WO2018072420A1

WO2018072420A1 - Storage management method and storage device

Info

Publication number: WO2018072420A1
Application number: PCT/CN2017/081335
Authority: WO
Inventors: 陈业夫; 王万振
Original assignee: 华为技术有限公司
Priority date: 2016-10-20
Filing date: 2017-04-21
Publication date: 2018-04-26
Also published as: CN106569742A; CN106569742B

Abstract

The present application relates to the field of computers, and in particular, to storage management technology. A storage management method, comprising: receiving a data read command (comprising the logical address of target data); according to the logical address, searching index data for a target data area corresponding to the logical address and the initial lifecycle number of the target data area; acquiring the lifecycle number of the target data area; when it is determined that the lifecycle number is inconsistent with the initial lifecycle number, not executing the data read command. In the present invention, during the reading process, if the initial lifecycle number of the target data area recorded by the index data is different from the current lifecycle number, the data read command is not executed. That is, during the reading process of the present invention, whether the index data is invalid is identified by means of the lifecycle number; if the index data is invalid, the data read command is not executed, thereby avoiding incorrect data from being read.

Description

Storage management method and storage device

Technical field

This application relates to the field of computers, and more particularly to storage management techniques.

Background technique

Currently, the storage medium of many computers (such as desktops) and controllers of disk arrays may include an SSD (Solid State Disk). Compared to traditional mechanical hard drives, SSDs have excellent read and write performance, but their capacity is small (because they are more expensive). Therefore, the SSD is widely used as a read-only cache, and hotspot data that is frequently accessed in the mechanical hard disk is placed in the SSD.

The above hotspot data is identified by LBA (Logical Block Address). Referring to Figure 1, the storage system divides the storage space of the SSD into several segments (the size is roughly several tens of MB), and according to the SSD The storage addresses are numbered in order from low to high, and each segment includes several blocks.

After the hotspot data is written into the storage space (physical storage space) of the SSD, the relationship between the physical storage address and the logical storage address needs to be established. That is, a forward index needs to be established in the system memory so that the corresponding segments and blocks can be found from the LBA. For example, if the hotspot data corresponding to LBA a is written to block x on segment r, a forward index a--->(r, x) is established. In addition, you need to create an inverted index (find the corresponding LBA from segment and block). For example, if the hotspot data corresponding to LBA a is written to block x on segment r as an example, the reverse index to be established is (r, x)--->a.

After all the segments on the SSD are used up, some segments need to be released. The forward index corresponding to the released segment is invalid. Therefore, during the process of reading data, an invalid forward index may be searched to read the wrong data.

Summary of the invention

In order to solve the above problem, the present application provides a storage management method and a storage device to solve the problem that an invalid forward index may be searched and data may be read incorrectly during data reading.

To achieve the above objective, the embodiment of the present invention provides the following technical solutions:

In one aspect, an embodiment of the present application provides a storage management method, where the method is applied to a storage device, where the storage device includes a processor and a solid state drive (SSD), the solid state drive includes a plurality of data areas, each data An area includes one or more blocks, and in the method performed by the processor, an initial lifecycle number is assigned to an object (eg, a storage disk, a data area), at the end of the lifetime or at the beginning of a new lifetime , giving the object a new lifecycle number. Before using this object, you need to compare whether the initial lifecycle number is consistent with the current lifecycle number. If they are inconsistent, the object is invalid and will not be used continuously. This will avoid reading the wrong data.

In one possible design, the above object is specifically a data area, such as a segment. Then the step performed by the processor includes: receiving a read data instruction including a logical address of the target data; searching in the index data according to the logical address, to obtain a target data area corresponding to the logical address and an initial life cycle number thereof (index The data includes a correspondence between the logical address and an initial life cycle number of the target data area; obtaining a life cycle number of the target data area, and when determining that the life cycle number is inconsistent with the initial life cycle number, The above read data instruction is not executed. Further, when it is determined that the life cycle number is the same as the initial life cycle number, the target data stored in the target data area is read. It can be seen that during the reading process, if the initial life cycle number of the target data area of the index data record is different from the current life cycle number of the target data area, the read data instruction will not be executed. That is, reading in the present invention In the process, the life cycle number is used to identify whether the index data is invalid. If it is invalid, the read data command is not executed, thereby avoiding reading the wrong data.

In a possible design, when it is determined that the life cycle number is inconsistent with the initial life cycle number, the processor may also delete the index data corresponding to the logical address. This avoids reading invalid index data and improves reading efficiency.

In one possible design, the storage device can also write the target data before receiving the read data command described above. The writing process may include: the processor receiving the write data instruction (including the target data and its logical address), determining the target data area corresponding to the target data and its initial life cycle number, and saving the logical address and the initial life cycle number. The correspondence between the two is related to the aforementioned index data. In one example, an initial lifecycle number can be assigned to the target data region after the target data is written. In another example, each data region is assigned a raw lifecycle number (typically 0) at the factory, or when the SSD is first initialized. In the process of using SSD, monotonous increment or monotonous decrement is performed based on the original life cycle number. After the target data is written, the current life cycle number of the target data area can be used as the initial life cycle number. Different from the existing storage management method, the existing storage management method establishes a forward index and a reverse index. In this embodiment, after the storage device writes the target data, the index data including the initial life cycle number of the target data region is established, and the index data in this embodiment is similar to the existing forward index, but In contrast, the correspondence between the logical address and the initial life cycle number is increased. In the meantime, in this embodiment, the previous reverse index is no longer maintained, which reduces memory consumption and reduces management complexity.

In one possible design, the storage device may also release the data area after the write process and before the read process. The releasing process may include receiving an instruction to release the target data area, and modifying the initial life cycle number to the life cycle number. In one example, the initial lifecycle number can be increased by m to get a new lifecycle number. m can be a positive integer or a negative integer. Compared with the existing release mode, the release mode provided by the embodiment of the present invention only needs to modify the initial life cycle number, avoids complicated operations, and improves processing efficiency.

In one possible design, the storage device may also perform data deletion. In an example, the deleting process may include: receiving a delete data instruction, the delete data instruction including a logical address of the target data; and setting the index data corresponding to the logical address to be invalid. In the existing storage mode, when it is necessary to delete the target data corresponding to LBA a, it is assumed that the forward index corresponding to LBA a is a--->> (r, x), and the reverse index is (r, x)-- ->a, you need to find (r, x) from the forward index a, then invalidate the reverse index (r, x) ---> a, and finally invalidate the forward index a---> (r, x). In contrast, in this embodiment, the index data corresponding to the logical address is directly set to be invalid, so that the operation steps can be greatly reduced.

On the other hand, an embodiment of the present invention provides a storage device, which has a function of realizing the behavior of the storage device in the foregoing method. The functions may be implemented by hardware or by corresponding software implemented by hardware. The hardware or software includes one or more modules corresponding to the functions described above.

In one possible design, the structure of the storage device includes: a processor and a memory, the processor executing the execution of the storage device by running a software program stored in the memory, calling data stored in the memory Methods.

In still another aspect, an embodiment of the present invention provides a computer storage medium for storing computer software instructions for use in the foregoing storage device, including a program designed to perform the above aspects.

In the present invention, in the reading process, if the initial life cycle number of the target data area of the index data record is different from the current life cycle number of the target data area, the read data instruction is not executed. That is, in the reading process of the present invention, the life cycle number is used to identify whether the index data is invalid, and if it is invalid, the data reading instruction is not executed, thereby avoiding Read the wrong data.

DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings to be used in the embodiments will be briefly described below. Obviously, the drawings in the following description are only some of the present application. For the embodiments, other drawings may be obtained from those skilled in the art without any inventive labor.

Figure 1 is a schematic diagram of the forward and reverse indexes;

2a is a schematic diagram of an application environment provided by an embodiment of the present application;

2b is an exemplary structural diagram of a storage device according to an embodiment of the present application;

3 is a schematic diagram of a general computer architecture of a controller of a storage device according to an embodiment of the present invention;

4 and 6-9 are exemplary flowcharts of a storage management method provided by an embodiment of the present application;

FIG. 5 is a schematic diagram of index data provided by an embodiment of the present application;

FIG. 10 is a schematic diagram of another exemplary structure of a storage device according to an embodiment of the present invention.

Detailed ways

The embodiment of the present application is to protect a storage management method and a storage device. The storage device may be a disk array or the like.

Please refer to a composition diagram of the storage device depicted in FIG. 2a, which includes a controller 201 and a disk enclosure 202.

Controller 201 can be a computing device such as a server, desktop computer, or the like. An operating system and other applications are installed on the controller 201. The controller 201 can receive an input/output (I/O) request from the application host, store the data carried in the I/O request, and write the data into the disk enclosure 202. In an application scenario, the controller 201 can be connected to an application host (not shown) through a SAN network. A schematic diagram of the structure of the controller 201 can be seen in FIG.

The disk enclosure 202 can include one or more hard disks. Referring to FIG. 2b, at least one of the hard disks is a Solid State Device (SSD). Of course, the SSD can also be installed in the slot of the controller 201.

3 is a diagram showing an example of the structure of the controller 201. As shown in FIG. 3, the controller 201 may include a processor 1, a memory 2, and a communication interface 3 connected through a bus (which may further include a front-end interface card and a back-end interface). Card), as well as input device 4 and output device 5.

The front end interface card can be used to communicate with the application host, and the processor 1 of the controller 201 can receive various operation instructions of the application host through the front end interface card.

The processor 1 of the controller 201 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. In the embodiment of the present invention, the processor 1 of the controller 201 can be configured to receive a write data request or a read data request from the application host, process the write data request or read the data request, request the read data or read the data. The request is sent to the SSD 21 and other operations.

The memory 2 is used to store the program. In addition, the memory 2 in this embodiment may also integrate a buffer function, for example, for buffering data received from the application host or data read from the solid state hard disk 21. Exemplarily, when receiving the multiple write data requests sent by the application host, the controller 201 may temporarily save the multiple write data requests in the memory 2, and when the capacity of the memory 2 reaches the water level line, send it to the solid state. The hard disk 21 is persistently stored.

Memory 2 may contain high speed RAM memory and may also include non-volatile memory, such as at least one disk memory. It can be understood that the memory 2 can be a random access memory. (Random-Access Memory, RAM), disk, hard disk, optical disk, solid state disk (SSD) or non-volatile memory, etc. can be stored in non-transitory machines. Read the media. It should be noted that, in the embodiment, the memory 2 and the cache may also be separately set.

The backend interface card can be used to communicate with the SSD 21, and the processor 1 of the controller 201 can send data to the SSD 21 for storage via the backend interface card.

The solid state hard disk 21 may further include an SSD controller and a storage medium. The SSD controller is configured to perform operations such as a write data request or a read data request sent by the processor 1.

It should be noted that the controller 201 belongs to the system controller and is different from the controller of the SSD itself.

More specifically, the SSD controller includes a Flash Translation Layer (FTL), and the correspondence between the logical address and the physical address of the data stored in the FTL. Therefore, the FTL is used to convert the logical address carried in the write data request or the read data request into a physical address in which the data is stored in the SSD, and the physical address in which the data is stored in the SSD may be the actual address in which the data is stored in the SSD, or may be The actual address is virtualized based on the address visible only to the SSD controller (the system controller is not visible).

The storage medium in a solid state drive usually consists of several flash memory chips. Each flash chip includes a number of blocks. In general, the standard capacity of a block may be 2 to the power of N (M), where N is a positive integer.

Normally, the blocks in the SSD are invisible to the system controller. The SSD storage space presents a number of consecutive logical spaces to the system controller. In this embodiment, for the convenience of description, a continuous logical space is referred to as a segment, and each segment corresponds to a logical space. The address is called a logical address. Inside the SSD, each segment corresponds to one or more blocks. It should be noted that the SSD controller does not sense the existence of the segment. Segment is a piece of logical space perceived by the system controller, corresponding to a logical address (also known as a logical address interval). For example, the logical address range corresponding to one segment is 0MB-1023MB; the logical address interval corresponding to another segment is 1024MB-2047MB; the logical address interval corresponding to one segment is 2048MB-3071MB, and so on.

The storage management of the embodiment of the present invention will be further described in detail below based on the common aspects of the present invention as described above.

FIG. 4 shows an interactive exemplary process of the storage management method provided by the embodiment of the present invention, which solves the problem that an invalid forward index may be searched during the process of reading data, and the wrong data is read. .

The method shown in FIG. 4 is applied in the application scenario shown in FIG. 2a, and the processor 1 of the controller 201 in the storage device shown in FIG. 3 interacts with other components.

The interaction process includes:

In Section 401: Processor 1 of controller 201 receives a read data instruction (from the application system).

The above read data instruction includes a logical address of the target data.

More specifically, the processor 1 can receive the above read data command through the front end interface card of the communication interface 3.

In one example, the logical address is an LBA (Logical Block Address). Unless otherwise stated, the LBA will be described as an example.

In section 402, the processor 1 of the controller 201 searches in the index data (maintained by the memory 2) according to the above logical address to acquire the target data area corresponding to the logical address and the initial life cycle number of the target data area.

The index data corresponding to each logical address LBA is maintained in the memory 2 of the controller 201. See Figure 5, any index The data includes a correspondence between a logical address and an initial life cycle number of the data area, and a correspondence between the logical address and the physical address.

The index data is created after the data is written to the SSD. Assume that the data corresponding to LBA a is written in block x of segment r, and the initial lifetime number of segment r is h, then the index data corresponding to LBA a can be a--->(r,x,h) Or a--->(h,r,x).

If the read data command includes LBA a, the segment r corresponding to LBA a is the target data region, and the index data a--->(r,x,h) or a--->(h,r,x) The h recorded in is the initial life cycle number of the target data area.

This article will describe how to build index data later.

In section 403: the processor 1 of the controller 201 acquires the current life cycle number of the target data area;

In addition to the index data, the correspondence between the data area and the current life cycle number is maintained in the memory 2 of the controller 201.

During the initial initialization of the SSD, the storage device can divide the storage space of the SSD into a plurality of data areas (the size is approximately several tens of MB), and number the data areas according to the storage address of the SSD from low to high, and Maintain the correspondence between each data area and the life cycle number. Since the data area is large (relative to the block), the amount of memory consumed by maintaining the correspondence between the data area and the life cycle number is small.

In one example, assuming a total of 100 data regions, the correspondence between the data region and the current lifecycle number can be as shown in Table 1 below:

数据区域标识Data area identifier	生命周期号 Life cycle number
11	1010
22	2020
……......
100100	33

Table 1

In one example, processor 1 of controller 201 can look up Table 1 above to obtain the current lifecycle number of the target data region.

The lifecycle number of the data area will change. For example, after releasing a data area, the lifecycle number of the data area will change. This article will introduce it later.

In section 404: when it is determined that the life cycle number of the acquired target data area does not coincide with the initial life cycle number, the processor 1 of the controller 201 does not execute the above read data instruction.

For example, if the initial lifetime number is h and the current lifecycle number of the obtained target data area is h+m, if the two are inconsistent, the read data instruction will not be executed.

In addition, if the current life cycle number of the acquired target data area does not match the initial life cycle number, it can be confirmed that the index data is invalid, and the data cannot be read from the SSD. At this point, data can be read from other storage media. How to read data from other storage media can be referred to the existing method, and will not be described here.

Of course, if the life cycle number of the acquired target data area is consistent with the initial life cycle number, the above read data instruction is executed.

It can be seen that, in the reading process of this embodiment, if the initial life cycle number of the target data area of the index data record is different from the current life cycle number of the target data area, the read data instruction is not executed. That is, in the reading process of the present invention, the life cycle number is used to identify whether the index data is invalid. If it is invalid, the read data command is not executed, thereby avoiding reading the erroneous data.

In addition, in other embodiments of the present invention, referring to FIG. 4, the foregoing interaction process may further include:

In section 405, the processor 1 of the controller 201 deletes the index data corresponding to the logical address in the read data command.

This can prevent subsequent processor 1 from reading invalid index data and improve reading efficiency.

FIG. 6 is another interactive exemplary process of a storage management method according to an embodiment of the present invention. The focus of this embodiment is to introduce the writing process of the above target data.

The method shown in FIG. 6 can be applied in the application scenario shown in FIG. 2a, and is mainly performed by the processor 1 of the controller 201 in the storage device shown in FIG. 3 interacting with other components.

The interaction process includes:

In section 601: Processor 1 of controller 201 receives a write data instruction (from the application system).

The write data instruction includes the above target data and a logical address.

More specifically, the processor 1 can receive the above write data command through the front end interface card of the communication interface 3.

In Section 602: the solid state hard disk 21 sequentially allocates a block (generally several KB to several tens of KB) to the target data from the free data area, and writes the target data into the allocated block.

More specifically, the processor 1 of the controller 201 can transmit data to the SSD 21 for storage via the backend interface card. The SSD controller in the solid state hard disk 21 sequentially allocates a block (generally several KB to several tens of KB) to the target data from the free data area, and writes the target data into the allocated block.

In section 603: the processor 1 of the controller 201 determines a target data area corresponding to the target data and an initial life cycle number of the target data area.

After the target data is written, the current life cycle number of the target data area can be used as the initial life cycle number.

For example, suppose that at the time T0, the target data is written into the block x of the segment r, and the target data region is segment r, and the life cycle number h of the segment r (time T0) can be obtained by querying the above table 1. Initial life cycle number.

In another example, an initial lifecycle number can be assigned to the target data area after the target data is written and stored in Table 1 above.

In another example, each data region is assigned a raw lifecycle number (typically 0) at the factory, or when the SSD is first initialized. In the process of using SSD, the accumulation or subtraction is performed on the basis of the original life cycle number (described later in this article), and the accumulated or subtracted results are stored in Table 1 above.

In section 604, the processor 1 of the controller 201 saves the correspondence between the above logical address and the initial life cycle number of the target data area to the above index data.

In Section 604, assuming that the target data corresponding to LBA a is written in block x of segment r, and the current life cycle number of segment r is h, the index data created is a--->(r,x, h) or a--->(h,r,x).

Different from the existing storage management method, the existing storage management method establishes a forward index and a reverse index. In this embodiment, after the storage device writes the target data, the initial life cycle number including the target data region is established. Index data, the index data in this embodiment is similar to the existing forward index, but in addition, the correspondence between the logical address and the initial life cycle number is increased. At the same time, in this embodiment, the reverse index is no longer maintained, and the memory consumption is reduced and the management complexity is reduced.

It should be noted that in some existing storage management modes, when the segment on the SSD needs to be released, an inverted index is required: assuming that segment r needs to be released, it is necessary to find each block corresponding to segment r according to the reverse index. The LBA, according to the searched LBA, invalidates (deletes) the forward index corresponding to segment r, and finally marks segment r as idle.

However, maintaining the reverse index from each block on the segment to the LBA requires a lot of memory, and the space management complexity is also high.

The embodiment of the invention illustrated in Figure 7 provides an interactive exemplary process involving the release of data regions.

The method shown in FIG. 7 is applied in the application scenario shown in FIG. 2a, and the processor 1 of the controller 201 in the storage device shown in FIG. 3 interacts with other components.

The interaction process includes:

At 700: processor 1 of controller 201 receives an instruction to release the target data region;

The instruction to release the target data area is internally triggered by the storage device. In practice, the storage device will detect that the data area has run out, and will choose to release some used segments, and then accept new data writes.

In Section 701: Processor 1 of controller 201 modifies the initial lifecycle number.

In one example, the initial lifecycle number can be increased by m to get a new lifecycle number. m can be a positive integer or a negative integer. More specifically, m can take +1.

Following the example of Table 1 above, assuming that the data area 1 is released, the initial life cycle number 10 of the data area 1 is incremented by 10, and (10+m) is stored in Table 1.

As mentioned above, each data area is assigned a raw lifecycle number (typically 0) at the factory or when the SSD is first initialized. In the process of using SSD, monotonous increment or monotonous decrement is performed based on the original life cycle number. In another example, the data area may be monotonically incremented by m each time the data area is released on the basis of the original life cycle number.

The 700 portion is executed after the correspondence between saving the logical address and the initial life cycle number of the target data region to the index data (that is, after the 604 portion), before receiving the read data instruction (that is, before the 601 portion) .

Compared with the existing release mode, the release mode provided by the embodiment of the present invention only needs to modify the initial life cycle number, avoids complicated operations, and improves processing efficiency.

In addition to reading/writing data and releasing data areas, the storage device may perform operations such as deleting target data, rewriting target data, and the like.

Based on the index data provided by embodiments of the present invention, FIG. 8 illustrates an interactive exemplary process involving deletion of target data.

The method shown in FIG. 8 is applied in the application scenario shown in FIG. 2a, and the processor 1 of the controller 201 in the storage device shown in FIG. 3 interacts with other components.

The interaction process includes:

In section 801: Processor 1 of controller 201 receives a delete data instruction (from the application system).

The delete data instruction includes a logical address of the above target data.

More specifically, the processor 1 can receive the above-described delete data command through the front end interface card of the communication interface 3.

At section 802: the processor 1 of the controller 201 sets the index data corresponding to the above logical address to be invalid.

In one example, the index data corresponding to the above logical address may be deleted.

It should be noted that, in the existing storage mode, when the target data corresponding to LBA a needs to be deleted, it is assumed that the forward index corresponding to LBA a is a--->> (r, x), and the reverse index is (r) , x)--->a, you need to find (r,x) from the forward index, then invalidate the reverse index (r,x)--->a, and finally invalidate the forward index a--- >(r,x).

In contrast, in this embodiment, the index data corresponding to the logical address is directly set to be invalid, so that the operation steps can be greatly reduced.

Assuming that the data of LBA a needs to be written to the SSD again because it is updated, based on the index data provided by the embodiment of the present invention, FIG. 9 shows an interactive exemplary flow involving repeated writing of the target data.

The method shown in FIG. 9 is applied in the application scenario shown in FIG. 2a, and the processor 1 of the controller 201 in the storage device shown in FIG. 3 interacts with other components.

The interaction process includes:

In Section 901: Processor 1 of controller 201 receives a write data instruction (from the application system).

Section 901 is the same as Section 601 and will not be described here.

In Section 902: the SSD controller in the SSD 21 sequentially allocates a block (generally several KB to several tens of KB) for the target data from the free data area, and writes the target data into the allocated block.

Assume that the target data corresponding to the previous LBA a is written to the block x on the segment r. In the process of repeated writing, the target data is allocated block y on the segment s, and the target data corresponding to the LBA a is written to Block y on segment s.

It should be noted that in order to improve the performance and life of the SSD, the writing is performed sequentially. Therefore, if you need to write the target data repeatedly, you need to re-allocate the storage space.

In section 903, the processor 1 of the memory controller 201 determines a new target data area corresponding to the target data and an initial life cycle number of the new target data area.

Following the previous example, it is assumed that the target data corresponding to LBA a is written to block y on segment s, then segment s is the new target data area, and lookup table 1 can obtain the life cycle number corresponding to segment s as the initial life cycle number. Assume that the initial life cycle number of segment s is i.

In section 904: the processor 1 of the controller 201 saves the correspondence between the above logical address and the initial life cycle number of the new target data area to the above index data.

If the previous example is still used, the index data corresponding to LBA a is updated from a--->(r,x,h) or a--->(h,r,x) to a--->(i,s , y) or a---> (s, y, i).

It should be noted that, in the existing storage mode, when the write is required to be repeated, after the target data is written into the allocated block, it is necessary to find (r, x) from the old forward index a, and then invalidate. Reverse the index (r, x) ---> a. Finally, update the forward index to a--->(s,y) and create a new reverse index (s,y)--->a.

In contrast, the repeated write mode provided in this embodiment directly updates the index data corresponding to the logical address, thereby greatly reducing the operation steps.

In summary, the core idea of the present invention is to assign a life cycle number to an object (such as a storage disk, a data area) to mark its lifetime, and in some cases, to end its lifetime or to start a new life, to give it a new Life cycle number. All objects using the object need to record the initial life cycle number of the object. Before using the object, it is necessary to compare whether the initial life cycle number is consistent with the current life cycle number. If they are inconsistent, the object is invalid and cannot be used anymore.

In addition to the technical solutions provided by all of the above embodiments, the idea of the present invention can also be applied to, for example, storage management of a storage disk. If the storage disk is released or damaged, add m to the initial lifecycle number of the storage disk to get a new lifecycle number. When the storage disk is accessed, the initial life cycle number is the same as the current life cycle number. If the value is inconsistent, the storage disk is invalid and cannot be accessed.

The foregoing provides an introduction to the solution provided by the embodiments of the present invention from the perspective of interaction between the various devices. It can be understood that various devices, such as storage devices, storage devices, etc., in order to implement the above functions, include hardware structures and/or software modules corresponding to the respective functions. Those skilled in the art will readily appreciate that the present invention can be implemented in a combination of hardware or hardware and computer software in combination with the elements and algorithm steps of the various examples described in the embodiments disclosed herein. Whether a function is implemented in hardware or computer software to drive hardware depends on the specific application and design constraints of the solution. A person skilled in the art can use different methods for implementing the described functions for each particular application, but such implementation should not be considered to be beyond the scope of the present invention.

FIG. 10 is a schematic diagram of a possible structure of a storage device involved in the foregoing embodiment, including:

The receiving module 101 is configured to receive a read data instruction (including a logical address of the target data);

The searching module 102 is configured to search the index data according to the foregoing logical address to obtain the target data area corresponding to the logical address and the initial life cycle number of the target data area.

The index data includes a correspondence between the logical address and an initial lifecycle number of the target data area.

The obtaining module 103 is configured to obtain a life cycle number of the target data area.

The reading module 104 is configured to not execute the read data command when determining that the life cycle number does not match the initial life cycle number.

For details, please refer to the foregoing description in this document, and no further details are given here.

In other embodiments of the present invention, still referring to FIG. 10, the foregoing storage device may further include a writing module 105, configured to:

Receiving a write data command (receivable by the receiving module 101), wherein the write data command includes the target data and a logical address of the target data; wherein the write data command is received before the receiving module 101 receives the read data command;

Determining a target data area corresponding to the target data and an initial life cycle number of the target data area (the target data area and the initial life cycle number may be determined by the obtaining module 103);

And storing a correspondence between the logical address and the initial life cycle number of the target data area to the index data.

Further, the writing module 105 can also perform the aforementioned operation of repeatedly writing the target data.

In other embodiments of the present invention, still referring to FIG. 10, the foregoing storage device may further include a release module 106 for After receiving the instruction to release the target data area, the initial life cycle number is modified to the above life cycle number.

The instruction to release the target data area is received before the receiving module 101 receives the read data command after the write module 105 saves the correspondence between the logical address and the initial life cycle number of the target data area to the index data.

In other embodiments of the present invention, still referring to FIG. 10, the foregoing storage device may further include a deleting module 107, configured to receive a delete data instruction (including a logical address of the target data) from the application system, and corresponding to the logical address. The index data is set to invalid.

The receiving module 101 can be used to support the storage device to communicate with other devices, for example, to support the storage device to communicate with other devices, such as the ones shown in FIG. 4, FIG. 6, FIG. 7, FIG. 8, FIG. instruction.

The lookup module 102 can execute the portion 402 of FIG. 4, the portion 603 shown in FIG. 6 (find the initial life cycle number), the portion 402, the portion 603 shown in FIG. 7, or the portion 903 shown in FIG. (Find the initial lifecycle number).

The acquisition module 103 can perform the 403 portion shown in FIG. 4 or 7.

The reading module 104 can perform the 404 portion and the 405 portion shown in FIG. 4 or 7.

The write module 105 can directly execute portions 601-604 shown in Figures 6 or 7, or can perform portions 601-604 shown in Figures 6 or 7 by interacting with other modules. Furthermore, the write module can perform the 901-904 portion shown in Figure 9 directly or by interacting with other modules.

The release module 106 can perform the 700-701 portion shown in Figure 7 directly or by interacting with other modules.

The deletion module 107 can perform the portions 801-802 shown in Figure 7 directly or by interacting with other modules.

The steps of a method or algorithm described in connection with the present disclosure may be implemented in a hardware, or may be implemented by a processor executing software instructions. The software instructions may be comprised of corresponding software modules that may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable hard disk, CD-ROM, or any other form of storage well known in the art. In the medium. An exemplary storage medium is coupled to the processor to enable the processor to read information from, and write information to, the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC. Additionally, the ASIC can be located in the user equipment. Of course, the processor and the storage medium may also reside as discrete components in the user equipment.

Those skilled in the art will appreciate that in one or more examples described above, the functions described herein can be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the functions may be stored in a computer readable medium or transmitted as one or more instructions or code on a computer readable medium. Computer readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one location to another. A storage medium may be any available media that can be accessed by a general purpose or special purpose computer.

The specific embodiments of the present invention have been described in detail with reference to the preferred embodiments of the present invention. The scope of the protection, any modifications, equivalent substitutions, improvements, etc., which are made on the basis of the technical solutions of the present invention, are included in the scope of the present invention.

Claims

A storage management method, characterized in that the method is applied to a storage device, the storage device comprising a processor and a solid state hard disk, the solid state hard disk comprising a plurality of data regions, each data region comprising one or more blocks Block, the method being performed by the processor, comprising the steps of:

Receiving a read data instruction, the read data instruction including a logical address of the target data;

Searching, in the index data, according to the logical address, to obtain a target data area corresponding to the logical address and an initial life cycle number of the target data area, where the index data includes the logical address and the target data area The correspondence between the initial life cycle numbers;

Obtaining a life cycle number of the target data area;

The read data instruction is not executed when it is determined that the life cycle number does not coincide with the initial life cycle number.
The method of claim 1 further comprising:

When it is determined that the lifecycle number is inconsistent with the initial lifecycle number, the index data corresponding to the logical address is deleted.
The method according to claim 1 or 2, further comprising: before said receiving the read data instruction:

Receiving a write data instruction, the write data instruction including the target data and a logical address of the target data;

Determining a target data area corresponding to the target data and an initial life cycle number of the target data area;

Saving a correspondence between the logical address and an initial lifetime number of the target data region to the index data.
The method according to claim 3, wherein after receiving the correspondence between the logical address and an initial lifetime number of the target data region to the index data, the receiving a read data instruction Previously included:

Receiving an instruction to release the target data area;

Modify the initial lifecycle number to the lifecycle number.
The method of claim 4, wherein the modifying the initial lifecycle number to the lifecycle number comprises:

The initial life cycle number is increased by m to obtain the life cycle number; the m is a positive integer or a negative integer.
The method of claim 1 further comprising:

Receiving a delete data instruction, the delete data instruction including a logical address of the target data;

The index data corresponding to the logical address is set to be invalid.
The method of claim 1 further comprising:

The target data stored in the target data region is read when it is determined that the lifecycle number is the same as the initial lifecycle number.
A storage device, comprising: a solid state drive comprising a plurality of data regions, each data region comprising one or more blocks;

The storage device further includes:

a receiving module, configured to receive a read data instruction, where the read data instruction includes a logical address of the target data;

a searching module, configured to search in the index data according to the logical address, to obtain a destination corresponding to the logical address And an initial life cycle number of the target data area, where the index data includes a correspondence between the logical address and an initial life cycle number of the target data area;

An obtaining module, configured to acquire a lifecycle number of the target data area;

And a reading module, configured to not execute the read data instruction when determining that the lifecycle number is inconsistent with the initial lifecycle number.
The device of claim 8, wherein the reading module is further configured to: delete the index data corresponding to the logical address when determining that the lifecycle number is inconsistent with the initial lifecycle number.
The device according to claim 8 or 9, further comprising a writing module for:

Receiving a write data instruction, the write data instruction including the target data and a logical address of the target data; determining a target data area corresponding to the target data and an initial life cycle number of the target data area; and, a saver Corresponding relationship between the logical address and the initial lifecycle number of the target data region to the index data; wherein the write data instruction is received before the receiving module receives the read data instruction.
The device of claim 10, further comprising:

a release module, configured to modify the initial lifecycle number to the lifecycle number after receiving an instruction to release the target data area; wherein the instruction to release the target data area is in the writing After the module saves the correspondence between the logical address and the initial lifecycle number of the target data area to the index data, the receiving module receives the read data instruction before receiving the data.
The device according to claim 10, wherein in the aspect of modifying the initial life cycle number to the life cycle number, the release module is configured to:

The initial life cycle number is increased by m to obtain the life cycle number; the m is a positive integer or a negative integer.