System and method for metering the performance of a data processing system

• US 20050138422A1
• Filed: 12/23/2003
• Published: 06/23/2005
• Est. Priority Date: 12/23/2003
• Status: Abandoned Application

• Current Assignee: Unisys Corporation
• Original Assignee: Unisys Corporation
• Inventors: Hancock, Peter J., Tanning, Ronald S., Hansen, Lee B., Lenz, Daniel J., Mikkelsen, Hans C., Hoffman, Philip M.
• Application Number:
  US10/744,685
• Publication Number:
  US 20050138422A1
• Time in Patent Office: Days
• US Class Current: 726/4
• CPC Class Codes: H04L 9/00 Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols

Abstract

A system and method for metering usage of a data processing system and scaling system performance is disclosed. In one embodiment, an authorization key is purchased that specifies both a baseline performance level and a ceiling performance level. The cost of the baseline and ceiling performance levels is included in the price of the key. After the key is installed on the data processing system, the system performance level is monitored and averaged over predetermined time periods. The customer is charged on a “pay-as-you-go” basis for any time periods during which the average performance level exceeds the baseline performance level. Performance of the data processing system is not allowed to exceed the ceiling level obtained with the authorization key. In one embodiment, the baseline level may be set to zero so that all performance consumption is purchased by the customer as it is utilized.

Claims

1. A method of metering performance of a data processing system, comprising:

monitoring the performance of the data processing system; and

charging a customer based on utilized performance that exceeds a baseline performance level.

2. The method of claim 1, wherein the baseline performance level is zero.

3. The method of claim 1, and further including allowing the customer to pre-pay for the baseline performance level.

4. The method of claim 1, and further including:

recording information for deriving the utilized performance; and

billing the customer based on the utilized performance averaged over a predetermined period of time and the predetermined period of time.

5. The method of claim 4, and further including allowing the customer to access the recorded information.

6. The method of claim 4, and further including periodically transferring the recorded information to a billing authority.

7. The method of claim 3, and further including limiting the performance of the data processing system to no more than a ceiling performance level.

8. The method of claim 7, and further including providing an authorization key for use with the data processing system that specifies at least one of the baseline performance level and the ceiling performance level.

9. The method of claim 7, wherein the data processing system may be configured in any of multiple configurations, each including at least one enabled processor, and further including:

configuring the data processing system in a selected one of the configurations;

determining the maximum performance level of the selected configuration;

deriving a scaling factor=(the ceiling performance level)/(the maximum performance level); and

scaling the performance of each of the enabled processors by the scaling factor.

10. The method of claim 9, wherein the scaling step is performed by forcing each of the enabled processors in the selected configuration to an idle state for a predetermined percentage of time determined by the scaling factor.

11. The method of claim 9, wherein a predetermined time interval is selected as a recording period, and further including performing the following steps during each of one or more of the recoding periods:

for each of the enabled processors, recording idle time wherein work is not being performed by the processor; and

calculating a utilized performance level for the recording period based on the maximum performance level of the selected configuration and the idle time recorded for each of the enabled processors.

12. The method of claim 11, and further including:

averaging the utilized performance level over an averaging period which is equal to, or greater than, the recoding period; and

charging the customer based on the amount the averaged utilized performance level exceeds the baseline performance level.

13. The method of claim 12, and further including charging the customer based, in part, on the length of the averaging period.

14. The method of claim 11, wherein a predetermined interval of time is selected as an averaging period, and further including performing the following steps during each of one or more of the averaging periods:

averaging, for each of the recording periods included within the averaging period, the utilized performance levels to obtain an averaged system utilized performance;

calculating an excess utilized performance level as the amount the averaged system utilized performance exceeds the baseline performance level;

calculating an excess consumption for the averaging period as a product of the averaging period and the excess utilized performance level; and

wherein the charging step comprises charging the customer for the excess consumption.

15. The method of claim 16, wherein a predetermined time period is selected as a billing period, and wherein, for each of one or more billing periods, the charging step includes charging the customer for the excess consumption during each of the averaging periods within the billing period.

16. The method of claim 7, wherein the data processing system may be used in any of multiple configurations, and wherein at least one of the multiple configurations includes multiple processing partitions that each includes at least one enabled processor, and further including:

configuring the data processing system in a configuration that includes multiple processing partitions;

determining the maximum performance level of a selected one of the processing partitions;

allocating a portion of the ceiling performance level to the selected processing partition;

deriving a scaling factor=(the allocated portion of the ceiling performance level)/(the maximum performance level); and

scaling the performance of each enable processor in the selected processing partition by the scaling factor.

17. The method of claim 16, and further including repeating the determining, allocating, deriving, and scaling steps for all of the processing partitions.

18. The method of claim 7, wherein the data processing system may be used in any of multiple configurations, and wherein at least one of the multiple configurations includes multiple processing partitions that each includes at least one enabled processor, and further including:

configuring the data processing system in a configuration that includes multiple processing partitions;

selecting a time interval for use as a recording period;

for each of the processors in each of the processing partitions, recording as idle time the time during the recording period wherein work is not being performed by the processor;

for each of the processing partitions, calculating a utilized performance during the recording period based on the maximum performance level of the processing partition and the idle time recorded for each of the enabled processors in the processing partition;

obtaining a system utilized performance during the recording period by adding the utilized performance for each of the processing partitions during the recording period; and

repeating the selecting, recording, calculating and obtaining steps for one or more of the recording periods.

19. The method of claim 18, and further including;

averaging the system utilized performance at predetermined averaging periods that are equal to, or greater than, the recording period; and

charging the customer at predetermined billing periods based on averaged system utilized performance derived for each of the averaging periods within the billing period.

20. The method of claim 18, wherein a predetermined interval of time is selected as an averaging period, and wherein the following step is performed during each of one or more averaging periods:

averaging the system utilized performance obtained for each of the recording periods within the averaging period;

calculating an excess utilized performance level as the amount the averaged system utilized performance exceeds the baseline performance level;

calculating an excess consumption for the averaging time period as the product of the averaging period and the excess utilized performance level; and

wherein the charging step comprises charging the customer for the excess consumption.

21. The method of Clam 20, wherein the charging step includes billing the customer for the excess consumption occurring during each of the averaging periods within a predetermined billing period.

22. A data processing system, comprising:

one or more processors;

a memory coupled to the processors; and

Software Controlled Performance Facility (SCPF) software stored within the memory to monitor performance of at least one of the processors, and to charge a customer based on the performance that is utilized.

23. The system of claim 22, and further including a system console communicatively coupled to the processors to enable one or more of the processors for use within the system;

and wherein the processors being monitored are the enabled one or more processors.

24. The system of claim 23, wherein the SCPF software further includes:

means for deriving a system utilized performance for the data processing system based on the amount of time each of the enabled processors is performing work and on a maximum performance level that may be delivered by all of the enabled processors; and

means for charging the customer based on the system utilized performance.

25. The system of claim 24, wherein the system console includes means for configuring the data processing system in any selected one of multiple possible configurations, and wherein the selected configuration determines the maximum performance level.

26. The system of claim 25, wherein the selected configuration includes at least one cache memory coupled to the enabled processors.

27. The system of claim 24, wherein the memory stores data specifying a baseline performance level, and wherein the SCPF software includes means for charging the customer based on the amount the system utilized performance of the enabled processors exceeds the baseline performance level.

28. The system of claim 27, wherein the memory further stores data specifying a ceiling performance level, and wherein the SCPF software includes means for limiting the performance of the data processing system to no more than the ceiling performance level.

29. The system of claim 28, wherein the SCPF software includes means for allowing a user to modify at least one of the baseline performance level and the ceiling performance level.

30. The system of claim 24,

wherein the system console includes means for configuring the data processing system into multiple processing partitions, each including at least one of the enabled processors;

and

further including means for monitoring utilized performance of each of the processing partitions based on the amount of time each enabled processor within the processing partition is performing work and on a maximum performance level that may be delivered by the processing partition.

31. The system of claim 30, and further including deriving the system utilized performance as the sum of the utilized performance of each of the processing partitions.

32. The system of claim 30, and further including:

means for averaging the utilized performance of each of the processing partitions over a predetermined averaging time period; and

means for deriving averaged system utilized performance as the sum of the averaged utilized performance of each of the processing partitions over the averaging time period.

33. The system of claim 32, wherein the memory stores data specifying a baseline performance level, and wherein the SCPF includes means for charging the customer based on the amount the averaged system utilized performance exceeds the baseline performance level.

34. The system of claim 33, and wherein the SCPF further includes means for charging the customer based, in part, on the averaging time period.

35. The system of claim 32, and further including billing software for billing the customer at each of predetermined billing time periods base on the averaged system utilized performance for each of the averaging time periods included in the billing time period.

36. The system of claim 33, wherein the billing software includes means for billing the customer at each of predetermined billing time periods based on an amount the averaged system utilized performance exceeds the baseline performance level for each of the averaging time periods included in the billing time period.

37. The system of claim 22, wherein the SCPF includes means for storing performance data describing the monitored performance, and means for allowing the customer to access the performance data.

38. A system for charging for performance of a data processing system having one or more processors, comprising:

means for recording performance of the one or more processors;

means for determining system utilized performance of the data processing system from the recorded performance of the one or more processors; and

means for charging a customer based on the system utilized performance of the data processing system.

39. The system of claim 38, wherein the means for determining utilized performance includes means for determining a maximum performance of the data processing system.

40. The system of claim 39, and further including:

means for obtaining a baseline performance level;

means for determining whether the system utilized performance exceeds the baseline performance level; and

means for charging the customer based upon the amount the system utilized performance exceeds the baseline performance level.

41. The system of claim 40, and further including:

system console means for creating multiple processing partitions that each includes at least one processor;

means for determining a maximum performance level for each of the processing partitions;

means for determining utilized performance of each of the processing partitions from the respective maximum performance level of the processing partition and work performed by the processors included within the processing partition; and

means for determining the system utilized performance as the sum of the utilized performance of all processing partitions.

42. The system of claim 41, and further including:

means for averaging the system utilized performance over an averaging period; and

means for charging the customer based on the system utilized performance over the averaging period and further on the length of the averaging period.