OPTIMIZING SOFTWARE APPLICATIONS IN A NETWORK

• US 20130060960A1
• Filed: 09/01/2011
• Published: 03/07/2013
• Est. Priority Date: 09/01/2011
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bachmann, David W., Forlenza, Randolph M., SANG, Miguel
• Application Number:
  US13/223,537
• Publication Number:
  US 20130060960A1
• Time in Patent Office: Days
• US Class Current: 709/233
• CPC Class Codes: H04L 47/32 by discarding or delaying data units, e.g. packets or frames
• CPC Class Codes: H04L 47/36 by determining packet size, e.g. maximum transfer unit [MTU]

Abstract

A method, system and computer program product include determining a dynamic target latency time for sending packets over a network, where the dynamic target latency time is based on at least one policy and delaying packets that are smaller than a maximum transmission unit (MTU) from being sent over the network until the dynamic target latency time has elapsed.

Claims

1. A method comprising:

determining a dynamic target latency time for sending packets over a network, wherein the dynamic target latency time is based on at least one policy; and

delaying packets that are smaller than a maximum transmission unit (MTU) from being sent over the network until the dynamic target latency time has elapsed.

2. The method of claim 1, wherein the determining the dynamic target latency time for sending the packets over the network comprises:

providing the dynamic target latency time for sending the packets over the network by an adaptive algorithm.

3. The method of claim 1, wherein the determining the dynamic target latency time for sending the packets over the network comprises:

assigning the dynamic target latency time to a service tier.

4. The method of claim 1, wherein the determining the dynamic target latency time for sending the packets over the network comprises:

assigning a first dynamic target latency time to a first service tier;

assigning a second dynamic target latency time to a second service tier, wherein the first service tier is higher than the second service tier, wherein the first dynamic target latency time is shorter than the second dynamic target latency time; and

selecting one of the first and second dynamic target latency times corresponding to the respective first or second service tier that is associated with the packets.

5. The method of claim 1, wherein the determining the dynamic target latency time for sending the packets over the network comprises:

determining a plurality of latency times; and

computing an average of the latency times.

6. The method of claim 1, wherein the determining the dynamic target latency time for sending the packets over the network comprises:

determining a current latency time; and

computing a percentage of the current latency time.

7. The method of claim 1, the determining the dynamic target latency time for sending the packets over the network comprises:

receiving the dynamic target latency time from an application providing the data to be sent.

8. A computer program product for optimizing software applications in a network, the computer program product comprising:

a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code configured to;

determine a dynamic target latency time for sending packets over a network, wherein the dynamic target latency time is based on at least one policy; and

delay packets that are smaller than a maximum transmission unit (MTU) from being sent over the network until the dynamic target latency time has elapsed.

9. The computer program code of claim 8,

wherein when determining the dynamic target latency time for sending the packets over the network, the computer readable program code is configured to:

provide the dynamic target latency time for sending the packets over the network by an adaptive algorithm.

10. The computer program code of claim 8, wherein when determining the dynamic target latency time for sending the packets over the network, the computer readable program code is configured to:

assign the dynamic target latency time to a service tier.

11. The computer program code of claim 8, wherein when determining the dynamic target latency time for sending the packets over the network, the computer readable program code is configured to:

assign a first dynamic target latency time to a first service tier;

assign a second dynamic target latency time to a second service tier, wherein the first service tier is higher than the second service tier, wherein the first dynamic target latency time is shorter than the second dynamic target latency time; and

select one of the first and second dynamic target latency times corresponding to the respective first or second service tier that is associated with the packets.

12. The computer program code of claim 8, wherein when determining the dynamic target latency time for sending the packets over the network, the computer readable program code is configured to:

determine a plurality of latency times; and

compute an average of the latency times.

13. The computer program code of claim 8, wherein when determining the dynamic target latency time for sending the packets over the network, the computer readable program code is configured to:

determine a current latency time; and

compute a percentage of the current latency time.

14. The computer program code of claim 8, wherein when determining the dynamic target latency time for sending the packets over the network, the computer readable program code is configured to:

receive the dynamic target latency time from an application providing the data to be sent.

15. A system comprising:

a processor; and

a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code which when executed by the processor executes a method comprising;

determining a dynamic target latency time for sending packets over a network, wherein the dynamic target latency time is based on at least one policy; and

delaying packets that are smaller than a maximum transmission unit (MTU) from being sent over the network until the dynamic target latency time has elapsed.

16. The system of claim 15,

wherein the determining the dynamic target latency time for sending the packets over the network comprises:

providing the dynamic target latency time for sending the packets over the network by an adaptive algorithm.

17. The system of claim 15, wherein the determining the dynamic target latency time for sending the packets over the network comprises:

assigning the dynamic target latency time to a service tier.

18. The system of claim 15, wherein the determining the dynamic target latency time for sending the packets over the network comprises:

assigning a first dynamic target latency time to a first service tier;

assigning a second dynamic target latency time to a second service tier, wherein the first service tier is higher than the second service tier, wherein the first dynamic target latency time is shorter than the second dynamic target latency time; and

selecting one of the first and second dynamic target latency times corresponding to the respective first or second service tier that is associated with the packets.

19. The system of claim 15, wherein the determining the dynamic target latency time for sending the packets over the network comprises:

determining a plurality of latency times; and

computing an average of the latency times.

20. The system of claim 15, wherein the determining the dynamic target latency time for sending the packets over the network comprises:

determining a current latency time; and

computing a percentage of the current latency time.

21. The system of claim 15, the determining the dynamic target latency time for sending the packets over the network comprises:

receiving the dynamic target latency time from an application providing the data to be sent.

22. A method comprising:

determining a dynamic target latency time for sending packets over a network, comprising;

determining one or more values; and

computing the dynamic target latency time using the determined value; and

delaying packets that are smaller than a maximum transmission unit (MTU) from being sent over the network until the dynamic target latency time has elapsed.

23. The method of claim 22, wherein the one or more values include one or more measured latency times.

24. The method of claim 22, wherein the one or more values include one or more measured latency times, and wherein the computing the dynamic target latency time using the determined value comprises:

computing a percentage of the one or more measured latency times.

25. The method of claim 22, wherein the one or more values include one or more measured latency times, and wherein the computing the dynamic target latency time using the determined value comprises:

computing an average of the one or more measured latency times.