data blocks, and the check block 3 for the first data block of the Object2 group, the new normal strip will be used. 5. The strip information of the new normal strip 6 and the new normal strip 7 is used as the second strip information and sent to the metadata server, and the new normal strip 5, the new normal strip 6 and the new normal are added to the metadata server. The strip information of the strip 7 is additionally deleted for the strip information of the original strip 1, the strip information of the strip 2, the strip information of the strip 3, and the strip information of the strip 4.

In addition, the streaming data is read according to the metadata of the streaming object data. After the strip is reconstructed, the data block storing the streaming data and the corresponding stripe are changed. Therefore, in order to ensure the reading of the streaming data. After the metadata server obtains the second strip information, it should also update the metadata of the streaming object data.

Applying the foregoing embodiment, the storage server acquires, from the metadata server, the first stripe information of the at least one damaged stripe, where the first stripe information includes: an identifier of the normal block and a stream to which the streaming data stored in the normal block belongs The object data is grouped according to the stream object data to which the stream data stored in the normal block belongs, and the normal blocks corresponding to the identifiers of the normal blocks are grouped, thereby constructing at least one new normal stripe, and transmitting the second stripe information to the element. The data server, the metadata server adds the second stripe information. It can be seen that, in the embodiment of the present application, when the normal block corresponding to the damaged strip is damaged again, the normal block corresponding to the damaged strip re-constructs the new normal strip, and the corresponding data block of the new normal strip is Normal block, so the stream data stored in the normal block that is damaged again can be repaired according to the information of the new normal stripe, so that the normal data block corresponding to the damaged strip is damaged again, and the normal data block is damaged again. The streaming data stored in it can be repaired.

Referring to FIG. 6, FIG. 6 is a schematic flowchart of another information processing method according to an embodiment of the present application, which is applied to a metadata server, and the method includes:

S601: Send the strip information of the at least one damaged strip to the storage server;

In this case, the storage server may use the stripe information of the at least one damaged stripe as the first stripe information, where the first stripe information includes: an identifier of the normal block and a streamed data stored in the normal block. Streaming object data; the normal block corresponding to the identifier of the normal block is used as the first data Blocking, grouping the first data blocks according to the streaming object data to which the streaming data stored in the normal block belongs; constructing at least one new normal strip for each set of the first data block.

In an embodiment of the present application, the stripe information of the damaged stripe acquired by the storage server may be: stripe information of all damaged strips currently stored in the metadata server. Generally, the metadata server may periodically send the stripe information of all the damaged strips currently stored to the storage server, or when the stripe information of the preset number of damaged strips is stored in the metadata server, The strip information of the preset number of damaged strips currently stored is sent to the storage server.

In an embodiment of the present application, referring to FIG. 7, on the basis of FIG. 6, each strip corresponds to N data blocks and M check blocks, where N and M are positive integers, and at least one piece is damaged. Before the stripe information of the stripe is sent to the storage server, the information processing method may further include:

S701: Receive an identifier of a bad block sent by the storage server.

Generally, the storage server can periodically detect whether there is a bad block locally, and when the presence is detected, send the identifier of the bad block to the metadata server.

S702: Determine strip information of a normal stripe corresponding to the identifier of the bad block;

S703: mark the normal block corresponding to the identifier of the bad block in the strip information of the normal stripe as a bad block;

S704: When the number of normal blocks marked as bad blocks in the strip information of the normal strip is greater than M, the strip information of the normal strip is updated to the strip information of the damaged strip.

S602: Receive second strip information sent by the storage server; the second strip information is strip information of at least one new normal stripe;

S603: Store the second strip information.

In addition, in order to ensure that the stream data stored in the normal data block that is damaged again can be accurately repaired, and avoiding a normal data block corresponding to multiple stripe information, the metadata server may also receive the second strip information after receiving the second strip information. Delete the first strip information.

Applying the foregoing embodiment, the storage server acquires, from the metadata server, the first stripe information of the at least one damaged stripe, where the first stripe information includes: an identifier of the normal block and a stream to which the streaming data stored in the normal block belongs The object data is grouped according to the stream object data to which the stream data stored in the normal block belongs, and the data blocks corresponding to the identifiers of the normal blocks are grouped, thereby constructing at least one new normal strip. Band, and send the second strip information to the metadata server, the metadata server adds the second strip information. It can be seen that, in the embodiment of the present application, when the normal block corresponding to the damaged strip is damaged again, the normal block corresponding to the damaged strip re-constructs the new normal strip, and the data block of the new normal strip is normal. Block, so according to the information of the new normal stripe, the stream data stored in the normal block that is damaged again can be repaired, thereby ensuring that the data block corresponding to the damaged strip is damaged again, and the damaged data block is stored. Repair of streaming data.

Corresponding to the method embodiment, the embodiment of the present application further provides an information processing apparatus.

Referring to FIG. 8, FIG. 8 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present application, which is applied to a storage server, where the apparatus includes:

a first information acquiring unit 801, configured to acquire strip information of at least one damaged strip from the metadata server, and use strip information of the at least one damaged strip as first strip information; the first strip The information includes: an identifier of a normal block and streaming object data to which the streaming data stored in the normal block belongs;

a block grouping unit 802, configured to use the normal block corresponding to the identifier of the normal block as the first data block, and group the first data block according to the streaming object data to which the streaming data stored in the normal block belongs;

a strip construction unit 803, configured to construct at least one new normal strip for each set of first data blocks;

a second information acquiring unit 804, configured to acquire stripe information of the at least one new normal stripe, and use stripe information of the at least one new normal stripe as the second stripe information;

The information sending unit 805 is configured to send the second stripe information to the metadata server, so that the metadata server adds the second stripe information.

In other embodiments of the present application, referring to FIG. 9, on the basis of FIG. 8, the apparatus may further include:

The block detecting unit 901 is configured to detect whether a bad block exists locally before acquiring the stripe information of the at least one damaged stripe from the metadata server;

The identifier sending unit 902 is configured to send the identifier of the bad block to the metadata server if the detection result of the block detecting unit 901 is yes, so that the metadata server is configured according to the The identification of the bad block updates the strip information of the normal strip and the strip information of the damaged strip.

In other embodiments of the present application, the first information acquiring unit 801 may be specifically configured to:

In other embodiments of the present application, the first stripe information may further include: an offset of the streaming data stored in the normal block in the streaming object data;

In this case, the device may further include:

In other embodiments of the present application, each strip corresponds to N data blocks and M check blocks, where N and M are positive integers;

The strip construction unit 803 can be specifically configured to:

Obtaining NS preset data blocks when the first first data blocks remain in the first data block of the group; and forming N normal blocks by the S first data blocks and the NS preset data blocks; And performing the erasure code calculation on the stream data stored in the S first data blocks and the data stored in the NS preset data blocks, and obtaining the verification data of the M check blocks, where the S first Constructing a new normal stripe, wherein S is a positive integer, the data block and the M check blocks corresponding to the NS preset data blocks, the S first data blocks, and the NS preset data blocks. S<N.

In other embodiments of the present application, the apparatus may further include:

a storage rejecting unit, configured to refuse to store data in the N-S preset data blocks to the storage Storage server.

Referring to FIG. 10, FIG. 10 is a schematic structural diagram of another information processing apparatus according to an embodiment of the present disclosure, which is applied to a metadata server, where the apparatus includes:

The information sending unit 1001 is configured to send the strip information of the at least one damaged strip to the storage server, so that the storage server uses the strip information of the at least one damaged strip as the first strip information, where the The information of the strip includes: the identifier of the normal block and the stream object data to which the stream data stored in the normal block belongs; the normal block corresponding to the identifier of the normal block is used as the first data block, and the stream stored in the normal block is used. Streaming object data to which the data belongs, grouping the first data block; constructing at least one new normal strip for each set of the first data block;

The information receiving unit 1002 is configured to receive second strip information sent by the storage server, where the second strip information is strip information of the at least one new normal stripe;

The information storage unit 1003 is configured to store the second strip information.

In this case, referring to FIG. 11, on the basis of FIG. 10, the apparatus may further include:

The identifier receiving unit 1101 is configured to receive an identifier of the bad block sent by the storage server before sending the stripe information of the at least one damaged strip to the storage server;

The information determining unit 1102 is configured to determine strip information of a normal stripe corresponding to the identifier of the bad block;

a block marking unit 1103, configured to mark a normal block corresponding to the identifier of the bad block in the stripe information of the normal stripe as a bad block;

The information updating unit 1104 is configured to update the strip information of the normal stripe to a strip of the damaged strip when the number of normal blocks marked as bad blocks in the strip information of the normal strip is greater than M information.

In other embodiments of the present application, the information sending unit 1001 may be specifically configured to:

The stripe information of all damaged strips currently stored is periodically sent to the storage server.

In other embodiments of the present application, the apparatus further includes:

The embodiment of the present application further provides a storage server, including a processor, a communication interface, a memory, and a communication bus; wherein the processor, the communication interface, and the memory complete communication with each other through a communication bus;

Memory for storing applications;

A processor that implements an information processing method when executing an application stored on the memory. The information processing method includes:

Obtaining at least one stripe information of the damaged stripe from the metadata server, and using the stripe information of the at least one damaged stripe as the first stripe information; the first stripe information includes: an identifier of the normal block and the storage in the normal block Streaming object data to which streaming data belongs;

Constructing at least one new normal strip for each set of first data blocks;

Obtaining strip information of at least one new normal stripe, and using stripe information of at least one new normal stripe as the second stripe information;

The second stripe information is sent to the metadata server to cause the metadata server to add the second stripe information.

In an embodiment of the present application, before the step of acquiring the stripe information of the at least one damaged strip from the metadata server, the method may further include:

Detect whether there is a bad block in the local area;

If so, the identifier of the bad block is sent to the metadata server, so that the metadata server updates the stripe information of the normal stripe and the stripe information of the damaged stripe according to the identifier of the bad block.

In an embodiment of the present application, the step of acquiring strip information of at least one damaged strip from the metadata server includes:

Receives stripe information of all corrupted strips currently stored by the metadata server.

In an embodiment of the present application, the first stripe information may further include: an offset of the streaming data stored in the normal block in the streaming object data;

In this case, after the step of grouping the first data block according to the streaming object data to which the streaming data stored in the normal block belongs, the method may further include:

The first data block in each set of the first data block is sorted in order of the offset of the streaming data stored in the normal block in the streaming object data from small to large.

In an embodiment of the present application, each strip corresponds to N data blocks and M check blocks, where N and M are positive integers;

In this case, the step of constructing at least one new normal strip for each set of first data blocks includes:

When the first data blocks are stored in the first data block of the group, the NS preset data blocks are obtained; the S first data blocks and the NS preset data blocks form N normal blocks, and the first ones are S. The stream data stored in the data block and the data stored in the NS preset data blocks are subjected to erasure code calculation, and the check data of the M check blocks is obtained, and the S first data blocks correspond to the NS preset data blocks. M check blocks, S first data blocks, and NS preset data blocks are constructed to construct a new normal stripe, where S is a positive integer, S < N.

In an embodiment of the present application, the information processing method may further include:

The data in the N-S preset data blocks is refused to be stored to the storage server.

The communication bus mentioned by the above storage server may be PCI (Peripheral Component) Interconnect, peripheral component interconnect standard) bus or EISA (Extended Industry Standard Architecture) bus. The communication bus can be divided into an address bus, a data bus, a control bus, and the like.

The communication interface is used for communication between the above storage server and other devices.

The memory may include a RAM (Random Access Memory), and may also include NVM (Non-Volatile Memory), such as at least one disk storage. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

The processor may be a general-purpose processor, including a CPU (Central Processing Unit), an NP (Network Processor), or the like; or a DSP (Digital Signal Processing) or an ASIC (Application) Specific Integrated Circuit, FPGA (Field-Programmable Gate Array) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.

The embodiment of the present application further provides a metadata server, including a processor, a communication interface, a memory, and a communication bus; wherein the processor, the communication interface, and the memory complete communication with each other through the communication bus;

Memory for storing applications;

Sending the stripe information of the at least one damaged strip to the storage server, so that the storage server uses the stripe information of the at least one damaged strip as the first stripe information, where the first stripe information includes: the identifier of the normal block and the normal block The streaming object data to which the streaming data stored in the stream belongs; the normal block corresponding to the identifier of the normal block is used as the first data block, and the first data block is performed according to the streaming object data to which the streaming data stored in the normal block belongs Grouping; constructing at least one new normal strip for each set of first data blocks;

Receiving, by the storage server, second strip information; the second strip information is strip information of at least one new normal stripe;

Store the second strip information.

In this case, before the step of sending the stripe information of the at least one damaged strip to the storage server, the method may further include:

Receiving an identifier of a bad block sent by the storage server;

Marking the normal block corresponding to the identifier of the bad block in the strip information of the normal stripe as a bad block;

In an embodiment of the present application, the step of transmitting the stripe information of the at least one damaged strip to the storage server includes:

In an embodiment of the present application, after the step of storing the second strip information, the method further includes:

Delete the first strip information.

Applying the foregoing embodiment, the storage server acquires, from the metadata server, the first stripe information of the at least one damaged stripe, where the first stripe information includes: an identifier of the normal block and a stream to which the streaming data stored in the normal block belongs The object data is grouped according to the stream object data to which the stream data stored in the normal block belongs, and the normal blocks corresponding to the identifiers of the normal blocks are grouped, thereby constructing at least one new normal stripe, and transmitting the second stripe information to the element. The data server, the metadata server adds the second stripe information. It can be seen that, in the embodiment of the present application, when the normal block corresponding to the damaged strip is damaged again, the normal block corresponding to the damaged strip re-constructs the new normal strip, and the corresponding data block of the new normal strip is Normal block, so it can be stored in the normal block that is damaged again based on the information of the new normal strip. The stored streaming data is repaired, so that when the normal data block corresponding to the damaged strip is damaged again, the streaming data stored in the corrupted normal data block can be repaired.

The communication bus mentioned by the above metadata server may be a PCI bus or an EISA bus or the like. The communication bus can be divided into an address bus, a data bus, a control bus, and the like.

The communication interface is used for communication between the above metadata server and other devices.

The memory may include RAM, and may also include an NVM, such as at least one disk storage. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

The above processor may be a general-purpose processor, including a CPU, an NP, etc.; or may be a DSP, an ASIC, an FPGA, or other programmable logic device, a discrete gate or a transistor logic device, or a discrete hardware component.

The embodiment of the present application also provides an application program for implementing an information processing method at runtime. The information processing method includes:

Constructing at least one new normal strip for each set of first data blocks;

Detect whether there is a bad block in the local area;

Store the second strip information.

Receiving an identifier of a bad block sent by the storage server;

Delete the first strip information.

The embodiment of the present application further provides a readable storage medium for storing an application, and the application is implemented to implement an information processing method. The information processing method includes:

The normal block corresponding to the identifier of the normal block is used as the first data block, and the flow stored in the normal block is used. Streaming object data to which the data belongs, grouping the first data block;

Constructing at least one new normal strip for each set of first data blocks;

Detect whether there is a bad block in the local area;

Sending the stripe information of the at least one damaged strip to the storage server, so that the storage server uses the stripe information of the at least one damaged strip as the first stripe information, where the first stripe information includes: the identifier of the normal block and the normal block The streaming object data to which the streaming data stored in the stream belongs; the normal block corresponding to the identifier of the normal block is used as the first data block, and the first data block is performed according to the streaming object data to which the streaming data stored in the normal block belongs Grouping; building at least one new positive for each group of first data blocks Constant strip

Store the second strip information.

Receiving an identifier of a bad block sent by the storage server;

Delete the first strip information.

Applying the foregoing embodiment, the storage server acquires, from the metadata server, the first stripe information of the at least one damaged stripe, where the first stripe information includes: an identifier of the normal block and a stream to which the streaming data stored in the normal block belongs The object data is grouped according to the stream object data to which the stream data stored in the normal block belongs, and the normal blocks corresponding to the identifiers of the normal blocks are grouped, thereby constructing at least one new normal stripe, and transmitting the second stripe information to the element. Data server, metadata server adds second strip letter interest. It can be seen that, in the embodiment of the present application, when the normal block corresponding to the damaged strip is damaged again, the normal block corresponding to the damaged strip re-constructs the new normal strip, and the corresponding data block of the new normal strip is Normal block, so the stream data stored in the normal block that is damaged again can be repaired according to the information of the new normal stripe, so that the normal data block corresponding to the damaged strip is damaged again, and the normal data block is damaged again. The streaming data stored in it can be repaired.

For the information processing apparatus, the storage server, the metadata server, the application program, and the readable storage medium embodiment, since it is basically similar to the information processing method embodiment, the description is relatively simple, and the related information refers to the information processing method embodiment. Part of the description can be.

It should be noted that, in this context, relational terms such as first and second are used merely to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply such entities or operations. There is any such actual relationship or order between them. Furthermore, the term "comprises" or "comprises" or "comprises" or any other variations thereof is intended to encompass a non-exclusive inclusion, such that a process, method, article, or device that comprises a plurality of elements includes not only those elements but also Other elements, or elements that are inherent to such a process, method, item, or device. An element that is defined by the phrase "comprising a ..." does not exclude the presence of additional equivalent elements in the process, method, item, or device that comprises the element.

The various embodiments in the present specification are described in a related manner, and the same or similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the information processing apparatus, the storage server, the metadata server, and the readable storage medium embodiment, since it is basically similar to the information processing method embodiment, the description is relatively simple, and the relevant places are referred to the information processing method embodiment. Part of the description is fine.

The above description is only the preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application are included in the scope of the present application.

Claims

An information processing method is applied to a storage server, and the method includes:

Obtaining strip information of at least one damaged strip from the metadata server, and using the strip information of the at least one damaged strip as the first strip information; the first strip information includes: normal block identifier and normal Streaming object data to which the streaming data stored in the block belongs;

The normal block corresponding to the identifier of the normal block is used as the first data block, and the first data block is grouped according to the streaming object data to which the streaming data stored in the normal block belongs;

Constructing at least one new normal strip for each set of first data blocks;

Obtaining stripe information of the at least one new normal stripe, and using the stripe information of the at least one new normal stripe as the second stripe information;

Transmitting the second stripe information to the metadata server to cause the metadata server to add the second stripe information.
The method according to claim 1, wherein before the step of acquiring the stripe information of the at least one damaged stripe from the metadata server, the method further comprises:

Detect whether there is a bad block in the local area;

If yes, the identifier of the bad block is sent to the metadata server, so that the metadata server updates the stripe information of the normal stripe and the stripe information of the damaged strip according to the identifier of the bad block.
The method according to claim 1 or 2, wherein the step of acquiring strip information of at least one damaged strip from the metadata server comprises:

Receiving stripe information of a preset number of damaged strips currently stored by the metadata server; or

Receiving stripe information of all currently stored corrupted strips periodically sent by the metadata server.
The method according to claim 1, wherein the first stripe information further comprises: an offset of the streaming data stored in the normal block in the streaming object data;

After the step of grouping the first data block according to the streaming object data to which the streaming data stored in the normal block belongs, the method further includes:

The first data block in each set of the first data block is sorted in order of the offset of the streaming data stored in the normal block in the streaming object data from small to large.
The method according to claim 4, wherein each strip corresponds to N data blocks and M check blocks, wherein N and M are positive integers;

The step of constructing at least one new normal strip for each set of first data blocks includes:

For each first data block of the group, the first data block in the first data block of the group is subjected to erasure coding calculation for the streaming data stored in each of the N first data blocks in order from the front to the back. Check data of M check blocks; constructing a new normal strip by each N first data blocks and M check blocks corresponding to the N first data blocks;

Obtaining NS preset data blocks when the first first data blocks remain in the first data block of the group; and forming the N normal blocks by the S first data blocks and the NS preset data blocks, And performing the erasure code calculation on the stream data stored in the S first data blocks and the data stored in the NS preset data blocks, and obtaining the verification data of the M check blocks, where the S first Constructing a new normal stripe, wherein S is a positive integer, the data block and the M check blocks corresponding to the NS preset data blocks, the S first data blocks, and the NS preset data blocks. S<N.
The method of claim 5, wherein the method further comprises:

Refusing to store data in the N-S preset data blocks to the storage server.
An information processing method, which is applied to a metadata server, the method comprising:

Transmitting the strip information of the at least one damaged strip to the storage server, so that the storage server uses the strip information of the at least one damaged strip as the first strip information, where the first strip information includes: The identifier of the block and the streaming object data to which the streaming data stored in the normal block belongs; the normal block corresponding to the identifier of the normal block is used as the first data block, and the streaming object belongs to the streaming data stored in the normal block Data, grouping the first data blocks; constructing at least one new normal strip for each set of first data blocks;

Receiving, by the storage server, second strip information; the second strip information is stripe information of the at least one new normal stripe;

The second strip information is stored.
The method according to claim 7, wherein each strip corresponds to N data blocks and M check blocks, wherein N and M are positive integers;

Before the step of transmitting the stripe information of the at least one damaged strip to the storage server, the method further includes:

Receiving an identifier of a bad block sent by the storage server;

Determining strip information of a normal strip corresponding to the identifier of the bad block;

Marking, in the strip information of the normal stripe, a normal block corresponding to the identifier of the bad block as a bad block;

When the number of normal blocks marked as bad blocks in the strip information of the normal strip is greater than M, the strip information of the normal strip is updated to the strip information of the damaged strip.
The method according to claim 7, wherein the step of transmitting the stripe information of the at least one damaged strip to the storage server comprises:

When the stripe information of the preset number of damaged strips is currently stored in the metadata server, the stripe information of all the damaged strips is sent to the storage server; or

Timing information of all damaged strips currently stored is periodically sent to the storage server.
The method according to any one of claims 7-9, wherein after the step of storing the second strip information, the method further comprises:

Delete the first strip information.
An information processing apparatus is applied to a storage server, and the apparatus includes:

a first information acquiring unit, configured to acquire strip information of at least one damaged strip from the metadata server, and use the strip information of the at least one damaged strip as the first strip information; the first strip information The method includes: an identifier of a normal block and streaming object data to which the streaming data stored in the normal block belongs;

a block grouping unit, configured to use the normal block corresponding to the identifier of the normal block as the first data block, and perform the first data block according to the streaming object data to which the streaming data stored in the normal block belongs Grouping

a strip building unit for constructing at least one new normal strip for each set of first data blocks;

a second information acquiring unit, configured to acquire stripe information of the at least one new normal stripe, and use the stripe information of the at least one new normal stripe as the second stripe information;

And an information sending unit, configured to send the second stripe information to the metadata server, so that the metadata server adds the second stripe information.
The device according to claim 11, wherein the device further comprises:

a block detecting unit, configured to detect whether a local bad block exists before acquiring the stripe information of the at least one damaged stripe from the metadata server;

An identifier sending unit, configured to send, by the block detection unit, an identifier of the bad block to the metadata server, so that the metadata server is configured according to the identifier of the bad block Update the strip information of the normal strip and the strip information of the damaged strip.
The device according to claim 11 or 12, wherein the first information acquiring unit is specifically configured to:

Receiving stripe information of a preset number of damaged strips currently stored by the metadata server; or

Receiving stripe information of all currently stored corrupted strips periodically sent by the metadata server.
The apparatus according to claim 11, wherein the first stripe information further comprises: an offset of the streaming data stored in the normal block in the streaming object data;

The device also includes:

a block sorting unit, configured to: after the first data block is grouped according to the streaming object data to which the streaming data stored in the normal block belongs, according to the streaming data stored in the normal block, in the streaming object data The order of the shifts from small to large, the first data block in each set of the first data block is sorted.
The apparatus according to claim 14, wherein each strip corresponds to N data blocks and M check blocks, wherein N and M are positive integers;

The strip building unit is specifically configured to:

For each first data block of the group, the first data block in the first data block of the group is subjected to erasure coding calculation for the streaming data stored in each of the N first data blocks in order from the front to the back. Check data of M check blocks; constructing a new normal strip by each N first data blocks and M check blocks corresponding to the N first data blocks;

Obtaining NS preset data blocks when the first first data blocks remain in the first data block of the group; and forming N normal blocks by the S first data blocks and the NS preset data blocks; And performing the erasure code calculation on the stream data stored in the S first data blocks and the data stored in the NS preset data blocks, and obtaining the verification data of the M check blocks, where the S first Constructing a new normal stripe, wherein S is a positive integer, the data block and the M check blocks corresponding to the NS preset data blocks, the S first data blocks, and the NS preset data blocks. S<N.
The device according to claim 15, wherein the device further comprises:

And a storage rejecting unit, configured to refuse to store data in the N-S preset data blocks to the storage server.
An information processing apparatus is applied to a metadata server, the apparatus comprising:

An information sending unit, configured to send the strip information of the at least one damaged strip to the storage server, so that the storage server uses the strip information of the at least one damaged strip as the first strip information, the first The stripe information includes: an identifier of a normal block and streaming object data to which the streaming data stored in the normal block belongs; a normal block corresponding to the identifier of the normal block is used as the first data block, and the flow is stored in the normal block. Streaming object data to which the data belongs, grouping the first data block; constructing at least one new normal strip for each set of the first data block;

An information receiving unit, configured to receive second strip information sent by the storage server; the second strip information is stripe information of the at least one new normal stripe;

An information storage unit, configured to store the second strip information.
The apparatus according to claim 17, wherein each strip corresponds to N data blocks and M check blocks, wherein N and M are positive integers;

The device also includes:

An identifier receiving unit, configured to receive an identifier of a bad block sent by the storage server before sending the stripe information of the at least one damaged strip to the storage server;

An information determining unit, configured to determine strip information of a normal stripe corresponding to the identifier of the bad block;

a block marking unit, configured to mark a normal block corresponding to the identifier of the bad block in the strip information of the normal stripe as a bad block;

An information updating unit, configured to update strip information of the normal stripe to stripe information of the damaged stripe when the number of normal blocks marked as bad blocks in the stripe information of the normal stripe is greater than M .
The device according to claim 17, wherein the information sending unit is specifically configured to:

When the stripe information of the preset number of damaged strips is currently stored in the metadata server, the stripe information of all the damaged strips is sent to the storage server; or

Timing information of all damaged strips currently stored is periodically sent to the storage server.
The device according to any one of claims 17 to 19, wherein the device further comprises:

And an information deleting unit, configured to delete the first strip information after storing the second strip information.
A storage server, comprising: a processor, a communication interface, a memory, and a communication bus; wherein the processor, the communication interface, and the memory complete communication with each other through the communication bus;

The memory is configured to store an application;

The processor, when used to execute an application stored on the memory, implements the method steps of any of claims 1-6.
A metadata server, comprising: a processor, a communication interface, a memory, and a communication bus; wherein the processor, the communication interface, and the memory complete communication with each other through the communication bus;

The memory is configured to store an application;

The processor, when executed to execute an application stored on the memory, implements the method steps of any one of claims 7-10.
An application, characterized in that the application is operative to implement the method steps of any of claims 1-6 at runtime.
An application, characterized in that the application is adapted to implement the method steps of any of claims 7-10 at runtime.
A readable storage medium, characterized in that the readable storage medium is for storing an application, the application being executed to implement the method steps of any of claims 1-6.
A readable storage medium, characterized in that the readable storage medium is for storing an application, the application being executed to implement the method steps of any of claims 7-10.