Method and apparatus for management of virtualized process collections

• US 7,685,251 B2
• Filed: 06/21/2007
• Issued: 03/23/2010
• Est. Priority Date: 06/21/2007
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: McGowan, Dilton Monroe II, Houlihan, John Richard
• Primary Examiner(s): NEURAUTER, GEORGE C
• Application Number:
  US11/766,517
• Publication Number:
  US 20080320122A1
• Time in Patent Office: 1,006 Days
• Field of Search: 709213-216, 709/224
• US Class Current: 709/215
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 11/3433 for load management allocation of a server based on load conditions G06F9/505; load rebalancing G06F9/5083; redistributing the load in a network by a load balancer H04L67/1029
• CPC Class Codes: G06F 2201/81 Threshold
• CPC Class Codes: G06F 2201/815 Virtual
• 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 9/5077 Logical partitioning of resources; Management or configuration of virtualized resources specific details on emulation or internal functioning of virtual machines G06F9/455

Abstract

A management software approach to automatic and dynamic migration of applications running within virtualized process collections while retaining state during the migration operation. Performance metrics are received for a virtualized process collection running in a first logical partition. A threshold value is calculated for the performance metrics. A performance state analysis of the performance metrics is executed to determine whether the calculated threshold value of the performance metrics exceed a maximum or minimum threshold specified in a stack tier policy for the virtualized process collection. A stack tier analysis of the performance metrics is executed to identify any trigger violations and determine a migration action to be taken for the virtualized process collection. Responsive to a determination that the number of identified trigger violations exceeds a trigger violation count, a migration event is generated to migrate the virtualized process collection to a second logical partition.

Claims

1. A computer implemented method for managing virtualized process collections, the computer implemented method comprising:

receiving performance metrics for a virtualized process collection running in a first logical partition;

calculating a threshold value for the performance metrics;

executing a performance state analysis of the performance metrics to determine whether the calculated threshold value of the performance metrics exceed a maximum or minimum threshold specified in a stack tier policy for the virtualized process collection;

executing a stack tier analysis of the performance metrics to identify any trigger violations and determine a migration action to be taken for the virtualized process collection; and

responsive to a determination that a number comprising the identified trigger violations exceeds a trigger violation count, generating a migration event to migrate the virtualized process collection to a second logical partition.

2. The computer implemented method of claim 1, wherein obtaining performance metrics for a virtualized process collection further comprises:

receiving the performance metrics from virtualized process collection agents; and

parsing value pairs in the performance metrics.

3. The computer implemented method of claim 1, wherein executing the performance state analysis further comprises:

obtaining the stack tier policy for the virtualized process collection;

determining whether the calculated threshold value of the performance metrics exceeds the maximum or minimum threshold specified for the virtualized process collection;

if the calculated threshold value of the performance metrics exceeds the maximum threshold value in the stack tier policy, recording the performance metrics as “

hot”

virtualized process collection trigger information and storing the performance metrics and virtualized process collection trigger information in a database;

if the calculated threshold value of the performance metrics exceeds the minimum threshold value in the stack tier policy, recording the performance metrics as “

cold”

virtualized process collection trigger information and storing the performance metrics and virtualized process collection trigger information in the database; and

if the calculated threshold value of the performance metrics does not exceed the maximum or minimum threshold value in the stack tier policy, storing the performance metrics in the database.

4. The computer implemented method of claim 1, wherein executing the stack tier analysis of the performance metrics to identify any trigger violations further comprises:

obtaining the stack tier policy for the virtualized process collection and the virtualized process collection trigger information;

determining that a trigger violation count has been exceeded, retrieving all performance metrics for a stack tier comprising the virtualized process collection;

calculating a performance state of the stack tier by averaging performance states of the virtualized process collections in the stack tier;

determining whether the calculated performance state of the stack tier is higher than a maximum performance state or lower than a minimum performance state specified in the stack tier policy;

if the calculated performance state is higher than the maximum performance state specified in the stack tier policy, generating a ‘

scale up’

or ‘

scale out’

migration event; and

if the calculated tier state is lower than the minimum performance state specified in the stack tier policy, generating a ‘

scale down’

or ‘

scale in’

migration event.

5. The computer implemented method of claim 4, wherein a ‘

scale down’

event migrates the virtualized process collection to a less powerful server.

6. The computer implemented method of claim 4, wherein a ‘

scale in’

event consolidates the virtualized process collection to a single server.

7. The computer implemented method of claim 4, wherein a ‘

scale up’

event migrates the virtualized process collection to a more powerful server.

8. The computer implemented method of claim 4, wherein a ‘

scale out’

event migrates the virtualized process collection to a dedicated server.

9. The computer implemented method of claim 1, wherein the threshold calculation is performed when the performance metrics are received for the virtualized process collection or during the stack tier analysis when a trigger violation count is exceeded.

10. The computer implemented method of claim 1, wherein the trigger violation count is a value which indicates how many times a trigger violation has occurred.

11. The computer implemented method of claim 1, wherein generating a migration event further comprises:

performing a checkpoint operating on the first logical partition;

executing the virtualized process collection configuration scripts on the second logical partition;

restarting the virtualized process collection on the second logical partition; and

responsive to a determination that a restart of the virtualized process collection on the second logical partition is successful, destroying the virtualized process collection on the first partition.

12. A data processing system for managing virtualized process collections, the data processing system comprising:

a bus;

a storage device connected to the bus, wherein the storage device contains computer usable code;

at least one managed device connected to the bus;

a communications unit connected to the bus; and

a processing unit connected to the bus, wherein the processing unit executes the computer usable code to receive performance metrics for a virtualized process collection running in a first logical partition;

calculate a threshold value for the performance metrics;

execute a performance state analysis of the performance metrics to determine whether the calculated threshold value of the performance metrics exceed a maximum or minimum threshold specified in a stack tier policy for the virtualized process collection;

execute a stack tier analysis of the performance metrics to identify any trigger violations and determine a migration action to be taken for the virtualized process collection; and

generate a migration event to migrate the virtualized process collection to a second logical partition in response to a determination that a number comprising the identified trigger violations exceeds a trigger violation count.

13. A computer program product for managing virtualized process collections, the computer program product comprising:

a computer usable storage medium having computer usable program code stored thereon, the computer usable program code comprising;

computer usable program code for receiving performance metrics for a virtualized process collection running in a first logical partition;

computer usable program code for calculating a threshold value for the performance metrics;

computer usable program code for executing a performance state analysis of the performance metrics to determine whether the calculated threshold value of the performance metrics exceed a maximum or minimum threshold specified in a stack tier policy for the virtualized process collection;

computer usable program code for executing a stack tier analysis of the performance metrics to identify any trigger violations and determine a migration action to be taken for the virtualized process collection; and

computer usable program code for generating a migration event to migrate the virtualized process collection to a second logical partition in response to a determination that a number comprising the identified trigger violations exceeds a trigger violation count.

14. The computer program product of claim 13, wherein the computer usable program code for obtaining performance metrics for a virtualized process collection further comprises:

computer usable program code for receiving the performance metrics from virtualized process collection agents; and

computer usable program code for parsing value pairs in the performance metrics.

15. The computer program product of claim 13, wherein the computer usable program code for executing the performance state analysis further comprises:

computer usable program code for obtaining the stack tier policy for the virtualized process collection;

computer usable program code for determining whether the calculated threshold value of the performance metrics exceeds the maximum or minimum threshold specified in a stack tier policy for the virtualized process collection;

computer usable program code for recording the performance metrics as “

hot”

virtualized process collection trigger information and storing the performance metrics and virtualized process collection trigger information in a database if the calculated threshold value of the performance metrics exceeds the maximum threshold value in the stack tier policy;

computer usable program code for recording the performance metrics as “

cold”

virtualized process collection trigger information and storing the performance metrics and virtualized process collection trigger information in the database if the calculated threshold value of the performance metrics exceeds the minimum threshold value in the stack tier policy; and

computer usable program code for storing the performance metrics in the database if the calculated threshold value of the performance metrics does not exceed the maximum or minimum threshold value in the stack tier policy.

16. The computer program product of claim 13, wherein the computer usable program code for executing the stack tier analysis of the performance metrics to identify any trigger violations further comprises:

computer usable program code for obtaining the stack tier policy for the virtualized process collection and the virtualized process collection trigger information;

computer usable program code for determining that a trigger violation count has been exceeded, retrieving all performance metrics for a stack tier comprising the virtualized process collection;

computer usable program code for calculating a performance state of the stack tier by averaging performance states of the virtualized process collections in the stack tier;

computer usable program code for determining whether the calculated performance state of the stack tier is higher than a maximum performance state or lower than a minimum performance state specified in the stack tier policy;

computer usable program code for generating a ‘

scale up’

or ‘

scale out’

migration event if the calculated performance state is higher than the maximum performance state specified in the stack tier policy; and

computer usable program code for generating a ‘

scale down’

or ‘

scale in’

migration event if the calculated tier state is lower than the minimum performance state specified in the stack tier policy.

17. The computer program product of claim 16, wherein the ‘

scale down’

migration event migrates the virtualized process collection to a less powerful server, wherein the ‘

scale in’

migration event consolidates the virtualized process collection to a single server, wherein the ‘

scale up’

migration event migrates the virtualized process collection to a more powerful server, and wherein the ‘

scale out’

migration event migrates the virtualized process collection to a dedicated server.

18. The computer program product of claim 13, wherein the threshold calculation is performed when the performance metrics are received for the virtualized process collection or during the stack tier analysis when a trigger violation count is exceeded.

19. The computer program product of claim 13, wherein the trigger violation count is a value which indicates how many times a trigger violation has occurred.

20. The computer program product of claim 13, wherein the computer usable program code for generating a migration event further comprises:

computer usable program code for performing a checkpoint operating on the first logical partition;

computer usable program code for executing the virtualized process collection configuration scripts on the second logical partition;

computer usable program code for restarting the virtualized process collection on the second logical partition; and

computer usable program code for destroying the virtualized process collection on the first partition in response to a determination that a restart of the virtualized process collection on the second logical partition is successful.