Scheduling a Parallel Job in a System of Virtual Containers

• US 20120060171A1
• Filed: 09/02/2010
• Published: 03/08/2012
• Est. Priority Date: 09/02/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bobroff, Norman, Fong, Liana Liyow, Liu, Yanbin, Seelam, Seetharami R.
• Granted Patent: US 8,869,164 B2
• Time in Patent Office: Days
• US Class Current: 718/105
• CPC Class Codes: G06F 2209/504 Resource capping
• CPC Class Codes: G06F 9/505 considering the load
• CPC Class Codes: G06F 9/5077 Logical partitioning of resources; Management or configuration of virtualized resources specific details on emulation or internal functioning of virtual machines G06F9/455
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Methods and apparatus are provided for scheduling parallel jobs in a system of virtual containers. At least one parallel job is assigned to a plurality of containers competing for a total capacity of a larger container, wherein the at least one parallel job comprises a plurality of tasks. The assignment method comprises determining a current utilization and a potential free capacity for each of the plurality of competing containers; and assigning the tasks to one of the plurality of containers based on the potential free capacities and at least one predefined scheduling policy. The predefined scheduling policy may comprise, for example, one or more of load balancing, server consolidation, maximizing the current utilizations, minimizing a response time of the parallel job and satisfying quality of service requirements. The load balancing can be achieved, for example, by assigning a task to a container having a highest potential free capacity.

Claims

1. A method for assigning at least one parallel job to a plurality of containers competing for a total capacity of a larger container, wherein the at least one parallel job comprises a plurality of tasks, the method comprising:

determining a current utilization and a potential free capacity for each of the plurality of competing containers; and

assigning the tasks to one of the plurality of containers based on the potential free capacities and at least one predefined scheduling policy.

2. The method of claim 1, wherein the potential free capacity is based on one or more of a total capacity, a comparison of one or more of the current utilizations to one or more corresponding equilibrium capacities and a relative resource weight of each of the plurality of competing containers, wherein the equilibrium capacity for each of the plurality of competing containers indicates a capacity that the corresponding container is entitled to.

3. The method of claim 1, wherein the assigning step further comprises the step of evaluating resource demands of the tasks.

4. The method of claim 1, wherein the at least one predefined scheduling policy comprises one or more of load balancing, server consolidation, maximizing the current utilizations, minimizing a response time of the parallel job and satisfying quality of service requirements.

5. The method of claim 4, wherein the assigning step performs the load balancing by assigning a task to a container having a highest potential free capacity.

6. The method of claim 5, wherein the assigning step assigns a task to one of two containers having a substantially equal potential free capacity based on an equilibrium capacity.

7. The method of claim 1, wherein the assigning step evaluates an impact of a new parallel job on existing one or more existing jobs.

8. The method of claim 1, further comprising the step of evaluating concurrent execution requirements of the tasks.

9. The method of claim 1, wherein the determining step further comprises the step of obtaining one or more of a minimum and maximum capacity for each of the plurality of containers.

10. The method of claim 1, further comprising the step of recalculating the potential free capacity when the set of plurality of containers is changed.

11. The method of claim 1, further comprising the step of recalculating the potential free capacity after the assignment of each work element.

12. An apparatus for assigning at least one parallel job to a plurality of containers competing for a total capacity of a larger container, wherein the at least one parallel job comprises a plurality of tasks, the apparatus comprising:

a memory; and

at least one processor, coupled to the memory, operative to;

determine a current utilization and a potential free capacity for each of the plurality of competing containers; and

assign the tasks to one of the plurality of containers based on the potential free capacities and at least one predefined scheduling policy.

13. The apparatus of claim 12, wherein the potential free capacity is based on one or more of a total capacity, a comparison of one or more of the current utilizations to one or more corresponding equilibrium capacities and a relative resource weight of each of the plurality of competing containers, wherein the equilibrium capacity for each of the plurality of competing containers indicates a capacity that the corresponding container is entitled to.

14. The apparatus of claim 12, wherein the assignment evaluates resource demands of the tasks.

15. The apparatus of claim 12, wherein the at least one predefined scheduling policy comprises one or more of load balancing, server consolidation, maximizing the current utilizations, minimizing a response time of the parallel job and satisfying quality of service requirements.

16. The apparatus of claim 15, wherein the assignment performs the load balancing by assigning a task to a container having a highest potential free capacity.

17. The apparatus of claim 12, wherein the assignment evaluates an impact of a new parallel job on existing one or more existing jobs.

18. The apparatus of claim 12, wherein the processor is further configured to evaluate concurrent execution requirements of the tasks.

19. An article of manufacture for assigning at least one parallel job to a plurality of containers competing for a total capacity of a larger container, wherein the at least one parallel job comprises a plurality of tasks, the article of manufacture comprising a machine readable storage medium containing one or more programs which when executed implement the steps of:

determining a current utilization and a potential free capacity for each of the plurality of competing containers; and

assigning the tasks to one of the plurality of containers based on the potential free capacities and at least one predefined scheduling policy.

20. The article of manufacture of claim 19, wherein the potential free capacity is based on one or more of a total capacity, a comparison of one or more of the current utilizations to one or more corresponding equilibrium capacities and a relative resource weight of each of the plurality of competing containers, wherein the equilibrium capacity for each of the plurality of competing containers indicates a capacity that the corresponding container is entitled to.

21. The article of manufacture of claim 19, wherein the assignment evaluates resource demands of the tasks.

22. The article of manufacture of claim 19, wherein the at least one predefined scheduling policy comprises one or more of load balancing, server consolidation, maximizing the current utilizations, minimizing a response time of the parallel job and satisfying quality of service requirements.

23. The article of manufacture of claim 22, wherein the assignment performs the load balancing by assigning a task to a container having a highest potential free capacity.

24. The article of manufacture of claim 19, wherein the assignment evaluates an impact of a new parallel job on existing one or more existing jobs.

25. The article of manufacture of claim 19, further comprising the step of evaluating concurrent execution requirements of the tasks.