CN107391393A - A kind of statistical method and device of FTL mapping tables - Google Patents

A kind of statistical method and device of FTL mapping tables Download PDF

Info

Publication number
CN107391393A
CN107391393A CN201710630630.0A CN201710630630A CN107391393A CN 107391393 A CN107391393 A CN 107391393A CN 201710630630 A CN201710630630 A CN 201710630630A CN 107391393 A CN107391393 A CN 107391393A
Authority
CN
China
Prior art keywords
ftl
functions
mapping tables
lba
ftl functions
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.)
Pending
Application number
CN201710630630.0A
Other languages
Chinese (zh)
Inventor
赵宝林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhengzhou Yunhai Information Technology Co Ltd
Original Assignee
Zhengzhou Yunhai Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhengzhou Yunhai Information Technology Co Ltd filed Critical Zhengzhou Yunhai Information Technology Co Ltd
Priority to CN201710630630.0A priority Critical patent/CN107391393A/en
Publication of CN107391393A publication Critical patent/CN107391393A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00—Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02—Addressing or allocation; Relocation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00—Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02—Addressing or allocation; Relocation
    • G06F12/0223—User address space allocation, e.g. contiguous or non contiguous base addressing
    • G06F12/023—Free address space management
    • G06F12/0238—Memory management in non-volatile memory, e.g. resistive RAM or ferroelectric memory

Abstract

The embodiment of the invention discloses a kind of statistical method and device of FTL mapping tables, wherein, method includes, and is used to represent FTL mapping tables by defining FTL functions, and define invalid value, the invalid value PBA value maximum not less than solid state hard disc physical space for FTL functions；When detecting LBA write-ins, according to the data newly write and current FTL functions, the FTL functions are fitted again, the FTL functions are updated with realizing.The space-consuming of FTL mapping tables is greatly reduced, improves space availability ratio；Be advantageous to preserve complete data volume during solid state hard disc power down, lift the storage performance of solid state hard disc；The space that the storage of FTL functions takes is less, will increasing for corresponding user's space, advantageously reduces product cost；Because space needed for FTL functions is less, the requirement for physical device also just reduces, and can greatly improve the flexibility of physics board typesetting.

Description

A kind of statistical method and device of FTL mapping tables
Technical field
The present embodiments relate to technical field of memory, more particularly to a kind of statistical method and device of FTL mapping tables.
Background technology
With big data, the fast development of cloud computing, data are presented huge explosion formula and increased, growth and the user's logarithm of data According to the requirement of storage performance increase, force memory technology also to obtain corresponding development, solid state hard disc because its read or write speed is fast, Energy consumption is relatively low, and is widely used.
At present in the firmware algorithm of solid state hard disc, due to the inherent characteristic of NAND chip, it is impossible to repeat to a PBA Middle write-in data, are so caused during solid state hard disc use, and LBA corresponds to PBA relation (FTL mapping tables) continuous Change, typically represent LBA (Logical with FTL (Flash translation layer, flash translation layer (FTL)) mapping table Block Address, logical block addresses) mapped between PBA (Physical Block Address, physical block address) Relation.LBA is used in FTL mapping tables, and as index, contents in table is mainly PBA values and other related contents, and such FTL reflects The scale of firing table is directly proportional with the capacity of solid state hard disc, i.e. the list item of the corresponding FTL mapping table of a LBA, solid state hard disc Amount of capacity decides the size of FTL mapping tables.
In order to can normally recover FTL mapping tables after power is turned off, any data, FTL mapping tables are not lost in guarantee Need to be stored in NAND.But as the growth of mass data, the capacity of solid state hard disc are also increasingly becoming big, corresponding FTL The scale of mapping table also becomes increasing, and accordingly, DDR the and NAND spaces stored needed for FTL mapping tables are also just unusual Greatly.Need the huge table being written to from DDR in NAND in lower electric process, it is necessary to spend the time it is longer preserve it is complete FTL mapping tables, due to power-off protection of solid state disk electric capacity can not be infinitely it is big, so may result in FTL mapping tables protect During depositing, occur powering off, FTL mapping table loss generation phenomenon so that when next time start make imperfect so as to cause to preserve Gone to recover the contents such as FTL tables and the metadata of correlation with more times.
The content of the invention
The purpose of the embodiment of the present invention is to provide a kind of statistical method and device of FTL mapping tables, to lift solid state hard disc Storage performance.
In order to solve the above technical problems, the embodiment of the present invention provides following technical scheme：
On the one hand the embodiment of the present invention provides a kind of statistical method of FTL mapping tables, including：
FTL functions are defined, and invalid value is defined for the FTL functions, the invalid value is empty not less than solid state hard disc physics Between maximum PBA values, for representing FTL mapping tables；
When detecting LBA write-ins, according to the data newly write and current FTL functions, the FTL functions are carried out again Fitting, the FTL functions are updated with realizing.
Optionally, the data that the basis newly writes and current FTL functions, fitting again is carried out to the FTL functions and is wrapped Include：
Point corresponding to the LBA changed is removed from current FTL functions；
According to the data newly write, the current FTL functions are fitted, the FTL functions after being updated.
Optionally, the data that the basis newly writes, the current FTL functions are fitted including：
According to the data newly write, the current FTL functions are fitted using Logistic Nonlinear Quasis hop algorithm.
Optionally, the data newly write in the basis and current FTL functions, are fitted again to the FTL functions Before, in addition to：
According to the speed of write-in data, it is determined that to the update mode of the FTL functions, the update mode includes single-point list Secondary renewal, the renewal of multiple spot single or multiple spot repeatedly update.
Optionally, the definition FTL functions include：
A variety of history FTL function datas are trained by way of machine learning, to obtain function library；
Based on each function in the function library, FTL functions are defined according to default rule.
Optionally, the FTL functions are：
In formula, fi(x) it is the multiple functions included in the function library, ai、biFor fitting parameter, x is to be worth corresponding to LBA, PBA=FTL (LBA).
Optionally, before the definition FTL functions, in addition to：
Constrained optimization is carried out to the FTL mapping tables according to default algorithm, so that the scale drop of corresponding FTL functions It is low, reduce the amount of calculation that function is fitted again.
Optionally, it is described that FTL mapping tables progress constrained optimization is included according to default algorithm：
Data attribute is sorted out to LBA according to corresponding to LBA, so that same type of LBA is placed in FTL mapping tables Meet on the PBA of preset rules.
On the other hand the embodiment of the present invention provides a kind of statistic device of FTL mapping tables, including：
Function representation module, invalid value is defined for defining FTL functions, and for the FTL functions, the invalid value is not small In the PBA values that solid state hard disc physical space is maximum, for representing FTL mapping tables；
Function update module, for when detecting LBA write-ins, according to the data that newly write and current FTL functions, to institute State FTL functions to be fitted again, the FTL functions are updated with realizing.
Optionally, the function update module is that point removes from current FTL functions corresponding to the LBA that will have been changed；Root According to the data newly write, the current FTL functions are fitted, the module of the FTL functions after being updated.
The embodiments of the invention provide a kind of statistical method of FTL mapping tables, is used to represent FTL by defining FTL functions Mapping table, and define invalid value, the invalid value PBA value maximum not less than solid state hard disc physical space for FTL functions；Work as inspection When measuring LBA write-ins, according to the data newly write and current FTL functions, the FTL functions are fitted again, to realize The FTL functions are updated.
The advantages of technical scheme that the application provides, is, uses FTL function representation FTL mapping tables, it is only necessary to function Coefficient and prototype preserved, avoid to take using substantial amounts of space and store huge array to complete FTL mapping tables Expression, greatly reduce the space-consumings of FTL mapping tables, improve space availability ratio；And due to FTL functions take space compared with Few, the time used when being stored is also just relatively fewer, the time being written to from DDR in NAND is shortened, so as to have Beneficial to complete data volume is preserved during solid state hard disc power down, the storage performance of solid state hard disc is lifted；FTL function storages account for Space is less, will increasing for corresponding user's space, advantageously reduces product cost；Due to space needed for FTL functions Less, when being stored in DDR of FTL functions, will reduce, the requirement for physical device to DDR demand in the process of running Also just reduce, the flexibility of physics board typesetting can be greatly improved.
In addition, the embodiment of the present invention provides corresponding realization device also directed to the statistical method of FTL mapping tables, further So that methods described has more practicality, described device has the advantages of corresponding.
Brief description of the drawings
, below will be to embodiment or existing for the clearer explanation embodiment of the present invention or the technical scheme of prior art The required accompanying drawing used is briefly described in technology description, it should be apparent that, drawings in the following description are only this hair Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can be with root Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic flow sheet of the statistical method of FTL mapping tables provided in an embodiment of the present invention；
Fig. 2 is the schematic flow sheet of the statistical method of another FTL mapping tables provided in an embodiment of the present invention；
Fig. 3 is a kind of embodiment structure chart of the statistic device of FTL mapping tables provided in an embodiment of the present invention；
Fig. 4 is another embodiment structure chart of the statistic device of FTL mapping tables provided in an embodiment of the present invention.
Embodiment
In order that those skilled in the art more fully understand the present invention program, with reference to the accompanying drawings and detailed description The present invention is described in further detail.Obviously, described embodiment is only part of the embodiment of the present invention, rather than Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise Lower obtained every other embodiment, belongs to the scope of protection of the invention.
Term " first ", " second ", " the 3rd " " in the description and claims of this application and above-mentioned accompanying drawing Four " etc. be for distinguishing different objects, rather than for describing specific order.In addition term " comprising " and " having " and Their any deformations, it is intended that cover non-exclusive include.Such as contain the process of series of steps or unit, method, The step of system, product or equipment are not limited to list or unit, but the step of may include not list or unit.
After the technical scheme of the embodiment of the present invention is described, the various non-limiting realities of detailed description below the application Apply mode.
Referring first to Fig. 1, Fig. 1 is that a kind of flow of statistical method of FTL mapping tables provided in an embodiment of the present invention is illustrated Figure, the embodiment of the present invention may include herein below：
S101：FTL functions are defined, and invalid value is defined for the FTL functions, the invalid value is not less than solid state hard disc thing The maximum PBA values in space are managed, for representing FTL mapping tables.
FTL functions are used to represent FTL mapping tables, such as f (x), x can be LBA, and f (x) is PBA, and both are represented using f (x) Mapping relations.FTL tables are represented using function fashion, it is only necessary to the coefficient and prototype of function are preserved, avoided Taken using substantial amounts of space and store huge array to complete the expression of FTL tables；The function is defined as FTL functions (FTL tables Up to formula).
When solid state hard disc initializes, that is, have not been written to before any data, all FTL list items are all invalid , all return values of FTL functions are defined as invalid value, the FTL functions are an initial constant function, and invalid value can be One larger numerical value, specific value can be chosen according to specific actual conditions, and the application does not do any restriction to this, still It may not exceed the maximum PBA values of physical space.
FTL tables are replaced using FTL function fashions, a representation are simply replaced with into line representation, for function table Up to formula there is still a need for function parameter more than comparison, but scale of the number of function parameter not with FTL tables is proportional； FTL functions are that the combination of many kinds of function is indicated, and define a kind of mode of FTL functions and can be：
A variety of history FTL function datas are trained by way of machine learning, to obtain function library；
With each function in the function library, FTL functions are defined according to default rule.
Each historical data is trained using machine learning algorithm, obtains basic function storehouse, the letter in these function libraries Number represents a kind of mapping relations between PBA and LBA, using these limited basic functions, is determined according to default rule Adopted FTL functions, default rule can be those skilled in the art by test of many times and study, and different application scenarios are determined Different Rule, the application do not do any restriction to this.Under a kind of embodiment, the expression formula for defining FTL functions can For：
In formula, fi(x) it is the multiple functions included in the function library, i.e. fi(x) the n function to be included in function library Prototype f1(x)、f2(x)、……、fn(x)；ai、biFor fitting parameter, x is to be worth corresponding to LBA, PBA=FTL (LBA).
So when x is equal to fixed LBA, corresponding PBA=FTL (LBA) can be got, this completes FTL The expression of function.
S102：When detecting LBA write-ins, according to the data newly write and current FTL functions, the FTL functions are entered Row is fitted again, and the FTL functions are updated with realizing.
During solid state hard disc use, continuous or discrete LBA write-ins are had, will be to right in existing FTL tables The value answered is modified, as long as changing the value on certain corresponding point for FTL functions, detailed process can be：
Point corresponding to the LBA changed is removed from current FTL functions；
According to the data newly write, the current FTL functions are fitted, the FTL functions after being updated.
For example, in no write-in data, f (x)=5,5 be invalid value.When the data is written, i.e., x changes When, f (x) is not 5, it is necessary to which by 5, this point removes, and is fitted with new write-in data with current function, obtains new function Substituted.
According to the data newly write, the current FTL functions are fitted using Logistic Nonlinear Quasis hop algorithm, Certainly, can be also fitted using other fitting algorithms, the application does not do any restriction to this.
The fit procedure of FTL functions belongs to the category of mathematical statistics and logistic regression, for the LBA of solid state hard disc FTL tables Completely random is may be considered with PBA, so being likely to occur iterations mistake using the method for linear fit and linear regression Greatly, larger is probably that can not obtain accurate fitting result, uses logistic nonlinear fittings, the curve based on RBF The drawbacks of the methods of fitting, radial neural network effectively can avoid linear method from bringing, can also use a variety of non-here Linear method combines the mode being corrected.
In technical scheme provided in an embodiment of the present invention, FTL function representation FTL mapping tables are used, it is only necessary to function Coefficient and prototype preserved, avoid to take using substantial amounts of space and store huge array to complete FTL mapping tables Expression, greatly reduce the space-consumings of FTL mapping tables, improve space availability ratio；And due to FTL functions take space compared with Few, the time used when being stored is also just relatively fewer, the time being written to from DDR in NAND is shortened, so as to have Beneficial to complete data volume is preserved during solid state hard disc power down, the storage performance of solid state hard disc is lifted；FTL function storages account for Space is less, will increasing for corresponding user's space, advantageously reduces product cost；Due to space needed for FTL functions Less, when being stored in DDR of FTL functions, will reduce, the requirement for physical device to DDR demand in the process of running Also just reduce, the flexibility of physics board typesetting can be greatly improved.
,, please present invention also provides another embodiment based on above-described embodiment under a kind of specific embodiment Refering to Fig. 2, specifically may include：
S201：FTL functions are defined, and invalid value is defined for the FTL functions, the invalid value is not less than solid state hard disc thing The maximum PBA values in space are managed, for representing FTL mapping tables；
Specifically, it can describe unanimously, just do not repeating herein with S101.
S202：When detecting LBA write-ins, it is determined that to the update mode of the FTL functions, the update mode includes single The renewal of point single, the renewal of multiple spot single or multiple spot repeatedly update.
The update mode of FTL functions can be determined according to the speed of write-in data, when write-in data are slower, can used single Secondary single-point renewal, when write-in data are very fast, the renewal of multiple spot single or multiple spot can be used repeatedly to update, this does not influence the application Realization.
S203：Constrained optimization is carried out to the FTL mapping tables according to default algorithm, so that the rule of corresponding FTL functions Mould reduces, and reduces the amount of calculation that function is fitted again.
The contents in table of FTL mapping tables is approximate completely random during solid state hard disc use, so results in FTL Mapping table it is larger, so as to FTL functions it is also relatively more.Mapping table can be constrained using algorithm, such as can basis Data attribute is sorted out to LBA corresponding to LBA, so that same type of LBA, which is placed in FTL mapping tables, meets preset rules PBA on, such as in a region of division；Also LBA can be segmented, is also segmented PBA, a certain section of LBA consolidates Fixed falls in one section of PBA, is random in this section, can so substantially reduce its randomness；Certainly, it can also be used His mode, the application do not do any restriction to this.
S204：According to the data newly write and current FTL functions, the FTL functions are fitted again, with realization pair The FTL functions are updated.
Specifically, it can describe unanimously, just do not repeating herein with S102.
Artificial participation is added in use, adds various algorithms and the FTL tables of this approximate random are changed into having one Set pattern rule, the scale of so corresponding FTL functions will substantially reduce, and reduce it and reconstruct the amount of calculation of conjunction, improve whole The operating efficiency of body；In addition, reducing the space-consuming of FTL functions, space availability ratio is improved.
The embodiment of the present invention provides corresponding realization device also directed to the statistical method of FTL mapping tables, further such that Methods described has more practicality.The statistic device of FTL mapping tables provided in an embodiment of the present invention is introduced below, hereafter The statistical method of the statistic device of the FTL mapping tables of description and above-described FTL mapping tables can be mutually to should refer to.
Referring to Fig. 3, Fig. 3 is the statistic device of FTL mapping tables provided in an embodiment of the present invention in a kind of embodiment Under structure chart, the device may include：
Function representation module 301, invalid value, the invalid value are defined for defining FTL functions, and for the FTL functions The PBA value maximum not less than solid state hard disc physical space, for representing FTL mapping tables；
Function update module 302, for when detecting LBA write-ins, according to the data that newly write and current FTL functions, The FTL functions are fitted again, the FTL functions are updated with realizing.
In some embodiments of the embodiment of the present invention, the function update module 302 will can have been changed Point removes from current FTL functions corresponding to LBA；According to the data newly write, the current FTL functions are fitted, obtained The module of FTL functions after to renewal.
In other embodiments of the present embodiment, the function representation module 301 can also for example include：
Training data unit 3011, for being trained by way of machine learning to a variety of history FTL function datas, To obtain function library；
Definition unit 3012, for based on each function in the function library, FTL letters to be defined according to default rule Number.
Optionally, in some embodiments of the present embodiment, referring to Fig. 4, described device may include：
Update mode determining module 303, for the speed according to write-in data, it is determined that the renewal side to the FTL functions Formula, the update mode include the renewal of single-point single, the renewal of multiple spot single or multiple spot and repeatedly updated.
In other embodiment, described device can also for example include：
Optimization module 304, for carrying out constrained optimization to the FTL mapping tables according to default algorithm, so that accordingly The scale of FTL functions reduces, and reduces the amount of calculation that function is fitted again.
In a kind of specific mode, the optimization module 304 can be that data attribute is carried out to LBA according to corresponding to LBA Sort out, so that same type of LBA is placed on the module met in FTL mapping tables on the PBA of preset rules.
The function of each functional module of the statistic device of FTL mapping tables described in the embodiment of the present invention can be according to the above method Method specific implementation in embodiment, its specific implementation process are referred to the associated description of above method embodiment, herein not Repeat again.
From the foregoing, it will be observed that the embodiment of the present invention uses FTL function representation FTL mapping tables, it is only necessary to the coefficient and original of function Type is preserved, and is avoided and is taken the huge array of storage to complete the expression of FTL mapping tables using substantial amounts of space, significantly The space-consuming of FTL mapping tables is reduced, improves space availability ratio；And because the space that FTL functions take is less, deposited The time used during storage is also just relatively fewer, shortens the time being written to from DDR in NAND, hard in solid-state so as to be advantageous to Complete data volume is preserved during disk power down, lifts the storage performance of solid state hard disc；FTL functions storage take space compared with It is few, will increasing for corresponding user's space, advantageously reduce product cost；Because space needed for FTL functions is less, running During when being stored in DDR of FTL functions, DDR demand will be reduced, the requirement for physical device also just reduce, energy Enough greatly improve the flexibility of physics board typesetting.
Each embodiment is described by the way of progressive in this specification, what each embodiment stressed be with it is other The difference of embodiment, between each embodiment same or similar part mutually referring to.For dress disclosed in embodiment For putting, because it is corresponded to the method disclosed in Example, so description is fairly simple, related part is referring to method part Explanation.
Professional further appreciates that, with reference to the unit of each example of the embodiments described herein description And algorithm steps, can be realized with electronic hardware, computer software or the combination of the two, in order to clearly demonstrate hardware and The interchangeability of software, the composition and step of each example are generally described according to function in the above description.These Function is performed with hardware or software mode actually, application-specific and design constraint depending on technical scheme.Specialty Technical staff can realize described function using distinct methods to each specific application, but this realization should not Think beyond the scope of this invention.
Directly it can be held with reference to the step of method or algorithm that the embodiments described herein describes with hardware, processor Capable software module, or the two combination are implemented.Software module can be placed in random access memory (RAM), internal memory, read-only deposit Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology In any other form of storage medium well known in field.
The statistical method and device of a kind of FTL mapping tables provided by the present invention are described in detail above.This Apply specific case in text to be set forth the principle and embodiment of the present invention, the explanation of above example is only intended to Help to understand method and its core concept of the invention.It should be pointed out that for those skilled in the art, Without departing from the principles of the invention, some improvement and modification can also be carried out to the present invention, these are improved and modification also falls Enter in the protection domain of the claims in the present invention.

Claims (10)

  1. A kind of 1. statistical method of FTL mapping tables, it is characterised in that including：
    FTL functions are defined, and invalid value is defined for the FTL functions, the invalid value is not less than solid state hard disc physical space most Big PBA values, for representing FTL mapping tables；
    When detecting LBA write-ins, according to the data newly write and current FTL functions, the FTL functions are intended again Close, the FTL functions are updated with realizing.
  2. 2. the statistical method of FTL mapping tables according to claim 1, it is characterised in that the data that the basis newly writes With current FTL functions, fitting again is carried out to the FTL functions to be included：
    Point corresponding to the LBA changed is removed from current FTL functions；
    According to the data newly write, the current FTL functions are fitted, the FTL functions after being updated.
  3. 3. the statistical method of FTL mapping tables according to claim 2, it is characterised in that the data that the basis newly writes, The current FTL functions are fitted including：
    According to the data newly write, the current FTL functions are fitted using Logistic Nonlinear Quasis hop algorithm.
  4. 4. the statistical method of FTL mapping tables according to claim 1, it is characterised in that in the number that the basis newly writes According to current FTL functions, to the FTL functions carry out again be fitted before, in addition to：
    According to the speed of write-in data, it is determined that to the update mode of the FTL functions, the update mode includes single-point single more Newly, the renewal of multiple spot single or multiple spot repeatedly update.
  5. 5. the statistical method of the FTL mapping tables according to claim 1-4 any one, it is characterised in that the definition FTL Function includes：
    A variety of history FTL function datas are trained by way of machine learning, to obtain function library；
    Based on each function in the function library, FTL functions are defined according to default rule.
  6. 6. the statistical method of FTL mapping tables according to claim 5, it is characterised in that the FTL functions are：
    <mrow> <mi>F</mi> <mi>T</mi> <mi>L</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>)</mo> </mrow> <mo>=</mo> <munderover> <mo>&amp;Pi;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <mrow> <mo>(</mo> <msub> <mi>a</mi> <mi>i</mi> </msub> <msub> <mi>f</mi> <mi>i</mi> </msub> <mo>(</mo> <mi>x</mi> <mo>)</mo> <mo>+</mo> <msub> <mi>b</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>;</mo> </mrow>
    In formula, fi(x) it is the multiple functions included in the function library, ai、biFor fitting parameter, x is to be worth corresponding to LBA, PBA =FTL (LBA).
  7. 7. the statistical method of the FTL mapping tables according to claim 1-4 any one, it is characterised in that in the definition Before FTL functions, in addition to：
    Constrained optimization is carried out to the FTL mapping tables according to default algorithm, so that the scale of corresponding FTL functions reduces, subtracted The amount of calculation that small function is fitted again.
  8. 8. the statistical method of FTL mapping tables according to claim 7, it is characterised in that described according to default algorithm pair The FTL mapping tables, which carry out constrained optimization, to be included：
    Data attribute is sorted out to LBA according to corresponding to LBA, meets so that same type of LBA is placed in FTL mapping tables On the PBA of preset rules.
  9. A kind of 9. statistic device of FTL mapping tables, it is characterised in that including：
    Function representation module, invalid value is defined for defining FTL functions, and for the FTL functions, the invalid value is not less than solid The maximum PBA values in state hard disc physical space, for representing FTL mapping tables；
    Function update module, for when detecting LBA write-ins, according to the data that newly write and current FTL functions, to described FTL functions are fitted again, and the FTL functions are updated with realizing.
  10. 10. the statistic device of FTL mapping tables according to claim 9, it is characterised in that the function update module is will Point removes from current FTL functions corresponding to the LBA changed；According to the data newly write, the current FTL functions are carried out Fitting, the module of the FTL functions after being updated.
CN201710630630.0A 2017-07-28 2017-07-28 A kind of statistical method and device of FTL mapping tables Pending CN107391393A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710630630.0A CN107391393A (en) 2017-07-28 2017-07-28 A kind of statistical method and device of FTL mapping tables

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710630630.0A CN107391393A (en) 2017-07-28 2017-07-28 A kind of statistical method and device of FTL mapping tables

Publications (1)

Publication Number Publication Date
CN107391393A true CN107391393A (en) 2017-11-24

Family

ID=60342927

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710630630.0A Pending CN107391393A (en) 2017-07-28 2017-07-28 A kind of statistical method and device of FTL mapping tables

Country Status (1)

Country Link
CN (1) CN107391393A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110895597A (en) * 2018-09-12 2020-03-20 长鑫存储技术有限公司 Transcoding logical function calculation method and device, storage medium and electronic equipment

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104516823A (en) * 2013-09-30 2015-04-15 华为技术有限公司 Method and device for storing data
CN105224478A (en) * 2015-09-25 2016-01-06 联想(北京)有限公司 A kind of formation of mapping table, renewal and restoration methods and electronic equipment
US20160048448A1 (en) * 2013-03-25 2016-02-18 Ajou University Industry-Academic Cooperation Foundation Method for mapping page address based on flash memory and system therefor
CN106547703A (en) * 2016-10-08 2017-03-29 华中科技大学 A kind of FTL optimization methods based on block group structure

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160048448A1 (en) * 2013-03-25 2016-02-18 Ajou University Industry-Academic Cooperation Foundation Method for mapping page address based on flash memory and system therefor
CN104516823A (en) * 2013-09-30 2015-04-15 华为技术有限公司 Method and device for storing data
CN105224478A (en) * 2015-09-25 2016-01-06 联想(北京)有限公司 A kind of formation of mapping table, renewal and restoration methods and electronic equipment
CN106547703A (en) * 2016-10-08 2017-03-29 华中科技大学 A kind of FTL optimization methods based on block group structure

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
厦门大学数据库实验室 林子雨: "第3章 闪存转换层", 《HTTP://DBLAB.XMU.EDU.CN/POST/4548/》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110895597A (en) * 2018-09-12 2020-03-20 长鑫存储技术有限公司 Transcoding logical function calculation method and device, storage medium and electronic equipment
CN110895597B (en) * 2018-09-12 2022-04-19 长鑫存储技术有限公司 Transcoding logical function calculation method and device, storage medium and electronic equipment

Similar Documents

Publication Publication Date Title
CN105242871B (en) A kind of method for writing data and device
CN110321247A (en) Memory system
CN107437110A (en) The piecemeal convolution optimization method and device of convolutional neural networks
CN103019887A (en) Data backup method and device
CN104756088A (en) Flexible wear management for non-volatile memory
CN104615594B (en) A kind of data-updating method and device
CN104077235A (en) Method of partitioning physical block and memory system thereof
CN106354890B (en) A kind of implementation method of the file system of the random access based on N-ary tree construction
CN105980992B (en) A kind of storage system, the method for identification data block stability and device
CN106779057A (en) The method and device of the calculating binary neural network convolution based on GPU
CN106775474A (en) A kind of Nand Flash abrasion equilibrium methods, device and memory
CN107153707A (en) A kind of Hash table construction method and system for nonvolatile memory
CN104714891B (en) A kind of flash data management method and device
CN104750432B (en) A kind of date storage method and device
CN103473266A (en) Solid state disk and method for deleting repeating data thereof
CN110795363B (en) Hot page prediction method and page scheduling method of storage medium
CN106970930A (en) Message, which is sent, determines method and device, tables of data creation method and device
CN110532200B (en) Memory system based on hybrid memory architecture
CN104462388B (en) A kind of redundant data method for cleaning based on tandem type storage medium
CN108733324A (en) A kind of data read-write method of solid state disk, device, equipment and storage medium
CN105917303A (en) Controller, method for identifying data block stability and storage system
CN103455534A (en) Document clustering method and device
CN110413454A (en) Data re-establishing method, device and storage medium based on storage array
CN109284233A (en) A kind of rubbish recovering method and relevant apparatus of storage system
CN108762989A (en) Date storage method, device, equipment and the readable storage medium storing program for executing of solid state disk

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20171124