CN101807212B - Caching method for embedded file system and embedded file system - Google Patents
Caching method for embedded file system and embedded file system Download PDFInfo
- Publication number
- CN101807212B CN101807212B CN 201010160993 CN201010160993A CN101807212B CN 101807212 B CN101807212 B CN 101807212B CN 201010160993 CN201010160993 CN 201010160993 CN 201010160993 A CN201010160993 A CN 201010160993A CN 101807212 B CN101807212 B CN 101807212B
- Authority
- CN
- China
- Prior art keywords
- buffer
- sector
- buffer location
- location
- data
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000001360 synchronised effect Effects 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 20
- 238000005516 engineering process Methods 0.000 description 19
- 230000006378 damage Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The problem to be solved of the invention is to provide a caching method, which can meet the requirements of performance and reliability and is suitable for an embedded file system and the embedded file system for realizing the method. The caching method comprises the following steps: directly reading integer data using a sector as a unit on a storage device; finishing reading metadata mainly by operating buffer zone units to possibly reduce the access times to a hardware storage device and total time consumed for accessing the hardware storage device; and synchronizing data of all buffer zone units to a corresponding sector of the storage device while closing a file to ensure the data integrity of the closed file.
Description
Technical field
The invention belongs to areas of information technology, relate in particular to a kind of caching technology that is applied to embedded file system.
Background technology
In file system, usually need to use level cache to visit memory device.Initial memory device is mainly that this class of picture disk is rotated memory device, and the characteristics of this kind equipment are to need very long rotation addressing process when visit data.Have this characteristics because rotate memory device, will cause the performance of file system low if addressing is all carried out in each access.The general caching technology is arisen at the historic moment under this background, and it has effectively improved the performance of access rotation memory device.
Memory pool of general caching utilization comes the data in buffer memory equipment, improves performance by the addressing number of times that reduces in memory device.File system is come managing memory apparatus take the sector as unit.After using the general caching technology, except the data that read effective sector, extra mutiread data of getting several contiguous sectors also, this mode are called in advance and read when reading storage device data; Write fashionablely in data, at first write data into data cached memory pool, more periodically the data in buffer memory are synchronized on memory device, this mode writes unified.The general caching technology greatly reduces by reading in advance and unifying to write the addressing number of times that makes memory device, thereby has effectively improved the performance of file system.
Although the general caching technology has more advantage, and is not suitable for embedded file system, major limitation is the reliability that the general caching technology can't guarantee embedded file system.The general caching technology depends on reading in advance of data and periodic unified writing, this will cause data to be written can be in buffer memory resident a period of time, thereby can not be real-time be synchronized to memory device.Usually need to face the challenge of unexpected power down due to embedded device, this just might cause residing in the loss of part data in buffer memory.If missing data is the critical data of file system just, as boot sector data, FAT(File Allocation Table, file allocation table) data, catalogue data etc., this will cause serious destruction to file system, even may cause the collapse of file system.
Along with the progress of technology, generally adopt now flash memory (being called for short FLASH) or standard flash memory card (Compact Flash is called for short the CF card) as memory device in embedded device.But Flash has the characteristics of random access, no longer includes the long restriction of addressing time, has also just reduced the dependence to caching technology.At present, in order to guarantee reliability, the way of removing buffer memory in embedded system is arranged.But after processing like this, can frequently access the problem that External memory equipment causes system performance to reduce because of the read-write operation of metadata again.
As seen, can not use existing general caching technology in embedded file system, and not use caching technology can't satisfy the demand of file system performance.Therefore be necessary to realize a kind of caching technology that is applicable to embedded file system, can satisfy performance requirement and not damage again the reliability of file system.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of caching method that is applicable to embedded file system of Performance And Reliability demand and buffer storage of realizing the embedded file system of the method taken into account.
The present invention is that to solve the problems of the technologies described above the technical scheme that adopts be that the caching method of embedded file system comprises:
Distribute a block buffer in internal memory; Described buffer zone comprises 2 buffer locations at least, but the data of each buffer location buffer memory sector;
When read-write during take the sector as the entire data of unit, the direct enterprising line operate in the operation sector of the purpose on memory device;
When the read-write metadata, operating the enterprising line operate of buffer location corresponding to sector with purpose;
When closing of a file, trigger the data in each buffer location synchronously to the corresponding sector of memory device.
, directly operate on memory device during take the sector as the entire data of unit when read-write; Mainly complete by the unit, operation buffer during the read-write metadata, reduce the summation that expends time in of number of times and the access hardware memory device of access hardware memory device as far as possible.The data of synchronous all buffer locations to the corresponding sector of memory device, guarantee the data integrity of buttoned-up file when closing of a file.
Preferably, described buffer zone comprises 3 buffer locations.
Adopting 3 buffer locations in the present invention program is that optimum way is that characteristic according to file system operation designs.In the process of file operation, need in its FAT sector, switch between directory sector and data sector usually back and forth the sector of read-write memory device.If buffer zone only has a buffer location, the switching that will cause each sector is re-synchronization and data cached all, can not play the effect that reduces the hardware storage device access times, in the time of too much can causing closing of a file again as buffer location in buffer zone, need synchronous overabundance of data, affect system reliability.
Concrete, memory device is flash memory or standard flash memory card.
Although widely used FLASH equipment does not need the very long addressing time in embedded system, each hardware access still needs Time Created, retention time and release time three kinds of time consumptions.Hardware access can make the time consumption after adding up very huge frequently, has a strong impact on the performance of file system, therefore need to reduce the number of times of hardware access as far as possible.In conjunction with the hardware characteristics of FLASH and test findings repeatedly, we find can obtain a performance and stable equilibrium point take the sector as unit visits FLASH.
Further, include two management parameters of sector number and sync mark in buffer location; Sector number represents the sector number of data cached correspondence in buffer location; Sync mark represents data cached whether the need synchronously in buffer location.
Whether the specific implementation of reading metadata: first searching in buffer zone has and buffer location corresponding to purpose operation sector if being, if any, directly this buffer location is carried out read operation; As no, distribute a freebuf unit in buffer zone, the data of purpose operation sector in memory device are read in this buffer location, the sector number of this buffer location is set simultaneously, then this buffer location is carried out read operation.
Whether the specific implementation of writing metadata: first searching in buffer zone has and buffer location corresponding to purpose operation sector if being, if any, directly metadata to be written is write in this buffer location; As no, data in memory device purpose operation sector are first read in the freebuf unit of distribution, the sector number of this buffer location is set simultaneously, then the metadata that need write is write this buffer location, the sync mark of this buffer location is set for needing synchronous regime.
Concrete, when the read-write metadata, as the buffer location corresponding to purpose operation sector of nothing in buffer zone and memory device, and can distribute without the freebuf unit in buffer zone, the executive buffer unit is replaced; Described buffer location replaces with, the buffer location of selecting corresponding sector number maximum is buffer zone as an alternative, and will replace data in buffer location synchronously to the corresponding sector of memory device, with the replacement buffer location after synchronously processing as the freebuf unit.The buffer location of described sector number maximum is for the dosFs file system, and in the dosFs file system, the sector number of data sector number is large than other type sector number.Preferably, select as much as possible data sector buffer location as an alternative, keep the data in FAT sector and directory sector; Make that FAT sector and directory sector are this fixingly needs again being buffered in buffer location of sector long period of frequent access can effectively improve performance relatively.
Realize the buffer storage of the embedded file system of said method, distribute the processing module of a block buffer in internal memory; Described buffer zone comprises 2 buffer locations at least, but the data of each buffer location buffer memory sector;
When read-write during take the sector as the entire data of unit, the direct processing module of the enterprising line operate in the operation sector of the purpose on memory device;
When read-write during metadata, in the processing module of the buffer location enterprising line operate corresponding with purpose operation sector;
When closing of a file, trigger the synchronous processing module to the corresponding sector of memory device of the data in each buffer location.
The invention has the beneficial effects as follows, take into account simultaneously reliability and performance requirement, compare with the general caching technology, committed memory of the present invention is little, and resident data is few, and loss of data destroys controlled.
Description of drawings
Fig. 1 is the file system structure schematic diagram of the embodiment of the present invention.
Fig. 2 is the synchronous processing flow chart of the buffer location of the embodiment of the present invention.
Fig. 3 is the metadata read-write processing flow chart of the embodiment of the present invention.
Fig. 4 is that the buffer location of the embodiment of the present invention is replaced the process flow diagram of processing.
Embodiment
The present invention is described in further detail below in conjunction with the drawings and specific embodiments.
Can find out in example from Fig. 1, embedded file system comprises file system cache device, memory device, buffer zone; Buffer zone has comprised 3 buffer locations (buffer location [0], buffer location [1], buffer location [2]) in this example, each buffer location can buffer memory the data of a sector, memory device is FLASH or CF card.For buffer zone of the present invention, suggestion is comprised of 2 to 5 buffer locations, can reach and satisfy performance requirement and do not damage again the effect of the reliability of file system.
The disposal route of file system cache device to data mainly contains:
1. during original state, at first distribute the buffer zone of 3 times of sector-size in internal memory; And this buffer zone is divided into 3 buffer locations, each buffer location has two management parameters: sector number and sync mark.Sector number represents the sector number of the data cached correspondence in buffer location, is initially sky; Sync mark represents whether the sector data of buffer memory needs synchronously, is initially to need not synchronously;
2. when read-write during take the sector as the entire data of unit, the operation of directly reading and writing entire data on the operation of the purpose on FLASH sector;
3. when read-write during metadata, with buffer location corresponding to purpose operation sector on carry out read-write operation:
When initially reading metadata, distribute a freebuf unit in buffer zone, the data in the destination sector in the FLASH of read operation are read in buffer location, record this sector number simultaneously in sector number, then carry out corresponding read operation.Whether follow-up when carrying out the read operation of metadata, first searching in buffer zone has and buffer location corresponding to purpose operation sector, if any, directly metadata to be written is write in this buffer location; As no, data in memory device purpose operation sector are first read in the freebuf unit of distribution, the sector number of this buffer location is set simultaneously, then the metadata that need write is write this buffer location, the sync mark of this buffer location is set for needing synchronous regime.
Whether when data writing, first searching in buffer zone has and buffer location corresponding to purpose operation sector, if any, directly metadata to be written is write in this buffer location; As no, distribute a freebuf unit in buffer zone, data in memory device purpose operation sector are first read in the freebuf unit of above distribution, the sector number of this buffer location is set simultaneously, the metadata that again need is write writes this buffer location, the sync mark that this buffer location is set is to need synchronous regime, but does not carry out synchronous operation this moment.As buffer location corresponding to the purpose of nothing in buffer zone and memory device operation sector, and can distribute without the freebuf unit in buffer zone, the executive buffer unit is replaced; Described buffer location replaces with, and selects the replacement buffer location, and will replace data in buffer location take the sector as unit synchronously to memory device, with the replacement buffer location after synchronously processing as the freebuf unit; The buffer location that can select corresponding sector number maximum in buffer zone is buffer location as an alternative.
4. when closing of a file, the sync mark in buffer zone need to be set to synchronous buffer location data to be synchronized to memory device FLASH.
Fig. 2 is the treatment scheme schematic diagram of buffer location sync section, can triggering synchronous be labeled as the processing that the data that need in each synchronous buffer location are synchronized to the corresponding buffer zone of storer when closing of a file.As shown in the figure, buffer location synchronously comprises the following steps:
201. this treatment scheme begins;
202. read the sync mark in the management parameters of current buffer location;
203. judge whether current buffer location needs synchronously, if need to would enter the synchronous flow process of data, be about to sync mark in buffer location for the data in the buffer location that needs synchronous regime synchronously to the corresponding sector of memory device, and the sync mark of the current buffer location that resets is not for needing synchronously; If do not need synchronously execution in step 204;
204. whether judgement is completed the buffer location traversal of buffer zone, does not complete rebound step 202; Execution in step 205 after completing;
205. this treatment scheme finishes;
Fig. 3 is the schematic flow sheet of metadata read-write section processes, and as shown in the figure, the read-write flow process of metadata comprises the following steps:
301. this treatment scheme begins;
302. be that a freebuf unit is distributed in purpose to be read and write operation sector according to peculiar strategy, and the data of this purpose operation sector read in the freebuf unit that has distributed;
If 303. need to carry out the write operation of metadata metadata to be written is written to this buffer location, and the management parameters of this buffer location is set, soon sector number is made as the sector number on corresponding stored equipment, and sync mark is made as needs synchronous regime; If corresponding read operation is carried out in read operation;
304. this treatment scheme finishes;
Fig. 4 is the treatment scheme schematic diagram that buffer location is replaced part, and as shown in the figure, buffer location synchronously comprises the following steps:
401. this treatment scheme begins;
If 402. purpose to be operated operates the sector, corresponding buffer location has been arranged in buffer zone, without any need for processing, this treatment scheme finishes; If do not have execution in step 403;
If 403. available free buffer location execution in step 406 in buffer zone; If there is no the freebuf unit carry out replacement policy, namely execution in step 404;
404. be the buffer location of sector number maximum in the replacement buffer zone at the strategy that carries out taking when replace the sector; Adopt such replacement policy to design according to the file system operation characteristic: in the file operation process, need to be in the FAT sector of memory device, repeatedly switch between directory sector and data sector, the data that wherein write in FAT sector and directory sector are less, and sector number is also just relatively fixing; Make relatively fixing being buffered in buffer location of sector long period that needs again frequently to access of these sector numbers can effectively improve performance.At dosFs(dos file system, be based on a kind of file system of FAT, being proposed by Microsoft the earliest) in file system, FAT sector number＜directory sector number＜data sector number can be made corresponding modification according to similarity relation in other file system.
405. will be synchronized to FLASH according to data based its synchronous necessity in above policy selection buffer location out;
406. purpose that will be to be operated operation sector data is cached in the buffer location that chooses;
407. the management parameters of this buffer location is set, and soon sector number is made as the sector number on corresponding stored equipment;
408. this treatment scheme finishes;
The embedded caching technology that proposes in the present invention has that committed memory is little, and resident data is few, and loss of data destroys controlled advantage.Technical scheme of the present invention is cache metadata only, therefore only need memory headroom seldom, and resident data seldom; Synchronous and closing of file is associated due to data, even power down is lost resident data, and also impact this file of not closing only, this has just guaranteed that destruction is controlled.
Above-described embodiment is illustrated as an example of dosFs file system cache device example, and the memory device of employing is FLASH.The present invention also is applicable to the embedded file system of other type, but the memory device of employing need to have the characteristics of random access.In this type systematic, the embedded caching technology of realizing according to technical solution of the present invention also belongs to category of the present invention.
Above-described specific embodiment, to purpose of the present invention, technical scheme and beneficial effect further describe, institute it should be noted the above only for specific embodiments of the invention, and those skilled in the art can carry out various changes and modification and not break away from the spirit and scope of the present invention the present invention.Like this, if within of the present invention these are revised and modification belongs to the scope of the technical scheme of claim record of the present invention and equivalent technologies, the present invention also is intended to comprise these changes and modification interior.
Claims (12)
1. the caching method of embedded file system, is characterized in that, comprising:
Distribute a block buffer in internal memory; Described buffer zone comprises 2 buffer locations at least, but the data of each buffer location buffer memory sector;
When read-write during take the sector as the entire data of unit, the direct enterprising line operate in the operation sector of the purpose on memory device;
When the read-write metadata, operating the enterprising line operate of buffer location corresponding to sector with purpose;
When closing of a file, trigger the data in each buffer location synchronously to the corresponding sector of memory device.
2. the caching method of embedded file system as claimed in claim 1, is characterized in that, described buffer zone comprises 3 buffer locations.
3. the caching method of embedded file system as claimed in claim 1 or 2, is characterized in that, described memory device is flash memory or standard flash memory card.
4. the caching method of embedded file system as claimed in claim 1 or 2, is characterized in that, includes two management parameters of sector number and sync mark in buffer location; Sector number represents the sector number of data cached correspondence in buffer location; Sync mark represents data cached whether the need synchronously in buffer location.
5. the caching method of embedded file system as claimed in claim 1 or 2, it is characterized in that, whether the specific implementation of reading metadata: first searching in buffer zone has and buffer location corresponding to purpose operation sector if being, if any, directly this buffer location is carried out read operation; As no, distribute a freebuf unit in buffer zone, the data of purpose operation sector in memory device are read in this buffer location, the sector number of this buffer location is set simultaneously, then this buffer location is carried out read operation.
6. the caching method of embedded file system as claimed in claim 1 or 2, it is characterized in that, whether the specific implementation of writing metadata: first searching in buffer zone has and buffer location corresponding to purpose operation sector if being, if any, directly metadata to be written is write in this buffer location; As no, data in memory device purpose operation sector are first read in the freebuf unit of distribution, the sector number of this buffer location is set simultaneously, then metadata to be written is write this buffer location, the sync mark of this buffer location is set for needing synchronous regime.
7. the caching method of embedded file system as claimed in claim 5, it is characterized in that, when the read-write metadata, as the buffer location corresponding to purpose operation sector of nothing in buffer zone and memory device, and can distribute without the freebuf unit in buffer zone, the executive buffer unit is replaced; Described buffer location replaces with, the buffer location of selecting corresponding sector number maximum is buffer location as an alternative, and will replace data in buffer location synchronously to the corresponding sector of memory device, with the replacement buffer location after synchronously processing as the freebuf unit.
8. the caching method of embedded file system as claimed in claim 6, it is characterized in that, when the read-write metadata, as the buffer location corresponding to purpose operation sector of nothing in buffer zone and memory device, and can distribute without the freebuf unit in buffer zone, the executive buffer unit is replaced; Described buffer location replaces with, the buffer location of selecting corresponding sector number maximum is buffer location as an alternative, and will replace data in buffer location synchronously to the corresponding sector of memory device, with the replacement buffer location after synchronously processing as the freebuf unit.
9. the buffer storage of embedded file system, is characterized in that, comprising:
Distribute the processing module of a block buffer in internal memory; Described buffer zone comprises 2 buffer locations at least, but the data of each buffer location buffer memory sector;
When read-write during take the sector as the entire data of unit, the direct processing module of the enterprising line operate in the operation sector of the purpose on memory device;
When read-write during metadata, in the processing module of the buffer location enterprising line operate corresponding with purpose operation sector;
When closing of a file, trigger the synchronous processing module to the corresponding sector of memory device of the data in each buffer location.
10. the buffer storage of embedded file system as claimed in claim 9, is characterized in that, comprises two management parameters of sector number and sync mark in each buffer location of buffer zone; Sector number represents the sector number on the memory device of data cached correspondence in buffer location; Sync mark represents data cached whether the need synchronously in buffer location.
11. the buffer storage as embedded file system as described in claim 9 or 10, it is characterized in that, whether the concrete operations of reading metadata in the processing module of the enterprising line operate of buffer location corresponding with purpose operation sector: first searching in buffer zone has and buffer location corresponding to purpose operation sector if being, if any, directly this buffer location is carried out read operation; As no, distribute a freebuf unit in buffer zone, the data of purpose operation sector in memory device are read in this buffer location, the sector number of this buffer location is set simultaneously, then this buffer location is carried out read operation.
12. the buffer storage as embedded file system as described in claim 9 or 10, it is characterized in that, whether the concrete operations of writing metadata in the processing module of the enterprising line operate of buffer location corresponding with purpose operation sector: first searching in buffer zone has and buffer location corresponding to purpose operation sector if being, if any, directly metadata to be written is write in this buffer location; As no, data in memory device purpose operation sector are first read in the freebuf unit of distribution, the sector number of this buffer location is set simultaneously, then the metadata that need write is write this buffer location, the sync mark of this buffer location is set for needing synchronous regime.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010160993 CN101807212B (en) | 2010-04-30 | 2010-04-30 | Caching method for embedded file system and embedded file system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010160993 CN101807212B (en) | 2010-04-30 | 2010-04-30 | Caching method for embedded file system and embedded file system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101807212A CN101807212A (en) | 2010-08-18 |
| CN101807212B true CN101807212B (en) | 2013-05-08 |
Family
ID=42609004
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010160993 Expired - Fee Related CN101807212B (en) | 2010-04-30 | 2010-04-30 | Caching method for embedded file system and embedded file system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101807212B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699613A (en) * | 2013-12-17 | 2014-04-02 | 迈普通信技术股份有限公司 | Method and system for buffering file system in embedded system |
| CN106708960B (en) * | 2016-11-30 | 2021-05-28 | 浙江宇视科技有限公司 | Repair method of NAS device file system and NAS device |
| CN107329697A (en) * | 2017-06-27 | 2017-11-07 | 湖南威胜信息技术有限公司 | Power information data access method and its electric energy meter for embedded system |
| CN109739683B (en) * | 2018-12-31 | 2022-08-05 | 河南思维自动化设备股份有限公司 | LKJ file writing method based on power failure protection medium and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101324899A (en) * | 2008-08-05 | 2008-12-17 | 北京海尔集成电路设计有限公司 | Method for rapidly writing NAND type FLASH |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7609709B2 (en) * | 2006-01-23 | 2009-10-27 | Alcatel-Lucent Usa Inc. | Video aware traffic management |
-
2010
- 2010-04-30 CN CN 201010160993 patent/CN101807212B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101324899A (en) * | 2008-08-05 | 2008-12-17 | 北京海尔集成电路设计有限公司 | Method for rapidly writing NAND type FLASH |
Non-Patent Citations (1)
| Title |
|---|
| 赵虹等.提高MINIX2_0文件属性信息的访问效率.《微机发展》.2003,第13卷(第9期),第71至73,77页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101807212A (en) | 2010-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9037820B2 (en) | Optimized context drop for a solid state drive (SSD) | |
| US8819367B1 (en) | Accelerated translation power recovery | |
| US10289556B2 (en) | Techniques to perform power fail-safe caching without atomic metadata | |
| CN101604226B (en) | Method for building dynamic buffer pool to improve performance of storage system based on virtual RAID | |
| CN103577121B (en) | A kind of highly reliable linear file access method based on Nand Flash | |
| CN101218566B (en) | Method and system for facilitating fast wake-up of a flash memory system | |
| US7130962B2 (en) | Writing cache lines on a disk drive | |
| CN102521147B (en) | Management method by using rapid non-volatile medium as cache | |
| US20140006687A1 (en) | Data Cache Apparatus, Data Storage System and Method | |
| CN103530237B (en) | A kind of rubbish recovering method of Solid-state disc array | |
| US20130042056A1 (en) | Cache Management Including Solid State Device Virtualization | |
| CN105339910B (en) | Virtual NAND capacity extensions in hybrid drive | |
| CN101458668A (en) | Caching data block processing method and hard disk | |
| CN103678166A (en) | Method and system for using solid-state disk as cache of computer | |
| US9875030B2 (en) | Media write operation | |
| CN101807212B (en) | Caching method for embedded file system and embedded file system | |
| CN100580669C (en) | Method for realizing cache memory relates to file allocation table on Flash storage medium | |
| CN103823634A (en) | Data processing method and system supporting non-random write mode | |
| CN105608014B (en) | A kind of storage device using MRAM | |
| CN105653468B (en) | A kind of storage device using MRAM | |
| US20100191899A1 (en) | Information Processing Apparatus and Data Storage Apparatus | |
| CN2603974Y (en) | Magnetic disc cache apparatus | |
| Prada et al. | Saving power in flash and disk hybrid storage system | |
| KR101373613B1 (en) | Hybrid storage device including non-volatile memory cache having ring structure | |
| CN102063462A (en) | Method and device for recovering storage resources from cache server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130508 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |