[go: up one dir, main page]

CN1308836C - Method and system for data storage - Google Patents

Method and system for data storage Download PDF

Info

Publication number
CN1308836C
CN1308836C CNB031370071A CN03137007A CN1308836C CN 1308836 C CN1308836 C CN 1308836C CN B031370071 A CNB031370071 A CN B031370071A CN 03137007 A CN03137007 A CN 03137007A CN 1308836 C CN1308836 C CN 1308836C
Authority
CN
China
Prior art keywords
memory block
memory
file
block
storage space
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
CNB031370071A
Other languages
Chinese (zh)
Other versions
CN1553342A (en
Inventor
郑吉智
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Accton Technology Corp
Original Assignee
Accton Technology Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Accton Technology Corp filed Critical Accton Technology Corp
Priority to CNB031370071A priority Critical patent/CN1308836C/en
Publication of CN1553342A publication Critical patent/CN1553342A/en
Application granted granted Critical
Publication of CN1308836C publication Critical patent/CN1308836C/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Images

Landscapes

  • Memory System (AREA)
  • Read Only Memory (AREA)

Abstract

The invention provides a method and a system for storing a file in a memory with block writing characteristics, wherein when the file is to be stored in the memory, the method mainly comprises the following steps: comparing the file with the size of the free storage space of each memory block in the memory to select an optimal memory block from the memory blocks with the free storage space; storing the data unit of the file corresponding to the storage space of the optimal memory block into the optimal memory block; and if the data unit still remains in the file after the data unit is stored, repeating the steps until the file is completely stored in the memory.

Description

The method and system of data storing
Technical field
The present invention relates to a kind of method and system of data storing, relate in particular to a kind of method and system that a file division can be become a plurality of data cells with storage this document.
Background technology
In each assembly of computer system, be used for the memory bank (Storage Device) of storage data always for a very important field.Generally speaking, memory bank can be divided into two big classifications, i.e. volatile storage body (Volatile Storage Device) and non-volatile memory body (Non-Volatile Storage Device).The so-called volatile storage body i.e. interior stored data of this memory bank can run off gradually along with the time, if and the power supply supply of this memory bank cut off, then be stored in wherein data with complete obiteration, and its benefit is that access speed is fast, for example (Dynamic Random Access Memory DRAM) promptly belongs to this class component to dynamic RAM; On the contrary; the so-called non-volatile memory body i.e. interior stored data of this memory bank can't run off along with the time; these data also can persist in this memory bank under the situation of supply of cutting off the electricity supply simultaneously; so even non-volatile memory body occupies crucial role having in the application that need still can keep data content under the situation that the power supply supply is cut off; it is very slow with respect to DRAM that yet its shortcoming is an access speed; flash memory (Flash Memory) for example, assemblies such as Winchester disk drive and floppy drive all belong to this class component.And be non-volatile storage body equally, be compared to the characteristic that needs at a large amount of storage areas as Winchester disk drive, and the convenient characteristic of carrying of floppy drive, flash memory then possesses smaller volume and access speed is faster arranged comparatively speaking, thus its extremely be suitable for as in the hub products such as (Switch Hub) to the application of non-volatile memory body.
Flash memory is a kind of memory storage that possesses the block write diagnostics, so-called block writes, meaning i.e. storage area in this memory bank is the block (it has some kinds of different sizes) of a plurality of regular lengths, and when a file is written into this memory bank, must be that unit cuts apart and stores with the block, this kind storage characteristics has caused if a block has been utilized to storage data, even still there is the storage area that is not utilized in this block, it is with other storage applications of unrenewable work, and this is the restriction in the sky earlier of this type of memory storage.In the prior art, the data storing of flash memory, be to take mode that the physical holding of the stock address is deposited in continuously, for instance, please refer to Fig. 1, Fig. 1 is the synoptic diagram that the flash memory 10 of prior art stores a file 20, wherein flash memory 10 has the part block to be used in storage data, in the time of now will depositing in file 20 in the flash memory 10, next idle block 12a of physical holding of the stock address in flash memory 10 then, in regular turn file 20 is deposited in continuously by divided data unit 22 in the block 12 of flash memory 10, till file 20 is all deposited in.Please note the end data unit 22a that file 20 deposits at last, because the size of generic-document is not to be a fixed value, so when file 20 is cut apart according to the size of the block 12 of use flash memory 10, it is cut apart the size of remaining end data unit 22a at last, usually can not conform to the block 12b size that it will deposit in, under this shape, because the block write diagnostics of flash memory 10, must having partly among the block 12b, the storage area is the idle storage that but can't be used for any data.
Yet the flash memory of above-mentioned prior art but has following several desirable not to the utmost parts: the flash memory of prior art read and write fashionable, all the physical holding of the stock address with each block of this flash memory is an index, though this access mode is direct, but but cause it portable poor often, because its storage area of the flash memory of different labels or different model quantity and address configuration big or small and wherein each block are all inequality, so when a computer system will be used flash memories of different types, must manage the modification of program at the flash memory of each type again, this can increase the cost of software maintenance; The flash memory of prior art deposit characteristic continuously in, can be because the existence in flash memory gap (Fragmentation), and cause the waste of storage area, so-called gap, promptly a flash memory is after using a period of time, because the continuous action that writes and delete, cause between its idle block discontinuous situation more and more frequent, be that its idle block can be utilized block to be divided into several sections and is not continuous state, at this moment, even one wants the size of store files littler than the size sum total of this section intra block, and this document will cause storing failure because continuous storage area is not enough, thisly having enough idle spaces but because of the discontinuous situation that can't store, is the waste of kind of storage area; In addition, the flash memory of prior art is according to the principle that deposits in continuously, and none storage block is chosen rule, this can cause the irrational use of block, this flash memory 10 with the prior art among Fig. 1 is an example, wherein if end data unit 22a is a string very short data, and its block 12b that just deposits the principle configuration continuously in is 10 fens big blocks, this will cause block 12b after storing end data unit 22a, stay a part of very large idle space but because of the block write diagnostics can't be utilized, thereby form waste; At last, because the flash memory of prior art all begins to seek idle continuous block from the start address of this flash memory and carries out the storage of data, this can cause partly specific block to write the indegree accumulation be many than other block, and each block in flash memory, it all has a maximum assurance effectively to write time numerical value, if after the writing indegree and reach this value an of block, its probability that breaks down will heighten, if so the part particular block reaches this value earlier than other block in the flash memory, and can't will always write the indegree mean allocation to each block, this will cause the shortening of this flash memory life, and increase user's cost.
In summary, the flash memory of prior art on reality is used, obviously exists inconvenience and defective, so be necessary to be improved.
Summary of the invention
At above-mentioned defective, purpose of the present invention is to provide a kind of method and system of data storage, to realize more reasonable use storage resources.
To achieve these goals, the invention provides a kind of method of data storing, it is used for a file is stored in the storer, this storer includes a plurality of memory blocks, and when this document is stored in this storer, must be unit with these memory blocks, this method mainly comprises the following step: compare the size of the idle storage area of each memory block in this document and this storer, to choose the suitableeest memory block from the memory block of the idle storage area of these tools; Store in this document corresponding to this data cell of the storage area of suitable memory block to this suitableeest memory block; And, then repeat above-mentioned steps, till this document is stored in this storer fully if still have the remaining storage data unit for the treatment of in this document after this data cell of storage.
The present invention also provides a kind of data storage system, comprises: a storer, and it has the block write diagnostics; One file system builds on the driver module of this storer, and a block arrangement method is provided, and when a file is stored in this storer, carries out the configuration of more efficient storage area.
The present invention utilizes the method for an optimized idle memory configurations and the design of one or two hierarchical data structures, make a file system when store files, carry out the configuration of more efficient storage area, to reach the purpose of more reasonable use storage resources to a memory storage that possesses the block write diagnostics.
Brief Description Of Drawings
Below in conjunction with accompanying drawing,, will make technical scheme of the present invention and other beneficial effects apparent by detailed description to embodiments of the invention.
Fig. 1 is the synoptic diagram of flash memory stores one file of prior art;
Fig. 2 is a system block diagrams of the present invention;
Fig. 3 is the system block diagrams of one embodiment of the invention;
The synoptic diagram that Fig. 4 understands for preliminary sweep;
Fig. 5 is the block arrangement method flow diagram;
Fig. 6 is the suitableeest block choosing method process flow diagram;
Fig. 7 is the synoptic diagram of idle block sequence.
Embodiment
Please refer to Fig. 2, show system of the present invention 30 calcspars among Fig. 2.The present invention sets up a file system 32 with data structure of two levels on the driver module of the storer 38 with block write diagnostics, according to the best configuration method one file is stored in this storer 38.This storer 38 includes a plurality of memory blocks 46, and when this document is stored in the storer 38, must be unit with memory block 46, wherein this document system 32 is mainly according to following steps access memory 38: relatively have the size of each memory block 46 of idle storage area in this document and the storer 38, to choose the suitableeest memory block in these memory blocks 46; Store this document corresponding to this data cell of the storage area of suitable memory block to this suitableeest memory block; And, if still have the remaining storage data unit for the treatment of in this document after this data cell of storage, then repeat above-mentioned steps, till this document is stored in this storer 38 fully.
Please refer to Fig. 3, show the system block diagrams of one embodiment of the invention among Fig. 3.In Fig. 3, be used for storing a file to storer 38,38 of this storeies are one to possess the memory storage of block write diagnostics, so include a plurality of memory blocks 46 (it has some kinds of different sizes), be used for storing the data cell that this document is produced after cutting apart, and this storer also includes a driver module (Driver) (not being shown among Fig. 3), and it is used for the action that the information that comprised according to file system 32 reads, writes and delete the memory block 46 of storer 38; And this document system 32 includes the data structure of two levels, comprise: an accumulation layer (Storage Layer) 42 and one file layers (File Layer) 44, wherein accumulation layer 42 provides the best configuration logical operation to select the suitableeest storer 38 block store files according to the idle block management principle of first in first out, and actual initial, end position and the size that corresponds to storer 38 of record data block 48; 44 of file layers are used for writing down the selected block 48 of each data cell of this document corresponding to this document.Can be used in the various computing machine Related products that include tool block write diagnostics storer, for example hub, graphic display card etc. in the system shown in Fig. 3 30; And the storer 38 of this tool block write diagnostics is generally a flash memory, but other storer with identical characteristics belongs to covering scope of the present invention equally.
As shown in Figure 3, when native system will be with a file write store 38, file system 32 can be chosen the suitable memory block 46 that stores the storer 38 of this document according to the best configuration method and store this document, file system 32 is chosen the memory block 46 of the storer 38 that is used to store this document, be the 4th in regular turn, 5,10,9 and 6 memory block 46, and in the block 48 of accumulation layer 42 record actual corresponding to the initial of those memory blocks, end position and size, simultaneously that this document is stored block 48 numbers and attribute log are in file layers 44.As mentioned above, can finish the write activity of this document; Similarly, in the time will in storer 38, reading out this document, this document system 32 can choose block 48 in the accumulation layer 42 according to the information in the file layers 44 of being recorded in, control this driver module the memory block 46 that corresponds to the storer 38 that is selected block 48 is read, and this data cell is docile and obedient the preface merging with reduction this document.As mentioned above, can finish the action of reading of this document; And when will be in storer 38 this document being deleted, this document system 32 can choose block 48 in the accumulation layer 42 according to the information in the file layers 44 of being recorded in, control this driver module the memory block 46 that corresponds to the storer 38 that is selected block 48 is deleted, and then the relevant information that will be recorded in the file layers 44 is removed.As mentioned above, can finish the deletion action of this document.
Under general situation, store a file to storer 38 time, computer system includes a volatile storage in addition and is used for all relevant informations in the above-mentioned data structure (comprising accumulation layer 42 and file layers 44) all are stored in this volatile storage for the processor use, to guarantee its execution speed.Yet, when computer system after losing power supply supply (for example shutdown), all data that are stored in this volatile storage will not exist, therefore when computer system when activating again, can do preliminary sweep to storer 38 and understand (Parsing), in this volatile storage, to rebulid the related administrative information of file layers 44 and accumulation layer 42, wherein this volatile storage is generally a dynamic RAM (DRAM), and this non-volatility memorizer can be a flash memory, please refer to Fig. 4, Fig. 4 is each memory block 46 in the use storer 38 of the present invention is understood employed non-volatility memorizer as preliminary sweep a embodiment, wherein a part of storage area in each memory block 46 is used for storing a preliminary sweep that is relevant to this document and points to its next memory block 46 etc. and separates read message 50, and in Fig. 4, show ground connection memory block 46 expressions its for storing end block of this document.Owing to be stored in the non-volatility memorizer, preliminary sweep is separated read message 50 and can't just be vanished from sight after losing the power supply supply, and when opening computer system, processor can utilize preliminary sweep to separate read message 50 and again this data structure information be built on the performance property storer next time.The above is preferred embodiment of the present invention, and other different application that can reach identical purpose is similarly institute of the present invention covering scope.
When utilizing file system 32 of the present invention to store a file, a certain ad hoc approach of foundation is chosen the memory block 46 of the suitableeest storage this document, and this method is that a best configuration method and this method are contained in the accumulation layer 42.Please refer to Fig. 5, Fig. 6 and Fig. 7, it is an embodiment of this method, wherein includes a block arrangement method 60 (as shown in Figure 5), the suitableeest block choosing method 70 (as shown in Figure 6), and an idle block sequence 80 (as shown in Figure 7).Idle block sequence 80 among Fig. 7 is the memory blocks 46 that have idle storage area in the storer 38, according to first in first out (First-In-First-Out, FIFO) principle, the sequence of array data block in regular turn, that is to say, a memory block 46a who enters idle state recently will be arranged in the last cis-position of idle block sequence 80 (the memory block 46a that promptly shows ground connection in Fig. 7, it is the end block of idle block sequence 80); And the block arrangement method 60 among Fig. 4 comprises the following step:
Step 61: beginning block arrangement method 60;
Step 62: the size of this document is made as a surplus value;
Step 63: check that whether this surplus value is greater than zero.If then execution in step 64, if not, then execution in step 66;
Step 64: carry out this suitableeest block choosing method 70 to choose the suitableeest memory block;
Step 65: store this document in this suitableeest memory block, simultaneously the size of this document is deducted this size of suitable memory block, and upgrade idle block sequence 80.Continue execution in step 62;
Step 66: finish block collocation method 60.
That is to say, when storing a file, then enter the program of block arrangement method 60, at first check the data cell whether this document remains to be stored, if having, then choose the suitableeest memory block according to the suitableeest block choosing method 70, and this document is stored in this suitableeest memory block, and upgrade idle block sequence 80, after the storage, if still remain the data cell that stores in this document, then repeat above-mentioned steps till whole file is stored in the memory bank 38.The suitableeest block choosing method 70 among Fig. 6 with the size of this document one by one with idle block sequence 80 in idle memory block 46 compare, it comprises the following step:
Step 71: begin the suitableeest block choosing method 70;
Step 72: set the initial value of suitable memory block size, and the block that enters idle state in the block sequence 80 of will leaving unused the earliest is made as present block;
Step 73: check whether this present block is an end block.If then execution in step 79, if not, then execution in step 74;
Step 74: whether the size of checking this present block is more than or equal to this surplus value.If then execution in step 75, if not, then execution in step 76;
Step 75: check this at present the size of suitable memory block whether less than this surplus value or greater than the size of this present block.If then execution in step 77, if not, then execution in step 78;
Step 76: check this at present the size of suitable memory block whether less than the size of this present block.If then execution in step 77, if not, then execution in step 78;
Step 77: this present block is made as the suitableeest new memory block;
Step 78: next idle block becomes a new present block in the idle block sequence 80.Continue execution in step 73;
Step 79: finish the suitableeest block choosing method 70.
That is to say that if the length of at least one idle memory block 46 is then chosen the length minimum more than or equal to the length of this document in those memory blocks 46, idle person at most stores this document; If the length of those idle memory blocks 46, is then chosen the length maximum less than the length of this document in those memory blocks 46 and idle person at most stores the data cell that this document splits.The above is the preferred embodiment of this certain rule, and other different application that can reach identical purpose is similarly institute of the present invention covering scope.
That is to say that method of the present invention comprises following steps: compare the size of the idle storage area of each memory block in this document and this storer, from the memory block of the idle storage area of these tools, to choose the suitableeest memory block; Store this document corresponding to this data cell of the storage area of suitable memory block to this suitableeest memory block; And, then repeat above-mentioned steps, till this document is stored in this storer fully if still have the remaining storage data unit for the treatment of in this document after this data cell of storage.
Compared to existing storing technology is the index and the characteristic of coming storage data with continuous block configuration mode with the physical holding of the stock address directly, and the present invention has good, the discontinuous block arrangement mode of software portability to be increased memory bank and use elasticity, use the advantages such as life-span of the suitableeest block choosing method to avoid unreasonable configuration to cause the idle block management rule of waste and first in first out to prolong the global storage body.
Be understandable that; for the person of ordinary skill of the art; can make other various corresponding changes and distortion according to technical scheme of the present invention and technical conceive, and all these changes and distortion all should belong to the protection domain of accompanying Claim of the present invention.

Claims (9)

1.一种数据储存的方法,其用来将一文件储存于一具有区块写入特性的存储器中,其特征在于,该方法包含下列步骤:1. A method for data storage, which is used to store a file in a memory with block write characteristics, characterized in that the method comprises the following steps: 比较该文件与该存储器中每一存储器区块闲置储存空间的大小,以从这些具闲置储存空间的存储器区块中选取一最适存储器区块;comparing the file with the size of free storage space of each memory block in the memory, so as to select an optimal memory block from the memory blocks with free storage space; 储存该文件对应于该最适存储器区块的储存空间的数据单元至该最适存储器区块中;以及storing the data unit of the file corresponding to the storage space of the optimal memory block into the optimal memory block; and 若储存该数据单元后该文件中仍有剩余的待储存数据单元,则重复上述步骤,直到该文件完全被储存于该存储器中为止。If there are still remaining data units to be stored in the file after storing the data unit, then repeat the above steps until the file is completely stored in the memory. 2.根据权利要求1所述的数据存储的方法,其特征在于,最适存储器区块的选取包含下列步骤:2. The method for data storage according to claim 1, wherein the selection of the most suitable memory block comprises the following steps: 设定最适存储器区块大小的初始值;setting the initial value of the optimal memory block size; 依据先进先出的顺序从该存储器区块中选取一具有闲置储存空间的存储器区块;selecting a memory block with idle storage space from the memory blocks according to a first-in-first-out order; 比较该被选取的存储器区块、目前最适存储器区块及该文件的大小,当该被选取的存储器区块大于或等于该文件,且目前最适的存储器区块小于该文件或大于该被选取的存储器区块时,则该被选取的存储器区块取代目前最适存储器区块成为新的最适存储器区块;及Comparing the selected memory block, the current optimal memory block and the size of the file, when the selected memory block is larger than or equal to the file, and the current optimal memory block is smaller than the file or larger than the selected When selecting a memory block, the selected memory block replaces the current optimum memory block to become a new optimum memory block; and 重复上述选取及比较步骤,直到该存储器区块中每一具有闲置储存空间的存储器区块完全被选取并比较后为止。The above steps of selecting and comparing are repeated until each memory block with free storage space in the memory block is completely selected and compared. 3.根据权利要求1所述的数据存储的方法,其特征在于,最适存储器区块的选取包含下列步骤:3. The method for data storage according to claim 1, wherein the selection of the most suitable memory block comprises the following steps: 设定最适存储器区块大小的初始值;setting the initial value of the optimal memory block size; 依据先进先出的顺序从该存储器区块中选取一具有闲置储存空间的存储器区块;selecting a memory block with idle storage space from the memory blocks according to a first-in-first-out order; 比较该被选取的存储器区块、目前最适存储器区块及该文件的大小,当该被选取的存储器区块小于该文件,且目前最适的存储器区块小于该被选取的存储器区块时,则该被选取的存储器区块取代目前最适存储器区块成为新的最适存储器区块;及Comparing the selected memory block, the current optimum memory block and the size of the file, when the selected memory block is smaller than the file, and the current optimum memory block is smaller than the selected memory block , then the selected memory block replaces the current optimum memory block to become a new optimum memory block; and 重复上述选取及比较步骤,直到该存储器区块中每一具有闲置储存空间的存储器区块完全被选取并比较后为止。The above steps of selecting and comparing are repeated until each memory block with free storage space in the memory block is completely selected and compared. 4.根据权利要求1所述的数据存储的方法,其特征在于,该存储器为一闪存。4. The data storage method according to claim 1, wherein the memory is a flash memory. 5.一种数据储存系统,其特征在于,包含:5. A data storage system, characterized in that it comprises: 一存储器,其具有区块写入特性;及a memory with block write characteristics; and 一文件系统,建立于该存储器的驱动模块上,提供一区块配置方法,于一文件储存于该存储器时,进行更有效率的储存空间配置;A file system, established on the drive module of the memory, provides a block allocation method for more efficient storage space allocation when a file is stored in the memory; 该区块配置方法,主要包含下列步骤:The block configuration method mainly includes the following steps: 比较该文件与该存储器中每一存储器区块闲置储存空间的大小,以从该具闲置储存空间的存储器区块中选取一最适存储器区块;comparing the file with the size of free storage space of each memory block in the memory, so as to select an optimal memory block from the memory blocks with free storage space; 储存该文件对应于该最适存储器区块的储存空间的数据单元至该最适存储器区块中;以及storing the data unit of the file corresponding to the storage space of the optimal memory block into the optimal memory block; and 若储存该数据单元后该文件中仍有剩余的待储存数据单元,则重复上述步骤,直到该文件完全被储存于该存储器中为止。If there are still remaining data units to be stored in the file after storing the data unit, then repeat the above steps until the file is completely stored in the memory. 6.根据权利要求5所述的数据存储的系统,其特征在于,该文件系统包含一存储层及一文件层,该存储层包含有多个数据区块,每一数据区块对应于该存储器的一存储器区块,并记录实际对应到该存储器区块的起始、结束位置及大小,该文件层用来记录该文件的各个数据单元所选取的数据区块。6. The data storage system according to claim 5, wherein the file system includes a storage layer and a file layer, the storage layer includes a plurality of data blocks, and each data block corresponds to the memory a memory block, and record the start and end positions and sizes actually corresponding to the memory block, and the file layer is used to record the data blocks selected by each data unit of the file. 7.据权利要求5所述的数据存储的系统,其特征在于,最适存储器区块的选取包含下列步骤:7. The data storage system according to claim 5, wherein the selection of the most suitable memory block comprises the following steps: 设定最适存储器区块大小的初始值;setting the initial value of the optimal memory block size; 依据先进先出的顺序从该存储器区块中选取一具有闲置储存空间的存储器区块;selecting a memory block with idle storage space from the memory blocks according to a first-in-first-out order; 比较该被选取的存储器区块、目前最适存储器区块及该文件的大小,当该被选取的存储器区块大于或等于该文件,且目前最适的存储器区块小于该文件或大于该被选取的存储器区块时,则该被选取的存储器区块取代目前最适存储器区块成为新的最适存储器区块;及Comparing the selected memory block, the current optimal memory block and the size of the file, when the selected memory block is larger than or equal to the file, and the current optimal memory block is smaller than the file or larger than the selected When selecting a memory block, the selected memory block replaces the current optimum memory block to become a new optimum memory block; and 重复上述选取及比较步骤,直到该存储器区块中每一具有闲置储存空间的存储器区块完全被选取并比较后为止。The above steps of selecting and comparing are repeated until each memory block with free storage space in the memory block is completely selected and compared. 8.根据权利要求5所述的数据存储的系统,其特征在于,最适存储器区块的选取包含下列步骤:8. The data storage system according to claim 5, wherein the selection of the most suitable memory block comprises the following steps: 设定最适存储器区块大小的初始值;setting the initial value of the optimal memory block size; 依据先进先出的顺序从该存储器区块中选取一具有闲置储存空间的存储器区块;selecting a memory block with idle storage space from the memory blocks according to a first-in-first-out order; 比较该被选取的存储器区块、目前最适存储器区块及该文件的大小,当该被选取的存储器区块小于该文件,且目前最适的存储器区块小于该被选取的存储器区块时,则该被选取的存储器区块取代目前最适存储器区块成为新的最适存储器区块;及Comparing the selected memory block, the current optimum memory block and the size of the file, when the selected memory block is smaller than the file, and the current optimum memory block is smaller than the selected memory block , then the selected memory block replaces the current optimum memory block to become a new optimum memory block; and 重复上述选取及比较步骤,直到该存储器区块中每一具有闲置储存空间的存储器区块完全被选取并比较后为止。The above steps of selecting and comparing are repeated until each memory block with free storage space in the memory block is completely selected and compared. 9.根据权利要求5所述的数据存储的系统,其特征在于,该具有区块写入特性的存储器为一闪存。9 . The data storage system according to claim 5 , wherein the memory with block write feature is a flash memory.
CNB031370071A 2003-05-27 2003-05-27 Method and system for data storage Expired - Fee Related CN1308836C (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CNB031370071A CN1308836C (en) 2003-05-27 2003-05-27 Method and system for data storage

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CNB031370071A CN1308836C (en) 2003-05-27 2003-05-27 Method and system for data storage

Publications (2)

Publication Number Publication Date
CN1553342A CN1553342A (en) 2004-12-08
CN1308836C true CN1308836C (en) 2007-04-04

Family

ID=34323478

Family Applications (1)

Application Number Title Priority Date Filing Date
CNB031370071A Expired - Fee Related CN1308836C (en) 2003-05-27 2003-05-27 Method and system for data storage

Country Status (1)

Country Link
CN (1) CN1308836C (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7685398B2 (en) * 2006-05-18 2010-03-23 Dell Products L.P. Intelligent system for determination of optimal partition size in a build to order environment
CN102867002A (en) * 2011-07-05 2013-01-09 北大方正集团有限公司 Method and device for processing electronic files
CN108959517B (en) * 2018-06-28 2021-06-01 河南思维轨道交通技术研究院有限公司 File management method and device and electronic equipment
TWI710905B (en) * 2019-05-06 2020-11-21 慧榮科技股份有限公司 Data storage device and method for loading logical-to-physical mapping table
TWI695264B (en) * 2019-05-20 2020-06-01 慧榮科技股份有限公司 A data storage device and a data processing method

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5784698A (en) * 1995-12-05 1998-07-21 International Business Machines Corporation Dynamic memory allocation that enalbes efficient use of buffer pool memory segments
US6105024A (en) * 1998-02-12 2000-08-15 Microsoft Corporation System for memory management during run formation for external sorting in database system
WO2002017057A2 (en) * 2000-08-18 2002-02-28 Network Appliance, Inc. Improved space allocation in a write anywhere file system
CN1409519A (en) * 2001-09-18 2003-04-09 深圳市中兴通讯股份有限公司上海第二研究所 Dynamic storage management method for cell header conversion table

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5784698A (en) * 1995-12-05 1998-07-21 International Business Machines Corporation Dynamic memory allocation that enalbes efficient use of buffer pool memory segments
US6105024A (en) * 1998-02-12 2000-08-15 Microsoft Corporation System for memory management during run formation for external sorting in database system
WO2002017057A2 (en) * 2000-08-18 2002-02-28 Network Appliance, Inc. Improved space allocation in a write anywhere file system
CN1409519A (en) * 2001-09-18 2003-04-09 深圳市中兴通讯股份有限公司上海第二研究所 Dynamic storage management method for cell header conversion table

Also Published As

Publication number Publication date
CN1553342A (en) 2004-12-08

Similar Documents

Publication Publication Date Title
US7769945B2 (en) Method and system for facilitating fast wake-up of a flash memory system
US7562202B2 (en) Systems, methods, computer readable medium and apparatus for memory management using NVRAM
US7792882B2 (en) Method and system for block allocation for hybrid drives
US8090924B2 (en) Method for the allocation of data on physical media by a file system which optimizes power consumption
CN108628542B (en) A file merging method and controller
US20070094445A1 (en) Method to enable fast disk caching and efficient operations on solid state disks
CN113626431A (en) LSM tree-based key value separation storage method and system for delaying garbage recovery
CN103440207A (en) Caching method and caching device
KR20100065786A (en) Cache synchronization method and system for fast power-off
CN107817945B (en) A data reading method and system of a hybrid memory structure
CN114356877A (en) A log structure merge tree hierarchical storage method and system based on persistent memory
CN114185492A (en) Solid state disk garbage recycling algorithm based on reinforcement learning
CN1308836C (en) Method and system for data storage
CN102955787A (en) Using method for file directory table, file writing method and main circuit board, CPU (central processing unit) and external storage applying same
CN116069252A (en) A control method, device and equipment for ZNS SSD equipment
Cheng et al. Lifespan-based garbage collection to improve SSD's reliability and performance
CN103258044B (en) Two-tuple NANDFLASH data file management method oriented to DSP
CN118778908A (en) A virtual block management method and storage device using the method
CN105630410A (en) Method for dynamically managing file memory area by nonvolatile random access memory chip
TWI724550B (en) Data storage device and non-volatile memory control method
CN105630697B (en) A kind of storage device using MRAM storage small documents
CN105608014B (en) A kind of storage device using MRAM
CN1444133A (en) Information processing device and program
CN110609817A (en) File storage system capable of preventing file fragmentation
US7206893B2 (en) Linking method under mother and child block architecture for building check area and logic page of the child block

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20070404

Termination date: 20160527