CN103176849A - Virtual machine clustering deployment method based on resource classification - Google Patents
Virtual machine clustering deployment method based on resource classification Download PDFInfo
- Publication number
- CN103176849A CN103176849A CN2013100784508A CN201310078450A CN103176849A CN 103176849 A CN103176849 A CN 103176849A CN 2013100784508 A CN2013100784508 A CN 2013100784508A CN 201310078450 A CN201310078450 A CN 201310078450A CN 103176849 A CN103176849 A CN 103176849A
- Authority
- CN
- China
- Prior art keywords
- physical machine
- node
- virtual machine
- machine
- physical
- 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.)
- Granted
Links
Images
Abstract
The invention discloses a virtual machine clustering deployment method based on resource classification. The method includes a transcript mechanism and a mirror image multi-channel parallel passing mechanism. According to the method, interference of mirror image document system fault on mirror image management and mirror image transmission can be effectively avoided through the transcript mechanism of a mirror image; meanwhile, through the mirror image multi-channel parallel passing mechanism, mirror image transmission speeds can be greatly improved, and response time of clustering deployment can be shortened; and besides, through a clustering deployment node selection algorithm, physical resources of a whole physical machine system can be effectively used, the phenomenon that the use ratio of a part of resources of a physical machine is high and the use ratio of the other part of the resources of the physical machine is low can be avoided, and load balancing of the whole system can be achieved.
Description
Technical field
The invention belongs to the Computer Service technical field, be specifically related to a kind of dispositions method of the cluster virtual machine based on resource classification.
Background technology
The flow process that cluster virtual machine is disposed generally is divided into: the cluster virtual machine resource characteristic is analyzed and the physical machine resource load is analyzed; The analysis of cluster virtual machine resource characteristic can also can be made analysis according to monitor data in the past according to system based on user's appointment, to determine its resource type; The physical machine resource load analyzes to determine which physical machine is fit to dispose the virtual machine of these clusters; Virtual machine image is prepared, and this comprises the preparation of mirror configuration file, and the transmission of mirror image; Complete at last the startup of virtual machine application cluster.
The clustered deploy(ment) strategy relates to a series of processes such as establishment of mirror image management, mirror image transmission, clustered deploy(ment) node selection, virtual machine.Wherein:
The mirror image management is the prerequisite that cluster virtual machine is disposed, want the efficient that the raising system disposes cluster virtual machine, can do many improvements above mirror image, as customized, the mirror image of mirror image according to resource types classify, the replication policy of mirror image, be all the key mechanism that improves system effectiveness.All mirror images all are stored in mirror site, in order to realize the safe and reliable of mirror image, are also generally to adopt the mirror image copies strategy.Current many products that can be used for doing mirror site are as the NFS(network file system(NFS)), financial telecommunications association of SWIFT(global cooperative bank) system, not only can conserve space, and improved efficient.
Cluster virtual machine is disposed node selection and is referred to select some physical machine nodes to be used for disposing virtual machine from the physical machine system.Current had a multiple deploying virtual machine selection strategy, the general strategy that adopts comprises greedy selection strategy and the balanced selection strategy of disposing disposed of order, no matter be to adopt which kind of strategy, all need to obtain from information or Performance Center the relevant information of candidate physical machine, comprise CPU, internal memory, the network bandwidth, I/O operating position.
The establishment of cluster virtual machine comprises that virtual machine configuration generates and the startup of virtual machine, required some configuration parameters of using when virtual machine configuration refers to virtual machine activation comprise memory requirements, virtual machine UUID(global unique identification symbol), CPU core number, image file deposit position, network configuration information etc.The startup of virtual machine comprises the establishment configuration file, copies image file, calls the virtual machine platform interface.
A good clustered deploy(ment) strategy need to satisfy user's request with the shortest time, even user's request is assigned on corresponding physical machine within the minimized time; Maximum system throughput makes the resource utilization of system reach maximum; Be with good expansibility; Minimize clustered deploy(ment) and operate the overhead that brings to system.Still there are some defectives in existing dispositions method in the face of new technological challenge, number of patent application is dispositions method and the device that 201110401608.1 Chinese patent application discloses a kind of virtual machine, method comprises: receive the request of disposing virtual machine, carry in described deployment request and dispose the virtual machine image file sign that virtual machine uses; Obtain the storage information of corresponding virtual machine image file in distributed file system according to described virtual machine image file sign, described distributed file system is comprised of this locality storage of a plurality of computing nodes; According to the load information of described storage information and described a plurality of computing nodes, select to dispose the computing node of described virtual machine, and the computing node deploy virtual machine of selecting.The method has adopted distributed file system, then these file system are difficult to meet the demands during in the face of the huge capacity demand of numerous cluster mirror images, and when the deployment cluster, traditional distributed file system is easy to become bottleneck when a mirror image being set up a plurality of transmission connection; Simultaneously, in a single day distributed file system runs into fault, very likely causes the loss of image file; In addition, only investigate physical nodes to the utilization factor of a certain resource during traditional clustered deploy(ment), there is no fully to analyze the resource characteristic of cluster, therefore can not take full advantage of the various resources of computing machine.
Summary of the invention
For the existing above-mentioned technical matters of prior art, the invention provides a kind of dispositions method of the cluster virtual machine based on resource classification, adopt the strategy of resource classification, cluster virtual machine is divided into the different resource type, can realize the load balancing of whole physical machine system.
A kind of dispositions method of the cluster virtual machine based on resource classification comprises the steps:
(1) resource type of cluster virtual machine is determined in concrete application corresponding according to cluster virtual machine;
(2) according to the resource type of cluster virtual machine, choose k physical machine node successively from the physical machine system, and each virtual machine in cluster virtual machine is distributed to respectively this k physical machine node, k is the number of virtual machine in cluster virtual machine;
(3) configuration file and the image file that cluster virtual machine is corresponding passes to each physical machine node that selects from template base.
Described resource type has three classes, is respectively computation-intensive, storage intensity and traffic-intensive type.
In described step (2), choose the physical machine node and virtual machine distributed to the method for physical machine node as follows from the physical machine system:
A. according to the resource type of cluster virtual machine, calculate the load information value F of every physical machine in the physical machine system;
B. for arbitrary physical machine in the physical machine system, calculate the load information value L of this physical machine, whether judge its load information value L greater than given overloading threshold, if, eliminate this physical machine, if not, keep this physical machine; Travel through according to this every physical machine;
C. the physical machine of choosing load information value F maximum from all physical machine that retain is as a physical machine node, and appoints from cluster virtual machine and get a virtual machine and distribute to this physical machine node;
D. return to execution in step a, cycling is until assign each virtual machine in cluster virtual machine.
If the resource type of described cluster virtual machine is computation-intensive, load information value F tries to achieve according to following formula:
F=α(1-c)+β(m+n)+node*γ
If the resource type of described cluster virtual machine is intensive for storage, load information value F tries to achieve according to following formula:
F=α(1-m)+β(c+n)+node*γ
If the resource type of described cluster virtual machine is the traffic-intensive type, load information value F tries to achieve according to following formula:
F=α(1-n)+β(c+m)+node*γ
Wherein: c, m and n are respectively the current cpu busy percentage of physical machine, memory usage and network bandwidth utilization factor, and node is the virtual machine number that is loaded with on current physical machine, and α, β and γ are given weight coefficient and are the practical experience value.
Described load information value L tries to achieve according to following formula:
L=a
1c+a
2m+a
3n+node*γ
Wherein: c, m and n are respectively the current cpu busy percentage of physical machine, memory usage and network bandwidth utilization factor, and node is the virtual machine number that is loaded with on current physical machine, a
1, a
2, a
3Be given weight coefficient and be the practical experience value with γ.
Preferably, in described step (3), the method that image file is passed to each physical machine node that selects from template base is as follows:
A. calculate the traffic load value T of each physical machine node that selects;
B. for arbitrary physical machine node, whether judge its traffic load value T greater than given load threshold, if, keep this physical machine node, if not, eliminate this physical machine node; Travel through according to this each physical machine node that selects;
C. build a transmit queue, the physical machine node that retains is deposited in described transmit queue by traffic load value T putting in order from small to large;
If D. in template base, image file has i copy, extract from transmit queue and arrange front i+1 physical machine node, and the image file in template base and i copy thereof are passed to respectively this i+1 physical machine node; After end of transmission, i+1 the physical machine node that makes image file and i the copy thereof in template base and obtain image file is all as transmission sources, extract from transmit queue again and arrange front 2i+2 physical machine node, make 2i+2 transmission sources transmit image file to this 2i+2 physical machine node respectively; Propagate according to this until in transmit queue each physical machine node all obtain image file, i is the natural number greater than 0;
E. for the physical machine node of eliminating in step B, make these physical machine nodes obtain image file or its copy by transmission from template base.
Described traffic load value T tries to achieve according to following formula:
T=a
4C+a
5N
Wherein: C and N be respectively the physical machine node current cpu busy percentage and the network bandwidth utilization factor of corresponding physical machine, a
4And a
5Be given weight coefficient and be the practical experience value.
Useful technique effect of the present invention is as follows:
(1) the present invention by the copy mechanism of mirror image, effectively avoids the mirror file system fault to the interference of mirror image management and mirror image transmission;
(2) the present invention by mirror image multidiameter delay pass through mechanism, can accelerate the speed that mirror image transmits greatly, shortens the response time of clustered deploy(ment);
(3) the present invention can effectively utilize the physical resource of whole physical machine system by clustered deploy(ment) node selection algorithm, avoids the utilization of physical machine part resource very high, and another part is quite idle, can also realize the load balancing of whole system.
Description of drawings
Fig. 1 is the steps flow chart schematic diagram of dispositions method of the present invention.
Fig. 2 is the schematic diagram that mirror image of the present invention transmits.
Fig. 3 is the experimental result contrast schematic diagram of mirror image transmission method of the present invention and traditional mirror image transmission method.
Fig. 4 (a) is cluster distribution method of the present invention and the traditional greedy distribution method contrast schematic diagram about cpu data.
Fig. 4 (b) is cluster distribution method of the present invention and the traditional greedy distribution method contrast schematic diagram about internal storage data.
Fig. 4 (c) is cluster distribution method of the present invention and the traditional greedy distribution method contrast schematic diagram about network bandwidth data.
Fig. 4 (d) is cluster distribution method of the present invention and the traditional greedy distribution method contrast schematic diagram about the I/O data.
Embodiment
In order more specifically to describe the present invention, below in conjunction with the drawings and the specific embodiments, the inventive method is elaborated.
As shown in Figure 1, a kind of dispositions method of the cluster virtual machine based on resource classification comprises the steps:
(1) resource type of cluster virtual machine is determined in concrete application corresponding according to cluster virtual machine;
Resource type has three classes, is respectively computation-intensive, storage intensity and traffic-intensive type;
Computation-intensive concentrates on Distributed Calculation, parallel computation, calculate in real time, the typical application comprises: the Distributed Computing Platform of MapRedcue(Google), BOINC(Berkeley open network computing platform), the CORBA(Common Object Request Broker Architecture), the distributed paralleling calculation platform of Dryad(Microsoft).
Data-intensive application mainly concentrates on mass file field of storage and cache field, and typical data-intensive applications comprises: the distribution file storage system of GFS(Google), the mass data distributed file system of CEPH(Linux), the distributed file system of HDFS(Hadoop), Memcached(distributed memory target cache system), the distributed cache system of Membase(NoSQL family).
The calculating of traffic-intensive type mainly concentrates on the magnanimity streaming and calculates and the large-scale complex event handling, and typical the application is the StreamInsight that Microsoft releases before.
Above-mentioned these application class are all to judge the resource type of application in experience, when an application is when newly using, just need to judge according to operational effect, rule of thumb show, can use CPU, internal memory, the network bandwidth of various application, the average utilization of I/O; After the utilization factor of the CPU that tests out the application that will dispose, internal memory, the network bandwidth, I/O, deduct respectively their average utilization, have the type of mxm., the resource type that just can be defined as using.
(2) according to the resource type of cluster virtual machine, choose k physical machine node successively from the physical machine system, and each virtual machine in cluster virtual machine is distributed to respectively this k physical machine node, k is the number of virtual machine in cluster virtual machine; In present embodiment, in cluster virtual machine to be disposed, the number k of virtual machine is 24.
Generally first filter the clustered deploy(ment) request before deployment, if calculate the physical machine system because the restriction of the aspects such as CPU, internal memory, file size, the network bandwidth by algorithm, cause in the time of can not completing this clustered deploy(ment), should filter the request of this time disposing, and to user feedback.The concrete implementation of disposing is as follows:
A. according to the resource type of cluster virtual machine, calculate the load information value F of every physical machine in the physical machine system;
If the resource type of cluster virtual machine is computation-intensive, load information value F tries to achieve according to following formula:
F=α(1-c)+β(m+n)+node*γ
If the resource type of cluster virtual machine is intensive for storage, load information value F tries to achieve according to following formula:
F=α(1-m)+β(c+n)+node*γ
If the resource type of cluster virtual machine is the traffic-intensive type, load information value F tries to achieve according to following formula:
F=α(1-n)+β(c+m)+node*γ
Wherein: c, m and n are respectively the current cpu busy percentage of physical machine, memory usage and network bandwidth utilization factor, and node is the virtual machine number that is loaded with on current physical machine, and α, β and γ are given weight coefficient; α=β in present embodiment=0.5, γ=0.2.
B. for arbitrary physical machine in the physical machine system, calculate the load information value L of this physical machine, whether judge its load information value L greater than given overloading threshold, if, eliminate this physical machine, if not, keep this physical machine; Travel through according to this every physical machine, in present embodiment, overloading threshold is set as 83;
Load information value L tries to achieve according to following formula:
L=a
1c+a
2m+a
3n+node*γ
Wherein: a
1, a
2And a
3Be given weight coefficient, a in present embodiment
1=0.4, a
2=a
3=0.3.
C. the physical machine of choosing load information value F maximum from all physical machine that retain is as a physical machine node, and appoints from cluster virtual machine and get a virtual machine and distribute to this physical machine node, simultaneously this physical machine node inserted in a priority query;
D. return to execution in step a, cycling is until assign each virtual machine in cluster virtual machine.
(3) configuration file and the image file that cluster virtual machine is corresponding passes to each physical machine node that selects from template base;
Wherein, because configuration file is generally smaller, so the physical machine node can directly acquire by transmission from template base; And image file is generally larger, therefore present embodiment adopts following transfer mode will image file be passed to each physical machine node from template base:
A. calculate the traffic load value T of each physical machine node that selects according to following formula;
T=a
4C+a
5N
Wherein: C and N be respectively the physical machine node current cpu busy percentage and the network bandwidth utilization factor of corresponding physical machine, a
4And a
5Be given weight coefficient, a in present embodiment
4=a
5=0.5.
B. for arbitrary physical machine node, whether judge its traffic load value T greater than given load threshold, if, keep this physical machine node, if not, eliminate this physical machine node; Travel through according to this each physical machine node that selects; In present embodiment, load threshold is set as in 0.7,24 physical machine node and has kept 22, has eliminated 2.
C. build a transmit queue, the physical machine node that retains is deposited in transmit queue by traffic load value T putting in order from small to large;
D. as shown in Figure 2, if in template base, image file has i copy (i=2 in present embodiment), extract from transmit queue and arrange front i+1 physical machine node, and the image file in template base and i copy thereof are passed to respectively this i+1 physical machine node; After end of transmission, i+1 the physical machine node that makes image file and i the copy thereof in template base and obtain image file is all as transmission sources, extract from transmit queue again and arrange front 2i+2 physical machine node, make 2i+2 transmission sources transmit image file to this 2i+2 physical machine node respectively; Propagate according to this until in transmit queue each physical machine node all obtain image file;
E. for 2 physical machine nodes eliminating in step B, make these 2 physical machine nodes obtain respectively image file and copy 1 thereof by transmitting from template base.
Start at last all virtual machines in cluster virtual machine, complete clustered deploy(ment).
Below we make present embodiment and traditional NFS single-point mirror image transmission and Swift mirror image dispose to transmit to compare by experiment, these two kinds of control methodss are all the modes that the cloud platform generally uses.After the test result that obtains present embodiment mirror image parallel duplex transmission policy and traditional NFS mirror image transmission policy and Swift mirror site, contrast three's time.In checking, the size of image file is 3G, mirror image quantity is respectively 1,2,4,5,6,7,8,16,32,64, the copy of present embodiment and traditional mirror image transmission method all is set in 2 situation, the passing time experimental result as shown in Figure 3, horizontal ordinate is mirror image quantity, and ordinate is passing time.
When the quantity of transmitting all was 1, the mirror image passing time of the mirror image passing time of present embodiment and NFS system was all similar; When mirror image transmits quantity hour, the mirror image way to manage performance of Swift mirror image way to manage and present embodiment is all similar; But when the quantity of transmitting is larger, mirror image passing time and the linear growth of quantity of NFS system, the passing time of Swift mirror site also increases larger, and the mirror image multidiameter delay passing time of present embodiment is the logarithmic relationship growth.Therefore, experimental result shows, when mirror image transmits quantity when larger, the mirror image transmission policy of present embodiment has more excellent transmission performance for the deployment of large-scale virtual machine cluster.
Below we compare with regard to CPU, internal memory, the network bandwidth, four kinds of data of I/O allocation algorithm and traditional greedy allocation algorithm of present embodiment, as shown in Figure 4.According to these four groups of correlation datas, can obtain CPU, internal memory, the network bandwidth, the data of I/O and the error mean values of mean value of two kinds of allocation algorithms, every numerical value is as shown in table 1:
Table 1
? | Greedy allocation algorithm | Present embodiment |
CPU | 13.61375 | 5.6125 |
Internal memory | 21.6258 | 1.7115 |
The network bandwidth | 7.6295 | 0.24575 |
I/O | 2.275 | 0.40345 |
As can be seen from the table, the cluster allocation algorithm based on resource classification that present embodiment proposes is compared with the greedy allocation algorithm of order, can make the load performance of whole physical machine system be in optimum condition, and every resource is made sufficient utilization.
Claims (6)
1. the dispositions method based on the cluster virtual machine of resource classification, comprise the steps:
(1) resource type of cluster virtual machine is determined in concrete application corresponding according to cluster virtual machine;
(2) according to the resource type of cluster virtual machine, choose k physical machine node successively from the physical machine system, and each virtual machine in cluster virtual machine is distributed to respectively this k physical machine node, k is the number of virtual machine in cluster virtual machine;
(3) configuration file and the image file that cluster virtual machine is corresponding passes to each physical machine node that selects from template base.
2. the dispositions method of the cluster virtual machine based on resource classification according to claim 1 is characterized in that: in described step (2), choose the physical machine node and virtual machine is distributed to the method for physical machine node as follows from the physical machine system:
A. according to the resource type of cluster virtual machine, calculate the load information value F of every physical machine in the physical machine system;
B. for arbitrary physical machine in the physical machine system, calculate the load information value L of this physical machine, whether judge its load information value L greater than given overloading threshold, if, eliminate this physical machine, if not, keep this physical machine; Travel through according to this every physical machine;
C. the physical machine of choosing load information value F maximum from all physical machine that retain is as a physical machine node, and appoints from cluster virtual machine and get a virtual machine and distribute to this physical machine node;
D. return to execution in step a, cycling is until assign each virtual machine in cluster virtual machine.
3. the dispositions method of the cluster virtual machine based on resource classification according to claim 2, it is characterized in that: if the resource type of described cluster virtual machine is computation-intensive, load information value F tries to achieve according to following formula:
F=α(1-c)+β(m+n)+node*γ
If the resource type of described cluster virtual machine is intensive for storage, load information value F tries to achieve according to following formula:
F=α(1-m)+β(c+n)+node*γ
If the resource type of described cluster virtual machine is the traffic-intensive type, load information value F tries to achieve according to following formula:
F=α(1-n)+β(c+m)+node*γ
Wherein: c, m and n are respectively the current cpu busy percentage of physical machine, memory usage and network bandwidth utilization factor, and node is the virtual machine number that is loaded with on current physical machine, and α, β and γ are given weight coefficient.
4. the dispositions method of the cluster virtual machine based on resource classification according to claim 2, it is characterized in that: described load information value L tries to achieve according to following formula:
L=a
1c+a
2m+a
3n+node*γ
Wherein: c, m and n are respectively the current cpu busy percentage of physical machine, memory usage and network bandwidth utilization factor, and node is the virtual machine number that is loaded with on current physical machine, a
1, a
2, a
3Be given weight coefficient with γ.
5. the dispositions method of the cluster virtual machine based on resource classification according to claim 1, it is characterized in that: in described step (3), the method that image file is passed to each physical machine node that selects from template base is as follows:
A. calculate the traffic load value T of each physical machine node that selects;
B. for arbitrary physical machine node, whether judge its traffic load value T greater than given load threshold, if, keep this physical machine node, if not, eliminate this physical machine node; Travel through according to this each physical machine node that selects;
C. build a transmit queue, the physical machine node that retains is deposited in described transmit queue by traffic load value T putting in order from small to large;
If D. in template base, image file has i copy, extract from transmit queue and arrange front i+1 physical machine node, and the image file in template base and i copy thereof are passed to respectively this i+1 physical machine node; After end of transmission, i+1 the physical machine node that makes image file and i the copy thereof in template base and obtain image file is all as transmission sources, extract from transmit queue again and arrange front 2i+2 physical machine node, make 2i+2 transmission sources transmit image file to this 2i+2 physical machine node respectively; Propagate according to this until in transmit queue each physical machine node all obtain image file, i is the natural number greater than 0;
E. for the physical machine node of eliminating in step B, make these physical machine nodes obtain image file or its copy by transmission from template base.
6. the dispositions method of the cluster virtual machine based on resource classification according to claim 5, it is characterized in that: described traffic load value T tries to achieve according to following formula:
T=a
4C+a
5N
Wherein: C and N be respectively the physical machine node current cpu busy percentage and the network bandwidth utilization factor of corresponding physical machine, a
4And a
5Be given weight coefficient.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310078450.8A CN103176849B (en) | 2013-03-12 | 2013-03-12 | A kind of dispositions method of the cluster virtual machine based on resource classification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310078450.8A CN103176849B (en) | 2013-03-12 | 2013-03-12 | A kind of dispositions method of the cluster virtual machine based on resource classification |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103176849A true CN103176849A (en) | 2013-06-26 |
CN103176849B CN103176849B (en) | 2016-04-27 |
Family
ID=48636749
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310078450.8A Active CN103176849B (en) | 2013-03-12 | 2013-03-12 | A kind of dispositions method of the cluster virtual machine based on resource classification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103176849B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103580923A (en) * | 2013-11-08 | 2014-02-12 | 华为技术有限公司 | Software deploying method and device |
WO2015149514A1 (en) * | 2014-03-31 | 2015-10-08 | 华为技术有限公司 | Virtual machine deploying method and apparatus |
WO2015184612A1 (en) * | 2014-06-05 | 2015-12-10 | 华为技术有限公司 | Resource scheduling method and apparatus |
CN105867998A (en) * | 2016-03-24 | 2016-08-17 | 国云科技股份有限公司 | Virtual machine cluster deployment algorithm |
CN105912382A (en) * | 2016-04-07 | 2016-08-31 | 浪潮电子信息产业股份有限公司 | Mirror image management device, system and method |
CN106951559A (en) * | 2017-03-31 | 2017-07-14 | 联想(北京)有限公司 | Data reconstruction method and electronic equipment in distributed file system |
CN107203394A (en) * | 2017-04-18 | 2017-09-26 | 中国科学院计算技术研究所 | A kind of high safety docker container batch dispositions methods and device |
CN107276835A (en) * | 2017-08-11 | 2017-10-20 | 郑州云海信息技术有限公司 | A kind of clustered deploy(ment) collocation method and system |
CN108536729A (en) * | 2018-02-24 | 2018-09-14 | 国家计算机网络与信息安全管理中心 | Across the subregion image file synchronous method of one kind and device |
CN109558214A (en) * | 2018-12-05 | 2019-04-02 | 腾讯科技(深圳)有限公司 | Host method for managing resource, device and storage medium under isomerous environment |
CN111158909A (en) * | 2019-12-27 | 2020-05-15 | 中国联合网络通信集团有限公司 | Cluster resource allocation processing method, device, equipment and storage medium |
CN116582546A (en) * | 2023-07-12 | 2023-08-11 | 深圳市智博通电子有限公司 | Network intercommunication method of virtual machine cluster based on super fusion node |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101311917A (en) * | 2007-05-24 | 2008-11-26 | 中国科学院过程工程研究所 | Particle model faced multi-tier direct-connection cluster paralleling computing system |
US20120110582A1 (en) * | 2010-10-29 | 2012-05-03 | International Business Machines Corporation | Real-time computing resource monitoring |
-
2013
- 2013-03-12 CN CN201310078450.8A patent/CN103176849B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101311917A (en) * | 2007-05-24 | 2008-11-26 | 中国科学院过程工程研究所 | Particle model faced multi-tier direct-connection cluster paralleling computing system |
US20120110582A1 (en) * | 2010-10-29 | 2012-05-03 | International Business Machines Corporation | Real-time computing resource monitoring |
Non-Patent Citations (1)
Title |
---|
庄威等: "云环境下基于多属性层次分析的虚拟机部署与调度策略", 《西安交通大学学报》 * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103580923B (en) * | 2013-11-08 | 2017-02-15 | 华为技术有限公司 | Software deploying method and device |
CN103580923A (en) * | 2013-11-08 | 2014-02-12 | 华为技术有限公司 | Software deploying method and device |
WO2015149514A1 (en) * | 2014-03-31 | 2015-10-08 | 华为技术有限公司 | Virtual machine deploying method and apparatus |
WO2015184612A1 (en) * | 2014-06-05 | 2015-12-10 | 华为技术有限公司 | Resource scheduling method and apparatus |
CN105519075A (en) * | 2014-06-05 | 2016-04-20 | 华为技术有限公司 | Resource scheduling method and apparatus |
CN105867998A (en) * | 2016-03-24 | 2016-08-17 | 国云科技股份有限公司 | Virtual machine cluster deployment algorithm |
CN105912382A (en) * | 2016-04-07 | 2016-08-31 | 浪潮电子信息产业股份有限公司 | Mirror image management device, system and method |
CN106951559B (en) * | 2017-03-31 | 2020-08-25 | 联想(北京)有限公司 | Data recovery method in distributed file system and electronic equipment |
CN106951559A (en) * | 2017-03-31 | 2017-07-14 | 联想(北京)有限公司 | Data reconstruction method and electronic equipment in distributed file system |
CN107203394A (en) * | 2017-04-18 | 2017-09-26 | 中国科学院计算技术研究所 | A kind of high safety docker container batch dispositions methods and device |
CN107276835A (en) * | 2017-08-11 | 2017-10-20 | 郑州云海信息技术有限公司 | A kind of clustered deploy(ment) collocation method and system |
CN108536729A (en) * | 2018-02-24 | 2018-09-14 | 国家计算机网络与信息安全管理中心 | Across the subregion image file synchronous method of one kind and device |
CN108536729B (en) * | 2018-02-24 | 2022-06-14 | 国家计算机网络与信息安全管理中心 | Cross-partition mirror image file synchronization method and device |
CN109558214A (en) * | 2018-12-05 | 2019-04-02 | 腾讯科技(深圳)有限公司 | Host method for managing resource, device and storage medium under isomerous environment |
CN111158909A (en) * | 2019-12-27 | 2020-05-15 | 中国联合网络通信集团有限公司 | Cluster resource allocation processing method, device, equipment and storage medium |
CN111158909B (en) * | 2019-12-27 | 2023-07-25 | 中国联合网络通信集团有限公司 | Cluster resource allocation processing method, device, equipment and storage medium |
CN116582546A (en) * | 2023-07-12 | 2023-08-11 | 深圳市智博通电子有限公司 | Network intercommunication method of virtual machine cluster based on super fusion node |
Also Published As
Publication number | Publication date |
---|---|
CN103176849B (en) | 2016-04-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103176849B (en) | A kind of dispositions method of the cluster virtual machine based on resource classification | |
CN101957863B (en) | Data parallel processing method, device and system | |
CN110134495B (en) | Container cross-host online migration method, storage medium and terminal equipment | |
Yan et al. | Blogel: A block-centric framework for distributed computation on real-world graphs | |
CN102724277B (en) | The method of live migration of virtual machine and deployment, server and group system | |
CN101296114B (en) | Parallel pattern matching method and system based on stream | |
CN111027736A (en) | Micro-service combined deployment and scheduling method under multi-objective optimization | |
CN103294548B (en) | A kind of I/O request dispatching method based on distributed file system and system | |
CN110308984B (en) | Cross-cluster computing system for processing geographically distributed data | |
CN104969213A (en) | Data stream splitting for low-latency data access | |
US9807152B2 (en) | Distributed processing device and distributed processing system as well as distributed processing method | |
CN103699433B (en) | One kind dynamically adjusts number of tasks purpose method and system in Hadoop platform | |
CN108182105A (en) | Local dynamic station moving method and control system based on Docker container techniques | |
CN106095531B (en) | A kind of dispatching method of virtual machine loaded based on grade and physical machine in cloud platform | |
CN107864211B (en) | Cluster resource dispatching method and system | |
CN103297499A (en) | Scheduling method and system based on cloud platform | |
Rupprecht et al. | SquirrelJoin: Network-aware distributed join processing with lazy partitioning | |
CN103761146A (en) | Method for dynamically setting quantities of slots for MapReduce | |
CN105426228B (en) | A kind of OpenStack virtual machine placement methods towards live streaming media and video code conversion | |
Schneider et al. | Dynamic load balancing for ordered data-parallel regions in distributed streaming systems | |
Li et al. | Replica-aware task scheduling and load balanced cache placement for delay reduction in multi-cloud environment | |
Chen et al. | Latency minimization for mobile edge computing networks | |
CN108540405A (en) | Internet resources moving method and device | |
Li et al. | Neighborhood search-based job scheduling for IoT big data real-time processing in distributed edge-cloud computing environment | |
More et al. | Energy-aware VM migration using dragonfly–crow optimization and support vector regression model in Cloud |
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 |