SYSTEMS AND METHODS FOR COORDINATED MANAGEMENT OF POWER USAGE AND RUNTIME PERFORMANCE IN PERFORMANCE-MANAGED COMPUTING ENVIRONMENTS

• US 20090254660A1
• Filed: 04/07/2008
• Published: 10/08/2009
• Est. Priority Date: 04/07/2008
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Kephart, Jeffrey Owen, Steinder, Malgorzata, Hanson, James E., Whalley, Ian Nicholas
• Granted Patent: US 8,301,742 B2
• Time in Patent Office: Days
• US Class Current: 709/226
• CPC Class Codes: H04L 12/10 Current supply arrangements

Abstract

Systems and methods are provided for dynamically controlling application placement and server resource allocation in a distributed system wherein a performance manager and power manager collaborate during run-time execution of data processing tasks to coordinate management and control of workload placement and server usage and dynamically determine a tradeoff between performance level and power usage that meets power and performance objectives

Claims

1. A distributed computing system, comprising:

a plurality of computing nodes interconnected in a network, wherein the computing nodes comprise a plurality of servers forming a server cluster that provides a shared pool of server resources for executing data processing tasks, and an automated resource management system to manage the plurality of servers;

wherein the automated resource management system comprises;

a performance manager that controls allocation of server resources and placement of workload on a set of servers in the server cluster according to performance constraints;

a power manager that controls power states and usage of servers in the server cluster according to power consumption constraints,

wherein the performance manager and power manager collaborate during run-time execution of data processing tasks to coordinate management and control of workload placement and server usage and dynamically determine a tradeoff between performance level and power usage that meets power and performance objectives.

2. The system of claim 1, wherein collaboration between the performance manager and power manager comprises the performance manager issuing a request for control of additional server resources, and the power manager either granting or denying the request.

3. The system of claim 1, wherein collaboration between the performance manager and power manager comprises the performance manager releasing control of server resources to the power manager.

4. The system of claim 1, wherein collaboration between the performance manager and power manager comprises the power manager recommending one or more additional servers for use by the performance manager which would result in a more desirable tradeoff between performance level and power usage for an increased workload.

5. The system of claim 1, wherein collaboration between the performance manager and power manager comprises the power manager recommending release of control of one or more servers by the performance manager, which would result in a more desirable tradeoff between performance level and power usage for a decreased workload.

6. The system of claim 1, wherein the power manager controls a power state of server nodes in a pool of unused server nodes to minimize power consumption, subject to power consumption constraints.

7. The system of claim 1, wherein power consumption constraints comprises a cost of powering on a server in view of a number of power cycles of the server.

8. The system of claim 1, wherein a tradeoff between performance and power consumption is determined using a utility function, which includes a performance function to compute a performance level and power usage function to compute a cost of power usage, to determine a net utility for a given allocation of workload over a set of server nodes.

9. The system of claim 8, wherein the performance function and power usage function are functions of CPU allocation.

10. The system of claim 8, wherein the utility function has user-definable control parameters to selective adjust an amount of tradeoff of performance against power usage.

11. A method for managing computing resources in a distributed system including a plurality of server nodes forming a server cluster that provides a shared pool of server resources for executing data processing tasks, said method comprising:

allocating server resources for placing applications over a set of server nodes in the server cluster to perform data processing tasks;

determining if a more optimal application placement can be made to achieve a more optimal balance between performance level and power usage and meet power and performance objectives for a current workload; and

dynamically adjusting resource allocation to obtain a more optimal application placement.

12. The method of claim 11, wherein the step of determining comprises evaluating a utility function, which includes a performance function to compute a performance level and power usage function to compute a cost of power usage, to determine a net utility for a given allocation of workload over a set of server nodes.

13. The method of claim 12, wherein the utility function has user-definable control parameters to selective adjust an amount of tradeoff of performance against power usage.

14. The method of claim 12, wherein the determining step is performed by collaboration between a power manager system and performance manager system to coordinate control of resource allocations to achieve performance level and power usage.

15. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for managing computing resources in a distributed system including a plurality of server nodes forming a server cluster that provides a shared pool of server resources for executing data processing tasks, said method steps comprising:

allocating server resources for placing applications over a set of server nodes in the server cluster to perform data processing tasks;

determining if a more optimal application placement can be made to achieve a more optimal balance between performance level and power usage and meet power and performance objectives for a current workload; and

dynamically adjusting resource allocation to obtain a more optimal application placement.

16. The program storage device of claim 15, wherein the instructions for determining comprise instructions for evaluating a utility function, which includes a performance function to compute a performance level and power usage function to compute a cost of power usage, to determine a net utility for a given allocation of workload over a set of server nodes.

17. The program storage device of claim 16, wherein the utility function has user-definable control parameters to selective adjust an amount of tradeoff of performance against power usage.

18. The program storage device of claim method of claim 15, wherein the instructions for determining comprise instructions for enabling collaboration between a power manager system and performance manager system to coordinate control of resource allocations to achieve performance level and power usage.