CN110389712A - Method for writing data and its device, solid state hard disk and computer readable storage medium - Google Patents
Method for writing data and its device, solid state hard disk and computer readable storage medium Download PDFInfo
- Publication number
- CN110389712A CN110389712A CN201810362066.3A CN201810362066A CN110389712A CN 110389712 A CN110389712 A CN 110389712A CN 201810362066 A CN201810362066 A CN 201810362066A CN 110389712 A CN110389712 A CN 110389712A
- Authority
- CN
- China
- Prior art keywords
- data
- data block
- physical storage
- storage areas
- block
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/0223—User address space allocation, e.g. contiguous or non contiguous base addressing
- G06F12/023—Free address space management
- G06F12/0238—Memory management in non-volatile memory, e.g. resistive RAM or ferroelectric memory
- G06F12/0246—Memory management in non-volatile memory, e.g. resistive RAM or ferroelectric memory in block erasable memory, e.g. flash memory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/0223—User address space allocation, e.g. contiguous or non contiguous base addressing
- G06F12/023—Free address space management
- G06F12/0253—Garbage collection, i.e. reclamation of unreferenced memory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/061—Improving I/O performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0638—Organizing or formatting or addressing of data
- G06F3/064—Management of blocks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0673—Single storage device
- G06F3/0679—Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP]
Abstract
The invention discloses a kind of method for writing data, data transfer apparatus solid state hard disk and computer readable storage mediums, method for writing data is applied to solid state hard disk, the solid state hard disk includes multiple physical storage areas, each physical storage areas includes multiple data blocks, multiple data blocks include storing data block and reserved data block, this method comprises: determining the population size of valid data in each storing data block of the physical storage areas when the reserved data block of at least one in the physical storage areas all writes full data；Judge the storing data block that the quantity in the physical storage areas with the presence or absence of valid data is zero；If so, the total data in the storing data block that the quantity for wiping valid data in the physical storage areas is zero.The writing speed of this method data is very fast, is particularly suitable for field of video monitoring.
Description
Technical field
The present invention relates to technical field of data processing more particularly to method for writing data, data transfer apparatus, solid state hard disks
And computer readable storage medium.
Background technique
Solid-state hard disk SSD (Solid State Drive, abbreviation SSD) is made of solid-state electronic storage chip array
Hard disk.
Solid-state hard disk SSD generally includes multiple logic storage units and physical memory cell, and physical memory cell can be used
Non-volatile memory medium, physical memory cell are generally divided into multiple data blocks for storing data, and client can wrap
Multiple logic storage units are included, the logical address of logic storage unit and the physical address of each data block have mapping relations, come
Logical address and data to be written are carried from the write order at upper-layer client end, it can be in mapping relations according to the logical address
Corresponding physical address is searched, data is written into and is written in data block corresponding with physical address, realizes data write-in.
In order to improve writing speed, physical memory cell is usually divided into multiple channels, each channel includes more
A data block can realize multiple channels and be written in parallel to, and be divided into multiple portions for example, data can be written into and be written every
In the data block in a channel.
For each channel, when the space of data block each in channel write-in data accounts for entire channel memory space (i.e.
Total memory space of all data blocks in the channel) certain proportion when, need to carry out garbage collection operation (Garbage
Collection, abbreviation GC), i.e. valid data in reading section data block, then by the write-in of the valid data monolith of reading its
In his Blank data block, then wipe the valid data data within the data block, the data block can be re-used as blank number
Data are re-write according to block.
Each channel carries out having randomness when data write-in, causes the quantity of the valid data in each channel different, when need
When being written into data and being respectively written into the data block in each channel, some possible channels may need to carry out garbage reclamation behaviour
Make, some channels do not need to carry out garbage collection operation, therefore the data that will cause each channel write-in data are inconsistent, influence to count
According to whole writing speed, the writing speed of data is slower.
Summary of the invention
The present invention provides a kind of method for writing data, data transfer apparatus, solid state hard disk and computer readable storage medium,
To solve deficiency in the related technology.
According to a first aspect of the embodiments of the present invention, a kind of method for writing data is provided, solid state hard disk is applied to, it is described solid
State hard disk includes multiple physical storage areas, and each physical storage areas includes multiple data blocks, and multiple data blocks include storage
Data block and reserved data block；This method comprises:
When the reserved data block of at least one in the physical storage areas all writes full data, determine that the physics is deposited
The population size of valid data in each storing data block in storage area domain；
Judge the storing data block that the quantity in the physical storage areas with the presence or absence of valid data is zero；
If so, the total data in the storing data block that the quantity for wiping valid data in the physical storage areas is zero.
Optionally, further includes:
If judge the storing data block that the quantity in the physical storage areas there is no valid data is zero, read each
Valid data in the part storing data block of the physical storage areas；
It will be where the corresponding storing data block for being written to the reading part valid data of the valid data that read
In the reserved data block of physical storage areas；
Wipe the total data in each part storing data block read.
Optionally, valid data in the part storing data block for reading each physical storage areas, comprising:
It determines that the quantity of valid data in each storing data block of each physical storage areas is the smallest respectively to deposit
Data block is stored up, as source storing data block；
The valid data in each source storing data block are read respectively.
Optionally, in the corresponding storage number for being written to the reading part valid data of the valid data by reading
According in the reserved data block of the physical storage areas where block, before further include:
Judge whether the total quantity of the valid data read is greater than or equal to write-in amount threshold；
If so, executing described correspond to the valid data read is written to depositing for the reading part valid data
Store up the step in the reserved data block of the physical storage areas where data block；
If it is not, then executing the step of valid data in the part storing data block for reading each physical storage areas
Suddenly.
Optionally, the valid data read in each source storing data block respectively, comprising:
The every page data of sequence read in each source storing data block respectively as unit of page；
Judge whether each page data read are valid data；
If so, executing whether the total quantity for judging the valid data read is greater than or equal to write-in amount threshold
The step of；
If it is not, it is every in each source storing data block then to execute reading respectively for the sequence described above as unit of page
The step of page data.
Optionally, the valid data by reading are corresponding is written to the storing data for reading the part valid data
In the reserved data block of physical storage areas where block, comprising:
By depositing where the storing data block of the valid data read the corresponding write-in reading part valid data
In the empty storage space for storing up the reserved data block in chip, after the empty storage space of the reserved data block is write completely, it will remain
Remaining part valid data be written to read the part valid data storing data block where physical storage areas in its
In the reserved data block of his storage chip.
According to a second aspect of the embodiments of the present invention, a kind of data transfer apparatus is provided, solid state hard disk is applied to, it is described solid
State hard disk includes multiple physical storage areas, and each physical storage areas includes multiple data blocks, and multiple data blocks include storage
Data block and reserved data block；The device includes:
Valid data amount determination unit, for when the reserved data block whole of at least one in the physical storage areas
When writing full data, the population size of valid data in each storing data block of the physical storage areas is determined；
Valid data amount judging unit, for judging that the quantity in the physical storage areas with the presence or absence of valid data is zero
Storing data block；
First data wipe unit, for when judging in the physical storage areas there are effective data volume to be zero to deposit
When storing up data block, the total data in storing data block that the quantity for wiping valid data in the physical storage areas is zero.
Optionally, further includes:
Valid data reading unit judges that the quantity in the physical storage areas there is no valid data is zero for working as
Storing data block when, read valid data in the part storing data block of each physical storage areas；
Determination unit is written in valid data, for the corresponding reading part that is written to of the valid data read to have
In the reserved data block for imitating the physical storage areas where the storing data block of data；
Second data wipe unit, for wiping the total data in each part storing data block read.
Optionally, the valid data reading unit is specifically used for:
It determines that the quantity of valid data in each storing data block of each physical storage areas is the smallest respectively to deposit
Data block is stored up, as source storing data block；
The valid data in each source storing data block are read respectively.
Optionally, further includes:
Valid data quantity judging unit is write for judging whether the total quantity of the valid data read is greater than or equal to
Enter amount threshold；
If so, executing described correspond to the valid data read is written to depositing for the reading part valid data
Store up the step in the reserved data block of the physical storage areas where data block；
If it is not, then executing the step of valid data in the part storing data block for reading each physical storage areas
Suddenly.
According to a third aspect of the embodiments of the present invention, a kind of solid state hard disk is provided, including processor, machine readable storage are situated between
Matter and physical storage medium, the physical storage medium include multiple physical storage areas, and each physical storage areas includes more
A data block, multiple data blocks include storing data block and reserved data block, and the machine readable storage medium is stored with can
The machine-executable instruction executed by the processor, the processor are promoted to execute above-mentioned by the machine-executable instruction
One the method.
According to a fourth aspect of the embodiments of the present invention, a kind of computer readable storage medium is provided, calculating is stored thereon with
Machine program realizes any of the above-described the method when described program is executed by processor.
According to the above technical scheme it is found that the method for writing data, when solid state hard disk is dishful state or close to dishful
When state, when the storing data block that the quantity there are valid data is zero, the storing data block is emptied, which makees
For the rewritable write-in data of data block of blank, therefore, there is no need to carry out garbage collection operation, number is written in each physical storage areas
According to speed it is consistent, do not influence the whole writing speed of data, the writing speed of data is very fast.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
It can the limitation present invention.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows and meets implementation of the invention
Example, and be used to explain the principle of the present invention together with specification.
Fig. 1 is the structural schematic diagram of physical memory cell in the solid state hard disk of the relevant technologies offer；
Fig. 2 is the work flow diagram for the method for writing data that an embodiment provides according to the present invention；
Fig. 3 is the configuration diagram for the storage system including solid state hard disk that an embodiment provides according to the present invention；
Fig. 4 is the work flow diagram for the method for writing data that another embodiment provides according to the present invention；
Fig. 5 is the work flow diagram for the method for writing data that another embodiment provides according to the present invention；
Fig. 6 is the work flow diagram for the method for writing data that another embodiment provides according to the present invention；
Fig. 7 is the work flow diagram for the method for writing data that another embodiment provides according to the present invention；
Fig. 8 is that the solid state hard disk that an embodiment provides according to the present invention carries out the structural schematic diagram of garbage collection procedure；
Fig. 9 is the block diagram for the data transfer apparatus that another embodiment provides according to the present invention；
Figure 10 is the hardware structure diagram for the solid state hard disk that an embodiment provides according to the present invention.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistented with the present invention.On the contrary, they be only with it is such as appended
The example of device and method being described in detail in claims, some aspects of the invention are consistent.
The structural schematic diagram of physical memory cell in a kind of solid state hard disk that Fig. 1 provides for the relevant technologies, as shown in Figure 1,
Physical memory cell in the solid state hard disk includes four channels, respectively first passage Channel1, second channel
Channel2, third channel Channel3 and fourth lane Channel4, each channel are logical for example including two data blocks, first
Road includes data block Blocka and data block Blocke, and second channel includes data block Blockb and data block Block f, third
Channel includes data block Block c and data block Block g, and fourth lane includes data block Block d and data block Block
H, the data block in each channel include user data block and garbage reclamation data block, also, each data block can be divided into it is more
A region, the Host Date in each zone user storage user data, such as figure in user data block, garbage reclamation data
Block in garbage collection operation for storing the valid data read from user data block, such as the GC Date in figure.
Physical memory cell can lead to the write order of the user data from upper layer or the write order of garbage collection operation
Cross Host Date or the GC Date carried in write order be respectively written into user data block or garbage reclamation data block in.
The method of above-mentioned data write-in, has the disadvantages that
First, need to judge that the type of write order is the write order of user data or the write order of garbage collection operation,
And then corresponding operation is executed according to the type of write order, which will increase the resource overhead of solid state hard disk；
Second, each channel carries out having randomness when data write-in, causes the quantity of the valid data in each channel different,
Will lead to the number difference that different channels carry out garbage reclamation, there is a continuing need for progress garbage collection operations in possible certain channels, and
Therefore certain channels, which do not need always progress garbage collection operation, will affect the whole writing speed of data；
Third, when carrying out garbage collection operation, each channel has independence, and the number of the garbage reclamation in each channel
Difference causes the write-in number of data block in each channel and erasing times different, and the write-in number and erasing times of data block
It will affect the service life of solid state hard disk, therefore, number be written and the high channel of erasing times will affect entire solid state hard disk
Service life；
4th, for field of video monitoring, since data volume is big and has continuity, need solid state hard disk to have steady
Fixed writing speed and higher manifolding number, and in above-mentioned wiring method, since the speed of each channel write-in data is inconsistent,
The whole writing speed of data is influenced, therefore is not suitable for the write-in of video monitoring data.
In view of the above problems in the related art, the embodiment of the invention provides method for writing data, are below wherein one
The method for writing data that kind embodiment provides, is applied to solid state hard disk, which includes multiple physical storage areas, often
A physical storage areas includes multiple data blocks, and multiple data blocks include storing data block and reserved data block；As shown in Fig. 2,
Method includes the following steps:
Step S10, when at least one reserved data block all writes full data in physical storage areas, determine that the physics is deposited
The population size of valid data in each storing data block in storage area domain；
Step S20, the storing data block that whether quantity of valid data is zero in the physical storage areas judged；
Step S30, if so, it is complete in the storing data block that the quantity for wiping valid data in the physical storage areas is zero
Portion's data.
As shown in figure 3, above-mentioned solid state hard disk includes n physical storage areas, respectively physical storage areas 1, physics
Storage region 2 ... ..., physical storage areas n-1, physical storage areas n；Each physical storage areas includes n+1 data block,
Respectively Block 0, Block 1 ... ..., Block n；It include storing data block and reserved data in plurality of data block
Block, it may for example comprise n storing data block and 1 reserved data block, Block 1-Block n are storing data block, and Block 0 is
Reserved data block, storing data block and reserved data block are not had any different in structure.
It may include multiple non-volatile memory mediums on hardware configuration in above-mentioned solid state hard disk, it may for example comprise multiple
FLASH chip or multiple dram chips, each non-volatile memory medium can be divided into multiple amount of physical memory, above-mentioned
Physical storage areas may include one or more amount of physical memory, each data block may include one or two
Above amount of physical memory.
For non-volatile memory medium is the solid state hard disk of NAND Flash chip, a NAND Flash can be wrapped
Multiple chip Die are included, there is independent operation note and status register inside each Die, each Die can be independent for one
Unit, each Die are divided into multiple physical storage blocks, and above-mentioned each data block can be one or two on Die
Above physical storage block.
Above-mentioned solid state hard disk may include conversion layer, the conversion layer effect be establish be located at upper layer client Host with
Mapping relations between the physical storage areas of lower layer make the accessible each physical storage areas of client, realize logarithm
According to write-in or read operation.
If non-volatile memory medium is that the above-mentioned conversion layer of NAND Flash chip can be FTL (Flash
Translation layer, abbreviation FTL).
As shown in figure 3, client Host may include n subregion, respectively subregion 1, subregion 2 ... ..., subregion n-1 divide
Area n, conversion layer may include n logic storage unit, respectively LBA 1, LBA2 ... ..., LBA n-1, LBA n, each subregion
There are mapping relations with each logic storage unit, each logic storage unit and each physical storage areas have mapping relations, therefore,
The corresponding relationship between each subregion and each physical storage areas is established by conversion layer, realizes the client Host on upper layer to each
The read-write operation of physical storage areas, for example, corresponding physical storage area can be written the data in each subregion of client Host
In domain.
Each subregion of above-mentioned client Host can respectively correspond each terminal device, can be by the number to be stored in each terminal device
According in corresponding physical storage areas in write-in solid state hard disk, terminal device is, for example, video camera, and multiple video cameras are corresponding each
Subregion is, it can be achieved that the video stream data that each video camera acquires is respectively written into each physical storage areas.
Data to be written are usually carried in data writing process, in the write order from upper-layer client end Host and are patrolled
Address is collected, it can be according to the physics of the logical address each data block in the logical address and physical storage areas of logic storage unit
The corresponding physical address of the logical address is found in mapping relations between address, is written into data write-in and physical address
In corresponding data block, data write-in is realized.
It is relatively independent when between above-mentioned each physical storage areas, it can run parallel, data fractionation can be written into
It is written in parallel in each physical storage areas at multiple portions.
As data are constantly written in physical storage areas, if data are continuously written into, data to be written can be successively
It is written in each storing data block in physical storage areas, with the continuous write-in of data, when each storing data block is fully written
Data, solid state hard disk is dishful state at this time；If data are random writings, the write-in physics that data to be written can be random is deposited
In storage area domain in each data block, with the continuous write-in of data, may have and write full data in the storing data block of part, and portion
There is a small amount of space that data are not written in point storing data block, when data are written in storing data blocks all in physical storage areas
When space accounts for the certain proportion of total memory space of entire physical storage areas, which is usually biggish ratio, such as
70%-90%, at this time it is believed that solid state hard disk is close to dishful state.
It, can will be to be written when receiving write order again when solid state hard disk is dishful state or when close to dishful state
Enter in data write-in reserved data block, at this point, can be by the number in relatively early write-in storing data block and in write-in reserved data block
According to the data of identical population size as invalid data (alternatively referred to as overwritten data), when writing full data in reserved data block,
If reserved data block has multiple, can be reserved when one of reserved data block writes full data or more than two of them
When data block writes full data, it will have the data of population size identical as the data of reserved data block as invalid data.
If data are continuously written into, which is typically distributed about in a storing data block, can be existed at this time
The case where data in one storing data block all invalid data；If data are random writings, which can
It can be the data being distributed in a storing data block, it is also possible to different storing data blocks are distributed in, at this point, storage may be not present
The case where data in data block all invalid data.
It is written in parallel to since above-mentioned physical storage areas can be, thus, it may be possible in one of physical storage areas
Reserved data block write full data, or there is the reserved data block in multiple physical storage areas to write full data, in order to retouch
It states conveniently, is herein one or multiple not in differentiation in description, becomes storing data block after reserved data block write-in data.
In the present embodiment, when at least one reserved data block all writes full data in physical storage areas, the object is determined
The population size for managing valid data in each storing data block of storage region, that is, determine in the data stored in each storing data block
The amount of storage size of valid data, when the data volume that there are wherein valid data in the storing data block in the physical storage areas
The storing data block for being zero, i.e., not having valid data in the storing data block is invalid data (i.e. overwritten data), at this point, wiping
Except the total data in the storing data block, that is, the storing data block is emptied, which can be used as blank after being emptied
Data block data are written again, the data block of the blank can be used as reserved data block, and reserved data block and storing data block are
Dynamic change.
Seen from the above description, the method for writing data, when solid state hard disk is dishful state or when close to dishful state,
When the storing data block that the quantity there are valid data is zero, the storing data block is emptied, the storing data block is as blank
The rewritable write-in data of data block, therefore, there is no need to carry out garbage collection operation, the speed of each physical storage areas write-in data
Degree is consistent, does not influence the whole writing speed of data, the writing speed of data is very fast.
For field of video monitoring, video stream data is continuously written into, and data to be written are sequentially written in each physics
In the storing data block of storage region, when reserved data block writes full, the quantity that inherently there are valid data is zero storage
When data block, that is, it there will necessarily be the feelings that invalid data (i.e. overwritten data) all concentrates in one or more storing data blocks
Condition can re-write data after emptying the storing data block, when solid state hard disk is dishful state again, empty again effectively
The storing data block that the quantity of data is zero, such iterative cycles, each physical storage areas do not need progress garbage reclamation behaviour
Make, therefore, the write-in number of data block and erasing times are almost the same in each physical storage areas, and each physical storage areas is write
Enter that speed is more stable, and is not in influence making for entire solid state hard disk since an erasable number of physical storage areas is excessively high
The case where with the service life.
Also, solid-state can be reduced also there is no need to judge the type of write order due to not needing progress garbage collection operation
The resource overhead of hard disk helps to improve the read or write speed of solid state hard disk, it can be seen that the method for writing data is particularly suitable for
Field of video monitoring.
Above-mentioned method for writing data is applicable to field of video monitoring, can be continuous as unit of data block by video stream data
It is written in corresponding physical storage areas, the video stream data in video camera corresponding with each subregion of client is stored respectively
Into different physical storage areas, the correspondence of logical partition and physical storage areas is realized, it is convenient that data are managed.
Further, when any physical storage areas is in dishful state, it can be concentrated as unit of data block and discharge it
In data, thus avoid garbage reclamation bring data be written latency issue, write data each time can effectively
Enter into data block, promotes the service life of solid state hard disk to greatest extent；And it is mutually indepedent between each physical storage areas,
It will not interfere with each other, so that solid state applications be made to operate in high speed and stable state, help to improve writing speed.
In an optional embodiment, as shown in figure 4, the above method can with the following steps are included:
If step S41, judging the storing data block that the quantity in the physical storage areas there is no valid data is zero
When, read valid data in the part storing data block of each physical storage areas；
It step S42, will be where the corresponding storing data block for being written to the reading part valid data of the valid data of reading
Physical storage areas reserved data block in；
Step S43, the total data in each section storing data block that erasing has been read.
The case where being random writing to data, invalid data may be the data being distributed in a storing data block, can also
Different storing data blocks can be distributed in, accordingly, it is possible to the case where invalid data all there is no data in storing data block,
The storing data block that the quantity in physical storage areas there is no valid data is zero is judged, at this point, due at least one
Full data are write in reserved data block, solid state hard disk is in close to dishful state, needs to carry out garbage collection operation.
In the present embodiment, when carrying out garbage collection operation, the part storing data of each physical storage areas is read first
Valid data in block, the part storing data block are usually wherein stored with the storing data block of valid data and invalid data,
Specifically, when reading valid data in the storing data block from each physical storage areas, can be parallel from each storing data
Valid data are read in block respectively, the identical valid data of population size can be read respectively from each storing data block every time,
But since the quantity of the valid data in each storing data block may be not identical, when reading every time, it is possible to, it is right
In certain physical storage areas, when the biggish memory space for reading one storing data block of multiple storing data blocks or reading
Afterwards, a certain number of valid data can be just read out, and for certain amount of physical memory, when the storage number for reading negligible amounts
According to block or after reading the lesser memory space of a storing data block, the valid data of identical quantity can be read out.
After reading valid data, the valid data of reading are needed to be written in reserved data block, in the present embodiment, will be read
The corresponding physical storage areas being written to where the storing data for reading the part valid data of the valid data taken is reserved
In data block.
After the valid data read are written in reserved data block, since preservation has been carried out in valid data, into
And the total data in the erasable each section storing data block read, that is, each section storing data block is emptied, is emptied
Data are written in the data block that storing data block can be used as blank again, complete garbage collection operation.
Above-mentioned data writing process for example, solid state hard disk there are four physical storage areas, respectively physical storage area
Domain 1, physical storage areas 2, physical storage areas 3 and physical storage areas 4, are deposited from the part of each physical storage areas respectively
16K valid data are read in storage data block then to respectively correspond all valid data of reading and be written to corresponding physical store
In the reserved data block in region.
For having read 4 16K valid data, will be read from the part storing data block in physical storage areas 1
16K valid data be written in the reserved data block of physical storage areas 1, likewise, will be from the portion in physical storage areas 2
The 16K valid data read in point storing data block are written in the reserved data block of physical storage areas 2, will be from physical store
The 16K valid data read in part storing data block in region 3 are written in the reserved data block of physical storage areas 3,
The 16K valid data read from the part storing data block in physical storage area, 4 are written to the pre- of physical storage areas 4
It stays in data block.
In the present embodiment, when valid data are written, the valid data read are written to corresponding physical storage area
The case where in domain, the data write-in of each physical storage areas is relatively independent, is not in across physical storage areas write-in, this
The writing speed of data not only can be improved in sample, and convenient for being managed to the data stored in physical storage areas.
In some instances, as shown in figure 5, the part of each physical storage areas of reading described in above-mentioned steps S41 is deposited
Store up valid data in data block, comprising:
Step S411, it determines that the quantity of valid data in each storing data block of each physical storage areas is the smallest respectively to deposit
Data block is stored up, as source storing data block；
Step S412, the valid data in each source storing data block are read respectively.
In the present embodiment, when reading valid data in the part storing data block from each physical region, it is first determined go out
The quantity of valid data is the smallest in each storing data block, as source storing data block, then from each physical storage areas
Source storing data block in read valid data, can be first wiped in the smallest storing data block of quantity of valid data in this way
Data, erasing speed is fast, and the speed of garbage reclamation can be improved, and therefore, is conducive to the writing speed for improving data.
In an optional embodiment, as shown in fig. 6, before above-mentioned steps S42 further include:
Step S413, whether the total quantity for the valid data that judgement has been read is greater than or equal to write-in amount threshold；
If so, executing above-mentioned steps 42, each physical storage areas is read described in above-mentioned steps S41 if otherwise executing
Valid data in the storing data block of part.
It in order to improve writing speed, is usually written again when data are greater than a certain quantity, and how many number is not read
According to being then just written later, data write-in number can be reduced in this way, improves write efficiency, accordingly, in the present embodiment, will
Before the valid data write-in reserved data block of reading, further first judge whether the total quantity of the valid data read is greater than
Or be equal to write-in amount threshold, that is, judge whether to meet data write conditions, be write when the total quantity of valid data is greater than or equal to
When entering amount threshold, that is, when meeting Writing condition, then will be in the corresponding reserved data block of the valid data that read write-in；When having
When imitating the total quantity of data less than write-in amount threshold, that is, when being unsatisfactory for Writing condition, executes again read valid data at this time
The step of, i.e., valid data are read again, are written again when the total quantity of valid data meets Writing condition.
In some instances, as shown in fig. 7, reading having in each source storing data block described in above-mentioned steps S412 respectively
Imitate data, comprising:
Step S4121, the every page data of sequence read in each source storing data block respectively as unit of page；
Step S4122, judge whether each page data read is valid data；
If so, whether the total quantity for executing the valid data for judging to have read described in above-mentioned steps S413 is greater than or waits
In write-in amount threshold step；
If it is not, then executing step S4121 described above, namely read the lower page of data in each source storing data block.
For non-volatile memory medium is the solid state hard disk of NAND Flash chip, in each physical storage areas
Each data block can be one or more the amount of physical memory on Die.
NAND Flash chip is a kind of non-volatile flash memory chip, with following characteristic, when data are written, each
Bit can only become 0 from 1, wipe and become 1 for each bit from 0 when data, and read and write data as unit of page, and with physical store
Block is that unit wipes data, and each physical storage block in NAND flash chip has maximum erasable number.
In the present embodiment, i.e., the mode as unit of page reads the data in each source storing data block respectively, for reading
Every page data further judge whether it is valid data, for example, by data check algorithm judge reading data whether
For valid data, if so, step S42 described above is then executed down, if it is not, then continuing to read each source storing data block
In lower page of data.
Fig. 8 show the structural schematic diagram that the solid state hard disk based on NAND Flash chip carries out garbage collection procedure, such as
Shown in Fig. 8, which includes n physical storage areas, respectively physical storage areas 1, physical storage areas 2 ... ...,
Physical storage areas n；Each physical storage areas includes multiple storage chip Die, and multiple storage chip Die constitute one
NAND Flash chip.
Physical storage areas 1 includes storage chip Die 11 to storage chip Die 1n；Physical storage areas 2 includes storage
Chip Die 21 to storage chip Die 2n；……；Physical storage areas n includes storage chip Die n1 to storage chip Die
Nn, each storage chip may include storing data block and several reserved data blocks.
Referring to the workflow for further illustrating above-described embodiment shown in Fig. 8, firstly, determining each physical store respectively
The smallest storing data block of quantity of valid data in each storing data block in region, as source storing data block, such as Fig. 8
Shown, it is source storing data block, object that the storing data block Block 11 in storage chip Die 11 is located in physical storage areas 1
Managing the storing data block Block 21 being located in storage chip Die 21 in storage region 2 is source storing data block ... ..., physics
Being located at the storing data block Block n1 in storage chip Die n1 in storage region n is source storing data block.
The data in each source storing data block in each physical storage areas are read respectively, are read respectively every time as unit of page
The page of data in each source storing data block is taken, parallel the 0th page data Page 0 read in source storing data block Block11,
Page 0 in the 0th page data Page 0 ... ... and source storing data block Blockn1 in the storing data block Block21 of source
Data Page 0 judges whether each page data read is valid data, for example, the 0th page data in each source storing data block
Page 0 is invalid data, then continues to read the lower page of data in each source storing data block, for example, the source storage read
The 3rd page data Page 3 in data block Block11 is valid data, the in the source storing data block Block21 read
21 page data Page 20 are valid data ... ..., the (n+1)th page data Page in the storing data block Blockn1 of source read
N is valid data.
Judge whether the total quantity of the valid data read is greater than write-in amount threshold, such as read page 10 at this time to have
Data are imitated, the total quantity size of the valid data of page 10 is 256K, is greater than write-in amount threshold 200K.
Then, the valid data correspondences of page read 10 are written in physical storage areas, it will be from source storing data block
The physical storage areas 1 that the valid data of page 3 read in Block11 are written where the storing data block Block11 of the source is deposited
It stores up in the reserved data block Block1n in chip Die 11, if several pages of significant figures are being written in the reserved data block Blockn1
When having write full after, remaining valid data can be written in other reserved data blocks of the physical storage areas 1.
Similar, the valid data pair of page 21 that will be read from the source storing data block Block21 of physical storage areas 2
It should be written in physical storage areas 2 and be located in the reserved data block Block2n in storage chip Die21；And so on, respectively will
The pre- residual of corresponding physical storage areas is written in the valid data read from the source storing data block of each physical storage areas
According in block, arrow indicates valid data to be written in corresponding reserved data block in Fig. 8, has only schematically marked portion in certain figure
Divide and corresponds to the write-in of valid data in reserved data block.
After the whole valid data read are written in corresponding reserved data block, each source storage number read is wiped
According to the total data in block, the operation of garbage reclamation is completed accordingly.
In some instances, corresponding be written to of the valid data read is read into the portion described in above-mentioned steps S43
Divide in the reserved data block of the physical storage areas where the storing data block of valid data, comprising:
By the storage where the corresponding storing data block for being written to the reading part valid data of the valid data read
It, will be remaining after the empty storage space of the reserved data block is write completely in the empty storage space of reserved data block in chip
Part valid data be written to read the part valid data storing data block where physical storage areas in other
In the reserved data block of storage chip.
For solid state hard disk, physical storage areas may include multiple storage chips, such as multiple Die, in order to be promoted
The read-write stability of data, the storing data that will need the part valid data being written that the reading part valid data are preferentially written
In reserved data block in storage chip where block, i.e., preferentially part valid data is written and reads the part valid data
Currently stored chip when the empty storage space in the reserved data block of the current storage chip writes full, then is written other and deposits
It stores up in chip, it is effective that the storage chip where reading the storing data block of the part valid data certainly also is located at the reading part
Physical storage areas where the storing data block of data.
For example, solid state hard disk includes four physical storage areas, respectively physical storage areas 1, physical storage area
Domain 2, physical storage areas 3 and physical storage areas 4；Physical storage areas 1 includes the first storage chip and the second storage chip,
Physical storage areas 2 includes third storage chip and the 4th storage chip, and physical storage areas 3 includes the 5th storage chip and the
Six storage chips, physical storage areas 4 include the 7th storage chip and the 8th storage chip, and each storage chip is divided into 10
Storing data block and 1 reserved data block.
16K valid data are read from the part storing data block of each physical storage areas respectively, read 4 16K
Valid data, wherein reading out 16K valid data from first storing data block in physical storage areas 1, first is deposited
Storage data block is located on the first storage chip, first storage chip namely positioned at physical storage areas 1；From physical storage areas
16K valid data are read out in second storing data block in 2, second storing data block is located on the 4th storage chip,
4th storage chip namely be located at physical storage areas 2；It is read out from the 8th storing data block in physical storage areas 3
16K valid data, the 8th storing data block are located on the 6th storage chip, the 8th storage chip namely be located at physical storage area
Domain 3；16K valid data, the 5th storing data block position are read out from the 5th storing data block in physical storage areas 4
In on the 7th storage chip, the 7th storage chip namely it is located at physical storage area 4.
The valid data of this 4 16K are written in the empty storage space of reserved data block of corresponding storage chip,
Specifically, by being deposited from the 4th where second storing data block for reading out 16K valid data in physical storage areas 2
The empty storage space of reserved data block in storage chip is write completely, such as is written with the effective of 2 16K in the empty storage space
Data, then again by the reserved data of third storage chip in the valid data write-in physical storage areas 2 of remaining 1 16K
In block；Likewise, will be from where the 5th storing data block for reading out 16K valid data in physical storage areas 4
In the empty storage space of reserved data block in seven storage chips, such as in the empty storage space it is written with having for 1 16K
It is not write yet after effect data completely, since valid data have write, therefore, there is no need to the 8th storage core in physical storage areas 4
Valid data are written again in the reserved data block of piece.
The embodiment of the invention also provides a kind of data transfer apparatus, are applied to solid state hard disk, and the solid state hard disk includes
Multiple physical storage areas, each physical storage areas include multiple data blocks, and multiple data blocks include storing data block and pre-
Stay data block；As shown in figure 9, the data transfer apparatus 09 includes:
Valid data amount determination unit 91 is complete for working as at least one described reserved data block in the physical storage areas
When full data are write in portion, the population size of valid data in each storing data block of the physical storage areas is determined；
Valid data amount judging unit 92 is with the presence or absence of the quantity of valid data in the physical storage areas for judging
Zero storing data block；
First data wipe unit 93, for when judging in the physical storage areas there are effective data volume to be zero
When storing data block, the total data in storing data block that the quantity for wiping valid data in the physical storage areas is zero.
In an optional embodiment, the data transfer apparatus further include:
Valid data reading unit judges that the quantity in the physical storage areas there is no valid data is zero for working as
Storing data block when, read valid data in the part storing data block of each physical storage areas；
Determination unit is written in valid data, for the corresponding reading part that is written to of the valid data read to have
In the reserved data block for imitating the physical storage areas where the storing data block of data；
Second data wipe unit, for wiping the total data in each part storing data block read.
In an optional embodiment, the valid data reading unit is specifically used for:
It determines that the quantity of valid data in each storing data block of each physical storage areas is the smallest respectively to deposit
Data block is stored up, as source storing data block；
The valid data in each source storing data block are read respectively.
In an optional embodiment, the data transfer apparatus further include:
Valid data quantity judging unit is write for judging whether the total quantity of the valid data read is greater than or equal to
Enter amount threshold；
If so, executing described correspond to the valid data read is written to depositing for the reading part valid data
Store up the step in the reserved data block of the physical storage areas where data block；
If it is not, then executing the step of valid data in the part storing data block for reading each physical storage areas
Suddenly.
Corresponding with the embodiment of aforementioned data wiring method, data transfer apparatus provided by the invention works as solid state hard disk
When for dishful state or close to dishful state, when the storing data block that the quantity there are valid data is zero, empties this and deposit
Data block is stored up, data block rewritable write-in data of the storing data block as blank therefore, there is no need to carry out garbage reclamation behaviour
Make, the speed of each physical storage areas write-in data is consistent, do not influence the whole writing speed of data, the writing speeds of data compared with
Fastly.
For device embodiment, wherein the realization process of the function and effect of each unit or subelement is specifically detailed in
The realization process of step is corresponded in the above method, details are not described herein.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, it can it is in one place, or may be distributed over multiple network lists
In member；Above-mentioned each unit can be merged into a unit, can also be further split into multiple subelements.
Through the above description of the embodiments, the device of the present embodiment can be realized or software by the mode of software
The mode of required common hardware is added to realize, naturally it is also possible to pass through hardware realization.Based on this understanding, skill of the invention
Substantially the part that contributes to existing technology can be embodied in the form of software products art scheme in other words, with software
For realization, as the device on a logical meaning, being will be non-volatile by the processor where the equipment of the application device
Property memory in corresponding computer program instructions be read into memory operation formed.
Referring to Figure 10, the present invention also provides a kind of hardware architecture diagram of solid state hard disk, which includes: communication interface
101, processor 102, machine readable storage medium 103, bus 104 and physical storage medium 105；Wherein, communication interface 101,
Processor 102, machine readable storage medium 103 and physical storage medium 105 complete mutual communication by bus 104.Place
Reason device 102 is by reading and executing machine corresponding with the control logic of method for writing data in machine readable storage medium 102
Above-described method for writing data can be performed in executable instruction, and the physical storage medium includes multiple physical storage areas,
Each physical storage areas includes multiple data blocks, and multiple data blocks include storing data block and reserved data block.
Machine readable storage medium 103 referred to herein can be any electronics, magnetism, optics or other physical stores
Device may include or store information, such as executable instruction, data, etc..For example, machine readable storage medium may is that
RAM (RadomAccess Memory, random access memory), volatile memory, nonvolatile memory, flash memory, storage are driven
Dynamic device (such as hard disk drive), any kind of storage dish (such as CD, dvd) perhaps similar storage medium or they
Combination.
Physical storage medium 104 can be one or more non-volatile memory mediums, the non-volatile memory medium example
For example FLASH chip or dram chip etc..
The embodiment of the present invention also provides a kind of computer readable storage medium, is stored thereon with computer program, the journey
Any of the above-described embodiment the method is realized when sequence is executed by processor.
Those skilled in the art are considering specification and after practicing disclosure disclosed herein, will readily occur to of the invention its
Its embodiment.The present invention is directed to cover any variations, uses, or adaptations of the invention, these modifications, purposes or
Person's adaptive change follows general principle of the invention and including the undocumented common knowledge in the art of the present invention
Or conventional techniques.The description and examples are only to be considered as illustrative, and true scope and spirit of the invention are wanted by right
It asks and points out.
Claims (12)
1. a kind of method for writing data is applied to solid state hard disk, which is characterized in that the solid state hard disk includes multiple physical stores
Region, each physical storage areas include multiple data blocks, and multiple data blocks include storing data block and reserved data block；The party
Method includes:
When the reserved data block of at least one in the physical storage areas all writes full data, the physical storage area is determined
The population size of valid data in each storing data block in domain；
Judge the storing data block that the quantity in the physical storage areas with the presence or absence of valid data is zero；
If so, the total data in the storing data block that the quantity for wiping valid data in the physical storage areas is zero.
2. the method according to claim 1, wherein further include:
If judge the storing data block that the quantity in the physical storage areas there is no valid data is zero, read each described
Valid data in the part storing data block of physical storage areas；
By the physics where the corresponding storing data block for being written to the reading part valid data of the valid data read
In the reserved data block of storage region；
Wipe the total data in each part storing data block read.
3. according to the method described in claim 2, it is characterized in that, the part storage for reading each physical storage areas
Valid data in data block, comprising:
The smallest storage number of quantity of valid data in each storing data block of each physical storage areas is determined respectively
According to block, as source storing data block；
The valid data in each source storing data block are read respectively.
4. according to the method described in claim 3, it is characterized in that, the valid data correspondence of reading is written to described
It reads in the reserved data block of the physical storage areas where the storing data block of the part valid data, before further include:
Judge whether the total quantity of the valid data read is greater than or equal to write-in amount threshold；
If so, executing described by the corresponding storage number for being written to the reading part valid data of the valid data read
According to the step in the reserved data block of the physical storage areas where block；
If it is not, the step of then executing valid data in the part storing data block for reading each physical storage areas.
5. according to the method described in claim 4, it is characterized in that, described read having in each source storing data block respectively
Imitate data, comprising:
The every page data of sequence read in each source storing data block respectively as unit of page；
Judge whether each page data read are valid data；
If so, executing the step whether total quantity for judging the valid data read is greater than or equal to write-in amount threshold
Suddenly；
If it is not, then executing the every number of pages of the sequence described above as unit of page read in each source storing data block respectively
According to the step of.
6. according to the method described in claim 4, it is characterized in that, described be written to reading for the valid data correspondence of reading
It takes in the reserved data block of the physical storage areas where the storing data block of the part valid data, comprising:
The corresponding write-in of the valid data read is read to the storage core where the storing data block of the part valid data
It, will be remaining after the empty storage space of the reserved data block is write completely in the empty storage space of reserved data block in piece
Part valid data be written to read the part valid data storing data block where physical storage areas in other deposit
In the reserved data block for storing up chip.
7. a kind of data transfer apparatus is applied to solid state hard disk, which is characterized in that the solid state hard disk includes multiple physical stores
Region, each physical storage areas include multiple data blocks, and multiple data blocks include storing data block and reserved data block；The dress
It sets and includes:
Valid data amount determination unit is all write completely for working as at least one described reserved data block in the physical storage areas
When data, the population size of valid data in each storing data block of the physical storage areas is determined；
Valid data amount judging unit, for judging that the quantity in the physical storage areas with the presence or absence of valid data is zero to deposit
Store up data block；
First data wipe unit, judge that there are the storage numbers that effective data volume is zero in the physical storage areas for working as
When according to block, the total data in storing data block that the quantity for wiping valid data in the physical storage areas is zero.
8. device according to claim 7, which is characterized in that further include:
Valid data reading unit, for when judging that the quantity in the physical storage areas there is no valid data is zero to deposit
When storing up data block, valid data in the part storing data block of each physical storage areas are read；
Determination unit is written in valid data, for corresponding be written to of the valid data read to be read the part significant figure
According to storing data block where physical storage areas reserved data block in；
Second data wipe unit, for wiping the total data in each part storing data block read.
9. device according to claim 8, which is characterized in that the valid data reading unit is specifically used for:
The smallest storage number of quantity of valid data in each storing data block of each physical storage areas is determined respectively
According to block, as source storing data block；
The valid data in each source storing data block are read respectively.
10. device according to claim 9, which is characterized in that further include:
Valid data quantity judging unit, for judging whether the total quantity of the valid data read is greater than or equal to write-in number
Measure threshold value；
If so, executing described by the corresponding storage number for being written to the reading part valid data of the valid data read
According to the step in the reserved data block of the physical storage areas where block；
If it is not, the step of then executing valid data in the part storing data block for reading each physical storage areas.
11. a kind of solid state hard disk, which is characterized in that the solid state hard disk includes processor, machine readable storage medium and physics
Storage medium, the physical storage medium include multiple physical storage areas, and each physical storage areas includes multiple data blocks,
Multiple data blocks include storing data block and reserved data block, and the machine readable storage medium is stored with can be by the processing
The machine-executable instruction that device executes, the processor are promoted to execute such as claim 1 to 6 times by the machine-executable instruction
One the method.
12. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that described program is processed
Any one of claim 1-6 the method is realized when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810362066.3A CN110389712B (en) | 2018-04-20 | 2018-04-20 | Data writing method and device, solid state disk and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810362066.3A CN110389712B (en) | 2018-04-20 | 2018-04-20 | Data writing method and device, solid state disk and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110389712A true CN110389712A (en) | 2019-10-29 |
| CN110389712B CN110389712B (en) | 2022-12-23 |
Family
ID=68284163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810362066.3A Active CN110389712B (en) | 2018-04-20 | 2018-04-20 | Data writing method and device, solid state disk and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110389712B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111078137A (en) * | 2019-11-07 | 2020-04-28 | 深圳市金泰克半导体有限公司 | Method for cleaning storage space |
| CN112162935A (en) * | 2020-09-30 | 2021-01-01 | 深圳市时创意电子有限公司 | Data processing method and device of storage chip, computer equipment and storage medium |
| CN113867642A (en) * | 2021-09-29 | 2021-12-31 | 杭州海康存储科技有限公司 | Data processing method and device and storage equipment |
| WO2023103819A1 (en) * | 2021-12-08 | 2023-06-15 | 北京拙河科技有限公司 | Video monitoring system and method based on hundred-megapixel data and video anomaly analysis system and method based on hundred-megapixel data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101819509A (en) * | 2010-04-19 | 2010-09-01 | 清华大学深圳研究生院 | Solid state disk read-write method |
| US9330727B1 (en) * | 2013-12-30 | 2016-05-03 | Emc Corporation | Binding a data object to a rotational hard drive |
| WO2016107442A1 (en) * | 2014-12-31 | 2016-07-07 | 华为技术有限公司 | Method for writing data to solid state drive and solid state drive |
-
2018
- 2018-04-20 CN CN201810362066.3A patent/CN110389712B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101819509A (en) * | 2010-04-19 | 2010-09-01 | 清华大学深圳研究生院 | Solid state disk read-write method |
| US9330727B1 (en) * | 2013-12-30 | 2016-05-03 | Emc Corporation | Binding a data object to a rotational hard drive |
| WO2016107442A1 (en) * | 2014-12-31 | 2016-07-07 | 华为技术有限公司 | Method for writing data to solid state drive and solid state drive |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111078137A (en) * | 2019-11-07 | 2020-04-28 | 深圳市金泰克半导体有限公司 | Method for cleaning storage space |
| CN111078137B (en) * | 2019-11-07 | 2021-07-06 | 深圳市金泰克半导体有限公司 | Method for cleaning storage space |
| CN112162935A (en) * | 2020-09-30 | 2021-01-01 | 深圳市时创意电子有限公司 | Data processing method and device of storage chip, computer equipment and storage medium |
| CN113867642A (en) * | 2021-09-29 | 2021-12-31 | 杭州海康存储科技有限公司 | Data processing method and device and storage equipment |
| CN113867642B (en) * | 2021-09-29 | 2023-08-04 | 杭州海康存储科技有限公司 | Data processing method, device and storage equipment |
| WO2023103819A1 (en) * | 2021-12-08 | 2023-06-15 | 北京拙河科技有限公司 | Video monitoring system and method based on hundred-megapixel data and video anomaly analysis system and method based on hundred-megapixel data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110389712B (en) | 2022-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109144887B (en) | Memory system and control method for controlling nonvolatile memory | |
| CN110389712A (en) | Method for writing data and its device, solid state hard disk and computer readable storage medium | |
| CN101154190B (en) | Mapping information managing apparatus and method | |
| KR101465789B1 (en) | Write and merge methods in memory card systems for reducing the number of page copies | |
| CN109117084A (en) | Logic block storage is dynamically readjusted into size | |
| CN109753443B (en) | Data processing method and device and electronic equipment | |
| DE112020002792B4 (en) | WEAR-ORIENTED BLOCK MODE CONVERSION IN NON-VOLATILE MEMORIES | |
| CN101329654A (en) | Nonvolatile memory control device, nonvolatile memory control method, and storage device | |
| CN113254358A (en) | Method and system for address table cache management | |
| CN106598504B (en) | data storage method and device | |
| US20230153236A1 (en) | Data writing method and apparatus | |
| CN110673789A (en) | Metadata storage management method, device, equipment and storage medium of solid state disk | |
| CN106528443A (en) | FLASH management system and method suitable for satellite-borne data management | |
| CN110347338B (en) | Hybrid memory data exchange processing method, system and readable storage medium | |
| CN104298615B (en) | Method for equalizing swap partition loss of memory | |
| CN107967125A (en) | Management method, device and the computer-readable recording medium of flash translation layer (FTL) | |
| CN108664217B (en) | Caching method and system for reducing jitter of writing performance of solid-state disk storage system | |
| CN113986773A (en) | Write amplification optimization method and device based on solid state disk and computer equipment | |
| CN103514098B (en) | For reclaiming the method and system of memory space | |
| CN106326132A (en) | Storage system, storage management device, storage, hybrid storage device and storage management method | |
| CN102880553A (en) | Read-write method of off-chip flash file system based on micro control unit (MCU) | |
| CN105630403A (en) | File storage system and file storage control method and apparatus therefor | |
| CN114442946A (en) | Physical block management method and solid state disk | |
| US10990520B2 (en) | Method for gabage collecting for non-volatile memory | |
| Kwon et al. | Data pattern aware FTL for SLC+ MLC hybrid SSD |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200317 Address after: 310051 room 307, floor B, building 2, No. 399, Danfeng Road, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Hangzhou Haikang Storage Technology Co.,Ltd. Address before: 430074 East Lake Development Zone, Wuhan City, Hubei Province, No. 1 Software Park, Guanshan Road, Phase 5, Building F4, Room 21, Room 01 Applicant before: WUHAN HIKSTORAGE TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |