CN104111894A - Method for improving multi-partition sequential read-write performance and system thereof - Google Patents
Method for improving multi-partition sequential read-write performance and system thereof Download PDFInfo
- Publication number
- CN104111894A CN104111894A CN201410340464.7A CN201410340464A CN104111894A CN 104111894 A CN104111894 A CN 104111894A CN 201410340464 A CN201410340464 A CN 201410340464A CN 104111894 A CN104111894 A CN 104111894A
- Authority
- CN
- China
- Prior art keywords
- solid state
- partition
- order
- hard disc
- state hard
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the technical field of storage and provides a method for improving multi-partition sequential read-write performance and a system thereof. The method comprises a step (A) of analyzing a master boot record of a solid state disk according to a file system partition protocol and establishing a partition information list of the solid state disk according to the master boot record; and a step (B) of performing separation and recombination on commands sent by a host end of the solid state disk according to the partition information list. Therefore, the method and the system reduce garbage block generation probability and improve the multi-partition sequential read-write performance of the solid state disk.
Description
Technical field
The present invention relates to technical field of memory, relate in particular to a kind of method and system thereof that promotes multi partition order readwrite performance.
Background technology
When SSD (Solid State Disk, solid state hard disc) is divided into after multiple subregions, these subregions carry out order read-write simultaneously, and after discovery long-play, performance sharply declines.Analyze from data stream, although each subregion is all order read-write, in the time that these read-write requests are converged in SSD, being construed to is random read-write, and random degree depends on the size of each read write command.
As shown in Figure 1, at present, the firmware of solid state hard disc is in the time processing multi partition read-write requests, and the command sequences just simply issuing according to main frame, processes successively.So no matter subregion is order read-write, or random read-write, is all random read-write (its degree depends on the size of single read write command, and single read write command is less, and random element is higher) for firmware.
As time goes on, the distribution of partition data on NAND (flash memory) is tending towards discrete, so just reduced the generation of executing garbage.When disk free space approaches while being finished, can cause a large amount of data-movings to produce abundant callable executing garbage, significantly improve and write amplification.And bring in from main frame, performance sharply declines, and order read-write does not reach the performance of expection.
Therefore, analyze from NAND, As time goes on, the data of each subregion more and more tend to discrete distribution, have so just caused frequently moving of data, write to amplify to become large, have affected serviceable life.
In summary, in actual use, obviously there is inconvenience and defect, so be necessary to be improved in existing multi partition order read-write technology.
Summary of the invention
For above-mentioned defect, the object of the present invention is to provide a kind of method and system thereof that promotes multi partition order readwrite performance, improve thus probability and the sequentially performance of read-write of solid state hard disc multi partition that executing garbage produces.
To achieve these goals, the invention provides a kind of method that promotes multi partition order readwrite performance, comprising:
A, according to file partition agreement, resolve the Main Boot Record of solid state hard disc, and the partition information list of setting up described solid state hard disc according to described Main Boot Record;
B, the order host side of described solid state hard disc being sent according to described partition information list separate and recombinate.
According to described method, described method also comprises:
C, described order is issued according to the maximum bandwidth of the flash memory of described solid state hard disc.
According to described method, in described step B, the order host side of described solid state hard disc being sent according to the subregion in described solid state hard disc separates, and the described order that belongs to same subregion is recombinated in identical logical block.
According to described method, at the subregion of described solid state hard disc during more than 4, described steps A also comprises: according to described file partition agreement, resolve Main Boot Record and the extended partition record of described solid state hard disc, and set up according to described Main Boot Record and extended partition record the partition information list that comprises described solid state hard disc extended partition.
According to above-mentioned arbitrary described method, described partition information list comprises: the initial LBA of each described subregion and LBA number;
Described order comprises order read command or the sequential write order that described host side is initiated.
In order to realize another goal of the invention of the present invention, the present invention also provides a kind of system that promotes multi partition order readwrite performance, comprising:
Set up module, for according to file partition agreement, resolve the Main Boot Record of solid state hard disc, and the partition information list of setting up described solid state hard disc according to described Main Boot Record;
Separating heavy pack module, separates and recombinates for the order host side of described solid state hard disc being sent according to described partition information list.
According to described system, described solid state hard disc also comprises:
Delivery module, for issuing described order according to the maximum bandwidth of the flash memory of described solid state hard disc.
According to described system, the order that described separating heavy pack module sends the host side of described solid state hard disc according to the subregion in described solid state hard disc separates, and the described order that belongs to same subregion is recombinated in identical logical block.
According to described system, at the subregion of described solid state hard disc during more than 4, the described module of setting up is according to described file partition agreement, resolve Main Boot Record and the extended partition record of described solid state hard disc, and set up according to described Main Boot Record and extended partition record the partition information list that comprises described solid state hard disc extended partition.
According to above-mentioned arbitrary described system, described partition information list comprises: the initial LBA of each described subregion and LBA number;
Described order comprises order read command or the sequential write order that described host side is initiated.
The present invention, by obtaining and analyze MBR and the EBR information of disk, sets up partition information table, comprises initial LBA and the LBA number of each subregion.Utilize the partition information table of having set up, the multi partition order read write command that host side is initiated separates.The order of each by stages is separated, and recombinates according to specific pattern, concentrates and distributes on NAND to reach maximum bandwidth and data.Therefore, in the present invention by the technical scheme that adopts subregion to separate and recombinate, can greatly improve the probability that executing garbage produces, be data-moving equally, also greatly reduced quantity, reduced and write amplification, extended the life-span of SSD.
Brief description of the drawings
Fig. 1 is host side order schematic flow sheet of the prior art;
Fig. 2 is the sequentially structural representation of the system of readwrite performance of lifting multi partition that first embodiment of the invention provides;
Fig. 3 is the sequentially structural representation of the system of readwrite performance of lifting multi partition that second embodiment of the invention provides;
Fig. 4 A is the mark schematic diagram of data block in Fig. 4 B～Figure 11;
Fig. 4 B is the variation schematic diagram that in prior art, order writes the flash memory of write order 1～6 solid state hard disc;
Fig. 5 is that prior art relaying is continued into order and caused without utilogic piece schematic diagram;
Fig. 6 is the variation schematic diagram of the flash memory of fill order solid state hard disc again after moving data in prior art;
Fig. 7 is data-moving and the upper data distribution schematic diagram of the rear NAND of fill order 7～9 in prior art;
Fig. 8 is the upper data distribution schematic diagram of NAND after fill order 7～9 data-movings in prior art;
Fig. 9 is the variation schematic diagram that in the embodiment of the present invention, order writes the flash memory of write order 1～6 solid state hard disc;
Figure 10 is that embodiment of the present invention relaying is continued the variation schematic diagram into the flash memory of write order 7～9 solid state hard discs;
Figure 11 is the variation schematic diagram of the flash memory of solid state hard disc after moving data in the embodiment of the present invention;
Figure 12 is the sequentially method flow diagram of readwrite performance of lifting multi partition that fourth embodiment of the invention provides.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Referring to Fig. 2, in the first embodiment of the present invention, provide a kind of system 100 that promotes multi partition order readwrite performance, comprising:
Set up module 10, for according to file partition agreement, resolve the Main Boot Record of solid state hard disc, and the partition information list of setting up solid state hard disc according to described Main Boot Record;
Separating heavy pack module 20, separates and recombinates for the order host side of solid state hard disc being sent according to described partition information list.
In this embodiment, set up module 10 according to the Main Boot Record of file partition protocol analysis solid state hard disc, then obtain the partition information list of solid state hard disc, as shown in table 1.In this table 1, described partition information list comprises: the initial LBA of each described subregion and LBA number.Then, the order that separating heavy pack module 20 sends the host side of described solid state hard disc according to described partition information list separates and recombinates, and concrete separates described order according to subregion.For example, table 1 comprised C two subregions of D, order is distinguished according to C, D district.And then according to different subregions, the order of each subregion is binned in together.The data of each subregion will can not tend to discrete distribution like this, prevent frequently moving of data.Wherein, described order comprises order read command or the sequential write order that described host side is initiated.
Referring to Fig. 3, in the second embodiment of the present invention, the system 100 that promotes multi partition order readwrite performance also comprises:
Delivery module 30, for issuing described order according to the maximum bandwidth of the flash memory of solid state hard disc.
In the third embodiment of the present invention, at the subregion of solid state hard disc during more than 4, the described module 10 of setting up is according to described file partition agreement, resolve Main Boot Record and the extended partition record of described solid state hard disc, and set up according to described Main Boot Record and extended partition record the partition information list that comprises described solid state hard disc extended partition.
In this embodiment, if the subregion of solid state hard disc, more than 4, needs other extended partition, therefore set up module 10 and will analyze Main Boot Record and extended partition record as shown in table 2.Then,, according to these two records, obtain partition information list.As table 2～table 4, taking DOS partition as example, there is first LBA (Logical Block Address in MBR (Master Boot Record, the i.e. Main Boot Record of hard disk), logical block addresses) inner, size is 512 bytes, and 000h～1BDh is guidance code, and 1BEh～1FDh is partition information, 16 byte representations for each partition information, by subregion agreement, parse disk MBR subregion, extended partition information, calculate the initial LBA information of each subregion.Can from LBA0, parse MBR, and then obtain successively subregion and extended partition, thereby set up partition information table.Secondly, order separates and restructuring.Owing to establishing partition information, be easy to realize so separate.For the distribution of partition data on NAND being concentrated relatively and reaching high bandwidth (under simple description, suppose that SSD has 4 CHANNEL, the each data volume of processing of each CHANNEL is 8K, owing to being independently between CHANNEL, can parallel processing, so maximum bandwidth is 4*8=32K, can be more complicated in reality, but principle is all to see maximum parallelism degree), between subregion, can take turns the pattern turning with reference to CPU time sheet, be fixed on certain CHANNEL and write, like this because each CHANNEL has request of data, first meets maximum parallelism degree, the second partition data is concentrated on certain CHANNEL.Time Slice Circular Scheduling is that one is the most ancient, the simplest, the most fair and use the widest algorithm. each process is assigned with a time period, is called its timeslice, and this process allows the time of operation.If process is also in operation in the time that timeslice finishes, CPU will be deprived of and distribute to another process.If process is blocked or finished before timeslice finishes, CPU switches at once.What scheduler program will do is exactly to safeguard a ready process list, and when process is finished after its timeslice, it is moved to the end of queue.
For example, as shown in table 1, SSD is divided into C and two subregions of D, and C district LPA (host side unit is LBA, can change into LPA with reference to LPA:LBA) interval is 64～85, LPA interval, D district is 86～101, the each Block of NAND comprises 8 Page, and 1 Page size is 1 LPA, and SSD has 2 CHANNEL, NAND provides 6 BLOCKS to write data, 2 BLOCKS moving data.
| Command number | Subregion | Initial LPA | LPA number |
| 1 | C | 64 | 8 |
| 2 | D | 86 | 8 |
| 3 | C | 66 | 6 |
| 4 | D | 90 | 8 |
| 5 | C | 64 | 12 |
| 6 | D | 90 | 6 |
| 7 | C | 66 | 6 |
| 8 | D | 86 | 10 |
| 9 | C | 64 | 8 |
| 10 | D | 96 | 6 |
Table 1
In one embodiment of the invention, preferably, the order that separating heavy pack module 20 sends the host side of described solid state hard disc according to the subregion in described solid state hard disc separates, and the described order that belongs to same subregion is recombinated in identical logical block.Be that command request separates according to subregion and recombinates, according to the partition information of having set up, isolate the order read write command of each subregion, recombinate simultaneously, ensure that maximum readwrite bandwidth distributes on NAND with data relative concentrated.
In the prior art, order is that order is carried out.When executing order 1～6, as shown in Figure 4 B, at this moment because be subject to NAND capacity limit, only remaining BLOCK#7 and BLOCK#8 can supply moving data to data, if continue to use BLOCK#7 and BLOCK#8, can cause without available BLOCK, as Fig. 5.Therefore carrying out subsequent commands, need to carry out data-moving to produce executing garbage, and then change into free block, as Fig. 6, so, BLOCK#1, BLOCK#2, BLOCK#3 and BLOCK#4 become executing garbage, through just wiping and can reusing, but increase like this expense that data block is moved, altogether moved 8 LPAs.When data block is in the time moving, SSD can not carry out host side order, shows in performance, is exactly that bandwidth declines.And when executing after order 7～9, the upper data of NAND distribute as Fig. 7.Equally, in order to ensure enough free blocks, must do data-moving, as shown in Figure 8.Altogether move 8 LPAs (LPA72,73,74,75,96,97,86 and 87), obtained free block BLOCK#5, BLOCK#6, BLOCK#7 and BLOCK#8.
And in an embodiment of the present invention, if separate and recombinate by adopting separating heavy pack module 20 to press subregion, improved the probability that produces executing garbage, reduce data-moving, as shown in Figure 9.BLOCK#1, and BLOCK#4 becomes executing garbage automatically.Continue fill order, when executing after order 7～9, the upper data of NAND distribute as Figure 10.Similarly need to carry out data-moving, as shown in figure 11, altogether move 6 LPAs (LPA64,65,72,73,86 and 87), obtain free block BLOCK#3, BLOCK#5 and BLOCK#6, add the executing garbage BLOCK#2 of automatic generation, is also 4 free blocks.Can find that the data moved concentrate than existing simultaneously because be these data as same subregion, in prior art, be to have mixed two subregions.
In above-mentioned multiple embodiment, the multiple modules that promote the system 100 of multi partition order readwrite performance can be the software units that is built in solid state hard disc, hardware cell or software and hardware combining unit.
Referring to Figure 12, the method for the lifting multi partition order readwrite performance providing in fourth embodiment of the invention, the system 100 of the lifting multi partition order readwrite performance that the above-mentioned multiple embodiment of the method employing provide realizes, and is described below:
In step S1501, set up module 10 according to file partition agreement, resolve the Main Boot Record of solid state hard disc, and the partition information list of setting up described solid state hard disc according to described Main Boot Record;
In step S1502, the order that separating heavy pack module 20 sends the host side of described solid state hard disc according to described partition information list separates and recombinates.
In this embodiment, set up module 10 according to file partition agreement, parse magnetic MBR subregion, set up partition information; Separating heavy pack module 20 is according to the partition information of having set up, and to host side, order separates, and does certain restructuring.So greatly improve the probability that piece produces, reduced moving of data, reduced and write amplification, therefore improved performance.
Preferably, in described step S1502, the order host side of described solid state hard disc being sent according to the subregion in described solid state hard disc separates, and the described order that belongs to same subregion is recombinated in identical logical block.
In the fifth embodiment of the present invention, described method also comprises:
Delivery module 30 issues described order according to the maximum bandwidth of described solid state hard disc.
In this embodiment, host side order through foundation module 10 subregions set with separating heavy pack module 20 according to subregion separate restructuring after, can be to be applicable to the maximum bandwidth form transmitting order to lower levels of SSD, and owing to being separated into subregion, become possibility so that the distribution of partition data on NAND concentrated.And after subregion restructuring, delivery module 30 is standard transmitting order to lower levels according to NAND maximum bandwidth.When As time goes on, this characteristic can improve the generation of executing garbage greatly, has reduced moving of data, has reduced and has write amplification, has also promoted performance simultaneously.
In the of the present invention the 6th implements, at the subregion of described solid state hard disc during more than 4, described step S1501 also comprises: according to described file partition agreement, resolve Main Boot Record and the extended partition record of described solid state hard disc, and set up according to described Main Boot Record and extended partition record the partition information list that comprises described solid state hard disc extended partition.Wherein, as shown in table 1, described partition information list comprises: the initial LBA of each described subregion and LBA number; Described order comprises order read command or the sequential write order that described host side is initiated.
In one embodiment of the invention, set up module 10 according to file system protocol, when computer starting and complete after self-inspection, first can find MBR (Main Boot Record) sector of disk and read leader record wherein, then give it by system control.And the information that MBR has comprised first order subregion, as table 2, taking DOS partition as example, MBR exists in first LBA, and size is 512 bytes, and 000h～1BDh is guidance code, 1BEh～1FDh is partition information, and therefore 16 byte representations for each partition information describe at most 4 subregions.If system will exceed 4 subregions, just need to set up extended partition, extended partition message structure, as shown in table 3.Extended partition size is also 512 bytes, and partition information leaves 1BEh～1DDh in, and each partition information is still with 16 byte representations.Partition table information structure.As shown in table 1, what only need care is last two parts information: initial LBA and LBA number.Visible by the partition table information in MBR and EBR, can be easy to set up partition information table, only need read the LPA at MBR and EBR place.The partition information table that 20 utilizations of separating heavy pack module have been set up, the multi partition that host side is initiated order read write command separates.The order of each by stages is separated, and recombinates according to specific pattern, concentrates and distributes on NAND to reach maximum bandwidth and data.On the basis of distinct above reason, carry out order read-write for multi partition simultaneously, be intended to by separating and recombinating, the command request of each subregion is separated, because each subregion itself is exactly order read-write, on NAND, deposits so the principle of also following order, thereby greatly reduce moving of data, reduce and write amplification, also just realized long-play property retention stable.In addition, order reads to depend on the mode of sequential write, therefore repeats no more.Wherein, table 2 is Main Boot Record structures of the solid state hard disc that provides of the embodiment of the present invention; Table 3 is extended partition leader record structures of the solid state hard disc that provides of the embodiment of the present invention; Table 4 is partition tables of the solid state hard disc that provides of the embodiment of the present invention; Be used for representing, in the time receiving user partition data, how to resolve and obtain the information of each subregion by table 2～table 4.
Standard MBR structure
Table 2
The general structure of extended partition
Table 3
MBR or EBR16-byte partitioned organization
Table 4
In sum, the present invention, by obtaining and analyze MBR and the EBR information of disk, sets up partition information table, comprises initial LBA and the LBA number of each subregion.Utilize the partition information table of having set up, the multi partition order read write command that host side is initiated separates.The order of each by stages is separated, and recombinates according to specific pattern, concentrates and distributes on NAND to reach maximum bandwidth and data.Therefore, in the present invention by the technical scheme that adopts subregion to separate and recombinate, can greatly improve the probability that executing garbage produces, be data-moving equally, also greatly reduced quantity, reduced and write amplification, extended the life-span of SSD.Being embodied in performance, is to have improved bandwidth.
Certainly; the present invention also can have other various embodiments; in the situation that not deviating from spirit of the present invention and essence thereof; those of ordinary skill in the art are when making according to the present invention various corresponding changes and distortion, but these corresponding changes and distortion all should belong to the protection domain of the appended claim of the present invention.
Claims (10)
1. a method that promotes multi partition order readwrite performance, is characterized in that, comprising:
A, according to file partition agreement, resolve the Main Boot Record of solid state hard disc, and the partition information list of setting up described solid state hard disc according to described Main Boot Record;
B, the order host side of described solid state hard disc being sent according to described partition information list separate and recombinate.
2. method according to claim 1, is characterized in that, described method also comprises:
C, described order is issued according to the maximum bandwidth of the flash memory of described solid state hard disc.
3. method according to claim 1, it is characterized in that, in described step B, the order host side of described solid state hard disc being sent according to the subregion in described solid state hard disc separates, and the described order that belongs to same subregion is recombinated in identical logical block.
4. method according to claim 1, it is characterized in that, at the subregion of described solid state hard disc during more than 4, described steps A also comprises: according to described file partition agreement, resolve Main Boot Record and the extended partition record of described solid state hard disc, and set up according to described Main Boot Record and extended partition record the partition information list that comprises described solid state hard disc extended partition.
5. according to the arbitrary described method of claim 1～4, it is characterized in that, described partition information list comprises: the initial LBA of each described subregion and LBA number;
Described order comprises order read command or the sequential write order that described host side is initiated.
6. a system that promotes multi partition order readwrite performance, is characterized in that, comprising:
Set up module, for according to file partition agreement, resolve the Main Boot Record of solid state hard disc, and the partition information list of setting up described solid state hard disc according to described Main Boot Record;
Separating heavy pack module, separates and recombinates for the order host side of described solid state hard disc being sent according to described partition information list.
7. system according to claim 6, is characterized in that, described system also comprises:
Delivery module, for issuing described order according to the maximum bandwidth of the flash memory of described solid state hard disc.
8. system according to claim 6, it is characterized in that, the order that described separating heavy pack module sends the host side of described solid state hard disc according to the subregion in described solid state hard disc separates, and the described order that belongs to same subregion is recombinated in identical logical block.
9. system according to claim 6, it is characterized in that, at the subregion of described solid state hard disc during more than 4, the described module of setting up is according to described file partition agreement, resolve Main Boot Record and the extended partition record of described solid state hard disc, and set up according to described Main Boot Record and extended partition record the partition information list that comprises described solid state hard disc extended partition.
10. according to the arbitrary described system of claim 6～9, it is characterized in that, described partition information list comprises: the initial LBA of each described subregion and LBA number;
Described order comprises order read command or the sequential write order that described host side is initiated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410340464.7A CN104111894A (en) | 2014-07-17 | 2014-07-17 | Method for improving multi-partition sequential read-write performance and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410340464.7A CN104111894A (en) | 2014-07-17 | 2014-07-17 | Method for improving multi-partition sequential read-write performance and system thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104111894A true CN104111894A (en) | 2014-10-22 |
Family
ID=51708692
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410340464.7A Pending CN104111894A (en) | 2014-07-17 | 2014-07-17 | Method for improving multi-partition sequential read-write performance and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104111894A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104639981A (en) * | 2015-02-05 | 2015-05-20 | 深圳创维－Rgb电子有限公司 | Television system starting method and television |
| CN107315544A (en) * | 2017-06-29 | 2017-11-03 | 郑州云海信息技术有限公司 | A kind of solid-state disk logical partition management method and device |
| CN107315546A (en) * | 2017-07-10 | 2017-11-03 | 郑州云海信息技术有限公司 | A kind of method and system of solid state hard disc low-level formatting |
| CN108701081A (en) * | 2016-01-11 | 2018-10-23 | 美光科技公司 | Device and method for the multiple subregions for accessing nonvolatile memory simultaneously |
| CN109271107A (en) * | 2018-09-01 | 2019-01-25 | 苏州韦科韬信息技术有限公司 | A method of promoting solid state hard disk sequence reading performance |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102830941A (en) * | 2012-06-15 | 2012-12-19 | 记忆科技(深圳)有限公司 | Solid-state hard disk driving method and storage system |
| CN103150128A (en) * | 2013-03-25 | 2013-06-12 | 中国人民解放军国防科学技术大学 | Implementation method of solid state drive (SSD) and disk-based reliable mixed storage system |
| US8738882B2 (en) * | 2011-06-03 | 2014-05-27 | Apple Inc. | Pre-organization of data |
-
2014
- 2014-07-17 CN CN201410340464.7A patent/CN104111894A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8738882B2 (en) * | 2011-06-03 | 2014-05-27 | Apple Inc. | Pre-organization of data |
| CN102830941A (en) * | 2012-06-15 | 2012-12-19 | 记忆科技(深圳)有限公司 | Solid-state hard disk driving method and storage system |
| CN103150128A (en) * | 2013-03-25 | 2013-06-12 | 中国人民解放军国防科学技术大学 | Implementation method of solid state drive (SSD) and disk-based reliable mixed storage system |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104639981A (en) * | 2015-02-05 | 2015-05-20 | 深圳创维－Rgb电子有限公司 | Television system starting method and television |
| CN108701081A (en) * | 2016-01-11 | 2018-10-23 | 美光科技公司 | Device and method for the multiple subregions for accessing nonvolatile memory simultaneously |
| US11354040B2 (en) | 2016-01-11 | 2022-06-07 | Micron Technology, Inc. | Apparatuses and methods for concurrently accessing multiple partitions of a non-volatile memory |
| CN108701081B (en) * | 2016-01-11 | 2022-06-21 | 美光科技公司 | Apparatus and method for simultaneously accessing multiple partitions of a non-volatile memory |
| US11768603B2 (en) | 2016-01-11 | 2023-09-26 | Micron Technology, Inc. | Apparatuses and methods for concurrently accessing multiple partitions of a non-volatile memory |
| CN107315544A (en) * | 2017-06-29 | 2017-11-03 | 郑州云海信息技术有限公司 | A kind of solid-state disk logical partition management method and device |
| CN107315546A (en) * | 2017-07-10 | 2017-11-03 | 郑州云海信息技术有限公司 | A kind of method and system of solid state hard disc low-level formatting |
| CN109271107A (en) * | 2018-09-01 | 2019-01-25 | 苏州韦科韬信息技术有限公司 | A method of promoting solid state hard disk sequence reading performance |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104111894A (en) | Method for improving multi-partition sequential read-write performance and system thereof | |
| US9864759B2 (en) | System and method for providing scatter/gather data processing in a middleware environment | |
| US8464003B2 (en) | Method and apparatus to manage object based tier | |
| CN104142853B (en) | Virtual machine storage resource dispositions method and device | |
| US10852966B1 (en) | System and method for creating mapped RAID group during expansion of extent pool | |
| CN103530388A (en) | Performance improving data processing method in cloud storage system | |
| US8819372B2 (en) | Preventing data loss during reboot and logical storage resource management device | |
| CN105518641A (en) | Method, device, and system for peer-to-peer data replication and method, device, and system for master node switching | |
| WO2016115920A1 (en) | Storage management method and apparatus and streaming media system | |
| CN108089825B (en) | Storage system based on distributed cluster | |
| US20150293719A1 (en) | Storage Space Processing Method and Apparatus, and Non-Volatile Computer Readable Storage Medium | |
| CN104731907A (en) | NOSQL-based data storage method | |
| CN103473266A (en) | Solid state disk and method for deleting repeating data thereof | |
| CN105468297A (en) | Quick synchronization method for master and slave device data in cloud storage system | |
| CN103268202A (en) | Capacity expanding method and capacity expanding equipment | |
| CN103116475B (en) | Method of automatic simplifying allocation expansion | |
| CN112783449A (en) | Data migration method and device | |
| JP2016500459A (en) | Monitoring record management method and device | |
| CN113377278A (en) | Solid state disk, garbage recycling and controlling method, equipment, system and storage medium | |
| US20230195315A1 (en) | Nonvolatile memory scheduling method, system and device, and readable storage medium | |
| US20160117107A1 (en) | High Performance Hadoop with New Generation Instances | |
| CN111552677B (en) | Quota management method, device, management node and storage medium | |
| JP2022016368A5 (en) | ||
| US8468303B2 (en) | Method and apparatus to allocate area to virtual volume based on object access type | |
| CN103064926B (en) | Data processing method and 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20141022 |
|
| RJ01 | Rejection of invention patent application after publication |