Infrastructure driven auto-scaling of workloads
US-2024419470-A1 · Dec 19, 2024 · US
US2016196168A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2016196168-A1 |
| Application number | US-201414909866-A |
| Country | US |
| Kind code | A1 |
| Filing date | Jun 24, 2014 |
| Priority date | Aug 5, 2013 |
| Publication date | Jul 7, 2016 |
| Grant date | — |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
To provide a virtual resource control system capable of appropriately defining the amounts of allocated virtual resources to individual service systems under an environment in which service systems are added or deleted. A resource excessive/lacking amount calculation means 54 simulates a resource consumption situation of each node in the service system by use of a hybrid model, and calculates the amount of excessive/lacking resource indicating the lacking amount or the excessive amount of the amount of allocated virtual resource corresponding to one entire service system corresponding to a service management device. The resource excessive/lacking amount calculation means 54 notifies the amount of excessive/lacking resource to a hub device 60 , and receives a notification of the new amount of allocated virtual resource corresponding to the entire service system. A notification by the resource excessive/lacking amount calculation means 54 and a response from the hub device 60 are made asynchronously.
Opening claim text (preview).
1 . A virtual resource control system comprising: service management devices corresponding to service systems for providing services on a one-to-one basis and directed for defining the amount of allocated virtual resource to an individual node in a corresponding service system; a hub device for receiving the amount of excessive/lacking resource indicating the lacking amount or the excessive amount of the amount of allocated virtual resource to one entire service system corresponding to a service management device, from the service management device, and notifying the amount of allocated virtual resource to one entire service system corresponding to the service management device to the service management device; and resource management devices for calculating the amount of allocated virtual resource to each entire service system, wherein each service management device comprises: a model holding unit for holding a service model expressing input and output of each node in a service system corresponding to the device in order of processings; a monitoring unit for measuring the amount of allocated virtual resource, the amount of unit consumed resource as the amount of virtual resource consumed for one request, and an average processing time for each node in the service system, and acquiring a log indicating a request made in the service system; a model generation unit for generating a resource model expressing the amount of unused resource and the amount of using resource of a node on input into the node based on the amount of allocated virtual resource, the amount of unit consumed resource, and an average processing time of each node as well as the service model, and generating a hybrid model in a combination of the service model and the resource model; a resource excessive/lacking amount calculation unit for simulating a resource consumption situation of each node in the service system by use of the hybrid model and the log, calculating the minimum amount of remaining resource as a minimum value of the amount of remaining virtual resource and the maximum amount of lacking resource as a maximum value of the amount of lacking virtual resource per node, calculating the amount of excessive/lacking resource based on the minimum amount of remaining resource and the maximum amount of lacking resource per node, notifying the amount of excessive/lacking resource to the hub device, and receiving a notification of the amount of allocated virtual resource to one entire service system corresponding to the service management device in which the lacking amount or the excessive amount indicated by the amount of excessive/lacking resource is eliminated from the hub device; and a virtual resource allocated amount update unit for updating the amount of allocated virtual resource in order to eliminate the minimum amount of remaining resource or the maximum amount of lacking resource per node, the hub device comprises: a resource excessive/lacking amount holding unit for holding the amount of excessive/lacking resource notified from each service management device; a total resource excessive/lacking amount calculation unit for calculating the total amount of excessive/lacking resource indicating the lacking amount or the excessive amount of the amount of allocated virtual resource to each entire service system based on the amount of excessive/lacking resource notified from each service management device every certain period of time, notifying the total amount of excessive/lacking resource to a resource management device, and receiving a notification of the amount of allocated virtual resource to each entire service system in which the total amount of excessive/lacking resource is eliminated from the resource management device; and a system-based virtual resource allocated amount calculation unit for calculating the amount of allocated virtual resource to one entire service system corresponding to a service management device in which the lacking amount or the excessive amount indicated by the amount of excessive/lacking resource is eliminated, and notifying the allocated amount to the service management device which has transmitted the amount of excessive/lacking resource, and the resource management device comprises: a total resource excessive/lacking amount holding unit for holding the total amount of excessive/lacking resource notified from the hub device; and a total virtual resource allocated amount calculation unit for confirming the total amount of excessive/lacking resource every certain period of time, calculating the amount of allocated virtual resource to each entire service system in which the total amount of excessive/lacking resource is eliminated, and notifying the allocated amount to the hub device. 2 . The virtual resource control system according to claim 1 , comprising a resource management device per type of a virtual resource. 3 . The virtual resource control system according to claim 2 , wherein the resource excessive/lacking amount calculation unit calculates the minimum amount of remaining resource, the maximum amount of lacking resource, and the amount of excessive/lacking resource per type of a virtual resource, the virtual resource allocated amount update unit updates the amount of allocated virtual resource per type of a virtual resource, the resource excessive/lacking amount holding unit holds the amount of excessive/lacking resource notified from each service management device per type of a virtual resource, the total resource excessive/lacking amount calculation unit calculates the total amount of excessive/lacking resource per type of a virtual resource, and notifies the total amount of excessive/lacking resource to a resource management device depending on a type of a virtual resource, and the system-based virtual resource allocated amount calculation unit calculates the amount of allocated virtual resource to one entire service system corresponding to a service management device per type of a virtual resource. 4 . The virtual resource control system according to claim 1 , wherein the model holding unit holds a service model expressing input and output of each node in a service system in order of processings and expressing branch and aggregation of output of nodes. 5 . A virtual resource control method using service management devices corresponding to service systems for providing services on a one-to-one basis and directed for defining the amount of allocated virtual resource to an individual node in a corresponding service system, a hub device for receiving the amount of excessive/lacking resource indicating the lacking amount or the excessive amount of the amount of allocated virtual resource to one entire service system corresponding to a service management device, from the service management device, and notifying the amount of allocated virtual resource to one entire service system corresponding to the service management device to the service management device, and resource management devices for calculating the amount of allocated virtual resource to each entire service system, wherein each service management device: holds a service model expressing input and output of each node in a service system corresponding to the device in order of processings, measures the amount of allocated virtual resource, the amount of unit consumed resource as the amount of virtual resource consumed for one request, and an average processing time for each node in the service system, and acquires a log indicating a request made in the service system, generates a resource model expressing the amount of unused resource and the amount of using resource of a node on input into the node based on the amount of allocated virtual resource, the amount of unit consumed resource, and an average processing time of each node as
considering the load · CPC title
Logical partitioning of resources; Management or configuration of virtualized resources (specific details on emulation or internal functioning of virtual machines G06F9/455) · CPC title
Partitioning or combining of resources · CPC title
Techniques for rebalancing the load in a distributed system · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.