CN108241471A - A kind of method for promoting solid state disk performance - Google Patents
A kind of method for promoting solid state disk performance Download PDFInfo
- Publication number
- CN108241471A CN108241471A CN201711225471.2A CN201711225471A CN108241471A CN 108241471 A CN108241471 A CN 108241471A CN 201711225471 A CN201711225471 A CN 201711225471A CN 108241471 A CN108241471 A CN 108241471A
- Authority
- CN
- China
- Prior art keywords
- data
- continuous
- solid state
- write
- state disk
- 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
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0608—Saving storage space on storage systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0646—Horizontal data movement in storage systems, i.e. moving data in between storage devices or systems
- G06F3/0652—Erasing, e.g. deleting, data cleaning, moving of data to a wastebasket
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
- G06F3/0659—Command handling arrangements, e.g. command buffers, queues, command scheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0683—Plurality of storage devices
- G06F3/0688—Non-volatile semiconductor memory arrays
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of methods for promoting solid state disk performance, it is characterized in that order is grouped according to the logical address of host write command in solid state disk, the continuous write command of logical address is grouped into the same group, it will be in the continuous NAND flash of data write-in physical address of same group of write command.After order flow management, continuous logic address date has been concentrated in continuous physical address, even if follow-up user deletes these data, covers write operation, the ineffective treatment that these legacy datas can also be concentrated, the entire block ranks of maximum probability it is invalid, this allows for the data block of the entire block ineffective treatments of the unordered processing of garbage reclamation program, can directly be reused after erasing, reduce garbage reclamation moving data amount, so as to reduce unnecessary data write-in.
Description
Technical field
The present invention relates to solid state disk control technology, more particularly to a kind of method for promoting solid state disk performance.
Background technology
Solid state disk, which completes user data write-in, will not usually carry out the differentiation of data, only be submitted according to user's write order suitable
Sequence carries out write operation.But front-end operations system may perform the write operation to multiple logical space sections simultaneously, this causes
Originally the user data of sequence in logic is stored in the physical space of dispersion, when subsequent user to this section of continuous logic
When location accesses, become non-sequential read operation at SSD ends, affect reading performance.Meanwhile as user is to the weight of data
It writes and delete operation, more valid data page and invalid data page block mixed in together, this increasing is formd in SSD
The workload of garbage reclamation is added, so as to reduce SSD service lifes.
In user terminal, it may be simultaneously present multiple threads and data write operation carried out to SSD, possible per thread write-in
Data are all continuous, but due at SSD ends, needing to respond the data write-in of multiple threads simultaneously, and each thread is excellent
First grade is identical, the continuous data of script logical address can be caused to be written in inside SSD and can not continuously store, multiple consecutive numbers
It is mixed in together according to the data of command stream.As performed inside tradition SSD under the several command streams of Fig. 1 shown in schematic diagram, T0, T1,
The continuous data block of logical address is written in tri- threads of T2 into SSD simultaneously, and SSD needs to respond three threads simultaneously so that life
It enables node can not be continuous inside SSD, becomes mixed and disorderly, it is also corresponding mixed and disorderly unordered when storing on NAND flash.For this
The operation of kind long data block, often concentrates in user terminal and writes, and concentrates and reads, and concentration is deleted, so, phenomenon described above can be made
Into two kinds of influences:First, because physical address storage is mixed and disorderly so that subsequently the sequence of this part chunk data is read in bottom
Become discontinuous when realization, influence whether the reading performance of data.Second, since the concentration of user's maximum probability is deleted so that
Originally can become to be dispersed in each physical block with the operation of monoblock data invalid, after long-time so that disk in valid data compared with
For dispersion, increase garbage reclamation pressure, then influence the SSD service life.
Invention content
For disadvantages described above, the probability for the sequential access for reading, updating or recycling the present invention seeks to any later data,
Realize the performance purpose for improving solid state disk.
The present invention proposes a kind of method for promoting solid state disk performance in order to solve problem above, it is characterised in that solid-state
Order is grouped according to the logical address of host write command in hard disk, the continuous write command of logical address is divided into same
Group, will be in the continuous NAND flash of data write-in physical address of same group of write command.
The method of the promotion solid state disk performance, it is characterised in that it is identical to number the write command for belonging to one group
Command stream is numbered, and when rear end stores, is stored separately for each command stream number, this causes the data that same commands stream is numbered
It can be stored in a manner that physical address is continuous in NAND flash.
The beneficial effects of the invention are as follows:After order flow management, continuous logic address date has been concentrated in continuously
In physical address, even if follow-up user deletes these data, covers write operation, these legacy datas can also be concentrated invalid
Change, the entire block ranks of maximum probability it is invalid, this allows for the number of the entire block ineffective treatments of the unordered processing of garbage reclamation program
According to block, it can directly be reused after erasing, reduce garbage reclamation moving data amount, write so as to reduce unnecessary data
Enter.
Description of the drawings
Fig. 1 is to perform schematic diagram under several command streams inside tradition SSD;
Fig. 2 is SSD command stream process charts;
Fig. 3 is the data profile for not having under more command streams order flow management;
Fig. 4 is the data profile that order flow management is increased under more command streams;
Fig. 5 is data profile in SSD after long-play.
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 shall fall within the protection scope of the present invention.
In view of the above problems, the present invention proposes a kind of SSD internal commands flow management policy, logic when being written by user
Address, logical address is continuous between judging whether each order, is continuously ordered for logical address, distributes identical command stream and compiles
Number, it when rear end stores, is stored separately for each command stream number, this allows the data that same commands stream is numbered with object
The reason continuous mode in address is stored in NAND flash, effectively solves the problems, such as caused by above-mentioned conventional write strategy two.Such as Fig. 2
It is shown in SSD command stream process charts, the continuous data of logical address are written in tri- threads of T0, T1, T2 into SSD simultaneously
Block, respectively T0_0, T0_1, T0_2, T0_3;T1_0、T1_1、T1_2、T1_3;T2_0、T2_1、T2_2、T2_3;, command stream
Management module carries out the command node received command stream number distribution, identical life according to the whether continuous characteristic of logical address
The command node of stream number is enabled to be brought together again, difference pair when rear end is to different command stream number allocated physical address
It treats, identical command stream numbered node is written into continuous physical address.
Fig. 3 is the data profile for not having under more command streams order flow management, and triangle expression belongs to T0 command streams, square
Shape expression belong to T1 command streams, it is round represent to belong to T2 command streams, Fig. 4 is the data that order flow management is increased under more command streams
Distribution map respectively describes distribution of the data in disk under order flow management and traditional data management, it can be seen that order
Flow management policy can be effectively to identifying consecutive data block, and they are managed concentratedly.
If Fig. 5 is data profile in SSD after long-play, under Routine Management, the data of script sequence are broken up
In SSD, as user carries out data the operation such as to delete, although data logical address is continuous in disk, it is dispersed in each object
It manages in address so that valid data, invalid data are distributed in a jumble in disk, and it is whole that this just needs garbage reclamation program to carry out data in disk
Reason, vacant physical space is vacateed with this.
After order flow management, continuous logic address date has been concentrated in continuous physical address, even if follow-up
User deletes these data, covers write operation, the ineffective treatment that these legacy datas can also be concentrated, the entire block of maximum probability
Rank it is invalid, this allows for the data block of the entire block ineffective treatments of the unordered processing of garbage reclamation program, directly after erasing
It reuses, reduces garbage reclamation moving data amount, so as to reduce unnecessary data write-in, increase the SSD service life.
Above disclosed is only an embodiment of the present invention, cannot limit the interest field of sheet 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 range that the present invention is covered.
Claims (2)
- A kind of 1. method for promoting solid state disk performance, it is characterised in that according to the logical address of host write command in solid state disk Order is grouped, the continuous write command of logical address is grouped into the same group, object is written into the data of same group of write command It manages in the continuous NAND flash in address.
- 2. the method according to claim 1 for promoting solid state disk performance, it is characterised in that one group will be belonged to and write finger It is same commands stream number to enable number, when rear end stores, is stored separately for each command stream number, this causes same commands The data of stream number can be stored in NAND flash in a manner that physical address is continuous.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711225471.2A CN108241471A (en) | 2017-11-29 | 2017-11-29 | A kind of method for promoting solid state disk performance |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711225471.2A CN108241471A (en) | 2017-11-29 | 2017-11-29 | A kind of method for promoting solid state disk performance |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108241471A true CN108241471A (en) | 2018-07-03 |
Family
ID=62700411
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711225471.2A Pending CN108241471A (en) | 2017-11-29 | 2017-11-29 | A kind of method for promoting solid state disk performance |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108241471A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109284233A (en) * | 2018-09-18 | 2019-01-29 | 郑州云海信息技术有限公司 | A kind of rubbish recovering method and relevant apparatus of storage system |
CN110737404A (en) * | 2019-09-02 | 2020-01-31 | 深圳市金泰克半导体有限公司 | Hard disk data storage method, device and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101582903A (en) * | 2009-06-24 | 2009-11-18 | 杭州华三通信技术有限公司 | Storing method of streaming media resource and device |
CN103744615A (en) * | 2013-12-17 | 2014-04-23 | 记忆科技(深圳)有限公司 | Dynamic compensation receiver and dynamic compensation receiving method |
WO2016107272A1 (en) * | 2014-12-29 | 2016-07-07 | 华为技术有限公司 | Solid state disk storage device, and data accessing method for solid state disk storage device |
CN106681663A (en) * | 2016-12-29 | 2017-05-17 | 记忆科技(深圳)有限公司 | Multithread write-in method for solid state disk |
CN107291631A (en) * | 2017-05-24 | 2017-10-24 | 记忆科技(深圳)有限公司 | In a kind of raising solid state hard disc during multiple stream readout performance method |
CN107329904A (en) * | 2017-06-30 | 2017-11-07 | 湖南国科微电子股份有限公司 | Method for reading data and device |
-
2017
- 2017-11-29 CN CN201711225471.2A patent/CN108241471A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101582903A (en) * | 2009-06-24 | 2009-11-18 | 杭州华三通信技术有限公司 | Storing method of streaming media resource and device |
CN103744615A (en) * | 2013-12-17 | 2014-04-23 | 记忆科技(深圳)有限公司 | Dynamic compensation receiver and dynamic compensation receiving method |
WO2016107272A1 (en) * | 2014-12-29 | 2016-07-07 | 华为技术有限公司 | Solid state disk storage device, and data accessing method for solid state disk storage device |
CN106681663A (en) * | 2016-12-29 | 2017-05-17 | 记忆科技(深圳)有限公司 | Multithread write-in method for solid state disk |
CN107291631A (en) * | 2017-05-24 | 2017-10-24 | 记忆科技(深圳)有限公司 | In a kind of raising solid state hard disc during multiple stream readout performance method |
CN107329904A (en) * | 2017-06-30 | 2017-11-07 | 湖南国科微电子股份有限公司 | Method for reading data and device |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109284233A (en) * | 2018-09-18 | 2019-01-29 | 郑州云海信息技术有限公司 | A kind of rubbish recovering method and relevant apparatus of storage system |
CN109284233B (en) * | 2018-09-18 | 2022-02-18 | 郑州云海信息技术有限公司 | Garbage recovery method of storage system and related device |
CN110737404A (en) * | 2019-09-02 | 2020-01-31 | 深圳市金泰克半导体有限公司 | Hard disk data storage method, device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20210109659A1 (en) | Use of outstanding command queues for separate read-only cache and write-read cache in a memory sub-system | |
US10282132B2 (en) | Methods and systems for processing PRP/SGL entries | |
CN105095116B (en) | Cache method, cache controller and the processor replaced | |
US8010740B2 (en) | Optimizing memory operations in an electronic storage device | |
CN104866428B (en) | Data access method and data access device | |
US9779022B2 (en) | Methods for caching and reading data to be programmed into a storage unit and apparatuses using the same | |
CN104484283B (en) | A kind of method for reducing solid state disk write amplification | |
US20170139825A1 (en) | Method of improving garbage collection efficiency of flash-oriented file systems using a journaling approach | |
CN104238962B (en) | The method and device of data is write into caching | |
US10936203B2 (en) | Memory storage device and system employing nonvolatile read/write buffers | |
CN104991738B (en) | A kind of solid-state disk and its read-write operation method | |
US11914520B2 (en) | Separate read-only cache and write-read cache in a memory sub-system | |
US20140089569A1 (en) | Write cache sorting | |
CN104461387A (en) | Method for improving reading property of solid-state hard disk for no mapping region | |
US20220300428A1 (en) | Management of Programming Mode Transitions to Accommodate a Constant Size of Data Transfer between a Host System and a Memory Sub-System | |
KR101374065B1 (en) | Data Distinguish Method and Apparatus Using Algorithm for Chip-Level-Parallel Flash Memory | |
US20160110107A1 (en) | Method for writing data into flash memory apparatus, flash memory apparatus, and storage system | |
US11520699B2 (en) | Using a common pool of blocks for user data and a system data structure | |
US9946461B2 (en) | In-flash immutable object processing | |
WO2018024214A1 (en) | Io flow adjustment method and device | |
CN113377695A (en) | Data distribution method of read-write separation solid-state storage device | |
CN113711193A (en) | Priority scheduling in queues to access cached data in a memory subsystem | |
US12026395B2 (en) | Operation based on consolidated memory region description data | |
US20230120184A1 (en) | Systems, methods, and devices for ordered access of data in block modified memory | |
CN108241471A (en) | A kind of method for promoting solid state disk performance |
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: 20180703 |
|
RJ01 | Rejection of invention patent application after publication |