CN103744624B - A kind of system architecture for realizing the data cached selectivity upgradings of storage system SSD - Google Patents
A kind of system architecture for realizing the data cached selectivity upgradings of storage system SSD Download PDFInfo
- Publication number
- CN103744624B CN103744624B CN201410011514.7A CN201410011514A CN103744624B CN 103744624 B CN103744624 B CN 103744624B CN 201410011514 A CN201410011514 A CN 201410011514A CN 103744624 B CN103744624 B CN 103744624B
- Authority
- CN
- China
- Prior art keywords
- data
- module
- upgrading
- data block
- ssd
- 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.)
- Active
Links
- 230000005012 migration Effects 0.000 claims description 11
- 238000013508 migration Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 238000000151 deposition Methods 0.000 claims 1
- 230000001174 ascending effect Effects 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
The invention discloses a kind of system architecture for realizing the data cached selectivity upgradings of storage system SSD, the system architecture is using the selective upgrade algorithm of data, in the queue that the data block hit for the first time is stored in entitled candidate's upgrade queue, the hit count that block is hit in each candidate's upgrade queue using following the trail of, when reaching upgrading limit value, during just the data block of hit can be cached from HDD hard disk caches to SSD, so as to realize delay buffer data, write operation is reduced, extends the target in SSD life-spans；Using the system architecture of the present invention, the data cached selectivity upgradings of SSD are ensure that, it is efficiently data cached, meet demand of the user to High Performance Cache and Memory System.
Description
Technical field
The present invention relates to a kind of system architecture of data for realizing storage system SSD cachings selectively upgrading, it is generally used for
In storage system, it is desirable to provide a kind of system architecture of selectivity upgrading data cached SSD.
Technical background
As the progress of today's society is, it is necessary to which the data message of processing is more and more, data volume is in explosive growth.This gives
Traditional storage system brings problems.Heritage storage system typically uses mechanical hard disk（HDD）, heritage storage system
Performance have become bottleneck.Nearly 2 years, SSD was that solid storage hard disk starts rise.On the one hand, SSD have in itself it is quick with
Machine access, low power consuming, ultralight ultra-thin, less trouble（On-mechanical part）The features such as.On the other hand, due to technology develop, SSD by
Gradually solve capacity small, the slow-footed problem of sequential access.Currently marketed newest SSD, single-deck capacity reaches several TB, PCIE
The SSD handling capacities of interface are more than 1GB/s, and IOPS reaches hundreds of thousands/s.SSD performances comprehensively exceed traditional mechanical hard disk, and its
The key indexs such as access speed, response time even more significantly exceed traditional mechanical hard disk.
But since SSD price will be significantly larger than HDD hard disks, therefore can meet current data using SSD as caching
The performance requirement of processing, can not improve storage system cost again.
SSD has some characteristics, and one is that SSD has life-span limitation, and SSD has the problem of erasable number of times is limited, write every time
It is once erasable that operation can all cause SSD to perform, therefore the quantity of write operation can directly affect erasable number of times, so as to influence SSD's
Life-span；Two be SSD capacity also far smaller than HDD hard disks, therefore SSD spaces are extremely precious.
The content of the invention
The technical problem to be solved in the present invention is：
The data of SSD cachings selectively upgrading urgent need is solved two problems, and one is to solve SSD life problems, how to be reduced
To SSD write operation, so as to extend SSD life-span；Two be the space for how effectively utilizing SSD, it is ensured that caching most worthy
Data.
By the system architecture of the storage system SSD data selectively upgradings cached, it can realize that SSD is data cached
Dynamic update, is greatly decreased SSD writing, increase write-in hit rate extends SSD life-span, efficiently empty using SSD storage
Between, meet the high performance demand of storage system.
The technical solution adopted in the present invention is：
A kind of system architecture for realizing the data cached selectivity upgradings of storage system SSD, the system architecture is supported in difference
Operating system, realize SSD it is data cached selectivity upgrading.The system architecture, will just using the selective upgrade algorithm of data
The data block of secondary hit is stored in the queue of entitled candidate's upgrade queue, is ordered using following the trail of in each candidate's upgrade queue
Middle piece of hit count, when reaching upgrading limit value, during just the data block of hit can be cached from HDD hard disk caches to SSD, from
And delay buffer data are realized, write operation is reduced, extends the target in SSD life-spans；
The system includes： 1）Data query cache module； 2）Candidate's upgrading data inquiry module； 3）Candidate's ascending series
According to processing module； 4）Upgrading limit value statistical module； 5）Data Migration module； 6）Hit count adjusting module, wherein：
Module 1）Data query cache module, is responsible for the inquiry in data cached queue and whether there is to data block, such as
Fruit is present, position of the direct returned data block in SSD cachings；If being not present, zero is returned；
Module 2）Candidate's upgrading data inquiry module, is responsible for whether the inquiry institute in candidate's upgrade queue deposits to data block
If it does, returning to the hit count for giving data block；If being not present, zero is returned；
Module 3）Candidate upgrade data processing module, be responsible for candidate upgrading give data block hit count increase and back into
The operation of team；
Module 4）Upgrading limit value statistical module, statistics upgrading limit value, calculates the institute cached in data cached queue first
There are the average hits of data block, calculation formula is the number of hit sum/data block of upgrading basic restrictions=data block, is risen
Level basic restrictions are the values of a dynamic change, as the foundation of data upgrading, in addition, upgrading limit value divides for reading and writing
There are not an acquiescence bonus values, read acquiescence bonus values and be less than write-in acquiescence bonus values, because SSD cachings are more suitable for
Read buffer.Final upgrading limit value can judge read-write situation, and its value gives tacit consent to the summation of bonus values for upgrading basic restrictions and read-write,
Only hit count is more than the data block of the value and can be just buffered into SSD cachings；
Module 5）Data Migration module, is responsible for data block being copied in SSD cachings from HDD；
Module 6）Hit count adjusting module, is responsible for the adjustment of the hit count of the data block of all hits, is a list
Only thread, specifies the time to carry out by user, generally selects business few time to carry out, because the hit meter of data block
Several can increase, therefore the module can dynamically reduce the hit meter of data block in data cached queue and candidate's upgrade queue
Number, reduced value is the average hits of all data blocks of candidate's upgrade queue, and data block hit count adjustment calculation formula is
Current hit count-reduced value, if institute's result of calculation is less than or equal to 0,1 is adjusted to by the hit count of the data block, it is ensured that
The reasonability of hit count.
The framework data selectively upgrading overall flow is as follows：
1st, when have read-write IO arrive, calling module 1）The corresponding data blocks of read-write IO are inquired about whether in SSD cachings, if
In the presence of position of the direct returned data block in SSD cachings；If being not present, zero is returned, illustrates that the data block is likely to require liter
Level is, it is necessary to calling module 2）；
2nd, module 2）It can be inquired about and whether there is in candidate's upgrade queue according to the corresponding data blocks of read-write IO, poll-final
After can calling module 3）Handled accordingly according to returning result；
3rd, module 3）According to module 2）Returning result, if returning to zero, miss mistake, this is counted before illustrating the data block
It is added to according to block in candidate's upgrade queue, and hit count is designated as 1；If returning to non-zero, illustrate that the data block was hit, return
Return hit count of the value for the data block, and calling module 4）Obtain upgrading limit value；
4th, module 3）Judge the data block whether the upgrading, if the hit count of the data block be less than upgrading limit value, will
The hit count of the data block adds joins the team again in the lump；If the hit count of the data block is more than or equal to upgrading limit value, should
The hit count of data block adds one, and calling module 5）；
5th, module 4）Upgrading basic restrictions now are calculated, and judge read-write IO type, if read operation, are then returned
The summation for basic restrictions and the reading acquiescence bonus values of upgrading, and calling module 3）；If write operation, then upgrading basic restrictions are returned
The summation of bonus values, and calling module 3 are given tacit consent to write-in）；
6th, module 5）Data Migration is completed, and the data block is deleted from candidate's upgrade queue, is added to data cached team
In row.
The real-time condition cached according to SSD dynamically adjusts upgrading limit value, realizes the data cached selectivity upgradings of SSD, from
And ensure the data buffer storage of storage system hottest point into SSD cachings, it is to avoid the waste in SSD spaces, it is efficient to be delayed using SSD
Deposit space.
Beneficial effects of the present invention are：
Using the system architecture of the present invention, the data cached selectivity upgradings of SSD are ensure that, it is efficiently data cached, it is full
Demand of the sufficient user to High Performance Cache and Memory System.Realize the data cached selectivity upgradings of SSD, the real-time feelings cached according to SSD
Condition dynamically adjusts upgrading limit value, delays data to be cached into SSD, SSD writing is greatly reduced, it is ensured that the data in caching
It is exactly the data of hottest point, extends SSD life-span, it is ensured that the efficient utilization of SSD spatial caches, it is overall to improve storage system
Energy.
Therefore this system architecture is used, the selectivity liter for realizing that storage system SSD is data cached that can efficiently, intelligent
Level.
Brief description of the drawings
Fig. 1 is data of the present invention selectively upgrading overall flow schematic diagram；
Fig. 2 is candidate's upgrading flow chart of data processing schematic diagram；
Fig. 3 is that hit count adjusts schematic flow sheet.
Embodiment
With reference to the accompanying drawings, by embodiment, the present invention is further described：
Embodiment of the present invention is simple, it is only necessary to the system module program of the present invention is installed in LINUX kernels.Root
According to the present invention, SSD caching systems can realize data cached selectivity upgrading automatically, when storage system needs caching number of upgrading
According to when, SSD caching systems can intelligence carry out data migration operation, by data from HDD be copied to SSD caching in, meet SSD delay
The selective upgrade feature of the data of deposit system.
A kind of system architecture for realizing the data cached selectivity upgradings of storage system SSD, the system architecture is supported in difference
Operating system, realize SSD it is data cached selectivity upgrading.The system architecture, will just using the selective upgrade algorithm of data
The data block of secondary hit is stored in the queue of entitled candidate's upgrade queue, is ordered using following the trail of in each candidate's upgrade queue
Middle piece of hit count, when reaching upgrading limit value, during just the data block of hit can be cached from HDD hard disk caches to SSD, from
And delay buffer data are realized, write operation is reduced, extends the target in SSD life-spans；
The system includes： 1）Data query cache module； 2）Candidate's upgrading data inquiry module； 3）Candidate's ascending series
According to processing module； 4）Upgrading limit value statistical module； 5）Data Migration module； 6）Hit count adjusting module, wherein：
Module 1）Data query cache module, is responsible for the inquiry in data cached queue and whether there is to data block, such as
Fruit is present, position of the direct returned data block in SSD cachings；If being not present, zero is returned；
Module 2）Candidate's upgrading data inquiry module, is responsible for whether the inquiry institute in candidate's upgrade queue deposits to data block
If it does, returning to the hit count for giving data block；If being not present, zero is returned；
Module 3）Candidate upgrade data processing module, be responsible for candidate upgrading give data block hit count increase and back into
The operation of team；
Module 4）Upgrading limit value statistical module, statistics upgrading limit value, calculates the institute cached in data cached queue first
There are the average hits of data block, calculation formula is the number of hit sum/data block of upgrading basic restrictions=data block, is risen
Level basic restrictions are the values of a dynamic change, as the foundation of data upgrading, in addition, upgrading limit value divides for reading and writing
There are not an acquiescence bonus values, read acquiescence bonus values and be less than write-in acquiescence bonus values, because SSD cachings are more suitable for
Read buffer.Final upgrading limit value can judge read-write situation, and its value gives tacit consent to the summation of bonus values for upgrading basic restrictions and read-write,
Only hit count is more than the data block of the value and can be just buffered into SSD cachings；
Module 5）Data Migration module, is responsible for data block being copied in SSD cachings from HDD；
Module 6）Hit count adjusting module, is responsible for the adjustment of the hit count of the data block of all hits, is a list
Only thread, specifies the time to carry out by user, generally selects business few time to carry out, because the hit meter of data block
Several can increase, therefore the module can dynamically reduce the hit meter of data block in data cached queue and candidate's upgrade queue
Number, reduced value is the average hits of all data blocks of candidate's upgrade queue, and data block hit count adjustment calculation formula is
Current hit count-reduced value, if institute's result of calculation is less than or equal to 0,1 is adjusted to by the hit count of the data block, it is ensured that
The reasonability of hit count.
As shown in figure 1, the framework data selectively upgrading overall flow is as follows：
1st, when have read-write IO arrive, calling module 1）The corresponding data blocks of read-write IO are inquired about whether in SSD cachings, if
In the presence of position of the direct returned data block in SSD cachings；If being not present, zero is returned, illustrates that the data block is likely to require liter
Level is, it is necessary to calling module 2）；
2nd, module 2）It can be inquired about and whether there is in candidate's upgrade queue according to the corresponding data blocks of read-write IO, poll-final
After can calling module 3）Handled accordingly according to returning result；
3rd, module 3）According to module 2）Returning result, if returning to zero, miss mistake, this is counted before illustrating the data block
It is added to according to block in candidate's upgrade queue, and hit count is designated as 1；If returning to non-zero, illustrate that the data block was hit, return
Return hit count of the value for the data block, and calling module 4）Obtain upgrading limit value；
4th, module 3）Judge the data block whether the upgrading, if the hit count of the data block be less than upgrading limit value, will
The hit count of the data block adds joins the team again in the lump；If the hit count of the data block is more than or equal to upgrading limit value, should
The hit count of data block adds one, and calling module 5）；
5th, module 4）Upgrading basic restrictions now are calculated, and judge read-write IO type, if read operation, are then returned
The summation for basic restrictions and the reading acquiescence bonus values of upgrading, and calling module 3）；If write operation, then upgrading basic restrictions are returned
The summation of bonus values, and calling module 3 are given tacit consent to write-in）；
6th, module 5）Data Migration is completed, and the data block is deleted from candidate's upgrade queue, is added to data cached team
In row.
The real-time condition cached according to SSD dynamically adjusts upgrading limit value, realizes the data cached selectivity upgradings of SSD, from
And ensure the data buffer storage of storage system hottest point into SSD cachings, it is to avoid the waste in SSD spaces, it is efficient to be delayed using SSD
Deposit space.
As shown in Fig. 2 candidate's upgrading flow chart of data processing is：
1st, module 3）According to module 2）Returning result, if returning to zero, miss mistake, this is counted before illustrating the data block
It is added to according to block in candidate's upgrade queue, and hit count is designated as 1；
If the 2, returning to non-zero, illustrate that the data block was hit, return value is the hit count of the data block, and calls mould
Block 4）Obtain upgrading limit value；
3rd, compare hits and upgrading limit value, if hits are less than or equal to upgrading limit value, say the life of the data block
Middle number adds joins the team again in the lump；
If the 4, hits are more than upgrading limit value, the hits of the data block are added one, and call Data Migration module
5）.
As shown in figure 3, hit count adjustment flow is：
1st, module 6）Obtain the average hits of all data blocks of candidate's upgrade queue；
2nd, take out data cached queue interior joint in turn, reduce the node hits and join the team again；
3rd, judge whether that all adjustment is finished, if not, repeating previous step；
4th, such as all adjustment is finished, then takes out candidate's upgrade queue interior joint in turn；
5th, decision node hit count subtracts whether average hit is less than 1, in this way, then makes the node hit count be equal to 1
And join the team again；
6th, if not, reducing the node hits and joining the team again；
7th, judge whether that all adjustment is finished, if not, return to step 4；
8th, such as all adjustment is finished, and flow is completed.
Claims (2)
1. a kind of system architecture for realizing the data cached selectivity upgradings of storage system SSD, it is characterised in that：The system architecture is adopted
With the selective upgrade algorithm of data, in the queue that the data block hit for the first time is stored in entitled candidate's upgrade queue, profit
The hit count that block is hit in each candidate's upgrade queue with following the trail of, just can be by the data block of hit when reaching upgrading limit value
In being cached from HDD hard disk caches to SSD, so as to realize delay buffer data, write operation is reduced, extends the target in SSD life-spans；
The system includes： 1）Data query cache module； 2）Candidate's upgrading data inquiry module； 3）At candidate's upgrading data
Manage module； 4）Upgrading limit value statistical module； 5）Data Migration module； 6）Hit count adjusting module, wherein：
Module 1）Data query cache module, is responsible for the inquiry in data cached queue and whether there is to data block, if deposited
In position of the direct returned data block in SSD cachings；If being not present, zero is returned；
Module 2）Candidate's upgrading data inquiry module, is responsible for the inquiry institute in candidate's upgrade queue and whether there is to data block, such as
Fruit is present, and returns to the hit count for giving data block；If being not present, zero is returned；
Module 3）Candidate's upgrading data processing module, the data block hit count for being responsible for upgrading candidate given by enquiry module increases
The operation that adduction is joined the team again；
Module 4）Upgrading limit value statistical module, statistics upgrading limit value, calculates all numbers cached in data cached queue first
According to the average hits of block, calculation formula is the number of hit sum/data block of upgrading basic restrictions=data block, base of upgrading
This limit value is the value of a dynamic change, the foundation upgraded as data, in addition, upgrading limit value has respectively for reading and writing
One acquiescence bonus values, reads acquiescence bonus values and is less than write-in acquiescence bonus values, final upgrading limit value can judge read-write situation,
Its value is upgrading basic restrictions and the summation of read-write acquiescence bonus values, and only hit count is more than or equal to the data block just meeting of the value
It is buffered into SSD cachings；
Module 5）Data Migration module, is responsible for data block being copied in SSD cachings from HDD；
Module 6）Hit count adjusting module, is responsible for the adjustment of the hit count of corresponding data block in candidate's upgrade queue,
It is a single thread, specifies the time to carry out by user, data block hit count adjustment calculation formula is current hit meter
Number-reduced value, reduced value is the average hits of all data blocks of candidate's upgrade queue；If institute's result of calculation is less than or equal to 0,
The hit count of the data block is adjusted to 1, it is ensured that the reasonability of hit count；
The framework data selectively upgrading overall flow is as follows：
A, when have read-write IO arrive, calling module 1）The corresponding data blocks of read-write IO are inquired about whether in SSD cachings, if depositing
In position of the direct returned data block in SSD cachings；If being not present, zero is returned, illustrates that the data block is likely to require liter
Level is, it is necessary to calling module 2）；
B, module 2）It can be inquired about and whether there is in candidate's upgrade queue according to the corresponding data blocks of read-write IO, meeting after poll-final
Calling module 3）Handled accordingly according to returning result；
C, module 3）According to module 2）Returning result, if returning to zero, miss mistake before illustrating the data block, by the data block
It is added in candidate's upgrade queue, and hit count is designated as 1；If returning to non-zero, illustrate that the data block was hit, return value
For the hit count of the data block, and calling module 4）Obtain upgrading limit value；
D, module 3）Judge the data block whether the upgrading, if the hit count of the data block be less than upgrading limit value, this is counted
Add according to the hit count of block and join the team again in the lump；If the hit count of the data block is more than or equal to upgrading limit value, by the data
The hit count of block adds one, and calling module 5）；
E, module 4）Upgrading basic restrictions now are calculated, and judge read-write IO type, if read operation, then upgrading are returned to
Basic restrictions and the summation for reading acquiescence bonus values, and calling module 3）；If write operation, then return to upgrading basic restrictions and write
Enter to give tacit consent to the summation of bonus values, and calling module 3）；
F, module 5）Data Migration is completed, and the data block is deleted from candidate's upgrade queue, is added into data cached queue.
2. a kind of system architecture for realizing the data cached selectivity upgradings of storage system SSD according to claim 1, it is special
Levy and be：The real-time condition cached according to SSD dynamically adjusts upgrading limit value, realizes the data cached selectivity upgradings of SSD.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410011514.7A CN103744624B (en) | 2014-01-10 | 2014-01-10 | A kind of system architecture for realizing the data cached selectivity upgradings of storage system SSD |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410011514.7A CN103744624B (en) | 2014-01-10 | 2014-01-10 | A kind of system architecture for realizing the data cached selectivity upgradings of storage system SSD |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103744624A CN103744624A (en) | 2014-04-23 |
| CN103744624B true CN103744624B (en) | 2017-09-22 |
Family
ID=50501645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410011514.7A Active CN103744624B (en) | 2014-01-10 | 2014-01-10 | A kind of system architecture for realizing the data cached selectivity upgradings of storage system SSD |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103744624B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10714159B2 (en) | 2018-05-09 | 2020-07-14 | Micron Technology, Inc. | Indication in memory system or sub-system of latency associated with performing an access command |
| US10942854B2 (en) | 2018-05-09 | 2021-03-09 | Micron Technology, Inc. | Prefetch management for memory |
| US10754578B2 (en) * | 2018-05-09 | 2020-08-25 | Micron Technology, Inc. | Memory buffer management and bypass |
| US11010092B2 (en) | 2018-05-09 | 2021-05-18 | Micron Technology, Inc. | Prefetch signaling in memory system or sub-system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102203749A (en) * | 2010-12-31 | 2011-09-28 | 华为技术有限公司 | Writing method and device of solid state driver under multi-level cache |
| KR20110115759A (en) * | 2010-04-16 | 2011-10-24 | 성균관대학교산학협력단 | Buffer cache managing method using ssd(solid state disk) extension buffer and apparatus for using ssd(solid state disk) as extension buffer |
| CN102760101A (en) * | 2012-05-22 | 2012-10-31 | 中国科学院计算技术研究所 | SSD-based (Solid State Disk) cache management method and system |
| CN102779017A (en) * | 2012-06-29 | 2012-11-14 | 华中科技大学 | Control method of data caching area in solid state disc |
| CN102799535A (en) * | 2012-06-29 | 2012-11-28 | 记忆科技(深圳)有限公司 | Solid-state disk and data processing method thereof |
| CN102831088A (en) * | 2012-07-27 | 2012-12-19 | 国家超级计算深圳中心(深圳云计算中心) | Data migration method and device based on mixing memory |
| CN103186350A (en) * | 2011-12-31 | 2013-07-03 | 北京快网科技有限公司 | Hybrid storage system and hot spot data block migration method |
| CN103257935A (en) * | 2013-04-19 | 2013-08-21 | 华中科技大学 | Cache management method and application thereof |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4988007B2 (en) * | 2010-05-13 | 2012-08-01 | 株式会社東芝 | Information processing apparatus and driver |
-
2014
- 2014-01-10 CN CN201410011514.7A patent/CN103744624B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110115759A (en) * | 2010-04-16 | 2011-10-24 | 성균관대학교산학협력단 | Buffer cache managing method using ssd(solid state disk) extension buffer and apparatus for using ssd(solid state disk) as extension buffer |
| CN102203749A (en) * | 2010-12-31 | 2011-09-28 | 华为技术有限公司 | Writing method and device of solid state driver under multi-level cache |
| CN103186350A (en) * | 2011-12-31 | 2013-07-03 | 北京快网科技有限公司 | Hybrid storage system and hot spot data block migration method |
| CN102760101A (en) * | 2012-05-22 | 2012-10-31 | 中国科学院计算技术研究所 | SSD-based (Solid State Disk) cache management method and system |
| CN102779017A (en) * | 2012-06-29 | 2012-11-14 | 华中科技大学 | Control method of data caching area in solid state disc |
| CN102799535A (en) * | 2012-06-29 | 2012-11-28 | 记忆科技(深圳)有限公司 | Solid-state disk and data processing method thereof |
| CN102831088A (en) * | 2012-07-27 | 2012-12-19 | 国家超级计算深圳中心(深圳云计算中心) | Data migration method and device based on mixing memory |
| CN103257935A (en) * | 2013-04-19 | 2013-08-21 | 华中科技大学 | Cache management method and application thereof |
Non-Patent Citations (2)
| Title |
|---|
| Improving Flash-based Disk Cache with Lazy Adaptive Replacement;Sai Huang 等;《Mass Storage Systems and Technologies(MSST),2013 IEEE 29th Symposium on》;20130510;第1-10页 * |
| 基于固态硬盘的云存储分布式缓存策略;李东阳 等;《计算机工程》;20130813;第39卷(第4期);第32-35页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103744624A (en) | 2014-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105117180B (en) | A kind of date storage method and device and solid state disk | |
| CN101673188B (en) | Data access method for solid state disk | |
| CN103744624B (en) | A kind of system architecture for realizing the data cached selectivity upgradings of storage system SSD | |
| CN103777905B (en) | Software-defined fusion storage method for solid-state disc | |
| US9274945B2 (en) | Processing unit reclaiming requests in a solid state memory device | |
| CN106095589B (en) | A kind of method, apparatus and system for distributing subregion | |
| CN108763103A (en) | A kind of EMS memory management process, device, system and computer readable storage medium | |
| CN108845768A (en) | A kind of date storage method, device, equipment and storage medium | |
| CN100383792C (en) | Buffer data base data organization method | |
| CN105095116A (en) | Cache replacing method, cache controller and processor | |
| CN110058932A (en) | A kind of storage method and storage system calculated for data flow driven | |
| CN105302840B (en) | A kind of buffer memory management method and equipment | |
| CN104571954B (en) | A kind of date storage method and device | |
| CN104536701A (en) | Realizing method and system for NVME protocol multi-command queues | |
| CN109582215A (en) | Execution method, hard disk and the storage medium of hard disk operation order | |
| CN105224474B (en) | The realization system of solid state hard disk flash translation layer (FTL) and the realization device of flash translation layer (FTL) | |
| US20190004968A1 (en) | Cache management method, storage system and computer program product | |
| CN104035925B (en) | Date storage method, device and storage system | |
| CN101373445A (en) | Method and apparatus for scheduling memory | |
| CN103345451A (en) | Data buffering method in multi-core processor | |
| CN101673192A (en) | Method for time-sequence data processing, device and system therefor | |
| CN104991743B (en) | Loss equalizing method applied to solid state hard disc resistance-variable storing device caching | |
| CN106527987A (en) | Non-DRAM SSD master control reliability improving system and method | |
| CN101221465A (en) | Data buffer zone implementing method for reducing hard disk power consumption | |
| US10275363B2 (en) | Cuckoo caching |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |