IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0203329
(2008-09-03)
|
등록번호 |
US-8214843
(2012-07-03)
|
발명자
/ 주소 |
- Boss, Gregory J.
- Doran, James R.
- Hamilton, II, Rick A.
- Sand, Anne R.
|
출원인 / 주소 |
- International Business Machines Corporation
|
대리인 / 주소 |
|
인용정보 |
피인용 횟수 :
16 인용 특허 :
6 |
초록
▼
Energy costs for conducting compute tasks at diverse data center sites are determined and are then used to route such tasks in a most efficient manner. A given compute task is first evaluated to predict potential energy consumption. The most favorable real-time energy costs for the task are determin
Energy costs for conducting compute tasks at diverse data center sites are determined and are then used to route such tasks in a most efficient manner. A given compute task is first evaluated to predict potential energy consumption. The most favorable real-time energy costs for the task are determined at the various data center sites. The likely time period of the more favorable cost as well as the stability at the data center are additional factors. A workload dispatcher then forwards the selected compute task to the data center having the most favorable real-time energy costs. Among the criteria used to select the most favorable data center is a determination that the proposed center presently has the resources for the task.
대표청구항
▼
1. A method for dynamically shifting compute workloads among data center sites based on real-time energy costs, the method comprising: evaluating via a processing unit a compute processing task of a compute workload that is capable of being relocated to determine a potential energy consumption neede
1. A method for dynamically shifting compute workloads among data center sites based on real-time energy costs, the method comprising: evaluating via a processing unit a compute processing task of a compute workload that is capable of being relocated to determine a potential energy consumption needed in watts and a length of time needed to perform the compute task;determining for each of a plurality of available data center sites respective energy prices per watt of energy provided by the sites and time durations for each of the respective energy prices, via the processing unit; andrelocating via the processing unit the compute task to a second data center site of the plurality of data center sites having a lowest energy price from a first of the data center sites that the compute job is assigned to if: a total cost to relocate the compute job to the second site and complete the compute job at the second site energy price is lower than a cost to complete the compute job at the first site energy price;the second site time energy price duration is long enough to complete the compute task if moved to the second site; andthe compute job workload of the first site will remain stable for a minimum required thrashing prevention threshold amount of time after moving the compute job to the second site; or moving the compute job to the second site will not exceed a specified threshold maximum number of moves for the compute job. 2. The method according to claim 1 further comprising: halting and bringing the compute job to a quiescent state before relocating the compute job to the second site. 3. The method according to claim 2, further comprising: relocating the compute job to the second site if the compute job is not able to be completed at the first site, by pausing the compute job and completing a remainder of the compute job at the second site after the relocating. 4. The method according to claim 3, including choosing the second site as a function of determining the second site is an optimum data center location for conducting the compute task. 5. The method according to claim 4, wherein the relocating the compute job to the second site is further including a function of stabilizing the workload among the data center sites. 6. The method according to claim 4, further comprising: re-evaluating the relocation of the compute task as often as energy costs change at any of the plurality of data sites. 7. A method for effecting compliance with power usage specifications through positive feedback, the method comprising: integrating computer-readable program code into a computer system comprising a processing unit, a computer readable memory and a computer readable tangible storage device, wherein the computer readable program code is embodied on the computer readable tangible storage device and comprises instructions that, when executed by the processing unit via the computer readable memory, cause the processing unit to:evaluate a compute processing task of a compute workload that is capable of being relocated to determine a potential energy consumption needed in watts and a length of time needed to perform the compute task;determine for each of a plurality of available data center sites respective energy prices per watt of energy provided by the sites and time durations for each of the respective energy prices; andrelocate the compute task to a second data center site of the plurality of data center sites having a lowest energy price from a first of the data center sites that the compute job is assigned to if:a total cost to relocate the compute job to the second site and complete the compute job at the second site energy price is lower than a cost to complete the compute job at the first site energy price;the second site time energy price duration is long enough to complete the compute task if moved to the second site; andthe compute job workload of the first site will remain stable for a minimum required thrashing prevention threshold amount of time after moving the compute job to the second site; ormoving the compute job to the second site will not exceed a specified threshold maximum number of moves for the compute job. 8. The method of claim 7, wherein the computer readable program code instructions, when executed by the computer processing unit, further cause the computer processing unit to halt and bring the compute job to a quiescent state before relocating the compute job to the second site. 9. The method of claim 8, wherein the computer readable program code instructions, when executed by the computer processing unit, further cause the computer processing unit to relocate the compute job to the second site if the compute job is not able to be completed at the first site, by pausing the compute job and completing a remainder of the compute job at the second site after the relocating. 10. The method of claim 9, wherein the computer readable program code instructions, when executed by the computer processing unit, further cause the computer processing unit to choose the second site as a function of determining the second site is an optimum data center location for conducting the compute task. 11. The method of claim 10, wherein the computer readable program code instructions, when executed by the computer processing unit, further cause the computer processing unit to relocate the compute job to the second site as a function of stabilizing the compute task workload among the plurality data center sites. 12. The method of claim 11, wherein the computer readable program code instructions, when executed by the computer processing unit, further cause the computer processing unit to re-evaluate the relocation of the compute task as often as energy costs change at any of the plurality of data sites. 13. A system, comprising: a processing unit in communication with a computer readable memory and a tangible computer-readable storage device;wherein the processing unit, when executing program instructions stored on the tangible computer-readable storage device via the computer readable memory:evaluates a compute processing task of a compute workload that is capable of being relocated to determine a potential energy consumption needed in watts and a length of time needed to perform the compute task;determines for each of a plurality of available data center sites respective energy prices per watt of energy provided by the sites and time durations for each of the respective energy prices; andrelocates the compute task to a second data center site of the plurality of data center sites having a lowest energy price from a first of the data center sites that the compute job is assigned to if:a total cost to relocate the compute job to the second site and complete the compute job at the second site energy price is lower than a cost to complete the compute job at the first site energy price;the second site time energy price duration is long enough to complete the compute task if moved to the second site; andthe compute job workload of the first site will remain stable for a minimum required thrashing prevention threshold amount of time after moving the compute job to the second site; ormoving the compute job to the second site will not exceed a specified threshold maximum number of moves for the compute job. 14. The system of claim 13, wherein the computer readable program code instructions, when executed by the computer processing unit, further cause the computer processing unit to halt and bring the compute job to a quiescent state before relocating the compute job to the second site. 15. The system of claim 14, wherein the computer readable program code instructions, when executed by the computer processing unit, further cause the computer processing unit to relocate the compute job to the second site if the compute job is not able to be completed at the first site, by pausing the compute job and completing a remainder of the compute job at the second site after the relocating. 16. The system of claim 15, wherein the computer readable program code instructions, when executed by the computer processing unit, further cause the computer processing unit to choose the second site as a function of determining the second site is an optimum data center location for conducting the compute task. 17. The system of claim 15, wherein the computer readable program code instructions, when executed by the computer processing unit, further cause the computer processing unit to relocate the compute job to the second site as a function of stabilizing the compute task workload among the plurality data center sites. 18. The system of claim 17, wherein the computer readable program code instructions, when executed by the computer processing unit, further cause the computer processing unit to re-evaluate the relocation of the compute task as often as energy costs change at any of the plurality of data sites. 19. An article of manufacture, comprising: a computer readable tangible storage device having computer readable program code embodied therewith, the computer readable program code comprising instructions that, when executed by a computer processing unit, cause the computer processing unit to:evaluate a compute processing task of a compute workload that is capable of being relocated to determine a potential energy consumption needed in watts and a length of time needed to perform the compute task;determine for each of a plurality of available data center sites respective energy prices per watt of energy provided by the sites and time durations for each of the respective energy prices; andrelocate the compute task to a second data center site of the plurality of data center sites having a lowest energy price from a first of the data center sites that the compute job is assigned to if:a total cost to relocate the compute job to the second site and complete the compute job at the second site energy price is lower than a cost to complete the compute job at the first site energy price;the second site time energy price duration is long enough to complete the compute task if moved to the second site; andthe compute job workload of the first site will remain stable for a minimum required thrashing prevention threshold amount of time after moving the compute job to the second site; ormoving the compute job to the second site will not exceed a specified threshold maximum number of moves for the compute job. 20. The article of manufacture of claim 19, wherein the computer readable program code instructions, when executed by the computer processing unit, further cause the computer processing unit to halt and bring the compute job to a quiescent state before relocating the compute job to the second site. 21. The article of manufacture of claim 20, wherein the computer readable program code instructions, when executed by the computer processing unit, further cause the computer processing unit to relocate the compute job to the second site if the compute job is not able to be completed at the first site, by pausing the compute job and completing a remainder of the compute job at the second site after the relocating. 22. The article of manufacture of claim 21, wherein the computer readable program code instructions, when executed by the computer processing unit, further cause the computer processing unit to choose the second site as a function of determining the second site is an optimum data center location for conducting the compute task. 23. The article of manufacture of claim 22, wherein the computer readable program code instructions, when executed by the computer processing unit, further cause the computer processing unit to relocate the compute job to the second site as a function of stabilizing the compute task workload among the plurality data center sites. 24. The article of manufacture of claim 23, wherein the computer readable program code instructions, when executed by the computer processing unit, further cause the computer processing unit to re-evaluate the relocation of the compute task as often as energy costs change at any of the plurality of data sites.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.