System utilization rate managing apparatus and system utilization rate managing method to be employed for it, and its program

• US 7,864,679 B2
• Filed: 09/21/2005
• Issued: 01/04/2011
• Est. Priority Date: 09/22/2004
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Tanaka, Atsuhiro, Ajiro, Yasuhiro
• Primary Examiner(s): Nguyen; Steven H
• Assistant Examiner(s): BOKHARI, SYED M
• Application Number:
  US11/230,634
• Publication Number:
  US 20060062148A1
• Time in Patent Office: 1,931 Days
• Field of Search: 370/352, 370/480, 370/259, 370/353, 370/354, 370/338, 370/234, 709/226, 709/224, 709/203, 709/231, 709/225, 395/200, 395/200.79, 455/423, 455/101, 455/226
• US Class Current: 370/232
• CPC Class Codes: H04L 41/0896 Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities flow or congestion control using dynamic resource allocation, e.g. in-call renegotiation, H04L47/76
• CPC Class Codes: H04L 43/00 Arrangements for monitoring or testing data switching networks
• CPC Class Codes: H04L 43/0882 Utilisation of link capacity

Abstract

A system utilization rate managing device that realizes a management of a system performance and an optimization of the number of operating nodes of different performances and architectures is provided.

A node maximum-performance setter of a processing device files a maximum performance of each node constituting an external system into a node maximum-performance memory section of a memory device. A resource utilization rate acquirer acquires a resource utilization rate of each node, and gives it to a virtual utilization rate calculation section. The virtual utilization rate calculation section calculates a virtual utilization rate of the system from the maximum performance of each node retained in a node maximum-performance memory section and the resource utilization rate of each node, and gives the virtual utilization rate to an output section. The output section outputs the virtual utilization rate to an output device.

Claims

1. A system utilization rate managing apparatus configured to calculate a system utilization rate of a node group composed of a plurality of computing nodes, said system utilization rate managing apparatus comprising:

a node maximum-performance setter configured to set a maximum performance of each of said plurality of said computing nodes;

a resource utilization rate acquirer configured to acquire a resource utilization rate of each of said plurality of said computing nodes; and

a virtual utilization rate calculator configured to calculate a virtual utilization rate of an entirety of said node group as a weighted mean of said maximum performance set for each of said plurality of said computing nodes in said node maximum-performance setter and said resource utilization rate acquired in said resource utilization rate acquirer for each of said plurality of said computing nodes, wherein the resource utilization rate is a rate of use of a CPU for each of said plurality of said computing nodes.

2. The system utilization rate managing apparatus according to claim 1, wherein said node maximum-performance setter comprises:

a request arrival-rate acquirer configured to acquire a request arrival rate of each of said plurality of said computing nodes;

a node maximum-performance calculator configured to calculate a maximum performance of each of said plurality of said computing nodes from said resource utilization rate acquired in said resource utilization rate acquirer for each of said plurality of said computing nodes and said request arrival rate acquired in said request arrival-rate acquirer for each of said plurality of said computing nodes and to retain the maximum performance of each of said plurality of said computing nodes.

3. The system utilization rate managing apparatus according to claim 1, comprising a service satisfaction degree evaluator configured to evaluate whether said virtual utilization rate calculated in said virtual utilization rate calculator satisfies a specified service level.

4. The system utilization rate managing apparatus according to claim 1, comprising:

a maximum performance comparator configured to compare a maximum performance set in said node maximum-performance setter for a computing node with a maximum performance to be retained for the computing node, which is currently employed; and

a reliability degree calculator configured to calculate a reliability degree from a number of times that a comparison was made in said maximum performance comparator and a number of times that a difference between said maximum performance set in said node maximum-performance setter for the computing node and a maximum performance to be retained for the computing node, which was employed, was within an allowable range.

5. The system utilization rate managing apparatus according to claim 1, comprising a means configured to display said calculated virtual utilization rate along a time series.

6. A system utilization rate managing method to be employed in a system utilization rate managing apparatus configured to calculate a system utilization rate of a node group composed of a plurality of computing nodes, said system utilization rate managing method comprising the steps of:

setting a maximum performance of each of said plurality of said computing nodes;

acquiring a resource utilization rate of each of said plurality of said computing nodes; and

calculating, by the system utilization rate managing apparatus, a virtual utilization rate of an entirety of said node group as a weighted mean of said set maximum performance for each of said plurality of said computing nodes and said acquired resource utilization rate for each of said plurality of said computing nodes, wherein the resource utilization rate is a rate of use of a CPU for each of said plurality of said computing nodes.

7. The system utilization rate managing method according to claim 6, wherein, said step of setting a maximum performance comprises the steps of:

acquiring a resource utilization rate of each of said plurality of said computing nodes;

acquiring a request arrival rate of each of said plurality of said computing nodes; and

calculating a maximum performance of each of said plurality of said computing nodes from said acquired resource utilization rate for each of said plurality of said computing nodes and said acquired request arrival rate for each of said plurality of said computing nodes to retain the maximum performance of each of said plurality of said computing nodes.

8. The system utilization rate managing method according to claim 6, comprising a step of evaluating whether said virtual utilization rate satisfies a specified service level.

9. The system utilization rate managing method according to claim 6, further comprising the steps of:

comparing a maximum performance set for a computing node with a maximum performance to be retained for the computing node, which is currently employed; and

calculating a reliability degree from a number of times that a comparison was made and a number of times that a difference between said maximum performance set for the computing node and a maximum performance to be retained for the computing node, which was employed, was within an allowable range.

10. The system utilization rate managing method according to claim 6, wherein said system utilization rate managing apparatus displays said calculated virtual utilization rate along a time series.

11. A non-transitory computer-readable medium comprising instructions for causing a processor in a system utilization rate managing apparatus to execute a method for managing a system utilization rate of a node group composed of a plurality of computing nodes, comprising the steps of:

setting a maximum performance of each of the plurality of the computing nodes;

acquiring a resource utilization rate of each of the plurality of the computing nodes; and

calculating a virtual utilization rate of an entirety of the node group as a weighted mean of the set maximum performance for each of the plurality of the computing nodes and the acquired resource utilization rate for each of the plurality of the computing nodes, wherein the resource utilization rate is a rate of use of a CPU for each of the plurality of the computing nodes.

12. The non-transitory computer-readable medium of claim 11, wherein the step of setting a maximum performance comprises:

acquiring a resource utilization rate of each of the plurality of the computing nodes;

acquiring a request arrival rate of each of the plurality of the computing nodes; and

calculating a maximum performance of each of the plurality of the computing nodes from the acquired resource utilization rate for each of the plurality of the computing nodes and the acquired request arrival rate for each of the plurality of the computing nodes to retain the maximum performance of each of the plurality of the computing nodes.

13. The non-transitory computer-readable medium of claim 11, wherein the method for managing a system utilization rate further comprises the step of evaluating whether the virtual utilization rate satisfies a specified service level.

14. The non-transitory computer-readable medium of claim 11, wherein the method of managing a system utilization rate further comprises the steps of comparing a maximum performance set for a computing node with a maximum performance to be retained for the computing node, which is currently employed;

and calculating a reliability degree from a number of times that a comparison was made and a number of times that a difference between the maximum performance set for the computing node and a maximum performance to be retained for the computing node, which was employed, was within an allowable range.

15. The non-transitory computer-readable medium of claim 11, wherein the method further comprises the step of displaying the calculated virtual utilization rate along a time series.

16. A system utilization rate managing apparatus configured to calculate a system utilization rate of a node group composed of a plurality of computing nodes, said system utilization rate managing apparatus comprising:

means for setting a maximum performance of each of said plurality of said computing nodes;

means for acquiring a resource utilization rate of each of said plurality of said computing nodes; and

means for calculating a virtual utilization rate of an entirety of said node group as a weighted mean of said set maximum performance for each of said plurality of said computing nodes and said acquired resource utilization rate for each of said plurality of said computing nodes, wherein the resource utilization rate is a rate of use of a CPU for each of said plurality of said computing nodes.

17. The system utilization rate managing apparatus of claim 16, wherein said means for setting a maximum performance of each of said plurality of said computing nodes comprises:

means for acquiring a request arrival rate of each of said plurality of said computing nodes; and

means for calculating a maximum performance of each of said plurality of said computing nodes from said acquired resource utilization rate for each of said plurality of said computing nodes and said acquired request arrival rate for each of said plurality of said computing nodes to retain the maximum performance of each of said plurality of said computing nodes.

18. The system utilization rate managing apparatus of claim 16, further comprising:

means for comparing a maximum performance set for a computing node with a maximum performance to be retained for the computing node, which is currently employed; and

means for calculating a reliability degree from a number of times that a comparison was made and a number of times that a difference between said maximum performance set for the computing node and a maximum performance to be retained for the computing node, which was employed, was within an allowable, range.

19. The system utilization rate managing apparatus of claim 16, further comprising means for displaying said calculated virtual utilization rate along a time series.