CN102637145B - Method for block management, memory device and controller thereof - Google Patents

Abstract

The invention provides a method for managing blocks, which is applied to a controller of a flash memory, wherein the flash memory comprises a plurality of blocks, and the method comprises the following steps: selecting a target block with the lowest erasing frequency from at least one part of blocks in a data area of the flash memory as a block to be erased, wherein the sequence numbers of the at least one part of blocks respectively correspond to the latest updating sequence of the at least one part of blocks; and determining whether valid data in the target block should be moved/copied to a high-loss block or a low-loss block according to the sequence number of the target block, wherein the loss degree of the high-loss block is greater than that of the low-loss block. The block management realized according to the invention can distinguish hot data from cold data, and utilize the blocks with higher wear level to store cold data and utilize the blocks with lower wear level to store hot data, thereby ensuring that the best processing efficiency is achieved when wear leveling operation is performed in the flash memory.

Description

Method for block management, memory device and controller thereof

technical field

The present invention relates to the access (Access) of flash memory (Flash Memory), and more specifically, relates to a method for block management, a related memory device and its controller.

Background technique

In recent years, due to the continuous development of flash memory technology, various portable memory devices (such as memory cards conforming to SD/MMC, CF, MS, XD standards) or solid state drives (Solid State Drive, SSD) with flash memory are widely used. implemented in many applications. Therefore, the access control of the flash memory in these memory devices has become a very hot topic.

As far as the commonly used NAND flash memory is concerned, it can be mainly divided into two types of flash memory: single-level cell (Single Level Cell, SLC) and multi-level cell (Multiple Level Cell, MLC). Each transistor in the single-level cell flash memory, which is regarded as a memory unit, has only two charge values, which are used to represent logic value 0 and logic value 1 respectively. In addition, the storage capacity of each transistor used as a memory unit in the multi-level cell flash memory is fully utilized, and it is driven by a higher voltage to record two groups (or more than one) in one transistor through different levels of voltage. ) bit information (00, 01, 11, 10); theoretically, the recording density of multi-level cell flash memory can reach twice the recording density of single-level cell flash memory, which is for NAND flash memory that has encountered bottlenecks in the development process It is very good news for related industries.

Compared with single-level cell flash memory, because multi-level cell flash memory is cheaper and can provide a larger capacity in a limited space, multi-level cell flash memory has quickly become a popular choice for portable memory devices on the market. mainstream. However, problems caused by the instability of multi-level cell flash memory have also emerged one by one. In order to ensure that the access control of the memory device to the flash memory complies with relevant specifications, the controller of the flash memory usually has some management mechanisms to properly manage data access.

According to related technologies, memory devices with these management mechanisms still have deficiencies. For example, the management mechanism of the related technology cannot guarantee the best processing performance when performing wear leveling (Wear Leveling) operation in the flash memory. Therefore, a novel method for block management is needed to adaptively select a block for saving valid data (Valid Data) during the erasing operation.

Contents of the invention

The technical problem to be solved by the present invention is to provide a block management method and related methods for the defect that the management mechanism of the prior art cannot guarantee the best processing performance when performing loss leveling operations in the flash memory. memory device and its controller to solve the above problems.

Another object of the present invention is to provide a method for block management, a related memory device and its controller, so as to achieve the best processing performance when performing wear leveling.

Another object of the present invention is to provide a method for block management, a related memory device and its controller, so that when performing an erase operation on a target block, it can be adaptively selected for preservation/storage A block of valid data (Valid Data) in the target block.

One of the technical solutions adopted by the present invention to solve the technical problems is: provide a method for block management, the method is applied to a controller of flash memory (Flash Memory), the flash memory includes a plurality of blocks, the method Including: selecting a target block with the lowest erase count (Erase Count) among at least a part of the blocks in a data area (Data Region) of the flash memory, as a block to be erased, wherein the at least a part of the blocks The sequence numbers of the blocks correspond to the sequence of the latest update of the at least a part of the blocks; and according to the sequence numbers of the target block, the valid data in the target block should be moved/copied to a high loss block (Heavily Worn Block) or A lightly worn block (Lightly Worn Block), wherein the degree of wear of the high loss block is greater than that of the lightly worn block.

In the above-mentioned method of the present invention, the step of determining that the valid data in the target block should be moved/copied to the high-loss block or the low-loss block according to the sequence number of the target block further includes:

calculating the difference between the sequence number of the target block and the sequence number of a latest accessed block; and

It is determined according to the difference that the valid data in the target block should be moved/copied to the high-loss block or the low-loss block.

In the above-mentioned method of the present invention, the step of determining that the valid data in the target block should be moved/copied to the high-loss block or the low-loss block according to the sequence number of the target block further includes:

The difference is compared with a threshold to determine whether to move/copy the valid data to the high loss block.

In the above-mentioned method of the present invention, the step of determining that the valid data in the target block should be moved/copied to the high-loss block or the low-loss block according to the sequence number of the target block further includes:

When the difference reaches the threshold, the valid data is moved/copied to the high loss block.

In the above-mentioned method of the present invention, the step of determining that the valid data in the target block should be moved/copied to the high-loss block or the low-loss block according to the sequence number of the target block further includes:

The difference is compared with a threshold to determine whether to move/copy the valid data to the low-loss block.

In the above-mentioned method of the present invention, the step of determining that the valid data in the target block should be moved/copied to the high-loss block or the low-loss block according to the sequence number of the target block further includes:

When the difference is lower than the threshold, the valid data is moved/copied to the low-loss block.

In the above-mentioned method of the present invention, the step of determining that the valid data in the target block should be moved/copied to the high-loss block or the low-loss block according to the sequence number of the target block further includes:

The difference is compared with the threshold to determine whether to move/copy the valid data to the high loss block.

The above-mentioned method of the present invention further includes:

A block whose erasing times reach a threshold value is selected from at least a part of blocks in a spare area of the flash memory as the high loss block.

The above-mentioned method of the present invention further includes:

Selecting a block whose erasing frequency is lower than a threshold value among at least a part of blocks in a spare area of the flash memory as the low-loss block, wherein the low-loss block is not the least erased block in the spare area number of blocks.

The above-mentioned method of the present invention further includes:

After moving/copying the valid data, the target block is erased.

In the above-mentioned method of the present invention, the step of determining that the valid data in the target block should be moved/copied to the high-loss block or the low-loss block according to the sequence number of the target block further includes:

Determining that valid data in the target block should be moved/copied to the high-loss block or the low-loss block according to the sequence number of the target block and at least one threshold value; and

The at least one threshold value is dynamically adjusted to change the probability of moving/copying valid data in the target block to the high-loss block or the low-loss block.

The second technical solution adopted by the present invention to solve the technical problem is: while providing the above method, a memory device is also correspondingly provided, which includes: a flash memory, the flash memory includes a plurality of blocks; and a controller, Used to access (Access) the flash memory and manage the multiple blocks. In addition, the controller selects a target block with the lowest erasing times among at least a part of blocks in a data area of the flash memory as a block to be erased, wherein the sequence numbers of the at least a part of blocks correspond to the The order of the most recent update of at least a portion of the blocks. In addition, the controller determines according to the sequence number of the target block that the valid data in the target block should be moved/copied to a high-loss block or a low-loss block, wherein the loss degree of the high-loss block is greater than the The degree of wear for low-loss blocks.

In the above memory device of the present invention, wherein the controller calculates the difference between the sequence number of the target block and the sequence number of a latest access block, and decides that the valid data in the target block should be determined according to the difference Data is moved/copied to the high loss block or the low loss block.

In the above-mentioned memory device of the present invention, the controller compares the difference with a threshold value to determine whether to move/copy the valid data to the high loss block.

In the above-mentioned memory device of the present invention, when the difference reaches the threshold value, the controller moves/copyes the valid data to the high loss block.

In the above-mentioned memory device of the present invention, the controller compares the difference with a threshold value to determine whether to move/copy the valid data to the low-loss block.

In the above-mentioned memory device of the present invention, when the difference is lower than the threshold value, the controller moves/copyes the valid data to the low-loss block.

In the above-mentioned memory device of the present invention, the controller compares the difference with the threshold value to determine whether to move/copy the valid data to the high loss block.

In the above-mentioned memory device of the present invention, the controller selects a block whose erasing times reach a threshold value from at least a part of blocks in a spare area of the flash memory as the high loss block.

In the above-mentioned memory device of the present invention, wherein the controller selects a block whose erasing frequency is lower than a threshold value among at least a part of blocks in a spare area of the flash memory as the low-loss block, and the The low loss block is not the block with the lowest erasure count in the spare area.

In the above memory device of the present invention, after moving/copying the valid data, the controller erases the target block.

The third technical solution adopted by the present invention to solve the technical problem is: while providing the above method, a corresponding memory device controller is also provided, the controller is used to access a flash memory, the flash memory includes a plurality of blocks, The controller includes: a read only memory (Read Only Memory, ROM), which is used to store a program code; and a microprocessor, which is used to execute the program code to control the access to the flash memory and manage the multiple blocks. In addition, the controller that executes the program code through the microprocessor selects a target block with the lowest erasing times among at least a part of blocks in a data area of the flash memory as a block to be erased, wherein The sequence numbers of the at least a part of the blocks respectively correspond to the latest updated sequence of the at least a part of the blocks. In addition, the controller executing the program code through the microprocessor decides to move/copy the valid data in the target block to a high loss block or a low loss block according to the sequence number of the target block, Wherein the loss degree of the high loss block is greater than the loss degree of the low loss block.

In the above-mentioned controller of the present invention, wherein the controller executing the program code through the microprocessor calculates the difference between the sequence number of the target block and the sequence number of a latest access block, and based on the difference The value determines whether the valid data in the target block should be moved/copied to the high loss block or the low loss block.

In the above-mentioned controller of the present invention, the controller executing the program code through the microprocessor compares the difference with a threshold value to determine whether to move/copy the valid data to the high-loss block.

In the above-mentioned controller of the present invention, when the difference reaches the threshold value, the controller executing the program code through the microprocessor moves/copyes the valid data to the high-loss block.

In the above-mentioned controller of the present invention, the controller executing the program code through the microprocessor compares the difference with a threshold value to determine whether to move/copy the valid data to the low-loss block.

In the above-mentioned controller of the present invention, when the difference is lower than the threshold value, the controller executing the program code through the microprocessor moves/copyes the valid data to the low-loss block.

In the above-mentioned controller of the present invention, the controller executing the program code through the microprocessor compares the difference with the threshold value to determine whether to move/copy the valid data to the high-loss block.

In the above-mentioned controller of the present invention, wherein the controller that executes the program code through the microprocessor selects a block whose number of times of erasing reaches a threshold value among at least a part of blocks in a spare area of the flash memory , as the high loss block.

In the above-mentioned controller of the present invention, wherein the controller that executes the program code through the microprocessor selects an area whose erasing frequency is lower than a threshold value among at least a part of blocks in a spare area of the flash memory block, as the low-loss block, and the low-loss block is not the block with the lowest erasure times in the spare area.

In the above-mentioned controller of the present invention, after moving/copying the valid data, the controller executing the program code through the microprocessor erases the target block.

Implementing the technical solution of the present invention has the following beneficial effects: the block management realized according to the present invention can distinguish between hot data and cold data, and use blocks with a higher degree of loss to store cold data and blocks with a lower degree of loss Store hot data. This ensures optimal processing performance when performing wear-leveling operations in flash memory.

Compared with related technologies, the present invention can achieve the goal of both operating performance and system resource usage control without greatly increasing the chip area and related costs.

Description of drawings

The present invention will be further described below in conjunction with accompanying drawing and embodiment, in the accompanying drawing:

1 is a schematic diagram of a memory device according to a first embodiment of the present invention;

FIG. 2A is a flowchart of a method for block management according to an embodiment of the present invention;

FIG. 2B and FIG. 2C respectively illustrate the implementation details of the method shown in FIG. 2A in different embodiments;

FIG. 3 shows blocks in the data area involved in the method shown in FIG. 2A in an embodiment;

FIG. 4A and FIG. 4B respectively illustrate implementation details of the method shown in FIG. 2A in different embodiments.

[Description of main component symbols]

Detailed ways

Please refer to FIG. 1. FIG. 1 is a schematic diagram of a memory device 100 according to a first embodiment of the present invention, wherein the memory device 100 of this embodiment is especially a portable memory device (for example: conforming to SD/MMC, CF, MS, XD standard memory card) or solid state drive (SSD, Solid State Drive), etc. The memory device 100 includes: a flash memory (Flash Memory) 120, which includes a plurality of blocks, and the plurality of blocks includes at least one information block (Block) 120B; and a controller, used for access (Access) The flash memory 120, wherein the controller is, for example, a memory controller 110. According to this embodiment, the memory controller 110 includes a microprocessor 112 , a read only memory (ROM) 112M, a control logic 114 , at least one buffer memory 116 , and an interface logic 118 . In addition, the ROM 112M of this embodiment is used to store a program code 112C, and the microprocessor 112 is used to execute the program code 112C to control access to the flash memory 120 . Please note that the program code 112C also has to be stored in the buffer memory 116 or any form of memory.

As shown in FIG. 1 , the above-mentioned at least one information block 120B is used to store information about block management, especially at least one index such as the latest accessed block index 120L. The latest access block index 120L can be used to record the latest access block in the flash memory 120 . For example: when the above-mentioned controller (for example: the memory controller 110 executing the program code 112C through the microprocessor 112) writes data into a certain block, the controller can record/update the latest access block index 120L , to indicate that the block is the most recently accessed block. Another example: when updating a certain block, the controller may record/update the latest access block index 120L to indicate that the block is the latest access block. In this embodiment, the controller may store a previous version of the latest access block index 120L in the flash memory 120, and store a copy version of the latest access block index 120L in the buffer memory 116 for dynamic The latest access block index 120L is updated. In addition, the controller can store the latest version of the latest access block index 120L in the buffer memory 116 to the flash memory 120 to replace the previous version of the latest access block index 120L. Please note that any information stored in the information block 120B can be stored in the memory controller 110 (such as the buffer memory 116 ), or in any memory accessible by the memory controller 110 . Storing the latest access block index 120L in the flash memory 120 is only an embodiment of the present invention, and is not a limitation of the present invention.

In practice, the memory controller 110 that executes the program code 112C through the microprocessor 112 can use its own internal components to perform many control operations, for example: use the control logic 114 to control the access operation of the flash memory 120 (especially for access operations of at least one block or at least one page), use the buffer memory 116 to perform required buffering, and use the interface logic 118 to communicate with a host device (HostDevice).

According to this embodiment, in addition to being able to access the flash memory 120, the controller can properly manage the above-mentioned multiple blocks. More specifically, when performing an erasing operation, the controller can adaptively select a block for storing valid data (Valid Data), so as to achieve the best processing performance of wear leveling (Wear Leveling). Please refer to FIG. 2A , and related details are further described as follows.

FIG. 2A is a flowchart of a block management method 910 according to an embodiment of the present invention. The method can be applied to the memory device 100 shown in FIG. 1 , especially the above-mentioned controller (eg, the memory controller 110 executing the program code 112C through the microprocessor 112 ). The method is described as follows:

In step 912, the controller selects the lowest erasing times (Erase Count) among at least a part of blocks in a data region (Data Region) of the flash memory 120 (for example: a part or all of the blocks in the data region). A target block is used as a block to be erased, wherein the serial numbers of the at least a part of the blocks respectively correspond to the latest updated sequence of the at least a part of the blocks. Please note that for any block in the at least a part of blocks, in addition to its logical address, this block has a sequence number, and this sequence number corresponds to the update sequence of this block, that is, this block is relative to the An update sequence for other blocks in at least a portion of the blocks. According to this embodiment, the flash memory 120 further includes a spare region (SpareRegion). In particular, the blocks belonging to the spare area are blocks that have not been used since the latest erasure, and the blocks belonging to the data area are blocks that have been used since the latest erasure, wherein the spare area and the The data area is a logical area division for each block in the flash memory 120 , rather than a physical area division.

In step 914, the controller decides according to the sequence number of the target block that the valid data (Valid Data) in the target block should be moved/copied to a high-loss block (Heavily WornBlock) or a low-loss block ( Lightly Worn Block). Note that the high loss block is more worn than the low loss block. In particular, the high-loss block represents a block with a higher wear level among the plurality of blocks, and the low-loss block represents a block with a lower wear level among the plurality of blocks. In practice, the controller can calculate the difference Diff between the sequence number of the target block and the sequence number of a latest accessed block, and decide that the valid data in the target block should be moved/copied according to the difference Diff to the high loss block or the low loss block. For example: the controller compares the difference Diff with a threshold to decide whether to move/copy the valid data to the high-loss block; when the difference Diff reaches the threshold, the controller moves/copy the valid data to the high loss block. Another example: the controller compares the difference Diff with a threshold value to determine whether to move/copy the valid data to the low-loss block; when the difference Diff is lower than the threshold value, the controller moves the valid data /Copy to this low-loss block.

According to an embodiment, such as a variation example of the embodiment shown in FIG. 2A, the controller can judge whether the valid data in the target block is cold data (for example: unpopular data) according to the sequence number of the target block, so as to Correspondingly determine whether to move/copy the valid data to the high-loss block, wherein when the difference Diff between the sequence number of the target block and the sequence number of the latest access block reaches a first threshold value TH1, the Valid data is judged as cold data, and the controller moves/copyes the valid data to the high loss block at this time. Thus, when the valid data is moved/copied to the high loss block, the controller can record/update the latest access block index 120L to indicate that the high loss block is the latest access block.

In addition, the controller can judge whether the valid data in the target block is hot data (for example: hot data) according to the serial number of the target block, so as to determine whether to move/copy the valid data to the low Lost block, wherein when the difference Diff between the sequence number of the target block and the sequence number of the latest access block is lower than a second threshold value TH2, the valid data is judged as hot data, at this time the control The device moves/copies the valid data to the low-loss block. Thus, when the valid data is moved/copied to the low loss block, the controller can record/update the latest access block index 120L to indicate that the low loss block is the latest access block. In addition, the above-mentioned first threshold TH1 and second threshold TH2 can be dynamically adjusted by the controller. Generally speaking, the first threshold TH1 is greater than or equal to the second threshold TH2.

FIG. 2B illustrates implementation details of the method 910 shown in FIG. 2A in an embodiment. The workflow shown in Figure 2B is explained as follows:

In step 932, the controller selects a target block in the data area, such as the above-mentioned target block, as a block to be erased.

In step 933, the controller calculates the difference Diff between the sequence number of the target block and the sequence number of the latest accessed block.

In step 934-1, the controller checks whether the difference Diff reaches the threshold TH1. When the difference Diff reaches the threshold TH1, go to step 936-1; otherwise, go to step 934-2.

In step 934-2, the controller checks whether the difference Diff is lower than the threshold TH2. When the difference Diff is lower than the threshold TH2, go to step 936-2; otherwise, go to step 936-3.

In step 936-1, the controller moves/copy valid data to a high loss block such as the high loss block described above.

In step 936-2, the controller moves/copies the valid data to a low-loss block such as the low-loss block described above.

In step 936-3, the controller moves/copy valid data to a low loss block, especially another low loss block selected according to different conditions, instead of the low loss block described in step 936-2. loss block. In practice, the wear level of the other low loss block can be between the wear level of the low loss block mentioned in step 936-2 and the wear level of the high loss block mentioned in step 936-1.

In step 938, the controller erases the target block.

According to an embodiment, such as a variation of the embodiment shown in FIG. 2B , the controller can divide the above-mentioned spare area into at least three layers, such as a high-loss block layer and an averagely worn block (Averagely Worn Block) layer , and a low-loss block layer. In particular, the high-loss block described in step 936-1 is selected from the high-loss block layer, and the low-loss block described in step 936-2 is selected from the low-loss block layer, wherein step 936- The other low-loss block described in 3 can be regarded as a medium-loss block, and is selected from the medium-loss block layer.

In practice, the controller can classify any one of the blocks in the spare area (which may be referred to as spare blocks) into the high loss block layer, the medium loss area according to the loss blocks of the blocks in the spare area. block layer, and one of the low-loss block layers, wherein the wear degree of the spare blocks in the high-loss block layer is higher than the wear degree of the spare blocks in the medium-loss block layer, and the wear degree of the medium-loss block layer is The wear degree of the spare blocks in the block layer is higher than the wear degree of the spare blocks in the low loss block layer. For example: the controller can classify blocks whose erasure times fall within the interval [13, 20] into the high-loss block layer, and classify blocks whose erasure times fall within the interval [7, 12] Classify to the medium-loss block layer, and classify blocks whose erasure times fall within the interval [1, 6] into the low-loss block layer. This is for the purpose of illustration only, not limitation of the present invention. According to some variations of this embodiment, the number of layers of each layer in the above spare area may be changed, and/or the range of each of the above intervals may be changed. According to one of these variations, in the case where the number of the above-mentioned layers exceeds three layers, the above-mentioned high-loss block layer may be called the most heavily-worn block (Most Heavily Worn Block) layer, and the above-mentioned low The loss block layer can be called the most lightly worn block (Most Lightly Worn Block) layer, in which the intervals corresponding to each layer change accordingly, so that the controller can classify more finely according to the degree of wear of the blocks in the spare area to each layer. For example: based on the order of loss level (starting with the highest), the layers may include: highest loss block layer, second highest loss block layer, third highest loss block layer, ..., medium loss block layer , ..., the third low-loss block layer, the second-lowest loss block layer, and the lowest-loss block layer.

FIG. 2C shows implementation details of the method 910 shown in FIG. 2A in an embodiment, where this embodiment is a variation of the embodiment shown in FIG. 2B . The workflow shown in Figure 2C is explained as follows:

In step 932, the controller selects a target block in the data area, such as the above-mentioned target block, as a block to be erased.

In step 933, the controller calculates the difference Diff between the sequence number of the target block and the sequence number of the latest accessed block.

In step 934-1, the controller checks whether the difference Diff reaches the threshold TH1. When the difference Diff reaches the threshold TH1, go to step 936-1; otherwise, go to step 936-2.

In step 936-1, the controller moves/copy valid data to a high loss block such as the high loss block described above.

In step 936 - 2 , the controller moves/copy valid data to a low loss block such as the low loss block described in step 914 .

In step 938, the controller erases the target block.

According to an embodiment, such as a variation of the embodiment shown in FIG. 2C , the controller also has to dynamically adjust the threshold TH1 . When in step 932, the erasing frequency of the block to be erased selected by the controller in the data area is too high, for example, higher than the erasing frequency threshold TH _E , it means that the erasing frequency of the block has exceeded The average number of erasures of the blocks in the data area (which may be called data blocks) is too high, and the data stored in the blocks has a very high probability of being hot data. At this time, the controller has to dynamically increase the threshold value TH1, so that in step 934-1, when the controller checks whether the difference Diff reaches the threshold value TH1, it has a higher probability to enter step 936-2 to ensure the Some hot data has to be moved to low-loss blocks. In this way, the controller can dynamically adjust at least one threshold such as the threshold TH1 to change the probability of moving/copying valid data in the target block to the high-loss block or the low-loss block.

FIG. 3 shows the blocks in the data area 300 involved in the method 910 shown in FIG. 2A in an embodiment, wherein the arrows between these blocks represent the order of being written or updated, rather than the physical connection relation. In this embodiment, blocks {310-1, 310-2, 310-3, 310-4, 310-5, 310-6, ..., 330-m ₀ , ..., 320-2, The serial numbers of 320-1} are {SN1, SN2, SN3900, SN4800, SN4801, SN4802, ..., SN9600, ..., SN14998, SN15000} respectively. The connection relationship of the blocks shown in FIG. 3 is used to represent the order in which the blocks in the data area 300 are stored. As shown in FIG. 3 , the latest block in which data is written is block 320 - 1 , and its sequence number is SN15000 , which can also be called the end of the block sequence. The block whose data is first written is block 310 - 1 , its sequence number is SN1 , and it can also be called the head of the block sequence. The sequential writing relationship of these blocks can be regarded as a link relationship, which is a logical connection relationship, not a physical connection relationship. And this logical connection relationship will change with the behavior of the main device randomly writing data. Due to the random writing of the master device, all the data in one or some blocks in the link have become invalid data (for example, the master device wants to update these data, so that the old data stored in these blocks become invalid data). Then the controller will erase the blocks and move the blocks from the data area to the spare area. In addition, the controller also needs to remove these blocks from the chain and re-establish the chain. For example, blocks that were originally linked after the removed blocks are replaced to re-establish the link. Therefore, the serial numbers shown in FIG. 3 are not all consecutive. For example, the serial number SN2 is followed by the serial number SN3900, and the serial numbers SN3-SN3899 no longer exist in the link relationship. Please note that the serial number SN3-SN3899 does not originally exist in the link relationship, and the block corresponding to the serial number SN3-SN3899 may cause the data stored in it to become invalid due to the random writing of the master device, thus, The controller erases the blocks and moves the blocks from the data area to the spare area. Therefore, the controller also removes the serial numbers (serial numbers SN3-SN3899) corresponding to these blocks from the link, and re-establishes the link.

Please note that the symbol SN in the serial number above can be removed directly, leaving only the value in the serial number for easy calculation of the difference Diff. For example: in the case where the threshold TH1 is equal to 7500 and the threshold TH2 is equal to 1024, block {310-c} such as block {310-1, 310-2, 310-3, 310-4, 310-5, 310 The data in -6,...,310-C} can be regarded as cold data (for example, data that is not frequently updated by the master device), because their sequence numbers {SN1, SN2, SN3900, SN4800, SN4801, SN4802, ...} corresponding to the difference {Diff} (that is, the difference {14999, 14998, 11100, 10200, 10199, 10198, ...}) all reach the threshold value TH1; and the block {320-h} such as block The data in blocks {320-1, 320-2, ..., 320-H} can be regarded as hot data (for example, data that is frequently updated by the master device) because their sequence numbers {SN15000, SN14998, .. The difference {Diff} corresponding to .} (that is, the difference {0, 2, ...}) is lower than the threshold value TH2; and the remaining blocks {330-m} such as block {330-1, 330 -2,...,330-m ₀ ,...,330-M} can be regarded as medium data because the difference {Diff} (for example: difference 5400 ) falls within the range of the interval [TH2, TH1). This is for the purpose of illustration only, not limitation of the present invention. According to some variations of this embodiment, in the situation where the threshold TH1 is equal to the threshold TH2, the above-mentioned intermediate data does not exist.

FIG. 4A and FIG. 4B respectively illustrate implementation details of the method 910 shown in FIG. 2A in different embodiments.

As shown in FIG. 4A, the controller selects a block whose erasing frequency is lower than a threshold value TH3 among at least a part of the blocks in the spare area 400 of the flash memory 120, as the low loss block described in step 914, wherein The low-loss block is not the block with the lowest erasure count in the spare area 400 (for example, the erase count of the low-loss block is not 0). In particular, the low loss block can be a block with a lower erase count (but not the lowest erase count) in the spare area 400 . In the case that the target block is a hot block (i.e., a block containing hot data) such as block 320-2, the controller moves/copyes the valid data to the low-loss block; and upon moving/copying After the valid data, the controller erases the target block 320 - 2 and logically arranges the target block 320 - 2 in the spare area 400 . In addition, the controller logically arranges the low-loss block in the data area 300, so that the low-loss block logically becomes the new tail of the block sequence in the data area 300 shown in FIG. 3 (that is, shown in FIG. 4A shown in the new trailer block 320-0).

As shown in FIG. 4B , the controller selects a block whose erasing times reach a threshold TH4 from at least a part of blocks in the spare area 400 of the flash memory 120 as the high loss block described in step 914 . In particular, the high loss block can be a block with a higher (or highest) erasure count in the spare area 400 . In the case that the target block is a cold block (i.e., a block containing cold data) such as block 310-2, the controller moves/copyes the valid data to the high-loss block; and upon moving/copying After the valid data, the controller erases the target block 310 - 2 and logically arranges the target block 310 - 2 in the spare area 400 . In addition, the controller logically arranges the high-loss block in the data area 300, so that the high-loss block logically becomes the new tail of the block sequence in the data area 300 shown in FIG. 3 (that is, shown in FIG. 4B shown in the new trailer block 320-0).

One of the advantages of the present invention is that the block management implemented according to the present invention can distinguish between hot data and cold data, and use blocks with higher loss level to store cold data and use blocks with lower loss level to store hot data. This ensures optimal processing performance when performing wear-leveling operations in flash memory. Compared with related technologies, the present invention can achieve the goal of both operating performance and system resource usage control without greatly increasing the chip area and related costs.

The above descriptions are only preferred embodiments of the present invention, and all equivalent changes and modifications made according to the scope of the patent application of the present invention shall fall within the scope of the present invention.

Claims (30)

1. A method for block management, the method is applied to a flash memory controller, the flash memory includes a plurality of blocks, it is characterized in that the method includes: Select a target block with the lowest erasing times among at least a part of the blocks in a data area of the flash memory as a block to be erased, wherein the sequence numbers of the at least a part of the blocks correspond to the at least a part of the blocks respectively order of most recent update; and According to the sequence number of the target block and at least one threshold value, it is determined that the valid data in the target block should be moved/copied to a high-loss block or a low-loss block, wherein the loss degree of the high-loss block is greater than the The degree of loss of low-loss blocks; The at least one threshold value is dynamically adjusted to change the probability of moving/copying valid data in the target block to the high-loss block or the low-loss block. 2. The method according to claim 1, wherein it is determined based on the sequence number of the target block that the valid data in the target block should be moved/copied to the high-loss block or the low-loss block The steps also include: calculating the difference between the sequence number of the target block and the sequence number of a latest accessed block; and It is determined according to the difference that the valid data in the target block should be moved/copied to the high-loss block or the low-loss block. 3. The method according to claim 2, wherein the at least one threshold value is two, namely a first threshold value and a second threshold value, wherein the target block should be determined according to the sequence number of the target block. The step of moving/copying the valid data in the block to the high loss block or the low loss block further includes: The difference is compared with the first threshold to determine whether to move/copy the valid data to the high loss block. 4. The method according to claim 3, wherein it is determined according to the sequence number of the target block that the valid data in the target block should be moved/copied to the high-loss block or the low-loss block The steps also include: When the difference reaches the first threshold, the valid data is moved/copied to the high loss block. 5. The method according to claim 2, wherein the at least one threshold value is two, namely a first threshold value and a second threshold value, wherein it is determined based on the sequence number of the target block that the target The step of moving/copying the valid data in the block to the high loss block or the low loss block further includes: The difference is compared with a second threshold to determine whether to move/copy the valid data to the low-loss block. 6. The method according to claim 5, wherein it is determined according to the sequence number of the target block that the valid data in the target block should be moved/copied to the high-loss block or the low-loss block The steps also include: When the difference is lower than the second threshold, the valid data is moved/copied to the low loss block. 7. The method according to claim 5, wherein it is determined based on the sequence number of the target block that the valid data in the target block should be moved/copied to the high-loss block or the low-loss block The steps also include: The difference is compared with the first threshold to determine whether to move/copy the valid data to the high loss block. 8. The method according to claim 1, wherein the at least one threshold value is two, which are respectively the third threshold value and the fourth threshold value, and the method further comprises: a backup in the flash memory A block whose erasure count reaches a third threshold value is selected from at least a part of the blocks in the area as the high-loss block. 9. The method according to claim 1, wherein the at least one threshold value is two, respectively the third threshold value and the fourth threshold value, and the method further includes: Select a block whose erasing frequency is lower than the fourth threshold value among at least a part of blocks in a spare area of the flash memory as the low-weary block, wherein the low-weary block is not the lowest erase block in the spare area Divided blocks. 10. The method of claim 1, further comprising: After moving/copying the valid data, the target block is erased. 11. A memory device, characterized in that it comprises: a flash memory comprising a plurality of blocks; and A controller is used to access the flash memory and manage the plurality of blocks, wherein the controller selects a target block with the lowest erasing times among at least a part of blocks in a data area of the flash memory, as a target block to be erasing blocks, and the serial numbers of the at least a part of the blocks respectively correspond to the sequence of the latest update of the at least a part of the blocks; Wherein the controller decides to move/copy the valid data in the target block to a high-loss block or a low-loss block according to the sequence number of the target block and at least a threshold value, and the high-loss block's The loss degree is greater than the loss degree of the low loss block, and the controller is used to dynamically adjust the at least one threshold value to change the valid data in the target block to move/copy to the high loss block or the low loss block block probability. 12. The memory device according to claim 11, wherein the controller calculates the difference between the sequence number of the target block and the sequence number of a latest access block, and decides based on the difference that the Valid data in the target block is moved/copied to the high loss block or the low loss block. 13. The memory device according to claim 12, wherein the at least one threshold value is two, namely a first threshold value and a second threshold value, wherein the controller compares the difference with the first threshold value value to decide whether to move/copy the valid data to the high loss block. 14. The memory device according to claim 13, wherein when the difference reaches the first threshold value, the controller moves/copy the valid data to the high loss block. 15. The memory device according to claim 12, wherein the at least one threshold value is two, namely a first threshold value and a second threshold value, wherein the controller compares the difference with the second threshold value Threshold value to decide whether to move/copy the valid data to the low-loss block. 16. The memory device according to claim 15, wherein when the difference is lower than the second threshold value, the controller moves/copy the valid data to the low loss block. 17. The memory device according to claim 15, wherein the controller compares the difference with the first threshold value to determine whether to move/copy the valid data to the high loss block. 18. The memory device according to claim 11, wherein the at least one threshold value is two, respectively a third threshold value and a fourth threshold value, wherein the controller is in a spare area of the flash memory A block whose erasing count reaches the third threshold value is selected from at least a part of the blocks as the high-loss block. 19. The memory device according to claim 11, wherein the at least one threshold value is two, respectively a third threshold value and a fourth threshold value, wherein the controller is in a spare area of the flash memory Select a block whose erasing count is lower than the fourth threshold value among at least a part of the blocks as the low loss block, and the low loss block is not the block with the lowest erasing count in the spare area. 20. The memory device according to claim 11, wherein after moving/copying the valid data, the controller erases the target block. 21. A controller of a memory device, the controller is used to access a flash memory, the flash memory includes a plurality of blocks, it is characterized in that the controller includes: a read-only memory for storing a program code; and a microprocessor for executing the program code to control access to the flash memory and manage the plurality of blocks, wherein the controller executing the program code through the microprocessor is in a data area of the flash memory Selecting a target block with the lowest number of times of erasure among at least a part of the blocks is a block to be erased, and the sequence numbers of the at least a part of the blocks correspond to the latest update order of the at least a part of the blocks; wherein the controller executing the program code through the microprocessor decides that valid data in the target block should be moved/copied to a high loss block or a low loss block according to the sequence number of the target block and at least a threshold value loss block, and the loss degree of the high loss block is greater than the loss degree of the low loss block, and the controller is used to dynamically adjust the at least one threshold value to change the effective data movement/copy in the target block The probability of going to the high loss block or the low loss block. 22. The controller according to claim 21, wherein the controller executing the program code through the microprocessor calculates the distance between the sequence number of the target block and the sequence number of a latest accessed block The difference, and according to the difference, it is decided that the valid data in the target block should be moved/copied to the high-loss block or the low-loss block. 23. The controller according to claim 22, wherein the at least one threshold value is two, respectively a first threshold value and a second threshold value, wherein the microprocessor executes the program code The controller compares the difference with a first threshold to determine whether to move/copy the valid data to the high loss block. 24. The controller according to claim 23, wherein when the difference reaches the first threshold value, the valid data is moved/copied by the controller executing the program code through the microprocessor to the high loss block. 25. The controller according to claim 24, wherein the at least one threshold value is two, respectively a first threshold value and a second threshold value, wherein the microprocessor executes the program code The controller compares the difference with a second threshold to determine whether to move/copy the valid data to the low-loss block. 26. The controller according to claim 25, wherein when the difference is lower than the second threshold value, the controller executing the program code through the microprocessor moves/ Copy to this low-loss block. 27. The controller according to claim 25, wherein the controller executing the program code through the microprocessor compares the difference with the first threshold value to determine whether to move the valid data/ Copy to the high loss block. 28. The controller according to claim 21, wherein the at least one threshold value is two, respectively a third threshold value and a fourth threshold value, wherein the microprocessor executes the program code The controller selects a block whose erasing times reaches a third threshold value from at least a part of blocks in a spare area of the flash memory as the high loss block. 29. The controller according to claim 21, wherein the at least one threshold value is two, respectively a third threshold value and a fourth threshold value, wherein the microprocessor executes the program code The controller selects a block whose erasing frequency is lower than a fourth threshold value among at least a part of blocks in a spare area of the flash memory as the low-loss block, and the low-loss block is not in the spare area The block with the lowest erasure count. 30. The controller according to claim 21, wherein after moving/copying the valid data, the controller executing the program code through the microprocessor erases the target block.