WO2014119719A1 - リソース制御システム、制御パターン生成装置、制御装置、リソース制御方法及びプログラム - Google Patents
リソース制御システム、制御パターン生成装置、制御装置、リソース制御方法及びプログラム Download PDFInfo
- Publication number
- WO2014119719A1 WO2014119719A1 PCT/JP2014/052239 JP2014052239W WO2014119719A1 WO 2014119719 A1 WO2014119719 A1 WO 2014119719A1 JP 2014052239 W JP2014052239 W JP 2014052239W WO 2014119719 A1 WO2014119719 A1 WO 2014119719A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- control
- resource
- virtual
- virtual system
- control pattern
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 23
- 238000013468 resource allocation Methods 0.000 claims abstract description 87
- 230000008859 change Effects 0.000 claims abstract description 83
- 238000012545 processing Methods 0.000 claims description 35
- 238000004088 simulation Methods 0.000 claims description 31
- 238000011156 evaluation Methods 0.000 claims description 16
- 238000009795 derivation Methods 0.000 claims description 13
- 238000005259 measurement Methods 0.000 claims description 2
- 238000003860 storage Methods 0.000 description 61
- 238000012544 monitoring process Methods 0.000 description 26
- 238000007726 management method Methods 0.000 description 16
- 238000004891 communication Methods 0.000 description 14
- 239000000284 extract Substances 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 238000012546 transfer Methods 0.000 description 8
- 230000006399 behavior Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 3
- 238000000491 multivariate analysis Methods 0.000 description 3
- 230000007704 transition Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized resources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3447—Performance evaluation by modeling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3457—Performance evaluation by simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/83—Admission control; Resource allocation based on usage prediction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/45595—Network integration; Enabling network access in virtual machine instances
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
Definitions
- the present invention is based on a Japanese patent application: Japanese Patent Application No. 2013-018202 (filed on Feb. 1, 2013), and the entire description of the application is incorporated herein by reference.
- the present invention relates to a resource control system, a control pattern generation device, a control device, a resource control method, and a program, and in particular, a resource control system, a control pattern generation device that controls resources allocated to a virtual system operating on a virtual data center,
- the present invention relates to a control device, a resource control method, and a program.
- vDC virtual data centers
- Various virtual systems such as Web servers and video distribution are operating on the vDC.
- the priority corresponding to each service assigned to each resource node is set in association with each resource node, and each processing time of each service by each resource node is set according to the passage of the processing time of each service.
- the priority set for the resource node is updated to a higher priority, and there is no empty resource node to which a new service is assigned, the first resource node to which the service has already been assigned and the second resource node to which the service has already been assigned Among resource nodes, a resource brokering system is disclosed in which a service assigned to a resource node with a lower updated priority is switched to the new service.
- Patent Document 2 discloses a communication service control system that realizes multi-classization of communication service quality levels by differentiating service levels by combining transfer priorities and call loss rates. According to the same document, this communication service control system is associated with transfer control means for controlling information transfer in the network based on transfer priority, and a plurality of predetermined communication service use request reception priorities. , A resource management unit that stores a threshold value of the resource amount that increases as the reception priority increases in a storage device, and, if there is a use request for the communication service, a requested resource use amount and a link that is used for the communication service.
- This communication service control system changes the communication quality level of the communication service with the same transfer priority by changing the reference of the remaining resource amount that can be accepted according to the reception priority for the communication service with the same transfer priority. It is described that the communication service is provided at a plurality of communication quality levels by combining the transfer control based on the transfer priority and the reception control based on the reception priority by differentiating.
- Patent Document 3 discloses a distributed workflow simulation system capable of realizing a simulation considering the influence of resource sharing in a distributed workflow system in which a business process flow is performed by a plurality of workflow execution devices.
- Non-Patent Documents 1 and 2 introduce a technique called OpenFlow that enables dynamic control of network resources.
- control is required to minimize the resource consumption while maintaining the performance service level.
- it is required to determine when and how much to allocate server resources and network resources and reflect the determination results.
- Patent Documents 1 and 2 described above have a problem that there is no guarantee that a desired result can be obtained even when applied to resource allocation of a virtual system on a vDC.
- the resource brokering system of Patent Document 1 it is possible to allocate resource nodes, but network resources are not considered.
- network resources can be optimized, but server resources are not considered.
- An object of the present invention is to provide a resource control system, a control pattern generation device, a control device, a resource control method, and a program that can contribute to the efficient allocation of resources to a virtual system operating on a virtual data center.
- a virtual system model generated by modeling the behavior of a network element and a server of a virtual system operating on a virtual data center, and a resource allocation change policy for the virtual system are defined.
- Control pattern generation means for generating a plurality of control patterns that are candidates for control instructions for the network resources and server resources of the virtual system from the resource allocation change policy, and service level prediction using the plurality of control patterns
- control means for selecting and applying a control pattern that satisfies the service level of the virtual system and satisfies a predetermined selection criterion from the plurality of control patterns based on the prediction result.
- a resource control system is provided.
- a virtual system model generated by modeling the behavior of a network element of a virtual system operating on a virtual data center and a server, and a policy for changing a resource allocation to the virtual system are defined.
- a control pattern generation apparatus is provided that generates a plurality of control patterns that are candidates for control instructions for network resources and server resources of the virtual system from a resource allocation change policy.
- service level prediction is performed using a plurality of control patterns that are candidates for control instructions for network resources and server resources of a virtual system, and the plurality of controls are performed based on the prediction result.
- a control device is provided that selects and applies a control pattern that satisfies the service level of the virtual system and satisfies a predetermined selection criterion from among the patterns.
- a virtual system model generated by modeling the behavior of a network element of a virtual system operating on a virtual data center and a server, and a policy for changing a resource allocation to the virtual system are defined.
- a resource control method comprising: selecting and applying a control pattern satisfying a service level of the virtual system and satisfying a predetermined selection criterion from the plurality of control patterns based on a prediction result. Is done.
- This method is linked to a specific machine called a resource control system that controls resources allocated to a virtual system operating on a virtual data center.
- a virtual system model generated by modeling behavior of a network element of a virtual system operating on a virtual data center and a server on a computer constituting a resource control apparatus, and A process for generating a plurality of control patterns that are candidates for control instructions for the network resources and server resources of the virtual system from a resource allocation change policy that defines a resource allocation change policy, and using the plurality of control patterns
- a program for executing the above is provided.
- This program can be recorded on a computer-readable (non-transient) storage medium. That is, the present invention can be embodied as a computer program product.
- FIG. 9 is an example of configuration information corresponding to the virtual system of FIG. 8.
- FIG. It is a figure which shows an example of the prediction formula which the resource control system of the 1st Embodiment of this invention produces
- FIG. 17 is a continuation diagram of FIG. 16. It is the figure which represented the control pattern of FIG.16 and FIG.17 with the graph. It is a figure which shows another example of a resource allocation change policy. It is a figure which shows another example of a resource allocation change policy.
- FIG. 18 is a diagram illustrating an example of a simulation result using the control patterns of FIGS. 14 and 16 to 17.
- FIG. 25 is a diagram showing resource allocation change policy candidates applicable to the virtual system of FIG. 24. It is a figure for demonstrating the simulation result by the control pattern produced
- control pattern generating means 11 for generating a plurality of control patterns that are candidates for control instructions for network resources and server resources of the virtual system, And a control means 12 for controlling the virtual system using the control pattern selected from the above.
- control pattern generation unit 11 generates a virtual system model generated by modeling the behavior of a network element of a virtual system operating on a virtual data center and a server, and allocation of resources to the virtual system.
- a plurality of control patterns that are candidates for control instructions for the network resources and server resources of the virtual system are generated from the resource allocation change policy that defines the change policy.
- the control unit 12 performs service level prediction using the plurality of control patterns, and satisfies the service level of the virtual system from the plurality of control patterns based on the prediction result, and a predetermined level Select and apply a control pattern that meets the criteria.
- the resource usage of the virtual system can be minimized. This makes it possible to increase resources that can be allocated to other virtual data centers (vDCs) and other virtual systems.
- vDCs virtual data centers
- the predetermined standard is not limited to selecting the one with the smallest resource consumption.
- a control pattern that reduces the resource consumption of the server resource or the network resource with the higher priority may be selected.
- a control pattern suitable for the predicted situation at a future time point may be selected in consideration of statistically obtained service demand and network traffic.
- network resources and server resources can be optimally allocated. Further, according to the present embodiment, it is possible to reduce the operating cost of the virtual system on the virtual data center (vDC). The reason is that the amount of server resources and network resources allocated can be automatically controlled, so that the operation amount of the operator can be reduced.
- vDC virtual data center
- FIG. 2 is a diagram illustrating a system configuration according to the first embodiment of this invention.
- a plurality of virtual data centers 400 coexisting on a cloud platform, a virtual resource management apparatus 300 that allocates resources to a virtual system on the virtual data center 400, and a resource control system 100 are connected via a network.
- the connected configuration is shown.
- FIG. 3 is a functional block diagram showing a detailed configuration of the first embodiment of the present invention.
- the virtual data center (vDC) 400 provides a virtual system composed of virtual appliances and virtual servers to a plurality of virtual data center users.
- FIG. 4 is an example of a virtual system that the virtual data center (vDC) 400 provides to the virtual data center user.
- a firewall that controls communication between the Internet and a virtual system, a load balancer that distributes access from the Internet side to a plurality of Web servers, and an application server that provides services in response to requests from the Web servers.
- DB server database server
- these devices do not need to be configured with physically independent devices, but are configured with virtual entities.
- a Web server an application server, and a DB server (database server)
- virtual servers based on server virtualization technology can be used.
- a firewall or load balancer can be realized by using Non-Patent Documents 1 and 2 to cause a specific switch to behave in the same manner as a firewall or load balancer.
- the virtual resource management device 300 is a device that manages the amount of resources allocated to the virtual system on the virtual data center 400 and provides a function for monitoring the usage status of the virtual system.
- the virtual resource management device 300 includes a virtual server resource management unit 301 that manages virtual server resources such as the Web server, application server, and DB server, and a virtual network resource management unit 302 that manages network resources.
- a virtual data center (vDC) monitoring unit 303 that outputs a usage status of the virtual system to the vDC monitoring information storage device 304 at a predetermined time interval and provides a monitoring function of the virtual system.
- vDC virtual data center
- the resource control system 100 includes a control pattern generation unit 110 and an autonomous control unit 120, and generates a control pattern that is a candidate for a control instruction and selects a control pattern that matches the operating status of the virtual system to manage virtual resources. Provides the ability to change resource allocation through the device.
- the vDC configuration storage device 201 stores configuration information (see, for example, FIG. 7 and FIG. 8) of a virtual system operating on a virtual data center (vDC) that is a control target of the resource control system 100.
- the resource allocation change policy storage device 203 stores a resource allocation change policy applicable to the constituent components of the virtual system (see, for example, FIGS. 13, 15, and 16). It is assumed that the resource allocation change policy is set with a resource consumption value obtained by quantifying the additional resource amount required for each control (see, for example, the resource consumption field in FIG. 14).
- the control pattern generation unit 110 includes a prediction formula generation unit 111, a model generation unit 112, and a control pattern derivation unit 113.
- the prediction formula generation unit 111 extracts component information to be predicted such as virtual appliances and virtual servers of the virtual system from the configuration information of the virtual system stored in the vDC configuration storage device 201, and changes the amount of resources allocated to each component A prediction formula for obtaining the processing time is generated.
- Such a prediction formula can be generated, for example, using multivariate analysis based on the processing time per unit request of each virtual appliance or virtual server, monitoring information on the allocated resource amount, and the like. Then, the processing time can be obtained as a prediction result by inputting the number of simultaneous processing requests expected at the prediction time point and the allocated resource amount to the prediction formula.
- the model generation unit 112 abstracts the behavior of the virtual system operating in the virtual data center (vDC) by synthesizing a prediction formula with the configuration information of the virtual system stored in the vDC configuration storage device 201. Generate a model.
- the control pattern derivation unit 113 selects a resource allocation change policy applicable to the virtual system model, and generates a plurality of control patterns that are candidates for control instruction contents by combining the resource allocation change policies.
- the control pattern derivation unit 113 stores the generated control pattern in the control pattern storage unit 101.
- the autonomous control unit 120 includes a simulation execution unit 121, a control pattern evaluation unit 122, and a control pattern application unit 123.
- the simulation execution unit 121 extracts the control pattern of the virtual system to be simulated from the control pattern storage unit 101, inputs the contents of the vDC monitoring information, simulates the behavior of each control pattern, and predicts the average processing time. .
- the simulated result is stored in the simulation result storage unit 124.
- the control pattern evaluation unit 122 selects a control pattern to be applied from among the control patterns predicted by the simulation execution unit 121 using a predetermined control pattern selection rule.
- a control pattern selection rule for selecting a control pattern that satisfies the service level stored in the service level storage unit 202 and that has the minimum resource consumption is set for the average processing time.
- the result of evaluation by the control pattern evaluation unit 122 is stored in the evaluated control pattern storage unit 125.
- the control pattern application unit 123 changes the resource allocation by decomposing the control pattern selected by the control pattern evaluation unit 122 into a server resource control instruction and a network resource control instruction and notifying the virtual resource management apparatus 300 of the control pattern.
- each unit (processing means) of the resource control device shown in FIG. 1 can also be realized by a computer program that causes a computer constituting the resource control device to execute each of the above-described processes using its hardware.
- the component indicated as “means” can also be indicated as “part” or “unit”, and each represents a unit of a component or a component of a system by hardware or a computer program. Is.
- FIG. 5 is a flowchart illustrating the operation (control pattern generation processing) of the resource control system according to the first embodiment of this invention.
- the prediction formula generation unit 111 of the control pattern generation unit 110 receives, from the vDC configuration storage device 201, virtual server and virtual appliance information that configures a virtual system that operates on a virtual data center (vDC).
- the prediction formula for obtaining the processing time is generated for each of the virtual server and the virtual appliance (loop of steps A1 to A4).
- the prediction formula generation unit 111 extracts the monitoring information of the target virtual system from the vDC monitoring information storage device 304, the processing time for each request to the virtual server or virtual appliance for which the prediction formula is created, and the time Get the average number of requests in Further, the prediction formula generation unit 111 acquires the number of CPU cores, the amount of memory resources, and the like assigned to the virtual server or virtual appliance for which the prediction formula is to be created from the vDC configuration storage device 201 (step A2).
- the prediction formula generation unit 111 formulates the relationship between the processing time for each request, the average number of simultaneous requests within that time, and the resource amount, and stores the relationship in the prediction formula storage unit 114 as a prediction formula (step A3).
- T the processing time of the virtual server or virtual appliance for which the prediction formula is to be created
- M the average number of simultaneous requests
- ⁇ and ⁇ are the coefficients and constants from the formulation
- the model generation unit 112 uses the virtual system configuration information extracted from the vDC configuration storage device 201 and the prediction formula described above to generate a virtual system model for each virtual system for which a virtual system model is to be generated. Generate (loop of steps A5 to A7).
- the model generation unit 112 generates a virtual system model by taking out the prediction formula from the prediction formula storage unit 114 and adding it to the configuration information of the virtual system that is a generation target of the virtual system model. Store in the means 115 (step A6).
- control pattern derivation unit 113 collates the virtual system model extracted from the model storage unit 115 with the resource allocation change policy describing the resource allocation change method extracted from the resource allocation change policy storage unit 203, and A resource allocation change policy applicable to the virtual system is selected (loop of steps A8 to A10).
- control pattern derivation unit 113 pattern matches the resource allocation change policy to the virtual system model extracted from the model storage unit 115, and selects a suitable resource allocation change policy (step A9).
- control pattern derivation unit 113 combines the applicable resource allocation change policies with respect to the virtual system model extracted from the model storage unit 115, and generates a control pattern that is a candidate for the control instruction content for the corresponding system.
- Stored in the control pattern storage means 101 (loop of steps A11 to A13).
- the control pattern stored in the control pattern storage unit 101 also stores the resource consumption of each control pattern in association with it. In this embodiment, the sum of the resource consumptions of the combined resource allocation change policy is used as the resource consumption of the control pattern.
- FIG. 6 is a flowchart illustrating the operation (autonomous control) of the resource control system according to the first embodiment of this invention.
- the simulation execution unit 121 of the autonomous control unit 120 reads out a set of control patterns related to a virtual system operating on a certain virtual data center (vDC) from the control pattern storage unit 101, and further, vDC
- the latest monitoring information of the virtual system is taken out from the monitoring information storage device 304, all control patterns are simulated, the average processing time for each control pattern is predicted, and stored in the simulation result storage means 124 (step B1). .
- control pattern evaluation unit 122 extracts the simulation result from the simulation result storage unit 124, further extracts the service level designation of the virtual system from the service level storage unit 202, and determines whether the average processing time is equal to or less than the service level. (Step B2).
- the control pattern evaluation unit 122 excludes the control pattern from the application candidates (Step B3).
- the control pattern evaluation unit 122 compares the control patterns whose average processing time is equal to or lower than the service level, selects, for example, the control pattern with the minimum resource consumption, and stores it in the evaluated control pattern storage unit 125 (step B4). ). As a result, a control pattern suitable for the most recent operation status of the virtual system is selected.
- control pattern application unit 123 takes out the selected control pattern from the control pattern storage unit 101 based on the information in the evaluated control pattern storage unit 125. Then, the control pattern application unit 123 decomposes the control pattern into a server resource control instruction and a network resource control instruction, and sends a control instruction to the virtual server resource management unit 301 and the virtual network resource management unit 302 of the virtual resource management apparatus 300. put out. Thereby, the resource allocation of the virtual system on the virtual data center (vDC) is changed.
- vDC virtual data center
- the autonomous control unit 120 is configured to select and apply an optimal control pattern according to the most recent operation status of the virtual system on the virtual data center (vDC). Therefore, the resource allocation of the virtual system is optimized.
- a virtual system including a virtual appliance such as a firewall, a load balancer, a Web server, an application server, and a DB server and a virtual server is operating on a virtual data center (vDC).
- vDC virtual data center
- the virtual appliance refers to a virtual machine that operates as a network appliance such as a firewall or a load balancer.
- the operating status of this system is monitored for each component by the vDC monitoring means 303 and stored in the vDC monitoring information storage device 304.
- FIG. 7 is a diagram illustrating an example of monitoring information stored in the vDC monitoring information storage device 304.
- vDCID virtual data center ID
- FW 1 firewall
- this virtual system when using modeling techniques represented by Petri Net, is represented by a directed bipartite graph in which components are represented by transitions and the messages they have are represented by places (circular) as shown in FIG. it can.
- the vDC configuration storage device 201 may store configuration information equivalent to this directed bipartite graph.
- FIG. 9 shows virtual system configuration information stored in the vDC configuration storage device 201.
- the components of the virtual system of the virtual data center (vDC) are described as transitions, and then information indicating these linkages (connection relationships) is stored.
- the prediction formula generation unit 111 of the control pattern generation unit 110 extracts the configuration information of the virtual system illustrated in FIG. 9 from the vDC configuration storage device 201.
- the prediction formula generation unit 111 extracts the monitoring information of the corresponding component from the vDC monitoring information storage device 304 using the virtual server / virtual appliance name (eg, FW1, Web1) described as the transition in the key as a key. , Get the request processing time for these components and the average number of requests in that time.
- the prediction formula generation unit 111 acquires the allocated resource amount such as the number of CPU cores and the memory amount allocated to the virtual server / virtual appliance from the vDC configuration storage device 201. Then, using multivariate analysis, the relationship between the processing time for each request, the average number of simultaneous requests within that time, and the resource amount is formulated as a prediction formula.
- FIG. 10 is an example of a prediction formula generated by the prediction formula generation unit 111 and stored in the prediction formula storage unit 114.
- the following prediction formula is generated for the Web server “Web1”.
- T_web1 ⁇ 3 * X_p04 / ( ⁇ 3 * cpu3 + ⁇ 3 * ram3) + ⁇ 3
- X_p04 is the number of simultaneous requests in Web1
- cpu3 is the number of allocated virtual CPU cores
- ram3 is a parameter indicating the allocated amount of RAM memory.
- ⁇ 3, ⁇ 3, ⁇ 3, and ⁇ 3 are coefficients and intercepts obtained by multivariate analysis. Note that components such as the Web server “Web1” may receive different types of requests. In this case, the processing time of these requests may be calculated separately to generate a prediction formula that performs weighted averaging, etc., or different types but no difference in processing time may be treated as the same type of request .
- the model generation unit 112 generates a virtual system model by adding the prediction formula extracted from the prediction formula storage unit 114 to the configuration information of the virtual system as illustrated in FIG. 9 from the vDC configuration storage device 201. Store in the storage means 115.
- FIG. 11 is an example of a virtual system model generated by the model generation unit 112 and stored in the model storage unit 115.
- prediction formulas are added to the respective components of the configuration information of the virtual system as shown in FIG.
- control pattern derivation unit 113 collates the virtual system model shown in FIG. 11 with the resource allocation change policy, and extracts a resource allocation change policy applicable to the virtual system model.
- FIG. 12 is a diagram showing a resource allocation change policy applicable to the load balancer on the virtual system in the same manner as the above Petri Net.
- the resource allocation change policy A in FIG. 12 indicates a resource allocation change policy for switching a certain load balancer to one flow controller (FC1) and two load balancers.
- a resource allocation change policy B in FIG. 12 indicates a resource allocation change policy for adding resources (the number of CPU cores and memory) to a certain load balancer.
- FIG. 13 is a diagram showing a resource allocation change policy equivalent to the resource allocation change policy shown in FIG.
- resource consumption when each resource allocation change policy of FIG. 12 is adopted in addition to the policy ID and policy name, resource consumption when each resource allocation change policy of FIG. 12 is adopted, application pattern information used for matching with the virtual system, and resource allocation change policy An entry is shown in association with the detailed contents of.
- the control pattern derivation unit 113 generates a control pattern by combining the resource allocation change policies obtained as described above.
- FIG. 14 shows an example in which only the resource allocation change policy A (load balancer switching) shown in FIGS. 12 and 13 is applied to the virtual system model shown in FIG.
- FIG. 15 is a graph equivalent to FIG.
- FIGS. 16 and 17 show the resource allocation change policy A (load balancer switching) and the resource allocation change policy B (DB server resource addition) shown in FIGS. 12 and 13 in the virtual system model shown in FIG. This is an example in which both are applied.
- FIG. 18 is a graph equivalent to FIGS. 16 and 17. In the example of FIG. 16, both resource allocation change policy A (load balancer switching) and resource allocation change policy B (DB server resource addition) are applied. It becomes the sum of the resource consumption of the policy and becomes “6”.
- control pattern derivation unit 113 creates a control pattern in which only the resource allocation change policy B (addition of DB server resource) of FIGS. 12 and 13 is applied to the virtual system model shown in FIG.
- FIG. 19 shows a resource allocation change policy for adding a clone to one component and performing scale-out, and a resource allocation change policy for adding a resource to one component, as in FIG.
- the upper part of FIG. 20 shows a resource allocation change policy that not only adds clones to one component, but also adds a flow controller to execute path control.
- the lower part of FIG. 20 shows a resource allocation change policy in which a flow controller is added to the preceding part of one component and flow control is also executed.
- the control pattern derivation unit 113 generates a control pattern by combining such resource allocation change policies.
- the simulation execution means 121 of the autonomous control means 120 reads a set of control patterns of the virtual system to be autonomously controlled as shown in FIGS. 14 and 17 from the control pattern storage means 101. Further, the simulation execution unit 121 extracts from the vDC monitoring information storage device 304 the monitoring information of the firewall part that is input to the most recent (for example, 30 minutes) virtual system from the monitoring information of the corresponding virtual system. Input to the control pattern to predict the average processing time of each control pattern.
- FIG. 21 shows simulation execution results of the control patterns of FIGS. 14 and 16 to 17 by the simulation execution means 121.
- the control pattern evaluation unit 122 extracts the simulation result from the simulation result storage unit 124, further extracts the service level designation of the virtual system as shown in FIG. 22 from the service level storage unit 202, and predicts when each control pattern is adopted. It is determined whether the average processing time is less than the service level.
- control pattern evaluation unit 122 excludes the control pattern from the application candidates. Then, the control pattern evaluation unit 122 compares the control patterns whose average processing time is equal to or lower than the service level, and selects the control pattern with the minimum resource consumption.
- control pattern evaluation unit 122 compares the simulation execution results of FIG. 21 and selects a control pattern with a control pattern ID with a resource consumption of Pattren1.
- FIG. 23 is an example of evaluated control pattern information stored in the evaluated control pattern storage unit 125.
- the control pattern application unit 123 extracts a control pattern corresponding to the evaluated control pattern information from the control pattern storage unit 101, and gives a control instruction to the virtual server resource management unit 301 and the virtual network resource management unit 302 of the virtual resource management apparatus 300. put out.
- the virtual system to which resources are allocated as shown in FIG. 8 is switched to resource allocation as shown in FIG.
- the resource allocation after the change is selected based on the result predicted by the simulation execution unit 121, the service level required for the corresponding virtual system is satisfied and the resource consumption is minimized. It is supposed to be.
- FIG. 24 is a diagram represented by a directed bipartite graph of a certain virtual system.
- FIG. 25 is an example of a resource allocation change policy applicable to the virtual system.
- Candidate 1 is an example of a resource allocation change policy for adding a load balancer and a clone Web server to a Web server in a virtual system.
- Candidate 2 is an example of a resource allocation change policy that enhances the performance of the Web server in the virtual system.
- Candidate 3 is an example of a resource allocation change policy that places a flow controller in front of a Web server in a virtual system and limits the number of connections.
- the upper part of FIG. 26 shows a result of predicting the service level by the simulation execution unit 121 by applying a control pattern generated by using each candidate one by one. For example, when 5 (seconds) is set as the service level, candidate 3 is a control pattern that cannot satisfy the service level, and thus is excluded from the adoption target. Then, the control pattern evaluation unit 122 compares candidate 1 and candidate 2 and selects candidate 2 with a small amount of resource consumption. As a result, the virtual system to which resources are allocated as shown in FIG. 24 is switched to resource allocation (enhancement of Web server performance) as shown in the lower part of FIG.
- the control pattern having the minimum resource consumption is selected from among the control patterns satisfying the service level.
- the control pattern may be selected based on other criteria. For example, even if the resource consumption is a minimum control pattern, if the predicted service level is very close to the requested service level, the control pattern can be prevented from being selected. In this way, it is possible to select a control pattern that can satisfy the service level even when the number of requests increases from the latest monitoring value.
- control pattern selection criteria such as selecting the control pattern that increases the server resource by “2” are also available. It can be adopted. Also, for example, if there is a control pattern that increases the resource consumption by “3” and a control pattern that increases the resource consumption by “2”, even if the resource consumption is larger, the consumption of network resources It is also possible to employ a control pattern selection criterion such as selecting a control pattern that does not increase the control pattern.
- the simulation is performed using the latest monitoring information as an input value.
- a more accurate simulation is performed using statistical information and various correction values. You can also.
- the example of using the resource allocation change policy that changes in the direction of increasing the resource allocation has been described, but the resource allocation change policy that changes in the direction of decreasing the resource allocation is used. You can also.
- the graph shown on the right side of FIG. 12 is the application pattern, and the graph on the left side of FIG. 12 is the resource allocation change policy.
- the resource consumption amount has a negative value.
- the control pattern generation means creates a plurality of control patterns for each of the virtual systems of a plurality of virtual data centers living on the cloud platform,
- the control means is a resource control system that selects and applies a control pattern to a virtual system in each virtual data center.
- the predetermined control criterion is a resource control system that is a criterion for selecting a control pattern with a small amount of resource consumption among a plurality of control patterns satisfying the service level.
- the predetermined selection criterion is a resource control that is a criterion for selecting a control pattern having a lower resource consumption amount of a higher priority of a server resource or a network resource among a plurality of control patterns satisfying the service level. system.
- the control pattern generation means includes Processing time when the allocated resource is changed based on the allocated resource amount and the measurement result of the processing time based on the allocated resource amount for each of the network elements and servers of the virtual system operating on the virtual data center.
- Prediction formula generating means for generating a prediction formula for predicting Virtual system model generation means for generating the virtual system model using configuration information of a virtual system operating on the virtual data center and a prediction expression generated by the prediction expression generation means;
- Control pattern derivation means for generating the control pattern by combining resource allocation change policies applicable to the configuration included in the virtual system model generated by the virtual system model generation means; Including resource control system.
- the control means includes Simulation execution means for executing a simulation for predicting a service level using the plurality of control patterns; Based on the simulation result, a control pattern evaluation unit that selects a control pattern that satisfies the service level of the virtual system and the resource consumption satisfies the predetermined selection criteria; Control pattern application means for changing the allocation of network resources and server resources according to the selected control pattern; Including resource control system.
- a resource control system, wherein the resource allocation change policy includes a resource allocation change policy for performing path control and flow rate control.
- Control pattern generation unit 11 Control pattern storage unit 112
- Model generation unit 113 Control pattern derivation unit 114
- Model storage unit 120
- Autonomous control unit 121
- Simulation execution unit 122
- control pattern evaluation unit 123
- control pattern application unit 124
- simulation result storage unit 125
- evaluated control pattern storage unit 201 virtual data center (vDC) configuration storage unit 202 service level storage unit 203
- resource allocation change policy storage unit 300
- Virtual server resource management means 302
- Virtual network resource management means 303
- Virtual data center (vDC) monitoring means Virtual data center (v C) monitoring information storage unit 400 virtual data center (vDC)
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer And Data Communications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
Description
本発明は、日本国特許出願:特願2013-018202号(2013年2月1日出願)に基づくものであり、同出願の全記載内容は引用をもって本書に組み込み記載されているものとする。
本発明は、リソース制御システム、制御パターン生成装置、制御装置、リソース制御方法及びプログラムに関し、特に、仮想データセンタ上で動作する仮想システムに割り当てるリソースの制御を行うリソース制御システム、制御パターン生成装置、制御装置、リソース制御方法及びプログラムに関する。
続いて、本発明の第1の実施形態について図面を参照して詳細に説明する。図2は、本発明の第1の実施形態のシステム構成を示す図である。図2を参照すると、クラウドプラットフォーム上に同居する複数の仮想データセンタ400と、仮想データセンタ400上の仮想システムにリソースを割り当てる仮想リソース管理装置300と、リソース制御システム100と、をネットワークを介して接続した構成が示されている。
図5は、本発明の第1の実施形態のリソース制御システムの動作(制御パターン生成処理)を示す流れ図である。図5を参照すると、まず、制御パターン生成手段110の予測式生成手段111は、vDC構成記憶装置201より、仮想データセンタ(vDC)上で稼働する仮想システムを構成する仮想サーバ及び仮想アプライアンス情報を取り出し、仮想サーバ及び仮想アプライアンスそれぞれについて、処理時間を求めるための予測式を生成する(ステップA1~A4のループ)。
T=γM+δ
図6は、本発明の第1の実施形態のリソース制御システムの動作(自律制御)を示す流れ図である。図6を参照すると、まず、自律制御手段120のシミュレーション実行手段121は、制御パターン記憶手段101から、ある仮想データセンタ(vDC)上で稼働する仮想システムに関する制御パターンの集合を読み出し、さらに、vDCモニタリング情報記憶装置304より、当該仮想システムの直近のモニタリング情報を取り出し、すべての制御パターンをシミュレートして制御パターン毎の平均処理時間を予測し、シミュレーション結果記憶手段124に格納する(ステップB1)。
以上の前提を元に、先の制御パターン生成処理について説明する。まず、制御パターン生成手段110の予測式生成手段111は、vDC構成記憶装置201より、図9に示す仮想システムの構成情報を取り出す。次に、予測式生成手段111は、その中でトランジションとして記述された仮想サーバ・仮想アプライアンス名(例:FW1、Web1)をキーとして、vDCモニタリング情報記憶装置304から該当するコンポーネントのモニタリング情報を取り出し、これらコンポーネントのリクエストの処理時間と、その時間内の平均リクエスト数を得る。さらに、予測式生成手段111は、vDC構成記憶装置201より、仮想サーバ・仮想アプライアンスに割り当てられたCPUコア数やメモリ量等の割当済みリソース量を取得する。そして、多変量解析を用いて、リクエスト毎の処理時間と、その時間内の平均同時リクエスト数及びリソース量の関係を予測式として定式化する。
T_web1=α3*X_p04/(γ3*cpu3+δ3*ram3)+β3
ここで、X_p04はWeb1における同時リクエスト数、cpu3は割り当てられた仮想CPUコア数、ram3は、割り当てられたRAMメモリ量を示すパラメータである。また、α3、γ3、δ3、β3は、多変量解析により求められた係数と切片である。なお、Webサーバ“Web1”等のコンポーネントが、種類の異なるリクエストを受ける場合がある。この場合、これらのリクエストの処理時間を別々に計算して加重平均等を行う予測式を生成してもよいし、種類が異なるが処理時間に差異のないものは同種のリクエストとして取り扱ってもよい。
続いて、先の自律制御処理について説明する。まず、自律制御手段120のシミュレーション実行手段121は、制御パターン記憶手段101より、図14、図16-図17に示すような、自律制御対象の仮想システムの制御パターンの集合を読み出す。さらに、シミュレーション実行手段121は、vDCモニタリング情報記憶装置304から、該当仮想システムのモニタリング情報のうち、直近(例えば、30分間)の仮想システムへの入力となるファイアウォール部分のモニタリング情報を取り出し、前記各制御パターンに入力して、各制御パターンの平均処理時間を予測する。図21は、シミュレーション実行手段121による図14、図16-図17の制御パターンのシミュレーション実行結果を示している。
[第1の形態]
(上記第1の視点によるリソース制御システム参照)
[第2の形態]
第1の形態のリソース制御システムにおいて、
前記制御パターン生成手段は、クラウドプラットフォーム上に同居する複数の仮想データセンタの仮想システムについてそれぞれ制御パターンを複数作成し、
前記制御手段は、各仮想データセンタの仮想システムに対する制御パターンを選定して適用するリソース制御システム。
[第3の形態]
第1又は第2の形態のリソース制御システムにおいて、
前記所定の選択基準は、前記サービスレベルを満たす複数の制御パターンのうち、リソースの消費量の少ない制御パターンを選択する基準であるリソース制御システム。
[第4の形態]
第1から第3いずれか一の形態のリソース制御システムにおいて、
前記所定の選択基準は、前記サービスレベルを満たす複数の制御パターンのうち、サーバリソース又はネットワークリソースのいずれか優先度の高い方のリソース消費量が少ない方の制御パターンを選択する基準であるリソース制御システム。
[第5の形態]
第1から第4いずれか一の形態のリソース制御システムにおいて、
前記制御パターン生成手段は、
前記仮想データセンタ上で動作する仮想システムのネットワーク要素とサーバのそれぞれについて、割当済みリソース量と、前記割当済みリソース量による処理時間の測定結果とに基づいて、割り当てリソースを変更した場合の処理時間を予測する予測式を生成する予測式生成手段と、
前記仮想データセンタ上で動作する仮想システムの構成情報と、前記予測式生成手段にて生成された予測式とを用いて、前記仮想システムモデルを生成する仮想システムモデル生成手段と、
前記仮想システムモデル生成手段にて生成された仮想システムモデルに含まれる構成に適用可能なリソース割当変更ポリシーを組み合わせて、前記制御パターンを生成する制御パターン派生手段と、
を含むリソース制御システム。
[第6の形態]
第1から第5いずれか一の形態のリソース制御システムにおいて、
前記制御手段は、
前記複数の制御パターンを用いてサービスレベルを予測するシミュレーションを実行するシミュレーション実行手段と、
前記シミュレーション結果を元に、前記仮想システムのサービスレベルを満たし、かつ、リソースの消費量が前記所定の選択基準を満たす制御パターンを選定する制御パターン評価手段と、
前記選定した制御パターンに従い、ネットワークリソースとサーバリソースの割り当てを変更する制御パターン適用手段と、
を含むリソース制御システム。
[第7の形態]
第1から第6いずれか一の形態のリソース制御システムにおいて、
前記リソース割当変更ポリシーに、経路制御と流量制御を実行するリソース割当変更ポリシーが含まれているリソース制御システム。
[第8の形態]
(上記第2の視点による制御パターン生成装置参照)
[第9の形態]
(上記第3の視点による制御装置参照)
[第10の形態]
(上記第4の視点によるリソース制御方法参照)
[第11の形態]
(上記第5の視点によるプログラム参照)
なお、上記第8~第11の形態は、第1の形態と同様に、第2~第7の形態に展開することが可能である。
12 制御手段
100 リソース制御システム
101 制御パターン記憶手段
111 予測式生成手段
112 モデル生成手段
113 制御パターン派生手段
114 予測式記憶手段
115 モデル記憶手段
120 自律制御手段
121 シミュレーション実行手段
122 制御パターン評価手段
123 制御パターン適用手段
124 シミュレーション結果記憶手段
125 評価済み制御パターン記憶手段
201 仮想データセンタ(vDC)構成記憶装置
202 サービスレベル記憶手段
203 リソース割当変更ポリシー記憶装置
300 仮想リソース管理装置
301 仮想サーバリソース管理手段
302 仮想ネットワークリソース管理手段
303 仮想データセンタ(vDC)モニタリング手段
304 仮想データセンタ(vDC)モニタリング情報記憶装置
400 仮想データセンタ(vDC)
Claims (11)
- 仮想データセンタ上で動作する仮想システムのネットワーク要素とサーバとの振る舞いをモデル化して生成した仮想システムモデルと、前記仮想システムへのリソースの割り当ての変更ポリシーを定めたリソース割当変更ポリシーとから、前記仮想システムのネットワークリソースとサーバリソースとに対する制御指示の候補となる制御パターンを複数生成する制御パターン生成手段と、
前記複数の制御パターンを用いてサービスレベルの予測を実行し、前記予測結果に基づいて、前記複数の制御パターンの中から、前記仮想システムのサービスレベルを満たし、かつ、所定の選択基準を満たす制御パターンを選定して適用する制御手段と、
を備えたリソース制御システム。 - 前記制御パターン生成手段は、クラウドプラットフォーム上に同居する複数の仮想データセンタの仮想システムについてそれぞれ制御パターンを複数作成し、
前記制御手段は、各仮想データセンタの仮想システムに対する制御パターンを選定して適用する請求項1のリソース制御システム。 - 前記所定の選択基準は、前記サービスレベルを満たす複数の制御パターンのうち、リソースの消費量の少ない制御パターンを選択する基準である請求項1又は2のリソース制御システム。
- 前記所定の選択基準は、前記サービスレベルを満たす複数の制御パターンのうち、サーバリソース又はネットワークリソースのいずれか優先度の高い方のリソース消費量が少ない方の制御パターンを選択する基準である請求項1又は2のリソース制御システム。
- 前記制御パターン生成手段は、
前記仮想データセンタ上で動作する仮想システムのネットワーク要素とサーバのそれぞれについて、割当済みリソース量と、前記割当済みリソース量による処理時間の測定結果とに基づいて、割り当てリソースを変更した場合の処理時間を予測する予測式を生成する予測式生成手段と、
前記仮想データセンタ上で動作する仮想システムの構成情報と、前記予測式生成手段にて生成された予測式とを用いて、前記仮想システムモデルを生成する仮想システムモデル生成手段と、
前記仮想システムモデル生成手段にて生成された仮想システムモデルに含まれる構成に適用可能なリソース割当変更ポリシーを組み合わせて、前記制御パターンを生成する制御パターン派生手段と、
を含む請求項1から4いずれか一のリソース制御システム。 - 前記制御手段は、
前記複数の制御パターンを用いてサービスレベルを予測するシミュレーションを実行するシミュレーション実行手段と、
前記シミュレーション結果を元に、前記仮想システムのサービスレベルを満たし、かつ、前記所定の選択基準を満たす制御パターンを選定する制御パターン評価手段と、
前記選定した制御パターンに従い、ネットワークリソースとサーバリソースの割り当てを変更する制御パターン適用手段と、
を含む請求項1から5いずれか一のリソース制御システム。 - 前記リソース割当変更ポリシーに、経路制御と流量制御を実行するリソース割当変更ポリシーが含まれている請求項1から6いずれか一のリソース制御システム。
- 仮想データセンタ上で動作する仮想システムのネットワーク要素とサーバとの振る舞いをモデル化して生成した仮想システムモデルと、前記仮想システムへのリソースの割り当ての変更ポリシーを定めたリソース割当変更ポリシーとから、前記仮想システムのネットワークリソースとサーバリソースとに対する制御指示の候補となる制御パターンを複数生成する制御パターン生成装置。
- 仮想システムのネットワークリソースとサーバリソースとに対する制御指示の候補となる複数の制御パターンを用いてサービスレベルの予測を実行し、前記予測結果に基づいて、前記複数の制御パターンの中から、前記仮想システムのサービスレベルを満たし、かつ、所定の選択基準を満たす制御パターンを選定して適用する制御装置。
- 仮想データセンタ上で動作する仮想システムのネットワーク要素とサーバとの振る舞いをモデル化して生成した仮想システムモデルと、前記仮想システムへのリソースの割り当ての変更ポリシーを定めたリソース割当変更ポリシーとから、前記仮想システムのネットワークリソースとサーバリソースとに対する制御指示の候補となる制御パターンを複数生成するステップと、
前記複数の制御パターンを用いてサービスレベルの予測を実行し、前記予測結果に基づいて、前記複数の制御パターンの中から、前記仮想システムのサービスレベルを満たし、かつ、所定の選択基準を満たす制御パターンを選定して適用するステップと、
を含むリソース制御方法。 - リソース制御装置を構成するコンピュータに、
仮想データセンタ上で動作する仮想システムのネットワーク要素とサーバとの振る舞いをモデル化して生成した仮想システムモデルと、前記仮想システムへのリソースの割り当ての変更ポリシーを定めたリソース割当変更ポリシーとから、前記仮想システムのネットワークリソースとサーバリソースとに対する制御指示の候補となる制御パターンを複数生成する処理と、
前記複数の制御パターンを用いてサービスレベルの予測を実行し、前記予測結果に基づいて、前記複数の制御パターンの中から、前記仮想システムのサービスレベルを満たし、かつ、所定の選択基準を満たす制御パターンを選定して適用する処理と、
を実行させるプログラム。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2014559769A JP6380110B2 (ja) | 2013-02-01 | 2014-01-31 | リソース制御システム、制御パターン生成装置、制御装置、リソース制御方法及びプログラム |
US14/761,800 US9740534B2 (en) | 2013-02-01 | 2014-01-31 | System for controlling resources, control pattern generation apparatus, control apparatus, method for controlling resources and program |
EP14746471.3A EP2953024A1 (en) | 2013-02-01 | 2014-01-31 | Resource control system, control pattern generation device, control device, resource control method and program |
CN201480007043.0A CN104981782B (zh) | 2013-02-01 | 2014-01-31 | 用于控制资源的系统、控制模式生成装置 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2013-018202 | 2013-02-01 | ||
JP2013018202 | 2013-02-01 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014119719A1 true WO2014119719A1 (ja) | 2014-08-07 |
Family
ID=51262416
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2014/052239 WO2014119719A1 (ja) | 2013-02-01 | 2014-01-31 | リソース制御システム、制御パターン生成装置、制御装置、リソース制御方法及びプログラム |
Country Status (5)
Country | Link |
---|---|
US (1) | US9740534B2 (ja) |
EP (1) | EP2953024A1 (ja) |
JP (1) | JP6380110B2 (ja) |
CN (1) | CN104981782B (ja) |
WO (1) | WO2014119719A1 (ja) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018181826A1 (ja) * | 2017-03-30 | 2018-10-04 | 日本電気株式会社 | レコメンドシステムと方法、装置、プログラム |
WO2019230577A1 (ja) * | 2018-06-01 | 2019-12-05 | 日本電信電話株式会社 | リソース予約管理装置およびリソース予約管理方法 |
WO2021149681A1 (ja) * | 2020-01-24 | 2021-07-29 | ファナック株式会社 | データ収集装置 |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10097410B2 (en) | 2014-06-26 | 2018-10-09 | Vmware, Inc. | Methods and apparatus to scale application deployments in cloud computing environments |
US10756929B2 (en) * | 2015-04-07 | 2020-08-25 | Umbra Technologies Ltd. | Systems and methods for providing a global virtual network (GVN) |
US10678596B2 (en) * | 2016-02-24 | 2020-06-09 | Alibaba Group Holding Limited | User behavior-based dynamic resource capacity adjustment |
US10796035B1 (en) * | 2016-03-21 | 2020-10-06 | EMC IP Holding Company LLC | Computing system with simulated hardware infrastructure to support development and testing of management and orchestration software |
US11347561B1 (en) * | 2018-04-30 | 2022-05-31 | Vmware, Inc. | Core to resource mapping and resource to core mapping |
US20200106714A1 (en) | 2018-09-28 | 2020-04-02 | Element Ai Inc. | System and method for managing network resources |
US11184234B2 (en) * | 2019-04-16 | 2021-11-23 | Ciena Corporation | Self-optimizing fabric architecture and self-assembling network |
US11635981B2 (en) * | 2020-08-25 | 2023-04-25 | Microsoft Technology Licensing, Llc | Virtualizing shared computing resources |
US11956213B2 (en) | 2022-05-18 | 2024-04-09 | VMware LLC | Using firewall policies to map data messages to secure tunnels |
US20230388180A1 (en) * | 2022-05-31 | 2023-11-30 | Microsoft Technology Licensing, Llc | Techniques for provisioning workspaces in cloud-based computing platforms |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007249445A (ja) * | 2006-03-15 | 2007-09-27 | Hitachi Ltd | クラスタシステムの負荷分散制御方法およびその装置 |
JP2008033852A (ja) * | 2006-08-01 | 2008-02-14 | Hitachi Ltd | リソース管理システム及びその方法 |
JP2008203934A (ja) * | 2007-02-16 | 2008-09-04 | Nec Corp | 分散ワークフローシミュレーションシステム、方法、及び、プログラム |
WO2009144822A1 (ja) * | 2008-05-30 | 2009-12-03 | 富士通株式会社 | 装置構成情報管理プログラム、装置構成情報管理装置及び装置構成情報管理方法 |
JP4557949B2 (ja) | 2006-04-10 | 2010-10-06 | 富士通株式会社 | 資源ブローカリングプログラム、該プログラムを記録した記録媒体、資源ブローカリング装置、および資源ブローカリング方法 |
JP4627461B2 (ja) | 2005-07-14 | 2011-02-09 | 日本電信電話株式会社 | 通信サービス制御システムと方法およびプログラム |
Family Cites Families (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8104038B1 (en) * | 2004-06-30 | 2012-01-24 | Hewlett-Packard Development Company, L.P. | Matching descriptions of resources with workload requirements |
US8087025B1 (en) * | 2004-06-30 | 2011-12-27 | Hewlett-Packard Development Company, L.P. | Workload placement among resource-on-demand systems |
US8549513B2 (en) * | 2005-06-29 | 2013-10-01 | Microsoft Corporation | Model-based virtual system provisioning |
US20070271560A1 (en) * | 2006-05-18 | 2007-11-22 | Microsoft Corporation | Deploying virtual machine to host based on workload characterizations |
US8555287B2 (en) * | 2006-08-31 | 2013-10-08 | Bmc Software, Inc. | Automated capacity provisioning method using historical performance data |
US8108855B2 (en) * | 2007-01-02 | 2012-01-31 | International Business Machines Corporation | Method and apparatus for deploying a set of virtual software resource templates to a set of nodes |
US8612987B2 (en) * | 2007-01-15 | 2013-12-17 | International Business Machines Corporation | Prediction-based resource matching for grid environments |
US9135075B2 (en) * | 2007-03-09 | 2015-09-15 | Hewlett-Packard Development Company, L.P. | Capacity planning for computing systems hosting multi-tier application based on think time value and resource cost of composite transaction using statistical regression analysis |
US8046767B2 (en) * | 2007-04-30 | 2011-10-25 | Hewlett-Packard Development Company, L.P. | Systems and methods for providing capacity management of resource pools for servicing workloads |
US8918496B2 (en) * | 2007-04-30 | 2014-12-23 | Hewlett-Packard Development Company, L.P. | System and method for generating synthetic workload traces |
US8756307B1 (en) * | 2007-07-30 | 2014-06-17 | Hewlett-Packard Development Company, L.P. | Translating service level objectives to system metrics |
US9842004B2 (en) * | 2008-08-22 | 2017-12-12 | Red Hat, Inc. | Adjusting resource usage for cloud-based networks |
EP2391961B1 (en) * | 2009-01-30 | 2016-10-05 | Hewlett-Packard Enterprise Development LP | System and method for integrating capacity planning and workload management |
US8055493B2 (en) * | 2009-01-30 | 2011-11-08 | Hewlett-Packard Development Company, L.P. | Sizing an infrastructure configuration optimized for a workload mix using a predictive model |
JP2010218307A (ja) * | 2009-03-17 | 2010-09-30 | Hitachi Ltd | 分散計算制御装置及び方法 |
US8117613B2 (en) * | 2009-04-08 | 2012-02-14 | Microsoft Corporation | Optimized virtual machine migration mechanism |
US20100281478A1 (en) * | 2009-05-01 | 2010-11-04 | Microsoft Corporation | Multiphase virtual machine host capacity planning |
US8627309B2 (en) * | 2010-02-25 | 2014-01-07 | Microsoft Corporation | Automated deployment and servicing of distributed applications |
US20110214124A1 (en) * | 2010-02-26 | 2011-09-01 | James Michael Ferris | Systems and methods for generating cross-cloud computing appliances |
JP5556507B2 (ja) * | 2010-08-30 | 2014-07-23 | 富士通株式会社 | 仮想マシン管理プログラム、仮想マシン管理方法、および仮想マシン管理装置 |
US20120060167A1 (en) * | 2010-09-08 | 2012-03-08 | Salsburg Michael A | Method and system of simulating a data center |
US8645529B2 (en) * | 2010-10-06 | 2014-02-04 | Infosys Limited | Automated service level management of applications in cloud computing environment |
CN102004671B (zh) * | 2010-11-15 | 2013-03-13 | 北京航空航天大学 | 一种云计算环境下数据中心基于统计模型的资源管理方法 |
US8806487B2 (en) * | 2011-01-14 | 2014-08-12 | Nec Laboratories America, Inc. | Calculating virtual machine resource utilization information |
US8793377B2 (en) * | 2011-05-03 | 2014-07-29 | International Business Machines Corporation | Identifying optimal virtual machine images in a networked computing environment |
US8806015B2 (en) * | 2011-05-04 | 2014-08-12 | International Business Machines Corporation | Workload-aware placement in private heterogeneous clouds |
US8930541B2 (en) * | 2011-11-25 | 2015-01-06 | International Business Machines Corporation | System, method and program product for cost-aware selection of templates for provisioning shared resources |
US8732291B2 (en) * | 2012-01-13 | 2014-05-20 | Accenture Global Services Limited | Performance interference model for managing consolidated workloads in QOS-aware clouds |
US9152443B2 (en) * | 2012-07-13 | 2015-10-06 | Ca, Inc. | System and method for automated assignment of virtual machines and physical machines to hosts with right-sizing |
US9135076B2 (en) * | 2012-09-28 | 2015-09-15 | Caplan Software Development S.R.L. | Automated capacity aware provisioning |
-
2014
- 2014-01-31 EP EP14746471.3A patent/EP2953024A1/en not_active Withdrawn
- 2014-01-31 JP JP2014559769A patent/JP6380110B2/ja active Active
- 2014-01-31 US US14/761,800 patent/US9740534B2/en active Active
- 2014-01-31 CN CN201480007043.0A patent/CN104981782B/zh active Active
- 2014-01-31 WO PCT/JP2014/052239 patent/WO2014119719A1/ja active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4627461B2 (ja) | 2005-07-14 | 2011-02-09 | 日本電信電話株式会社 | 通信サービス制御システムと方法およびプログラム |
JP2007249445A (ja) * | 2006-03-15 | 2007-09-27 | Hitachi Ltd | クラスタシステムの負荷分散制御方法およびその装置 |
JP4557949B2 (ja) | 2006-04-10 | 2010-10-06 | 富士通株式会社 | 資源ブローカリングプログラム、該プログラムを記録した記録媒体、資源ブローカリング装置、および資源ブローカリング方法 |
JP2008033852A (ja) * | 2006-08-01 | 2008-02-14 | Hitachi Ltd | リソース管理システム及びその方法 |
JP2008203934A (ja) * | 2007-02-16 | 2008-09-04 | Nec Corp | 分散ワークフローシミュレーションシステム、方法、及び、プログラム |
JP4872702B2 (ja) | 2007-02-16 | 2012-02-08 | 日本電気株式会社 | 分散ワークフローシミュレーションシステム、方法、及び、プログラム |
WO2009144822A1 (ja) * | 2008-05-30 | 2009-12-03 | 富士通株式会社 | 装置構成情報管理プログラム、装置構成情報管理装置及び装置構成情報管理方法 |
Non-Patent Citations (2)
Title |
---|
"OpenFlow Switch Specification" Version 1.3.1 (Wire Protocol 0x04)", Retrieved from the Internet <URL:http://www.opennetworking.org/images/stories/downloads/specification/openflow-spec-v1.3.1.pdf> [retrieved on 20130109] |
NICK MCKEOWN ET AL.,: "OpenFlow: Enabling Innovation in Campus Networks", 14 March 2008 (2008-03-14), Retrieved from the Internet <URL:http://www.openflow.org/documents/openflow-wp-latest.pdf> |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018181826A1 (ja) * | 2017-03-30 | 2018-10-04 | 日本電気株式会社 | レコメンドシステムと方法、装置、プログラム |
JPWO2018181826A1 (ja) * | 2017-03-30 | 2020-02-06 | 日本電気株式会社 | レコメンドシステムと方法、装置、プログラム |
WO2019230577A1 (ja) * | 2018-06-01 | 2019-12-05 | 日本電信電話株式会社 | リソース予約管理装置およびリソース予約管理方法 |
JP2019211890A (ja) * | 2018-06-01 | 2019-12-12 | 日本電信電話株式会社 | リソース予約管理装置およびリソース予約管理方法 |
US11343199B2 (en) | 2018-06-01 | 2022-05-24 | Nippon Telegraph And Telephone Corporation | Resource reservation management device and resource reservation management method |
WO2021149681A1 (ja) * | 2020-01-24 | 2021-07-29 | ファナック株式会社 | データ収集装置 |
Also Published As
Publication number | Publication date |
---|---|
EP2953024A1 (en) | 2015-12-09 |
JP6380110B2 (ja) | 2018-08-29 |
US20150363240A1 (en) | 2015-12-17 |
JPWO2014119719A1 (ja) | 2017-01-26 |
US9740534B2 (en) | 2017-08-22 |
CN104981782B (zh) | 2019-03-26 |
CN104981782A (zh) | 2015-10-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6380110B2 (ja) | リソース制御システム、制御パターン生成装置、制御装置、リソース制御方法及びプログラム | |
Gouareb et al. | Virtual network functions routing and placement for edge cloud latency minimization | |
Mahmud et al. | Quality of Experience (QoE)-aware placement of applications in Fog computing environments | |
JP7413835B2 (ja) | 遅延保証を備えたモニタリングに基づくエッジコンピューティングサービス | |
Kim et al. | Multi-agent reinforcement learning-based resource management for end-to-end network slicing | |
Cappanera et al. | VNF placement for service chaining in a distributed cloud environment with multiple stakeholders | |
Zhang et al. | A dynamic planning model for deploying service functions chain in fog-cloud computing | |
Pietrabissa et al. | Lyapunov-based design of a distributed wardrop load-balancing algorithm with application to software-defined networking | |
Ibrahim et al. | Heuristic resource allocation algorithm for controller placement in multi-control 5G based on SDN/NFV architecture | |
Dezhabad et al. | Learning-based dynamic scalable load-balanced firewall as a service in network function-virtualized cloud computing environments | |
Baresi et al. | PAPS: A Framework for Decentralized Self-management at the Edge | |
Azad et al. | A fuzzy-based method for task scheduling in the cloud environments using inverted ant colony optimisation algorithm | |
Farkiani et al. | Prioritized deployment of dynamic service function chains | |
Maia et al. | A multi-objective service placement and load distribution in edge computing | |
CN116032767A (zh) | 一种面向智融标识网络的算力服务链管控系统架构 | |
Mostafa | Cooperative fog communications using a multi-level load balancing | |
Lin et al. | Column generation based service function chaining embedding in multi-domain networks | |
KR20200062887A (ko) | 강화학습에 기반하여 시스템의 제어 동작의 품질을 보장하기 위한 장치 및 방법 | |
Benedetti et al. | Reinforcement learning applicability for resource-based auto-scaling in serverless edge applications | |
Baresi et al. | PAPS: A serverless platform for edge computing infrastructures | |
Li et al. | Optimal service selection and placement based on popularity and server load in multi-access edge computing | |
Liu et al. | A method for adaptive resource adjustment of dynamic service function chain | |
CN106717084B (zh) | 重叠速率区分区的设备和方法 | |
Gadre et al. | Centralized approaches for virtual network function placement in SDN-enabled networks | |
Nishanbayev et al. | Formalization of the Task of Building a Cloud-data Center based on a Software-Defined Network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14746471 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2014746471 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14761800 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 2014559769 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |