CN102223419A - Virtual resource dynamic feedback balanced allocation mechanism for network operation system - Google Patents
Virtual resource dynamic feedback balanced allocation mechanism for network operation system Download PDFInfo
- Publication number
- CN102223419A CN102223419A CN2011101860995A CN201110186099A CN102223419A CN 102223419 A CN102223419 A CN 102223419A CN 2011101860995 A CN2011101860995 A CN 2011101860995A CN 201110186099 A CN201110186099 A CN 201110186099A CN 102223419 A CN102223419 A CN 102223419A
- Authority
- CN
- China
- Prior art keywords
- resource
- module
- request
- virtual
- virtual machine
- 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
Images
Landscapes
- Computer And Data Communications (AREA)
Abstract
The invention relates to a virtual resource dynamic feedback balanced allocation mechanism for a network operation system. The mechanism comprises a resource request module, a resource real-time monitoring module, a resource dynamic management module and a resource allocating and scheduling module. The mechanism can be used for monitoring, predicating and performing dynamic and balanced allocation on the virtual resources of the whole network operation system so as to achieve the purposes of fully utilizing resources and realizing reliable service. By adopting the method, a favorable effect of improving the utilization ratio and the stability of the system resources is achieved.
Description
Technical field
The present invention relates to a kind of balanced distribution mechanism of virtual resource dynamical feedback of network-oriented operating system, this mechanism is applied to distributed networked operating system, belongs to the Computer Science and Technology field.
Background technology
Traditional terminal operating system, normally embedded OS adds a set of network protocols, typical as ICP/IP protocol and other application protocol bunch use C/S or B/S pattern to be connected with network terminal in application layer, ask respective service.The user can know and know and calculate and storage resources carries out in this locality.The user obtains the different service of quality by the local information that needs to the network terminal acquisition request according to the time delay of network.But such pattern is coupled software and hardware closely, can't adapt to the quick variation of business demand, simultaneously because the development of software does not catch up with the development speed of hardware, also cause system can't fully effectively use resource to the congenital underutilization of hardware resource.Along with the develop rapidly of computer and network technology, networked operating system has appearred, and its application model is as shown in Figure 1.
So-called networked operating system is by Intel Virtualization Technology and modern network technology, and the operation system function border extension to network side, is calculated configuration, scheduling, management with resource in a unified framework.The resource virtualizing of networking operating system is all kinds of heterogeneous resources such as calculating, storage, network are realized unified management, flexible configuration, scheduling flexibly and safety by means of Intel Virtualization Technology operation.The present invention relates to a kind of balanced distribution mechanism of virtual resource dynamical feedback of network-oriented operating system, its target be monitor network operating system in real time virtual resource utilize situation, and according to the balanced Resources allocation of the situation of real-time monitoring dynamical feedback, reach fully, reasonably use and shared network in resource and make it to obtain the purpose of maximum using.
At present, also carrying out positive research and checking sex work, also has certain distance for the real-time monitoring of the virtual resource of networked operating system and dynamic assignment from large-scale commercialization.
Summary of the invention
Described at background technology, the objective of the invention is to propose a kind of balanced distribution mechanism of virtual resource dynamical feedback of network-oriented operating system.
The present invention realizes by the following technical solutions:
The balanced distribution mechanism of the virtual resource dynamical feedback of network-oriented operating system of the present invention mainly is made up of four parts.
(1) resource request module: the resource request module is that networked operating system is carried out mutual interface with the external world, after this module is accepted user's request, according to user's kind, user's feature and user's request type are ranked to user's request, and the request of higher prior is come the front.
(2) resource real-time monitoring module: resource real-time monitoring module main task is the virtual resource pond in the real-time monitor network operating system, deposit the information of collecting the virtual resource pond in database, and carry out alert analysis, when the resource in the virtual resource pond in the monitor message of gathering surpasses alarm line, send alarm to the resource dynamic management module.
(3) resource dynamic management module: accept the monitor message that the resource real-time monitoring module provides to networked operating-system resources, analyzing each virtual machine operation conditions provides allocation strategy needed information for the resource allocation scheduling module, and networked operating system management and configuration interface are provided.
(4) resource allocation scheduling module: the optimal selection that the resource allocation scheduling module provides according to the resource dynamic management module, user's resource request is mapped in the resource pool of response, the equilibrium of the virtual resource of maintaining network operating system distributes.
The operation logic of the balanced distribution mechanism of the dynamical feedback of the virtual resource of network-oriented operating system of the present invention as shown in Figure 2.
Its specific implementation method comprises following step:
(1) the resource request module provides request interface to the user, the user is according to interface, press form and propose resource bid to networked operating system, after the resource request module receives user's request, feature according to the user, request to the user is ranked, and with the user of high priority, perhaps urgent request comes the request queue front.
(2) all dispose a remote monitoring Agent (agency) on all virtual machines of Resource Server, by Agent regularly send the real-time running state information of this virtual machine to resource real-time monitoring module (remote monitoring Server).Wherein the interval of Fa Songing can allow User Defined.Here we regularly sent information to remote monitoring Server with 5 seconds cycles.The information that Agent sends comprises CPU (central processing unit) utilance C, internal memory operating position M, and disk utilance D, process is counted real-time operating positions such as P.Remote monitoring Server collects the monitor message that Agent sends in real time and notes.
(3) the resource dynamic management module calculates the integrated load value L of all virtual machines according to the real time information of resource real-time monitoring module record, and user and keeper can prevent whether server overload and decision from increasing virtual machine and Resource Server by definition alarm critical value.
(4) optimal selection that provides according to the resource dynamic management module of resource allocation scheduling module is mapped to resource request on the virtual machine in the resource pool, reaches the reasonable utilization of virtual resource according to this, improves the operational efficiency and the stability of whole system.
For the calculating of integrated load value L, we do following regulation:
(1) L=0; Represent that this virtual machine is unavailable, the request that has connected can continue to obtain service, but refuses any new application request.When virtual machine need be safeguarded or the operating position of virtual machine is suitable for the situation of planting therewith when having reached alarm level.
(2) L!=0; The account form of L is L=C* α+M* β+D* γ+P* δ;
In order to calculate the value of L, we have introduced the one group of factor alpha that can dynamically adjust, beta, gamma, δ, wherein alpha+beta+γ+δ=1.
We can be according to CPU in the actual conditions, internal memory, and disk and the process number difference of importance in virtual machine comes its weight coefficient is adjusted, until finding one group of coefficient pressing close to current application most.In actual moving process, the coefficient that we adopt is followed successively by 0.4,0.3,0.1,0.2.And for C, M, D, the acquisition of P, its core mechanism be according to the past period virtual machine operation conditions predict the value that it is following.
We are example to calculate CPU, and the Agent on the virtual machine sends virtual machine i cpu busy percentage record x with 5 seconds cycles Server in the resource real-time monitoring module on management server
i[t], Server can note after receiving data, and the resource dynamic management module gets access to the utilance of CPU in a certain period by Server, by the analysis to the utilance historical record of virtual machine CPU, judge the following period running status of each virtual machine of prediction, load-bearing capacity.Because different virtual machine has different physical computing ability simultaneously because the difference of allocating task so need carry out real-time track record to virtual machine, is also carried out real-time estimate and judgement simultaneously.
When the resource allocation scheduling module is received the request that the resource request module sends, the notice resource management module, this moment, MA (Moving average) moving average prediction algorithm was used in the utilance record back of resource management module reading database, predicted the cpu busy percentage y of next period in future of each virtual machine
i[t], owing to need real-time estimate,, upgrade in each period so the prediction record also is a time series:
Y[t so] be our prediction following a moment CPU load value C.
Equally, we are to internal memory, after disk utilization rate and process number use the prediction of moving average prediction algorithm, have obtained the M at following a moment respectively, and D and P are introduced into the computing formula of above-mentioned L, and the virtual machine k that selects L value minimum sends it back the resource request module.
L
k=min{L
1[t],L
2[t],L
3[t]…L
n[t]}
Like this, in the process of system's operation, we constantly adjust the integrated load value L on the virtual machine on each Resource Server, when having new task to arrive, we are assigned to it on virtual machine of the minimum i.e. system load minimum at that time of L value, the duty ratio that guarantees this system according to this is balanced, stable.
Description of drawings
Fig. 1: the application model of networked operating system platform;
Fig. 2: the balanced distribution mechanism schematic diagram of the dynamical feedback of networked operating system virtual resource;
Fig. 3: the specific implementation pattern that shows networked operating system;
Fig. 4: show a plurality of Core server clusters and share the secondary server cluster;
Fig. 5: the forecasting process that shows networked operating system;
Fig. 6: show the process that networked operating-system resources distributes;
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the invention, the technical scheme in the embodiment of the invention is clearly and completely described, obviously, described embodiment also only is a part of embodiment of the present invention, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills belong to the scope of protection of the invention not making the every other embodiment that is obtained under the creative work prerequisite.
The user uses by the third party that browser or mobile phone terminal internet interview networking operating system platform are provided.Wherein the application of application layer is to be that application provider provides by third party's service platform.Concrete implementation pattern as shown in Figure 3, wherein the network side platform is the core place of whole system platform.
In the deployment of reality, the network side platform is made up of Core server cluster and secondary server cluster.A plurality of Core server clusters can be shared a secondary server cluster, as shown in Figure 5.
The Core server cluster is the physical basis of whole networked operating system, and it all is made up of Resource Server, constitutes the resource pool of networked operating system.The system manager is responsible for the projected resources server, creates and is application provider's distribution virtual machine.Each several VME operating system of Resource Server isolated operation.Resources of virtual machine is the most important resource of whole operation system management, and resources of virtual machine comprises the computing capability of real computer, storage capacity, network capacity or the like.
The secondary server cluster is that the work of supporting network operating system and one group of supporting device disposing mainly comprise: load-balanced server, management server or the like.Load-balanced server is born the resource allocation scheduling module, mainly is for the equilibrium of carrying out resource between a plurality of Resource Servers of Core server cluster distributes, and avoids single Resource Server to bear excessive load and causes system crash.Management server is then born resource real-time monitoring module and resource dynamic management module.Mainly be real-time monitoring and the management of carrying out networked operating-system resources, networked operating system management and configuration interface are provided.
We install RHQ Server as the monitoring resource module on management server, be used to monitor the running status of whole Core server, and all the virtual machine deploy RHQ Agent on Resource Server, we bind RHQ Server on RHQ Agent simultaneously, RHQ Agent can deposit data in database after RHQ Server obtains with certain time interval (5 seconds) all information to RHQ Server transmission virtual machine running status regularly like this.About the setting in the time interval, though very short interval can reflect the load of each virtual machine more definitely, very frequent operation meeting brings certain load to virtual machine.So compromise (Tradeoff) here arranged, and we will be set between 5 to 20 seconds in the time interval in general recommendations.
The keeper can define the alarm critical value of oneself virtual machine and whole Resource Server respectively.When new task requests is arranged, the running state information of receiving according to RHQ Server is come the comprehensive load value L of all virtual machines at computing application place, when the L value of finding virtual machine has has met or exceeded the alarm critical value of definition, send alarm to load-balanced server (resource distribution module), load-balanced server can be changed to 0 with its L value, represents that this virtual machine is unavailable.Final load-balanced server assigns the task in the minimum virtual machine of L value and goes.
Platform can provide the virtual resource running state information to the user in the resource request module, by timer is set, the information of the database in the poll certain hour section regularly, curve plotting figure, when receiving the alarm of monitoring resource module, illustrate that needing to add new resource comes the processing section load, first field feedback, close application, share the pressure of virtual machine and Resource Server.
When the resource management management server receive that each Resource Server sends after monitoring resource module running status, alarm as the No Assets monitoring module, data are handled, extract the cpu busy percentage C of each virtual machine on the Resource Server, each virtual machine cpu busy percentage to next period uses the MA algorithm to predict respectively, prediction of output vector C Fig. 5, predicted vector C sorts, export minimum utilance machine k, give resource distribution module with this information by the http technical transmission, when the needs Resources allocation, k is allocated in application.Fig. 6
The major technique advantage
The virtual resource allocation mechanism of present networked operating system platform is static allocation mostly, perhaps artificially set, many times resource rational utilization because static partition characteristic causes some resources of virtual machine bottleneck, can not be made a big impact to whole efficiency simultaneously.Adopt the resource allocation mechanism of dynamical feedback, can each virtual machine state of real-time tracking, can alarm for the bigger virtual machine of utilization of resources load wherein, conveniently artificially handle.
Use prediction algorithm that the operation conditions in each virtual resource future is estimated simultaneously, use the request of estimating resource to distribute and arrive optimized distribution effects.Mode with static allocation compares, and the present invention can improve resource utilization greatly, improves entire system efficient simultaneously.
Claims (2)
1. the balanced distribution mechanism of the virtual resource dynamical feedback of network-oriented operating system comprises:
(1) resource request module: the resource request module is that networked operating system is carried out mutual interface with the external world, after this module is accepted user's request, kind according to the user, user's feature, with user's request type user's request is ranked, the request of higher prior is come the front, and request module is according to the information of distribution module, to the user feedback system state simultaneously.
(2) resource real-time monitoring module: resource real-time monitoring module main task is the virtual resource pond in the real-time monitor network operating system, deposit the information of collecting the virtual resource pond in database, and carry out alert analysis, when the resource in the virtual resource pond in the monitor message of gathering surpasses alarm line, send alarm to the resource dynamic management module.
(3) resource dynamic management module: accept the monitor message that the resource real-time monitoring module provides to networked operating-system resources, analyzing each virtual machine operation conditions provides allocation strategy needed information for the resource allocation scheduling module, and networked operating system management and configuration interface are provided.
(4) resource allocation scheduling module: the optimal selection that the resource allocation scheduling module provides according to the resource dynamic management module, user's resource request is mapped in the resource pool of response, the equilibrium of the virtual resource of maintaining network operating system distributes.
In the balanced distribution mechanism of the dynamical feedback of the virtual resource of network-oriented operating system to the calculating of integrated load L value
(1) L=0; Represent that this virtual machine is unavailable, the request that has connected can continue to obtain service, but refuses any new application request.When virtual machine need be safeguarded or the operating position of virtual machine is suitable for the situation of planting therewith when having reached alarm level.
(2) L!=0; The account form of L is L=C* α+M* β+D* γ+P* δ;
Wherein C represents CPU (central processing unit) utilance, and M represents the internal memory operating position, and D represents the disk utilance, and P represents the process number.In order to calculate the value of L, we have introduced the one group of factor alpha that can dynamically adjust, beta, gamma, δ, wherein alpha+beta+γ+δ=1.We can be according to CPU in the actual conditions, internal memory, and disk and the process number difference of importance in virtual machine comes its weight coefficient is adjusted, until finding one group of coefficient pressing close to current application most.In actual moving process, the coefficient that we adopt is followed successively by 0.4,0.3,0.1,0.2.And for C, M, D, the acquisition of P be according to the past period virtual machine operation conditions predict the value that it is following.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011101860995A CN102223419A (en) | 2011-07-05 | 2011-07-05 | Virtual resource dynamic feedback balanced allocation mechanism for network operation system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011101860995A CN102223419A (en) | 2011-07-05 | 2011-07-05 | Virtual resource dynamic feedback balanced allocation mechanism for network operation system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102223419A true CN102223419A (en) | 2011-10-19 |
Family
ID=44779844
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2011101860995A Pending CN102223419A (en) | 2011-07-05 | 2011-07-05 | Virtual resource dynamic feedback balanced allocation mechanism for network operation system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102223419A (en) |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102404389A (en) * | 2011-11-04 | 2012-04-04 | 浪潮齐鲁软件产业有限公司 | Network invoicing method based on cloud compute and data asynchronous transmission technology |
CN102420867A (en) * | 2011-12-01 | 2012-04-18 | 浪潮电子信息产业股份有限公司 | Cluster storage entry resolution method based on real-time load balancing mechanism |
CN102571746A (en) * | 2011-11-23 | 2012-07-11 | 西安交通大学 | Virtual machine deployment method oriented to side channel attack defense of cloud computation environment |
CN102799488A (en) * | 2012-07-06 | 2012-11-28 | 中山大学深圳研究院 | Application resource management system applied to digital television |
CN103164283A (en) * | 2012-05-10 | 2013-06-19 | 上海兆民云计算科技有限公司 | Method and system for dynamic scheduling management of virtualized resources in virtualized desktop system |
CN103795766A (en) * | 2012-11-02 | 2014-05-14 | 腾讯科技(深圳)有限公司 | P2SP (Peer to Server & Peer) multi-source download system |
CN103812911A (en) * | 2012-11-14 | 2014-05-21 | 中兴通讯股份有限公司 | Method and system for controlling and utilizing service resources of PaaS (platform as a service) cloud computing platform |
CN103984602A (en) * | 2014-05-20 | 2014-08-13 | 华为技术有限公司 | VM (virtual machine) resource scheduling method, device and system |
CN104063265A (en) * | 2014-07-04 | 2014-09-24 | 云南电网公司 | Method for comprehensively evaluating virtual resources |
CN104331327A (en) * | 2014-12-02 | 2015-02-04 | 山东乾云启创信息科技有限公司 | Optimization method and optimization system for task scheduling in large-scale virtualization environment |
CN104572302A (en) * | 2015-01-04 | 2015-04-29 | 中国联合网络通信集团有限公司 | Method and device for distributing resources |
CN104902001A (en) * | 2015-04-07 | 2015-09-09 | 杭州电子科技大学 | Method for load balancing of Web requests based on operating system virtualization |
WO2015192664A1 (en) * | 2014-06-19 | 2015-12-23 | 中兴通讯股份有限公司 | Device monitoring method and apparatus |
CN105389392A (en) * | 2015-12-18 | 2016-03-09 | 浪潮(北京)电子信息产业有限公司 | Metadata load statistical method and system |
WO2016206441A1 (en) * | 2015-06-26 | 2016-12-29 | 中兴通讯股份有限公司 | Method and device for allocating virtual resource, and computer storage medium |
CN106790636A (en) * | 2017-01-09 | 2017-05-31 | 上海承蓝科技股份有限公司 | A kind of equally loaded system and method for cloud computing server cluster |
WO2018010564A1 (en) * | 2016-07-13 | 2018-01-18 | Huawei Technologies Co., Ltd. | Adaptive resource management in distributed computing systems |
CN108132840A (en) * | 2017-11-16 | 2018-06-08 | 浙江工商大学 | Resource regulating method and device in a kind of distributed system |
FR3061784A1 (en) * | 2017-01-12 | 2018-07-13 | Bull Sas | METHOD FOR EVALUATING THE PERFORMANCE OF AN APPLICATION CHAIN IN A COMPUTER INFRASTRUCTURE |
CN108632384A (en) * | 2018-05-15 | 2018-10-09 | 西安电子科技大学 | Load-balancing method based on the prediction of video request number |
CN111124801A (en) * | 2019-11-19 | 2020-05-08 | 平安科技(深圳)有限公司 | Intelligent system resource monitoring method and device and computer readable storage medium |
CN111488218A (en) * | 2020-03-13 | 2020-08-04 | 合肥中科类脑智能技术有限公司 | All-in-one machine computing system and method |
CN111580972A (en) * | 2020-05-08 | 2020-08-25 | 北京字节跳动网络技术有限公司 | Virtual resource processing method and device |
CN112911007A (en) * | 2021-02-04 | 2021-06-04 | 上海七牛信息技术有限公司 | PCDN (Peer-to-Peer Domain name System) resource management system and PCDN resource management method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101593133A (en) * | 2009-06-29 | 2009-12-02 | 北京航空航天大学 | Load balancing of resources of virtual machine method and device |
CN101697526A (en) * | 2009-10-10 | 2010-04-21 | 中国科学技术大学 | Method and system for load balancing of metadata management in distributed file system |
CN101938416A (en) * | 2010-09-01 | 2011-01-05 | 华南理工大学 | Cloud computing resource scheduling method based on dynamic reconfiguration virtual resources |
CN101986274A (en) * | 2010-11-11 | 2011-03-16 | 东软集团股份有限公司 | Resource allocation system and resource allocation method in private cloud environment |
CN102104631A (en) * | 2011-02-28 | 2011-06-22 | 南京邮电大学 | Method for ensuring quality of service of knowledge system based on cloud computing technology |
CN102111337A (en) * | 2011-03-14 | 2011-06-29 | 浪潮(北京)电子信息产业有限公司 | Method and system for task scheduling |
-
2011
- 2011-07-05 CN CN2011101860995A patent/CN102223419A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101593133A (en) * | 2009-06-29 | 2009-12-02 | 北京航空航天大学 | Load balancing of resources of virtual machine method and device |
CN101697526A (en) * | 2009-10-10 | 2010-04-21 | 中国科学技术大学 | Method and system for load balancing of metadata management in distributed file system |
CN101938416A (en) * | 2010-09-01 | 2011-01-05 | 华南理工大学 | Cloud computing resource scheduling method based on dynamic reconfiguration virtual resources |
CN101986274A (en) * | 2010-11-11 | 2011-03-16 | 东软集团股份有限公司 | Resource allocation system and resource allocation method in private cloud environment |
CN102104631A (en) * | 2011-02-28 | 2011-06-22 | 南京邮电大学 | Method for ensuring quality of service of knowledge system based on cloud computing technology |
CN102111337A (en) * | 2011-03-14 | 2011-06-29 | 浪潮(北京)电子信息产业有限公司 | Method and system for task scheduling |
Cited By (36)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102404389A (en) * | 2011-11-04 | 2012-04-04 | 浪潮齐鲁软件产业有限公司 | Network invoicing method based on cloud compute and data asynchronous transmission technology |
CN102571746B (en) * | 2011-11-23 | 2014-11-05 | 西安交通大学 | Virtual machine deployment method oriented to side channel attack defense of cloud computation environment |
CN102571746A (en) * | 2011-11-23 | 2012-07-11 | 西安交通大学 | Virtual machine deployment method oriented to side channel attack defense of cloud computation environment |
CN102420867A (en) * | 2011-12-01 | 2012-04-18 | 浪潮电子信息产业股份有限公司 | Cluster storage entry resolution method based on real-time load balancing mechanism |
CN103164283A (en) * | 2012-05-10 | 2013-06-19 | 上海兆民云计算科技有限公司 | Method and system for dynamic scheduling management of virtualized resources in virtualized desktop system |
CN103164283B (en) * | 2012-05-10 | 2018-08-10 | 上海兆民云计算科技有限公司 | Virtualization resource dynamic dispatching management method and system in a kind of virtual desktop system |
CN102799488A (en) * | 2012-07-06 | 2012-11-28 | 中山大学深圳研究院 | Application resource management system applied to digital television |
CN102799488B (en) * | 2012-07-06 | 2015-03-25 | 中山大学深圳研究院 | Application resource management system applied to digital television |
CN103795766B (en) * | 2012-11-02 | 2018-11-23 | 腾讯科技(深圳)有限公司 | A kind of P2SP multi-source download system |
CN103795766A (en) * | 2012-11-02 | 2014-05-14 | 腾讯科技(深圳)有限公司 | P2SP (Peer to Server & Peer) multi-source download system |
CN103812911A (en) * | 2012-11-14 | 2014-05-21 | 中兴通讯股份有限公司 | Method and system for controlling and utilizing service resources of PaaS (platform as a service) cloud computing platform |
CN103812911B (en) * | 2012-11-14 | 2018-05-08 | 中兴通讯股份有限公司 | A kind of method and system controlled using PaaS cloud computing platform Service Sources |
CN103984602A (en) * | 2014-05-20 | 2014-08-13 | 华为技术有限公司 | VM (virtual machine) resource scheduling method, device and system |
WO2015192664A1 (en) * | 2014-06-19 | 2015-12-23 | 中兴通讯股份有限公司 | Device monitoring method and apparatus |
CN105306234A (en) * | 2014-06-19 | 2016-02-03 | 中兴通讯股份有限公司 | Equipment monitoring method and device |
CN104063265A (en) * | 2014-07-04 | 2014-09-24 | 云南电网公司 | Method for comprehensively evaluating virtual resources |
CN104331327A (en) * | 2014-12-02 | 2015-02-04 | 山东乾云启创信息科技有限公司 | Optimization method and optimization system for task scheduling in large-scale virtualization environment |
CN104331327B (en) * | 2014-12-02 | 2017-07-11 | 山东乾云启创信息科技股份有限公司 | The optimization method of task scheduling and optimization system in large scale virtualisation environment |
CN104572302B (en) * | 2015-01-04 | 2018-09-11 | 中国联合网络通信集团有限公司 | A kind of method and device for realizing resource allocation |
CN104572302A (en) * | 2015-01-04 | 2015-04-29 | 中国联合网络通信集团有限公司 | Method and device for distributing resources |
CN104902001B (en) * | 2015-04-07 | 2018-04-06 | 杭州电子科技大学 | Web request load-balancing method based on operating system virtualization |
CN104902001A (en) * | 2015-04-07 | 2015-09-09 | 杭州电子科技大学 | Method for load balancing of Web requests based on operating system virtualization |
WO2016206441A1 (en) * | 2015-06-26 | 2016-12-29 | 中兴通讯股份有限公司 | Method and device for allocating virtual resource, and computer storage medium |
CN105389392A (en) * | 2015-12-18 | 2016-03-09 | 浪潮(北京)电子信息产业有限公司 | Metadata load statistical method and system |
WO2018010564A1 (en) * | 2016-07-13 | 2018-01-18 | Huawei Technologies Co., Ltd. | Adaptive resource management in distributed computing systems |
US10503558B2 (en) | 2016-07-13 | 2019-12-10 | Huawei Technologies Co., Ltd. | Adaptive resource management in distributed computing systems |
CN106790636A (en) * | 2017-01-09 | 2017-05-31 | 上海承蓝科技股份有限公司 | A kind of equally loaded system and method for cloud computing server cluster |
FR3061784A1 (en) * | 2017-01-12 | 2018-07-13 | Bull Sas | METHOD FOR EVALUATING THE PERFORMANCE OF AN APPLICATION CHAIN IN A COMPUTER INFRASTRUCTURE |
WO2018130764A1 (en) * | 2017-01-12 | 2018-07-19 | Bull Sas | Method for evaluating the performance of a chain of applications within an it infrastructure |
CN108132840A (en) * | 2017-11-16 | 2018-06-08 | 浙江工商大学 | Resource regulating method and device in a kind of distributed system |
CN108632384A (en) * | 2018-05-15 | 2018-10-09 | 西安电子科技大学 | Load-balancing method based on the prediction of video request number |
CN111124801A (en) * | 2019-11-19 | 2020-05-08 | 平安科技(深圳)有限公司 | Intelligent system resource monitoring method and device and computer readable storage medium |
CN111124801B (en) * | 2019-11-19 | 2023-06-13 | 平安科技(深圳)有限公司 | Intelligent system resource monitoring method and device and computer readable storage medium |
CN111488218A (en) * | 2020-03-13 | 2020-08-04 | 合肥中科类脑智能技术有限公司 | All-in-one machine computing system and method |
CN111580972A (en) * | 2020-05-08 | 2020-08-25 | 北京字节跳动网络技术有限公司 | Virtual resource processing method and device |
CN112911007A (en) * | 2021-02-04 | 2021-06-04 | 上海七牛信息技术有限公司 | PCDN (Peer-to-Peer Domain name System) resource management system and PCDN resource management method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102223419A (en) | Virtual resource dynamic feedback balanced allocation mechanism for network operation system | |
Jiang et al. | Optimal cloud resource auto-scaling for web applications | |
CN103118124B (en) | A kind of cloud computing load balancing method based on the many agencies of layering | |
CN105912401B (en) | A kind of distributed data batch processing system and method | |
CN102508709B (en) | Distributed-cache-based acquisition task scheduling method in purchase, supply and selling integrated electric energy acquiring and monitoring system | |
Liu et al. | Task scheduling and server provisioning for energy-efficient cloud-computing data centers | |
CN110096349A (en) | A kind of job scheduling method based on the prediction of clustered node load condition | |
CN104902001B (en) | Web request load-balancing method based on operating system virtualization | |
Tong et al. | A load balancing strategy based on the combination of static and dynamic | |
CN102981890B (en) | A kind of calculation task in Visualized data centre and virtual machine deployment method | |
CN103605567A (en) | Cloud computing task scheduling method facing real-time demand change | |
CN104216782A (en) | Dynamic resource management method for high-performance computing and cloud computing hybrid environment | |
CN109976917A (en) | A kind of load dispatching method, device, load dispatcher, storage medium and system | |
CN102012891B (en) | Computer cluster management method, device and system | |
Cao et al. | Energy efficient allocation of virtual machines in cloud computing environments based on demand forecast | |
CN105404549B (en) | Scheduling virtual machine system based on yarn framework | |
CN102339233A (en) | Cloud computing centralized management platform | |
CN101986661A (en) | Improved MapReduce data processing method under virtual machine cluster | |
CN106209433B (en) | Application system energy-efficient deployment device towards framework under a kind of cloud environment | |
CN108132840A (en) | Resource regulating method and device in a kind of distributed system | |
CN107122235A (en) | Public infrastructure resource regulating method based on application priority | |
CN107203256A (en) | Energy-conservation distribution method and device under a kind of network function virtualization scene | |
CN112749008A (en) | Cloud resource distribution system based on OpenStack and construction method thereof | |
Bi et al. | Dynamic fine-grained resource provisioning for heterogeneous applications in virtualized cloud data center | |
Cao et al. | Online cost-rejection rate scheduling for resource requests in hybrid clouds |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20111019 |