CN105159775A - Load balancer based management system and management method for cloud computing data center - Google Patents
Load balancer based management system and management method for cloud computing data center Download PDFInfo
- Publication number
- CN105159775A CN105159775A CN201510475609.9A CN201510475609A CN105159775A CN 105159775 A CN105159775 A CN 105159775A CN 201510475609 A CN201510475609 A CN 201510475609A CN 105159775 A CN105159775 A CN 105159775A
- Authority
- CN
- China
- Prior art keywords
- elastic panel
- panel nodes
- load
- virtual machine
- nodes pond
- 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
Abstract
The invention discloses a load balancer based management system and management method for a cloud computing data center. The management system comprises an elastic node pool cluster, a load balancer cluster and a management apparatus, wherein the elastic node pool cluster comprises a plurality of elastic node pools, each elastic node pool comprises a plurality of virtual machines, and the virtual machines are used for externally providing services through virtual IPs; the load balancer cluster comprises a plurality of load balancers, and each load balancer is connected with a set number of the elastic node pools and used for providing a load balance service for each elastic node pool connected with the load balancer; and the management apparatus is used for managing the load balancers and the elastic node pools and dynamically adjusting the number of the virtual machines in the elastic node pools by adopting a preset load balance policy according to a load state of each elastic node pool. According to the load balancer based management system and management method, the number of the virtual machines in the elastic node pools is automatically increased or reduced, so that business jamming and system resource waste are avoided.
Description
Technical field
The present invention relates to cloud computing administrative skill, particularly a kind of management system of the cloud computation data center based on load equalizer and management method.
Background technology
Cloud computing is a kind of new paragon using shared resource, changes the pattern of the local physical resource of traditional whole uses.User only needs to be connected to cloud computation data center by network, requirement description to resources such as calculating, storage, networks is proposed, cloud computation data center will describe according to demand carries out scheduling of resource and distributes actual physical resource carrying out run user application, meets consumers' demand.Along with the development of Information technology, cloud computing progressively becomes the Hot spots for development of industry, and the cloud computation data center platform of domestic and international all big enterprises also starts to come into operation one after another.
Traditional cloud computation data center is only be manually rule of thumb the server of each business configuration fixed qty, when offered load is too high, response service cannot changes fast, cause service card to pause and even collapse; And when business is idle, server still work, causes the unnecessary waste of system resource.In order to solve the problems of the technologies described above, prior art proposes load-balancing technique.
Load-balancing technique is a kind of according to load-balancing algorithm, network request is distributed to the technology of the available server in a server cluster.In cloud computing, network service request can be assigned to the enterprising row relax of the less server of load by load-balancing technique, to improve the treatment effeciency of network service request, make web visitor obtain better experience.
Although the use of load equalizer can improve the service performance of system greatly, guarantee system can not rise suddenly and sharply because of Single Point of Faliure or visit capacity and cause business to collapse, but present inventor studies discovery, when Operational Visit amount rises suddenly and sharply, business can only all be given each service node by existing load-balancing technique, quantity due to existing service node is fixing, therefore when visit capacity exceedes certain limit, service node cannot process, still there is the possibility of business collapse, and when Operational Visit is less, service node occurs a large amount of idle, still there is the situation of the wasting of resources.
Summary of the invention
In order to solve the problems of the technologies described above, the invention provides a kind of management system and management method of the cloud computation data center based on load equalizer, effectively solve the business collapse of prior art existence and the technical matters of the wasting of resources.
In order to reach the object of the invention, the invention provides a kind of management system of the cloud computation data center based on load equalizer, comprising elastic panel nodes pond cluster, load equalizer cluster and management devices, wherein,
Elastic panel nodes pond cluster, comprises several elastic panel nodes ponds, and each elastic panel nodes pond comprises several virtual machines, and described virtual machine is used for externally providing service by virtual IP address;
Load equalizer cluster, comprises several load equalizers, and each load equalizer is connected, for providing load balancing service for connected each elastic panel nodes pond with the elastic panel nodes pond of setting quantity;
Management devices, be connected with each load equalizer in described load equalizer cluster, for load management balanced device and elastic panel nodes pond, according to the load state in each elastic panel nodes pond, adopt the quantity of virtual machine in elastic panel nodes pond described in default load balancing dynamic conditioning.
Further, described management devices comprises load balancing administration module and elastic panel nodes pond administration module, wherein,
Load balancing administration module, for being each load equalizer configuration elastic panel nodes pond, is each elastic panel nodes pond configuration virtual IP, port and protocol;
Elastic panel nodes pond administration module, for obtaining the load state in described elastic panel nodes pond, and according to the quantity of virtual machine in described load state and load balancing dynamic conditioning elastic panel nodes pond.
Further, described load balancing administration module comprises device management unit Sum fanction administrative unit, wherein,
Device management unit, for being each load equalizer configuration elastic panel nodes pond;
Regulation management unit, for being each elastic panel nodes pond configuration virtual IP, port and protocol.
Further, described elastic panel nodes pond administration module comprises load monitoring unit, node management unit, Template Manager unit and IP administrative unit, wherein,
Load monitoring unit, obtains the load state in described elastic panel nodes pond for the api interface by calling described load equalizer;
Node management unit, for according to described load state and the load balancing preset, generates newly-increased virtual machine control command and sends to Template Manager unit, or generation deletion virtual machine control command sends to IP administrative unit;
Template Manager unit, for storage virtual machine mirror image template base, after receiving described newly-increased virtual machine control command, generates new virtual machine and the identifier of described new virtual machine is sent to IP administrative unit;
IP administrative unit, for the identifier of storage virtual machine and the IP Dynamic link library of correspondence, after receiving described deletion virtual machine control command, deletes the idle identifier of virtual machine and the IP Dynamic link library of correspondence; Also for after the identifier receiving described new virtual machine, it is this new virtual machine configuration of IP Dynamic link library.
Further, described load balancing is: when the duration being in high load condition when described elastic panel nodes pond exceedes default time threshold, increase the quantity of virtual machine in described elastic panel nodes pond; The duration being in low load condition when described elastic panel nodes pond, when exceeding default time threshold, reduces the quantity of virtual machine in described elastic panel nodes pond.
Further, described elastic panel nodes pond is in high load condition and refers to, in system performance situation, network performance conditions and data performance situation, any one status index is more than or equal to its high threshold; Described elastic panel nodes pond is in low load condition and refers to, status indexes all in system performance situation, network performance conditions and data performance situation is all less than or equal to its Low threshold.
Further, described system performance situation refers to the average CPU utilization of virtual machine in elastic panel nodes pond and average memory usage, described network performance conditions refers to average total linking number and the average active linking number of virtual machine in elastic panel nodes pond, and described data performance situation refers to the averaging network influx of virtual machine in elastic panel nodes pond, averaging network discharge and average network traffics.
In order to reach the object of the invention, present invention also offers a kind of management method of the cloud computation data center based on load equalizer, comprising:
Create the elastic panel nodes pond cluster comprising several elastic panel nodes ponds, the virtual machine that several externally provide service is set in each elastic panel nodes pond;
Create the load equalizer cluster comprising several load equalizers, being the elastic panel nodes pond of each load equalizer configuration setting quantity, is each elastic panel nodes pond configuration virtual IP, port and protocol;
Obtain the load state in described elastic panel nodes pond, and according to described load state, adopt the quantity of virtual machine in elastic panel nodes pond described in default load balancing dynamic conditioning.
Further, the load state in the described elastic panel nodes pond of described acquisition, and according to described load state, adopt the quantity of virtual machine in elastic panel nodes pond described in default load balancing dynamic conditioning, specifically comprise:
Step 31, obtained the load state in described elastic panel nodes pond by the api interface calling described load equalizer;
Step 32, judge whether described elastic panel nodes pond is in high load condition, is perform step 34, otherwise perform step 33;
Step 33, judge whether described elastic panel nodes pond is in low load condition, is perform step 35, otherwise perform step 31;
Whether the duration that step 34, judgement are in high load condition exceedes default time threshold, is increase the quantity of virtual machine in described elastic panel nodes pond, performs step 31, otherwise performs step 31;
Whether the duration that step 35, judgement are in low load condition exceedes default time threshold, is reduce the quantity of virtual machine in described elastic panel nodes pond, performs step 31, otherwise performs step 31.
Further, described load balancing is: when the duration being in high load condition when described elastic panel nodes pond exceedes default time threshold, increase the quantity of virtual machine in described elastic panel nodes pond; The duration being in low load condition when described elastic panel nodes pond, when exceeding default time threshold, reduces the quantity of virtual machine in described elastic panel nodes pond; Described elastic panel nodes pond is in high load condition and refers to, in system performance situation, network performance conditions and data performance situation, any one status index is more than or equal to its high threshold; Described elastic panel nodes pond is in low load condition and refers to, status indexes all in system performance situation, network performance conditions and data performance situation is all less than or equal to its Low threshold; Described system performance situation refers to the average CPU utilization of virtual machine in elastic panel nodes pond and average memory usage, described network performance conditions refers to average total linking number and the average active linking number of virtual machine in elastic panel nodes pond, and described data performance situation refers to the averaging network influx of virtual machine in elastic panel nodes pond, averaging network discharge and average network traffics.
The invention provides a kind of management system and management method of the cloud computation data center based on load equalizer, by proposing the concept in elastic panel nodes pond, with elastic panel nodes pond for application, the service of load equalizer is concentrated on elastic panel nodes pond, there is the advantages such as easy expansion, easy exploiting and easy care.Simultaneously, by load equalizers all in management devices unified management cloud data center, not only can merge the load-balancing device of various ways and performance, form isomery load balancing system, service resources can also be allocated in system level, there is the advantages such as highly compatible, high applicability and high reliability.Further, the load state in elastic panel nodes pond is obtained by the api interface calling load equalizer, according to the system performance situation in elastic panel nodes pond, network performance conditions and data performance situation, according to the load balancing preset, automatic increase or reduce the quantity of virtual machine in elastic panel nodes pond, not only can avoid by newly-increased virtual machine the service card that access storm causes to pause, and avoid system resource waste by the virtual machine reducing the free time.
Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from instructions, or understand by implementing the present invention.Object of the present invention and other advantages realize by structure specifically noted in instructions, claims and accompanying drawing and obtain.
Accompanying drawing explanation
Accompanying drawing is used to provide the further understanding to technical solution of the present invention, and forms a part for instructions, is used from and explains technical scheme of the present invention, do not form the restriction to technical solution of the present invention with the embodiment one of the application.
Fig. 1 is the structural representation of the management system of the cloud computation data center that the present invention is based on load equalizer;
Fig. 2 is the structural representation of management devices of the present invention;
Fig. 3 is the processing flow chart of the management method of the cloud computation data center that the present invention is based on load equalizer;
Fig. 4 is the processing flow chart of virtual machine quantity in dynamic conditioning elastic panel nodes pond of the present invention.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly understand, hereinafter will be described in detail to embodiments of the invention by reference to the accompanying drawings.It should be noted that, when not conflicting, the embodiment in the application and the feature in embodiment can combination in any mutually.
Can perform in the computer system of such as one group of computer executable instructions in the step shown in the process flow diagram of accompanying drawing.Further, although show logical order in flow charts, in some cases, can be different from the step shown or described by order execution herein.
The design concept that the present invention is based on the management system of the cloud computation data center of load equalizer is: according to the loading condition automatic expansion virtual machine node of virtual machine or automatically reduce virtual machine node, load sharing is carried out by automatically increasing virtual machine node, the service card avoiding access storm to cause pauses, by automatically reducing the resource of virtual machine node releasing idling, reduce system resource waste, effectively solve service card that prior art exists and pause and the technical matters of the wasting of resources.
One of important feature of cloud computing is that business generally runs in virtual machine, by the development interface API that virtualization software and load equalizer provide, can obtain the ruuning situation of virtual machine very easily.Another important feature of cloud computing is in large scale, and by being distributed in different geographical, the network equipment that has Different Rule parameter and have a different performance forms.Therefore, the Managed Solution of cloud computation data center not only will consider that unified resource information is collected and scheduling, also will consider the factors such as easy expansion, easy exploiting, easy care.
Fig. 1 is the structural representation of the management system of the cloud computation data center that the present invention is based on load equalizer.As shown in Figure 1, management system of the present invention comprises management devices, load equalizer cluster and elastic panel nodes pond cluster, wherein,
Elastic panel nodes pond cluster comprises several elastic panel nodes ponds, and each elastic panel nodes pond comprises several virtual machines.In the present invention, the elastic panel nodes pond as an application is provided with a virtual IP address (service IP), makes the virtual machine in elastic panel nodes pond externally provide service by virtual IP address.
Load equalizer cluster comprises several load equalizers, and each load equalizer is connected, for providing load balancing service for connected each elastic panel nodes pond with the elastic panel nodes pond of setting quantity.Wherein, setting quantity can be 1,2 or multiple, and the api interface of load equalizer is carried out adaptation, and the management devices for upper strata provides unified calling interface.
Management devices is connected with each load equalizer in load equalizer cluster, for managing all load equalizers and elastic panel nodes pond, according to the load state in each elastic panel nodes pond, adopt the quantity of virtual machine in this elastic panel nodes pond of load balancing dynamic conditioning pre-set, realize the wasting of resources when service card of tackling more delicately when business rises suddenly and sharply pauses idle with business.
Fig. 2 is the structural representation of management devices of the present invention.As shown in Figure 2, management devices of the present invention comprises interconnective load balancing administration module and elastic panel nodes pond administration module.Wherein:
Load balancing administration module, be connected with each load equalizer in load equalizer cluster, for load equalizers all in unified management cloud data center, by invocation facility interface be each load equalizer configuration elastic panel nodes pond, and be each elastic panel nodes pond configuration virtual IP, port, agreement, algorithm etc., make user by the virtual machine in virtual IP address dynamic access elastic panel nodes pond.
Elastic panel nodes pond administration module, be connected with each load equalizer in load equalizer cluster, the load state in elastic panel nodes pond is obtained for the api interface by calling load equalizer, and according to the quantity of virtual machine in load state and load balancing dynamic conditioning elastic panel nodes pond, realize the increase of virtual machine or the minimizing of virtual machine in elastic panel nodes pond.
Further, as shown in Figure 2, load balancing administration module of the present invention comprises device management unit Sum fanction administrative unit.Wherein, device management unit is connected with each load equalizer in load equalizer cluster, for by invocation facility interface being each load equalizer configuration elastic panel nodes pond, the quantity in the elastic panel nodes pond configured by adjustment load equalizer, can realize the allotment of service resources in system level.Regulation management unit is connected with each load equalizer in load equalizer cluster, and be connected with device management unit, for being each elastic panel nodes pond configuration virtual IP, port, agreement and algorithm etc., elastic panel nodes pond for different geographical, Different Rule parameter and different performance configures different parameters, configure suitable load-balancing algorithm for multi-form and load equalizer that is different performance, realize the highly compatible of system, high applicability and high reliability.
Further, as shown in Figure 2, elastic panel nodes pond of the present invention administration module comprises load monitoring unit, node management unit, Template Manager unit and IP administrative unit.Wherein, load monitoring unit is connected with each load equalizer in load equalizer cluster, obtains the load state in elastic panel nodes pond for the api interface by calling load equalizer.Node management unit is connected with load monitoring unit, for the load state obtained according to load monitoring unit and the load balancing be stored in advance in node management unit, generate newly-increased virtual machine control command and send to Template Manager unit, or generation deletion virtual machine control command sends to IP administrative unit.Template Manager unit is connected with node management unit, for storage virtual machine mirror image template base, after the newly-increased virtual machine control command receiving node management unit transmission, select suitable server as host, from virtual machine image template base load images template to host and instantiation, generate new virtual machine, the identifier of new virtual machine is sent to IP administrative unit.IP administrative unit is connected with node management unit, for store and managerial elasticity node pool in the identifier of each virtual machine and the IP Dynamic link library of correspondence, after the deletion virtual machine control command receiving node management unit transmission, delete the idle identifier of virtual machine and the IP Dynamic link library of correspondence.In addition, IP administrative unit is also connected with Template Manager unit, after the identifier receiving the new virtual machine that Template Manager unit sends, is this new virtual machine configuration of IP Dynamic link library, and stores the identifier of this new virtual machine and the IP Dynamic link library of correspondence.Template Manager unit and IP administrative unit are connected each load equalizer in load equalizer cluster simultaneously, to realize the operation of newly-increased virtual machine and deletion virtual machine.
In the present invention, the load state in elastic panel nodes pond mainly comprises system performance situation, network performance conditions and data performance situation, reflects the load state in elastic panel nodes pond with these three kinds of status indexes.
Present system performance condition refers to the average CPU utilization of virtual machine in elastic panel nodes pond and average memory usage.This status index, for reflecting the performance load situation of VME operating system in elastic panel nodes pond, can be obtained by the api interface calling load equalizer.In practical application, average CPU utilization and average memory usage can by following formulae discovery out, and n is the quantity of virtual machine in elastic panel nodes pond.
Network performance conditions of the present invention refers to average total linking number and the average active linking number of virtual machine in elastic panel nodes pond.This status index, for reflecting the network access quantity loading condition of virtual machine in elastic panel nodes pond, can be obtained by the api interface calling load equalizer.In practical application, average total linking number and average active linking number can by following formulae discovery out, and n is the quantity of virtual machine in elastic panel nodes pond.
Data performance situation of the present invention refers to the averaging network influx of virtual machine in elastic panel nodes pond, averaging network discharge and average network traffics.This status index, for reflecting the data traffic loads situation of virtual machine in elastic panel nodes pond, can be obtained by the api interface calling load equalizer.In practical application, averaging network influx, averaging network discharge and average network traffics can by following formulae discovery out, and n is the quantity of virtual machine in elastic panel nodes pond.
In the present invention, high threshold and the Low threshold of system performance situation is set respectively, the high threshold of network performance conditions and Low threshold, and the high threshold of data performance situation and Low threshold.When in system performance situation, network performance conditions and data performance situation, any one status index is more than or equal to its high threshold, namely judge that elastic panel nodes pond is in high load condition, and when status indexes all in system performance situation, network performance conditions and data performance situation is all less than or equal to its Low threshold, just judge that elastic panel nodes pond is in low load condition.Load balancing of the present invention is: when the duration that elastic panel nodes pond is in high load condition exceedes default time threshold, increases the quantity of virtual machine in elastic panel nodes pond; When the duration that elastic panel nodes pond is in low load condition exceedes default time threshold, reduce the quantity of virtual machine in elastic panel nodes pond.Wherein, high threshold, Low threshold and time threshold can set according to the actual conditions of different business systems, the present invention is in high load condition about elastic panel nodes pond and is in the decision rule of low load condition, effectively can reduce the erroneous judgement because individual case index instability causes.In practical application, can design timed thread, the ruuning situation in periodic monitoring or acquisition elastic panel nodes pond, whole process is automatic, intelligent, without the need to human intervention.
The invention provides a kind of management system framework based on elastic panel nodes pond, by defining the concept in elastic panel nodes pond, with elastic panel nodes pond for application, the service of load equalizer is concentrated on elastic panel nodes pond, there is the advantages such as easy expansion, easy exploiting and easy care.Simultaneously, by load equalizers all in management devices unified management cloud data center, not only can merge the load-balancing device of various ways and performance, form isomery load balancing system, service resources can also be allocated in system level, there is the advantages such as highly compatible, high applicability and high reliability.Further, the load state in elastic panel nodes pond is obtained by the api interface calling load equalizer, according to the system performance situation in elastic panel nodes pond, network performance conditions and data performance situation according to the load balancing preset, the scale in automatic expansion or contraction elastic panel nodes pond, namely increase or reduce the quantity of virtual machine in elastic panel nodes pond, not only can avoid by newly-increased virtual machine the service card that access storm causes to pause, and avoid system resource waste by the virtual machine reducing the free time.Enforcement of the present invention, the service card can tackled more delicately when cloud computation data center business rises suddenly and sharply pauses, and system resource waste when significantly reducing the business free time.
On the management system technical scheme basis of the aforementioned cloud computation data center based on load equalizer, present invention also offers a kind of management method of the cloud computation data center based on load equalizer.Fig. 3 is the processing flow chart of the management method of the cloud computation data center that the present invention is based on load equalizer.As shown in Figure 3, management method of the present invention comprises:
Step 1, establishment comprise the elastic panel nodes pond cluster in several elastic panel nodes ponds, in each elastic panel nodes pond, arrange the virtual machine that several externally provide service;
Step 2, establishment comprise the load equalizer cluster of several load equalizers, and being the elastic panel nodes pond of each load equalizer configuration setting quantity, is each elastic panel nodes pond configuration virtual IP, port and protocol;
Step 3, obtain the load state in described elastic panel nodes pond, and according to described load state, adopt the quantity of virtual machine in elastic panel nodes pond described in the load balancing dynamic conditioning preset.
Fig. 4 is the processing flow chart of virtual machine quantity in dynamic conditioning elastic panel nodes pond of the present invention.As shown in Figure 4, step 3 of the present invention comprises:
Step 31, obtained the load state in described elastic panel nodes pond by the api interface calling described load equalizer;
Step 32, judge whether described elastic panel nodes pond is in high load condition, is perform step 34, otherwise perform step 33;
Step 33, judge whether described elastic panel nodes pond is in low load condition, is perform step 35, otherwise perform step 31;
Whether the duration that step 34, judgement are in high load condition exceedes default time threshold, is increase the quantity of virtual machine in described elastic panel nodes pond, performs step 31, otherwise performs step 31;
Whether the duration that step 35, judgement are in low load condition exceedes default time threshold, is reduce the quantity of virtual machine in described elastic panel nodes pond, performs step 31, otherwise performs step 31.
In preceding solution, load balancing is: when the duration that elastic panel nodes pond is in high load condition exceedes default time threshold, increases the quantity of virtual machine in elastic panel nodes pond; When the duration that elastic panel nodes pond is in low load condition exceedes default time threshold, reduce the quantity of virtual machine in elastic panel nodes pond.Wherein, elastic panel nodes pond is in high load condition and refers to, in system performance situation, network performance conditions and data performance situation, any one status index is more than or equal to its high threshold; Elastic panel nodes pond is in low load condition and refers to, status indexes all in system performance situation, network performance conditions and data performance situation is all less than or equal to its Low threshold.System performance situation refers to the average CPU utilization of virtual machine in elastic panel nodes pond and average memory usage, network performance conditions refers to average total linking number and the average active linking number of virtual machine in elastic panel nodes pond, and data performance situation refers to the averaging network influx of virtual machine in elastic panel nodes pond, averaging network discharge and average network traffics.
It is identical with the process means in aforementioned management system technical scheme with the process means reducing virtual machine quantity that the present invention increases virtual machine quantity, repeats no more.
Although the embodiment disclosed by the present invention is as above, the embodiment that described content only adopts for ease of understanding the present invention, and be not used to limit the present invention.Those of skill in the art belonging to any the present invention; under the prerequisite not departing from the spirit and scope disclosed by the present invention; any amendment and change can be carried out in the form implemented and details; but scope of patent protection of the present invention, the scope that still must define with appending claims is as the criterion.
Claims (10)
1. based on a management system for the cloud computation data center of load equalizer, it is characterized in that, comprise elastic panel nodes pond cluster, load equalizer cluster and management devices, wherein,
Elastic panel nodes pond cluster, comprises several elastic panel nodes ponds, and each elastic panel nodes pond comprises several virtual machines, and described virtual machine is used for externally providing service by virtual IP address;
Load equalizer cluster, comprises several load equalizers, and each load equalizer is connected, for providing load balancing service for connected each elastic panel nodes pond with the elastic panel nodes pond of setting quantity;
Management devices, be connected with each load equalizer in described load equalizer cluster, for load management balanced device and elastic panel nodes pond, according to the load state in each elastic panel nodes pond, adopt the quantity of virtual machine in elastic panel nodes pond described in default load balancing dynamic conditioning.
2. management system according to claim 1, is characterized in that, described management devices comprises load balancing administration module and elastic panel nodes pond administration module, wherein,
Load balancing administration module, for being each load equalizer configuration elastic panel nodes pond, is each elastic panel nodes pond configuration virtual IP, port and protocol;
Elastic panel nodes pond administration module, for obtaining the load state in described elastic panel nodes pond, and according to the quantity of virtual machine in described load state and load balancing dynamic conditioning elastic panel nodes pond.
3. management system according to claim 2, is characterized in that, described load balancing administration module comprises device management unit Sum fanction administrative unit, wherein,
Device management unit, for being each load equalizer configuration elastic panel nodes pond;
Regulation management unit, for being each elastic panel nodes pond configuration virtual IP, port and protocol.
4. management system according to claim 2, is characterized in that, described elastic panel nodes pond administration module comprises load monitoring unit, node management unit, Template Manager unit and IP administrative unit, wherein,
Load monitoring unit, obtains the load state in described elastic panel nodes pond for the api interface by calling described load equalizer;
Node management unit, for according to described load state and the load balancing preset, generates newly-increased virtual machine control command and sends to Template Manager unit, or generation deletion virtual machine control command sends to IP administrative unit;
Template Manager unit, for storage virtual machine mirror image template base, after receiving described newly-increased virtual machine control command, generates new virtual machine and the identifier of described new virtual machine is sent to IP administrative unit;
IP administrative unit, for the identifier of storage virtual machine and the IP Dynamic link library of correspondence, after receiving described deletion virtual machine control command, deletes the idle identifier of virtual machine and the IP Dynamic link library of correspondence; Also for after the identifier receiving described new virtual machine, it is this new virtual machine configuration of IP Dynamic link library.
5. according to the arbitrary described management system of Claims 1 to 4, it is characterized in that, described load balancing is: when the duration being in high load condition when described elastic panel nodes pond exceedes default time threshold, increase the quantity of virtual machine in described elastic panel nodes pond; The duration being in low load condition when described elastic panel nodes pond, when exceeding default time threshold, reduces the quantity of virtual machine in described elastic panel nodes pond.
6. management system according to claim 5, is characterized in that, described elastic panel nodes pond is in high load condition and refers to, in system performance situation, network performance conditions and data performance situation, any one status index is more than or equal to its high threshold; Described elastic panel nodes pond is in low load condition and refers to, status indexes all in system performance situation, network performance conditions and data performance situation is all less than or equal to its Low threshold.
7. management system according to claim 6, it is characterized in that, described system performance situation refers to the average CPU utilization of virtual machine in elastic panel nodes pond and average memory usage, described network performance conditions refers to average total linking number and the average active linking number of virtual machine in elastic panel nodes pond, and described data performance situation refers to the averaging network influx of virtual machine in elastic panel nodes pond, averaging network discharge and average network traffics.
8. based on a management method for the cloud computation data center of load equalizer, it is characterized in that, comprising:
Create the elastic panel nodes pond cluster comprising several elastic panel nodes ponds, the virtual machine that several externally provide service is set in each elastic panel nodes pond;
Create the load equalizer cluster comprising several load equalizers, being the elastic panel nodes pond of each load equalizer configuration setting quantity, is each elastic panel nodes pond configuration virtual IP, port and protocol;
Obtain the load state in described elastic panel nodes pond, and according to described load state, adopt the quantity of virtual machine in elastic panel nodes pond described in default load balancing dynamic conditioning.
9. management method according to claim 8, it is characterized in that, the load state in the described elastic panel nodes pond of described acquisition, and according to described load state, adopt the quantity of virtual machine in elastic panel nodes pond described in default load balancing dynamic conditioning, specifically comprise:
Step 31, obtained the load state in described elastic panel nodes pond by the api interface calling described load equalizer;
Step 32, judge whether described elastic panel nodes pond is in high load condition, is perform step 34, otherwise perform step 33;
Step 33, judge whether described elastic panel nodes pond is in low load condition, is perform step 35, otherwise perform step 31;
Whether the duration that step 34, judgement are in high load condition exceedes default time threshold, is increase the quantity of virtual machine in described elastic panel nodes pond, performs step 31, otherwise performs step 31;
Whether the duration that step 35, judgement are in low load condition exceedes default time threshold, is reduce the quantity of virtual machine in described elastic panel nodes pond, performs step 31, otherwise performs step 31.
10. management method according to claim 8 or claim 9, it is characterized in that, described load balancing is: when the duration being in high load condition when described elastic panel nodes pond exceedes default time threshold, increase the quantity of virtual machine in described elastic panel nodes pond; The duration being in low load condition when described elastic panel nodes pond, when exceeding default time threshold, reduces the quantity of virtual machine in described elastic panel nodes pond; Described elastic panel nodes pond is in high load condition and refers to, in system performance situation, network performance conditions and data performance situation, any one status index is more than or equal to its high threshold; Described elastic panel nodes pond is in low load condition and refers to, status indexes all in system performance situation, network performance conditions and data performance situation is all less than or equal to its Low threshold; Described system performance situation refers to the average CPU utilization of virtual machine in elastic panel nodes pond and average memory usage, described network performance conditions refers to average total linking number and the average active linking number of virtual machine in elastic panel nodes pond, and described data performance situation refers to the averaging network influx of virtual machine in elastic panel nodes pond, averaging network discharge and average network traffics.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510475609.9A CN105159775A (en) | 2015-08-05 | 2015-08-05 | Load balancer based management system and management method for cloud computing data center |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510475609.9A CN105159775A (en) | 2015-08-05 | 2015-08-05 | Load balancer based management system and management method for cloud computing data center |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105159775A true CN105159775A (en) | 2015-12-16 |
Family
ID=54800638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510475609.9A Pending CN105159775A (en) | 2015-08-05 | 2015-08-05 | Load balancer based management system and management method for cloud computing data center |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105159775A (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106375419A (en) * | 2016-08-31 | 2017-02-01 | 东软集团股份有限公司 | Deployment method and device of distributed cluster |
| CN106412135A (en) * | 2016-12-14 | 2017-02-15 | 国云科技股份有限公司 | Load balancing method for improving distributed object storage service capability |
| CN106533839A (en) * | 2016-11-30 | 2017-03-22 | 郑州云海信息技术有限公司 | Application node monitoring method and apparatus of hybrid cloud |
| CN106603631A (en) * | 2016-11-17 | 2017-04-26 | 北京奇艺世纪科技有限公司 | Distributed message system and expansion method thereof |
| CN106936882A (en) * | 2015-12-31 | 2017-07-07 | 深圳先进技术研究院 | A kind of electronic article transaction system |
| CN107085539A (en) * | 2017-04-27 | 2017-08-22 | 北京邮电大学 | A kind of cloud Database Systems and cloud database resource dynamic adjusting method |
| CN107273178A (en) * | 2016-04-06 | 2017-10-20 | 阿里巴巴集团控股有限公司 | The method and apparatus for configuring virtualization system |
| CN107395731A (en) * | 2017-07-28 | 2017-11-24 | 郑州云海信息技术有限公司 | A kind of adjusting method and device of the container cluster based on service orchestration |
| CN107577441A (en) * | 2017-10-17 | 2018-01-12 | 郑州云海信息技术有限公司 | A kind of OSD slow disk processing method, system, device and computer-readable storage medium |
| CN107656807A (en) * | 2016-07-26 | 2018-02-02 | 华为技术有限公司 | The automatic elastic telescopic method and device of a kind of virtual resource |
| CN107743152A (en) * | 2017-12-07 | 2018-02-27 | 南京易捷思达软件科技有限公司 | The implementation method of the High Availabitity of load equalizer in a kind of OpenStack cloud platforms |
| CN108900590A (en) * | 2018-06-20 | 2018-11-27 | 郑州云海信息技术有限公司 | A kind of distributed software construction method and device |
| CN108989442A (en) * | 2018-07-27 | 2018-12-11 | 中国联合网络通信集团有限公司 | Data distributing method, system and control node |
| CN109068285A (en) * | 2018-07-26 | 2018-12-21 | 成都鼎桥通信技术有限公司 | A kind of implementation method in cluster pond |
| CN109189329A (en) * | 2018-08-08 | 2019-01-11 | 杭州数梦工场科技有限公司 | The method of adjustment and device of memory node weight |
| CN109416650A (en) * | 2016-06-30 | 2019-03-01 | 诺基亚美国公司 | Centralized load balancer with weighted hashing function |
| CN110278257A (en) * | 2019-06-13 | 2019-09-24 | 中信银行股份有限公司 | A kind of method of mobilism configuration distributed type assemblies node label |
| CN110968419A (en) * | 2018-09-30 | 2020-04-07 | 北京国双科技有限公司 | Data receiving method and device |
| CN111182011A (en) * | 2018-11-09 | 2020-05-19 | 中移（杭州）信息技术有限公司 | Service set distribution method and device |
| CN113630383A (en) * | 2021-07-08 | 2021-11-09 | 付腾瑶 | Edge cloud cooperation method and device |
| CN115051993A (en) * | 2022-06-01 | 2022-09-13 | 上海弘积信息科技有限公司 | Elastic expansion method of service virtual machine based on MC centralized management system |
| CN115865932A (en) * | 2023-02-27 | 2023-03-28 | 天翼云科技有限公司 | Traffic scheduling method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102130938A (en) * | 2010-12-03 | 2011-07-20 | 中国科学院软件研究所 | Resource supply method oriented to Web application host platform |
| CN102143046A (en) * | 2010-08-25 | 2011-08-03 | 华为技术有限公司 | Load balancing method, equipment and system |
| CN102214117A (en) * | 2010-04-07 | 2011-10-12 | 中兴通讯股份有限公司 | Virtual machine management method, system and server |
| CN102427475A (en) * | 2011-12-08 | 2012-04-25 | 曙光信息产业(北京)有限公司 | Load balance scheduling system in cloud computing environment |
| CN104111874A (en) * | 2014-02-13 | 2014-10-22 | 西安未来国际信息股份有限公司 | High-concurrence high-reliability load balance software architecture design of virtual mainframe in cloud computing environment |
| KR20150049342A (en) * | 2013-10-30 | 2015-05-08 | 에스코어 주식회사 | High Availability Load Balancing Method and Apparatus for Cluster Expanding and Reduciing Virtual Machine Automatically |
-
2015
- 2015-08-05 CN CN201510475609.9A patent/CN105159775A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102214117A (en) * | 2010-04-07 | 2011-10-12 | 中兴通讯股份有限公司 | Virtual machine management method, system and server |
| CN102143046A (en) * | 2010-08-25 | 2011-08-03 | 华为技术有限公司 | Load balancing method, equipment and system |
| CN102130938A (en) * | 2010-12-03 | 2011-07-20 | 中国科学院软件研究所 | Resource supply method oriented to Web application host platform |
| CN102427475A (en) * | 2011-12-08 | 2012-04-25 | 曙光信息产业(北京)有限公司 | Load balance scheduling system in cloud computing environment |
| KR20150049342A (en) * | 2013-10-30 | 2015-05-08 | 에스코어 주식회사 | High Availability Load Balancing Method and Apparatus for Cluster Expanding and Reduciing Virtual Machine Automatically |
| CN104111874A (en) * | 2014-02-13 | 2014-10-22 | 西安未来国际信息股份有限公司 | High-concurrence high-reliability load balance software architecture design of virtual mainframe in cloud computing environment |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106936882A (en) * | 2015-12-31 | 2017-07-07 | 深圳先进技术研究院 | A kind of electronic article transaction system |
| CN107273178A (en) * | 2016-04-06 | 2017-10-20 | 阿里巴巴集团控股有限公司 | The method and apparatus for configuring virtualization system |
| CN107273178B (en) * | 2016-04-06 | 2021-07-27 | 阿里巴巴集团控股有限公司 | Method and device for configuring virtualization system |
| CN109416650A (en) * | 2016-06-30 | 2019-03-01 | 诺基亚美国公司 | Centralized load balancer with weighted hashing function |
| CN107656807A (en) * | 2016-07-26 | 2018-02-02 | 华为技术有限公司 | The automatic elastic telescopic method and device of a kind of virtual resource |
| CN107656807B (en) * | 2016-07-26 | 2021-06-29 | 华为技术有限公司 | Automatic elastic expansion method and device for virtual resources |
| CN106375419A (en) * | 2016-08-31 | 2017-02-01 | 东软集团股份有限公司 | Deployment method and device of distributed cluster |
| CN106603631A (en) * | 2016-11-17 | 2017-04-26 | 北京奇艺世纪科技有限公司 | Distributed message system and expansion method thereof |
| CN106533839A (en) * | 2016-11-30 | 2017-03-22 | 郑州云海信息技术有限公司 | Application node monitoring method and apparatus of hybrid cloud |
| CN106412135A (en) * | 2016-12-14 | 2017-02-15 | 国云科技股份有限公司 | Load balancing method for improving distributed object storage service capability |
| CN107085539A (en) * | 2017-04-27 | 2017-08-22 | 北京邮电大学 | A kind of cloud Database Systems and cloud database resource dynamic adjusting method |
| CN107085539B (en) * | 2017-04-27 | 2019-12-10 | 北京邮电大学 | cloud database system and dynamic cloud database resource adjustment method |
| CN107395731A (en) * | 2017-07-28 | 2017-11-24 | 郑州云海信息技术有限公司 | A kind of adjusting method and device of the container cluster based on service orchestration |
| CN107577441B (en) * | 2017-10-17 | 2020-08-21 | 苏州浪潮智能科技有限公司 | OSD slow disc processing method, system, device and computer storage medium |
| CN107577441A (en) * | 2017-10-17 | 2018-01-12 | 郑州云海信息技术有限公司 | A kind of OSD slow disk processing method, system, device and computer-readable storage medium |
| CN107743152A (en) * | 2017-12-07 | 2018-02-27 | 南京易捷思达软件科技有限公司 | The implementation method of the High Availabitity of load equalizer in a kind of OpenStack cloud platforms |
| CN108900590A (en) * | 2018-06-20 | 2018-11-27 | 郑州云海信息技术有限公司 | A kind of distributed software construction method and device |
| CN109068285A (en) * | 2018-07-26 | 2018-12-21 | 成都鼎桥通信技术有限公司 | A kind of implementation method in cluster pond |
| CN109068285B (en) * | 2018-07-26 | 2021-08-27 | 成都鼎桥通信技术有限公司 | Method for realizing cluster pool |
| CN108989442A (en) * | 2018-07-27 | 2018-12-11 | 中国联合网络通信集团有限公司 | Data distributing method, system and control node |
| CN109189329A (en) * | 2018-08-08 | 2019-01-11 | 杭州数梦工场科技有限公司 | The method of adjustment and device of memory node weight |
| CN110968419A (en) * | 2018-09-30 | 2020-04-07 | 北京国双科技有限公司 | Data receiving method and device |
| CN111182011B (en) * | 2018-11-09 | 2022-06-10 | 中移（杭州）信息技术有限公司 | Service set distribution method and device |
| CN111182011A (en) * | 2018-11-09 | 2020-05-19 | 中移（杭州）信息技术有限公司 | Service set distribution method and device |
| CN110278257A (en) * | 2019-06-13 | 2019-09-24 | 中信银行股份有限公司 | A kind of method of mobilism configuration distributed type assemblies node label |
| CN113630383A (en) * | 2021-07-08 | 2021-11-09 | 付腾瑶 | Edge cloud cooperation method and device |
| CN113630383B (en) * | 2021-07-08 | 2023-03-28 | 杨妍茜 | Edge cloud cooperation method and device |
| CN115051993A (en) * | 2022-06-01 | 2022-09-13 | 上海弘积信息科技有限公司 | Elastic expansion method of service virtual machine based on MC centralized management system |
| CN115865932A (en) * | 2023-02-27 | 2023-03-28 | 天翼云科技有限公司 | Traffic scheduling method and device, electronic equipment and storage medium |
| CN115865932B (en) * | 2023-02-27 | 2023-06-23 | 天翼云科技有限公司 | Traffic scheduling method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105159775A (en) | Load balancer based management system and management method for cloud computing data center | |
| CN108965485B (en) | Container resource management method and device and cloud platform | |
| US9158586B2 (en) | Systems and methods for managing cloud computing resources | |
| CN102137014B (en) | Resource management method, system and resource manager | |
| US10129101B2 (en) | Application driven and adaptive unified resource management for data centers with Multi-Resource Schedulable Unit (MRSU) | |
| CN103051564B (en) | The method and apparatus of dynamic resource allocation | |
| KR100956636B1 (en) | System and method for service level management in virtualized server environment | |
| US20150200867A1 (en) | Task scheduling using virtual clusters | |
| CN105335229B (en) | Scheduling method and device of service resources | |
| CN110221920B (en) | Deployment method, device, storage medium and system | |
| CN103533063A (en) | Method and device capable of realizing dynamic expansion of WEB (World Wide Web) application resource | |
| KR20170056350A (en) | NFV(Network Function Virtualization) resource requirement verifier | |
| CN104679594B (en) | A kind of middleware distributed computing method | |
| CN105024842A (en) | Method and device for capacity expansion of server | |
| Wang et al. | Bandwidth guaranteed virtual network function placement and scaling in datacenter networks | |
| CN104092756A (en) | Cloud storage system resource dynamic allocation method based on DHT mechanism | |
| CN111092921B (en) | Data acquisition method, device and storage medium | |
| CN104917805A (en) | Load sharing method and equipment | |
| CN105046393B (en) | Traffic resource management system based on cloud computing | |
| Vijayalakshmi et al. | Investigations on job scheduling algorithms in cloud computing | |
| CN112822062A (en) | Management method for desktop cloud service platform | |
| Yu et al. | Towards predictable performance via two-layer bandwidth allocation in cloud datacenter | |
| CN112468458B (en) | Scheduling method based on neutron layering mechanism | |
| CN112073223B (en) | System and method for managing and controlling operation of cloud computing terminal and cloud server | |
| CN114675972A (en) | Method and system for flexibly scheduling cloud network resources based on integral algorithm |
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 |
Application publication date: 20151216 |
|
| RJ01 | Rejection of invention patent application after publication |