TWM652759U - data storage device - Google Patents

Abstract

A data storage device includes a control unit, a buffer storage unit and a main storage unit. The control unit is used to convert a data to be stored into one or more data parts temporarily stored in the buffer storage unit, and perform the following processing on each data part: determine whether the size of the data part reaches a predetermined size, If not, write the data portion from the buffer storage unit to the first storage portion in a first writing mode. If yes, write the data portion directly from the buffer storage unit to the buffer storage unit in a second writing mode. the second storage section. The first writing mode enables a single storage element of the first storage part to store a single bit of data, and the second writing mode enables a single storage element of the second storage part to store multiple bits of data. material.

Description

data storage device

The present invention relates to a storage device, in particular to a data storage device for storing digital data.

Solid-state drives (SSDs for short) have better reading speeds than traditional mechanical hard drives, and have become popular in today's electronic product market.

In short, solid-state drives usually use floating gate transistors as their internal smallest storage units (also called cells), and the current storage types of solid-state drives are divided into "single-layer storage" (referred to as "single-layer storage"). SLC), "multi-tier storage" (sometimes also called "two-tier storage", referred to as MLC), "three-tier storage" (referred to as TLC) and "quad-tier storage" (referred to as QLC).

As for SLC, each cell of SLC can only store one bit of data. Although it has the fastest data access speed compared to MLC, TLC, and QLC, its cost is also the highest. A single cell of MLC, TLC, and QLC can store two-bit, three-bit, and four-bit data respectively, so they have an advantage over SLC in terms of cost. However, the more bits each cell can store, the higher the storage cost. The slower the speed.

Based on the above, users are often troubled by the trade-off between access speed and cost. Therefore, how to improve the existing technology to achieve a better balance between access speed and cost has become a question worth exploring. the issue.

Therefore, one of the objectives of the present invention is to provide a data storage device that helps balance access speed and cost.

The new data storage device is suitable for electrical connection with a computer component; the data storage device includes a control unit, a buffer storage unit electrically connected to the control unit, and a main storage unit. The main storage unit includes a first storage part electrically connected to the control unit, and a second storage part electrically connected to the control unit, wherein the first storage part and the second storage part each have a plurality of pages, and Each page has a plurality of storage elements electrically connected to the control unit. When the control unit receives a data to be stored to be stored through the computer component, the control unit converts the data to be stored into one or more data parts that are temporarily stored in the buffer storage unit, and for each The data part performs a write process, wherein the control unit performs the write process on each data part including: judging whether the data size of the data part reaches a predetermined size, and when the judgment result is no, use a first A write mode is used to write the data portion from the buffer storage unit to one of the pages in the first storage portion. When the determination result is yes, a second write mode is used to write the data portion from the buffer storage unit. Write directly to one of the pages in the second storage part, wherein the first writing mode enables a single storage element in the first storage part to store a single bit of data, and the second writing mode A single storage element in the second storage part can store multiple bits of data.

In some implementations of the new data storage device, the control unit is also used to determine whether there is a full page in which the size of the stored data reaches a preset size in the pages of the first storage part. And when the judgment result is yes, the data in the full page is transferred from the full page to one of the pages in the second storage part in the second writing mode, and the default size is equal to or smaller than the predetermined size.

In some implementations of the novel data storage device, the configuration positions of the first storage part and the second storage part in the main storage unit are predetermined and fixed.

The function of the present invention is that the control unit of the data storage device can decide to write the data part to the first data part in the faster first writing mode based on whether the data size of each data part reaches a predetermined size. To store part of the data, it is still necessary to use the second writing mode with higher data storage density to write the data part to the second storage part, that is, to determine the storage mode and storage area according to the size of the data part. , this data storage device helps to achieve a better balance between access speed and cost, so it can indeed improve the existing technology.

Before the present invention is described in detail, it should be noted that, unless otherwise defined, the term "electrically connected" described in this patent specification is used to describe computer hardware (such as electronic systems, equipment, devices, units). , components), and generally refers to the "wired electrical connection" between multiple computer hardware that are physically connected to each other through conductor/semiconductor materials, and the use of wireless communication technologies (such as but not Limited to wireless networks, Bluetooth and electromagnetic induction, etc.) to achieve "radio connection" for wireless data transmission. On the other hand, unless otherwise defined, the "electrical connection" described in this patent specification also generally refers to the "direct electrical connection" achieved by direct coupling between multiple computer hardware components, as well as the "direct electrical connection" between multiple computer hardware components. There is an "indirect electrical connection" achieved through indirect coupling with other computer hardware.

Before the present invention is described in detail, it should be noted that the "unit" mentioned in this patent specification represents computer hardware rather than software. For example, "processing unit" is used to represent a computer with data processing functions. Hardware. On the other hand, the "unit" mentioned in this patent specification can refer to a single computer hardware with specific functions, or it can refer to a group of computer hardware with similar functions. For example, a "processing unit" can be It refers to a single processor with data processing functions, but it can also refer to a collection of processors.

Referring to Figure 1, an embodiment of the new data storage device 1 is suitable for being installed in a computer component 5 and electrically connected to the computer component 5, so that the data storage device 1 can be written through the computer component 5. data or read data.

Specifically, in this example, the data storage device 1 is implemented as a solid state drive device, and the computer component 5 is, for example, a computer motherboard equipped with a central processing unit. Furthermore, the data storage device 1 can be electrically connected to the computer component 5 through a connection interface such as SATA or PCI-E. It should be added that in the application of this embodiment, as long as the computer component 5 is computer hardware that allows the installation of a hard disk to read and write data on the hard disk, it can be used as the data storage device 1 of this embodiment. Application object, therefore, the computer component 5 is not limited to a computer motherboard equipped with a central processing unit.

In this embodiment, the data storage device 1 includes a control unit 11 adapted to be electrically connected to the computer component 5, a buffer storage unit 12 electrically connected to the control unit 11, and a buffer storage unit 12 electrically connected to the control unit 11. main storage unit 13.

In this embodiment, the control unit 11 is a processor implemented with an integrated circuit and has data computing and instruction sending and receiving functions, and is equivalent to the central processing unit of the data storage device 1 . However, in similar implementations, the control unit 11 may also be a collection of multiple processors, or a central processing module including one or more processors.

The buffer storage unit 12 is a random access memory (Random-Access Memory) electrically connected to the control unit 11 . Moreover, in this embodiment, the buffer storage unit 12 is used as a time-sharing buffer (Translation Storage Buffer, TSB for short) of the data storage device 1, and is used for the control unit 11 to temporarily store the data to be written. The data stored in the main storage unit 13 is entered.

The main storage unit 13 is implemented by, for example, NAND flash memory, but is not limited thereto. In more detail, the main storage unit 13 includes a first storage part 131 electrically connected to the control unit 11 and a second storage part 132 electrically connected to the control unit 11 . The first storage part 131 and the second storage part 132 each have a plurality of pages 133 (also referred to as Pages) with the same storage capacity.

The pages 133 are the basic units of the storage blocks (also called Blocks, not shown) that constitute the first storage part 131 and the second storage part 132. For example, each page 128 or Two hundred and fifty-six pages 133 will constitute a storage block, but it is not limited to this. Further, as shown in FIG. 2 , each page 133 has a plurality of storage elements 134 electrically connected to the control unit 11 . Specifically, each storage device 134 is a floating gate transistor, and, depending on the data storage technology used in each page 133 (such as SLC technology, MLC technology, TLC technology or QLC technology), the data in the page 133 Each storage element 134 may be used to store one, two, three or four bits of data.

It should be added that each page 133 refers to the smallest unit of data read/written in the first storage part 131 and the second storage part 132, and the storage capacity size of each page 133 can be, for example, 2KB or 4KB. , 8KB or 16KB. In other words, for each page 133 , the control unit 11 can only read or write data to all the storage elements 134 of the page 133 , but cannot only read or write data to a part of the storage elements 134 of the page 133 . to read or write.

In this embodiment, the first storage part 131 is a storage area implemented using SLC technology in the main storage unit 13, and the second storage part 132 is a storage area implemented using TLC technology. In other words, in this embodiment, each storage element 134 in the first storage part 131 is used to store a single bit of data, and each storage element 134 in the second storage part 132 is used to store Store three bits of data. However, in other embodiments, the second storage part 132 may also be a storage area implemented using MLC or QLC technology. In short, the second storage part 132 can enable each storage element 134 to store multiple The bit data storage area can be implemented, so the actual implementation is not limited to this embodiment.

Furthermore, in this embodiment, the arrangement positions of the first storage part 131 and the second storage part 132 in the main storage unit 13 are predetermined and fixed. In other words, the first storage part 131 and the second storage part 132 are fixed storage areas that are preconfigured in the main storage unit 13 . In addition, the storage space ratio of the first storage part 131 and the second storage part 132 may be, for example, one to four. However, it should be understood that the ratio of the two storage spaces may be freely determined based on different cost considerations or other requirements. Adjustment is not particularly limited in this embodiment.

The following describes the operation mode of the data storage device 1 of this embodiment.

First, when the control unit 11 receives a data to be stored in the data storage device 1 via the computer component 5, the control unit 11 determines the storage capacity of each page 133 (for example, but not limited to 4KB). ) perform file division on the data to be stored to convert the data to be stored into multiple data parts that can jointly constitute the data to be stored, and temporarily store all or part of the data parts in the buffer storage unit 12 . It should be added that if the file size of the entire data to be stored does not reach the storage capacity of a single page 133, the control unit 11 will treat the entire data to be stored as a single data part.

After the control unit 11 temporarily stores the data portions in the buffer storage unit 12 , the control unit 11 performs a writing process for each data portion in the buffer storage unit 12 . Specifically, the way the control unit 11 performs the writing process for each data part is to determine whether the data size of the data part reaches a predetermined size, and the predetermined size is equal to a single page 133 in this embodiment. The size of the storage capacity (such as but not limited to 4KB). Therefore, in this embodiment, the control unit 11 is equivalent to determining whether the data part can just fill a blank page 133.

If the control unit 11 determines that the data size of the data part does not reach the predetermined size (that is, the judgment result is no), the control unit 11 writes the data part from the buffer storage unit 12 in a first writing mode. to one of the pages 133 with sufficient remaining capacity in the first storage part 131 . Specifically, the first writing mode in this embodiment is an SLC writing mode, which enables a single storage element 134 in the first storage part 131 to store a single bit of data. In other words, in this embodiment, if the control unit 11 determines that the data size of the data part is not enough to fill a blank page 133, the control unit 11 will adopt the SLC writing mode with a relatively fast writing speed. , and the data part is written into one of the pages 133 in the first storage part 131, so that the data part is transferred from the buffer storage unit 12 to the first storage part 131 implemented with SLC technology for storage. .

On the other hand, if the control unit 11 determines that the data size of the data part has reached the predetermined size (that is, the judgment result is yes), the control unit 11 writes the data part from the buffer storage unit in a second writing mode. 12 is written "directly" to one of the empty pages 133 in the second storage portion 132. Specifically, the second writing mode in this embodiment is a TLC writing mode, which enables a single storage element 134 in the second storage part 132 to store three bits of data. In other words, if the control unit 11 determines that the data size of the data part is enough to fill a blank page 133, the control unit 11 will use the TLC writing mode with relatively high data storage density to write the data part into In one of the pages 133 in the second storage part 132, the data part is directly transferred from the buffer storage unit 12 to the second storage part 132 implemented with TLC technology for storage.

It is particularly emphasized that once the control unit 11 determines that the data size of the data part reaches the predetermined size, the control unit 11 will "directly" transfer the data part from the buffer storage unit 12 to the second storage part 132 Instead of first transferring the data part from the buffer storage unit 12 to the first storage part 131 for storage, and then transferring the data part from the first storage part 131 to the second storage part 132 for storage. Thereby, this embodiment can save the extra time required to "indirectly" transfer the data part from the buffer storage unit 12 to the second storage part 132 for storage. Therefore, this embodiment can The writing operation of transferring the data part from the buffer storage unit 12 to the second storage part 132 is completed with a relatively shorter overall processing time and less workload, while avoiding the problems caused by the "indirect" transfer method. Latency, therefore, this embodiment has excellent stability and performance, and can slow down the wear and tear of the first storage part 131 caused by being read and written.

It should be added that in other embodiments, the second writing mode can also be an MLC writing mode or a QLC writing mode. In short, the second writing mode can only enable a single storage element 134 to store The writing mode of multiple bits of data can be implemented and is not limited to this embodiment.

After the control unit 11 writes each data part into one of the first storage part 131 and the second storage part 132 (equivalent to writing the data to be stored into the main storage unit 13 for storage), The control unit 11 determines whether there is one or more full pages 133' in which the size of one or more stored data has reached a preset size among the pages 133 of the first storage part 131 (exemplarily shown in FIG. 1 The default size may be, for example, consistent with the storage capacity of a single page 133 (such as but not limited to 4KB), but may also be slightly smaller than the storage capacity of a single page 133 , such as but not limited to Limited to ninety-five percent of its storage capacity, in other words, the preset size may be equal to or slightly smaller than the aforementioned predetermined size. Moreover, when the control unit 11 determines that there is indeed a full page 133' in the pages 133 of the first storage part 131 (that is, the judgment result is yes), the control unit 11 saves each full page 133'. The data in the full page 133' is transferred from the full page 133' to one of the blank pages 133 of the second storage part 132 in the second writing mode, that is, the data in the full page 133' is transferred from the first storage part 131 is transferred to the second storage part 132 for storage, thereby freeing up the available storage space of the first storage part 131.

The above is an example description of the operation mode of this embodiment.

To sum up, the control unit 11 of the data storage device 1 can decide to write the data part to the third data part in the faster first writing mode based on whether the data size of each data part reaches a predetermined size. To store a storage part 131, it is still necessary to write the data part to the second storage part 132 for storage in the second writing mode with higher data storage density, that is, the storage mode and storage area are determined according to the size of the data part. , thereby, the data storage device 1 helps to achieve a better balance between access speed and cost, and also has excellent stability and performance, so it can indeed achieve the purpose of the present invention.

However, the above are only examples of the present invention, and should not be used to limit the scope of the present invention. All simple equivalent changes and modifications made based on the patent scope of the present invention and the content of the patent specification are still within the scope of the present invention. Within the scope covered by this new patent.

1: Data storage device 11:Control unit 12: Buffer storage unit 13:Main storage unit 131: First storage part 132: Second storage part 133:Page 133’: Pagination is full 134:Storage component 5:Computer components

Other features and functions of the present invention will be clearly presented in the embodiments with reference to the drawings, in which: Figure 1 is a block schematic diagram schematically showing an embodiment of the new data storage device and a computer component suitable for use in conjunction with the embodiment; and FIG. 2 is an incomplete schematic diagram illustrating a page included in this embodiment and a plurality of storage elements included therein.

1: Data storage device

11:Control unit

12: Buffer storage unit

13:Main storage unit

131: First storage part

132: Second storage part

133:Page

133’: Pagination is full

5:Computer components

Claims (3)

A data storage device suitable for electrical connection with a computer component; the data storage device includes: a control unit; a buffer storage unit electrically connected to the control unit; and A main storage unit includes a first storage part electrically connected to the control unit, and a second storage part electrically connected to the control unit, wherein the first storage part and the second storage part each have a plurality of pages, And each page has a plurality of storage elements electrically connected to the control unit; When the control unit receives a data to be stored to be stored through the computer component, the control unit converts the data to be stored into one or more data parts that are temporarily stored in the buffer storage unit, and for each The data part performs a write process, wherein the control unit performs the write process on each data part including: judging whether the data size of the data part reaches a predetermined size, and when the judgment result is no, use a first A write mode is used to write the data portion from the buffer storage unit to one of the pages in the first storage portion. When the determination result is yes, a second write mode is used to write the data portion from the buffer storage unit. Write directly to one of the pages in the second storage part, wherein the first writing mode enables a single storage element in the first storage part to store a single bit of data, and the second writing mode A single storage element in the second storage part can store multiple bits of data. The data storage device as claimed in claim 1, wherein the control unit is also used to determine whether there is a full page in which the size of the stored data reaches a preset size in the pages of the first storage part, And when the judgment result is yes, the data in the full page is transferred from the full page to one of the pages in the second storage part in the second writing mode, and the default size is equal to or smaller than the predetermined size. The data storage device as claimed in claim 1, wherein the arrangement positions of the first storage part and the second storage part in the main storage unit are predetermined and fixed.

Images