CN102200892B - Capacity expansion method based on dynamic redundant array of independent disks (RAID) system - Google Patents
Capacity expansion method based on dynamic redundant array of independent disks (RAID) system Download PDFInfo
- Publication number
- CN102200892B CN102200892B CN 201110111802 CN201110111802A CN102200892B CN 102200892 B CN102200892 B CN 102200892B CN 201110111802 CN201110111802 CN 201110111802 CN 201110111802 A CN201110111802 A CN 201110111802A CN 102200892 B CN102200892 B CN 102200892B
- Authority
- CN
- China
- Prior art keywords
- band collection
- band
- disk
- collection unit
- raid
- 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 50
- 238000013507 mapping Methods 0.000 claims abstract description 20
- 230000008859 change Effects 0.000 claims description 12
- 238000013508 migration Methods 0.000 abstract description 20
- 230000005012 migration Effects 0.000 abstract description 20
- 230000008569 process Effects 0.000 description 16
- 230000010339 dilation Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000002679 ablation Methods 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000007858 starting material Substances 0.000 description 1
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The objective of the invention is to provide a capacity expansion method based on a dynamic redundant array of independent disks (RAID) system. The capacity expansion method comprises the following steps of: firstly, dividing the dynamic RAID system into a plurality of stripe sets; secondly, selecting one stripe set p, selecting a stripe set unit which is numbered p-q, moving to a newly-added disk which is numbered r, keeping the offset of the stripe set unit invariable, and updating an address mapping table, wherein q is equal to (p) mod (m+n), and r is equal to (q) mod (m+n); and finally, traversing all stripe sets according to the steps to finish capacity expansion. The dynamic RAID system is formed by introducing a stripe set concept to the conventional RAID system, so data is accessed by the stripe sets instead of the disk by introduction of the stripe sets. By the capacity expansion method, a theoretic data migration minimum can be reached, migration unit is the stripe set unit,and time require for migration of same data quantity is less.
Description
Technical field
The invention belongs to technical field of data storage, particularly relate to a kind of expansion method based on dynamic RAID system.
Background technology
The information that modern society produces, take 2002 as example, one year has produced the information of about 5EB, wherein 92% fresh information major part is stored in the disk, large capacity disc has become present requisite storage medium; The storage of important information seems particularly crucial such as company information, irreclaimable information more than ten sky appearred in 50% the company that studies show that, data appear in 43% company closes down after forever losing at once, closing down after the serious loss of data appears in 93% company, and data reliability is particularly important in the data storage.And from its birth, just storage system, obtained using very widely based on the memory technology of raid-array RAID, because the recovery of the obliterated data that adopts the storage system of RAID structure can guarantee the reliability of system and cause owing to disk failure, but the continuous increase along with quantity of information, the data of depositing among the RAID also constantly increase, the disk active volume constantly reduces, when original design capacity has not satisfied the data increase, disk will face the predicament that the space exhausts.In case disk space exhausts, buy new disk then on new disk RAID the original RAID data of reconstruct be consuming time very large, but also be faced with several days when the machine time, this service request to the 7/24 present time is a very large challenge.
Summary of the invention
The object of the present invention is to provide a kind of expansion method based on dynamic RAID system, this expansion method can solve the technical matterss such as traditional RAID system length consuming time and migration data amount in dilation process be large.
The invention provides a kind of expansion method based on dynamic RAID system, establishing the original disk number is m, and newly-increased disk number is n, and newly-increased disk is numbered respectively 0 to n-1, and the method may further comprise the steps:
(1) be the band collection with dynamic RAID system divides;
(2) choose a band collection p, judge the p-q that is numbered that whether has a band collection unit among the band collection p, wherein p is band collection numbering, q=((p) mod (m+n)), if exist, then with this band collection cell moving to the newly-increased disk that is numbered r and keep the side-play amount of this band collection unit constant, and upgrade the address mapping table of this band collection unit, wherein r=((q) mod (n)); If do not exist, then do not do any operation;
(3) judge whether n equals 1, if change step (6) over to; Otherwise, make t=1, enter step (4);
(4) judge whether have band collection unit in the band collection (p+t) be numbered (p+t) q, if exist, then with this band collection cell moving to the newly-increased disk that is numbered r and keep the side-play amount of this band collection unit constant, and upgrade the address mapping table of this band collection unit, wherein (p+t) is band collection numbering; If do not exist, then do not do any operation;
(5) judge whether t equals (n-1), if enter step (6); Otherwise, make t=t+1, change step (4) over to;
(6) according to the operation of step (2) to (5), all band collection of dividing in the traversal step (1).
Proposed by the invention dynamic RAID system is the concept that has increased a band collection in traditional RAID system, and the introducing by the band collection is so that visit data by disk and become by the band collection and visit data.Expansion method based on dynamic RAID system of the present invention has following advantage with respect to traditional expansion method:
1. can realize online dilatation, avoid shutting down the situation that can't realizing of causing served.
2. dilation process migration data amount is little, the RAID that consists of at original m disk increases n disk, in order to reach load balancing, theoretic Data Migration minimum value is the n/ (m+n) that accounts for total amount of data, and expansion method of the present invention can reach this minimum value.
3. in data migration process, traditional RAID migration be the small data piece, and this method migration is long data block, the time of the same data volume needs of disk migration still less like this.
Description of drawings
The schematic diagram of Fig. 1 collection and band;
Fig. 2 side-play amount schematic diagram;
Fig. 3 sets up the address mapping table procedure chart;
Fig. 4 scheduler mapping table procedure chart;
Fig. 5 m=4, the disk dilation process figure of n=1;
Fig. 6 modified address mapping table procedure chart;
Fig. 7 data read process figure;
Fig. 8 m=4, the disk dilation process figure of n=2;
Fig. 9 data capacity reducing procedure chart.
Embodiment
Below in conjunction with accompanying drawing of the present invention and related example, dynamic RAID system is described more clearly and based on the expansion method of dynamic RAID system.
The basic structure of storage data is bands among the RAID, and stripe size has 16K, 32K, 64K, 128K, 256K several, and RAID5 generally gets 32K or 64K.Band is distributed in each disk, and a band can only have a data block in each disk, and this data block generally is called stripe cell.
Existing RAID is when structure, it all is the mode store data that adopts band, because band belongs to the smaller data acquisition of granularity, can form a very large address mapping table during Data Migration, therefore the present invention is in the concept of this proposition " band collection ", and the band collection is the larger data acquisition of granularity, and band collection can be made of hundreds of even thousands of bands, each band collection forms the RAID of a small grain size, and these small grain size RAID need not consider the RAID rank.All stripe cell that belong to same band collection in each disk can be used as an integral body, and this integral body is called " band collection unit ".
Figure 1 shows that the RAID that is formed by 4 disks, wherein A1, B1, C1, four data blocks of D1 consist of a band, A1, B1, C1, D1 are called stripe cell, the band collection that four bands consist of, A1 to A4, B1 to B4, C1 is called band collection unit to C4, D1 to D4.In order to make things convenient for the realization of Data Migration, the below is numbered band collection and band collection unit, for a top band collection among Fig. 1 (being the band collection that A1 forms to C4, D1 to D4 to B4, C1 to A4, B 1), be numbered 0 (in computer major, to the numbering of storage medium all since 0), be numbered 1 for following band collection.The numbering of band collection unit also is since 0, and it is 1 that the numbering that first band collection element number of concentrating at a band is band collection unit A1, B1, C1, D1 among 0, Fig. 1 is 0, the second band collection element number, by that analogy.The numbering of band collection unit integrates as object of reference with band, is the internal number of band collection, and this numbering does not change with the movement of band collection unit.The overall situation numbering of band collection unit adds what the internal number of band collection formed by the band collection numbering at its place, be numbered 1 such as the band collection below among Fig. 1, band collection unit internal number on the disk 0 is 0, band collection unit internal number on the disk 1 is 1, and the overall situation of these two band collection unit is numbered 1-0 and 1-1 so.In the situation that do not obscure, this paper just is called the overall situation of band collection unit numbering the numbering of band collection unit.
The numbering of band collection unit can obtain according to the LBA address that main frame provides, and LBA is the linear address of an one dimension.When making up the band collection, it all is artificial the setting that band is concentrated the number of band and stripe size, suppose that band concentrates total e band, and the size of each band is s, so can be by LBA divided by (e * s) amasss, and the merchant who obtains is that the band collection is numbered.Suppose each bar with m stripe cell, each stripe unit size is exactly s/m so.To the s delivery, divided by stripe unit size s/m, the merchant who obtains is exactly the internal number in the band collection element number this result by LBA.
Dynamic RAID of the present invention system comprises a plurality of disks and the RAID controller that consists of RAID, the concept that this dynamic RAID system has logically divided the band collection, so that a plurality of bands have consisted of a band collection, the similar sub-RAID of band collection, this dynamic RAID system also comprises an address mapping table, and this address mapping table records the positional information of all band collection unit.
Concretely, dynamically the band collection of RAID is a division in logic, when RAID builds, can configure the quantity that band is concentrated band according to disk size, hard disk such as 150G, the size of stripe cell is 16KB, can select so 2M as the size of a band collection unit, just says that also band concentrates and to have 2M/16KB=128 band.Especially, for each band collection, can configure different RAID ranks, only think that in the present invention all band collection all are same ranks, illustrate with this.Dynamically RAID in order to make things convenient for the Mobile data piece, has also made up an address mapping table after having constructed such band collection, and this address mapping table is comprised of the two-stage table.The one-level table is band collection table, each band set pair is answered a list item in the one-level table, each one-level table list item points to a secondary table, the position of all band collection unit of each band collection of record in the secondary table, there are three row the position of the corresponding band collection unit of each secondary table list item in the secondary table, first row is the internal number of band collection unit, secondary series represents the numbering of this place, band collection unit disk, and this side-play amount of band collection unit in disk is shown in the 3rd tabulation.Side-play amount represents the band collection element number between this band collection unit and the disk starter strip collection unit, as shown in Figure 2, four band collection unit of band collection 0 are placed on the top of disk, the reference position of disk namely, therefore side-play amount is 0, four band collection unit of band collection 1 are placed on the position apart from a band collection of disk reference position unit, so side-play amount is 1, by that analogy.
Address mapping table is the process of a Dynamic Establishing, whenever writes a band collection unit, just adds secondary list item corresponding to this band collection unit.As shown in Figure 3, it has represented the process of setting up of address mapping table, integrates unit 0-0 as example to write band, first according to collection number 0, set up 0 of collection in the one-level table, and then set up the secondary table of collection 0 correspondence, and the numbering 0 of band collection unit 0-0, disk number 0, side-play amount 0 is inserted in the secondary table.When data mobile is arranged, revise corresponding secondary table content, as shown in Figure 4, band collection unit 0-0 is from original position movement to disk after 4, at first search collection 0 one-level table, by collecting 0 position of finding band collection unit 0 in the secondary table, revise disk number position disk 4, because the side-play amount or 0 of band collection unit 0-0 in disk 4, so the side-play amount part does not change.Band collection unit 0-0 moves to after the reposition, numbering or 0-0, because this band collection unit still belongs to collection first band collection unit of 0, on data, its is preserved still collects the data of the beginning in 0, and therefore numbering does not change.
Certain value that has surpassed total memory capacity when original m data in magnetic disk, such as 80%, just need dilatation.In an original m disk, the band collection is by m band collection cell formation, in case dilatation n disk, for load balancing, must move to newly-increased disk to partial data from original disk, so that the data volume of each disk is approximate identical, the visit capacity of each disk could be similar to identically like this, namely needs all the band collection cell distribution on m the disk realization dilatation and load balancing in m+n the disk.
Expansion method based on dynamic RAID of the present invention, its basic thought is after increasing new disk, some the band collection unit of the band collection on the original disk is moved on the new disk, and guarantee the data distributing equilibrium, the band collection that the spatial composing of newly vacating is new is used for storing new data.Concrete Data Migration mode has multiple, and every employing project organization of the present invention and thinking are done some simple designs that change or change, and all fall into the scope of protection of the invention.
The below is with m=4, and n=1 is the reading/writing method that example is introduced data after the method for dynamic RAID dilatation and the dilatation in detail.
1. dynamic RAID expansion method
Data Migration does not need mobile all data in expansion method of the present invention, as shown in Figure 5,4 disks are arranged in the original disk array, be numbered respectively 0 to 3, newly increased a disk, be numbered new disk 0, each band collection is chosen a band collection cell moving to newly-increased disk, it is just out vacant that original disk moves out of the white space of data, can fill new data.
The expansion method detailed process is as follows:
(1) divides the band collection, have 128 bands with each band collection and be as the criterion and divide the number of record band collection.
(2) choose band collection 0, judge whether to exist band collection unit 0-0 (p=0, q=0mod 5), exist, then this band collection unit is moved on to newly-increased disk 0 (r=0mod n, n=1, so r here equals 0 forever);
(3) because n=1 directly selects next band to move;
(4) choose band collection 1, judge whether to exist band collection unit 1-1 (p=0, q=1mod 5), exist, then band collection unit 1-1 is moved to the 0th new disk;
(5) choose band collection 2, judge whether to exist band collection unit 2-2 (p=0, q=2mod 5), exist, then band collection unit 2-2 is moved to the 0th new disk;
(6) choose band collection 3, judge whether to exist band collection unit 3-3 (p=0, q=3mod 5), exist, then band collection unit 3-3 is moved to the 0th new disk;
(7) choose band collection 4, judge whether to exist band collection unit 4-4 (p=0, q=4mod 5), do not exist, then do not do any operation;
(8) Data Migration of the next band collection of continuation, all band collection of dividing in the traversal step (1) according to the method described in the present invention.
After each band collection cell moving, need to upgrade the address mapping table of this band collection unit, the disk number that is about to this band collection unit changes to new disk number.
As seen from Figure 5, band collection unit number on each disk is the same, and with on 4 these zones from band collection 0 to the band collection, 4 band collection unit have been increased on the newly-increased disk, always have 20 band collection unit on original four disks, the Data Migration amount is 4/20=0.2, and is identical with n/ (m+n)=1/5, reached theoretic minimum value.
2. the method for writing data after the disk dilatation
After Data Migration is finished, a lot of white spaces can appear in each disk, and these zones can be used for forming new band collection, fill in new data.The new data ablation process is finished in two steps, and the first step is that new data is write disk, and second step is to revise corresponding address mapping table.
Fig. 6 shown and write after the band collection 8, and the situation of modified address mapping table is only indicated the situation that address mapping table corresponding to band collection unit 8-1 made amendment on figure, and the modification process of all the other band collection unit is similar.After band collection unit 8-1 writes disk, at first search the one-level table at band collection 8 places, if do not have, expression band collection 8 is new datas, then adds the one-level list item of band collection 8, then adds a secondary table.According to the numbering of band collection unit, this band collection unit record second row in secondary table.When dividing the band collection, disk and the side-play amount each band collection unit deposited are calculated, and are 1 position if band collection unit 8-1 is placed on the side-play amount of disk 1, and the secondary list item of then filling in is: 8-1, disk 1, skew 1.
3. the method for reading data after the disk dilatation
Obtain the numbering of band collection unit according to the method for setting forth previously by the LBA address, then access band collection one-level table, obtain disk and the side-play amount at all places, band collection unit of whole band collection, thereby find this band collection unit and from the relevant position reading out data according to these information.
As shown in Figure 7, if want to read this band collection unit of 8-3, at first find the position of band collection 8 in the one-level table by 8 these values, secondly the secondary table of pointing to by the one-level table, find band collection unit 3 in the secondary table, the position that obtains to deposit this band collection unit is at disk 3, and side-play amount is 3, preferably reads disk 3 side-play amounts and be 3 band collection unit.
For m=4, the dynamic RAID expansion method of n=2, as shown in Figure 8, mobile band integrates the unit as 0-0,1-0,1-1,2-1,2-2,3-2 etc.
4. the dynamic disk capacity reduction method of RAID
Except the expansion method of the above-mentioned dynamic RAID of this paper, dynamically RAID can also be used in the capacity reducing aspect.The process of capacity reducing is exactly that m disk reduced n, wherein m>n.Capacity reducing has also comprised the movement of data block, but the condition of capacity reducing is that the number of the band collection unit of composition band collection must be less than or equal to m-n, otherwise the band collection unit that same band collection will occur belonging to is placed on the same disk, so just can not guarantee the reliability of the data.
The capacity reducing process as shown in Figure 9, Fig. 9 only simply draws the situation of 4 collection.In the capacity reducing process, mobile band collection unit just writes secondary table to the new disk number of band collection unit and disk bias internal amount at every turn, and the process of change secondary table is the same when ablation process and migration, until the data block on n disk Removes All.
The present invention not only is confined to above-mentioned embodiment, persons skilled in the art are according to content disclosed by the invention, can adopt other multiple embodiment to implement the present invention, such as the Data Migration mode of mentioning among the present invention, in order to reach the purpose that a plurality of disks can load balancing, in fact have the several data migration pattern.Therefore, every employing project organization of the present invention and thinking are done some simple designs that change or change, and all fall into the scope of protection of the invention.
Claims (1)
1. expansion method based on dynamic RAID system, establishing the original disk number is m, and newly-increased disk number is n, and newly-increased disk is numbered respectively 0 to n-1, and the method may further comprise the steps:
(1) be the band collection with dynamic RAID system divides;
(2) choose a band collection p, judge the p-q that is numbered that whether has a band collection unit among the band collection p, wherein p is band collection numbering, q=((p) mod(m+n)), if exist, then with this band collection cell moving to the newly-increased disk that is numbered r and keep the side-play amount of this band collection unit constant, and upgrade the address mapping table of this band collection unit, wherein r=((q) mod(n)); If do not exist, then do not do any operation; Described band collection unit refers to belong in each disk all stripe cell of same band collection; Described address mapping table is comprised of one-level table and secondary table, and the one-level table is band collection table, and each one-level table list item all points to a secondary table, and secondary table is band collection cell list, and each secondary table list item all records the position of a band collection unit;
(3) judge whether n equals 1, if change step (6) over to; Otherwise, make t=1, enter step (4);
(4) judge whether have band collection unit in the band collection (p+t) be numbered (p+t)-q, if exist, then with this band collection cell moving to the newly-increased disk that is numbered r and keep the side-play amount of this band collection unit constant, and upgrade the address mapping table of this band collection unit, wherein (p+t) is band collection numbering; If do not exist, then do not do any operation;
(5) judge whether t equals (n-1), if enter step (6); Otherwise, make t=t+1, change step (4) over to;
(6) according to the operation of step (2) to (5), all band collection of dividing in the traversal step (1).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110111802 CN102200892B (en) | 2011-04-29 | 2011-04-29 | Capacity expansion method based on dynamic redundant array of independent disks (RAID) system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110111802 CN102200892B (en) | 2011-04-29 | 2011-04-29 | Capacity expansion method based on dynamic redundant array of independent disks (RAID) system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102200892A CN102200892A (en) | 2011-09-28 |
CN102200892B true CN102200892B (en) | 2013-09-18 |
Family
ID=44661600
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 201110111802 Expired - Fee Related CN102200892B (en) | 2011-04-29 | 2011-04-29 | Capacity expansion method based on dynamic redundant array of independent disks (RAID) system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102200892B (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102999428A (en) * | 2012-11-01 | 2013-03-27 | 华中科技大学 | Four-stage addressing method for tile recording disk |
CN104182176B (en) * | 2013-05-24 | 2017-06-27 | 华中科技大学 | A kind of rapid volume-expanding method of RAID RAID5 |
CN106293526B (en) * | 2016-08-05 | 2019-04-12 | 上海交通大学 | A kind of expandable method and system of three disks fault-tolerant array |
CN107045427A (en) * | 2017-05-02 | 2017-08-15 | 郑州云海信息技术有限公司 | A kind of method of the online capacity extension of RAID card |
CN113127438B (en) * | 2019-12-30 | 2023-07-28 | 北京百度网讯科技有限公司 | Method, apparatus, server and medium for storing data |
CN111913919B (en) * | 2020-08-12 | 2024-08-06 | 湖北南邦创电科技有限公司 | File storage management method and storage medium |
CN112130768B (en) * | 2020-09-18 | 2023-01-10 | 苏州浪潮智能科技有限公司 | Disk array online capacity expansion method and device and computer readable storage medium |
CN113296702B (en) * | 2021-05-20 | 2023-01-10 | 山东云海国创云计算装备产业创新中心有限公司 | Disk array capacity expansion method, device, equipment and storage medium |
CN115309348B (en) * | 2022-10-11 | 2023-03-10 | 苏州浪潮智能科技有限公司 | Metadata management method and device, computer equipment and storage medium |
CN115437578B (en) * | 2022-11-04 | 2023-03-24 | 苏州浪潮智能科技有限公司 | Data migration method, device, equipment and medium of disk array |
CN115599313B (en) * | 2022-12-05 | 2023-03-17 | 苏州浪潮智能科技有限公司 | Disk array capacity expansion method, system, storage medium and equipment |
CN115840540B (en) * | 2023-02-23 | 2023-05-02 | 苏州浪潮智能科技有限公司 | RAID array capacity expansion method, device, equipment, RAID card and medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101251789A (en) * | 2008-03-28 | 2008-08-27 | 清华大学 | Cheap magnetic disc redundant array RAID5 roll rapid capacitance enlarging method |
CN101587425A (en) * | 2009-06-16 | 2009-11-25 | 杭州华三通信技术有限公司 | A kind of method and device that increases magnetic disc redundant array redundancy |
-
2011
- 2011-04-29 CN CN 201110111802 patent/CN102200892B/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101251789A (en) * | 2008-03-28 | 2008-08-27 | 清华大学 | Cheap magnetic disc redundant array RAID5 roll rapid capacitance enlarging method |
CN101587425A (en) * | 2009-06-16 | 2009-11-25 | 杭州华三通信技术有限公司 | A kind of method and device that increases magnetic disc redundant array redundancy |
Non-Patent Citations (2)
Title |
---|
"磁盘阵列扩容技术的研究与实现";武文智;《中国优秀硕士学位论文全文数据库(电子期刊)》;20100515;16-22 * |
武文智."磁盘阵列扩容技术的研究与实现".《中国优秀硕士学位论文全文数据库(电子期刊)》.2010,16-22. |
Also Published As
Publication number | Publication date |
---|---|
CN102200892A (en) | 2011-09-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102200892B (en) | Capacity expansion method based on dynamic redundant array of independent disks (RAID) system | |
CN102779096B (en) | Page, block and face-based three-dimensional flash memory address mapping method | |
CN101751406B (en) | Method and device for realizing column storage based relational database | |
CN101625627B (en) | Data read-in method, disc redundant array and controller thereof | |
CN110347336A (en) | A kind of key assignments storage system based on NVM with SSD mixing storage organization | |
US8639891B2 (en) | Method of operating data storage device and device thereof | |
CN101645043B (en) | Methods for reading and writing data and memory device | |
CN103838853B (en) | Mixed file system based on different storage media | |
US10997025B2 (en) | RAID-based globally resource-shared data storage system | |
CN102682108B (en) | Row and line mixed database storage method | |
CN107526550A (en) | A kind of two benches merging method based on log-structured merging tree | |
CN106095342A (en) | Watt recording disc array construction method and the system of a kind of dynamically changeable long strip | |
CN102184080B (en) | Curing band based data reading and writing method used after capacity expansion of RAID (Redundant Array of Independent Disk) system | |
CN107221351B (en) | Optimization processing method of error correcting code in solid-state disk system and application thereof | |
CN101923496A (en) | Method for achieving parallel reconstruction of data on RAID | |
CN113296702B (en) | Disk array capacity expansion method, device, equipment and storage medium | |
CN102999428A (en) | Four-stage addressing method for tile recording disk | |
CN102609358B (en) | Method for aggregating static data and solid-state disk thereof | |
CN102411632B (en) | Chain table-based memory database page type storage method | |
CN104182176A (en) | Rapid dilatation method for RAID 5 (redundant array of independent disks) | |
CN106354890A (en) | Implementation method of random access file system based on N-ary tree structure | |
CN104156432A (en) | File access method | |
CN106095330A (en) | A kind of storage method and apparatus of metadata | |
CN101470663B (en) | Method for processing address discontinuity in MTD design of NAND flash memory | |
US10877698B2 (en) | Semiconductor device for managing cold addresses of nonvolatile memory device |
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: 20130918 |
|
CF01 | Termination of patent right due to non-payment of annual fee |