COMPUTING COMPONENT AND ENVIRONMENT MOBILITY

• US 20100138530A1
• Filed: 12/03/2008
• Published: 06/03/2010
• Est. Priority Date: 12/03/2008
• Status: Active Grant

• Current Assignee: Taiwan Semiconductor Manufacturing Company Limited
• Original Assignee: International Business Machines Corporation
• Inventors: Dawson, Christopher J., Hamilton, Rick A. II, Brillhart, David C., Seaman, James W.
• Granted Patent: US 8,171,325 B2
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: G06F 1/206 comprising thermal management
• CPC Class Codes: G06F 9/4856 resumption being on a different machine, e.g. task migration, virtual machine migration G06F9/5088 takes precedence
• CPC Class Codes: G06F 9/4893 taking into account power or heat criteria power management in computers in general G06F1/3203; thermal management in computers in general G06F1/206
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Methods, services, devices, and programmable code are provided for moving computing processes without loss of service. Powered components supporting a computing infrastructure executing computing processes are monitored for thermal characteristics, each associated with at least one of the deployed components. A thermal characteristic rule set comprising a threshold is applied to the monitored characteristics, and in response to an association with a monitored characteristic correlating with the threshold, a computing process is moved from one powered component to another having a monitored thermal characteristics not correlated with the threshold, the moving in real-time and without causing an interruption of service to an end user using the moved process.

Claims

1. A method for moving computing processes without loss of service, comprising:

deploying a plurality of powered components supporting a computing infrastructure;

executing a computing process on a first at least one of the deployed powered components;

monitoring a plurality of thermal characteristics, each of the plurality of thermal characteristics associated with a one of the deployed plurality of powered components;

applying a thermal characteristic rule set comprising a threshold to the monitored thermal characteristics; and

in response to an association of the first at least one powered component with a monitored thermal characteristic correlating with the applied threshold, moving the computing process from the first at least one powered component to a second of the plurality of powered components;

wherein a one of the monitored plurality of thermal characteristics associated with the second powered component does not correlate with the threshold; and

wherein the moving is in real-time and without causing an interruption of service to an end user using the moved process.

2. The method of claim 1, wherein the first at least one powered component is a first server, the process is a computing application running on the first server, and the second powered component is a second server.

3. The method of claim 2, wherein the moved running process is a logical partition server environment appearing to the end user as an individual physical server, the logical partition server environment comprising a computing operating system and a plurality of running applications, and wherein the first and the second servers are different servers.

4. The method of claim 3, further comprising:

applying a mobility rule set in response to the threshold correlating, wherein the moving the logical partition server environment running on the first server to the second server is a function of the applying the mobility rule set; and

in response to the applying a mobility rule set, moving an additional process running on a third of the powered components to another of the plurality of powered components in response to a one of the monitored thermal characteristics associated with the third powered component correlating with the threshold, wherein the another powered component may be the second powered component or a fourth of the powered components, and wherein the additional at least one process moving is in real-time and without causing an interruption of service to an end user using the moved at least one additional process.

5. The method of claim 4, the moving the additional at least one process further comprising selecting and moving each of a plurality of additional processes from others of the plurality of powered components until the thermal characteristics correlating with the threshold is abated.

6. The method of claim 5, the mobility rule set further comprising a predefined timing function, the method comprising:

the moving the logical partition server activating the predefined timing function;

the activated predefined timing function preventing the moving the additional at least one process until after a specified time period has elapsed;

taking a temperature measurement subsequent to the elapse of the specified time period; and

verifying that the thermal characteristics correlating with the threshold is not abated as a function of the subsequent temperature measurement.

7. The method of claim 1, wherein the threshold is a target temperature;

wherein the monitored thermal characteristic associated with the first powered component is a first temperature, the threshold correlating comprising the first temperature exceeding the target temperature; and

wherein the monitored thermal characteristic associated with the second powered component is a second temperature, the second temperature below the target temperature.

8. The method of claim 1, wherein the threshold is a temperature differential threshold;

wherein the monitored thermal characteristic associated with the first powered component is a first temperature and the monitored thermal characteristic associated with the second powered component is a second temperature lower than the first temperature; and

wherein the correlating with the threshold comprises the first temperature differing from the second temperature by a value greater than the temperature differential threshold.

9. The method of claim 1, wherein the monitored thermal characteristic is a temperature, the monitored thermal characteristic associated with the first powered component is a first temperature and the monitored thermal characteristic associated with the second powered component is a second temperature;

wherein the threshold is a threshold percentage;

wherein the threshold percentage correlating comprises determining that a current monitored value of the first temperature is greater than a prior monitored value of the first temperature by more than the threshold percentage; and

wherein a current value of the monitored second temperature is not greater than a prior monitored value of the second temperature by more than the threshold percentage.

10. The method of claim 1, wherein the first powered component is a hard drive, the process is a server memory process accessing the first hard drive, and the second powered component is a second hard drive.

11. The method of claim 10, wherein the first hard drive and the second hard drive reside on different servers.

12. The method of claim 10, wherein the first hard drive and the second hard drive reside on a same server.

13. A service for moving computing processes without loss of service, comprising:

deploying a computational device infrastructure configured to monitor a plurality of thermal characteristics, each of the plurality of thermal characteristics associated with a one of a deployed plurality of powered components supporting a computing infrastructure;

the computational device infrastructure applying a thermal characteristic rule set comprising a threshold to the monitored thermal characteristics; and

in response to an association of a first at least one powered component with a monitored thermal characteristic correlating with the applied threshold, moving a computing process executing on the first at least one powered component to a second of the plurality of powered components;

wherein a one of the monitored plurality of thermal characteristics associated with the second powered component does not correlate with the threshold; and

wherein the moving is in real-time and without causing an interruption of service to an end user using the moved process.

14. The service of claim 13, wherein the first at least one powered component is a first server, the process is a computing application running on the first server, and the second powered component is a second server.

15. The service of claim 14, wherein the moved running process is a logical partition server environment appearing to the end user as an individual physical server, the logical partition server environment comprising a computing operating system and a plurality of running applications, and wherein the first and the second servers are different servers.

16. The service of claim 15, wherein the threshold is a temperature differential threshold;

and

wherein the monitored thermal characteristic associated with the first powered component is a first temperature and the monitored thermal characteristic associated with the second powered component is a second temperature lower than the first temperature; and

the computational device infrastructure correlating with the threshold comprising the first temperature differing from the second temperature by a value greater than the temperature differential threshold.

17. The service of claim 13, wherein the first powered component is a hard drive, the process is a server memory process accessing the first hard drive, and the second powered component is a second hard drive.

18. A method for moving computing processes without loss of service, comprising:

producing computer executable program code;

storing the code on a computer readable medium;

providing the program code to be deployed and executed on a computer system, the program code causing the computer system to;

monitor a plurality of thermal characteristics, each of the plurality of thermal characteristics associated with a one of a deployed plurality of powered components supporting a computing infrastructure;

apply a thermal characteristic rule set comprising a threshold to the monitored thermal characteristics; and

in response to an association of a first at least one powered component with a monitored thermal characteristic correlating with the applied threshold, move a computing process executing on the first at least one powered component to a second of the plurality of powered components;

wherein a one of the monitored plurality of thermal characteristics associated with the second powered component does not correlate with the threshold; and

wherein the moving is in real-time and without causing an interruption of service to an end user using the moved process.

19. The method of claim 18, wherein the first at least one powered component is a first server, the process is a computing application running on the first server, and the second powered component is a second server.

20. The method of claim 19, wherein the moved running process is a logical partition server environment appearing to the end user as an individual physical server, the logical partition server environment comprising a computing operating system and a plurality of running applications, and wherein the first and the second servers are different servers.

21. A programmable device comprising:

a processing means;

a memory in communication with the processing means; and

a network interface in communication with the processing means and the memory;

wherein the processing means is configured to;

monitor a plurality of thermal characteristics, each of the plurality of thermal characteristics associated with a one of a deployed plurality of powered components supporting a computing infrastructure;

apply a thermal characteristic rule set comprising a threshold to the monitored thermal characteristics; and

in response to an association of a first at least one powered component with a monitored thermal characteristic correlating with the applied threshold, move a computing process executing on the first at least one powered component to a second of the plurality of powered components;

wherein a one of the monitored plurality of thermal characteristics associated with the second powered component does not correlate with the threshold; and

wherein the moving is in real-time and without causing an interruption of service to an end user using the moved process.

22. The programmable device of claim 21, wherein the first at least one powered component is a first server, the process is a computing application running on the first server, and the second powered component is a second server.

23. The programmable device of claim 22, wherein the moved running process is a logical partition server environment appearing to the end user as an individual physical server, the logical partition server environment comprising a computing operating system and a plurality of running applications, and wherein the first and the second servers are different servers.

24. The programmable device of claim 23, wherein the threshold is a temperature differential threshold;

and

wherein the monitored thermal characteristic associated with the first powered component is a first temperature and the monitored thermal characteristic associated with the second powered component is a second temperature lower than the first temperature; and

the programmable device correlating with the threshold comprising the first temperature differing from the second temperature by a value greater than the temperature differential threshold.

25. The programmable device of claim 21, wherein the first powered component is a hard drive, the process is a server memory process accessing the first hard drive, and the second powered component is a second hard drive.