SYSTEMS AND METHODS FOR USING WORKLOAD CHARACTERISTICS FOR SIZING AND PLACEMENT FOR POWER-AWARE CONSOLIDATION

• US 20110191461A1
• Filed: 02/02/2010
• Published: 08/04/2011
• Est. Priority Date: 02/02/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: De, Pradipta, Nayak, Tapan K., Verma, Akshat, Dasgupta, Gargi B., Kothari, Ravi
• Granted Patent: US 8,463,900 B2
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: G06F 15/173 using an interconnection network, e.g. matrix, shuffle, pyramid, star, snowflake
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system

Abstract

Embodiments of the invention provide power savings via performing application workload consolidation to servers using off-peak values for application workload demand. Embodiments of the invention are designed to achieve significant power savings while containing performance risk associated with server consolidation.

Claims

1. A method comprising:

utilizing one or more processors to execute a program of instructions stored in a program storage device, the program of instructions configured for clustering application workloads for placement on one or more servers and comprising;

computer readable program code configured to identify application workloads that are similar and cluster similar workloads to create one or more application workload clusters; and

computer readable program code configured to automatically consolidate application workloads to the one or more servers utilizing a first parameter describing an application workload and a second parameter describing an application workload;

the first parameter representing a typical resource usage of an application workload;

the second parameter representing a maximum resource usage of an application workload.

2. The method according to claim 1, wherein the typical resource usage is a ninety percentile level of resource usage of the application workload.

3. The method according to claim 1, wherein the program of instructions further comprises computer readable program code configured to ensure every selected server at which application workload is to be consolidated has a proportional allocation from each application workload cluster.

4. The method according to claim 2, wherein two applications workloads are defined to be a part of a cluster of application workloads if the two application workloads peak together at the same time.

5. The method according to claim 4, wherein an application workload is defined to be peaking at any time T if utilization of server resources by the application workload exceeds the first parameter at time T.

6. The method according to claim 1, wherein a capacity of the one or more servers is greater than a second parameter of an individual application workload cluster placed on the one or more servers.

7. The method according to claim 1, wherein a capacity of the one or more servers is greater than a sum of first parameters of all application workloads placed on the server.

8. The method according to claim 1, wherein a capacity of the one or more servers is greater than a sum of first parameters of all application workloads placed on the server and second parameters of the application workloads placed.

9. The method according to claim 1, wherein the program of instructions further comprises computer readable program code configured to ensure that a predetermined maximum number of similar application workloads to be consolidated on any one server is not exceeded.

10. The method according to claim 8, wherein the similar application workloads are defined as application workloads that peak at a similar time.

12. The apparatus according to claim 10, wherein the typical resource usage is a ninety percentile level of resource usage of the application workload.

13. The apparatus according to claim 10, wherein the program of instructions further comprises computer readable program code configured to ensure every selected server at which application workload is to be consolidated has a proportional allocation from each clustering of application workloads.

14. The apparatus according to claim 12, wherein two applications workloads are defined to be a part of a cluster of application workloads if the two application workloads peak together at the same time.

15. The apparatus according to claim 14, wherein an application workload is defined to be peaking at any time T if utilization of server resources by the application workload exceeds the first parameter at time T

16. The apparatus according to claim 10, wherein a capacity of the one or more servers is greater than a second parameter of an individual application workload cluster placed on the one or more servers.

17. The apparatus according to claim 10, wherein a capacity of the one or more servers is greater than a sum of first parameters of all application workloads placed on the server.

18. The apparatus according to claim 10, wherein a capacity of the one or more servers is greater than a sum of first parameters of all application workloads placed on the server and second parameters of the application workloads placed.

19. The apparatus according to claim 10, wherein the computer readable program code further comprises computer readable program code configured to ensure that a predetermined maximum number of similar application workloads to be consolidated on any one server is not exceeded.

11. An apparatus comprising:

one or more processors; and

a computer readable storage medium having a program of instructions embodied therewith and executable by the one or more processors, the program of instructions comprising;

computer readable program code configured to cluster application workloads to be consolidated; and

computer readable program code configured to automatically consolidate application workloads to the one or more servers utilizing a first parameter describing an application workload and a second parameter describing an application workload;

the first parameter representing a typical resource usage of an application workload;

the second parameter representing a maximum resource usage of an application workload.

20. A computer program product comprising:

a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising;

computer readable program code configured to cluster application workloads to be consolidated; and

computer readable program code configured to automatically consolidate application workloads to the one or more servers utilizing a first parameter describing an application workload and a second parameter describing an application workload;

the first parameter representing a body of the distribution of the application workload use of server capacity;

the second parameter representing a tail of the distribution of the application workload use of server capacity.