CN105389128B - A kind of solid state hard disk date storage method and storage control - Google Patents
A kind of solid state hard disk date storage method and storage control Download PDFInfo
- Publication number
- CN105389128B CN105389128B CN201510752334.9A CN201510752334A CN105389128B CN 105389128 B CN105389128 B CN 105389128B CN 201510752334 A CN201510752334 A CN 201510752334A CN 105389128 B CN105389128 B CN 105389128B
- Authority
- CN
- China
- Prior art keywords
- logical address
- written
- data block
- data
- frequently
- 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.)
- Active
Links
Classifications
-
- 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
- G06F3/0614—Improving the reliability of storage systems
- G06F3/0616—Improving the reliability of storage systems in relation to life time, e.g. increasing Mean Time Between Failures [MTBF]
-
- 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
- G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
- G06F3/0656—Data buffering arrangements
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to a kind of solid state hard disk date storage method and storage controls.A kind of storage control is provided in one embodiment, comprising: data processing unit generates data block to be written according to the metadata of data to be written and data to be written, and determines the first logical address of data block to be written;Data determining unit judges whether the first logical address is common logical address, and generates non-common data block or write signal to be covered according to result;Number is write in the covering that chained list control unit updates logical address and the first logical address in chained list according to the first logical address;Binary search tree control unit updates binary search tree according to chained list, and provides common logical address according to the sequence of binary search tree;Frequently-used data library control unit is used to update frequently-used data library according to common logical address;And/or it is written into data block covering write-in frequently-used data library according to write signal to be covered.A kind of solid state hard disk date storage method and storage control provided by the present invention overcome the deficiencies in the prior art, by handling a large amount of covering write operations, extend the service life of solid state hard disk.
Description
Technical field
The present invention relates to data processing field more particularly to a kind of solid state hard disk date storage methods and storage control.
Background technique
In the prior art, using flash memory as the service life of the solid state hard disk (Solid State Drives, SSD) of storage medium with
Write operation number is closely bound up.After the write-in number to the same data storage cell is more than certain amount, this data is deposited
Storage unit may be difficult to that data are written again, if most of storage unit in SSD is in a state in which, need to change new
SSD.Although extending the service life of SSD now with many technologies, such as write-in amplifying technique, the SSD optimization of Intel company,
It is evenly distributed the write-in number of each storage unit in SSD as much as possible.But it for the scene write largely is covered, puts down
Respectively cloth still can't resolve problem.As shown in Figure 1, in virtual desktop architecture (Virtual Desktop
Infrastructure, abbreviation VDI) under main memory scene, the write operation of solid state hard disk is largely that covering write operation (is more than
80%), therefore processing covering write operation is the key that extend SSD to write the service life.
Summary of the invention
The embodiment of the present invention provides the date storage method and storage control of a kind of solid state hard disk, is write by handling covering
Extend solid state hard disk writes the service life.
On the one hand, the present invention provides a kind of solid state hard disk storage control, and storage control includes: that data processing unit is used
In generating data block to be written according to the metadata of data to be written and data to be written, and determine the of data block to be written
One logical address;Data determining unit is for judging whether the first logical address is common logical address;If the first logical address
Non- common logical address is then written into data block and exports as non-common data block to solid state hard disk, if the first logical address
To commonly use logical address, then write signal to be covered is generated;Chained list control unit updates chained list according to the first logical address, updates chain
Number is write in the covering of logical address and the first logical address in table;Binary search tree control unit updates y-bend according to chained list and searches
Suo Shu writes the sequence of number to the covering of multiple logical addresses, and is provided and commonly used logically according to the sequence of binary search tree
Location;Frequently-used data library control unit is used for according to the frequently-used data block commonly used in logical address update frequently-used data library;And/or
Person is written into data block covering write-in frequently-used data library according to write signal to be covered.
Preferably, data block to be written includes: and is aligned to divide according to specified block size after data aggregate to be written to obtain
Metadata, the data to be written of number data block to be written are written in data acquisition system, data processing unit in storage control caching
First logical address of block.
Preferably, if the first logical address becomes common logical address for the first time, frequently-used data library control unit will update
Before belong to common logical address but be not belonging to the logical address of common logical address after updating as the second logical address, and will
Data block corresponding to second logical address is exported as non-common data block to solid state hard disk, and by the first logical address institute
Frequently-used data library is written in corresponding data block to be written.
Preferably, data block to be written is new data block;Data determining unit is written into data block as non-typical number
It is exported according to block;First logical address is inserted into chained list by chained list control unit, and it is preset that the covering of the first logical address write number
It is 1.
Preferably, data block to be written is frequently-used data block;Data determining unit judges that the first logical address is patrolled to be common
It collects address and exports write signal to be covered;The covering of first logical address is write number and adds 1 by chained list control unit;Frequently-used data
Library control unit is written into data block covering write-in frequently-used data library according to write signal to be covered.
Preferably, binary search tree writes number to covering and sorts according to sequence from more to less, and covering of the sequence in preceding N is write
The corresponding logical address of number is common logical address, and commonly using the corresponding data block of logical address is frequently-used data block.
It should be noted that chained list, binary search tree and frequently-used data inventory are stored in the caching of storage control, and solid
After state hard disk use, by storage control cache in data be written solid state hard disk, which includes: chained list, two
Pitch the metadata of search tree and frequently-used data library and data block.
On the other hand, the present invention provides a kind of solid state hard disk date storage method, method the following steps are included:
Data block to be written is generated according to the metadata of data to be written and data to be written, and determines data to be written
First logical address of block;
Judge whether the first logical address is common logical address, it, will if the non-common logical address of the first logical address
Data block to be written is exported as non-common data block to solid state hard disk, if the first logical address is common logical address, is produced
Raw write signal to be covered;
Chained list is updated according to the first logical address, the covering of logical address and the first logical address in update chained list is write secondary
Number;
Number sequence is write to the covering of at least one logical address in chained list, and is patrolled according at least one after sequence
It collects address and common logical address is provided;At least one logical address includes the first logical address;
The frequently-used data block in frequently-used data library is updated according to common logical address;And/or it is write letter according to be covered
It number is written into data block covering write-in frequently-used data library.
Preferably, the data acquisition system for dividing and obtaining, data processing are aligned according to specified block size after data aggregate to be written
Unit saves the metadata of data block to be written, the first logical address of data block to be written in the buffer.
Preferably, frequently-used data library step is updated according to common logical address, comprising: if the first logical address becomes for the first time
Common logical address will then belong to common logical address before update, but the logical address of common logical address is not belonging to after updating
As the second logical address, and export using data block corresponding to the second logical address as non-common data block hard to solid-state
Disk, and frequently-used data library is written into data block to be written corresponding to the first logical address.
The embodiment of the present invention mainly pass through record logical address be coated overwrite number, by logical address covering write number compared with
The resident caching of more data or metadata ensure that a large amount of coverings write on so that most of covering write operation carries out in the buffer
It is hit in caching, to reduce the write-in number of solid state hard disk, and then achievees the purpose that extend the solid state disk write service life.
Detailed description of the invention
Fig. 1 is that schematic diagram is write in internal solid hard disk covering in one week under main memory virtual desktop architecture scene;
Fig. 2 is usage scenario figure of the storage control provided in an embodiment of the present invention under VDI main memory scene;
Fig. 3 is a kind of storage control structural schematic diagram provided in an embodiment of the present invention;
Fig. 4 is the workflow schematic diagram that data store for the first time;
Fig. 5 is chained list, binary search tree and frequently-used data library variation diagram corresponding to Fig. 4;
Fig. 6 is that new data stores workflow schematic diagram;
Fig. 7 is chained list, binary search tree and frequently-used data library variation diagram corresponding to Fig. 6;
Fig. 8 is that non-common data block stores workflow schematic diagram;
Fig. 9 is chained list, a kind of variation diagram of binary search tree and frequently-used data library corresponding to Fig. 8;
Figure 10 is chained list, binary search tree and frequently-used data library another kind variation diagram corresponding to Fig. 8;
Figure 11 is that frequently-used data block stores workflow schematic diagram;
Figure 12 is chained list, binary search tree and frequently-used data library variation diagram corresponding to Figure 11.
Specific embodiment
Below by drawings and examples, technical scheme of the present invention will be described in further detail.
Fig. 2 is usage scenario figure of the storage control provided in an embodiment of the present invention under VDI main memory scene, such as Fig. 2 institute
Show, under VDI scene, server receives data to be written, and server will be to by optical-fibre channel (FC) or the network switch
The data of write-in are transferred to storage control by FC link or Ethernet, and storage control handles data to be written
Afterwards, most of data for needing covering to write will be covered in storage control and is write, do not need to carry out by remaining, least a portion of
Largely cover the data write-in solid state hard disk write.Provided storage control executes at this data through the embodiment of the present invention
Agent storing process is managed, can be greatly reduced and carry out largely covering the number write in solid state hard disk.By taking Fig. 2 as an example, server
10W data to be written are received, the data being written in solid state hard disk are only the 20% of former data to be written, wherein 80% covering
Write data carried out in storage control covering write.
Fig. 3 is a kind of storage control structural schematic diagram provided in an embodiment of the present invention, as shown in figure 3, the present embodiment institute
The storage control 11 of offer includes: that data processing unit 101, data determining unit 102, chained list control unit 103, y-bend are searched
Suo Shu control unit 104 and frequently-used data library unit 105.
Data processing unit 101, for receiving data VIN to be written, after being written into data VIN polymerization, according to specified
Block size carries out piecemeal alignment and divides, and obtains data block BLK to be written, and is written into data block BLK output, also, data
Processing unit 101 is written into the first logical address LBA write-in storage of the metadata of data block BLK, data block BLK to be written
In the caching of controller 11.Wherein, metadata includes the first logical address LBA and data block object to be written of data block to be written
Manage address mapping relations and other data of data block to be written are described;
Data determining unit 102, for receiving data block BLK, the first logical address LBA and common logical address to be written
Whether OLBA is that common logical address OLBA judges to the first logical address LBA: if the first logical address LBA is common
Logical address OLBA then generates write signal OBL to be covered and exports to frequently-used data library control unit 105;If the first logical address
The non-common logical address OBLA of LBA is then written into data block BLK and exports as non-common data block NBLK to solid state hard disk
SSD;And the first logical address LBA is exported to chained list control unit 103;
Chained list control unit 103, for receiving the first logical address LBA, and according to the first logical address LBA to being stored in
Chained list in the storage caching of controller 11 is updated, and the covering of logical address LBAn and the first address in update chained list are write secondary
Number Nm, and write times N m for covering and export to binary search tree control unit 104, the chained list for record logical address LBAn and
Times N n, the specific update mode of chained list are write in the covering of logical address LBAn are as follows: if the first address LBA has record in chained list,
Times N m then is write into the corresponding covering of the first address LBA directly in chained list and adds 1;If the first address LBAn is in chained list without note
Record is then inserted into the first LBA in chained list and writes times N m and be predisposed to 1 its corresponding covering;
Binary search tree control unit 104 writes times N m for receiving covering, writes times N m to being stored according to covering
Binary search tree in the storage caching of controller 11 is updated, and will finally be obtained N number of common logical address OLBA and be exported to normal
With database control unit 105;Specifically, it if times N m no record in binary search tree is write in the covering received, will cover
Overwrite times N m is inserted into binary search tree;If times N m is write in the covering received record in binary search tree, directly more
The value of times N m is write in covering in new binary search tree;Binary search tree is write times N n to covering and is carried out according to order from more to less
Sequence, and the covering using sequence in preceding N writes logical address corresponding to number as common logical address OLBA;
Frequently-used data library control unit 105 will be to according to write signal OBL to be covered for receiving write signal OBL to be covered
Writing data blocks BLK covering write-in frequently-used data library, and N number of common logical address OLBA is received, update frequently-used data library.
It should be noted that the caching that the size of N value depends on storage control 11 is big in above-mentioned storage control 11
It is small.
Further, chained list control unit 103 can also export chained list to binary search tree control unit 104, and y-bend is searched
Covering in chained list is write times N n and is ranked up from more to less by Suo Shu control unit 104, is frequently-used data according to ranking results
Library control unit 105 provides N number of common logical address OLBA.
It should be noted that updating the specific reality in frequently-used data library in the storage control 11 provided by the present embodiment
Apply mode are as follows: frequently-used data library control unit 105 judges N number of commonly use logically after receiving N number of common logical address OLBA
Location OLBA whether there is the first logical address LBA, and if it exists, will then belong to before update after common logical address OLBA, update not
Belong to the logical address of common logical address OLBA as the second logical address LBAD, frequently-used data library control unit 105 will be normal
It is deleted with the corresponding data block of the second logical address LBAD in database, and solid state hard disk is written as non-common data block NBLK
SSD, while data block corresponding to the first logical address LBA being obtained from solid-state hard disk SSD and frequently-used data library is written.
It should be noted that when chained list, binary search tree in above-mentioned storage control 11 and frequently-used data library
What solid-state hard disk SSD was established when first used: chained list is used to record the logical address LBAn's and logical address LBAn of data block
Times N n is write in covering, and binary search tree is write times N n using the covering in chained list and established as key assignments, and frequently-used data library is with binary search
The covering of N is established based on writing data block corresponding to number before sorting in tree, and chained list, binary search tree and frequently-used data
Library is stored in the caching of storage control 11 when using solid-state hard disk SSD, when solid-state hard disk SSD is stopped using, is stored in
In solid-state hard disk SSD.
Fig. 4 is the workflow schematic diagram that data store for the first time, as shown in figure 4, when solid-state hard disk SSD is first storage
When, the workflow of storage control 11 is step S001- step S006:
Step S001 receives data to be written, after being written into data aggregate, carries out piecemeal alignment according to specified block size
It divides and obtains data block to be written (step S001 can be realized by the data processing unit 101 in Fig. 3);
Step S002 judges whether solid-state hard disk SSD is to store for the first time, if so then execute step S004 and step S003;
Step S003 is written into data block write-in solid-state hard disk SSD;
Step S004 establishes chained list according to data block to be written, which patrols for recording the first of data block to be written
Number is write in the covering for collecting address and its first logical address;
Step S005 writes number and establishes binary search tree as key assignments according to chained list to cover, which will cover
Number is write to be ranked up according to sequence from more to less;
Sequence is write data block corresponding to number in the covering of preceding N and made by step S006 according to the sequence of binary search tree
Frequently-used data library is established for frequently-used data block, the logical address of frequently-used data block is common logical address.
Fig. 5 is chained list, binary search tree and frequently-used data library variation diagram corresponding to Fig. 4, as shown in figure 5, covering is write time
Number N1 > N2 > N3 > N4 > N5 > N6.The process for establishing chained list, binary search tree and frequently-used data library is as shown in Figure 5.
Fig. 6 be new data store workflow schematic diagram, as shown in fig. 6, solid-state hard disk SSD it is non-when first used, and
When data to be written are new data (data never occurred in solid-state hard disk SSD), the workflow of storage control 11
Journey is step S101- step S106:
Step S101 is identical as step S001, and it will not be described here;
Step S102 judges whether solid-state hard disk SSD is to store for the first time, if it is not, thening follow the steps S102;
Step S103, the logical address for treating writing data blocks are judged, if the non-common logical address of logical address, holds
Row step S104 and step S105;
Step S104 is written into data block write-in solid-state hard disk SSD;
Step S105 is inserted into the first logical address of data block to be written, and covering the first logical address in chained list
Overwrite number is preset as 1, and executes step S106;
Step S106 updates binary search tree according to chained list, i.e., is inserted into new covering in binary search tree and writes number.
Fig. 7 is chained list, binary search tree and frequently-used data library variation diagram 2 corresponding to Fig. 6, as shown in fig. 7, covering is write time
Number N1 > N2 > N3 > N4 > N5 > N6 > N7, LBA7 are the first logical address of data block to be written, N7 right by the first logical address
Number is write in the covering answered, and after data block to be written is written, the variation of chained list, binary search tree and frequently-used data library is as schemed
Show.
Fig. 8 is that non-common data block stores workflow schematic diagram, as shown in figure 8, solid-state hard disk SSD is in non-first use
When, and when data to be written are non-frequently-used data (store in solid-state hard disk SSD, but be not belonging to frequently-used data library), it deposits
The workflow for storing up controller 11 is step S201- step S207:
Step S201- step S203 and step S101- step S103 operate identical, and it will not be described here;
Step S204 is written into data block and covers in solid-state hard disk SSD and writes;
Step S205 directly updates covering corresponding to the first logical address of data block to be written in chained list and writes number,
I.e. covering writes number and adds 1;
Step S206 updates binary search tree according to chained list, i.e., covering corresponding to the first logical address is write number more
Newly;
Step S207 after receiving N number of common logical address, judges N number of common logical address with the presence or absence of first logically
Location, and if it exists, will then belong to after common logical address, update before update and be not belonging to the logical address of common logical address as the
Two logical addresses delete the corresponding data block of the second logical address in frequently-used data library, and are written as non-common data block
Solid-state hard disk SSD, while data block corresponding to the first logical address being obtained from solid-state hard disk SSD and frequently-used data is written
Library.
Fig. 9 is chained list, a kind of variation diagram of binary search tree and frequently-used data library corresponding to Fig. 8, as shown in figure 9, covering
Write 1 > N2 of times N > N3 > N4 > N5 > N6, after data block to be written is written, chained list, binary search tree and frequently-used data library one
Kind variation is after data block to be written is written, on frequently-used data library without influence.
Figure 10 is chained list, binary search tree and frequently-used data library another kind variation diagram corresponding to Fig. 8, as shown in Figure 10,
1 > N2 of times N > N4 > N3 > N5 > N6 is write in covering, after data block to be written is written, chained list, binary search tree and frequently-used data library
Another variation be data block to be written write-in after, have change to frequently-used data library.
Figure 11 is that frequently-used data block stores workflow schematic diagram, and as shown in figure 11, solid-state hard disk SSD is in non-first use
When, and when data block to be written is frequently-used data block, the workflow of storage control 11 is step S301- step S306:
Step S301- step S302, identical as step S101- step S102, it will not be described here;
Step S303, the first logical address for treating writing data blocks are judged, if the first logical address is common patrols
Address is collected, S304 and step S305 are thened follow the steps;
Step S304 is written into data block and covers in frequently-used data library and writes;
Step S305- step S306 is identical as step S205- step S206, and it will not be described here;
Figure 12 is chained list, binary search tree and frequently-used data library variation diagram corresponding to Figure 11, and as shown in figure 12, covering is write
1 > N2 of times N > N3 > N4 > N5 > N6, the first logical address of data block to be written is LBA2, to write number be N3 for covering, write-in to
After writing data blocks, on frequently-used data library without influence.
Professional should further appreciate that, described in conjunction with the examples disclosed in the embodiments of the present disclosure
Unit and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, hard in order to clearly demonstrate
The interchangeability of part and software generally describes each exemplary composition and step according to function in the above description.
These functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.
Professional technician can use different methods to achieve the described function each specific application, but this realization
It should not be considered as beyond the scope of the present invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can be executed with hardware, processor
The combination of software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only memory
(ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technical field
In any other form of storage medium well known to interior.
Above-described specific embodiment has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that being not intended to limit the present invention the foregoing is merely a specific embodiment of the invention
Protection scope, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all include
Within protection scope of the present invention.
Claims (9)
1. a kind of solid state hard disk storage control, the storage control include:
Data processing unit, for generating data block to be written according to the metadata of data to be written and the data to be written,
And determine the first logical address of the data block to be written;
Data determining unit, for judging whether first logical address is common logical address;If described first logically
The non-common logical address in location, then export the data block to be written as non-common data block to solid state hard disk, if described
One logical address is common logical address, then generates write signal to be covered;
Chained list control unit updates chained list according to first logical address, updates logical address in the chained list and described
Number is write in the covering of first logical address;
Binary search tree control unit is write the covering of multiple logical addresses according to chained list update binary search tree secondary
Several sequences, and the common logical address is provided according to the sequence of the binary search tree;
Frequently-used data library control unit, for updating the frequently-used data block in frequently-used data library according to the common logical address;
And/or the data block covering to be written is written in the frequently-used data library according to the write signal to be covered, it is described
Frequently-used data inventory is stored in the caching of the storage control.
2. storage control according to claim 1, which is characterized in that the data block to be written includes: described to be written
Enter the data acquisition system for being aligned division acquisition according to specified block size after data aggregate, data processing unit in the storage control
The metadata of the data block to be written, the first logical address of the data block to be written are written in caching.
3. storage control according to claim 1, which is characterized in that if first logical address becomes common for the first time
Logical address, then frequently-used data library control unit will belong to common logical address but be not belonging to after updating described before update
The logical address of common logical address as the second logical address, and using data block corresponding to second logical address as
Non- common data block is exported to the solid state hard disk, and data block to be written corresponding to first logical address is written
The frequently-used data library.
4. storage control according to claim 1, which is characterized in that the data block to be written is new data block;Institute
Data determining unit is stated to export the data block to be written as non-common data block;The chained list control unit is by described
One logical address is inserted into the chained list, and number is write in the covering of first logical address and is predisposed to 1.
5. storage control according to claim 1, which is characterized in that the data block to be written is frequently-used data block;
The data determining unit judges first logical address for common logical address and exports write signal to be covered;The chain
The covering of first logical address is write number and adds 1 by table control unit;Frequently-used data library control unit according to it is described to
It covers write signal and the frequently-used data library is written into the data block covering to be written.
6. storage control described in one of -5 according to claim 1, which is characterized in that the binary search tree is to the covering
It writes number to sort according to sequence from more to less, it is normal that the sequence, which writes the corresponding logical address of number in the covering of preceding N,
With logical address, the corresponding data block of the common logical address is the frequently-used data block.
7. a kind of solid state hard disk date storage method, which is characterized in that the described method comprises the following steps:
Data block to be written is generated according to the metadata of data to be written and the data to be written, and determination is described to be written
First logical address of data block;
Judge whether first logical address is common logical address, if the non-common logical address of first logical address,
It then exports the data block to be written as non-common data block to solid state hard disk, if first logical address is common patrols
Address is collected, then generates write signal to be covered;
Chained list is updated according to first logical address, updates logical address in the chained list and first logical address
Number is write in covering;
Number sequence is write to the covering of at least one logical address in chained list, and logically according at least one after sequence
Location provides the common logical address;At least one logical address includes the first logical address;
The frequently-used data block in frequently-used data library is updated according to the common logical address;And/or according to described to be covered
The data block covering to be written is written in the frequently-used data library write signal, and the frequently-used data inventory is stored in storage control
In the caching of device.
8. the method according to the description of claim 7 is characterized in that the data block to be written includes: the data to be written
The data acquisition system for dividing and obtaining is aligned after polymerization according to specified block size, data processing unit saves described to be written in the buffer
First logical address of the metadata of data block, the data block to be written.
9. the method according to the description of claim 7 is characterized in that described update frequently-used data according to the common logical address
Library step, comprising: if first logical address becomes common logical address for the first time, will belong to before update and commonly use logically
Location, but be not belonging to the logical address of the common logical address as the second logical address after updating, and by second logic
Data block corresponding to address is exported as non-common data block to the solid state hard disk, and by the first logical address institute
The frequently-used data library is written in corresponding data block to be written.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510752334.9A CN105389128B (en) | 2015-11-06 | 2015-11-06 | A kind of solid state hard disk date storage method and storage control |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510752334.9A CN105389128B (en) | 2015-11-06 | 2015-11-06 | A kind of solid state hard disk date storage method and storage control |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105389128A CN105389128A (en) | 2016-03-09 |
CN105389128B true CN105389128B (en) | 2019-04-19 |
Family
ID=55421447
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510752334.9A Active CN105389128B (en) | 2015-11-06 | 2015-11-06 | A kind of solid state hard disk date storage method and storage control |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105389128B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106168883A (en) * | 2016-05-05 | 2016-11-30 | 诸葛晴凤 | A kind of efficient data tissue and access method |
CN110018897B (en) * | 2018-01-09 | 2023-05-26 | 阿里巴巴集团控股有限公司 | Data processing method and device and computing equipment |
CN109117098A (en) * | 2018-09-27 | 2019-01-01 | 郑州云海信息技术有限公司 | A kind of method of improve data transfer performance in solid state hard disk |
CN115599308B (en) * | 2022-11-28 | 2023-03-21 | 苏州浪潮智能科技有限公司 | Garbage recycling method and device for solid state disk, electronic equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101437046A (en) * | 2008-12-11 | 2009-05-20 | 成都市华为赛门铁克科技有限公司 | Method for processing data of solid-state hard disk, solid-state hard disk and network appliance |
CN101459679A (en) * | 2007-12-12 | 2009-06-17 | 华为技术有限公司 | Network storage device and data read-write control method |
CN102375693A (en) * | 2010-08-16 | 2012-03-14 | 成都市华为赛门铁克科技有限公司 | Consumption balance processing method and system as well as solid hard disk |
CN104657283A (en) * | 2015-02-04 | 2015-05-27 | 成都三零嘉微电子有限公司 | Method for improving read/write performance of NFTL (Nand flash translation layer) algorithm |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011022657A (en) * | 2009-07-13 | 2011-02-03 | Fujitsu Ltd | Memory system and information processor |
-
2015
- 2015-11-06 CN CN201510752334.9A patent/CN105389128B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101459679A (en) * | 2007-12-12 | 2009-06-17 | 华为技术有限公司 | Network storage device and data read-write control method |
CN101437046A (en) * | 2008-12-11 | 2009-05-20 | 成都市华为赛门铁克科技有限公司 | Method for processing data of solid-state hard disk, solid-state hard disk and network appliance |
CN102375693A (en) * | 2010-08-16 | 2012-03-14 | 成都市华为赛门铁克科技有限公司 | Consumption balance processing method and system as well as solid hard disk |
CN104657283A (en) * | 2015-02-04 | 2015-05-27 | 成都三零嘉微电子有限公司 | Method for improving read/write performance of NFTL (Nand flash translation layer) algorithm |
Also Published As
Publication number | Publication date |
---|---|
CN105389128A (en) | 2016-03-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9311015B2 (en) | Storage system capable of managing a plurality of snapshot families and method of operating thereof | |
US9146877B2 (en) | Storage system capable of managing a plurality of snapshot families and method of snapshot family based read | |
CN107102819B (en) | Method and equipment for writing data into solid state disk | |
CN105389128B (en) | A kind of solid state hard disk date storage method and storage control | |
KR102440370B1 (en) | System and method for identifying hot data and stream in a solid-state drive | |
CN107122130B (en) | Data deduplication method and device | |
US10445022B1 (en) | Optimization of log-structured merge (LSM) tree-based databases using object solid state drive (SSD) devices | |
US8225060B2 (en) | Data de-duplication by predicting the locations of sub-blocks within the repository | |
CN106874217A (en) | Accumulator system and control method | |
CN106874211A (en) | The control method of accumulator system and nonvolatile memory | |
US9495286B2 (en) | Method and arrangement for completion or recovery of data transactions in a flash type memory device using a commit process | |
CN110399333B (en) | Method, apparatus and computer program product for deleting snapshots | |
CN106527973A (en) | A method and device for data deduplication | |
CN110377233B (en) | SSD (solid State disk) reading performance optimization method and device, computer equipment and storage medium | |
CN107291405A (en) | A kind of NorFlash data managing method and device | |
WO2014157243A1 (en) | Storage control device, control method for storage control device, and control program for storage control device | |
CN110287152A (en) | A kind of method and relevant apparatus of data management | |
CN104077078B (en) | Read memory block, update the method and device of memory block | |
CN110389714A (en) | Method, apparatus and computer storage medium for data input and output | |
KR20040076313A (en) | Method of Seperated Buffer cache Management | |
CN106775456B (en) | A kind of data processing method, apparatus and system | |
US11402999B2 (en) | Adaptive wear leveling using multiple partitions | |
US9286204B2 (en) | Memory controller | |
CN107846327A (en) | A kind of processing method and processing device of network management performance data | |
KR20120039166A (en) | Nand flash memory system and method for providing invalidation chance to data pages |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |