CN108089996A - A kind of method of the solid state disk reading performance of elevator belt SLC cachings - Google Patents
A kind of method of the solid state disk reading performance of elevator belt SLC cachings Download PDFInfo
- Publication number
- CN108089996A CN108089996A CN201711228407.XA CN201711228407A CN108089996A CN 108089996 A CN108089996 A CN 108089996A CN 201711228407 A CN201711228407 A CN 201711228407A CN 108089996 A CN108089996 A CN 108089996A
- Authority
- CN
- China
- Prior art keywords
- slc
- data
- tlc
- reading performance
- solid state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
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
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/0802—Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
- G06F12/0866—Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches for peripheral storage systems, e.g. disk cache
- G06F12/0871—Allocation or management of cache space
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of elevator belt SLC caching solid state disk reading performance method, it is characterised in that triggering SLC is data cached move TLC data when, when moving TLC maintain treat moving data each Bank in former SLC storage order.For the SSD systems with SLC Cache, a kind of method in the concurrency for user data being maintained to be distributed on NAND SLC Cache data-movings to common Block processes is proposed so that after SLC Cache write completely, SSD remains to maintain higher reading performance.
Description
Technical field
The present invention relates to solid state disk control technology, more particularly to a kind of solid state disk reading performance of elevator belt SLC cachings
Method.
Background technology
For the SSD with SLCCache, user data write-in reads the stage of SLCCache, can obtain very high read-write
Bandwidth, but after SLCCache writes full, to common Block processes, user data exists by the data-moving in SLCCache
The concurrency being distributed on NAND can be disturbed so that apparent decline occurs in subsequent reading performance.
The process that Fig. 1 is conventional SLCBlock data-movings to TLCBlock illustrates, and Bank is represented can be only in solid state disk
The unit of vertical parallel work-flow, each Bank include multiple Block.Either reach triggering item when the data cached as SLC are full
When data cached update is arrived the operation of common Block by part, since SLC cachings are converted by TLC, usually once
The ablation process of TLCBlock needs to provide the data volume of three SLCpage sizes.Such as Fig. 1 examples, it is assumed that the solid state disk has 4
A Bank, be respectively Bank0~Bank3, in order to ensure data read succession and ensure concurrent operations, be written to SLC by
Storage 0,4,8,12... in Bank0；Storage 1,5,9,13... in Bank1；Storage 2,6,10,14... in Bank2；In Bank3
Storage 3,7,11,15...；Since the ablation process of a usual TLCBlock needs the data of three SLCpage sizes of offer
Amount, therefore in order from SLC after reading data, write in order in TLC, the storage data of each Bank are in TLC
Storage 0,1,2,12,13,14... in Bank0；Storage 3,4,5... in Bank1；Storage 6,7,8... in Bank2；In Bank3
Storage 9,10,11...；It moves the concurrency that rear order is read and is destroyed and (such as the reading of logical data 0~2 cannot and be distributed
Into), order reading performance can be a greater impact.
The content of the invention
For disadvantages described above, the present invention seeks to how to improve SLCCache write it is full after by SLCCache data-movings to general
The reading performance of the SSD of logical Block processes.
The present invention proposes a kind of method of the solid state disk reading performance of elevator belt SLC cachings in order to solve problem above,
It is characterized in that triggering SLC is data cached move TLC data when, when moving TLC maintain treat moving data in former SLC
In each Bank storage order.
The method of the solid state disk reading performance of described elevator belt SLC cachings, it is characterised in that SLC is data cached removes for triggering
When moving on to TLC data, data cached read in of SLC to be moved is cached, and according to affiliated Bank sequence numbers by reading order point
Group caching forms each group of data in order respectively in the corresponding Bank of operating unit write-in TLC that TLC writes.
The beneficial effects of the invention are as follows：For the SSD systems with SLCCache, propose a kind of by SLC Cache data
The method for moving the concurrency for common Block processes user data being maintained to be distributed on NAND so that write in SLCCache full
Afterwards, SSD remains to maintain higher reading performance.
Description of the drawings
The process that Fig. 1 is conventional SLCBlock data-movings to TLCBlock illustrates；
Fig. 2 is that the process of moving of concurrency is maintained to illustrate after improving.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without creative efforts
Embodiment belongs to the scope of protection of the invention.
Fig. 2 is that the process of moving of concurrency is maintained to illustrate after improving.In order to maintain concurrency, to the data of reading, according to
From Bank resequenced so that the data from same Bank can be written to (purpose in identical Bank
Bank and source Bank does not require identical), so as to maintain the concurrency that user data is distributed on NAND so that order is read to protect
Hold higher reading performance.SLC is written to by storage 0,4,8,12... in Bank0；Storage 1,5,9,13... in Bank1；In Bank2
Storage 2,6,10,14...；Storage 3,7,11,15... in Bank3；Move TLC be maintain by Bank0 storage 0,4,8,
12...；Storage 1,5,9,13... in Bank1；Storage 2,6,10,14... in Bank2；Storage 3,7,11,15... in Bank3；
Original order read-write property is kept, maintains concurrency.
The above disclosed interest field for being only an embodiment of the present invention, sheet cannot being limited with this certainly,
One of ordinary skill in the art will appreciate that realize all or part of flow of above-described embodiment, and according to the claims in the present invention institute
The equivalent variations of work still fall within the scope that the present invention is covered.
Claims (2)
1. the method for the solid state disk reading performance of a kind of elevator belt SLC caching, it is characterised in that SLC is data cached moves in triggering
During to TLC data, maintain to treat the storage order of moving data each Bank in former SLC when moving TLC.
2. the method for the solid state disk reading performance of elevator belt SLC cachings according to claim 1, it is characterised in that triggering
SLC is data cached when moving TLC data, and data cached read in of SLC to be moved is cached, and according to affiliated Bank sequence numbers
By sequential packet caching is read, the operating unit write-in TLC that each group of data are formed to TLC write-ins in order respectively is corresponding
In Bank.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711228407.XA CN108089996A (en) | 2017-11-29 | 2017-11-29 | A kind of method of the solid state disk reading performance of elevator belt SLC cachings |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711228407.XA CN108089996A (en) | 2017-11-29 | 2017-11-29 | A kind of method of the solid state disk reading performance of elevator belt SLC cachings |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108089996A true CN108089996A (en) | 2018-05-29 |
Family
ID=62172437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711228407.XA Pending CN108089996A (en) | 2017-11-29 | 2017-11-29 | A kind of method of the solid state disk reading performance of elevator belt SLC cachings |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108089996A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462181A (en) * | 2014-10-08 | 2015-03-25 | 记忆科技(深圳)有限公司 | SSD rear end data path management acceleration module and SSD equipment |
| CN105988719A (en) * | 2015-02-07 | 2016-10-05 | 深圳市硅格半导体有限公司 | Storage device and data processing method thereof |
| CN106339326A (en) * | 2016-08-26 | 2017-01-18 | 记忆科技(深圳)有限公司 | Method for improving sequential read performance of solid state disk (SSD) |
| CN107273304A (en) * | 2017-05-24 | 2017-10-20 | 记忆科技(深圳)有限公司 | A kind of method and solid state hard disc for improving solid state hard disc order reading performance |
| CN107357534A (en) * | 2017-07-18 | 2017-11-17 | 深圳市德名利电子有限公司 | A kind of dynamic switching method and system of flash block pattern |
-
2017
- 2017-11-29 CN CN201711228407.XA patent/CN108089996A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462181A (en) * | 2014-10-08 | 2015-03-25 | 记忆科技(深圳)有限公司 | SSD rear end data path management acceleration module and SSD equipment |
| CN105988719A (en) * | 2015-02-07 | 2016-10-05 | 深圳市硅格半导体有限公司 | Storage device and data processing method thereof |
| CN106339326A (en) * | 2016-08-26 | 2017-01-18 | 记忆科技(深圳)有限公司 | Method for improving sequential read performance of solid state disk (SSD) |
| CN107273304A (en) * | 2017-05-24 | 2017-10-20 | 记忆科技(深圳)有限公司 | A kind of method and solid state hard disc for improving solid state hard disc order reading performance |
| CN107357534A (en) * | 2017-07-18 | 2017-11-17 | 深圳市德名利电子有限公司 | A kind of dynamic switching method and system of flash block pattern |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9798472B1 (en) | Extent level cache destaging | |
| US9177670B1 (en) | Method and apparatus for flash cache management | |
| US8639883B2 (en) | Reducing write amplification in a cache with flash memory used as a write cache | |
| US20180232314A1 (en) | Method for storing data by storage device and storage device | |
| JP2009211227A5 (en) | ||
| US11157399B2 (en) | Data storage devices and data processing methods with dynamic programming scheme | |
| CN111061649B (en) | Storage space self-adaptive allocation method of memory | |
| KR20100021868A (en) | Buffer cache management method for flash memory device | |
| CN103257935A (en) | Cache management method and application thereof | |
| CN108595110B (en) | Method for improving reading performance by using Nand characteristic and solid state disk | |
| TW200713024A (en) | Hardware oriented target-side native command queuing tag management | |
| CN101482802A (en) | Expansion method and device for redundant array of independent disks 5 | |
| US20170185294A1 (en) | Memory system and operating method thereof | |
| CN109697170B (en) | Method for accessing flash memory module, related flash memory controller and electronic device | |
| CN107832236A (en) | A kind of method for improving solid state hard disc write performance | |
| KR100787856B1 (en) | Method for changing page in flash memory storage | |
| CN107273304A (en) | A kind of method and solid state hard disc for improving solid state hard disc order reading performance | |
| CN103744800A (en) | Cache operation method and device for replay mechanism | |
| CN107562643B (en) | RAID (redundant array of independent disks) management method for solid state disk | |
| US20160239416A1 (en) | Methods for Reading Data from a Storage Unit of a Flash Memory and Apparatuses Using the Same | |
| US20090254729A1 (en) | Method of wear leveling for a non-volatile memory | |
| CN107145301A (en) | Data access method and device based on hybrid magnetic disc | |
| CN102779098B (en) | The cooperating type adaptive prefetching methods, devices and systems of hybrid cache | |
| US20130111108A1 (en) | Solid state drive and method for controlling cache memory thereof | |
| CN108089996A (en) | A kind of method of the solid state disk reading performance of elevator belt SLC cachings |
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 |
Application publication date: 20180529 |
|
| RJ01 | Rejection of invention patent application after publication |