Facilitating optimization of response time in computer networks

• US 20060085541A1
• Filed: 10/19/2004
• Published: 04/20/2006
• Est. Priority Date: 10/19/2004
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Vashaw, Barton C., Gissel, Thomas R., Cuomo, Gennaro A., Gunther, Harvey W.
• Application Number:
  US10/968,015
• Publication Number:
  US 20060085541A1
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: H04L 41/083 for increasing network speed
• CPC Class Codes: H04L 41/0896 Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities flow or congestion control using dynamic resource allocation, e.g. in-call renegotiation, H04L47/76
• CPC Class Codes: H04L 69/04 Protocols for data compression, e.g. ROHC
• CPC Class Codes: H04L 69/24 Negotiation of communication capabilities

Abstract

A system and method are disclosed for leveraging bandwidth and processor utilization to advantageously influence response time performance. The objective of such leveraging is to maximize transaction throughput (e.g., requests per second) between a pair of servers when the servers are connected through less than optimal networks and/or network connections. Such an optimization is accomplished by determining whether or not adjusting request and/or reply sizes by applying a compression factor (i.e., to facilitate compression) will have a desirable influence on response time performance. Such determination is based on decision criteria including, but are not limited to, network protocol performance, CPU utilization, bandwidth utilization, and estimates of the CPU time and network time costs of sending compressed verses uncompressed data.

Claims

1. A method configured for facilitating optimization of resource utilization in a data processing system, comprising:

determining operating parameter levels exhibited by a data processing system, wherein at least a portion of said operating parameter levels influence response time performance for the data processing system;

determining resource optimization mode dependent upon at least one of said operating parameter levels; and

determining data compression influence on said response time performance dependent upon said resource optimization mode.

2. The method of claim 1 wherein determining said operating parameter levels includes at least one of monitoring processor utilization, monitoring aggregate bandwidth utilization, measuring network parameters and estimating compressibility of outbound data.

3. The method of claim 1 wherein determining said resource optimization mode includes:

selecting processor optimization mode in response to determining that said response time performance for the data processing unit is bound by processor utilization;

selecting bandwidth optimization mode in response to determining that said response time performance for the data processing system is bound by bandwidth utilization; and

selecting round-trip time optimization mode in response to determining that said response time performance for the data processing system is unbound by processor utilization and bandwidth utilization.

4. The method of claim 3 wherein optimizing said data compression influence includes at least one of:

in response to choosing processor optimization mode, comparing processor cycles required for compressing outbound data and sending said compressed outbound data and processor cycles required for sending said outbound data in uncompressed form;

in response to choosing bandwidth optimization mode, comparing bandwidth utilization associated with sending said outbound data in compressed form and bandwidth utilization associated with sending said outbound data in uncompressed form; and

in response to choosing round-trip time optimization mode, comparing round-trip time for outbound data in compressed form and round-trip time for outbound data in uncompressed form.

5. The method of claim 1 wherein optimizing said data compression influence includes at least one of:

in response to determining that response time performance for the data processing unit is bound by processor utilization, comparing processor cycles required for compressing outbound data and sending said compressed outbound data and processor cycles required for sending said outbound data in uncompressed form;

in response to determining that said response time performance for the data processing unit is bound by bandwidth utilization, comparing bandwidth utilization associated with sending said outbound data in compressed form and bandwidth utilization associated with sending said outbound data in uncompressed form; and

in response to determining that said response time performance is unbound by processor utilization and bandwidth utilization, comparing round-trip time for outbound data in compressed form and round-trip time for outbound data in uncompressed form.

6. The method of claim 1, further comprising:

compressing outbound data from the data processing systems in response to optimizing said data compression in a manner provides a desired influence, wherein optimizing said data compression influence includes determining a compression factor and compressing said outbound data includes applying the compression factor to said outbound data.

7. The method of claim 6, further comprising:

updating information used in determining the compression factor in response to optimizing the influence of said data compression.

8. A method configured for facilitating optimization of resource utilization in a data processing system, comprising:

determining resource optimization mode for a data processing system dependent upon at least one of a plurality of operating parameter levels exhibited by the data processing system;

implementing a resource optimization strategy dependent upon at least one of said resource optimization modes, said operating parameter levels, and reference responsiveness parameters; and

updating information utilized in determining the resource optimization strategy dependent upon information derived from said implementing the resource optimization strategy.

9. The method of claim 8 wherein determining said resource optimization mode includes:

selecting processor optimization mode in response to determining that said response time performance for the data processing unit is bound by processor utilization;

selecting bandwidth optimization mode in response to determining that said response time performance for the data processing system is bound by bandwidth utilization; and

selecting round-trip time optimization mode in response to determining that said response time performance for the data processing system is unbound by processor utilization and bandwidth utilization.

10. The method of claim 9 wherein implementing said resource optimization strategy includes determining data compression influence on said response time performance dependent upon said resource optimization mode.

11. The method of claim 10 wherein optimizing said data compression influence includes at least one of:

in response to determining that response time performance for the data processing unit is bound by processor utilization, comparing processor cycles required for compressing outbound data and sending said compressed outbound data and processor cycles required for sending said outbound data in uncompressed form;

in response to determining that said response time performance for the data processing unit is bound by bandwidth utilization, comparing bandwidth utilization associated with sending said outbound data in compressed form and bandwidth utilization associated with sending said outbound data in uncompressed form; and

in response to determining that said response time performance is unbound by processor utilization and bandwidth utilization, comparing round-trip time for outbound data in compressed form and round-trip time for outbound data in uncompressed form.

12. The method of claim 10 wherein implementing said resource optimization strategy includes compressing outbound data from the data processing systems in response to optimizing said data compression in a manner that provides a desired influence, wherein optimizing said data compression influence includes determining a compression factor and compressing said outbound data includes applying the compression factor to said outbound data.

13. The method of claim 12, further comprising:

updating information used in determining the compression factor in response to optimizing the influence of said data compression.

14. The method of claim 8 wherein:

implementing the resource optimization strategy is performed in response to optimizing said data compression in a manner that provides a desired influence; and

said implementing includes;

implementing one of uncompressed data transmission and a first data compression method in response to processor utilization exhibited by the data processing system exceeding a respective specified threshold;

implementing a second data compression method in response to bandwidth utilization exhibited by the data processing system exceeding a respective specified threshold and

implementing a round-trip time optimization strategy in response to said processor utilization and said bandwidth utilization being below said respective specified thresholds.

15. The method of claim 14 wherein:

implementing the first data compression method includes sending outbound data in a compressed form created using a lossy-type data compression method;

implementing the second data compression method includes compressing outbound data in a manner that provides for a corresponding compression-induced increase in response time performance; and

implementing the round-trip optimization strategy includes sending said outbound data in a compressed form in response to determining round-trip time for sending said outbound data in said compressed form is less than round-trip time for said outbound data in uncompressed form.

16. A method configured for facilitating optimization of resource utilization in a data processing system, comprising:

determining operating parameter levels exhibited by a data processing system, wherein said operating parameter levels influence response time performance exhibited by the data processing system;

implementing one of uncompressed data transmission and a first data compression method in response to processor utilization exhibited by the data processing system exceeding a respective specified threshold;

implementing a second data compression method in response to bandwidth utilization exhibited by the data processing system exceeding a respective specified threshold; and

implementing round-trip time optimization in response to said processor utilization and said bandwidth utilization being below said respective specified thresholds.

17. The method of claim 16 wherein:

implementing the first data compression method includes sending outbound data in a compressed form created using a lossy-type data compression method;

implementing the second data compression method includes compressing outbound data in a manner that provides for a corresponding compression-induced increase in response time performance; and

implementing the round-trip optimization strategy includes sending said outbound data in a compressed form in response to determining round-trip time for sending said outbound data in said compressed form is less than round-trip time for said outbound data in uncompressed form.

18. A data processing system, comprising:

at least one data processing device;

instructions processable by said at least one data processing device; and

an apparatus from which said instructions are accessible by said at least one data processing device;

wherein said instructions are configured for enabling said at least one data processing device to facilitate;

determining operating parameter levels exhibited by a data processing system, wherein at least a portion of said operating parameter levels influence response time performance for the data processing system;

determining resource optimization mode dependent upon at least one of said operating parameter levels; and

optimizing data compression influence on said response time performance dependent upon said resource optimization mode.

19. The system of claim 18 wherein determining said operating parameter levels includes at least one of monitoring processor utilization, monitoring aggregate bandwidth utilization, measuring network parameters and estimating compressibility of outbound data.

20. The system of claim 18 wherein determining said resource optimization mode includes:

selecting processor optimization in response to determining that said response time performance for the data processing unit is bound by processor utilization;

selecting bandwidth optimization in response to determining that said response time performance for the data processing system is bound by bandwidth utilization; and

selecting round-trip time optimization in response to determining that said response time performance for the data processing system is unbound by processor utilization and bandwidth utilization.

21. The system of claim 20 wherein optimizing said data compression influence includes at least one of:

in response to choosing processor optimization, comparing processor cycles required for compressing outbound data and sending said compressed outbound data and processor cycles required for sending said outbound data in uncompressed form;

in response to choosing bandwidth optimization, comparing bandwidth utilization associated with sending said outbound data in compressed form and bandwidth utilization associated with sending said outbound data in uncompressed form; and

in response to choosing round-trip time optimization, comparing round-trip time for outbound data in compressed form and round-trip time for outbound data in uncompressed form.

22. The system of claim 18 wherein optimizing said data compression influence includes at least one of:

in response to determining that response time performance for the data processing unit is bound by processor utilization, comparing processor cycles required for compressing outbound data and sending said compressed outbound data and processor cycles required for sending said outbound data in uncompressed form;

in response to determining that said response time performance for the data processing unit is bound by bandwidth utilization, comparing bandwidth utilization associated with sending said outbound data in compressed form and bandwidth utilization associated with sending said outbound data in uncompressed form; and

in response to determining that said response time performance is unbound by processor utilization and bandwidth utilization, comparing round-trip time for outbound data in compressed form and round-trip time for outbound data in uncompressed form.

23. The system of claim 18 wherein said instructions are further configured for enabling said at least one data processing device to facilitate:

compressing outbound data from the data processing systems in response to determining that said data compression provides a desired influence, wherein optimizing said data compression influence includes determining a compression factor and compressing said outbound data includes applying the compression factor to said outbound data.

24. The system of claim 23 wherein said instructions are further configured for enabling said at least one data processing device to facilitate:

updating information used in determining the compression factor in response to optimizing the influence of said data compression.

25. A data processing system, comprising:

at least one data processing device;

instructions processable by said at least one data processing device; and

an apparatus from which said instructions are accessible by said at least one data processing device;

wherein said instructions are configured for enabling said at least one data processing device to facilitate;

determining resource optimization mode for a data processing system dependent upon at least one of a plurality of operating parameter levels exhibited by the data processing system;

implementing a resource optimization strategy dependent upon at least one of said resource optimization mode, said operating parameter levels, and reference responsiveness parameters; and

updating information utilized in determining the resource optimization strategy dependent upon information derived from said implementing the resource optimization strategy.

26. The system of claim 25 wherein determining said resource optimization mode includes:

selecting processor optimization in response to determining that said response time performance for the data processing unit is bound by processor utilization;

selecting bandwidth optimization in response to determining that said response time performance for the data processing system is bound by bandwidth utilization; and

selecting round-trip time optimization in response to determining that said response time performance for the data processing system is unbound by processor utilization and bandwidth utilization.

27. The system of claim 26 wherein implementing the resource optimization strategy include optimizing data compression influence on said response time performance dependent upon said resource optimization mode.

28. The system of claim 27 wherein optimizing said data compression influence includes at least one of:

in response to determining that response time performance for the data processing unit is bound by processor utilization, comparing processor cycles required for compressing outbound data and sending said compressed outbound data and processor cycles required for sending said outbound data in uncompressed form;

in response to determining that said response time performance for the data processing unit is bound by bandwidth utilization, comparing bandwidth utilization associated with sending said outbound data in compressed form and bandwidth utilization associated with sending said outbound data in uncompressed form; and

in response to determining that said response time performance is unbound by processor utilization and bandwidth utilization, comparing round-trip time for outbound data in compressed form and round-trip time for outbound data in uncompressed form.

29. The system of claim 27 wherein implementing aid resource optimization strategy includes compressing outbound data from the data processing systems in response to optimizing said data compression in a manner that provides a desired influence, wherein optimizing said data compression influence includes determining a compression factor and compressing said outbound data includes applying the compression factor to said outbound data.

30. The system of claim 29 wherein said instructions are further configured for enabling said at least one data processing device to facilitate:

updating information used in determining the compression factor in response to optimizing the influence of said data compression.

31. The system of claim 25 wherein said instructions are further configured for enabling said at least one data processing device to facilitate:

optimizing data compression influence on said response time performance dependent upon said resource optimization mode; and

implementing the resource optimization strategy in response to optimizing said data compression in a manner that provides a desired influence, wherein said implementing includes;

implementing one of uncompressed data transmission and a first resource optimization strategy in response to processor utilization exhibited by the data processing system exceeding a respective specified threshold;

implementing a second resource optimization strategy in response to bandwidth utilization exhibited by the data processing system exceeding a respective specified threshold and

implementing a round-trip time optimization strategy in response to said processor utilization and said bandwidth utilization being below said respective specified thresholds.

32. The system of claim 31 wherein:

implementing the first resource optimization strategy includes sending outbound data in a compressed form created using a lossy-type data compression method;

implementing the second resource optimization strategy includes compressing outbound data in a manner that provides for a corresponding compression-induced increase in response time performance; and

implementing the round-trip optimization strategy includes sending said outbound data in a compressed form in response to determining round-trip time for sending said outbound data in said compressed form is less than round-trip time for said outbound data in uncompressed form.

33. A data processing system, comprising:

at least one data processing device;

instructions processable by said at least one data processing device; and

an apparatus from which said instructions are accessible by said at least one data processing device;

wherein said instructions are configured for enabling said at least one data processing device to facilitate;

determining operating parameter levels exhibited by a data processing system, wherein said operating parameter levels influence response time performance exhibited by the data processing system;

implementing one of uncompressed data transmission and a first data compression method in response to processor utilization exhibited by the data processing system exceeding a respective specified threshold;

implementing a second data compression method in response to bandwidth utilization exhibited by the data processing system exceeding a respective specified threshold; and

implementing a round-trip time optimization strategy in response to said processor utilization and said bandwidth utilization being below said respective specified thresholds.

34. The system of claim 33 wherein:

implementing the first data compression method includes sending outbound data in a compressed form created using a lossy-type data compression method;

implementing the second data compression method includes compressing outbound data in a manner that provides for a corresponding compression-induced increase in response time performance; and

implementing the round-trip optimization strategy includes sending said outbound data in a compressed form in response to determining round-trip time for sending said outbound data in said compressed form is less than round-trip time for said outbound data in uncompressed form.