TW202036300A - Data storage device and control method for non-volatile memory - Google Patents

Abstract

High-efficiency control technology for non-volatile memory. A data storage device includes a non-volatile memory and a controller. The controller allocates an active block from a plurality of spare blocks of the non-volatile memory to fill in write data requested by the host. When performing garbage collection, the controller further regards the active block as the destination for collecting the valid data from another block.

Description

Data storage device and non-volatile memory control method

This case is about the control of non-volatile memory.

Non-volatile memory has many forms-for example, flash memory (flash memory), magnetoresistive RAM (Magnetoresistive RAM), ferroelectric random access memory (Ferroelectric RAM), resistive random access Memory (Resistive RAM), Spin Transfer Torque-RAM (STT-RAM)... etc. are used for long-term data storage and can be used as storage media to realize a data storage device.

Non-volatile memory usually has its special storage characteristics. The technical field needs to develop corresponding control technology corresponding to the storage characteristics of non-volatile memory.

A data storage device implemented according to an embodiment of this case includes a non-volatile memory and a controller. The controller configures an active block from a plurality of idle blocks of the non-volatile memory to fill in write data required by the host. When the controller performs garbage collection, the active block is also used as the destination of the effective data of other blocks.

When the number of the idle blocks is less than a critical number, the controller can use the active block as the transfer destination of the valid data of the source block.

The controller can also use the active block as a transfer destination of valid data of the second source block when a second source block meets an endangered condition.

In one embodiment, the controller allows valid data from one source block to be completely moved to the active block before allowing valid data from another source block to be moved to the active block.

In one embodiment, the controller moves valid data of a source block to the active block in a plurality of batches, and allows the write data sent by the host to fill the active block between different batches.

In one embodiment, the controller estimates a ratio between the effective data amount of a source block and the idle space of the active block, and sets the effective data amount of each batch to be moved according to the ratio. According to the ratio, the controller can further set the amount of data written by the host to fill the active block between two batches.

In one embodiment, the controller estimates a ratio between the effective data amount of a source block and the write data amount requested by the host, and sets the effective data amount of each batch transfer according to the ratio.

In one embodiment, the second source block that meets the endangered condition is invalid for error correction.

In one embodiment, the second source block that meets the endangered condition is for preventive removal.

In one embodiment, the second source block that meets the endangered condition is moved with loss average.

In one embodiment, after the controller moves all the valid data of a source block to the active block, it releases the source block as an idle block before the end writing of the active block is completed.

In one embodiment, the controller operates a flag. The controller uses the flag to indicate that the active block is allowed to save valid data from other source blocks after all valid data in a source block is moved to the active block.

The operation of the above controller on the non-volatile memory can also be realized by other structures. This case can also realize the control method of non-volatile memory with the aforementioned concepts, including: operating a non-volatile memory according to the requirements of a host; configuring an active block from a plurality of idle blocks of the non-volatile memory and filling in the host The required write data; when the number of idle blocks is less than a critical number, the active block is used as the transfer destination of the valid data of a first source block; and a second source block meets a In the end-of-loss condition, the active block is used as the transfer destination of the valid data of the second source block.

Hereinafter, specific embodiments are given in conjunction with accompanying drawings to illustrate the content of the present invention in detail.

The following description lists various embodiments of the present invention. The following description introduces the basic concept of the present invention, and is not intended to limit the content of the present invention. The actual scope of invention shall be defined in accordance with the scope of patent application.

Non-volatile memory can be flash memory (Flash Memory), magnetoresistive RAM (Magnetoresistive RAM), ferroelectric random access memory (Ferroelectric RAM), resistive RAM (RRAM) ), Spin Transfer Torque-RAM (STT-RAM), etc., provide storage media for long-term data storage. The following discussion takes the flash memory as an example.

Nowadays, data storage devices often use flash memory as storage media to store user data from the host. There are many types of data storage devices, including memory cards (Memory Card), universal serial bus flash devices (USB Flash Device), solid state drives (SSD)... and other products. One application is to use multi-chip packaging to package flash memory and its controller together-called embedded flash memory modules (such as eMMC).

The data storage device using flash memory as the storage medium can be applied to a variety of electronic devices. The electronic devices include smart phones, wearable devices, tablet computers, virtual reality equipment, etc. The computing module of the electronic device can be regarded as a host, which operates the data storage device used to access the flash memory therein.

Data storage devices using flash memory as storage media can also be used to construct data centers. For example, the server may operate a solid state drive (SSD) array to form a data center. The server can be regarded as the host, operating the connected solid-state drive to access the flash memory.

FIG. 1 illustrates a data storage device 100 according to an embodiment of the present invention. The data storage device 100 includes a flash memory 102 and a controller 104. The host 106 indirectly accesses the flash memory 102 through the controller 104. In addition to receiving and executing write commands from the host 106, the controller 104 also actively moves the user data stored in the flash memory 102.

Flash memory has its special storage characteristics, which are described below.

The host 106 distinguishes user data by logical addresses (for example, logical block address LBA or global host page number GHP... etc.). The physical space of the flash memory 102 is divided into a plurality of blocks (Blocks) for allocation. Each block (Block) includes a plurality of pages (Pages). Each page includes N sectors (Sectors), N is an integer greater than 1, such as: 4. A page of 16KB space can be divided into four sectors, each of which is 4KB. In one embodiment, a block is arranged according to the page number, from low to high number to store user data.

In one embodiment, the data storage device adopts multi-channel technology, which can virtualize multiple blocks of different channels into a super block, and multiple pages can be virtualized into a super page, and use super blocks and super pages to perform data Storage space management can speed up the data throughput of data storage devices.

The data storage device records the correspondence between the logical address and the physical address of the user data in a logical-physical address mapping table (Logical-Physical Mapping Table, L2P Table).

The storage space of flash memory needs to be erased before it can be used again. The smallest unit of erase (Erase) is a block. Blocks can be divided into data blocks, active blocks and idle blocks. Idle blocks can be used as active blocks to write user data. When the active block is filled with user data, after closing processing (writing EOB (End of Block) information), the active block is changed to a data block. As user data is updated, some user data stored in the data block will be changed from valid data to invalid data. When the user data stored in the data block are all invalid data, it will be changed to an idle block after erasure. In another embodiment, a data block full of invalid data is changed to an idle block, and the erasing process is performed when the idle block becomes an active block.

The use of flash memory involves data movement procedures, which can be divided into garbage collection procedures and non-garbage collection procedures. When the number of free blocks is insufficient, the storage space can be garbage collected (Garbage Collection) processing. For example, when multiple data blocks (also called source blocks) only store sporadic valid data, garbage collection can be performed and the valid data can be collected into one active block (also called destination block) to recover multiple data Block, increase the number of idle blocks.

There are many types of non-garbage collection programs, which are judged based on the endangered condition. For example, the data block (source block) where the error correction failure (ECC failed) is generated also needs to be moved to timely rescue the user data that can still be read. In addition, data blocks (source blocks) that are read too frequently also need to be moved to avoid user data damage caused by the reduction of the data storage capacity of the data block. This operation is also called preventive move (Early Move). In addition, data migration may also be initiated in response to wear leveling considerations between blocks, for example, all user data (including valid data and invalid data) in the data block (source block) with a low number of reads Move to the active block (destination block) with a higher erase count to recover the data block. In addition, the loss averaging process can also be combined with the garbage collection process, that is, the loss averaging process moves the valid data of multiple data blocks (source blocks) to the active block (destination block) with a higher erasure count.

It should be noted that the data transfer is preferably realized by data copying.

In the figure, the idle blocks of the flash memory 102 belong to the idle block pool 108, and the data blocks belong to the data block pool 110. When the host 106 submits a write command or the controller 104 starts the data transfer procedure, the controller 104 selects an idle block from the idle block pool 108 as the active block A0. At this time, the idle area of the idle block pool 108 The number of blocks will be reduced by one. Afterwards, the user data is written into the active block A0. When the active block A0 is turned off and becomes a data block, the number of data blocks will increase by one.

This case proposes a high-performance data storage method that can meet various data storage needs. In addition to storing user data from the host (the host 106 requests to write to the flash memory 102 with a write command), start data migration procedures, such as garbage collection, error correction failing migration, preventive migration, and loss-averaging migration , Or other, you can use this high-performance data storage method to store user data in the source box (data block).

The controller 104 generally uses an active block (labeled as A0) to receive user data from the host. The user data is usually provided by a write command. In particular, instead of using another active block (called A1 to distinguish it from A0) to store user data from the source block, the controller 104 in this case makes the active block A0 also serve as the destination of the data transfer process, and Instead of using active block A1. Once there is a data migration requirement, such as garbage collection, error correction and invalidation migration, preventive migration, loss-average migration, or others, this case can collect the user data of the source block in the data migration process to active block A0. Compared with the traditional technology that simultaneously configures the active block A0 and the active block A1, the design of this case has several advantages, which are described as follows.

First of all, the active block A0 in this case can not only store user data requested by the host with a write command, but also store user data from the source block. Therefore, the usage of idle blocks can be reduced.

In the traditional example of using active block A1, in response to sudden power outages, the Sudden Power Off Recovery (SPOR) program must take special consideration of data reliability, and will discard the closed active Block A1 is still subject to the user data on the source block. Therefore, as long as the active block A1 is not closed, all source blocks in the data transfer process must be retained and cannot be released. The above design obviously drags down the recovery of source blocks, causing the number of idle blocks to not increase in time, and even leading to the start of different types of data transfer procedures.

Compared with the traditional technology, this case uses the active block A0 as the target block in the data transfer process. The SPOR procedure will not completely discard the active block A0. After the data transfer is completed, the source block in the data transfer process can be recovered, and there is no need to save it for the SPOR process. Therefore, compared with the traditional technology that specifically uses the active block A1 as the target block, the number of idle blocks in this case can be effectively increased to overcome the above-mentioned problems.

In addition, in order to close the active block A1 as the target block in the traditional technology, some dummy data may be filled in, which will reduce the data storage capacity of the data block and increase the erasure frequency of the block. , Shorten the life of flash memory. In contrast, using the active block A0 as the destination of the data transfer program can avoid the writing of false data and overcome the above-mentioned problems.

In one implementation, the controller 104 allows the valid data of a source block (whether garbage collection or non-garbage collection) to be completely moved to the active block A0 before allowing another source block (regardless of garbage collection or non-garbage collection). Valid data of garbage collection) is moved to the active block A0.

As mentioned above, data transfer procedures can be divided into garbage collection procedures and non-garbage collection procedures. When the number of idle blocks is less than the threshold TH1, the controller 104 starts the garbage collection process, and uses the active block A0 as the target block in the garbage collection process, as shown by the garbage collection path GC.

For non-garbage collection procedures, such as error correction failure removal, preventive removal, loss average removal, etc., the controller 104 also uses the active block A0 as a target block in the non-garbage collection process, such as the non-garbage collection path Non_GC mark.

In one implementation, in addition to storing user data from the host 106, the active block A0 is also used as the target block of the garbage collection process. After the active block A0 stores user data from the host 106, if the active block A0 is not closed, the active block A0 can be used as the destination block in the garbage collection process to store users from the source block BLK#0 data. Under this setting, if all valid data of the source block (take BLK#0 as an example) has been moved, the source block BLK#0 can be recycled and become an idle block without waiting for the active block A0 to close.

In one embodiment, in addition to storing user data from the host 106, the active block A0 can be used as a target block for the non-garbage collection process. After the active block A0 stores the user data from the host 106, if the active block A0 is not closed, the active block A0 can be used as the destination block of the non-garbage collection process to store the source block (take BLK#1 as Example) user data. Under this setting, if all the valid data of the source block BLK#1 has been moved, the source block BLK#1 can be recycled and become an idle block without waiting for the active block A0 to close.

In one embodiment, in addition to storing user data from the host 106, the active block A0 can be used as a target block for garbage collection procedures and non-garbage collection procedures. After the active block A0 stores the user data from the host, if the active block A0 is not closed, the controller 104 can start the garbage collection process to move the user data of the source block (take BLK#0 as an example) to the active block Block A0. If the active block A0 is still not closed, the controller 104 can start the non-garbage collection process and move the user data of the source block BLK#0 to the active block A0. What's more, the active block A0 can be used as the target block of the non-garbage collection process to store user data from the source block (take BLK#1 as an example). Under this setting, if all valid data of the source block BLK#0 or source block BLK#1 has been moved, the source block BLK#0 or source block BLK#1 can be recycled and become idle blocks. There is no need to wait for the active block A0 to close.

In addition, user data from the host, garbage collection program, or non-garbage collection program is preferably stored or moved to active block A0 in sections (in batches) and staggered, where section means storing or moving a certain amount User data of to the active block A0, or store or move a certain amount of user data to the active block A0 at a preset time; staggered means that the data is provided by multiple data sources in turn, among which the data source can be the host or garbage The source block of the recycling program or non-garbage collection program.

In one embodiment, the controller 104 estimates the ratio of the effective data volume of the source block and the user data volume from the host 106, and sets the data volume for segment transfer and segment writing according to the ratio. In another embodiment, the controller 104 estimates the effective data amount of the source block and the ratio of the free space of the active block A0, and sets the amount of data to be moved and written in segments according to the ratio.

Figures 2A-2B illustrate the high-efficiency data storage method implemented according to an embodiment of this case with a flowchart, and use the flag cleanflag to control the movement of data.

Step S202: The controller 104 configures the active block A0. The controller 104 allocates one of the idle blocks from the idle block pool 108 as the active block A0.

Step S204: The controller 104 initializes the flag cleanflag to "DISABLE". The flag cleanflag status "DISABLE" means that the active block A0 can also be configured as the destination block of the data transfer process.

Step S206: The controller 104 judges whether to execute the data transfer procedure? If yes, execute step S210, if otherwise, execute step S208. When the preset condition is met, for example, the number of idle blocks is less than the threshold TH1, or an error correction failure occurs, the controller 104 starts (executes) the data transfer process.

Step S208: The controller 104 determines whether to close the active block A0? If yes, execute step S214, if otherwise, execute step S212. If the active block A0 still has free space to store data, the controller 104 does not close the active block A0.

Step S212: The controller 104 writes the user data from the host 106 into the active block A0, and then returns to step S206. In the above, the controller 104 executes step S206 first, and then executes step S208 and step S212, which means that the controller 104 will preferentially move the user data of the data movement procedure. In another embodiment, the controller 104 may first perform steps S208 and S212, and then perform step S206. Under this setting, the controller 104 will write the user data of the host 106 into the active block A0 first.

Step S214: The controller 104 closes the active block A0. If the active block A0 has no free space to store data, the controller 104 closes the active block A0 and writes EOB information into the last page of the active block A0.

Step S210: The controller 104 determines the data transfer amount of the data transfer procedure, where the data transfer amount can be a fixed value, determined by the ratio of the data amount of the source block to the user data amount from the host 106, or the source zone The data volume of the block and the proportion of the free space of the active block A0 are determined. The source block can be a source block of a garbage collection program or a non-garbage collection program. The amount of data movement is preferably the amount of valid data.

Step S216: The controller 104 sets the flag cleanflag to "START", where "START" represents the active block A0 as the target block for data transfer, and prepares to execute the data transfer.

Step S218: The controller 104 transfers the user data of the data transfer amount from the source block to the active block A0. The controller 104 can move the user data of the source block to the active block A0 all at once or in sections. Assuming that the source block has x user data, and the amount of user data from the host 106 is n*x, the ratio of the two is 1:n, x = 16, for example, n = 10. If the data is moved in segments, the controller 104 can move M user data to the active block A0 in each segment. M, for example, =4, and the number of segments to be moved=4. Figure 3 illustrates an example of segmented movement. After the user data Data#0...Data#3 is moved to the active block A0, the host 106 can be inserted to write the user data to the active block A0, and then the user data Data#4...Data#7 can be moved to the active block A0: The remaining eight user data are moved from the source block to the active block A0 in the same way. If it is a one-time data transfer, the host 106 is not inserted to write user data, and the controller 104 transfers all 16 user data to the active block A0. In addition, when data is moved, M is preferably a multiple of a section, and it can cover an integer multiple of pages. For example, the controller 104 only writes data of one page at a time, then M=4, which means that the four sections of one page are moved together. In one embodiment, the controller 104 writes the data of one super page at a time, M=16.

Step S220: The controller 104 sets the flag cleanflag to "FINISH", where "FINISH" indicates that the one-time or segmented data transfer has been completed.

Step S222: The controller 104 writes the user data from the host 106 to the active block A0. After the user data of the data transfer amount has been transferred at this stage, the controller 104 changes the source of the data to the host 106, that is, writes the user data from the host 106 to the active block A0. Wherein, the controller 104 can write a fixed number of user data, or 40 (n*M, n=10 and M=4) user data calculated by the above ratio into the active block A0.

Step S224: The controller 104 judges whether the data transfer procedure is completed? If yes, execute step S226, if otherwise, execute step S216. If the controller 104 moves the user data of the source block to the active block A0 in sections, the controller 104 will repeat steps S216~S224, for example, the number of repetitions=4 (16 in total and 4 in each segment , Then repeat 4 times and move in four stages).

Step S226: The controller 104 sets the flag cleanflag to "DISABLE".

Step S228: The controller 104 changes the source block to an idle block. At this time, the number of the idle block pool is increased by 1. Step S228 can be independent of whether the active block A0 is closed or not. The number of idle blocks can be made up in time.

In one of step S212, step S214, step S218, and step S222, the controller 104 further includes updating the logical-physical address mapping table according to the user data stored in the active block A0. The controller 104 preferably first After generating the physical-logical address mapping table of the user data of the active block A0, the physical-logical address mapping table is used to update the logical-physical address mapping table.

In an implementation manner, step S222 may include time limit judgment. When the time limit is exceeded, the flow proceeds to step S224.

In one embodiment, the amount of data to be transferred in sections (S218) and written in sections (S222) depends on the effective data amount of the source block and the ratio of the free space of the active block A0. If the active block A0 has only a small amount of free space, but the amount of effective data in the source block is large, the controller 104 increases the effective data moved in each segment (S218), or/and restricts the host 106 user who writes in each segment Data (S222). In this way, the source block can be completely moved before the host block A0 is closed.

The user's operating habits may cause the device to repeatedly power off and power on (called power cycling). For example, a mobile phone user opens the lid to view information and then closes the lid. A large amount of idle blocks are consumed, and garbage collection needs occur. Certain blocks may also be read too frequently, resulting in ECC failed movement, early move, wear leveling movement, or other effective data movement requests. This case allows the excessively low number of idle blocks to be filled in time.

The operation of the above controller 104 on the flash memory 102 can also be implemented by other structures. Anyone who does not configure active block A1 for the purpose of moving data between blocks falls within the scope of protection of this case. In this case, the aforementioned concept can be used to realize the control method of non-volatile memory.

Although the present invention has been disclosed as above in the preferred embodiment, it is not intended to limit the present invention. Anyone familiar with the art can make some changes and modifications without departing from the spirit and scope of the present invention. Therefore, the present invention The scope of protection shall be subject to the scope of the attached patent application.

100: Data storage device; 102: Flash memory; 104: Controller; 106: host; 108: Idle block pool; 110: Data block pool; A0: Active block; Data#0...Data#7: User data; GC: garbage collection path; Non_GC: Other effective data movement paths that are not garbage collected; S202...S228: Steps.

Figure 1 illustrates a data storage device 100 according to an embodiment of the present case; and Figures 2A-2B illustrate the high-efficiency data storage method implemented according to an embodiment of this case with a flowchart, and use the flag cleanflag to control the movement of data; and Figure 3 illustrates an example of segmented movement.

100: Data storage device

102: flash memory

104: Controller

106: host

108: Idle block pool

110: Data block pool

A0: Active block

GC: garbage collection path

Non_GC: Other effective data movement paths for non-garbage collection

Claims (26)

A data storage device includes: A non-volatile memory; and A controller operates the non-volatile memory according to the request of a host, among them: The controller configures an active block from a plurality of idle blocks of the non-volatile memory to fill in the write data requested by the host; and When the controller performs garbage collection, it also uses the active block as the destination of the effective data of other blocks. Such as the data storage device of request 1, where: When the number of the idle blocks is less than a critical number, the controller uses the active block as a transfer destination of valid data of a first source block. Such as the data storage device of request 2, where: The controller further uses the active block as a transfer destination of valid data of the second source block when a second source block meets an endangered condition. Such as the data storage device of request 3, where: The controller allows valid data from one source block to be completely moved to the active block before allowing valid data from another source block to be moved to the active block. Such as the data storage device of request 4, where: The controller moves the valid data of a source block to the active block in a plurality of batches, and allows the write data sent by the host to fill the active block between different batches. Such as the data storage device of request 5, where: The controller estimates a ratio between the effective data amount of a source block and the idle space of the active block, and sets the effective data amount moved in each batch according to the ratio. Such as the data storage device of request 6, where: According to the ratio, the controller sets the amount of data written in the active block that the host is allowed to fill in between the two batches. Such as the data storage device of request 5, where: The controller estimates a ratio between the effective data amount of a source block and the write data amount requested by the host, and sets the effective data amount of each batch to be moved according to the ratio. Such as the data storage device of request 3, where: The second source block that meets the endangered condition is invalid for error correction. Such as the data storage device of request 3, where: The second source block that meets the endangered condition is for preventive removal. Such as the data storage device of request 3, where: The second source block that satisfies the endangered condition is a loss average shift. Such as the data storage device of request 3, where: After the controller moves all valid data of a source block to the active block, it releases the source block as an idle block before the end of the active block is written. Such as the data storage device of request 4, where: The controller operates a flag; and The controller uses the flag to indicate that the active block is allowed to save valid data from other source blocks after all valid data in a source block is moved to the active block. A non-volatile memory control method, including: Operate a non-volatile memory according to the requirements of a host; Configure an active block from a plurality of idle blocks of the non-volatile memory to fill in the write data requested by the host; and When garbage collection is performed, the active block is also used as the destination of the effective data of other blocks. For example, the non-volatile memory control method of claim 14 further includes: When the number of the idle blocks is less than a critical number, the active block is used as a transfer destination of valid data of a first source block. For example, the non-volatile memory control method of claim 15, including: When a second source block meets an endangered condition, the active block is used as the transfer destination of the effective data of the second source block. For example, the non-volatile memory control method of claim 16 further includes: After the effective data of one source block is completely moved to the active block, the effective data of another source block is allowed to be moved to the active block. For example, the non-volatile memory control method of claim 17 further includes: The valid data of a source block is moved to the active block in a plurality of batches, and the write data sent by the host is allowed to fill the active block between different batches. For example, the non-volatile memory control method of claim 18 includes: Estimate a ratio between the effective data amount of a source block and the idle space of the active block, and set the effective data amount of each batch to be moved according to the ratio. For example, the non-volatile memory control method of claim 19 includes: According to the ratio, set the amount of data written by the host to fill the active block between two batches. For example, the non-volatile memory control method of claim 18 includes: Estimate a ratio between the effective data amount of a source block and the write data amount requested by the host, and set the effective data amount of each batch to move according to the ratio. Such as the non-volatile memory control method of claim 16, in which: The second source block that meets the endangered condition is invalid for error correction. Such as the non-volatile memory control method of claim 16, in which: The second source block that meets the endangered condition is for preventive removal. Such as the non-volatile memory control method of claim 16, in which: The second source block that satisfies the endangered condition is a loss average shift. The non-volatile memory control method described in claim 16 further includes: After all valid data of a source block is moved to the active block, the source block is released as an idle block before the end writing of the active block is completed. For example, the non-volatile memory control method of claim 17 further includes: Operate a flag; and After all the valid data of a source block is moved to the active block, the flag is used to indicate that the active block is allowed to save the valid data of other source blocks.

Images