CN106155588B - Information processing method and solid state hard disk - Google Patents
Information processing method and solid state hard disk Download PDFInfo
- Publication number
- CN106155588B CN106155588B CN201610509509.8A CN201610509509A CN106155588B CN 106155588 B CN106155588 B CN 106155588B CN 201610509509 A CN201610509509 A CN 201610509509A CN 106155588 B CN106155588 B CN 106155588B
- Authority
- CN
- China
- Prior art keywords
- read
- storage unit
- write
- write speed
- solid state
- 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
- G06F3/061—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
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
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)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
The embodiment of the present invention discloses a kind of information processing method applied to solid state hard disk, comprising: the write command that receiving host is sent determines the corresponding multiple Destination Storage Units of the write command based on address mapping table；Determine the read or write speed rank of multiple Destination Storage Units；By the corresponding write operation of the multiple Destination Storage Units of batch processing, wherein the corresponding write operation of Destination Storage Unit with identical read or write speed rank is handled in same a batch, updates address mapping table.Based on information processing method disclosed by the invention, the efficiency of solid state disk write data can be improved on the whole.The invention also discloses another information processing methods and solid state hard disk for being applied to solid state hard disk.
Description
Technical field
The invention belongs to solid state hard disk technical field more particularly to information processing method and solid state hard disks.
Background technique
Solid state hard disk (Solid State Drives, abbreviation SSD) is a kind of novel hard disk, mainly by controller, dynamic
State memory and multiple flash memory particles are constituted, wherein each flash memory particle includes data buffer zone and multiple storage units.Solid-state
Hard disk has the advantage that read or write speed is high, noiseless, operating temperature range is big, small in size and light-weight, at present in electronic equipment
In be widely used.
The read-write efficiency for how improving solid state hard disk is the important technological problems that those skilled in the art face.
Summary of the invention
In view of this, the purpose of the present invention is to provide solid state hard disk and its information processing method, it is hard to improve solid-state
The read-write efficiency of disk.
To achieve the above object, the invention provides the following technical scheme:
In a first aspect, the present invention provides a kind of information processing method, it is applied to solid state hard disk, the information processing method packet
Include: the write command that receiving host is sent determines the corresponding multiple Destination Storage Units of the write command based on address mapping table；Really
The read or write speed rank of fixed the multiple Destination Storage Unit, wherein the reading of the storage unit with identical read or write speed rank
The difference of writing rate is within a preset range；By the corresponding write operation of the multiple Destination Storage Unit of batch processing, wherein have phase
With the Destination Storage Unit of read or write speed rank, corresponding write operation is handled in same a batch, updates address mapping table.
Preferably, described to determine that the write command is corresponding more based on address mapping table in above- mentioned information processing method
A Destination Storage Unit, comprising: the free memory locations in the solid state hard disk are determined based on the address mapping table；Described
Select multiple storage units for meeting constraint condition as Destination Storage Unit in free memory locations.
Preferably, it in above- mentioned information processing method, selects multiple to meet constraint condition in the free memory locations
Storage unit as Destination Storage Unit, specifically: select multiple erasable numbers default in the free memory locations
Storage unit in time intervals.
Preferably, it in above- mentioned information processing method, selects multiple to meet constraint condition in the free memory locations
Storage unit as Destination Storage Unit, specifically: determine the access frequency of the corresponding M data block of the write command respectively
Rate, M are the integer greater than 1；According to the access frequency of the M data block, the corresponding read-write of the M data block is determined respectively
Speed step；Read or write speed rank read or write speed grade corresponding with the M data block is selected in the free memory locations
Not identical multiple storage units；Correspondingly, by data block write-in read or write speed rank read-write speed corresponding with the data block
Spend the identical Destination Storage Unit of rank.
Preferably, in above- mentioned information processing method, in initial phase, by the reading of the storage unit of the solid state hard disk
Writing rate rank is configured to same levels；In the solid state hard disk operation phase, according to preset strategy statistical data in flash memory
Transmission time between the data buffer zone and storage unit of grain, the read-write of the storage unit is determined according to the transmission time
Speed step.
Preferably, in above- mentioned information processing method, it is described according to preset strategy statistical data flash memory particle data
Transmission time between buffer area and storage unit, specifically: after reaching the default sampling interval, statistical data is in flash memory particle
Data buffer zone and storage unit between transmission time.
Second aspect, the present invention provide a kind of information processing method, are applied to solid state hard disk, the information processing method packet
Include: the reading instruction that receiving host is sent determines the corresponding multiple Destination Storage Units of the reading instruction based on address mapping table；Really
The read or write speed rank of fixed the multiple Destination Storage Unit, wherein the reading of the storage unit with identical read or write speed rank
The difference of writing rate is within a preset range；By the corresponding read operation of the multiple Destination Storage Unit of batch processing, wherein have phase
With the Destination Storage Unit of read or write speed rank, corresponding read operation is handled in same a batch.
Preferably, in above- mentioned information processing method, in initial phase, by the reading of the storage unit of the solid state hard disk
Writing rate rank is configured to same levels；In the solid state hard disk operation phase, according to preset strategy statistical data in flash memory
Transmission time between the data buffer zone and storage unit of grain, the read-write of the storage unit is determined according to the transmission time
Speed step.
Preferably, in above- mentioned information processing method, it is described according to preset strategy statistical data flash memory particle data
Transmission time between buffer area and storage unit, specifically: after reaching the default sampling interval, statistical data is in flash memory particle
Data buffer zone and storage unit between transmission time.
The third aspect, the present invention provide a kind of solid state hard disk, including controller, dynamic memory and multiple flash memory particles,
The flash memory particle includes data buffer zone and multiple storage units；
The write command that the controller receiving host is sent, determines that the write command is corresponding multiple based on address mapping table
Destination Storage Unit determines the read or write speed rank of the multiple Destination Storage Unit, stores by the multiple target of batch processing
The corresponding write operation of unit, and update address mapping table, wherein the Destination Storage Unit with identical read or write speed rank is corresponding
Write operation handled in same a batch；The reading instruction that the controller receiving host is sent, determines institute based on address mapping table
The corresponding multiple Destination Storage Units of reading instruction are stated, determine the read or write speed rank of the multiple Destination Storage Unit, at criticizing
Manage the corresponding read operation of the multiple Destination Storage Unit, wherein the Destination Storage Unit pair with identical read or write speed rank
The read operation answered is handled in same a batch；
Wherein, there is the difference of the read or write speed of the storage unit of identical read or write speed rank within a preset range.
Preferably, in above-mentioned solid state hard disk, the controller is determining that the write command is corresponding based on address mapping table
The aspect of multiple Destination Storage Units, is specifically used for: the controller determines the solid state hard disk based on the address mapping table
In free memory locations, select multiple storage units for meeting constraint condition to deposit in the free memory locations as target
Storage unit.
Preferably, in above-mentioned solid state hard disk, the controller selects multiple satisfactions to constrain in the free memory locations
Aspect of the storage unit of condition as Destination Storage Unit, is specifically used for: the controller is in the free memory locations
Select storage unit of multiple erasable numbers in preset times section.
Preferably, in above-mentioned solid state hard disk, the controller selects multiple satisfactions to constrain in the free memory locations
Aspect of the storage unit of condition as Destination Storage Unit, is specifically used for:
The controller determines the access frequency of the corresponding M data block of the write command respectively, according to the M data
The access frequency of block determines the corresponding read or write speed rank of the M data block respectively, selects in the free memory locations
The identical multiple storage units of read or write speed rank read or write speed rank corresponding with the M data block；The controller will
The identical Destination Storage Unit of read or write speed rank read or write speed rank corresponding with the data block is written in data block.
Preferably, it in initial phase, configures the read or write speed rank of the storage unit of the solid state hard disk to identical
Rank；The controller is also used to: in the solid state hard disk operation phase, according to preset strategy statistical data in flash memory particle
Transmission time between data buffer zone and storage unit determines the read or write speed of the storage unit according to the transmission time
Rank.
It can be seen that the invention has the benefit that
Information processing method disclosed by the invention, receiving host send write command after, based on address mapping table determination write
Corresponding multiple Destination Storage Units are instructed, are stored later according to each target of the read or write speed partition of the level of each Destination Storage Unit
Batch where unit, the corresponding write operation of Destination Storage Unit with identical read or write speed rank is at same a batch
Reason.
Information processing method disclosed by the invention, receiving host send reading instruction after, based on address mapping table determine reading
Corresponding multiple Destination Storage Units are instructed, are stored later according to each target of the read or write speed partition of the level of each Destination Storage Unit
Batch where unit, the corresponding read operation of Destination Storage Unit with identical read or write speed rank is at same a batch
Reason.
Based on information processing method disclosed by the invention, so that the higher Destination Storage Unit of read or write speed and read or write speed
Lower Destination Storage Unit is not in same batch processing, process of the higher Destination Storage Unit of read or write speed in same batch processing
In, which completes the time Destination Storage Unit minimum by read or write speed in the batch of read/write operation
It determines, the time which completes read/write operation is shorter, can improve the read-write of solid state hard disk on the whole
Data efficiency.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is a kind of flow chart of information processing method disclosed by the invention applied to solid state hard disk；
Fig. 2 is the flow chart of another information processing method disclosed by the invention applied to solid state hard disk；
Fig. 3 is the flow chart of another information processing method disclosed by the invention applied to solid state hard disk；
Fig. 4 is the flow chart of another information processing method disclosed by the invention applied to solid state hard disk；
Fig. 5 is the hardware structure diagram of solid state hard disk disclosed by the invention and host.
Specific embodiment
Solid state hard disk is mainly made of controller, dynamic memory and multiple flash memory particles.Wherein, each flash memory particle packet
Include data buffer zone and multiple storage units.From host to the process of solid state disk read-write data, host and solid-state are specifically included that
Data transmission procedure between the controller of hard disk, the data between the controller and dynamic memory of solid state hard disk are transmitted across
Data transmission procedure between journey and the controller and flash memory particle of solid state hard disk.
The bandwidth of interface and the controller of solid state hard disk and master between the controller and dynamic memory of solid state hard disk
The bandwidth of interface between machine is all very high, can be normally reached 10GB/s, and the controller of solid state hard disk and flash memory particle it
Between bandwidth it is relatively low, generally only 400MB/s.Therefore, the data between the controller of solid state hard disk and flash memory particle pass
Defeated process is the key factor for determining the read-write efficiency of solid state hard disk.
In order to improve the data transmission efficiency between the controller of solid state hard disk and flash memory particle, generally use at present parallel
The mode of processing.
Such as: the write command sent for host, the controller of solid state hard disk determine multiple Destination Storage Units, will
Multiple Destination Storage Units are divided into multiple groups, and data are written to first group of Destination Storage Unit in a parallel fashion later, when the
After one group of Destination Storage Unit completes write operation, then data are written to second group of Destination Storage Unit in a parallel fashion, when
After second group of Destination Storage Unit completes write operation, then data are written to third group Destination Storage Unit in a parallel fashion,
And so on, by data by batch multiple Destination Storage Units of write-in.
Such as: the controller determination of the reading instruction sent for host, solid state hard disk is stored with the more of corresponding data
Multiple Destination Storage Units are divided into multiple groups by a Destination Storage Unit, are stored in a parallel fashion from first group of target later
Unit reads data is deposited after first group of Destination Storage Unit completes read operation, then in a parallel fashion from second group of target
Storage unit reads data, after second group of Destination Storage Unit completes read operation, then in a parallel fashion from third group target
Storage unit reads data, and so on, by the data of the multiple Destination Storage Units storages of batch reading.
It is found by the applicant that:
Since the material of flash memory particle and technique etc. have differences, this makes the flash memory particle in the same solid state hard disk
Electrical characteristic is not identical, in addition, the storage unit in even same flash memory particle, each storage unit complete read operation or
Time required for write operation is also different.Also, with the variation of environment and using the passage of time, in solid state hard disk
The difference that each storage unit completes the time required for read operation or write operation can be increasing.With above-mentioned parallel mode
During reading and writing data, the access time of every batch of data is all limited by the most slow storage unit of read or write speed, reduces whole
The read-write efficiency of body.
The present invention discloses solid state hard disk and its information processing method, is writing data to flash memory particle or is reading from flash memory particle
Access handles using the lesser storage unit of read or write speed difference as a batch during, improves solid-state on the whole
The read-write efficiency of hard disk.
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, Fig. 1 is a kind of flow chart of information processing method disclosed by the invention applied to solid state hard disk.It should
Information processing method includes:
Step S11: the write command that receiving host is sent determines that the corresponding multiple targets of write command are deposited based on address mapping table
Storage unit.
Solid state hard disk preserves address mapping table, and address mapping table includes between the logical address and physical address of data
Mapping relations.After the controller of solid state hard disk receives the write command of host transmission, idle deposit is searched based on address mapping table
Storage unit determines multiple storage units in idle storage unit, and the multiple storage units determined are for storing host hair
The aforementioned multiple storage units determined are known as Destination Storage Unit for the ease of statement by the data to be stored sent.
Step S12: the read or write speed rank of multiple Destination Storage Units is determined.Wherein, there is identical read or write speed rank
Storage unit read or write speed difference within a preset range.
After determining the corresponding multiple Destination Storage Units of write command based on address mapping table, each target is determined respectively
The read or write speed rank of storage unit.The read or write speed rank of storage unit can characterize the read or write speed of the storage unit, tool
There is the storage unit of identical read or write speed rank, the difference of read or write speed is within a preset range.
Step S13: by the corresponding write operation of the multiple Destination Storage Units of batch processing, wherein there is identical read or write speed grade
The corresponding write operation of other Destination Storage Unit is handled in same a batch, updates address mapping table.
In existing processing method, due to the division of Destination Storage Unit be it is random, do not consider the storage of each target
The read or write speed of unit, it is therefore more likely that leading in each group Destination Storage Unit that there may be the lower targets of read or write speed to deposit
Storage unit.And the time that each group Destination Storage Unit completes write operation is all limited by the target storage that read or write speed is most slow in the group
Unit, the time that this causes each group Destination Storage Unit to complete write operation is longer, reduces the efficiency of solid state disk write data.
In step S13 of the invention, it is divided according to the read or write speed rank of multiple Destination Storage Units, is had
There is the corresponding write operation of Destination Storage Unit of identical read or write speed rank to be handled in same a batch.That is, will read-write
Speed is identical or the corresponding write operation of the lesser Destination Storage Unit of read or write speed difference is handled in same a batch, and reads and writes
The corresponding write operation of the biggish Destination Storage Unit of speed difference will not be in same batch processing.
Due to same batch processing be in multiple Destination Storage Units read or write speed is identical or read or write speed difference compared with
Small Destination Storage Unit, therefore, the higher Destination Storage Unit of read or write speed is during same a batch executes write operation, this batch
The time that secondary Destination Storage Unit completes write operation determines by the minimum Destination Storage Unit of read or write speed in the batch, rather than
Determined by the lower Destination Storage Unit of other read or write speeds, thus the batch target storage unit complete write operation time compared with
It is short, the efficiency of solid state disk write data can be improved on the whole.
Information processing method disclosed by the invention, receiving host send write command after, based on address mapping table determination write
Corresponding multiple Destination Storage Units are instructed, are stored later according to each target of the read or write speed partition of the level of each Destination Storage Unit
Batch where unit, the corresponding write operation of Destination Storage Unit with identical read or write speed rank is at same a batch
Reason.Based on information processing method disclosed by the invention, so that the higher Destination Storage Unit of read or write speed and read or write speed are lower
Destination Storage Unit not in same batch processing, the higher Destination Storage Unit of read or write speed during same batch processing,
The batch target storage unit completes the time of write operation, is determined by the minimum Destination Storage Unit of read or write speed in the batch,
The time that the batch target storage unit completes write operation is shorter, can improve the efficiency of solid state disk write data on the whole.
In above- mentioned information processing method, as an implementation, determine that write command is corresponding based on address mapping table
Multiple Destination Storage Units, specifically:
The free memory locations in solid state hard disk are determined based on address mapping table；
Select multiple storage units as Destination Storage Unit in free memory locations.
Solid state hard disk preserves address mapping table, and the controller of solid state hard disk is assured that solid-state using address mapping table
Free memory locations in hard disk select multiple storage units as Destination Storage Unit in free memory locations.
In above- mentioned information processing method, write command pair is determined based on address mapping table as a preferred implementation manner,
The multiple Destination Storage Units answered, specifically:
The free memory locations in solid state hard disk are determined based on address mapping table；
Select multiple storage units for meeting constraint condition as Destination Storage Unit in free memory locations.
In above-mentioned preferred embodiment, the controller of solid state hard disk selects multiple satisfactions to constrain in free memory locations
The storage unit of condition can advanced optimize the performance of solid state hard disk by the way that constraint condition is arranged as Destination Storage Unit.
In implementation, which can be diversified forms.Correspondingly, selecting multiple satisfactions in free memory locations about
The storage unit of beam condition has diversified forms as Destination Storage Unit.It is illustrated below with reference to Fig. 2 and Fig. 3.
Referring to fig. 2, Fig. 2 is the flow chart of another information processing method disclosed by the invention.The information processing method packet
It includes:
Step S21: the write command that receiving host is sent determines that the idle storage in solid state hard disk is single based on address mapping table
Member.
Step S22: storage unit of multiple erasable numbers in preset times section is selected in free memory locations.
Step S23: the read or write speed rank of multiple Destination Storage Units is determined.Wherein, there is identical read or write speed rank
Storage unit read or write speed difference within a preset range.
Step S24: by the corresponding write operation of the multiple Destination Storage Units of batch processing, wherein there is identical read or write speed grade
The corresponding write operation of other Destination Storage Unit is handled in same a batch, updates address mapping table.
The erasable number of flash memory particle is limited in solid state hard disk, when the erasable number of some flash memory particle reaches the upper limit
When, the data in the flash memory particle will be unable to read.In information processing method shown in Fig. 2, the controller of solid state hard disk is true
During the storage unit that sets the goal, using the erasable number of storage unit as a selection gist, in free memory locations
It selects storage unit of multiple erasable numbers in preset times section as Destination Storage Unit, on the one hand can guarantee solid-state
The balanced of each storage unit uses in hard disk, on the other hand can also be to avoid writing data into the storage list that will be broken down
Member ensures the safety of data.
Referring to Fig. 3, Fig. 3 is the flow chart of another information processing method disclosed by the invention.The information processing method packet
It includes:
Step S31: the write command that receiving host is sent determines that the idle storage in solid state hard disk is single based on address mapping table
Member.
Step S32: determining the access frequency of the corresponding M data block of write command respectively, and M is the integer greater than 1.
The write command that host is sent corresponds to multiple data blocks, is denoted as M data block, the controller of solid state hard disk is wanted
By the flash memory particle of M data block write-in solid state hard disk.User can have differences the access frequency of M data block, if will
The high high storage unit of data block deposit read or write speed of access frequency, then the time needed for subsequent reading data block compared with
It is short, it can be improved user experience.
Step S33: according to the access frequency of M data block, the corresponding read or write speed rank of M data block is determined respectively.
After the controller of solid state hard disk determines the access frequency of M data block respectively, according to the access frequency of M data block
The corresponding read or write speed rank of M data block is determined respectively.The reading that the access frequency and read or write speed rank of data block are characterized
Writing rate correlation, that is to say, that: the read-write that the corresponding read or write speed rank of the high data block of access frequency is characterized
Speed, the read or write speed that the corresponding read or write speed rank of the data block low higher than access frequency is characterized.
In implementation, the access frequency of data block and the mapping relations of read or write speed rank are preset, is determining M data
After the access frequency of block, the corresponding read or write speed rank of M data block can be quickly determined by the mapping relations.
Step S34: read or write speed rank read or write speed rank corresponding with M data block is selected in free memory locations
Identical multiple storage units.
After determining the corresponding read or write speed rank of M data block, the controller of solid state hard disk is in free memory locations
The identical multiple storage units of middle selection read or write speed rank read or write speed rank corresponding with M data block.
It is illustrated in conjunction with an example:
If the write command that host is sent corresponds to 16 data blocks, determined according to the access frequency of 16 data blocks each
The corresponding read or write speed rank of data block are as follows: rank 1, rank 2 and rank 4.So, the controller of solid state hard disk is stored in the free time
Unit selection at least one read or write speed rank is the free memory locations of rank 1, at least one read or write speed rank is rank 2
Free memory locations and at least one read or write speed rank are the free memory locations of rank 4, as Destination Storage Unit.
Step S35: the read or write speed rank of multiple Destination Storage Units is determined.Wherein, there is identical read or write speed rank
Storage unit read or write speed difference within a preset range.
Step S36: by the corresponding write operation of the multiple Destination Storage Units of batch processing, wherein there is identical read or write speed grade
The corresponding write operation of other Destination Storage Unit is handled in same a batch, and by data block write-in read or write speed rank with should
The identical Destination Storage Unit of the corresponding read or write speed rank of data block updates address mapping table.
It is illustrated still with examples detailed above: in the process by the corresponding write operation of the multiple Destination Storage Units of batch processing
In, it is rank 1 by data block write-in read or write speed rank if the corresponding read or write speed rank of data block is rank 1
Destination Storage Unit, if the corresponding read or write speed rank of data block be rank 2, by the data block be written read or write speed
Rank is the Destination Storage Unit of rank 2, if the corresponding read or write speed rank of data block is rank 4, by the data block
The Destination Storage Unit that read or write speed rank is rank 4 is written.Also, the Destination Storage Unit with identical read or write speed rank
Corresponding write operation is handled in same a batch.
In information processing method shown in Fig. 3, using the access frequency of the corresponding M data block of write command as determining mesh
A foundation for marking storage unit has identical during write operation corresponding by the multiple Destination Storage Units of batch processing
The corresponding write operation of the Destination Storage Unit of read or write speed rank is handled in same a batch, and it is hard can to improve on the whole solid-state
Disk writes data efficiency；In addition, by the way that read or write speed rank read or write speed rank corresponding with the data block is written in data block
Identical Destination Storage Unit, so that the high storage unit of data block deposit read or write speed that access frequency is high, shortens subsequent reads
Time needed for taking the data block, it can be improved user experience.
Present invention information processing method disclosed above, lays particular emphasis on the process of solid state disk write data.The present invention is hereafter public
Another information processing method is opened, the process that solid state hard disk reads data is laid particular emphasis on.
Referring to fig. 4, Fig. 4 is the flow chart of another information processing method disclosed by the invention applied to solid state hard disk.
The information processing method includes:
Step S41: the reading instruction that receiving host is sent determines the corresponding multiple targets of the reading instruction based on address mapping table
Storage unit.
After the controller of solid state hard disk receives the reading instruction of host transmission, which is determined based on address mapping table
The aforementioned multiple storage units determined are known as target and deposited by multiple storage units where the data answered for the ease of statement
Storage unit.
Step S42: the read or write speed rank of multiple Destination Storage Units is determined.Wherein, there is identical read or write speed rank
Storage unit read or write speed difference within a preset range
Step S43: by the corresponding read operation of the multiple Destination Storage Units of batch processing.Wherein, there is identical read or write speed grade
The corresponding read operation of other Destination Storage Unit is handled in same a batch.
In existing processing method, due to the division of Destination Storage Unit be it is random, do not consider the storage of each target
The read or write speed of unit, it is therefore more likely that leading in each group Destination Storage Unit that there may be the lower targets of read or write speed to deposit
Storage unit.And the time that each group Destination Storage Unit completes read operation is all limited by the target storage that read or write speed is most slow in the group
Unit, the time that this causes each group Destination Storage Unit to complete read operation is longer, reduces the efficiency that solid state hard disk reads data.
In step S43 of the invention, it is divided according to the read or write speed rank of multiple Destination Storage Units, is had
There is the corresponding read operation of Destination Storage Unit of identical read or write speed rank to be handled in same a batch.That is, will read-write
Speed is identical or the corresponding read operation of the lesser Destination Storage Unit of read or write speed difference is handled in same a batch, and reads and writes
The corresponding read operation of the biggish Destination Storage Unit of speed difference will not be in same batch processing.
Due to same batch processing be in multiple Destination Storage Units read or write speed is identical or read or write speed difference compared with
Small Destination Storage Unit, therefore, the higher Destination Storage Unit of read or write speed is during same a batch executes read operation, this batch
The time that secondary Destination Storage Unit completes read operation determines by the minimum Destination Storage Unit of read or write speed in the batch, rather than
Determined by the lower Destination Storage Unit of other read or write speeds, thus the batch target storage unit complete read operation time compared with
It is short, the efficiency that solid state hard disk reads data can be improved on the whole.
Information processing method disclosed by the invention, receiving host send reading instruction after, based on address mapping table determine reading
Corresponding multiple Destination Storage Units are instructed, are stored later according to each target of the read or write speed partition of the level of each Destination Storage Unit
Batch where unit, the corresponding read operation of Destination Storage Unit with identical read or write speed rank is at same a batch
Reason.Based on information processing method disclosed by the invention, so that the higher Destination Storage Unit of read or write speed and read or write speed are lower
Destination Storage Unit not in same batch processing, the higher Destination Storage Unit of read or write speed during same batch processing,
The batch target storage unit completes the time of read operation, is determined by the minimum Destination Storage Unit of read or write speed in the batch,
The time that the batch target storage unit completes read operation is shorter, can improve the efficiency that solid state hard disk reads data on the whole.
In present invention information processing method disclosed above, in initial phase, by the storage unit of solid state hard disk
Read or write speed rank is configured to same levels.In addition, the read or write speed of storage unit can by data flash memory particle data
Transmission time between buffer area and storage unit is measured, and therefore, in the solid state hard disk operation phase, is counted according to preset strategy
Transmission time of the data between the data buffer zone and storage unit of flash memory particle, determines storage unit according to transmission time
Read or write speed rank.
In implementation, transmission time and read or write speed rank of the data between data buffer zone and storage unit are preset
Mapping relations, the read or write speed rank of storage unit is determined according to the mapping relations.
The inspection of transmission time is carried out during data are transmitted between the data buffer zone of flash memory particle and storage unit
It surveys, adverse effect can be caused to the transmission rate of data.
In view of the variation of the read or write speed of storage unit is more slow, and the variation of the read or write speed of storage unit is deposited
In certain rule, as a preferred implementation manner, according to preset strategy statistical data flash memory particle data buffer zone with
Transmission time between storage unit, specifically:
After reaching the default sampling interval, biography of the statistical data between the data buffer zone and storage unit of flash memory particle
The defeated time.
Based on the preferred embodiment, the influence to message transmission rate can be reduced.
Invention additionally discloses a kind of solid state hard disk, hardware configuration can be found in Fig. 5.The solid state hard disk 10 includes controller
100, dynamic memory 200 and multiple flash memory particles 300, flash memory particle 300 include data buffer zone and multiple storage units.
The write command that 100 receiving host 20 of controller is sent, determines the corresponding multiple mesh of write command based on address mapping table
Storage unit is marked, determines the read or write speed rank of multiple Destination Storage Units, it is corresponding by the multiple Destination Storage Units of batch processing
Write operation, and update address mapping table.Wherein, the corresponding write operation of Destination Storage Unit with identical read or write speed rank exists
It is handled with a batch.
The reading instruction that 100 receiving host 20 of controller is sent, determines the corresponding multiple mesh of reading instruction based on address mapping table
Storage unit is marked, determines the read or write speed rank of multiple Destination Storage Units, it is corresponding by the multiple Destination Storage Units of batch processing
Read operation.Wherein, the corresponding read operation of Destination Storage Unit with identical read or write speed rank is handled in same a batch.
The read or write speed rank of storage unit can characterize the read or write speed of the storage unit, have identical read or write speed grade
The difference of the read or write speed of other storage unit is within a preset range.
Solid state hard disk disclosed by the invention is determined after the read/write instruction for receiving host transmission based on address mapping table
The corresponding multiple Destination Storage Units of the read/write instruction, it is each according to the read or write speed partition of the level of each Destination Storage Unit later
Batch where Destination Storage Unit, the corresponding read/write operation of Destination Storage Unit with identical read or write speed rank is same
A batch is handled.Due to the higher Destination Storage Unit of read or write speed with the lower Destination Storage Unit of read or write speed not same
One batch processing, for the higher Destination Storage Unit of read or write speed during same batch processing, the batch target storage unit is complete
It is determined at the time of read/write operation by the minimum Destination Storage Unit of read or write speed in the batch, the batch target storage unit
The time for completing read/write operation is shorter, can improve the read-write data efficiency of solid state hard disk on the whole.
As an implementation, controller 100 is determining that the corresponding multiple targets of write command are deposited based on address mapping table
The aspect of storage unit, is specifically used for: controller 100 determines the free memory locations in solid state hard disk based on address mapping table,
Select multiple storage units as Destination Storage Unit in free memory locations.
As another embodiment, controller 100 is determining the corresponding multiple targets of write command based on address mapping table
The aspect of storage unit, is specifically used for: controller 100 determines the free memory locations in solid state hard disk based on address mapping table,
Select multiple storage units for meeting constraint condition as Destination Storage Unit in free memory locations.
As another example, controller 100 selects multiple storage lists for meeting constraint condition in free memory locations
Aspect of the member as Destination Storage Unit, be specifically used for: controller 100 selects multiple erasable numbers to exist in free memory locations
Storage unit in preset times section.
As another example, controller 100 selects multiple storage lists for meeting constraint condition in free memory locations
Aspect of the member as Destination Storage Unit, is specifically used for: controller 100 determines the visit of the corresponding M data block of write command respectively
It asks frequency, according to the access frequency of M data block, determines the corresponding read or write speed rank of M data block respectively, stored in the free time
The identical multiple storage units of read or write speed rank read or write speed rank corresponding with M data block are selected in unit.Correspondingly,
Controller 100 stores the identical target of data block write-in read or write speed rank read or write speed rank corresponding with data block single
Member.
Wherein, the read or write speed correlation that the access frequency of data block and read or write speed rank are characterized.Also
It is to say: the read or write speed that the corresponding read or write speed rank of the high data block of access frequency is characterized, the number low higher than access frequency
The read or write speed characterized according to the corresponding read or write speed rank of block.
In implementation, the access frequency of data block and the mapping relations of read or write speed rank are preset, is determining M data
After the access frequency of block, the corresponding read or write speed rank of M data block can be determined at high speed by the mapping relations.
Solid state hard disk disclosed by the invention configures the read or write speed rank of storage unit to identical in initial phase
Rank.Controller 100 is also used to: in the solid state hard disk operation phase, according to preset strategy statistical data flash memory particle data
Transmission time between buffer area and storage unit determines the read or write speed rank of storage unit according to transmission time.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.For solid-state disclosed in embodiment
For hard disk, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method portion
It defends oneself bright.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (14)
1. a kind of information processing method, it is applied to solid state hard disk, which is characterized in that the information processing method includes:
The write command that receiving host is sent, determines the corresponding multiple Destination Storage Units of the write command based on address mapping table；
Determine the read or write speed rank of the multiple Destination Storage Unit, wherein the storage list with identical read or write speed rank
The difference of the read or write speed of member is within a preset range；
By the corresponding write operation of the multiple Destination Storage Unit of batch processing, wherein the target with identical read or write speed rank
The corresponding write operation of storage unit is handled in same a batch, updates address mapping table.
2. information processing method according to claim 1, which is characterized in that described to be write based on described in address mapping table determination
Instruct corresponding multiple Destination Storage Units, comprising:
The free memory locations in the solid state hard disk are determined based on the address mapping table；
Select multiple storage units for meeting constraint condition as Destination Storage Unit in the free memory locations.
3. information processing method according to claim 2, which is characterized in that selected in the free memory locations multiple
Meet the storage unit of constraint condition as Destination Storage Unit, specifically:
Storage unit of multiple erasable numbers in preset times section is selected in the free memory locations.
4. information processing method according to claim 2, which is characterized in that
Select multiple storage units for meeting constraint condition as Destination Storage Unit in the free memory locations, specifically
Are as follows: the access frequency of the corresponding M data block of the write command is determined respectively, and M is the integer greater than 1；According to the M data
The access frequency of block determines the corresponding read or write speed rank of the M data block respectively；It is selected in the free memory locations
The identical multiple storage units of read or write speed rank read or write speed rank corresponding with the M data block；
Correspondingly, the identical target of data block write-in read or write speed rank read or write speed rank corresponding with the data block is deposited
Storage unit.
5. information processing method according to any one of claim 1 to 4, which is characterized in that
In initial phase, same levels are configured by the read or write speed rank of the storage unit of the solid state hard disk；
In the solid state hard disk operation phase, according to preset strategy statistical data in the data buffer zone of flash memory particle and storage list
Transmission time between member determines the read or write speed rank of the storage unit according to the transmission time.
6. information processing method according to claim 5, which is characterized in that described to be dodged according to preset strategy statistical data
The transmission time between the data buffer zone of particle and storage unit is deposited, specifically:
After reaching the default sampling interval, when transmission of the statistical data between the data buffer zone and storage unit of flash memory particle
Between.
7. a kind of information processing method, it is applied to solid state hard disk, which is characterized in that the information processing method includes:
The reading instruction that receiving host is sent, determines the corresponding multiple Destination Storage Units of the reading instruction based on address mapping table；
Determine the read or write speed rank of the multiple Destination Storage Unit, wherein the storage list with identical read or write speed rank
The difference of the read or write speed of member is within a preset range；
By the corresponding read operation of the multiple Destination Storage Unit of batch processing, wherein the target with identical read or write speed rank
The corresponding read operation of storage unit is handled in same a batch.
8. information processing method according to claim 7, which is characterized in that in initial phase, by the solid state hard disk
The read or write speed rank of storage unit be configured to same levels；
In the solid state hard disk operation phase, according to preset strategy statistical data in the data buffer zone of flash memory particle and storage list
Transmission time between member determines the read or write speed rank of the storage unit according to the transmission time.
9. information processing method according to claim 8, which is characterized in that described to be dodged according to preset strategy statistical data
The transmission time between the data buffer zone of particle and storage unit is deposited, specifically:
After reaching the default sampling interval, when transmission of the statistical data between the data buffer zone and storage unit of flash memory particle
Between.
10. a kind of solid state hard disk, which is characterized in that including controller, dynamic memory and multiple flash memory particles, the flash memory
Grain includes data buffer zone and multiple storage units；
The write command that the controller receiving host is sent, determines the corresponding multiple targets of the write command based on address mapping table
Storage unit determines the read or write speed rank of the multiple Destination Storage Unit, by the multiple Destination Storage Unit of batch processing
Corresponding write operation, and update address mapping table, wherein the Destination Storage Unit with identical read or write speed rank is corresponding to be write
Operation is handled in same a batch；The reading instruction that the controller receiving host is sent, determines the reading based on address mapping table
Corresponding multiple Destination Storage Units are instructed, determine the read or write speed grade of the corresponding multiple Destination Storage Units of the reading instruction
Not, by the corresponding read operation of the corresponding multiple Destination Storage Units of reading instruction described in batch processing, wherein have identical read or write speed
The corresponding read operation of the Destination Storage Unit of rank is handled in same a batch；
The difference of the read or write speed of storage unit with identical read or write speed rank is within a preset range.
11. solid state hard disk according to claim 10, which is characterized in that the controller is determined based on address mapping table
The aspect of the corresponding multiple Destination Storage Units of the write command, is specifically used for:
The controller determines the free memory locations in the solid state hard disk based on the address mapping table, deposits in the free time
Select multiple storage units for meeting constraint condition as Destination Storage Unit in storage unit.
12. solid state hard disk according to claim 11, which is characterized in that the controller is in the free memory locations
Aspect of multiple storage units for meeting constraint condition as Destination Storage Unit is selected, is specifically used for:
The controller selects storage unit of multiple erasable numbers in preset times section in the free memory locations.
13. solid state hard disk according to claim 11, which is characterized in that the controller is in the free memory locations
Aspect of multiple storage units for meeting constraint condition as Destination Storage Unit is selected, is specifically used for:
The controller determines the access frequency of the corresponding M data block of the write command respectively, according to the M data block
Access frequency determines the corresponding read or write speed rank of the M data block respectively, and read-write is selected in the free memory locations
The identical multiple storage units of speed step read or write speed rank corresponding with the M data block；
The identical mesh of read or write speed rank read or write speed rank corresponding with the data block is written in data block by the controller
Mark storage unit.
14. solid state hard disk described in any one of 0 to 13 according to claim 1, which is characterized in that in initial phase, by institute
The read or write speed rank for stating the storage unit of solid state hard disk is configured to same levels；
The controller is also used to: in the solid state hard disk operation phase, according to preset strategy statistical data in flash memory particle
Transmission time between data buffer zone and storage unit determines the read or write speed of the storage unit according to the transmission time
Rank.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610509509.8A CN106155588B (en) | 2016-06-30 | 2016-06-30 | Information processing method and solid state hard disk |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610509509.8A CN106155588B (en) | 2016-06-30 | 2016-06-30 | Information processing method and solid state hard disk |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106155588A CN106155588A (en) | 2016-11-23 |
| CN106155588B true CN106155588B (en) | 2019-04-26 |
Family
ID=57350761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610509509.8A Active CN106155588B (en) | 2016-06-30 | 2016-06-30 | Information processing method and solid state hard disk |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106155588B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106201347B (en) * | 2016-07-04 | 2019-07-26 | 联想(北京)有限公司 | Information processing method and solid state hard disk |
| CN116339643B (en) * | 2023-05-26 | 2023-08-04 | 苏州浪潮智能科技有限公司 | Formatting method, formatting device, formatting equipment and formatting medium for disk array |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101154189A (en) * | 2006-09-27 | 2008-04-02 | 三星电子株式会社 | Mapping apparatus and method for non-volatile memory supporting different cell types |
| CN103049349A (en) * | 2012-11-29 | 2013-04-17 | 记忆科技(深圳)有限公司 | Snapshot method and system based on tiered storage |
| CN103927265A (en) * | 2013-01-04 | 2014-07-16 | 深圳市龙视传媒有限公司 | Content hierarchical storage device, content acquisition method and content acquisition device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10048895B2 (en) * | 2013-12-06 | 2018-08-14 | Concurrent Ventures, LLC | System and method for dynamically load balancing storage media devices based on a mid-range performance level |
-
2016
- 2016-06-30 CN CN201610509509.8A patent/CN106155588B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101154189A (en) * | 2006-09-27 | 2008-04-02 | 三星电子株式会社 | Mapping apparatus and method for non-volatile memory supporting different cell types |
| CN103049349A (en) * | 2012-11-29 | 2013-04-17 | 记忆科技(深圳)有限公司 | Snapshot method and system based on tiered storage |
| CN103927265A (en) * | 2013-01-04 | 2014-07-16 | 深圳市龙视传媒有限公司 | Content hierarchical storage device, content acquisition method and content acquisition device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106155588A (en) | 2016-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105117180B (en) | A kind of date storage method and device and solid state disk | |
| CN106201347B (en) | Information processing method and solid state hard disk | |
| CN104115133B (en) | For method, system and the equipment of the Data Migration for being combined non-volatile memory device | |
| CN101447928B (en) | Method and device for processing fragment information | |
| CN108810041A (en) | A kind of data write-in of distributed cache system and expansion method, device | |
| CN106201923B (en) | Method for reading and writing data and device | |
| CN104881259B (en) | A kind of data processing method and device and storage device | |
| CN106155588B (en) | Information processing method and solid state hard disk | |
| CN104699422A (en) | Determination method and determination device of cache data | |
| CN105573917B (en) | Techniques for selecting an amount of reserved space | |
| CN106610903A (en) | Tiered storage system, storage controller, and method for deduplication and storage tiering | |
| CN108334460B (en) | Data cache method and device | |
| CN108334284A (en) | Tail delay perception foreground garbage collection algorithm | |
| CN109471843A (en) | A kind of metadata cache method, system and relevant apparatus | |
| CN104461384B (en) | A kind of method for writing data and storage device | |
| CN110377233A (en) | SSD reading performance optimization method, device, computer equipment and storage medium | |
| US8601200B2 (en) | Controller for solid state disk which controls access to memory bank | |
| CN109445687A (en) | A kind of date storage method and protocol server | |
| CN105260139B (en) | A kind of disk management method and system | |
| JP2013206154A (en) | Data presence/absence determination device, data presence/absence determination method and data presence/absence determination program | |
| CN109256166A (en) | The method for deleting and flash memories of flash memories | |
| CN105302474B (en) | Control the method for write operation and the controller of flash memory of flash memory | |
| CN110321298A (en) | A kind of time interval determines method, apparatus, electronic equipment and medium | |
| CN105094742B (en) | A kind of method and apparatus for writing data | |
| CN109446115A (en) | A kind of mapping table management method, device and computer readable storage medium |
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 |