CN105278874A - Big data platform system and running method therefor - Google Patents
Big data platform system and running method therefor Download PDFInfo
- Publication number
- CN105278874A CN105278874A CN201510586856.6A CN201510586856A CN105278874A CN 105278874 A CN105278874 A CN 105278874A CN 201510586856 A CN201510586856 A CN 201510586856A CN 105278874 A CN105278874 A CN 105278874A
- Authority
- CN
- China
- Prior art keywords
- virtual machine
- request
- storage volume
- hard disk
- data platform
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a big data platform system capable of realizing separation of computation type applications and data, and a running method therefor, and belongs to the technical field of cloud computing and big data. The system can realize decoupling and separation of the applications and the data, and solve the problems of difficulty in migration from applications to data and multi-table associative computing of the data due to a strong dependence relationship between the applications and the data in an existing big data platform technology. The running method for the big data platform system comprises: virtually combining hard disks of a plurality of physical machines into a virtual hard disk; dividing the virtual hard disk into a plurality of storage volumes; and receiving a request and creating a virtual machine (which can be just all of a CPU and a memory of a complete machine, but still is the virtual machine) used for running the request, wherein the storage volumes are mounted for the virtual machine according to the demands of the request.
Description
Technical field
The invention belongs to cloud computing, large data technique field, be specifically related to a kind of large data platform system and operation method thereof, it can realize calculation type application and data separating.
Background technology
Along with the maturation of cloud computing and large data technique, traditional computing application pattern based on local computer is also at the trend development to clustering, high in the clouds, become the Main way of IT technical development, cluster is the main representative that the large data platform of representative is carried on IAAS (namely equipment serve) cloud especially especially in a distributed manner.
Shown in Fig. 1, large data platform mainly applies for resource with the form of physical machine to IAAS at present, as large data platform comprises multiple physical machine (server of entity), now by whole physical machine according to overall resource delivery, formed calculate and store tightly coupled node resource; And for Web application or function application, then apply for resource with virtual machine form to IAAS, specifically comprise and the resources (node resource) such as the hard disk of each physical machine, internal memory, CPU are divided into multiple part, when receiving a request (as function application, Web application etc.), " portion " hard disk, internal memory, CPU is then therefrom selected to form a virtual machine, to run this request.
Visible, according to above resource distribution mode, various application (request) and its run needed for data be all tight knot close, when computational resource (virtual machine, physical machine) is closed, application stops, and the data needed for application cannot be accessed by other computational resources (cannot realize the multilist association computing of data).That is, close-coupled and indivisible between data and application, but this close-coupled can cause many problems: first, when the migration will carrying out applying due to reasons such as system upgrade, equipment transfers, renewal, data needed for application are difficult to move thereupon, must be carried out the backup, synchronous etc. of data by special complicated approach, troublesome poeration, reliability is low; Secondly, when system occurs surprisingly delaying machine because of fault etc., the safety of application desired data is difficult to ensure (even if having data backup), causes the robustness of system low.
Summary of the invention
The present invention is directed to the strong dependence problem of application and data in existing large data platform technology, realize the migration of application to data and the problem of data multilist association computing, a kind of large data platform system and the operation method thereof that can realize calculation type application and data separating are provided.
The technical scheme that solution the technology of the present invention problem adopts is a kind of calculating and the large data platform system Resourse Distribute of data separating and operation method, and it comprises:
A virtual hard disk is integrated into by virtual for the hard disk of multiple physical machine;
Described virtual hard disk is divided into multiple storage volume;
Receiving one ask and create the virtual machine for running described request, is wherein storage volume described in described virtual machine carry according to the demand of described request.
Preferably, when creating the virtual machine for running described request, record the storage volume of described virtual machine carry as the storage volume corresponding with this request simultaneously; After reception one is asked and created the virtual machine for running described request, also comprise: stop described request, and close the virtual machine for running this request; Again receiving this request and create the virtual machine for running described request, is wherein the storage volume of described this request correspondence of virtual machine carry.
Preferably, described reception one is asked and the virtual machine created for running described request also comprises: be that described virtual machine distributes CPU and internal memory.
Further preferably, distribute CPU for described virtual machine and internal memory comprises: be that described virtual machine distributes CPU and internal memory, described CPU and interiorly save as the CPU of a physical machine and a part for internal memory; And, a part for the hard disk of the corresponding physical machine of the storage volume for described virtual machine carry.
Further preferably, described request is function application or Web application.
Further preferably, for described virtual machine distribution CPU and internal memory comprise: be that described virtual machine distributes CPU and internal memory, described CPU and interior whole CPU and the internal memory saving as a physical machine; And, whole hard disks of the corresponding physical machine of the storage volume for described virtual machine carry.
Further preferably, described request is large data platform request.
The technical scheme that solution the technology of the present invention problem adopts is a kind of large data platform system, and it comprises:
Multiple physical machine with hard disk;
Virtual integral unit, for being integrated into a virtual hard disk by virtual for the hard disk of multiple physical machine;
Cutting unit, for being divided into multiple storage volume by described virtual hard disk;
Virtual machine unit, asks for receiving one and creates the virtual machine for running described request, is wherein storage volume described in described virtual machine carry according to the demand of described request.
Preferably, described large data platform system also comprises: record cell, for recording the storage volume of the described virtual machine carry running each request, and it can be used as the storage volume corresponding with respective request.
Preferably, described large data platform system also comprises: allocation units, for distributing CPU and internal memory for described virtual machine.
In large data platform system of the present invention and operation method thereof, first the hard disk of multiple physical machine is integrated into a virtual hard disk, again each storage volume of this virtual hard disk is distributed to each virtual machine (can whole resources of a just in time corresponding physical machine, but still be virtual machine) use afterwards; Thus, wherein the hard disk of each physical machine (node) has all become a part for the storage resources shared, be separated with virtual machine, be convenient to unified utilization management, and then it also just achieves the decoupling zero (in other words loose coupling) of application and data, when moving when applying, upgrading, termination etc. will restart this application, as long as its original corresponding storage volume is distributed to its virtual machine again, the transfer realizing data that can be simple, reliable, complete, enhance the flexibility of system, ease of manageability and robustness, the multilist association computing of data can be realized.
Accompanying drawing explanation
Fig. 1 is the schematic diagram of existing large data platform system operation method;
Fig. 2 is the process flow diagram of a kind of large data platform system operation method of embodiments of the invention;
Fig. 3 is the schematic diagram of a kind of large data platform system operation method of embodiments of the invention;
Fig. 4 is the composition schematic block diagram of a kind of large data platform system of embodiments of the invention.
Embodiment
For making those skilled in the art understand technical scheme of the present invention better, below in conjunction with the drawings and specific embodiments, the present invention is described in further detail.
Embodiment 1:
The present embodiment provides a kind of large data platform system operation method, and it comprises:
S101, be integrated into a virtual hard disk by virtual for the hard disk of multiple physical machine.
S102, described virtual hard disk is divided into multiple storage volume.
S103, receiving one and ask and create the virtual machine for running described request, is wherein storage volume described in described virtual machine carry according to the demand of described request.
In the large data platform system operation method of the present embodiment, first the hard disk of multiple physical machine is integrated into a virtual hard disk, more each storage volume of this virtual hard disk is distributed to each virtual machine afterwards and use; Thus, wherein the hard disk of each physical machine (node) has all become a part for the storage resources shared, be separated with virtual machine, be convenient to unified utilization management, and then it also just achieves the decoupling zero (in other words loose coupling) of application and data, when moving when applying, upgrading, termination etc. will restart this application, as long as its original corresponding storage volume is distributed to its virtual machine again, the transfer realizing data that can be simple, reliable, complete, enhance the flexibility of system, ease of manageability and robustness, the multilist association computing of data can be realized.
Embodiment 2:
As shown in Figures 2 to 4, the present embodiment provides a kind of large data platform system operation method, and it comprises the following steps:
S201, be integrated into a virtual hard disk by virtual for the hard disk of multiple physical machine.
That is, large data platform system comprises multiple physical machine (server of entity), each physical machine has oneself the hardware resource (node resource) such as hard disk, CPU, internal memory, and this step is by existing virtualization storage administrative skill, the hard disk of whole physical machine is integrated into a large virtual hard disk, to carry out holistic management.
Such as, the Cinder module of the OpenStack cloud management platform of available US National Aeronautics and Space Administration exploitation, a virtual hard disk is integrated into by virtual for the hard disk in multiple X86 server in SDS (software definition storage) mode, thus make the virtual storage volume that whole storage resources becomes shared, and bring unified management in the container (resource pool) of Cinder-Volume service into, served the scheduling and controlling realized storage volume by Cinder-Scheduler, and the calling interface of storage volume is provided by Cinder-Api service.
S202, virtual hard disk is divided into multiple storage volume.
That is, by the storage management technique of routine, virtual hard disk is divided into multiple storage volume (Lun), each storage volume is distributed to each virtual machine.
Wherein, the concrete dividing mode of storage volume can the demand of request on the estimation determine.Such as, wherein the hard disk of part server can be divided into multiple storage volume, i.e. a hard disk part for the corresponding server of each storage volume; Or, also can have the hard disk of part server separately as a storage volume, i.e. the hard disk of the corresponding server of each storage volume; Again or, also can be the corresponding storage volume of hard disk of multiple server.
Below in advance by virtual for the hard disk of all physical machine and the technology of bundling at least has following advantage: first, the hard disk of each physical machine is being placed under unified management all the time, the most convenient, reliable to the management of storage space, efficiency is high.Secondly, in the process of segmentation storage volume, storage space the most reasonably can be distributed demand on the estimation: such as, the corresponding multiple hard disk of a storage volume can be had, thus meet the demand to the very large particular request of memory space requirements; For another example, when a storage volume can take most space of a hard disk, then available less hard disk integral is as this storage volume, or by the sub-fraction of more big hard disk as this storage volume, thus avoid the remaining storage space cannot applied on a small quantity in a hard disk, realize making full use of whole storage space.Finally, the segmentation of storage volume completes in advance, therefore only with the simple operations carrying out carry storage volume in system operation, the operand needed for it is little, and speed is fast.
S203, receive one ask and create the virtual machine for running request, wherein according to ask demand be virtual machine carry storage volume.
That is, when system acceptance is to request (as run application, building database etc.) from user, then for this request creates virtual machine, and according to the situation of asking, for its carry (mount) one or more storage volume is as its hard disk.
Concrete, the demand of system first analytical applications, dispatched by the Nova-Scheduler service of the Nova module of Openstack cloud management platform afterwards, call Cinder-Api service and find storage volume up to specification and calling interface thereof in the virtual resource pond of SDS management, and served by this storage volume carry on a virtual machine by Nova-Volume.
Preferably, also comprise in this step: the storage volume (as recorded the address of calling interface) simultaneously recording virtual machine carry as the storage volume corresponding with this request, with as the foundation redistributing storage volume.
Preferably, this step also comprises: for virtual machine distributes CPU and internal memory.
That is, also the CPU of each physical machine and internal memory also can be distributed to virtual machine in this step, thus the full virtual machine of payment " storage volume+CPU+ internal memory " is to run corresponding request.
Concrete, when there being request application virtual machine, its work order is accepted by the portal application of Openstack cloud management platform, and descendingly give Nova module, and the resource in Nova-Scheduler service search NovaDatabase, CPU in each physical machine and internal memory are carried out virtual (segmentation) by Vcenter according to the specification of virtual machine in the mirror image of Nova-Glance service and NovaKeystone, and by virtualized CPU and Memory Allocation to virtual machine.
Wherein, according to the difference of request, above carry storage volume is divided into following two kinds of situations with the operation of distribution CPU, internal memory:
Situation a: when above request is for function application or Web application, more than for virtual machine distribution CPU and internal memory comprise: be virtual machine distribution CPU and internal memory, CPU and interiorly save as the CPU of a physical machine and a part for internal memory; And, a part for the hard disk of the corresponding physical machine of the storage volume for virtual machine carry.
That is, as shown in Figure 3, when to be applied as memory space requirements be not very large general upper layer application (function application or Web application), then according to existing method, the CPU of a physical machine and internal memory are split, and gives this virtual machine by wherein a part of CPU and Memory Allocation; Meanwhile, carry is also (but itself and non-immediate split by the hard disk of physical machine obtain) of a part of storage space of the hard disk of a corresponding physical machine to the storage volume of this virtual machine.Should be appreciated that the CPU (and internal memory) of hard disk now corresponding to storage volume and virtual machine, may not from Same Physical machine.
Situation b: when asking as large data platform request (back end or database as Hadoop), for virtual machine distributes CPU and internal memory comprises then: be that virtual machine distributes CPU and internal memory, CPU and interior whole CPU and the internal memory saving as a physical machine; And, whole hard disks of the corresponding physical machine of the storage volume for virtual machine carry.
That is, as shown in Figure 3, when request needs very large storage space, the present embodiment is not that it distributes the physical machine of an entity as prior art.But by the Nova module of Openstack cloud management platform according to the specification requirement in NovaKeystone, by CPU whole for physical machine and internal memory (as the CPU of 16C, the internal memory of 256GB) all distribute to this request, and select a storage volume to carry out carry in the virtual resource pond of SDS management, and whole hard disks of the corresponding physical machine of this storage volume.Be to be understood that, although in the present case, the resource distributing to virtual machine application is equivalent to an overall physical machine, but now its hard disk distributes with the form of virtual storage volume, and the CPU (and internal memory) of hard disk now corresponding to this storage volume and virtual machine may not from Same Physical machine; Therefore, what now create remains " virtual machine ", and non-physical physical machine.
S204, preferred, stop request, and close the virtual machine for running this request.
That is, when the logical calculated of the Mapreduce part in large data platform or Sprk part etc. needs migration or when there is the situations such as the machine of delaying, then needs first to close existing virtual machine, certainly also just terminate each request run by virtual machine.
S205, preferred, again receiving this request and create the virtual machine for running request, is wherein the storage volume of this request correspondence of virtual machine carry.
After migration completes, when again receiving the request of certain application, then according to the method for step S203, again for it creates virtual machine, and the storage volume that the storage volume wherein distributing to this virtual machine uses before being exactly its virtual machine (storage volume of this request correspondence recorded namely); Like this, the desired data of this application also along with storage volume completes migration naturally, and need not carry out separately data backup, the work such as synchronous again, and its process is simple, reliable.
Be to be understood that; although be described for OpenStack cloud management platform, X86 server, SDS mode etc. in the present embodiment; but they all do not form limitation of the invention; as long as run large data platform system (as the X86 resource of calculation type according to above practical methods; minicomputer resource, the allocation scheme etc. of SAN storage resources) all belong to protection scope of the present invention.
Embodiment 3:
As shown in Figure 4, the present embodiment provides a kind of large data platform system, and it comprises:
Multiple physical machine with hard disk;
Virtual integral unit, for being integrated into a virtual hard disk by virtual for the hard disk of multiple physical machine;
Cutting unit, for being divided into multiple storage volume by virtual hard disk;
Virtual machine unit, asks for receiving one and creates the virtual machine for running request, wherein according to request demand be virtual machine carry storage volume.
That is, the large data platform system that the present embodiment provides has according to unit needed for the operation of above method.
In the large data platform system of the present embodiment, first the hard disk of multiple physical machine is integrated into a virtual hard disk, more each storage volume of this virtual hard disk is distributed to each virtual machine afterwards and use; Thus, wherein the hard disk of each physical machine (node) has all become a part for the storage resources shared, be separated with virtual machine, be convenient to unified utilization management, and then it also just achieves the decoupling zero (in other words loose coupling) of application and data, when moving when applying, upgrading, termination etc. will restart this application, as long as its original corresponding storage volume is distributed to its virtual machine again, the transfer realizing data that can be simple, reliable, complete, enhance the flexibility of system, ease of manageability and robustness, the multilist association computing of data can be realized.
Preferably, above large data platform system also comprises: record cell, for recording the storage volume of the virtual machine carry running each request, and it can be used as the storage volume corresponding with respective request.
Preferably, above large data platform system also comprises: allocation units, for distributing CPU and internal memory for virtual machine.
Be understandable that, the illustrative embodiments that above embodiment is only used to principle of the present invention is described and adopts, but the present invention is not limited thereto.For those skilled in the art, without departing from the spirit and substance in the present invention, can make various modification and improvement, these modification and improvement are also considered as protection scope of the present invention.
Claims (10)
1. a large data platform system operation method, is characterized in that, comprising:
A virtual hard disk is integrated into by virtual for the hard disk of multiple physical machine;
Described virtual hard disk is divided into multiple storage volume;
Receiving one ask and create the virtual machine for running described request, is wherein storage volume described in described virtual machine carry according to the demand of described request.
2. large data platform system operation method according to claim 1, is characterized in that, when creating the virtual machine for running described request, records the storage volume of described virtual machine carry as the storage volume corresponding with this request simultaneously; After reception one is asked and created the virtual machine for running described request, also comprise:
Stop described request, and close the virtual machine for running this request;
Again receiving this request and create the virtual machine for running described request, is wherein the storage volume of described this request correspondence of virtual machine carry.
3. large data platform system operation method according to claim 1 and 2, is characterized in that, described reception one is asked and the virtual machine created for running described request also comprises:
For described virtual machine distributes CPU and internal memory.
4. large data platform system operation method according to claim 3, is characterized in that, for described virtual machine distribution CPU and internal memory comprise:
For described virtual machine distributes CPU and internal memory, described CPU and interiorly save as the CPU of a physical machine and a part for internal memory;
And, a part for the hard disk of the corresponding physical machine of the storage volume for described virtual machine carry.
5. large data platform system operation method according to claim 4, is characterized in that,
Described request is function application or Web application.
6. large data platform system operation method according to claim 3, is characterized in that, for described virtual machine distribution CPU and internal memory comprise:
For described virtual machine distributes CPU and internal memory, described CPU and interior whole CPU and the internal memory saving as a physical machine;
And, whole hard disks of the corresponding physical machine of the storage volume for described virtual machine carry.
7. large data platform system operation method according to claim 6, is characterized in that,
Described request is large data platform request.
8. a large data platform system, is characterized in that, comprising:
Multiple physical machine with hard disk;
Virtual integral unit, for being integrated into a virtual hard disk by virtual for the hard disk of multiple physical machine;
Cutting unit, for being divided into multiple storage volume by described virtual hard disk;
Virtual machine unit, asks for receiving one and creates the virtual machine for running described request, is wherein storage volume described in described virtual machine carry according to the demand of described request.
9. large data platform system according to claim 8, is characterized in that, also comprise:
Record cell, for recording the storage volume of the described virtual machine carry running each request, and it can be used as the storage volume corresponding with respective request.
10. large data platform system according to claim 8, is characterized in that, also comprise:
Allocation units, for distributing CPU and internal memory for described virtual machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510586856.6A CN105278874A (en) | 2015-09-15 | 2015-09-15 | Big data platform system and running method therefor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510586856.6A CN105278874A (en) | 2015-09-15 | 2015-09-15 | Big data platform system and running method therefor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105278874A true CN105278874A (en) | 2016-01-27 |
Family
ID=55147961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510586856.6A Pending CN105278874A (en) | 2015-09-15 | 2015-09-15 | Big data platform system and running method therefor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105278874A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106095335A (en) * | 2016-06-07 | 2016-11-09 | 国网河南省电力公司电力科学研究院 | A kind of electric power big data elastic cloud calculates storage platform architecture method |
| 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 |
| CN106844035A (en) * | 2017-02-09 | 2017-06-13 | 腾讯科技（深圳）有限公司 | A kind of method and device realized the release of Cloud Server resource or recover |
| CN107193499A (en) * | 2017-05-26 | 2017-09-22 | 郑州云海信息技术有限公司 | A kind of moving method and device of container data volume |
| CN107566511A (en) * | 2017-09-20 | 2018-01-09 | 郑州云海信息技术有限公司 | A kind of method and cloud storage system for realizing cloud storage |
| CN107783818A (en) * | 2017-10-13 | 2018-03-09 | 北京百度网讯科技有限公司 | Deep learning task processing method, device, equipment and storage medium |
| CN107797766A (en) * | 2017-09-27 | 2018-03-13 | 郑州云海信息技术有限公司 | A kind of method and apparatus for creating volume |
| CN109656467A (en) * | 2017-10-11 | 2019-04-19 | 阿里巴巴集团控股有限公司 | Data transmission system, data interactive method, device and the electronic equipment of cloud network |
| CN110413378A (en) * | 2019-07-30 | 2019-11-05 | 上海金融期货信息技术有限公司 | Computing resource creation method and system under a kind of cloud computing |
| CN111026422A (en) * | 2019-11-28 | 2020-04-17 | 浙江大华技术股份有限公司 | Container-based application data upgrading method and device and computer storage medium |
| WO2021184983A1 (en) * | 2020-03-16 | 2021-09-23 | 华为技术有限公司 | Virtual machine migration method, and related device |
| WO2024140131A1 (en) * | 2022-12-30 | 2024-07-04 | 华为技术有限公司 | Software upgrading method and apparatus |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101416175A (en) * | 2006-03-30 | 2009-04-22 | 微软公司 | Creating templates of offline resources |
| CN103092671A (en) * | 2011-09-07 | 2013-05-08 | 国际商业机器公司 | Method and system for determining virtual machine image pattern distributions in a networked computing environment |
| US20130275975A1 (en) * | 2010-10-27 | 2013-10-17 | Hitachi, Ltd. | Resource management server, resource management method and storage medium in which resource management program is stored |
| US20140040891A1 (en) * | 2012-08-03 | 2014-02-06 | International Business Machines Corporation | Selecting provisioning targets for new virtual machine instances |
| CN103870341A (en) * | 2014-03-12 | 2014-06-18 | 汉柏科技有限公司 | Method and system of adjusting resources of virtual machine |
| CN103885833A (en) * | 2012-12-20 | 2014-06-25 | 中国移动通信集团公司 | Method and system for managing resources |
-
2015
- 2015-09-15 CN CN201510586856.6A patent/CN105278874A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101416175A (en) * | 2006-03-30 | 2009-04-22 | 微软公司 | Creating templates of offline resources |
| US20130275975A1 (en) * | 2010-10-27 | 2013-10-17 | Hitachi, Ltd. | Resource management server, resource management method and storage medium in which resource management program is stored |
| CN103092671A (en) * | 2011-09-07 | 2013-05-08 | 国际商业机器公司 | Method and system for determining virtual machine image pattern distributions in a networked computing environment |
| US20140040891A1 (en) * | 2012-08-03 | 2014-02-06 | International Business Machines Corporation | Selecting provisioning targets for new virtual machine instances |
| CN103885833A (en) * | 2012-12-20 | 2014-06-25 | 中国移动通信集团公司 | Method and system for managing resources |
| CN103870341A (en) * | 2014-03-12 | 2014-06-18 | 汉柏科技有限公司 | Method and system of adjusting resources of virtual machine |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106095335A (en) * | 2016-06-07 | 2016-11-09 | 国网河南省电力公司电力科学研究院 | A kind of electric power big data elastic cloud calculates storage platform architecture method |
| CN106095335B (en) * | 2016-06-07 | 2019-01-11 | 国网河南省电力公司电力科学研究院 | A kind of electric power big data elasticity cloud computing storage platform framework method |
| 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 |
| CN106844035A (en) * | 2017-02-09 | 2017-06-13 | 腾讯科技（深圳）有限公司 | A kind of method and device realized the release of Cloud Server resource or recover |
| CN106844035B (en) * | 2017-02-09 | 2023-03-24 | 腾讯科技（深圳）有限公司 | Method and device for realizing resource release or recovery of cloud server |
| CN107193499A (en) * | 2017-05-26 | 2017-09-22 | 郑州云海信息技术有限公司 | A kind of moving method and device of container data volume |
| CN107566511A (en) * | 2017-09-20 | 2018-01-09 | 郑州云海信息技术有限公司 | A kind of method and cloud storage system for realizing cloud storage |
| CN107797766A (en) * | 2017-09-27 | 2018-03-13 | 郑州云海信息技术有限公司 | A kind of method and apparatus for creating volume |
| CN109656467A (en) * | 2017-10-11 | 2019-04-19 | 阿里巴巴集团控股有限公司 | Data transmission system, data interactive method, device and the electronic equipment of cloud network |
| 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 |
| CN107783818B (en) * | 2017-10-13 | 2021-12-24 | 北京百度网讯科技有限公司 | Deep learning task processing method, device, equipment and storage medium |
| CN107783818A (en) * | 2017-10-13 | 2018-03-09 | 北京百度网讯科技有限公司 | Deep learning task processing method, device, equipment and storage medium |
| CN110413378A (en) * | 2019-07-30 | 2019-11-05 | 上海金融期货信息技术有限公司 | Computing resource creation method and system under a kind of cloud computing |
| CN111026422A (en) * | 2019-11-28 | 2020-04-17 | 浙江大华技术股份有限公司 | Container-based application data upgrading method and device and computer storage medium |
| CN111026422B (en) * | 2019-11-28 | 2022-08-09 | 浙江大华技术股份有限公司 | Container-based application data upgrading method and device and computer storage medium |
| WO2021184983A1 (en) * | 2020-03-16 | 2021-09-23 | 华为技术有限公司 | Virtual machine migration method, and related device |
| WO2024140131A1 (en) * | 2022-12-30 | 2024-07-04 | 华为技术有限公司 | Software upgrading method and apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105278874A (en) | Big data platform system and running method therefor | |
| US10261815B2 (en) | Methods and systems to determine and improve cost efficiency of virtual machines | |
| US10243872B2 (en) | Management of storage cluster performance with hybrid workloads | |
| US10671951B2 (en) | Methods and systems to determine container costs and attribute container costs to applications | |
| US9747136B2 (en) | Methods and systems that allocate cost of cluster resources in virtual data centers | |
| US8972986B2 (en) | Locality-aware resource allocation for cloud computing | |
| US8825863B2 (en) | Virtual machine placement within a server farm | |
| US10452665B2 (en) | Methods and systems to reduce time series data and detect outliers | |
| US9733989B1 (en) | Non-disruptive load-balancing of virtual machines between data centers | |
| US20130219033A1 (en) | End-to-end provisioning of storage clouds | |
| US9038063B2 (en) | Determining virtual machine image pattern distributions in a networked computing environment | |
| US10243815B2 (en) | Methods and systems to evaluate data center resource allocation costs | |
| US8813076B2 (en) | Virtual machine updates | |
| US9432300B2 (en) | Allocation of storage resources in a networked computing environment based on energy utilization | |
| US9189259B2 (en) | Provisioning of virtual machine pools based on historical data in a networked computing environment | |
| US9916092B2 (en) | Methods and systems to allocate physical data-storage costs to logical disks | |
| US9800484B2 (en) | Optimizing resource utilization in a networked computing environment | |
| US20180165698A1 (en) | Methods and systems to determine virtual storage costs of a virtual datacenter | |
| US10891148B2 (en) | Methods and systems for identifying application components in distributed computing facilities | |
| US10169275B2 (en) | System, method, and recording medium for topology-aware parallel reduction in an accelerator | |
| US20160366016A1 (en) | Virtualization of consistency groups | |
| US11989586B1 (en) | Scaling up computing resource allocations for execution of containerized applications | |
| US11194758B1 (en) | Data archiving using a compute efficient format in a service provider environment | |
| Shaikh et al. | Dynamic memory allocation technique for virtual machines | |
| US11995466B1 (en) | Scaling down computing resource allocations for execution of containerized applications |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160127 |