System and method for replacing an inoperable master workload management process

• US 20060136929A1
• Filed: 12/21/2004
• Published: 06/22/2006
• Est. Priority Date: 12/21/2004
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Crawford, Isom L. Jr., Turicchi, Thomas Edwin Jr., Miller, Troy Don
• Granted Patent: US 7,979,862 B2
• Time in Patent Office: Days
• US Class Current: 718/105
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system

Abstract

In one embodiment, a method comprises executing respective workload management processes within a plurality of computing compartments to allocate at least processor resources to applications executed within the plurality of computing compartments, selecting a master workload management process to reallocate processor resources between the plurality of computing compartments in response to requests from the workload management processes to receive additional resources, monitoring operations of the master workload management process by the other workload management processes, detecting, by the other workload management processes, when the master workload management process becomes inoperable, and selecting a replacement master workload management process by the other workload management processes in response to the detecting.

Claims

1. A method, comprising:

executing respective workload management processes within a plurality of computing compartments to allocate at least processor resources to applications executed within said plurality of computing compartments;

selecting a master workload management process to reallocate processor resources between said plurality of computing compartments in response to requests from said workload management processes to receive additional resources;

monitoring operations of said master workload management process by the other workload management processes;

detecting, by the other workload management processes, when said master workload management process becomes inoperable; and

selecting a replacement master workload management process by the other workload management processes in response to said detecting.

2. The method of claim 1 wherein said monitoring comprises:

determining whether said master workload management process performs a method call to said other workload management processes.

3. The method of claim 2 wherein said method call is a method call to obtain information associated with reallocation decisions to be made by said master workload management process.

4. The method of claim 1 wherein said monitoring comprises:

determining whether said master workload management process fails to respond to a method call.

5. The method of claim 1 further comprising:

operating a timer associated with a last detected operation of said master workload management process.

6. The method of claim 1 wherein each of said other workload management processes transitions to a non-member state in response to said detecting.

7. The method of claim 6 wherein each of said other workload management processes communicate with each other to determine whether each of said other workload management processes have reached said non-member state before performing said selecting a replacement.

8. The method of claim 1 further comprising:

reestablishing operation of said previous master workload management process;

generating an exception when said previous master workload management process attempts to perform an operation associated with reallocation of processing resources after said selecting a replacement has been performed; and

joining, by said previous master workload management process, said other workload management processes as a member process.

9. The method of claim 1 wherein said computing compartments are virtual partitions.

10. The method of claim 1 further comprising:

generating an identifier to identify a current master workload management process.

11. The method of claim 1 wherein said current master workload management process passes said identifier to methods that perform allocation of resources between said plurality of computing compartments.

12. A computer-readable medium comprising executable instructions, comprising:

code for creating respective workload management processes for each of a plurality of computing compartments, wherein said workload management processes send requests to obtain additional resources to a master workload management process of said workload management processes;

code for monitoring operations of said master workload management process;

code for detecting when said master workload management processes becomes inoperable; and

code for selecting a replacement master workload management process by the other workload management processes in response to said detecting.

13. The computer-readable medium of claim 12 wherein said code for monitoring is operable to determine whether said master workload management process has performed a method call to said other workload management processes.

14. The computer-readable medium of claim 13 wherein said method call is a method call to obtain information associated with reallocation decisions to be made by said master workload management process.

15. The computer-readable medium of claim 12 further comprising:

code for maintaining a timer associated with a last detected operation of said master workload management process.

16. The computer-readable medium of claim 12 further comprising:

code for communicating between each of said plurality of other workload management processes to determine whether each of said other workload management processes have detected that said master workload management process has become inoperable.

17. The computer-readable medium of claim 16 wherein said code for selecting a replacement is operable only after each of said other workload management processes have detected that said master workload management process has become inoperable.

18. The computer-readable medium of claim 12 further comprising:

code for generating an exception when said previous master workload process attempts to perform an operation associated with reallocation of processing resources after a replacement has been selected.

19. The computer-readable medium of claim 18 wherein said previous master workload management process calls a method to re-associate with said other workload management processes after receiving said exception.

20. The computer-readable medium of claim 12 further comprising:

code for generating an identifier to identify a current master workload management process.