CN101788889B - Memory virtualization system and method - Google Patents
Memory virtualization system and method Download PDFInfo
- Publication number
- CN101788889B CN101788889B CN2010101177157A CN201010117715A CN101788889B CN 101788889 B CN101788889 B CN 101788889B CN 2010101177157 A CN2010101177157 A CN 2010101177157A CN 201010117715 A CN201010117715 A CN 201010117715A CN 101788889 B CN101788889 B CN 101788889B
- Authority
- CN
- China
- Prior art keywords
- magnetic disc
- logic magnetic
- physical disk
- module
- disk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000008569 process Effects 0.000 abstract description 14
- 238000013021 overheating Methods 0.000 abstract 1
- 238000013507 mapping Methods 0.000 description 28
- 238000005516 engineering process Methods 0.000 description 14
- 238000013500 data storage Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
Images
Landscapes
- Signal Processing For Digital Recording And Reproducing (AREA)
Abstract
The invention discloses a memory virtualization system and a method to balance IO load of physical disks. In the system, a striping module processes the physical disks by means of striping data to build a logic pond; a disk-building module builds a logic disk or a logic disk array on a logic memory pond; and a volume-building module builds a logic volume on the logic disk or the logic disk array. With the three layers of virtualization process, a read and write request of a customer is performed by being dispersed to the plurality of physical disks, and compared with the prior art that the read and write request of the customer is performed by being concentrated on one physical disk, the invention balances the IO load of the physical disks, effectively prevents some date of the physical disks from over heating, and improves the security and the performance of the memory system.
Description
Technical field
The present invention relates to storage virtualization technology, relate in particular to a kind of memory virtualization system and method.
Background technology
Mass storage system (MSS) is stored by classification, has solved data Heat range problem, but the storage system of classification storage is because special hardwares such as employing SSD cause storage system very expensive.How on the storage system of common no hardware specific demand, to solve the overheated problem of local data, just seem very important.
Usually storage system is solving on the IO problem of rear end, all is to adopt the virtual way of two-layer IO.Particularly, under certain memory controller, make up the RAID system of some dishes, construction logic volume in the RAID system carries out logical unit number (LUN) mapping and uses for the user again.Such as, selected 10 physical disks make up RAID5 in a storage system that 500 dishes are arranged, and set up logical volume then and shine upon this LUN on this RAID5.Because this LUN visit temperature is very high, 10 physical disk response IO bottlenecks cause access performance not high, and other 490 disks do not run up at this moment, the IO processing power of not contributing this to have.Like this,, be balanced in the storage system on other the physical disk, become the technical matters that needs to be resolved hurrily how with the load of the dish of this high temperature.
Current also have technology for balanced IO loading problem, carried out the thorough distribution of IO, but this technology and incompatible original tight coupling storage system, and this technology also still is a solution that two-layer IO is virtual simultaneously, can not make up RAID.
Summary of the invention
Technical matters to be solved by this invention is that a kind of memory virtualization system and method need be provided, with balance IO load of physical.
In order to solve the problems of the technologies described above, the present invention at first provides a kind of memory virtualization system, comprises that striped module, disk are set up module, volume is set up module and physical disk, wherein:
Described striped module is used for described physical disk is carried out the data stripe processing, sets up the logical storage pond, and sets up first addresses map relation between described logical storage pond and the described physical disk;
Described disk is set up module, be used for setting up logic magnetic disc or logic magnetic disc array on described logical storage pond, and described second addresses map of setting up between described logic magnetic disc or logic magnetic disc array and the described logical storage pond concerns;
Described volume is set up module, be used for setting up described logical volume on described logic magnetic disc or logic magnetic disc array, and described the 3rd addresses map of setting up between described logical volume and described logic magnetic disc or the logic magnetic disc array concerns;
Described physical disk is used for finishing the physics read-write of user to described physical disk according to mechanical read-write requests;
Wherein,
Described volume is set up module and also is used for first read-write requests of described physical disk being converted the user to described logical volume second reading write request, according to described the 3rd addresses map relation described second reading write request is sent to described disk and sets up module;
Described disk is set up module and also is used for receiving described second reading write request according to the 3rd addresses map relation, and according to described second addresses map relation described second reading write request is sent to described striped module;
Described striped module also is used for receiving described second reading write request according to second addresses map relation, convert described second reading write request to described mechanical read-write requests, and described mechanical read-write requests is sent to described physical disk according to described first addresses map relation.
Preferably, described striped module is used for when setting up described logical storage pond, adopt data break up processing with data scatter on a plurality of physical disks.
Preferably, described disk set up module be used for according to the fixed allocation strategy or distribution according to need strategy set up described logic magnetic disc;
Wherein,
Described fixed allocation strategy equals the storage space of described physical disk for the storage space of described logic magnetic disc or logic magnetic disc array;
Described distribution according to need strategy is the storage space of described logic magnetic disc or the logic magnetic disc array storage space greater than described physical disk.
Preferably, when described disk is set up module and is used for setting up described logic magnetic disc according to described distribution according to need strategy, be further used for pointing out the memory by using rate of described physical disk.
Preferably, described volume is set up module and be used for setting up the fixing fixed allocation logical volume of storage size on described logic magnetic disc or logic magnetic disc array, perhaps sets up the adjustable distribution according to need logical volume of storage size.
In order to solve the problems of the technologies described above, the present invention also provides a kind of Storage Virtualization method, comprising:
Described physical disk is carried out the data stripe processing, set up the logical storage pond, and set up first addresses map relation between described logical storage pond and the described physical disk;
On described logical storage pond, set up logic magnetic disc or logic magnetic disc array, and set up described second addresses map relation between described logic magnetic disc or logic magnetic disc array and the described logical storage pond;
On described logic magnetic disc or logic magnetic disc array, set up described logical volume, and set up described the 3rd addresses map relation between described logical volume and described logic magnetic disc or the logic magnetic disc array;
First read-write requests of described physical disk is converted the user to described logical volume second reading write request, convert described second reading write request to mechanical read-write requests according to described the 3rd addresses map relation and second addresses map relation, and described mechanical read-write requests is sent to described physical disk according to described first addresses map relation;
Described physical disk is finished the physics read-write of user to described physical disk according to described mechanical read-write requests.
Preferably, when setting up described logical storage pond, adopt data break up processing with data scatter on a plurality of physical disks.
Preferably, described logic magnetic disc is set up according to fixed allocation strategy or distribution according to need strategy;
Wherein,
Described fixed allocation strategy equals the storage space of described physical disk for the storage space of described logic magnetic disc or logic magnetic disc array;
Described distribution according to need strategy is the storage space of described logic magnetic disc or the logic magnetic disc array storage space greater than described physical disk.
Preferably, when setting up described logic magnetic disc, further point out the memory by using rate of described physical disk according to described distribution according to need strategy.
Preferably, on described logic magnetic disc or logic magnetic disc array, establish the fixing fixed allocation logical volume of storage size, perhaps establish the adjustable distribution according to need logical volume of storage size.
The present invention has realized three layers of virtualized memory virtualization system of read-write and method by the L 3 virtual processing.By the L 3 virtual processing user's a read-write requests is spread to and to carry out read-write operation on a plurality of physical disks, middle user read-write requests concentrates on the physical disk and carries out read-write operation compared to existing technology, the present invention has realized balance IO load of physical, effectively prevent the overheated of part physical disk data, improved the safety and the performance of storage system.
Other features and advantages of the present invention will be set forth in the following description, and, partly from instructions, become apparent, perhaps understand by implementing the present invention.Purpose of the present invention and other advantages can realize and obtain by specifically noted structure in instructions, claims and accompanying drawing.
Description of drawings
Accompanying drawing is used to provide further understanding of the present invention, and constitutes the part of instructions, is used from explanation the present invention with embodiments of the invention one, is not construed as limiting the invention.In the accompanying drawings:
Fig. 1 is the composition synoptic diagram of system embodiment of the present invention;
Fig. 2 is the schematic flow sheet of the inventive method embodiment.
Embodiment
Describe embodiments of the present invention in detail below with reference to drawings and Examples, how the application technology means solve technical matters to the present invention whereby, and the implementation procedure of reaching technique effect can fully understand and implements according to this.
Need to prove that if do not conflict, each feature among the embodiment of the invention and the embodiment can mutually combine, all within protection scope of the present invention.In addition, can in computer system, carry out in the step shown in the process flow diagram of accompanying drawing such as a set of computer-executable instructions, and, though there is shown logical order in flow process, but in some cases, can carry out step shown or that describe with the order that is different from herein.
Fig. 1 is the composition synoptic diagram of memory virtualization system embodiment of the present invention.As shown in Figure 1, this system embodiment comprises that mainly striped module 110, disk are set up module 120 and volume is set up module 130, wherein:
Disk is set up module 120, be used on the logical storage pond, setting up logic magnetic disc or logic magnetic disc array (RAID) (mainly constituting) by logic magnetic disc, and second addresses map of setting up between logic magnetic disc or logic magnetic disc array and the logical storage pond concerns formation logic magnetic disc layer;
Volume is set up module 130, be used for setting up logical volume on logic magnetic disc or RAID, and the 3rd addresses map of setting up between logical volume and logic magnetic disc or the RAID concerns formation logical volume layer.
Above-mentioned volume is set up module 130 after setting up logical volume, by LUN shine upon to the user be a physical disk, the user sets up file system on this physical disk, then correspondence is set up the corresponding document system on logical volume.When the user sends first read-write requests on file system, volume is set up module 130 and is converted the read-write requests on the file system to logical volume second reading write request, and be rolled onto the 3rd addresses map relation between logic magnetic disc or the RAID according to logic, the second reading write request is sent to disk set up logic magnetic disc or the logic magnetic disc array that module 120 is set up.
After above-mentioned disk is set up logic magnetic disc that module 120 set up or logic magnetic disc array and is received this second reading write request, concern to second addresses map between the logical storage pond according to logic magnetic disc or logic magnetic disc array, this second reading write request is sent to the logical storage pond that striped module 110 is set up.
The logical storage pond that above-mentioned striped module 110 is set up is after receiving the second reading write request that logic magnetic disc or logic magnetic disc array are sent, convert this second reading write request to mechanical read-write requests that the physical disk drives program can be discerned and handle, and concern according to first addresses map between logical storage pond and the physical disk, should the machinery read-write requests send to physical disk, finish the physics read-write of user physical disk by this physical disk.
The logical storage pond that above-mentioned striped module 110 is set up concerns with the addresses map between the actual physical disk, for the ground floor in the technical solution of the present invention L 3 virtualization virtual.Disk is set up logic magnetic disc that module 120 sets up or logic magnetic disc array to the mapping relations between the logical storage pond, for the second layer in the technical solution of the present invention L 3 virtualization virtual.Volume is set up logic that module 130 sets up and is rolled onto addresses map relation between logic magnetic disc or the RAID, is the L 3 virtualization in the technical solution of the present invention L 3 virtualization.
When the read-write requests of the big data quantity that the user is sent is handled, the present invention is by the L 3 virtual processing, respond a read-write requests simultaneously by a plurality of physical disks, a physical disk responds a read-write requests separately compared to existing technology, improve response speed and treatment effeciency, and realized the load balancing of read-write.
Above-mentioned striped module 110 is used in the process of setting up the logical storage pond, adopt data to break up processing data scatter (is being allowed data scatter to all physical disks) on a plurality of physical disks as far as possible, so handle and improved readwrite performance and load-balancing performance.In the data scatter processing procedure, can select linear mapping to scatter or the Hash mapping distribution.Below introduce the detailed process that linear mapping is scattered and Hash mapping is scattered respectively.
In the data scatter process, dissemination fineness need be set, the data granularity when this dissemination fineness is represented to store physical disk in the data scatter process.
In the linear mapping distribution process, data are broken up after the processing, the data after will breaing up according to this dissemination fineness store on each physical disk in turn.If the amount of capacity of each physical disk does not wait, when then the storage of part physical disk had been expired, follow-up storage was just carried out between all the other physical disks that are not filled with in turn.
Illustrate and understand the linear mapping distributing method by an object lesson.The capacity in logical storage pond equals the capacity sum of all physical disks, is 300G such as logical storage pond size, and it is dish A and the dish B of 100G that the physical store dish has 2 block sizes, and the dish C of two 50G sizes and dish D.If the dissemination fineness size is 64K, then the linear mapping distribution just can be understood as the data storage of 0-64K on the 0-64K of dish A, the data storage of 65K-128K is on the 0-64K of dish B, the data storage of 129K-192K is on the 0-64K of dish C, the data storage of 193-256K is on the 0-64K of dish D, then the data storage of 257-320K the dish A 65-128K on, and the like.After the data of each dish linear mapping 50G, remaining data from 201 to 300G only can store on dish A and the dish B dish, because dish C and dish D exhaust.
Linear mapping is very simple directly mapping distributing method, but when increasing physical disk, this distributing method can cause subsequent address to drop on the physical disk of increase, does not break up follow-up data, fully load balancing.The dish E that for example adds a 100G on the storage pool of aforementioned 300G again, then the addressing from these 100G data of 301 to 400G just all drops on the dish E.
It is much the same that Hash mapping distribution process is scattered process with linear mapping, also needs to specify the size of dissemination fineness, the data granularity size of just breaing up.Scattering different place with linear mapping mainly is that the Hash mapping distribution no longer is a linear relationship, but a kind of stochastic relation.
For convenience of description, by another example the Hash mapping distribution is described.Be the physical disk of 64G such as 3 capacity, be respectively dish X, dish Y and dish Z, the storage pool size then is 192G.Dissemination fineness still is set to 64K, and then every physical disk has 64G/64K=1024 storage block, and sequence number is labeled as 0-1023 successively, and the storage pool of 192G has 3072 storage blocks, and sequence number is labeled as 0-3071 successively.Pass through Hash mapping, the data of 0-64K are such as on the 0-64K that is stored in dish Y, the data of 65K-128K are such as on the 0-64K that is stored in dish X, the data storage of 129K-192K (data storage that also is first three granularity is coiled Z for dish Y-dish X-in proper order) on the 0-64K of dish Z then, the 65-128K that the data of 193-256K not necessarily can be stored in dish Y goes up (linear mapping is scattered and then can be stored on the dish Y), but may be stored on any of coiling among X, dish Y and the dish Z.
Hash mapping is scattered and is whole uniformly dispersing, can absolute granularity not scatter evenly as linear mapping is scattered.The embodiment of the invention used Hash mapping when carrying out data scatter is scattered to FNV Hash mapping of the prior art and is scattered, and it is that a kind of high speed Hash mapping commonly used is scattered that this FNV Hash mapping is scattered.
When above-mentioned disk is set up module 120 and is set up logic magnetic disc, can be according to fixed allocation strategy and distribution according to need strategy; Fixed allocation strategy wherein is commonly referred to the Regular allocation strategy in storage system, the storage space that is logic magnetic disc or logic magnetic disc array (also claims soft size, soft size) storage space that equals the actual physical disk (also claims hard size, hard size), distribution according to need strategy wherein is meant the storage space of the storage space of logic magnetic disc or logic magnetic disc array greater than physical disk.
In the fixed allocation strategy, the logical memory space that can use can't surpass the actual physical disk space.And in the distribution according to need strategy, how many storage spaces are the logical memory space that can use can in use, need just to distribute how many actual physical disk spaces greater than the actual physical disk space.
Disk is set up module 120 and when setting up logic magnetic disc, is further used for the memory by using rate of real-time prompting physical disk according to the distribution according to need strategy.Such as the logical memory space of occur to need using during greater than the actual physical disk space, disk is set up module 120 just can be by the mode of prompting physical disk memory by using rate, the appearance of the not enough situation of physical disk capacity is in time avoided in the space of notifying the keeper to increase physical disk.
In the foregoing description, the logic magnetic disc layer is virtual to be turned to the logic magnetic disc address and has addresses map to the address in logical storage pond.The logic magnetic disc layer is equivalent to two-layer virtualized physical disk, can on make up the RAID system.
Above-mentioned volume is set up the logical volume that module 130 is set up, and only belongs to a logic magnetic disc; And can set up a plurality of logical volumes on a logic magnetic disc.The foundation strategy of logical volume also comprises two kinds, a kind of is directly to set up the fixing fixed allocation logical volume of storage size on logic magnetic disc (the RAID system that perhaps many logic magnetic discs are formed), and another is exactly to set up the adjustable distribution according to need logical volume of storage size on logic magnetic disc; Need to prove that the storage size of distribution according to need logical volume must be not more than logic magnetic disc remaining space size (soft size).
Above-mentioned logical volume layer is virtual to turn to the addresses map relation of logical volume to logic magnetic disc (or the RAID system that is made of logic magnetic disc), above-mentioned disk is set up module 120 and is set up logic magnetic disc according to the distribution according to need strategy, according to the actual usage space decision of logical volume.
Fig. 2 is the schematic flow sheet of the inventive method embodiment.In conjunction with system embodiment shown in Figure 1, method embodiment shown in Figure 2 mainly comprises the steps:
Step S210 carries out the data stripe processing to physical disk, sets up the logical storage pond, and sets up first addresses map relation between logical storage pond and the physical disk;
Step S220 sets up logic magnetic disc or logic magnetic disc array on the logical storage pond, and sets up second addresses map relation between logic magnetic disc or logic magnetic disc array and the logical storage pond;
Step S230 sets up logical volume on logic magnetic disc or logic magnetic disc array, and sets up the 3rd addresses map relation between logical volume and logic magnetic disc or the logic magnetic disc array;
Step S240 converts the user to logical volume second reading write request to first read-write requests of physical disk;
Step S250 converts the second reading write request to mechanical read-write requests according to the 3rd addresses map relation and second addresses map relation, and according to first addresses map relation mechanical read-write requests is sent to physical disk;
Step S260, physical disk is finished the physics read-write of user to physical disk according to mechanical read-write requests.
In the process of setting up the logical storage pond, can adopt data to break up processing data scatter (is being allowed data scatter to all physical disks) on a plurality of physical disks as far as possible, so processing can improve readwrite performance and load-balancing performance.In the data scatter processing procedure, can select aforesaid linear mapping to scatter or the Hash mapping distribution.
Above-mentioned logic magnetic disc is set up according to fixed allocation strategy or distribution according to need strategy, wherein:
This fixed allocation strategy equals the storage space of this physical disk for the storage space of this logic magnetic disc or logic magnetic disc array;
This strategy of distributing according to need is the storage space of this logic magnetic disc or the logic magnetic disc array storage space greater than this physical disk.
When setting up this logic magnetic disc, further point out the memory by using rate of this physical disk according to this distribution according to need strategy.
On this logic magnetic disc or logic magnetic disc array, establish the fixing fixed allocation logical volume of storage size, perhaps establish the adjustable distribution according to need logical volume of storage size.
In an application example of the present invention, this storage system is made up of N memory controller, and each controller is the some physical disks of control down.By inventing a virtual store pond after the striping processing, this virtual store pond can be regarded a logic magnetic disc as, and to address mapping relation should be arranged, the data uniformly dispersing in the virtual store pond is on each physical disk between this logic magnetic disc and the physical disk.
The present invention adopts three layers of IO Intel Virtualization Technology, make the hot spot data problem in the storage system obtain good solution, the physical disk of total system is virtualized into a physical store pond, on this physical store pond, carry out the construction logic disk again for application demand, thereby improve readwrite performance, solution problem of load balancing to remove local data's problems of excessive heat.
Tightly coupled storage system is directly to make up RAID on physical disk, rolls up with the RAID construction logic.Logical volume of the present invention is to be structured on the logic magnetic disc, perhaps on the RAID that logic magnetic disc makes up, the read-write interface of logic magnetic disc and physical disk all is the standard interface of device drives level, that is to say that logical volume of the present invention can be structured in also that RAID goes up or physical disk on, realized that IO scatters the compatibility with the tight coupling storage system.
The present invention is when solving storage system IO load, and the RAID of compatible tight coupling storage system uses, and has proposed three layers of IO storage virtualization technology.This technology is broken two-layer Intel Virtualization Technology commonly used in the storage system, virtual by adding one deck map addresses again, IO load balancing when having realized the storage system visit, it is overheated can not to produce local data, the too frequent problem of local physical disk read-write, improved the processing power of whole storage system, and on logic magnetic disc, can construct the RAID system simultaneously, realized compatibility with original two-layer IO virtual system.And owing to adopted the distribution according to need strategy, further improved the utilization rate of physical disk, again storage system has been increased disk when needed.
Need to prove, can in computer system, carry out in the step shown in the process flow diagram of accompanying drawing such as a set of computer-executable instructions, and, though there is shown logical order in flow process, but in some cases, can carry out step shown or that describe with the order that is different from herein.In addition, those skilled in the art should be understood that, above-mentioned each module of the present invention or each step can realize with the general calculation device, they can concentrate on the single calculation element, perhaps be distributed on the network that a plurality of calculation element forms, alternatively, they can be realized with the executable program code of calculation element, thereby, they can be stored in the memory storage and carry out by calculation element, perhaps they are made into each integrated circuit modules respectively, perhaps a plurality of modules in them or step are made into the single integrated circuit module and realize.Like this, the present invention is not restricted to any specific hardware and software combination.
Though the disclosed embodiment of the present invention as above, the embodiment that described content just adopts for the ease of understanding the present invention is not in order to limit the present invention.Technician in any the technical field of the invention; under the prerequisite that does not break away from the disclosed spirit and scope of the present invention; can do any modification and variation what implement in form and on the details; but scope of patent protection of the present invention still must be as the criterion with the scope that appending claims was defined.
Claims (8)
1. a memory virtualization system is characterized in that, comprises that striped module, disk are set up module, volume is set up module and physical disk, wherein:
Described striped module is used for described physical disk is carried out the data stripe processing, sets up the logical storage pond, and sets up first addresses map relation between described logical storage pond and the described physical disk;
Described disk is set up module, be used for setting up logic magnetic disc or logic magnetic disc array on described logical storage pond, and second addresses map of setting up between described logic magnetic disc or logic magnetic disc array and the described logical storage pond concerns;
Described volume is set up module, be used for setting up logical volume on described logic magnetic disc or logic magnetic disc array, and the 3rd addresses map of setting up between described logical volume and described logic magnetic disc or the logic magnetic disc array concerns;
Described physical disk is used for finishing the physics read-write of user to described physical disk according to mechanical read-write requests;
Wherein,
Described volume is set up module and also is used for first read-write requests of described physical disk being converted the user to described logical volume second reading write request, according to described the 3rd addresses map relation described second reading write request is sent to described disk and sets up module;
Described disk is set up module and also is used for receiving described second reading write request according to described the 3rd addresses map relation, and according to described second addresses map relation described second reading write request is sent to described striped module;
Described striped module also is used for receiving described second reading write request according to described second addresses map relation, convert described second reading write request to described mechanical read-write requests, and described mechanical read-write requests is sent to described physical disk according to described first addresses map relation;
Wherein, described striped module is used for when setting up described logical storage pond, adopt data break up processing with data scatter on a plurality of physical disks.
2. system according to claim 1 is characterized in that:
Described disk is set up module and is used for setting up described logic magnetic disc or logic magnetic disc array according to fixed allocation strategy or distribution according to need strategy;
Wherein,
Described fixed allocation strategy equals the storage space of described physical disk for the storage space of described logic magnetic disc or logic magnetic disc array;
Described distribution according to need strategy is the storage space of described logic magnetic disc or the logic magnetic disc array storage space greater than described physical disk.
3. system according to claim 2 is characterized in that:
When described disk is set up module and is used for setting up described logic magnetic disc according to described distribution according to need strategy, be further used for pointing out the memory by using rate of described physical disk.
4. system according to claim 1 is characterized in that:
Described volume is set up module and be used for setting up the fixing fixed allocation logical volume of storage size on described logic magnetic disc or logic magnetic disc array, perhaps sets up the adjustable distribution according to need logical volume of storage size.
5. a Storage Virtualization method is characterized in that, comprising:
Physical disk is carried out the data stripe processing, set up the logical storage pond, and set up first addresses map relation between described logical storage pond and the described physical disk;
On described logical storage pond, set up logic magnetic disc or logic magnetic disc array, and set up second addresses map relation between described logic magnetic disc or logic magnetic disc array and the described logical storage pond;
On described logic magnetic disc or logic magnetic disc array, set up logical volume, and set up the 3rd addresses map relation between described logical volume and described logic magnetic disc or the logic magnetic disc array;
First read-write requests of described physical disk is converted the user to described logical volume second reading write request, convert described second reading write request to mechanical read-write requests according to described the 3rd addresses map relation and second addresses map relation, and described mechanical read-write requests is sent to described physical disk according to described first addresses map relation;
Described physical disk is finished the physics read-write of user to described physical disk according to described mechanical read-write requests;
Wherein, when setting up described logical storage pond, adopt data break up processing with data scatter on a plurality of physical disks.
6. method according to claim 5 is characterized in that:
Described logic magnetic disc or logic magnetic disc array are set up according to fixed allocation strategy or distribution according to need strategy;
Wherein,
Described fixed allocation strategy equals the storage space of described physical disk for the storage space of described logic magnetic disc or logic magnetic disc array;
Described distribution according to need strategy is the storage space of described logic magnetic disc or the logic magnetic disc array storage space greater than described physical disk.
7. method according to claim 6 is characterized in that:
When setting up described logic magnetic disc, further point out the memory by using rate of described physical disk according to described distribution according to need strategy.
8. method according to claim 5 is characterized in that:
On described logic magnetic disc or logic magnetic disc array, establish the fixing fixed allocation logical volume of storage size, perhaps establish the adjustable distribution according to need logical volume of storage size.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101177157A CN101788889B (en) | 2010-03-03 | 2010-03-03 | Memory virtualization system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101177157A CN101788889B (en) | 2010-03-03 | 2010-03-03 | Memory virtualization system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101788889A CN101788889A (en) | 2010-07-28 |
| CN101788889B true CN101788889B (en) | 2011-08-10 |
Family
ID=42532118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010101177157A Active CN101788889B (en) | 2010-03-03 | 2010-03-03 | Memory virtualization system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101788889B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9965184B2 (en) | 2015-10-19 | 2018-05-08 | International Business Machines Corporation | Multiple storage subpools of a virtual storage pool in a multiple processor environment |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102147713B (en) * | 2011-02-18 | 2013-06-12 | 杭州宏杉科技有限公司 | Method and device for managing network storage system |
| CN102609220A (en) * | 2012-01-19 | 2012-07-25 | 北京天地云箱科技有限公司 | Method and device for creating logical volumes |
| CN104731517A (en) * | 2013-12-19 | 2015-06-24 | 中国移动通信集团四川有限公司 | Method and device for allocating capacity of storage pool |
| CN104050014B (en) * | 2014-05-23 | 2017-12-29 | 上海爱数信息技术股份有限公司 | Efficient storage management method based on virtual platform |
| CN105808157A (en) * | 2014-12-31 | 2016-07-27 | 中兴通讯股份有限公司 | Storage architecture creating method, storage access method and storage system |
| CN107562367B (en) * | 2016-07-01 | 2021-04-02 | 阿里巴巴集团控股有限公司 | Method and device for reading and writing data based on software storage system |
| CN106712943A (en) * | 2017-01-20 | 2017-05-24 | 郑州云海信息技术有限公司 | Secure storage system |
| CN108733308B (en) | 2017-04-17 | 2021-06-22 | 伊姆西Ip控股有限责任公司 | Method and apparatus for managing disk pool |
| CN107256723A (en) * | 2017-05-31 | 2017-10-17 | 郑州云海信息技术有限公司 | A kind of method of testing and device for storing product |
| CN109656467B (en) * | 2017-10-11 | 2021-12-03 | 阿里巴巴集团控股有限公司 | Data transmission system of cloud network, data interaction method and device and electronic equipment |
| CN111522499B (en) * | 2019-02-01 | 2023-08-08 | 香港商希瑞科技股份有限公司 | Operation data reading device and reading method thereof |
| CN113553005B (en) * | 2021-07-06 | 2023-12-22 | 杭州宏杉科技股份有限公司 | Data read-write method, device and equipment for simplifying LUN |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1304961C (en) * | 2005-03-11 | 2007-03-14 | 清华大学 | Memory virtualized management method based on metadata server |
| JP5057656B2 (en) * | 2005-05-24 | 2012-10-24 | 株式会社日立製作所 | Storage system and storage system operation method |
-
2010
- 2010-03-03 CN CN2010101177157A patent/CN101788889B/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9965184B2 (en) | 2015-10-19 | 2018-05-08 | International Business Machines Corporation | Multiple storage subpools of a virtual storage pool in a multiple processor environment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101788889A (en) | 2010-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101788889B (en) | Memory virtualization system and method | |
| CN102449607B (en) | Storage system provided with a plurality of flash packages | |
| US9329804B2 (en) | System and method for micro-tiering in non-volatile memory | |
| TWI525433B (en) | Adaptive address mapping with dynamic runtime memory mapping selection | |
| JP2005128733A (en) | Logically partitionable storage device and storage device system | |
| US20140258615A1 (en) | Storage control apparatus and storage system comprising multiple storage control apparatuses | |
| CN103023963B (en) | A kind of method for cloud storage resources configuration optimization | |
| CN108733308B (en) | Method and apparatus for managing disk pool | |
| US20130318196A1 (en) | Storage system and storage control method for using storage area based on secondary storage as cache area | |
| US20090276588A1 (en) | Free space utilization in tiered storage systems | |
| CN104115109A (en) | Storage apparatus with a plurality of nonvolatile semiconductor storage units and control method thereof to place hot data in storage units with higher residual life and cold data in storage units with lower residual life | |
| CN106293521A (en) | A kind of mapping granule adaptive flash translation layer (FTL) management method | |
| CN101727293A (en) | Method, device and system for setting solid state disk (SSD) memory | |
| CN104536903B (en) | A kind of mixing storage method and system stored classifiedly by data attribute | |
| JP2012533099A (en) | Storage system, storage apparatus, and storage system optimization method for storage system | |
| US8489845B2 (en) | Storage system comprising multiple storage control apparatus | |
| US10860260B2 (en) | Method, apparatus and computer program product for managing storage system | |
| CN104731517A (en) | Method and device for allocating capacity of storage pool | |
| CN104866428A (en) | Data access method and data access device | |
| CN104461735A (en) | Method and device for distributing CPU resources in virtual scene | |
| CN103902475B (en) | Solid state disk concurrent access method and device based on queue management mechanism | |
| CN110770691A (en) | Hybrid data storage array | |
| CN102263818B (en) | Method for storing and reading file data, and apparatus thereof | |
| CN101645837A (en) | Method and device for realizing load balancing | |
| CN105808157A (en) | Storage architecture creating method, storage access method and storage system |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201111 Address after: 215100 No. 1 Guanpu Road, Guoxiang Street, Wuzhong Economic Development Zone, Suzhou City, Jiangsu Province Patentee after: SUZHOU LANGCHAO INTELLIGENT TECHNOLOGY Co.,Ltd. Address before: 100085 Beijing, Haidian District on the road to information on the ground floor, building 2-1, No. 1, C Patentee before: Inspur (Beijing) Electronic Information Industry Co.,Ltd. |