CN107678690A - A kind of implementation method of solid state hard disc and its RAID array - Google Patents
A kind of implementation method of solid state hard disc and its RAID array Download PDFInfo
- Publication number
- CN107678690A CN107678690A CN201710910760.XA CN201710910760A CN107678690A CN 107678690 A CN107678690 A CN 107678690A CN 201710910760 A CN201710910760 A CN 201710910760A CN 107678690 A CN107678690 A CN 107678690A
- Authority
- CN
- China
- Prior art keywords
- data
- flash memory
- raid
- passage
- raid5
- 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
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0673—Single storage device
- G06F3/0674—Disk device
-
- 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
- G06F3/062—Securing 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
- G06F3/0638—Organizing or formatting or addressing of data
- G06F3/0644—Management of space entities, e.g. partitions, extents, pools
-
- 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
- G06F3/0689—Disk arrays, e.g. RAID, JBOD
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)
- Techniques For Improving Reliability Of Storages (AREA)
Abstract
The present invention relates to the implementation method of a kind of solid state hard disc and its RAID array, including:Using the flash memory particle of solid state hard disc as minimum memory unit, establish raid5, form a hard disk groups, produce redundancy scheme, and the back-up disk using several flash memory particles as the raid5, use all hard disks and back-up disk of the method hard disk groups of hardware unloading to be virtualized into as a complete hard disk.All flash memory particle groups using virtualization technology are built up the disk array with redundancy properties by the present invention, and user can only see one piece of hard disk in use, now the available memory space of user be several flash memory particles capacity with.In addition, when user storage data, data storage is written in parallel in each flash memory particle, and the read or write speeds of data obtains increasing to being greatly improved.And the redundancy of data can be improved using raid5 redundancy schemes, a flash memory particle damage does not influence other flash memory particles, protects data storage.
Description
Technical field
The present invention relates to the implementation method of a kind of solid state hard disc and its RAID array, belongs to storage medium design
Technical field.
Background technology
Hard disk is developed so far the history in more than 50 years, and in the course of this decades, the volume of hard disk is less and less
And capacity is increasing, the rotating speed of hard disk is also growing with each passing hour with interface.When first item hard disk emerges, it has two refrigerators
So wide, inside is mounted with the disks of 50 two feet of diameters, about 1 ton of weight, and micro harddisk, CF hard disks only just coin now
Size.
Hard disk is generally divided into solid state hard disc, mechanical hard disk, the class of hybrid hard disk three at present.Solid state hard disc uses flash memory particle
To store, mechanical hard disk is stored using magnetic disk, and hybrid hard disk is one kind that magnetic hard-disk and flash memory are integrated together
Hard disk.Most hard disks are all Fixed disks, are fixed on by permanently sealing in hard disk drive.
Hard disk has the function that irreplaceable as storage medium in Development of storage technology history.And currently most develop
The hard disk type of potentiality is exactly solid state hard disc.Solid state disk read-write speed is fast, and due to not needing magnetic head, solid state hard disc is not sought
Time, read and the speed of write-in is all very high.In addition.Compared to mechanical hard disk, the shockproof crash resistance of solid state hard disc is very high, and low work(
Consume noiseless lighter.These advantages cause the use of solid-state disk more and more frequent.
But solid state hard disc is expensive, and restricted lifetime, due to using flash memory as storage medium, once one piece is dodged
Depositing to break down can cause solid state hard disc really to make a mistake, and cause it not use.Particularly, when event occurs for solid state hard disc
Barrier, data storage is irrecoverable, and that is sporadically dispersed in each flash memory because of data, be from the flash chip after damage
Middle data recovery, as a consequence it is hardly possible to.
If the reliability of solid state hard disc can be ensured using redundancy scheme in use, then can improves solid
The performance of state hard disk.Several pieces of identical hard disks in use, are generally established raid by common hard disk, increase redundancy work(
Can, and storage cell of one piece of hard disk as minimum, it is difficult to have redundancy feature.
Chinese patent literature CN 103034458A disclose the side that RAID is realized in a kind of solid state hard disc
Method and device.This method includes:At least two pages in each data block are bound into vertical verification band;To vertical verification
Data are sequentially written in each page of band, and using last page of vertical verification band as the vertical verification band
Verify the page.But due to not taking into full account the influence factor of passage in SSD, institute when the patent binds verification band
So that the fault-tolerant of channel failure in SSD can not be realized, and the speed concurrently the brought lifting of different passages can not be made full use of.
Chinese patent literature CN 102915212A disclose the RAID implementation methods of solid state hard disc a kind of, solid state hard disc and
Electronic equipment, the implementation method include:Determined to carry out solid state hard disc the subregion of subregion according to RAID type
Number;The solid state hard disc is divided into by multiple subregions according to physical address according to the number of partitions;Independence is established respectively for each subregion
Flash translation layer (FTL);RAID is created using multiple subregions of solid state hard disc as logic magnetic disc.But the patent
In the logical partition that refers to still exist each partition data can not parallel processing the problem of, although improving data reliability,
But the efficiency of data access can be reduced.
The content of the invention
In view of the shortcomings of the prior art, the invention provides a kind of realization side of the RAID array of solid state hard disc
Method;This method can improve data by increasing raid hardware acceleration units in the case where not influenceing data rate memory
Redundancy, ensure still to may insure the normal access of data in the case of the flash memory particle failure of part.
The invention provides a kind of solid state hard disc for realizing RAID array.
Term is explained:
1st, RAID5, it is the storage solution that a kind of storage performance, data safety and carrying cost are taken into account.RAID5 can be with
It is not understood as RAID0 and RAID1 half-way house.RAID5 can be systems with data safety guarantee, but degree of protection than
Mirror is low and disk space usage is higher than Mirror.The data reading speed that RAID5 has and RAID0 is similar, only
The parity information that has been more, writing the speed ratios of data, to carry out write operation to single disk slightly slow.It is simultaneously because more
The corresponding parity information of individual data, RAID5 disk space usage is higher than RAID1, and carrying cost is relatively low,
It is to use more a solution at present.
2nd, SSD, Fixed disk, multiple flash memory particles form, a flash memory particle is by multiple data blocks (Block) structure
Into a data block is made up of multiple pages (page).
3rd, RAID array (RAID) technology, it is that a kind of physical hard disk polylith independence combines in some way
Get up to be formed a hard disk groups, i.e. logic hard disk, so as to provide storage performance higher than single hard disk and data redundant reliability
Technology.
The technical scheme is that:
A kind of implementation method of the RAID array of solid state hard disc, including:With the flash memory under same passage in SSD
Particle is unit, and raid5 is formed with the flash memory particle under other passages.Make full use of the concurrent capability of each passage;In tradition
SSD controller in, add hardware RAID unit, realize the acceleration of calculating, reduce speed caused by internal raid building processes
Loss.
It is different from the mode of traditional SSD data storages, when the present invention carries out data storage, by the flash memory of different passages
Particle is constructed as raid5, is stored in the data of a passage originally, can be split as different slice of datas, carries out calculating school
Test, be concurrently stored in the flash memory particle of different passages together with slice of data after obtaining check value.Wherein calculate the portion of verification
Point, realized using the hardware cell of raid acceleration.
According to currently preferred, the particle under solid state hard disc difference passage is constructed as raid5, comprised the following steps:
(1) the flash memory particle under each passage is subjected to the cutting (in units of page or block) according to fixed size, it is complete
Into the striping of particle group, bound with the flash memory particle of other passage same positions;Store initial data striped data and
Verification data.As shown in Figure 1, it is assumed that the flash memory particle in SSD is divided into 4 passages, and what each passage can be independently enters
The access and storage of row data, carry out data storage in the way of raid5.
(2) when carrying out data storage, cutting is carried out to the initial data to be stored according to the quantity of passage and stripe size,
The slice of data of initial data after cutting is stored in the bar that the different passage flash memory particles that step (1) obtains divide in advance successively
In band, slice of data is verified successively, obtains the verification data of formed objects, and verification data DYNAMIC DISTRIBUTION obtains in step (1)
To different passage flash memory particles band in.As shown in figure 1, number of channels is 4, initial data D meeting cuttings are D1-D24, according to
In each channel, the flash memory particle of all passage same positions binds one group, carries out the cutting of formed objects, deposits for secondary storage
The slice of data and verification data of initial data are put, verification data is uniformly deposited in different channels respectively.
(3) when carrying out digital independent, while the slice of data being stored in different passage flash memory granule strip bands is read,
Verified by checking algorithm, if there is the data of bad block or partial destruction, then corrected, recover correct original
Beginning data.
According to currently preferred, in traditional SSD controller, hardware RAID unit added, realizes the cutting of data
The acceleration calculated with verification, speed loss caused by the internal raid building processes of reduction, including step are as follows:
(1) as shown in Fig. 2 raid accelerates the input of data cutting unit to include SSD number of channels, each passage flash memory
The capacity of particle and the size of data that will be stored, the output of data cutting unit be stored data section, the number of section
Amount is dynamically adjusted with input factor, so the size of data storage can directly determine the degree of data cutting.Will
Each data slicer can be larger when the data of storage are big, effectively improves the processing speed of data, realizes to tradition
The dynamic adjustment of stripe size in raid5.Will not be chaotic when in order to carry out digital independent, for each data being stored into
The position where corresponding slice numbers and first section will be recorded, the section hardware cell has certain caching can be with
Improve data access efficiency.
(2) Fig. 2 has embodied the function that raid accelerates data check unit, i.e., calculates check value according to data slicer,
And by data slicer and check value parallel memorizing in different passages.The concrete structure of the calculating verification unit as shown in figure 3,
Even-odd check, D are realized using digital NAND gate0-7For information bit, DSchoolFor check bit, specifically it is calculated as:
(3) overall hard disk composition as shown in figure 4, from conventional hard unlike raid accelerator modules addition, it is responsible
The data stored to flash memory particle are cut into slices, check value calculating, most obtain data deposit flash memory particle with check value at last
In.
A kind of solid state hard disc for realizing RAID array, using the concurrent reading and writing row of each passage in SSD,
Data storage and the speed accessed are improved, using raid5 accelerator modules, stripe size dynamic when realizing the raid5 storages of data
Change and verification data quick calculating.The hardware cell is located at SSD controller end, the data that can issue controller
Process instruction carries out raid5 processing mapping, and controller need not be concerned about raid5 processing details, therefore data will not be brought to deposit
The efficiency of storage declines.Once there is the damage of flash memory particle, controller will not be reported when data access is not influenceed, until
Corrupted data is just notified that controller has bad block and needs to handle to the stage that can not be repaired, so as to postpone ssd service life.
Beneficial effects of the present invention are:
1st, make full use of the concurrent reading and writing performance of different passage flash memory particles in SSD, using the flash memory particle of different passages as
Unit, raid5 is constructed as, realizes and still ensure the read-write of data in the case where passage portion flash memory particle damages, improve
The security of data.According to the difference of number of active lanes, the reliability of data can improve 10% or so.
2nd, using raid acceleration hardware units, the adjustment of dynamic raid5 stripe sizes when being stored to different pieces of information is realized, is carried
Storage efficiency under high different data streams storage;Hardware check computing unit has effectively unloaded upper layer application or SSD controller
Load, the reduction of efficiency will not be brought on the basis of raid redundancy guarantees are realized.
Brief description of the drawings
Fig. 1 is the schematic diagram that the present invention sets up RAID5 with different passage flash memory particles in SSD;
Fig. 2 is RAID5 accelerating hardwares workflow schematic diagram of the present invention;
Fig. 3 is the hardware elementary diagram of even-odd check of the present invention;
Fig. 4 is the SSD Organization Charts that the present invention finally realizes;
Embodiment
The present invention is further qualified with reference to Figure of description and embodiment, but not limited to this.
Embodiment 1
A kind of implementation method of the RAID array of solid state hard disc, including:With the flash memory under same passage in SSD
Particle is unit, and raid5 is formed with the flash memory particle under other passages.Make full use of the concurrent capability of each passage;In tradition
SSD controller in, add hardware RAID unit, realize the acceleration of calculating, reduce speed caused by internal raid building processes
Loss.
It is different from the mode of traditional SSD data storages, when the present invention carries out data storage, by the flash memory of different passages
Particle is constructed as raid5, is stored in the data of a passage originally, can be split as different slice of datas, carries out calculating school
Test, be concurrently stored in the flash memory particle of different passages together with slice of data after obtaining check value.Wherein calculate the portion of verification
Point, realized using the hardware cell of raid acceleration.
Particle under solid state hard disc difference passage is constructed as raid5, comprised the following steps:
(1) the flash memory particle under each passage is subjected to the cutting (in units of page or block) according to fixed size, it is complete
Into the striping of particle group, bound with the flash memory particle of other passage same positions;Store initial data striped data and
Verification data.As shown in Figure 1, it is assumed that the flash memory particle in SSD is divided into 4 passages, and what each passage can be independently enters
The access and storage of row data, carry out data storage in the way of raid5.
(2) when carrying out data storage, cutting is carried out to the initial data to be stored according to the quantity of passage and stripe size,
The slice of data of initial data after cutting is stored in the bar that the different passage flash memory particles that step (1) obtains divide in advance successively
In band, slice of data is verified successively, obtains the verification data of formed objects, and verification data DYNAMIC DISTRIBUTION obtains in step (1)
To different passage flash memory particles band in.As shown in figure 1, number of channels is 4, initial data D meeting cuttings are D1-D24, according to
In each channel, the flash memory particle of all passage same positions binds one group, carries out the cutting of formed objects, deposits for secondary storage
The slice of data and verification data of initial data are put, verification data is uniformly deposited in different channels respectively.
(3) when carrying out digital independent, while the slice of data being stored in different passage flash memory granule strip bands is read,
Verified by checking algorithm, if there is the data of bad block or partial destruction, then corrected, recover correct original
Beginning data.
In traditional SSD controller, hardware RAID unit is added, realizes the acceleration that the cutting of data and verification calculate,
Speed loss caused by reducing internal raid building processes, including step are as follows:
(1) as shown in Fig. 2 raid accelerates the input of data cutting unit to include SSD number of channels, each passage flash memory
The capacity of particle and the size of data that will be stored, the output of data cutting unit be stored data section, the number of section
Amount is dynamically adjusted with input factor, so the size of data storage can directly determine the degree of data cutting.Will
Each data slicer can be larger when the data of storage are big, effectively improves the processing speed of data, realizes to tradition
The dynamic adjustment of stripe size in raid5.Will not be chaotic when in order to carry out digital independent, for each data being stored into
The position where corresponding slice numbers and first section will be recorded, the section hardware cell has certain caching can be with
Improve data access efficiency.
(2) Fig. 2 has embodied the function that raid accelerates data check unit, i.e., calculates check value according to data slicer,
And by data slicer and check value parallel memorizing in different passages.The concrete structure of the calculating verification unit as shown in figure 3,
Even-odd check, D are realized using digital NAND gate0-7For information bit, DSchoolFor check bit, specifically it is calculated as:
(3) overall hard disk composition as shown in figure 4, from conventional hard unlike raid accelerator modules addition, it is responsible
The data stored to flash memory particle are cut into slices, check value calculating, most obtain data deposit flash memory particle with check value at last
In.
Embodiment 2
A kind of solid state hard disc for the RAID array for realizing solid state hard disc, using each passage in SSD
Concurrent reading and writing row, data storage and the speed accessed are improved, using raid5 accelerator modules, bar when realizing the raid5 storages of data
Dynamically change the quick calculating with verification data with size.The hardware cell is located at SSD controller end, can be by controller
The data processing instructions issued carry out raid5 processing mapping, and controller need not be concerned about raid5 processing details, therefore will not
The efficiency of data storage is brought to decline.Once there is the damage of flash memory particle, will not be reported when data access is not influenceed
Controller, until corrupted data to the stage that can not be repaired just is notified that controller has bad block and needs to handle, so as to postpone ssd
Service life.
Claims (6)
- A kind of 1. solid state hard disc, it is characterised in that including be sequentially connected interface, SSD controller, RAID5 hardware acceleration units, Some passages, the RAID5 hardware acceleration units connect some passages respectively, and every passage includes several Flash memory particle;The SSD controller is used to issue data processing instructions;The RAID5 hardware acceleration units are used to realize data Dynamic change, the quick calculating of verification data of stripe size when raid5 is stored, and the data processing that SSD controller is issued Instruction carries out raid5 processing mapping.
- A kind of 2. solid state hard disc according to claim 1, it is characterised in that the RAID5 hardware acceleration units include according to The RAID of secondary connection accelerates data cutting unit, RAID to accelerate data check unit;The RAID accelerate data cutting unit according to number of channels, each passage flash memory particle capacity, to be stored it is original Data, cutting is carried out to the initial data to be stored, obtains the slice of data for the initial data to be stored;The RAID accelerates data check unit to be used for the check value for calculating the slice of data of initial data;And by initial data Slice of data and the check value parallel memorizing asked for are in different passages.
- 3. the implementation method of the RAID array of the solid state hard disc described in claim 1 or 2, it is characterised in that including: Using the flash memory particle under same passage as unit, raid5 is formed with the flash memory particle under other passages.
- 4. the implementation method of the RAID array of solid state hard disc according to claim 3, it is characterised in that will be solid Flash memory particle under state hard disk difference passage is constructed as raid5, comprises the following steps:(1) striping:Flash memory particle under each passage is subjected to cutting according to fixed size, completes the band of flash memory particle Change, the flash memory particle of the same position of different passages is bound;(2) initial data stores:Cutting is carried out to the initial data to be stored according to the quantity of passage and stripe size, after cutting The slice of data of initial data be stored in successively in the band that the different passage flash memory particles that step (1) obtains divide in advance, Slice of data is verified successively, obtains the verification data of formed objects, and verification data DYNAMIC DISTRIBUTION obtains not in step (1) In band with passage flash memory particle;(3) initial data is read:When reading initial data, while read the section being stored in different passage flash memory granule strip bands Data, verified by checking algorithm, if there is the data of bad block or partial destruction, then corrected, recovered just True initial data.
- 5. the implementation method of the RAID array of solid state hard disc according to claim 4, it is characterised in that will be every Flash memory particle under individual passage carries out cutting in units of the page or data block.
- 6. the implementation method of the RAID array of the solid state hard disc according to claim 4 or 5, it is characterised in that The step (2), comprises the following steps:A, number of channels, the capacity of each passage flash memory particle, the initial data to be stored are inputted to the RAID and accelerates number According to cutting unit, the RAID accelerates data cutting unit to carry out cutting to the initial data to be stored, and exports the original to be stored The slice of data of beginning data, and record the quantity of the slice of data for the initial data to be stored, the of the initial data to be stored The position of one slice of data;B, the check value of the slice of data of data check unit calculating initial data is accelerated by the RAID;Using it is digital with it is non- Door realizes even-odd check, shown in calculation formula such as formula (I)-formula (IV):In formula (I)-formula (IV), D0、D1、D2、D3、D4、D6、D6、D7For information bit, DSchoolFor check bit;The RAID accelerates data check unit by the slice of data of initial data and the check value parallel memorizing asked in difference Passage in.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710910760.XA CN107678690A (en) | 2017-09-29 | 2017-09-29 | A kind of implementation method of solid state hard disc and its RAID array |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710910760.XA CN107678690A (en) | 2017-09-29 | 2017-09-29 | A kind of implementation method of solid state hard disc and its RAID array |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107678690A true CN107678690A (en) | 2018-02-09 |
Family
ID=61137708
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710910760.XA Pending CN107678690A (en) | 2017-09-29 | 2017-09-29 | A kind of implementation method of solid state hard disc and its RAID array |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107678690A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108984133A (en) * | 2018-08-27 | 2018-12-11 | 杭州阿姆科技有限公司 | The implementation method of RAID in a kind of SSD |
CN110858122A (en) * | 2018-08-23 | 2020-03-03 | 杭州海康威视***技术有限公司 | Method and device for storing data |
CN112748857A (en) * | 2019-10-30 | 2021-05-04 | 伊姆西Ip控股有限责任公司 | Method, electronic device and computer program product for storage management |
CN112817533A (en) * | 2021-01-29 | 2021-05-18 | 深圳忆联信息***有限公司 | SSD management method, device computer equipment and storage medium |
CN117311647A (en) * | 2023-11-30 | 2023-12-29 | 武汉麓谷科技有限公司 | Method for realizing Raid based on ZNS solid state disk |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201130371Y (en) * | 2007-11-05 | 2008-10-08 | 湖南源科创新科技股份有限公司 | High-speed storage array based on SATA interface solid state hard disk |
US20120017036A1 (en) * | 2010-07-19 | 2012-01-19 | Byungcheol Cho | Hybrid storage system for a multi-level raid architecture |
CN103019617A (en) * | 2012-11-25 | 2013-04-03 | 向志华 | Establishing method for efficiently realizing internal RAID of SSD, data reading and writing method and device |
CN103577111A (en) * | 2012-07-23 | 2014-02-12 | 上海宝存信息科技有限公司 | Nonvolatile memory based dynamic redundant array of independent disks (RAID) storage system and method |
CN103718162A (en) * | 2011-08-12 | 2014-04-09 | 华为技术有限公司 | Method and apparatus for flexible raid in ssd |
CN105573681A (en) * | 2015-12-31 | 2016-05-11 | 湖南国科微电子股份有限公司 | Method and system for establishing RAID in SSD |
CN106527971A (en) * | 2016-10-08 | 2017-03-22 | 华中科技大学 | Method for improving read performance of SSD during junk recovery period |
-
2017
- 2017-09-29 CN CN201710910760.XA patent/CN107678690A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201130371Y (en) * | 2007-11-05 | 2008-10-08 | 湖南源科创新科技股份有限公司 | High-speed storage array based on SATA interface solid state hard disk |
US20120017036A1 (en) * | 2010-07-19 | 2012-01-19 | Byungcheol Cho | Hybrid storage system for a multi-level raid architecture |
CN103718162A (en) * | 2011-08-12 | 2014-04-09 | 华为技术有限公司 | Method and apparatus for flexible raid in ssd |
CN103577111A (en) * | 2012-07-23 | 2014-02-12 | 上海宝存信息科技有限公司 | Nonvolatile memory based dynamic redundant array of independent disks (RAID) storage system and method |
CN103019617A (en) * | 2012-11-25 | 2013-04-03 | 向志华 | Establishing method for efficiently realizing internal RAID of SSD, data reading and writing method and device |
CN105573681A (en) * | 2015-12-31 | 2016-05-11 | 湖南国科微电子股份有限公司 | Method and system for establishing RAID in SSD |
CN106527971A (en) * | 2016-10-08 | 2017-03-22 | 华中科技大学 | Method for improving read performance of SSD during junk recovery period |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110858122A (en) * | 2018-08-23 | 2020-03-03 | 杭州海康威视***技术有限公司 | Method and device for storing data |
CN110858122B (en) * | 2018-08-23 | 2023-10-20 | 杭州海康威视***技术有限公司 | Method and device for storing data |
CN108984133A (en) * | 2018-08-27 | 2018-12-11 | 杭州阿姆科技有限公司 | The implementation method of RAID in a kind of SSD |
CN108984133B (en) * | 2018-08-27 | 2022-01-28 | 杭州阿姆科技有限公司 | Method for realizing RAID in SSD |
CN112748857A (en) * | 2019-10-30 | 2021-05-04 | 伊姆西Ip控股有限责任公司 | Method, electronic device and computer program product for storage management |
CN112748857B (en) * | 2019-10-30 | 2024-04-26 | 伊姆西Ip控股有限责任公司 | Method, electronic device and computer program product for storage management |
CN112817533A (en) * | 2021-01-29 | 2021-05-18 | 深圳忆联信息***有限公司 | SSD management method, device computer equipment and storage medium |
CN117311647A (en) * | 2023-11-30 | 2023-12-29 | 武汉麓谷科技有限公司 | Method for realizing Raid based on ZNS solid state disk |
CN117311647B (en) * | 2023-11-30 | 2024-03-15 | 武汉麓谷科技有限公司 | Method for realizing Raid based on ZNS solid state disk |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107678690A (en) | A kind of implementation method of solid state hard disc and its RAID array | |
US11042441B2 (en) | Stripe mapping in memory | |
CN102880428B (en) | The creation method of distributed Redundant Array of Independent Disks (RAID) and device | |
US9235503B2 (en) | Stripe-based non-volatile multilevel memory operation | |
CN107250975B (en) | Data storage system and data storage method | |
CN101587425B (en) | Method and device for increasing magnetic disc redundant array redundancy | |
US6393516B2 (en) | System and method for storage media group parity protection | |
CN105573681B (en) | Method and system for establishing RAID in SSD | |
CN103049222A (en) | RAID5 (redundant array of independent disk 5) write IO optimization processing method | |
CN111782439B (en) | Double-disk circulation verification method based on horizontal coding | |
JPH04230512A (en) | Method and apparatus for updating record for dasd array | |
CN103488432B (en) | Hybrid disk array, deferred write verification method for hybrid disk array, and data recovery method for hybrid disk array | |
CN102122235A (en) | RAID4 (redundant array of independent disks) system and data reading and writing method thereof | |
CN101504625A (en) | Method for implementing independent disk redundancy array, solid state disk and electronic equipment | |
CN108733326B (en) | Disk processing method and device | |
CN108984133B (en) | Method for realizing RAID in SSD | |
CN109491613A (en) | A kind of continuous data protection storage system and its storage method using the system | |
CN111400083A (en) | Data storage method and system and storage medium | |
CN110413454A (en) | Data re-establishing method, device and storage medium based on storage array | |
US11256447B1 (en) | Multi-BCRC raid protection for CKD | |
CN102981969A (en) | Method for deleting repeated data and solid hard disc thereof | |
CN103336727A (en) | NAND flash memory storage device and data operation method for same | |
CN103544124B (en) | The access method of Nand flash storages | |
CN115237342A (en) | RAID5 verification method for data verification by array disk | |
CN107728943B (en) | Method for delaying generation of check optical disc and corresponding data recovery method |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180209 |