CN104156216B - A kind of memory management system and method towards cloud computing - Google Patents
A kind of memory management system and method towards cloud computing Download PDFInfo
- Publication number
- CN104156216B CN104156216B CN201410400258.0A CN201410400258A CN104156216B CN 104156216 B CN104156216 B CN 104156216B CN 201410400258 A CN201410400258 A CN 201410400258A CN 104156216 B CN104156216 B CN 104156216B
- Authority
- CN
- China
- Prior art keywords
- storage
- module
- memory
- access
- interface
- 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 25
- 238000003860 storage Methods 0.000 claims abstract description 169
- 230000006978 adaptation Effects 0.000 claims abstract description 61
- 238000007726 management method Methods 0.000 claims description 31
- 238000012545 processing Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 3
- 230000008878 coupling Effects 0.000 abstract description 4
- 238000010168 coupling process Methods 0.000 abstract description 4
- 238000005859 coupling reaction Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000014759 maintenance of location Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 239000003034 coal gas Substances 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- -1 electricity Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011800 void material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Abstract
A kind of memory management architecture system and method towards cloud computing that the present invention is provided, the system includes physical store cluster module, driving adaptation layer module, data access scheduler module, unified memory interface module and client;The system and method are packaged by storage class different in the physical store cluster module to rear end, and unified interface is provided to front end.The unification of interface is realized for the different drivings that different block device service facilities is provided.The scalability of cloud service platform can be greatly improved using this method, the high cohesion and lower coupling of cloud service platform framework is realized, the flexible scalability under cloud computing environment is realized, meets the structure of enterprise's private clound, public cloud.
Description
Technical field
The present invention relates to Computer Applied Technology, more particularly to it is a kind of towards the memory management system of cloud computing and side
Method.
Background technology
With the rise of cloud computing, deep change is just occurring for computer realm.China's cloud computing service market is in
Starting stage, cloud computing technology has been provided with certain development foundation with equipment.China's cloud computing service market in general scale compared with
It is small, but the pursuit impetus is obvious.Estimate according to Gartner, China in 2011 is in global about 90,000,000,000 dollars cloud computing service market
Portion is less than 3%, but year speedup reaches 40%, it is contemplated that following China will gradually contract with the external gap in terms of cloud computing
It is small.
Summarizing cloud computing has following feature:
(1) it is ultra-large:" cloud " has suitable scale, and Google's Google cloud computings have possessed more than 100 ten thousand services
Device, Amazon, IBM, Microsoft, Yahoo etc. " cloud " possesses hundreds of thousands platform server.Enterprise's private clound typically possesses on hundreds of
Thousand servers." cloud " can assign user unprecedented computing capability.
(2) virtualize:Cloud computing supports user to obtain application service at an arbitrary position, using various terminals.Asked
Resource comes from " cloud ", rather than fixed tangible entity.The somewhere in " cloud " is applied to run, but actually user need not
Solution, the particular location without worry application operation.Only need to a notebook or a mobile phone, it is possible to take by network
All for being engaged in realizing that we need, or even including task as supercomputing.
(3) high reliability:" cloud " has used the measures such as many copies of data are fault-tolerant, calculate node isomorphism is interchangeable to ensure clothes
The high reliability of business, it is reliable using local computer using cloud computing ratio.
(4) versatility:Cloud computing can construct Protean answer not for specific application under the support of " cloud "
With same " cloud " can support different application operations simultaneously.
(5) enhanced scalability:The scale of " cloud " can be with dynamic retractility, the need for meeting application and userbase growth.
(6) on-demand service:" cloud " is a huge resource pool, and you buy on demand;Cloud can be as running water, electricity, coal gas
Such charging.
(7) it is extremely cheap:Because the special fault-tolerant measure of " cloud " can constitute cloud using extremely cheap node, " cloud "
Automation centralized management make a large amount of enterprises without burden increasingly high data center management cost, the versatility of " cloud " makes
The utilization rate of resource is substantially improved than legacy system, therefore user can enjoy the low-cost advantage of " cloud " to the full, often only
Spend hundreds of dollars, several days time just the completing to be previously required to tens of thousands of dollars, time several months could complete of the task.
With the development of cloud computing, domestic extrapolated cloud management platform resource management, data processing, operation monitoring and
Quick development is all achieved in terms of interaction process in recent years.In terms of cloud management platform interaction process, although at present
The research on cloud management is still in the starting stage both at home and abroad, fails to be formed the solution of system, but major cloud computing factories
Business and open source community are all made that positive exploration to cloud management intellectualized technology from different perspectives.
Use for reference existing correlative study achievement both at home and abroad, with reference to the advantage of current cloud management platform, research and develop it is comprehensive, across flat
Platform, intellectuality, large-scale cloud management platform will have great economy and social value.Large-scale cloud resource intelligent can be supported
Management takes with scheduling, the management of extensive magnanimity cloud data intelligent and processing, cloud operation intelligent monitoring and safety guarantee and cloud
The cloud management platform of business intelligent interaction processing is one of main trend of cloud computing development.
In cloud management platform, under great elastic storage demand and performance requirement, calculate node is required to
Dynamic addition virtual volume.Block device storage that virtual machine is mainly supported by cloud management platform is realized.Block device has difference
Type, the storage of rear end can be DAS (the direct additional storages of Direct Attached Storage), NAS (Network
Attached Storage network attached storages), SAN (Storage Area Network storage area networks), object storage
Or distributed file system.Now single storage class is only supported in cloud management platform rear end, can not increasingly meet enterprise
The need for.
The content of the invention
In order to solve the above problems, the present invention proposes a kind of memory management framework towards cloud computing so that cloud
A variety of different storage classes are supported in management platform rear end, greatly improve the scalability of cloud service platform, realize cloud service
The high cohesion and lower coupling of platform architecture, realize the flexible scalability under cloud computing environment, meet enterprise's private clound, public affairs
There is the structure of cloud.
In order to achieve the above object, the present invention proposes system described in a kind of memory management system towards cloud computing
Including:Physical store cluster module, driving adaptation layer module, data access scheduler module, unified memory interface module.
The physical store cluster module, including different types of storage system, are supported by storage area network with communicating
The application net iSCSI and NFS NFS protocol that subsystem is built externally provide memory space.
The driving adaptation layer module, the interface access to different storage class agreements in the way of driving adaptation is united
One;The driving adaptation layer is respectively the inhomogeneity of offer iSCSI in the physical store cluster module and NFS protocol
The adaptation that the storage system of type enters line interface is accessed.
The data access scheduler module, is conducted interviews using message queue to data input/output I/O requests of access
Scheduling;The task of the message queue is handled, and suitable drive is selected in the driving adaptation layer module according to predetermined policy
Dynamic adapter nodes perform task, and a live-vertex of the data access scheduler module selection volume minimum number is created
Volume.
The unified memory interface module, externally provides the declarative state transfer Rest application programming interfaces of standard
API Access mode, is responsible for receiving and processing Rest requests, and the request is put into described in the data access scheduler module
In message queue.
Preferably, the different types of storage system in the physical store cluster module includes:It is directly additional to deposit
Store up DAS, it is the application net IP SAN that network attached storage NAS, storage area network and communication subsystem are built, distributed storage, right
As storage.
Preferably, it is described that the unified service of progress is accessed to the interface of different storage class agreements in the way of driving adaptation
Operate on memory node, manage memory space;There are a driving adaptation module, Duo Gesuo on each memory node
Memory node is stated to join together to constitute memory resource pool.
It is preferably, described that the interface of different storage class agreements is accessed before carrying out unification in the way of driving adaptation,
Each memory node generates a storage example in a registered manner, and network attached storage NAS driving equipment can be with
Multiple NAS physical storage devices are added, it is real to correspond to a storage after each described NAS physical storage devices registration
Example, the information record of the storage example is in the data access scheduler module.
Preferably, the data access scheduler module is visited the data I/O requests of access using message trunking queue
Ask that scheduling also includes:The storage information of the storage example of the driving adaptation layer module of registration is recorded, according in request content
Volume size, the speed of application select different storage examples to issue the order for creating volume;The storage information of the storage example, bag
Include the Protocol IP address interconnected between the type of storage, network, used and distributed storage size, storage speed size.
The invention also provides a kind of memory management method towards cloud computing, methods described includes:
Unified memory interface module is received in the Rest API Access modes of standard and handles Rest requests, and described will be asked
Ask and be put into the message queue of data access scheduler module.
The data access scheduler module is conducted interviews scheduling using message trunking queue to the data I/O Request of access;Place
Manage the task of the message queue, and according to predetermined policy selected in driving adaptation layer module suitable driving adapter nodes come
Execution task, the data access scheduler module selection rolls up a live-vertex of minimum number to create volume.
Interface access of the adaptation layer module to different storage class agreements in the way of driving adaptation is driven to be unified;Institute
State the different storage classes progress that driving adaptation layer is respectively the offers iSCSI and NFS protocol in physical store cluster module
The adaptation of interface is accessed.
The physical store cluster includes different types of storage system, supports to pass through storage area network and communication subsystem
The application net iSCSI and NFS NFS protocol of structure externally provide memory space.
Preferably, the different types of storage system in the physical store cluster module includes:DAS、NAS、IP
SAN, distributed storage, object storage.
Preferably, it is described that the unified service of progress is accessed to the interface of different storage class agreements in the way of driving adaptation
Operate on memory node, manage memory space;There are a driving adaptation module, Duo Gesuo on each memory node
Memory node is stated to join together to constitute memory resource pool.
It is preferably, described that the interface of different storage class agreements is accessed before carrying out unification in the way of driving adaptation,
Each memory node generates a storage example in a registered manner, and a NAS driving equipment can add multiple NAS things
Storage device is managed, a storage example can be corresponded to after each described NAS physical storage devices registration, the storage example
Information record is in the data access scheduler module.
Preferably, the data access scheduler module is conducted interviews using message trunking queue to the data I/O Request of access
Scheduling also includes:The storage information of the storage example of the driving adaptation layer module of registration is recorded, according to Shen in request content
Volume size, speed please selects different storage examples to issue the order for creating volume;The storage information of the storage example, including
The type of storage, IP address, used and distributed storage size, storage speed size.
Compared with prior art, what the present invention was provided is a kind of towards the memory management architecture system of cloud computing and side
Method, the system includes physical store cluster module, driving adaptation layer module, data access scheduler module, unified memory interface mould
Block and client;The system and method are packaged by storage class different in the physical store cluster module to rear end,
Unified interface is provided to front end.The storage class of rear end can be DAS, NAS, SAN, and object is stored or distributed document
System.The unification of interface is realized for the different drivings that different block device service facilities is provided.Can be big using this method
The big scalability for improving cloud service platform, realizes the high cohesion and lower coupling of cloud service platform framework, realizes in cloud meter
The flexible scalability under environment is calculated, the structure of enterprise's private clound, public cloud is met.
Brief description of the drawings
The accompanying drawing in the embodiment of the present invention is illustrated below, the accompanying drawing in embodiment is for entering one to the present invention
Step understands, is used to explain the present invention together with specification, does not constitute limiting the scope of the invention.
Memory management block architecture diagrams of the Fig. 1 towards cloud computing;
Memory management framework detailed structure views of the Fig. 2 towards cloud computing;
The embodiment flow chart of the process of Fig. 3 clients one virtual volume of application.
Embodiment
For the ease of the understanding of those skilled in the art, the invention will be further described below in conjunction with the accompanying drawings, not
It can be used for limiting the scope of the invention.
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually it is combined.
Describe embodiments of the present invention in detail below with reference to drawings and Examples, how the present invention is applied whereby
Technological means solves technical problem, and reaches the implementation process of technique effect and can fully understand and implement according to this.The application is real
Apply each feature be combineding with each other under the premise of not colliding in example and embodiment, protection scope of the present invention it
It is interior.
First, as shown in figure 1, the present invention proposes a kind of memory management system 01 towards cloud computing, the system
System includes:Physical store cluster module 05, driving adaptation layer module 04, data access scheduler module 03 and unified memory interface mould
Block 02.
The physical store cluster module 05, including different types of storage system, are supported by storage area network with leading to
The application net iSCSI and NFS NFS protocol that letter subsystem is built externally provide memory space.
Preferably, the different types of storage system in the physical store cluster module 05 includes:DAS
(Network Attached Storage network building-outs are deposited by (the direct additional storages of Direct Attached Storage), NAS
Storage), IP SAN (the application net that storage area network and communication subsystem are built), distributed storage, object storage.
The driving adaptation layer module 04, progress is accessed in the way of driving adaptation to the interface of different storage class agreements
It is unified.The driving adaptation layer is respectively the difference of offer iSCSI in the physical store cluster module and NFS protocol
The adaptation that the storage system of type enters line interface is accessed.
Preferably, it is described that the unified service of progress is accessed to the interface of different storage class agreements in the way of driving adaptation
Operate on memory node, manage memory space;There is a driving adaptation module 04 on each memory node, it is multiple
The memory node joins together to constitute memory resource pool.
It is preferably, described that the interface of different storage class agreements is accessed before carrying out unification in the way of driving adaptation,
Each memory node generates a storage example in a registered manner, and a NAS driving equipment can add multiple NAS things
Storage device is managed, a storage example can be corresponded to after each described NAS physical storage devices registration, the storage example
Information record is in the data access scheduler module 03.
The data access scheduler module 03, is visited data input/output I/O requests of access using message queue
Ask scheduling;The task of the message queue is handled, and selects suitable in the driving adaptation layer module 04 according to predetermined policy
Driving adapter nodes perform task, a live-vertex of the selection of the data access scheduler module 03 volume minimum number comes
Create volume.Preferably, the data access scheduler module 03 is visited the data I/O requests of access using message trunking queue
Ask that scheduling also includes:The storage information of the storage example of the driving adaptation layer module 04 of registration is recorded, according to request content
Volume size, the speed of middle application select different storage examples to issue the order for creating volume.
Preferably, the storage information of the storage example, including the type of storage, IP address, used and distributed storage
Space size, storage speed size.
The unified memory interface module 02, the declarative state transfer Rest application programmings for externally providing standard connect
Mouth API Access mode, is responsible for receiving and processing Rest requests, and ask to be put into the data access scheduler module 03 by described
In message queue.
Client is provided in the management function for localling create volume, inquiry volume, deleting volume, unloading volume, passes through the Rest
API Access mode and the unified memory interface module 02 of rear end carry out data transmission.
Present invention also offers a kind of memory management method towards cloud computing, methods described mainly includes following step
Suddenly:
Step S100, client are provided in the management function for localling create volume, inquiry volume, deleting volume, unloading volume, are passed through
Rest API Access mode and the unified memory interface module 02 of rear end carry out data transmission.
Step S101, unified memory interface module 02 are received in the Rest API Access modes of standard and handle Rest and asked
Ask, and the request is put into the message queue of data access scheduler module 03.
Step S102, the data access scheduler module 03 are carried out using message trunking queue to the data I/O Request of access
Access scheduling.
Preferably, it is contemplated that storage size, message queue is usually one than larger cluster message queue.
Preferably, the data access scheduler module 03 asks to carry out using message trunking queue to the data I/O of access
Access scheduling includes:The task of task queue is handled, and is appointed according to the suitable driving adapter nodes of predetermined policy selection to perform
Business, the selection of data access scheduler module 03 rolls up a live-vertex of minimum number to create volume.
Preferably, the data access scheduler module 03 asks to carry out using message trunking queue to the data I/O of access
Access scheduling also includes:The storage information of the storage example of the driving adaptation layer module 04 of registration is recorded, according in request content
Volume size, the speed of application select different storage examples to issue the order for creating volume.
Preferably, the storage information of the storage example, including the type of storage, IP address, used and distributed storage
Space size, storage speed size.
Step S103, driving adaptation layer module 04 are accessed the interface of different storage class agreements in the way of driving adaptation
Unified;The driving adaptation layer is respectively that the different storage classes for providing iSCSI and NFS protocol enter the adaptation of line interface
Access.
Preferably, the different types of storage system in the physical store cluster module 05 includes:DAS、NAS、
IP SAN, distributed storage, object storage.
Preferably, it is described that the unified service of progress is accessed to the interface of different storage class agreements in the way of driving adaptation
Operate on memory node, manage memory space;There are a driving adaptation module, Duo Gesuo on each memory node
Memory node is stated to join together to constitute memory resource pool.
It is preferably, described that the interface of different storage class agreements is accessed before carrying out unification in the way of driving adaptation,
Each memory node generates a storage example in a registered manner, and a NAS driving equipment can add multiple NAS things
Storage device is managed, a storage example can be corresponded to after each described NAS physical storage devices registration, the storage example
Information record is in the data access scheduler module.
Step S104, physical store cluster module 05 include different types of storage system, support to pass through storage area network
The application net iSCSI and NFS NFS protocol built with communication subsystem externally provides memory space.
A kind of memory management architecture system and method towards cloud computing that the present invention is provided, by different to rear end
Storage be packaged, to front end provide unified interface.The storage of rear end can be DAS, NAS, SAN, object storage or
Person's distributed file system.The unification of interface is realized in the driving different by providing of different block device service facilities.Utilize this
Method can greatly improve the scalability of cloud service platform, realize the high cohesion and lower coupling of cloud service platform framework, realize
Flexible scalability under cloud computing environment, meets the structure of enterprise's private clound, public cloud.
One embodiment of the present of invention, the process that user passes through one virtual volume of client application is described below.
Fig. 3 is flow chart according to an embodiment of the invention.
As shown in figure 3, cluster server deployment method comprises the steps.
Step S110, client application creates a virtual volume, and client initiates a request, and content includes virtual volume
Size, speed step, client ip etc..
Step S111, unified memory interface is transmitted the request to Rest interface modes.
Step S112, data access scheduler module suitably drives in layer, data dispatch module according to request selecting and recorded
The storage information that chartered driving adaptation layer stores example, these information include the type of storage, IP address, used
With distribution storage size, storage speed size.Data access scheduler module is according to the volume size of the content application of request, speed
The different storage example of degree selection issues the order for creating volume.
Step S113, driving adaptation layer calls the notice of settlement physical store cluster such as iSISC to go to create volume, herein according to choosing
The driving establishing layer difference selected goes to investigate corresponding storage order.
Step S114, physical store cluster creates real volume, and result is returned, and mainly passes through different physical stores
Order is realized.
Step S115, data access dispatch layer driving adaptation layer returning result, record information, essential record physical volume and void
Intend the corresponding relation of volume, mapped during for data access.
Step S116, unified memory interface returns to client by volume information is created.
Step S117, unified memory interface is transmitted the request to Rest interface modes.
In addition, the step of the flow of accompanying drawing 3 is illustrated can such as one group computer executable instructions computer
Performed in system.And, although logical order is shown in flow charts, but in some cases, can be with different from this
The order at place performs shown or described step.
One of ordinary skill in the art will appreciate that all or part of step of above-described embodiment can use computer journey
Sequence flow realizes that the computer program can be stored in a computer-readable recording medium, the computer program exists
(such as system, unit, device) is performed on corresponding hardware platform, upon execution, including the step of embodiment of the method it
One or its combination.
Alternatively, all or part of step of above-described embodiment can also use integrated circuit to realize, these steps can
To be fabricated to integrated circuit modules one by one respectively, or the multiple modules or step in them are fabricated to single integrated electricity
Road module is realized.So, the present invention is not restricted to any specific hardware and software combination.
Each device/functional module/functional unit in above-described embodiment can be realized using general computing device, it
Can concentrate on single computing device, can also be distributed on the network that multiple computing devices are constituted.
Each device/functional module/functional unit in above-described embodiment realized using in the form of software function module and as
Independent production marketing in use, can be stored in a computer read/write memory medium.Computer mentioned above
Read/write memory medium can be read-only storage, disk or CD etc..
It should be noted that embodiment described above be for only for ease of it will be understood by those skilled in the art that, and
It is not used in and limits the scope of the invention, on the premise of the inventive concept of the present invention is not departed from, those skilled in the art couple
Any obvious replacement and improvement that the present invention is made etc. is within protection scope of the present invention.
Claims (8)
1. a kind of memory management system towards cloud computing, it is characterised in that the system includes:Physical store cluster mould
Block, driving adaptation layer module, data access scheduler module, unified memory interface module;
The physical store cluster module, including different types of storage system, support to pass through storage area network and the subsystem that communicates
The application net iSCSI and NFS NFS protocol that system is built externally provide memory space;
The driving adaptation layer module, the interface access to different storage class agreements in the way of driving adaptation is unified;
The driving adaptation layer is respectively the different type of offer iSCSI in the physical store cluster module and NFS protocol
Storage system enter line interface adaptation access;
The data access scheduler module, the tune that conducts interviews is asked using message queue to data input/output I/O of access
Degree;The task of the message queue is handled, and suitable driving is selected in the driving adaptation layer module according to predetermined policy
Adapter nodes perform task, and a live-vertex of the data access scheduler module selection volume minimum number creates volume;
The unified memory interface module, externally provides the declarative state transfer Rest application programming interfaces API of standard
Access mode, is responsible for receiving and processing Rest requests, and ask to be put into described in the data access scheduler module to disappear by described
Cease in queue;
The data access scheduler module conducts interviews to dispatch using message queue to the data I/O requests of access also to be included:Note
The storage information of the storage example of the driving adaptation layer module of registration is recorded, according to the volume size, speed applied in request content
The different storage example of degree selection issues the order for creating volume;The storage information of the storage example, includes type, the net of storage
The Protocol IP address that is interconnected between network, used and distributed storage size, storage speed size.
2. the system as claimed in claim 1, it is characterised in that described different types of in the physical store cluster module
Storage system includes:The application that direct additional storage DAS, network attached storage NAS, storage area network and communication subsystem are built
Net IP SAN, distributed storage, object storage.
3. the system as claimed in claim 1, it is characterised in that it is described in the way of driving adaptation to different storage class agreements
Interface access and carry out unified service operation on memory node, manage memory space;Have one on each memory node
The individual driving adaptation layer module, multiple memory nodes join together to constitute memory resource pool.
4. system as claimed in claim 3, it is characterised in that it is described in the way of driving adaptation to different storage class agreements
Interface access carry out it is unified before, each memory node generates a storage example, a network in a registered manner
Additional storage NAS driving equipments add multiple NAS physical storage devices, each described NAS physical storage devices registration
A storage example can be corresponded to afterwards, and the information record of the storage example is in the data access scheduler module.
5. a kind of memory management method towards cloud computing, it is characterised in that methods described includes:
Unified memory interface module is received in the Rest API Access modes of standard and handles Rest requests, and the request is put
In the message queue for entering data access scheduler module;
The data access scheduler module is conducted interviews scheduling using message queue to the data I/O Request of access;Disappear described in processing
The task of queue is ceased, and selects suitable driving adapter nodes to appoint to perform in driving adaptation layer module according to predetermined policy
Business, the data access scheduler module selection rolls up a live-vertex of minimum number to create volume;
Interface access of the adaptation layer module to different storage class agreements in the way of driving adaptation is driven to be unified;It is described to drive
Dynamic adaptation layer is respectively that the different storage classes of offer iSCSI in physical store cluster module and NFS protocol enter line interface
Adaptation access;
The physical store cluster includes different types of storage system, supports to build with communication subsystem by storage area network
Application net iSCSI and NFS NFS protocol memory space is externally provided;
The data access scheduler module conducts interviews to dispatch using message queue to the data I/O Request of access also to be included:Record
The storage information of the storage example of the driving adaptation layer module of registration, according to the volume size, speed applied in request content
The different storage example of selection issues the order for creating volume;The storage information of the storage example, including the type of storage, IP
Location, used and distributed storage size, storage speed size.
6. method as claimed in claim 5, it is characterised in that described different types of in the physical store cluster module
Storage system includes:DAS, NAS, IP SAN, distributed storage, object storage.
7. method as claimed in claim 5, it is characterised in that it is described in the way of driving adaptation to different storage class agreements
Interface access and carry out unified service operation on memory node, manage memory space;Have one on each memory node
The individual driving adaptation layer module, multiple memory nodes join together to constitute memory resource pool.
8. method as claimed in claim 7, it is characterised in that it is described in the way of driving adaptation to different storage class agreements
Interface access carry out it is unified before, each memory node generates a storage example in a registered manner, and a NAS drives
Dynamic equipment adds multiple NAS physical storage devices, and a storage can be corresponded to after each described NAS physical storage devices registration
Example, the information record of the storage example is in the data access scheduler module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410400258.0A CN104156216B (en) | 2014-08-14 | 2014-08-14 | A kind of memory management system and method towards cloud computing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410400258.0A CN104156216B (en) | 2014-08-14 | 2014-08-14 | A kind of memory management system and method towards cloud computing |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104156216A CN104156216A (en) | 2014-11-19 |
CN104156216B true CN104156216B (en) | 2017-11-03 |
Family
ID=51881723
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410400258.0A Active CN104156216B (en) | 2014-08-14 | 2014-08-14 | A kind of memory management system and method towards cloud computing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104156216B (en) |
Families Citing this family (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104639658A (en) * | 2015-03-12 | 2015-05-20 | 浪潮集团有限公司 | Realization method for accessing object storage by file system mounting |
CN104902005A (en) * | 2015-04-13 | 2015-09-09 | 中国联合网络通信集团有限公司 | Method and system for resource scheduling in hybrid cloud, and private cloud |
WO2016172862A1 (en) * | 2015-04-28 | 2016-11-03 | 华为技术有限公司 | Memory management method, device and system |
CN105007311A (en) * | 2015-07-03 | 2015-10-28 | 叶秀兰 | System and method for resource management based on cloud platform and cloud computing |
US9697034B2 (en) * | 2015-08-07 | 2017-07-04 | Futurewei Technologies, Inc. | Offloading probabilistic computations in data analytics applications |
CN105183666B (en) * | 2015-09-14 | 2018-04-27 | 浪潮(北京)电子信息产业有限公司 | A kind of dispatch control method, apparatus and system |
CN105262816B (en) * | 2015-10-27 | 2019-02-19 | 北京天华星航科技有限公司 | Isomerization management method based on cloud management platform |
CN105573672B (en) * | 2015-12-11 | 2019-01-25 | 上海爱数信息技术股份有限公司 | A kind of virtualization storage method and system based on NFS |
CN106210046A (en) * | 2016-07-11 | 2016-12-07 | 浪潮(北京)电子信息产业有限公司 | A kind of volume based on Cinder is across cluster hanging method and system |
CN106534306A (en) * | 2016-11-14 | 2017-03-22 | 北京大学(天津滨海)新代信息技术研究院 | Extensible heterogeneous cloud platform adaptation method and system |
CN106814975A (en) * | 2017-01-20 | 2017-06-09 | 郑州云海信息技术有限公司 | A kind of memory management method and its system for polymorphic type storage device |
US10652361B2 (en) * | 2017-08-09 | 2020-05-12 | Open Text Corporation | Systems and methods for building and providing polymorphic REST services for heterogeneous repositories |
CN107886244A (en) * | 2017-11-10 | 2018-04-06 | 郑州云海信息技术有限公司 | A kind of business intelligence training system based on public cloud |
CN109947354A (en) * | 2017-12-20 | 2019-06-28 | 北京航天泰坦科技股份有限公司 | A kind of non-stop layer isomery space-time data storage system and method based on Agent |
CN108681578B (en) * | 2018-05-10 | 2021-07-16 | 腾讯科技(深圳)有限公司 | Business data storage method, device, server and storage medium |
CN109508323A (en) * | 2018-10-12 | 2019-03-22 | 量子云未来(北京)信息科技有限公司 | A kind of document storage system and file memory method |
CN109375879B (en) * | 2018-10-30 | 2021-11-19 | 福建易视科技有限公司 | Programmable distributed storage method and system |
CN109783253B (en) * | 2018-12-28 | 2023-02-14 | 南京唯实科技有限公司 | Distributed message data bus based on kafka |
CN110300178B (en) * | 2019-07-02 | 2021-07-20 | 迈普通信技术股份有限公司 | Communication equipment, service card, master control card, file access method and device |
CN110990113A (en) * | 2019-10-31 | 2020-04-10 | 北京浪潮数据技术有限公司 | Storage management method, system and related device in storage cluster |
CN111367503A (en) * | 2020-03-24 | 2020-07-03 | 中国建设银行股份有限公司 | Management method, device and equipment of multi-element storage and storage medium |
CN112291322A (en) * | 2020-10-22 | 2021-01-29 | 浪潮云信息技术股份公司 | Application management method and system based on IMS |
CN112925477A (en) * | 2021-01-28 | 2021-06-08 | 上海商汤智能科技有限公司 | Data processing method and device and storage system |
CN112965790B (en) * | 2021-03-29 | 2022-05-31 | 华云数据控股集团有限公司 | PXE protocol-based virtual machine starting method and electronic equipment |
CN113419687B (en) * | 2021-07-13 | 2022-08-12 | 广东电网有限责任公司 | Object storage method, system, equipment and storage medium |
CN113485650A (en) * | 2021-07-26 | 2021-10-08 | 南京鹏云网络科技有限公司 | Data arrangement system |
CN114513530B (en) * | 2022-04-19 | 2022-08-19 | 山东省计算中心(国家超级计算济南中心) | Cross-domain storage space bidirectional supply method and system |
CN114936255B (en) * | 2022-05-13 | 2023-05-02 | 北京透彻未来科技有限公司 | Universal distributed storage system access system |
CN114968100A (en) * | 2022-05-19 | 2022-08-30 | 威海海洋职业学院 | User data stable storage equipment based on cloud computing |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103607469A (en) * | 2013-11-28 | 2014-02-26 | 东莞中国科学院云计算产业技术创新与育成中心 | Cloud platform for achieving distributed isomerous data sharing and data sharing method thereof |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9712495B2 (en) * | 2011-05-03 | 2017-07-18 | International Business Machines Corporation | Methods and systems for selective encryption and secured extent quota management for storage servers in cloud computing |
-
2014
- 2014-08-14 CN CN201410400258.0A patent/CN104156216B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103607469A (en) * | 2013-11-28 | 2014-02-26 | 东莞中国科学院云计算产业技术创新与育成中心 | Cloud platform for achieving distributed isomerous data sharing and data sharing method thereof |
Non-Patent Citations (1)
Title |
---|
分布式文件系统在云存储环境下的若干问题研究;李书鹏;《中国优秀硕士学位论文全文数据库 信息科技辑》;20110915(第09期);第7-46页 * |
Also Published As
Publication number | Publication date |
---|---|
CN104156216A (en) | 2014-11-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104156216B (en) | A kind of memory management system and method towards cloud computing | |
US10554646B2 (en) | Providing domain-joined remote applications in a cloud environment | |
US10102027B2 (en) | Migrating virtual asset | |
US10152577B2 (en) | Cross tenant data access | |
US8621051B2 (en) | End-to end provisioning of storage clouds | |
CN104579740B (en) | For managing the method and system of virtual network interface | |
CN107426034A (en) | A kind of extensive container scheduling system and method based on cloud platform | |
CN106027593B (en) | For dynamically maintaining the method and system of data structure | |
CN107003906A (en) | The type of cloud computing technology part is to type analysis | |
US9459897B2 (en) | System and method for providing data analysis service in cloud environment | |
CN104135542B (en) | Isomery load balancing management system and method in a kind of cloud computing environment | |
US20110314164A1 (en) | Intelligent network storage planning within a clustered computing environment | |
CN108932588A (en) | A kind of the GROUP OF HYDROPOWER STATIONS Optimal Scheduling and method of front and back end separation | |
US9246920B2 (en) | Cloud resource cloning based on collaborative content | |
US20230009930A1 (en) | Continuous Liveness and Integrity of Applications During Migration | |
CN114846480A (en) | Quantum computing services supporting multiple quantum computing technologies | |
US11734092B2 (en) | Systems and methods for extending the data model of a monolithic database through a microservice for a multi-tenant platform | |
Gundu et al. | The Dynamic Computational Model and the New Era of Cloud Computation Using Microsoft Azure | |
US10581994B2 (en) | Facilitating communication between an origin machine and a target machine | |
CN111062682B (en) | Work order processing method and device | |
US20230083684A1 (en) | Visualizing api invocation flows in containerized environments | |
DeCusatis et al. | Cloud Computing Data Center Networking | |
Zhu | Cloud Factories | |
CN107800803A (en) | A kind of Novel cloud calculating main frame connection management implementation method |
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 |