CN103049312A - Input/output (IO) optimizing processing method and system thereof - Google Patents
Input/output (IO) optimizing processing method and system thereof Download PDFInfo
- Publication number
- CN103049312A CN103049312A CN2012105215744A CN201210521574A CN103049312A CN 103049312 A CN103049312 A CN 103049312A CN 2012105215744 A CN2012105215744 A CN 2012105215744A CN 201210521574 A CN201210521574 A CN 201210521574A CN 103049312 A CN103049312 A CN 103049312A
- Authority
- CN
- China
- Prior art keywords
- ftl
- translation layer
- flash translation
- piece
- described flash
- 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
Links
Images
Abstract
The invention is suitable for the technical field of storage and provides an input/output (IO) optimizing processing method and a system thereof. The method includes: obtaining state characteristics of a flash translation layer; and selecting appropriate IO and/or application data in an IQ queue according to the state characteristics of the flash translation layer to perform optimizing processing. The IO optimizing processing method and the system of the IO optimizing processing method improve coordination of the application data and the flash translation layer and performance of the flash translation layer.
Description
Technical field
The present invention relates to technical field of memory, relate in particular to a kind of method and system thereof of IO optimization process.
Background technology
It is fast that flash memory possesses access speed, noiselessness, and the little characteristics of dispelling the heat are widely used in storage market.Because the physical medium characteristics of flash memory, there are some limited-access, it can single byte mode read or write, but erasing must be a whole block, write for covering simultaneously, must first the valid data on the piece be read in the internal memory, then wipe monoblock, again with valid data with new data more together in the write-in block, this process is called for short " reading-revise-write ".
In addition, in SSD (solid state disk), usually encapsulate Flash File System data management system-NAND FTL (Flash Translation Layer, flash translation layer (FTL)) and also be referred to as FTL (Flash TranslationLayer, flash translation layer (FTL)).FTL is a conversion layer between a nand flash memory chip and the basic document system, and it makes operating system can access nand flash memory equipment with file system as access hard disk.FTL holistic management flash equipment comprises from bottom flash devices allocation piece, address translation, consecutive mean read-write and refuse collection.In some flash equipment, can in hardware, realize a part of FTL.In the FTL of prior art realizes, often its function is realized in the control chip of a sealing or standalone module in, often provide less interface to show the internal work state.That is to say that application data and FTL lack coordination, cause the FTL performance lower, be unfavorable for IO (input/output, input and output) optimization process.
In summary, existing IO optimization process technology obviously exists inconvenience and defective in actual use, so be necessary to be improved.
Summary of the invention
For above-mentioned defective, the object of the present invention is to provide a kind of method and system thereof of IO optimization process, with the harmony between raising application data and the flash translation layer (FTL) and the performance of flash translation layer (FTL).
To achieve these goals, the invention provides a kind of method of IO optimization process, described method comprises the steps:
Obtain the status flag of flash translation layer (FTL);
The priority processing of carrying out according to suitable IO and/or application data in the status flag selection IO formation of described flash translation layer (FTL).
According to described method, the described step of obtaining the status flag of flash translation layer (FTL) comprises:
Obtain described flash translation layer (FTL) and carrying out the page or leaf of garbage reclamation and/or the information of piece; And/or
Obtain the information of the piece of the ongoing balance abrasion of described flash translation layer (FTL); And/or
Obtain that described flash translation layer (FTL) is ongoing to be read-revise-information of the piece write.
According to described method, described status flag according to described flash translation layer (FTL) selects that the suitable step of carrying out priority processing comprises in the IO formation:
Select with described flash translation layer (FTL) carrying out garbage reclamation page and/or the relevant IO of piece carry out priority processing; And/or
Selection is carried out priority processing with the relevant IO of the piece of the ongoing balance abrasion of described flash translation layer (FTL); And/or
Select to read-to revise with described flash translation layer (FTL) is ongoing-the relevant IO of piece that writes carries out priority processing.
According to described method, when application corresponding to IO of processing at described flash translation layer (FTL) had write cache device system, described status flag according to described flash translation layer (FTL) selected that the suitable step of carrying out priority processing comprises in the IO formation:
Select with described flash translation layer (FTL) carrying out garbage reclamation page and/or the relevant junk data of piece carry out priority processing; And/or
Selection is carried out priority processing with the relevant junk data of the piece of the ongoing balance abrasion of described flash translation layer (FTL); And/or
Select to read-to revise with described flash translation layer (FTL) is ongoing-the relevant junk data of piece write carries out priority processing.
According to described method, before the step of the described status flag that obtains flash translation layer (FTL), comprise:
Record the step of the status flag of described flash translation layer (FTL).
In order to realize another goal of the invention of the present invention, the present invention also provides a kind of system of IO optimization process, and described system comprises:
Acquisition module is for the status flag that obtains flash translation layer (FTL);
Processing module is used for selecting suitable IO and/or the application data of IO formation to carry out priority processing according to the status flag of described flash translation layer (FTL).
According to described system, described acquisition module comprises:
First obtains submodule, is used for obtaining described flash translation layer (FTL) and is carrying out the page or leaf of garbage reclamation and/or the information of piece; And/or
Second obtains submodule, for the information of the piece that obtains the ongoing balance abrasion of described flash translation layer (FTL); And/or
The 3rd obtains submodule, is used for obtaining that described flash translation layer (FTL) is ongoing to be read-revise-information of the piece write.
According to described system, described processing module comprises:
First processes submodule, and the page or leaf and/or the relevant IO of piece that are carrying out garbage reclamation for selection and described flash translation layer (FTL) carry out priority processing; And/or
Second processes submodule, is used for selection and carries out priority processing with the relevant IO of the piece of the ongoing balance abrasion of described flash translation layer (FTL); And/or
The 3rd processes submodule, be used for selecting reading-revising with described flash translation layer (FTL) is ongoing-the relevant IO of piece that writes carries out priority processing.
According to described system, when application corresponding to IO of processing at described flash translation layer (FTL) has write cache device system, described first process submodule select with described flash translation layer (FTL) carrying out garbage reclamation page and/or the relevant junk data of piece carry out priority processing; And/or
Described second processes the submodule selection carries out priority processing with the relevant junk data of the piece of the ongoing balance abrasion of described flash translation layer (FTL); And/or
The described the 3rd processes submodule selects to read-revise with described flash translation layer (FTL) is ongoing-and the relevant junk data of piece write carries out priority processing.
According to described system, described system also comprises:
Logging modle is for the status flag that records described flash translation layer (FTL).
The present invention is by obtaining the status flag of flash translation layer (FTL); Then select the priority processing of carrying out of suitable IO in the IO formation and/or application data according to the status flag of described flash translation layer (FTL).FTL is combined with application, preferred, by the state of FTL detection self, initiatively obtaining data from IO formation or application processes, thereby accelerated the storage efficiency of application data, promoted the IO performance of using, the harmony between raising application data and the FTL and the performance of FTL.
Description of drawings
Fig. 1 is the system architecture schematic diagram of the IO optimization process that provides of first embodiment of the invention;
Fig. 2 be the present invention second and third, the system architecture schematic diagram of the IO optimization process that provides of five embodiment;
Fig. 3 is the method flow diagram of the IO optimization process that provides of sixth embodiment of the invention;
Fig. 4 is the application that provides of one embodiment of the invention and the mutual schematic diagram of flash translation layer (FTL);
Fig. 5 is the method flow diagram of the IO optimization process that provides of one embodiment of the invention.
Embodiment
In order to make purpose of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, is not intended to limit the present invention.
Referring to Fig. 1, a kind of system 100 of IO optimization process is provided in the first embodiment of the present invention, described system comprises:
In this is implemented, at first obtain the status flag of flash translation layer (FTL) by acquisition module 10, processing module 20 can be grasped the situation that current flash translation layer (FTL) is processed IO by the status flag of flash translation layer (FTL), and IO and/or the application data that then will be fit to priority processing are processed in advance.Can improve like this harmony between application data and the FTL and the performance of FTL.
Referring to Fig. 2, in the second embodiment of the present invention, acquisition module 10 comprises:
First obtains submodule 11, is used for obtaining described flash translation layer (FTL) and is carrying out the page or leaf of garbage reclamation and/or the information of piece; And/or
Second obtains submodule 12, for the information of the piece that obtains the ongoing balance abrasion of described flash translation layer (FTL); And/or
The 3rd obtains submodule 13, is used for obtaining that described flash translation layer (FTL) is ongoing to be read-revise-information of the piece write.
In this embodiment, first obtain submodule 11 and obtain page or leaf and/or the information of piece that described flash translation layer (FTL) is carrying out garbage reclamation; To grasp current relevant IO disposition by the page or leaf of these garbage reclamation and/or the information of piece; Second obtains the information that submodule 12 obtains the piece of the ongoing balance abrasion of described flash translation layer (FTL), and the information of the piece by these balance abrasions then also will be grasped the situation of the corresponding I that current flash translation layer (FTL) processing; In addition, the 3rd obtains submodule 13 will obtain also that described flash translation layer (FTL) is ongoing to be read-revise-information of the piece write, to grasp the situation of the corresponding I that current flash translation layer (FTL) processing.
Referring to Fig. 2, in the third embodiment of the present invention, processing module 20 comprises:
The 3rd processes submodule 23, be used for selecting reading-revising with described flash translation layer (FTL) is ongoing-the relevant IO of piece that writes carries out priority processing.
In this embodiment, first processes submodule 21, the second processing submodule 22 and the 3rd processing submodule 23 selects respectively corresponding relevant IO to carry out priority processing, to timely relevant IO be processed like this, reduce the time that IO processes, improve the efficient that IO processes.
In the fourth embodiment of the present invention, when application corresponding to IO of processing at described flash translation layer (FTL) has write cache device system, described first process submodule 21 select with described flash translation layer (FTL) carrying out garbage reclamation page and/or relevant dirty (rubbish) data of piece carry out priority processing; And/or
Described second processes submodule 22 selections carries out priority processing with relevant dirty (rubbish) data of the piece of the ongoing balance abrasion of described flash translation layer (FTL); And/or
The described the 3rd processes submodule 23 selects to read-revise with described flash translation layer (FTL) is ongoing-and relevant dirty (rubbish) data of piece write carry out priority processing.
In this embodiment, first processes submodule 21, the second processing submodule 22 and the 3rd processing submodule 23 processes corresponding application data respectively immediately, thereby has accelerated the storage efficiency of application data.Therefore, flash translation layer (FTL) initiatively obtains data and processes by detecting the state of self from IO formation or application, not only accelerated the storage efficiency of application data, has also promoted the IO performance of using.
Referring to Fig. 2, in the fifth embodiment of the present invention, system 100 also comprises:
In this embodiment, logging modle 30 comprises the key message of record: the page or leaf, the block message that 1) are carrying out garbage reclamation; 2) carry out the block message 3 of balance abrasion) block message reading-revise-write.Can in time grasp current solid state hard disc according to these information and need data to be processed.
In above-mentioned a plurality of embodiment, a plurality of modules of this system 100 can be software units, hardware cell or software and hardware combining unit.
Referring to Fig. 3, in the sixth embodiment of the present invention, provide a kind of method of IO optimization process, described method comprises the steps:
Among the step S301, acquisition module 10 obtains the status flag of flash translation layer (FTL);
Among the step S302, processing module 20 is carried out priority processing according to suitable IO and/or application data in the status flag selection IO formation of described flash translation layer (FTL).
In this embodiment, the method of the coordination of FTL and application is provided, concrete as for the address translation among the FTL, balance abrasion (wear-leveling), garbage reclamation (Garbage Collector), realize with FTL of the prior art, do not do the description emphasis here.
In the seventh embodiment of the present invention, described step S301 comprises:
First obtains submodule 11 obtains page or leaf and/or the information of piece that described flash translation layer (FTL) is carrying out garbage reclamation; And/or
Second obtains the information that submodule 12 obtains the piece of the ongoing balance abrasion of described flash translation layer (FTL); And/or
The 3rd obtains submodule 13 obtains that described flash translation layer (FTL) is ongoing to be read-revise-information of the piece write.
In this embodiment, by a plurality of submodules of acquisition module 10, obtain respectively the information of the relevant data block of processing under a plurality of states of flash translation layer (FTL).Preferably, acquisition module 10 and processing module 20 all can be arranged in the flash translation layer (FTL).
In the eighth embodiment of the present invention, described step S302 comprises:
First process submodule 21 select with described flash translation layer (FTL) carrying out garbage reclamation page and/or the relevant IO of piece carry out priority processing; And/or
Second processes submodule 22 selections carries out priority processing with the relevant IO of the piece of the ongoing balance abrasion of described flash translation layer (FTL); And/or
The 3rd processes submodule 23 selects to read-revise with described flash translation layer (FTL) is ongoing-and the relevant IO of piece that writes carries out priority processing.
A plurality of submodules in the processing module 20 eigenstate current according to flash translation layer (FTL) selects suitable IO to process in this embodiment, to improve the storage efficiency of application data, promoted the IO performance of using.
In the ninth embodiment of the present invention, when the application corresponding to IO of described flash translation layer (FTL) processing had write cache device system, described step S302 comprised:
First process submodule 21 select with described flash translation layer (FTL) carrying out garbage reclamation page and/or relevant dirty (rubbish) data of piece carry out priority processing; And/or
Second processes submodule 22 selections carries out priority processing with relevant dirty (rubbish) data of the piece of the ongoing balance abrasion of described flash translation layer (FTL); And/or
The 3rd processes submodule 23 selects to read-revise with described flash translation layer (FTL) is ongoing-and relevant dirty (rubbish) data of piece write carry out priority processing.
In this embodiment, suitable IO carries out priority processing in the selection application IO formation.When FTL carrying out garbage reclamation, balance abrasion, reading-revise-when writing, the status flag information current according to FTL is selected preferentially to process with these page, IO that piece is relevant.When there is write cache system in application, when FTL carrying out garbage reclamation, balance abrasion, reading-revise-when writing, select to process with these page, dirty high priority data that piece is relevant.In a plurality of embodiment of the present invention, the dirty data also can be expressed as old data.Described priority processing can be to process immediately, in advance to the processing of described related data.
In the tenth embodiment of the present invention, before described step S301, comprise: the step of the status flag of the described flash translation layer (FTL) of logging modle 30 records, with record FTL internal operation status information.
Referring to Fig. 4, in one embodiment of the invention, provide the mutual signal process of application and flash translation layer (FTL), be described below:
FTL is carrying out garbage reclamation, balance abrasion or is reading-revise-when writing, according to its page/ block address that relates to, obtain related IO from the IO formation and process; In the system that has write cache (writing cache memory), from write cache, obtain related dirty data and process.Garbage reclamation algorithm among the concrete FTL selects an optimum piece to carry out garbage reclamation, and some page datas in this piece are invalid, but may have the page of some active pages; Then each cma algorithm is all different.And in the dynamic equalization wearing and tearing algorithm of FTL, pool of free blocks is browsed, seek the module unit (block) of an erase count value minimum.In case find satisfactory, just new data is write, and this piece is sent into the data block pond, the logical address that then physical address and the main frame of new piece is sended over is set up each other mapping relations at the conversion mapping table.And the physical block of initial mapping will be wiped free of, and the renewal erase count is also sent in the pool of free blocks, but may there be the page of active page in this piece, and this part data also must be moved in the new piece so.Obtain the logical address of the page of active page in this piece; Search the IO that is associated with the page of active page in the IO formation of upper strata, namely there is common factor in this IO address realm with the page address of active page or links to each other;
In addition, in the system that has write cache, the dirty data that the page of active page in the physical block with described initial mapping is associated are searched in continuation in write cache, namely the address realm of these data exists with the page address of active page and occurs simultaneously or link to each other.After obtaining above-mentioned information, garbage reclamation algorithm, balance abrasion algorithm among the FTL can be optimized, and accelerate the processing of user data.
Referring to Fig. 5, in one embodiment of the invention, the method for the IO optimization process that provides is described below:
Among the step S501, select certain piece of carrying out garbage reclamation, balance abrasion, reading-revise-write;
Among the step S502, will chat page copy that operation relates on carrying out in buffer memory;
Among the step S503, from the IO formation, search read command and whether hit and chat buffer memory, if so, return and read the IO data;
Among the step S504, from the IO formation, search whether page or leaf in related this piece of write order, if carry out Optimum Operation;
Among the step S505, search whether page or leaf in related this piece of dirty data from write cache, if carry out Optimum Operation.
In this embodiment, carry out garbage reclamation, balance abrasion, read-revise-when writing, read first active page in buffer memory when FTL selects a piece, can check whether exist read command to hit this buffer memory this moment in the IO formation, if existence, then return data.When FTL selects a piece to carry out garbage reclamation, read first active page in buffer memory, at this moment can judge whether exist the write order data to link to each other with active page in the IO formation or have common factor, if exist, so these IO data are write in the new free block together with active page, thereby promote the IO treatment effeciency.In like manner, in the system that has write cache, seek the dirty data that link to each other with active page, write in the lump in the new free block.When FTL is carrying out static equilibrium when wearing and tearing, the active page in the object block also can copy in the free block, also can be the IO that chats and optimize action.What take as FTL is static equilibrium when wearing and tearing, on the basis of dynamic equalization wearing and tearing algorithm, those inactive module units are carried out addressing, if free block has surpassed the upper limit that sets, FTL starts browse operation, the module unit of searching erase count value minimum in the data block pond, and the module unit of erase count value maximum in the pool of free blocks.Count value maximum in erase count value minimum in the data block pond and the pool of free blocks is subtracted each other, if the result has surpassed capping, the data of the module unit of erase count value minimum will be transferred in the module unit of erase count value maximum in the pool of free blocks in the data block pond so.The piece that is erase count value minimum in the data block pond will be wiped free of, and is placed in the pool of free blocks.Original in pool of free blocks the piece of count value maximum and be transferred in the data block pond then owing to being written into the content of other pieces.After converting, the conversion mapping table will upgrade in FTL.
In said process, object block is the module unit of erase count value minimum in the data block pond, and there is the page of active page in this piece.The data of these effective pages can copy in the middle of the buffer memory, then find the data related with the page of object block active page in the IO formation or among the write cache, the page data of these data and active page is merged, occur simultaneously if namely exist, with the data in the latest data renewal buffer memory that finds; If link to each other, with data and the data cached associating that finds, then unification writes in the free block.After this process was finished, this association IO data write in the free block fully, and IO returns; Dirty data that should association among the write cache write in the free block fully, and this dirty Data Identification is the removing state.When a piece among the FTL read in execution-revise-when writing, active page also can copy in the buffer memory, also can be the IO that chats and optimize action.
Concrete execution reads-revises-and operating process when writing comprises that the valid data in the piece read in the buffer memory; New data writes in this buffer memory, may cover the valid data in described, has simultaneously the page or leaf of valid data in the home block; Wipe this piece; In IO formation, write cache, search the data related with this piece active page; Data in these data and the above-mentioned buffer memory are merged.Data cached after merging write in the middle of the piece of having wiped; New data and related IO data write in this piece fully, and IO returns; Dirty data that should association among the write cache write in this piece fully, and the dirty Data Identification is the removing state.
In sum, the present invention is by obtaining the status flag of flash translation layer (FTL); Then select the priority processing of carrying out of suitable IO in the IO formation and/or application data according to the status flag of described flash translation layer (FTL).FTL is combined with application, preferred, by the state of FTL detection self, initiatively obtaining data from IO formation or application processes, thereby accelerated the storage efficiency of application data, promoted the IO performance of using, the harmony between raising application data and the FTL and the performance of FTL.
Certainly; the present invention also can have other various embodiments; in the situation that do not deviate from spirit of the present invention and essence thereof; those of ordinary skill in the art work as can make according to the present invention various corresponding changes and distortion, but these corresponding changes and distortion all should belong to the protection domain of the appended claim of the present invention.
Claims (10)
1. the method for an IO optimization process is characterized in that, described method comprises the steps:
Obtain the status flag of flash translation layer (FTL);
The priority processing of carrying out according to suitable IO and/or application data in the status flag selection IO formation of described flash translation layer (FTL).
2. method according to claim 1 is characterized in that, the described step of obtaining the status flag of flash translation layer (FTL) comprises:
Obtain described flash translation layer (FTL) and carrying out the page or leaf of garbage reclamation and/or the information of piece; And/or
Obtain the information of the piece of the ongoing balance abrasion of described flash translation layer (FTL); And/or
Obtain that described flash translation layer (FTL) is ongoing to be read-revise-information of the piece write.
3. method according to claim 2 is characterized in that, described status flag according to described flash translation layer (FTL) selects that the suitable step of carrying out priority processing comprises in the IO formation:
Select with described flash translation layer (FTL) carrying out garbage reclamation page and/or the relevant IO of piece carry out priority processing; And/or
Selection is carried out priority processing with the relevant IO of the piece of the ongoing balance abrasion of described flash translation layer (FTL); And/or
Select to read-to revise with described flash translation layer (FTL) is ongoing-the relevant IO of piece that writes carries out priority processing.
4. method according to claim 3, it is characterized in that, when application corresponding to IO of processing at described flash translation layer (FTL) had write cache device system, described status flag according to described flash translation layer (FTL) selected that the suitable step of carrying out priority processing comprises in the IO formation:
Select with described flash translation layer (FTL) carrying out garbage reclamation page and/or the relevant junk data of piece carry out priority processing; And/or
Selection is carried out priority processing with the relevant junk data of the piece of the ongoing balance abrasion of described flash translation layer (FTL); And/or
Select to read-to revise with described flash translation layer (FTL) is ongoing-the relevant junk data of piece write carries out priority processing.
5. method according to claim 1 is characterized in that, comprises before the step of the described status flag that obtains flash translation layer (FTL):
Record the step of the status flag of described flash translation layer (FTL).
6. the system of an IO optimization process is characterized in that, described system comprises:
Acquisition module is for the status flag that obtains flash translation layer (FTL);
Processing module is used for selecting suitable IO and/or the application data of IO formation to carry out priority processing according to the status flag of described flash translation layer (FTL).
7. system according to claim 6 is characterized in that, described acquisition module comprises:
First obtains submodule, is used for obtaining described flash translation layer (FTL) and is carrying out the page or leaf of garbage reclamation and/or the information of piece; And/or
Second obtains submodule, for the information of the piece that obtains the ongoing balance abrasion of described flash translation layer (FTL); And/or
The 3rd obtains submodule, is used for obtaining that described flash translation layer (FTL) is ongoing to be read-revise-information of the piece write.
8. system according to claim 7 is characterized in that, described processing module comprises:
First processes submodule, and the page or leaf and/or the relevant IO of piece that are carrying out garbage reclamation for selection and described flash translation layer (FTL) carry out priority processing; And/or
Second processes submodule, is used for selection and carries out priority processing with the relevant IO of the piece of the ongoing balance abrasion of described flash translation layer (FTL); And/or
The 3rd processes submodule, be used for selecting reading-revising with described flash translation layer (FTL) is ongoing-the relevant IO of piece that writes carries out priority processing.
9. system according to claim 8, it is characterized in that, when application corresponding to IO of processing at described flash translation layer (FTL) has write cache device system, described first process submodule select with described flash translation layer (FTL) carrying out garbage reclamation page and/or the relevant junk data of piece carry out priority processing; And/or
Described second processes the submodule selection carries out priority processing with the relevant junk data of the piece of the ongoing balance abrasion of described flash translation layer (FTL); And/or
The described the 3rd processes submodule selects to read-revise with described flash translation layer (FTL) is ongoing-and the relevant junk data of piece write carries out priority processing.
10. system according to claim 6 is characterized in that, described system also comprises:
Logging modle is for the status flag that records described flash translation layer (FTL).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012105215744A CN103049312A (en) | 2012-12-07 | 2012-12-07 | Input/output (IO) optimizing processing method and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012105215744A CN103049312A (en) | 2012-12-07 | 2012-12-07 | Input/output (IO) optimizing processing method and system thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103049312A true CN103049312A (en) | 2013-04-17 |
Family
ID=48061962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012105215744A Pending CN103049312A (en) | 2012-12-07 | 2012-12-07 | Input/output (IO) optimizing processing method and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103049312A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106354486A (en) * | 2016-08-08 | 2017-01-25 | 珠海全志科技股份有限公司 | Nand flash equipment management method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102163175A (en) * | 2011-04-26 | 2011-08-24 | 西安交通大学 | Hybrid address mapping method based on locality analysis |
| CN102298555A (en) * | 2011-08-22 | 2011-12-28 | 宜兴市华星特种陶瓷科技有限公司 | Modular flash management system based on Not AND (NAND) technology |
-
2012
- 2012-12-07 CN CN2012105215744A patent/CN103049312A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102163175A (en) * | 2011-04-26 | 2011-08-24 | 西安交通大学 | Hybrid address mapping method based on locality analysis |
| CN102298555A (en) * | 2011-08-22 | 2011-12-28 | 宜兴市华星特种陶瓷科技有限公司 | Modular flash management system based on Not AND (NAND) technology |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106354486A (en) * | 2016-08-08 | 2017-01-25 | 珠海全志科技股份有限公司 | Nand flash equipment management method and system |
| CN106354486B (en) * | 2016-08-08 | 2019-06-18 | 珠海全志科技股份有限公司 | The method and system of nand flash equipment management |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11960726B2 (en) | Method and apparatus for SSD storage access | |
| CA2673434C (en) | Memory device performance enhancement through pre-erase mechanism | |
| US8364931B2 (en) | Memory system and mapping methods using a random write page mapping table | |
| CN102511044B (en) | Method for deleting the data and device thereof | |
| CN102576333B (en) | Data cache in nonvolatile memory | |
| CN102508788B (en) | SSD (solid state drive) and SSD garbage collection method and device | |
| CN103136116A (en) | Memory storage system and central control device, management method and blackout recovery method thereof | |
| US20130166828A1 (en) | Data update apparatus and method for flash memory file system | |
| CN103543955A (en) | Method and system for reading cache with solid state disk as equipment and solid state disk | |
| Lee et al. | HFTL: hybrid flash translation layer based on hot data identification for flash memory | |
| CN102981963A (en) | Implementation method for flash translation layer of solid-state disc | |
| CN102541760A (en) | Computer system based on solid-state hard disk | |
| KR101374065B1 (en) | Data Distinguish Method and Apparatus Using Algorithm for Chip-Level-Parallel Flash Memory | |
| CN103744611A (en) | Computer system based on solid state disc as cache and cache accelerating method | |
| CN103744798A (en) | Garbage recycling method of solid state discs | |
| CN103077119A (en) | Data processing system and method | |
| CN105745628A (en) | Terminal, service provision apparatus, and coupon server, electronic wallet system having same, control method thereof, and recording medium in which computer program is recorded | |
| CN110543435B (en) | Mixed mapping operation method, device and equipment of storage unit and storage medium | |
| CN103034586B (en) | By method and the system thereof of flash translation layer (FTL) identification upper layer application | |
| CN109783019B (en) | Intelligent data storage management method and device | |
| KR20140109689A (en) | Apparatus and method for optimization for improved performance and enhanced lifetime of hybrid flash memory devices | |
| CN102867046B (en) | Database optimizing method based on solid state hard disc and system | |
| KR101191650B1 (en) | Apparatus and method for mapping the data address in NAND flash memory | |
| CN105589912A (en) | Method and storage structure for processing frequently written document with MRAM (Magnetic Random Access Memory) | |
| CN103049312A (en) | Input/output (IO) optimizing processing method and system thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130417 |