METHOD AND SYSTEM FOR DYNAMICALLY ADJUSTING PACKET SIZE TO DECREASE DELAYS OF STREAMING DATA TRANSMISSIONS ON NOISY TRANSMISSION LINES

• US 20080181259A1
• Filed: 01/31/2007
• Published: 07/31/2008
• Est. Priority Date: 01/31/2007
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Andreev, Dmitry, Grunin, Galina, Vilshansky, Gregory
• Granted Patent: US 7,733,785 B2
• Time in Patent Office: Days
• US Class Current: 370/519
• CPC Class Codes: H04L 65/752 adapting media to network capabilities
• CPC Class Codes: H04L 65/80 Responding to QoS
• CPC Class Codes: H04L 69/40 for recovering from a failure of a protocol instance or entity, e.g. service redundancy protocols, protocol state redundancy or protocol service redirection management of faults, events, alarms or notifications in data switching networks H04L41/06

Abstract

A method and system for dynamically adjusting packet size to decrease a delay of a streaming data transmission. A measurement is obtained by a measuring computing unit (i.e., data transmission server or client computing unit). The first measurement is either (1) a delay of a streaming data transmission being sent from the data transmission server to the client computing unit via a plurality of packets or (2) a frequency of damaged packets of the plurality of packets. The damaged packets contribute to the delay of the streaming data transmission. The packet size is adjusted by the data transmission server. The packet size adjusting includes utilizing the measurement and facilitating a reduction of the streaming data transmission delay. The delay results from noise on one or more communication link segments used by the streaming data transmission.

Claims

1. A computer-based method of dynamically adjusting packet size to decrease a delay of a streaming data transmission, said method comprising:

obtaining a first measurement by a measuring computing unit, wherein said first measurement is selected from the group consisting of a delay of a streaming data transmission being sent from a data transmission server to a client computing unit via a plurality of packets and a frequency of damaged packets of said plurality of packets, said damaged packets contributing to said delay of said streaming data transmission, and wherein said measuring computing unit is said data transmission server or said client computing unit; and

adjusting a packet size by said data transmission server, said packet size being a size associated with each packet of said plurality of packets, said adjusting said packet size including utilizing said first measurement and facilitating a reduction of said delay,

wherein said delay results from noise on one or more communication link segments over which said streaming data transmission is sent from said data transmission server to said client computing unit.

2. The method of claim 1, wherein said first measurement is said delay of said streaming data transmission, and wherein said method further comprises:

obtaining a target value of said delay that indicates a tolerable delay that does not require an adjustment of any packet included in said streaming data transmission;

obtaining a first set of one or more measurements of said delay, said first set of one or more measurements obtained in response to one or more expirations of one or more predefined time intervals of a first plurality of predefined time intervals, and said first set of one or more measurements including said first measurement;

determining that said first measurement is greater than said target value; and

decreasing, by said data transmission server, said packet size by a first predefined amount, said decreasing said packet size including changing said packet size from a pre-decrease size to a decreased size, and said decreasing said packet size performed in response to said determining that said first measurement is greater than said target value.

3. The method of claim 2, further comprising:

obtaining a new measurement of said delay, said obtaining said new measurement subsequent to said decreasing said packet size and subsequent to a predefined waiting period;

determining a characteristic of said new measurement, wherein said characteristic of said new measurement is selected from the group consisting of said new measurement is less than said target value, said new measurement is less than said first measurement but not less than said target value, and said new measurement is greater than or equal to said first measurement;

obtaining a second set of one or more measurements of said delay if said characteristic is said new measurement is less than said target value, said obtaining said second set of one or more measurements of said delay performed by said measuring computing unit, and said second set of one or more measurements obtained in response to one or more expirations of one or more predefined time intervals of a second plurality of predefined time intervals;

decreasing said packet size by an additional amount if said characteristic is said new measurement is less than said first measurement but not less than said target value, said decreasing said packet size by said additional amount performed by said data transmission server; and

restoring said packet size to said pre-decrease size if said characteristic is said new measurement is greater than or equal to said first measurement, said restoring performed by said data transmission server.

4. The method of claim 3, wherein said measuring computing unit is said data transmission server, and wherein said method further comprises:

sending, by said data transmission server and to said client computing unit over a primary connection, data of said streaming data transmission, said data of said streaming data transmission including a selected portion of said data of said streaming data transmission, and said primary connection being a Transmission Control Protocol (TCP) connection between said data transmission server and said client computing unit;

receiving, by said data transmission server and from said client computing unit, said selected portion via a pacing connection, said selected portion being received without substantial damage caused by said noise, said selected portion being substantially unique within said data of said streaming data transmission, and said pacing connection being a TCP connection or a User Datagram Protocol (UDP) connection;

identifying, by said data transmission server, an original position of said selected portion in said data of said streaming data transmission; and

computing, by said data transmission server, said delay, said computing including utilizing said original position.

5. The method of claim 3, wherein said measuring computing unit is said data transmission server, and wherein said method further comprises:

sending, by said data transmission server and to said client computing unit over a connection, data of said streaming data transmission, said data of said streaming data transmission including a selected portion of said data of said streaming data transmission, said connection being a TCP connection between said data transmission server and said client computing unit;

receiving, by said data transmission server and from said client computing unit, said selected portion of said data of said streaming data transmission via said connection, said selected portion being received without substantial damage caused by said noise, and said selected portion being substantially unique within said data of said streaming data transmission;

identifying, by said data transmission server, an original position of said selected portion in said data of said streaming data transmission; and

computing, by said data transmission server, said delay, said computing including utilizing said original position.

6. The method of claim 3, wherein said measuring computing unit is said data transmission server, and wherein said method further comprises:

receiving, by an application of said data transmission server and from a TCP stack, a first timestamp of a transmission of a portion of said streaming data transmission from said data transmission server to said client computing unit;

receiving, by said application of said data transmission server and from said TCP stack, a second timestamp of an acknowledgment packet indicating an acknowledgment of a receipt by said client computing unit of said portion; and

computing said delay, said computing including calculating, by said data transmission server, a difference between said first timestamp and said second timestamp.

7. The method of claim 3, wherein said measuring computing unit is said client computing unit, and wherein said method further comprises:

receiving, by said client computing unit and from said data transmission server over a primary connection, data of said streaming data transmission, said data of said streaming data transmission including a selected portion of said data of said streaming data transmission, and said primary connection being a TCP connection between said data transmission server and said client computing unit;

receiving, by said client computing unit and from said data transmission server, said selected portion via a pacing connection, said selected portion being substantially unique within said data of said streaming data transmission, and said pacing connection being a TCP connection or a UDP connection between said data transmission server and said client computing unit;

identifying, by said client computing unit, an original position of said selected portion in said data of said streaming data transmission; and

computing, by said client computing unit, said delay, said computing including utilizing said original position.

8. The method of claim 3, further comprising:

increasing, by said data transmission server in response to one or more expirations of one or more predefined time intervals of a third plurality of predefined time intervals, said packet size by a second predefined amount, said increasing said packet size including changing said packet size from a pre-increase size to an increased size;

obtaining, by said data transmission server and subsequent to said increasing, a post-increase measurement of said delay;

determining, by said data transmission server, that said post-increase measurement is less than a pre-increase measurement associated with said pre-increase size, said pre-increase measurement being said first measurement or said new measurement; and

maintaining said packet size at said increased size in response to said determining that said post-increase measurement is less than said pre-increase measurement.

9. The method of claim 3, further comprising:

increasing, by said data transmission server in response to one or more expirations of one or more predefined time intervals of a third plurality of predefined time intervals, said packet size by a second predefined amount, said increasing said packet size including changing said packet size from a pre-increase size to an increased size;

obtaining, by said data transmission server and subsequent to said increasing, a post-increase measurement of said delay;

determining, by said data transmission server, that said post-increase measurement is greater than or equal to a pre-increase measurement associated with said pre-increase size, said pre-increase measurement being said first measurement or said new measurement; and

reverting said packet size to said pre-increase size in response to said determining that said post-increase measurement is greater than or equal to said pre-increase measurement.

10. The method of claim 1, wherein said first measurement is said frequency of damaged packets, and wherein said method further comprises:

generating, by said data transmission server, a table that associates optimal packet sizes with frequencies of damaged packets in a one-to-one correspondence, each optimal packet size also associated with a length of a header of a packet of said plurality of packets;

receiving, by said data transmission server, said first measurement; and

determining, by said data transmission server, an optimal packet size for said data transmission, said optimal packet size being associated with said first measurement in said table.

11. A computing system comprising a processor and a computer-readable memory unit coupled to said processor, said memory unit containing instructions that when executed by said processor implement a method of dynamically adjusting packet size to decrease a delay of a streaming data transmission, said method comprising:

obtaining a first measurement by a measuring computing unit, wherein said first measurement is selected from the group consisting of a delay of a streaming data transmission being sent from a data transmission server to a client computing unit via a plurality of packets and a frequency of damaged packets of said plurality of packets, said damaged packets contributing to said delay of said streaming data transmission, and wherein said measuring computing unit is said data transmission server or said client computing unit; and

adjusting a packet size by said data transmission server, said packet size being a size associated with each packet of said plurality of packets, said adjusting said packet size including utilizing said first measurement and facilitating a reduction of said delay,

wherein said delay results from noise on one or more communication link segments over which said streaming data transmission is sent from said data transmission server to said client computing unit.

12. The computer system of claim 11, wherein said first measurement is said delay of said streaming data transmission, and wherein said method further comprises:

obtaining a target value of said delay that indicates a tolerable delay that does not require an adjustment of any packet included in said streaming data transmission;

obtaining a first set of one or more measurements of said delay, said first set of one or more measurements obtained in response to one or more expirations of one or more predefined time intervals of a first plurality of predefined time intervals, and said first set of one or more measurements including said first measurement;

determining that said first measurement is greater than said target value; and

decreasing, by said data transmission server, said packet size by a first predefined amount, said decreasing said packet size including changing said packet size from a pre-decrease size to a decreased size, and said decreasing said packet size performed in response to said determining that said first measurement is greater than said target value.

13. The computer system of claim 12, wherein said method further comprises:

obtaining a new measurement of said delay, said obtaining said new measurement subsequent to said decreasing said packet size and subsequent to a predefined waiting period;

determining a characteristic of said new measurement, wherein said characteristic of said new measurement is selected from the group consisting of said new measurement is less than said target value, said new measurement is less than said first measurement but not less than said target value, and said new measurement is greater than or equal to said first measurement;

obtaining a second set of one or more measurements of said delay if said characteristic is said new measurement is less than said target value, said obtaining said second set of one or more measurements of said delay performed by said measuring computing unit, and said second set of one or more measurements obtained in response to one or more expirations of one or more predefined time intervals of a second plurality of predefined time intervals;

decreasing said packet size by an additional amount if said characteristic is said new measurement is less than said first measurement but not less than said target value, said decreasing said packet size by said additional amount performed by said data transmission server; and

restoring said packet size to said pre-decrease size if said characteristic is said new measurement is greater than or equal to said first measurement, said restoring performed by said data transmission server.

14. The computer system of claim 13, wherein said measuring computing unit is said data transmission server, and wherein said method further comprises:

sending, by said data transmission server and to said client computing unit over a primary connection, data of said streaming data transmission, said data of said streaming data transmission including a selected portion of said data of said streaming data transmission, and said primary connection being a Transmission Control Protocol (TCP) connection between said data transmission server and said client computing unit;

receiving, by said data transmission server and from said client computing unit, said selected portion via a pacing connection, said selected portion being received without substantial damage caused by said noise, said selected portion being substantially unique within said data of said streaming data transmission, and said pacing connection being a TCP connection or a User Datagram Protocol (UDP) connection;

identifying, by said data transmission server, an original position of said selected portion in said data of said streaming data transmission; and

computing, by said data transmission server, said delay, said computing including utilizing said original position.

15. The computer system of claim 13, wherein said measuring computing unit is said data transmission server, and wherein said method further comprises:

sending, by said data transmission server and to said client computing unit over a connection, data of said streaming data transmission, said data of said streaming data transmission including a selected portion of said data of said streaming data transmission, said connection being a TCP connection between said data transmission server and said client computing unit;

receiving, by said data transmission server and from said client computing unit, said selected portion of said data of said streaming data transmission via said connection, said selected portion being received without substantial damage caused by said noise, and said selected portion being substantially unique within said data of said streaming data transmission;

identifying, by said data transmission server, an original position of said selected portion in said data of said streaming data transmission; and

computing, by said data transmission server, said delay, said computing including utilizing said original position.

16. The computer system of claim 13, wherein said measuring computing unit is said data transmission server, and wherein said method further comprises:

receiving, by an application of said data transmission server and from a TCP stack, a first timestamp of a transmission of a portion of said streaming data transmission from said data transmission server to said client computing unit;

receiving, by said application of said data transmission server and from said TCP stack, a second timestamp of an acknowledgment packet indicating an acknowledgment of a receipt by said client computing unit of said portion; and

computing said delay, said computing including calculating, by said data transmission server, a difference between said first timestamp and said second timestamp.

17. The computer system of claim 13, wherein said measuring computing unit is said client computing unit, and wherein said method further comprises:

receiving, by said client computing unit and from said data transmission server over a primary connection, data of said streaming data transmission, said data of said streaming data transmission including a selected portion of said data of said streaming data transmission, and said primary connection being a TCP connection between said data transmission server and said client computing unit;

receiving, by said client computing unit and from said data transmission server, said selected portion via a pacing connection, said selected portion being substantially unique within said data of said streaming data transmission, and said pacing connection being a TCP connection or a UDP connection between said data transmission server and said client computing unit;

identifying, by said client computing unit, an original position of said selected portion in said data of said streaming data transmission; and

computing, by said client computing unit, said delay, said computing including utilizing said original position.

18. The computer system of claim 13, wherein said method further comprises:

increasing, by said data transmission server in response to one or more expirations of one or more predefined time intervals of a third plurality of predefined time intervals, said packet size by a second predefined amount, said increasing said packet size including changing said packet size from a pre-increase size to an increased size;

obtaining, by said data transmission server and subsequent to said increasing, a post-increase measurement of said delay;

determining, by said data transmission server, that said post-increase measurement is less than a pre-increase measurement associated with said pre-increase size, said pre-increase measurement being said first measurement or said new measurement; and

maintaining said packet size at said increased size in response to said determining that said post-increase measurement is less than said pre-increase measurement.

19. The computer system of claim 13, wherein said method further comprises:

increasing, by said data transmission server in response to one or more expirations of one or more predefined time intervals of a third plurality of predefined time intervals, said packet size by a second predefined amount, said increasing said packet size including changing said packet size from a pre-increase size to an increased size;

obtaining, by said data transmission server and subsequent to said increasing, a post-increase measurement of said delay;

determining, by said data transmission server, that said post-increase measurement is greater than or equal to a pre-increase measurement associated with said pre-increase size, said pre-increase measurement being said first measurement or said new measurement; and

reverting said packet size to said pre-increase size in response to said determining that said post-increase measurement is greater than or equal to said pre-increase measurement.

20. The computer system of claim 11, wherein said first measurement is said frequency of damaged packets, and wherein said method further comprises:

generating, by said data transmission server, a table that associates optimal packet sizes with frequencies of damaged packets in a one-to-one correspondence, each optimal packet size also associated with a length of a header of a packet of said plurality of packets;

receiving, by said data transmission server, said first measurement; and

determining, by said data transmission server, an optimal packet size for said data transmission, said optimal packet size being associated with said first measurement in said table.

21. A computer program product comprising a computer-usable medium including computer-usable program code for dynamically adjusting packet size to decrease a delay of a streaming data transmission, said computer program product comprising:

computer-usable code for obtaining a first measurement by a measuring computing unit, wherein said first measurement is selected from the group consisting of a delay of a streaming data transmission being sent from a data transmission server to a client computing unit via a plurality of packets and a frequency of damaged packets of said plurality of packets, said damaged packets contributing to said delay of said streaming data transmission, and wherein said measuring computing unit is said data transmission server or said client computing unit; and

computer-usable code for adjusting a packet size by said data transmission server, said packet size being a size associated with each packet of said plurality of packets, said computer-usable code for adjusting said packet size including computer-usable code for utilizing said first measurement and computer-usable code for facilitating a reduction of said delay,

wherein said delay results from noise on one or more communication link segments over which said streaming data transmission is sent from said data transmission server to said client computing unit.

22. The program product of claim 21, wherein said first measurement is said delay of said streaming data transmission, and wherein said program product further comprises:

computer-usable code for obtaining a target value of said delay that indicates a tolerable delay that does not require an adjustment of any packet included in said streaming data transmission;

computer-usable code for obtaining a first set of one or more measurements of said delay, said first set of one or more measurements obtained in response to one or more expirations of one or more predefined time intervals of a first plurality of predefined time intervals, and said first set of one or more measurements including said first measurement;

computer-usable code for determining that said first measurement is greater than said target value; and

computer-usable code for decreasing, by said data transmission server, said packet size by a first predefined amount, said computer-usable code for decreasing said packet size including computer-usable code for changing said packet size from a pre-decrease size to a decreased size, wherein said decreasing said packet size is performed in response to said determining that said first measurement is greater than said target value.

23. The program product of claim 22, further comprising:

computer-usable code for obtaining a new measurement of said delay, said obtaining said new measurement being subsequent to said decreasing said packet size and subsequent to a predefined waiting period;

computer-usable code for determining a characteristic of said new measurement, wherein said characteristic of said new measurement is selected from the group consisting of said new measurement is less than said target value, said new measurement is less than said first measurement but not less than said target value, and said new measurement is greater than or equal to said first measurement;

computer-usable code for obtaining a second set of one or more measurements of said delay if said characteristic is said new measurement is less than said target value, said obtaining said second set of one or more measurements of said delay performed by said measuring computing unit, and said second set of one or more measurements obtained in response to one or more expirations of one or more predefined time intervals of a second plurality of predefined time intervals;

computer-usable code for decreasing said packet size by an additional amount if said characteristic is said new measurement is less than said first measurement but not less than said target value, said decreasing said packet size by said additional amount performed by said data transmission server; and

computer-usable code for restoring said packet size to said pre-decrease size if said characteristic is said new measurement is greater than or equal to said first measurement, said restoring performed by said data transmission server.

24. The program product of claim 23, wherein said measuring computing unit is said data transmission server, and wherein said program product further comprises:

computer-usable code for sending, by said data transmission server and to said client computing unit over a primary connection, data of said streaming data transmission, said data of said streaming data transmission including a selected portion of said data of said streaming data transmission, and said primary connection being a Transmission Control Protocol (TCP) connection between said data transmission server and said client computing unit;

computer-usable code for receiving, by said data transmission server and from said client computing unit, said selected portion via a pacing connection, said selected portion being received without substantial damage caused by said noise, said selected portion being substantially unique within said data of said streaming data transmission, and said pacing connection being a TCP connection or a User Datagram Protocol (UDP) connection;

computer-usable code for identifying, by said data transmission server, an original position of said selected portion in said data of said streaming data transmission; and

computer-usable code for computing, by said data transmission server, said delay, said computer-usable code for computing including computer-usable code for utilizing said original position.

25. The program product of claim 23, wherein said measuring computing unit is said data transmission server, and wherein said program product further comprises:

computer-usable code for sending, by said data transmission server and to said client computing unit over a connection, data of said streaming data transmission, said data of said streaming data transmission including a selected portion of said data of said streaming data transmission, said connection being a TCP connection between said data transmission server and said client computing unit;

computer-usable code for receiving, by said data transmission server and from said client computing unit, said selected portion of said data of said streaming data transmission via said connection, said selected portion being received without substantial damage caused by said noise, and said selected portion being substantially unique within said data of said streaming data transmission;

computer-usable code for identifying, by said data transmission server, an original position of said selected portion in said data of said streaming data transmission; and

computer-usable code for computing, by said data transmission server, said delay, said computer-usable code for computing including computer-usable code for utilizing said original position.

26. The program product of claim 23, wherein said measuring computing unit is said data transmission server, and wherein said program product further comprises:

computer-usable code for receiving, by an application of said data transmission server and from a TCP stack, a first timestamp of a transmission of a portion of said streaming data transmission from said data transmission server to said client computing unit;

computer-usable code for receiving, by said application of said data transmission server and from said TCP stack, a second timestamp of an acknowledgment packet indicating an acknowledgment of a receipt by said client computing unit of said portion; and

computer-usable code for computing said delay, said computer-usable code for computing including computer-usable code for calculating, by said data transmission server, a difference between said first timestamp and said second timestamp.

27. The program product of claim 23, wherein said measuring computing unit is said client computing unit, and wherein said program product further comprises:

computer-usable code for receiving, by said client computing unit and from said data transmission server over a primary connection, data of said streaming data transmission, said data of said streaming data transmission including a selected portion of said data of said streaming data transmission, and said primary connection being a TCP connection between said data transmission server and said client computing unit;

computer-usable code for receiving, by said client computing unit and from said data transmission server, said selected portion via a pacing connection, said selected portion being substantially unique within said data of said streaming data transmission, and said pacing connection being a TCP connection or a UDP connection between said data transmission server and said client computing unit;

computer-usable code for identifying, by said client computing unit, an original position of said selected portion in said data of said streaming data transmission; and

computer-usable code for computing, by said client computing unit, said delay, said computer-usable code for computing including computer-usable code for utilizing said original position.

28. The program product of claim 23, further comprising:

computer-usable code for increasing, by said data transmission server in response to one or more expirations of one or more predefined time intervals of a third plurality of predefined time intervals, said packet size by a second predefined amount, said computer-usable code for increasing said packet size including computer-usable code for changing said packet size from a pre-increase size to an increased size;

computer-usable code for obtaining, by said data transmission server and subsequent to said increasing, a post-increase measurement of said delay;

computer-usable code for determining, by said data transmission server, that said post-increase measurement is less than a pre-increase measurement associated with said pre-increase size, said pre-increase measurement being said first measurement or said new measurement; and

computer-usable code for maintaining said packet size at said increased size in response to said determining that said post-increase measurement is less than said pre-increase measurement.

29. The program product of claim 23, further comprising:

computer-usable code for increasing, by said data transmission server in response to one or more expirations of one or more predefined time intervals of a third plurality of predefined time intervals, said packet size by a second predefined amount, said computer-usable code for increasing said packet size including computer-usable code for changing said packet size from a pre-increase size to an increased size;

computer-usable code for obtaining, by said data transmission server and subsequent to said increasing, a post-increase measurement of said delay;

computer-usable code for determining, by said data transmission server, that said post-increase measurement is greater than or equal to a pre-increase measurement associated with said pre-increase size, said pre-increase measurement being said first measurement or said new measurement; and

computer-usable code for reverting said packet size to said pre-increase size in response to said determining that said post-increase measurement is greater than or equal to said pre-increase measurement.

30. The program product of claim 21, wherein said first measurement is said frequency of damaged packets, and wherein said program product further comprises:

computer-usable code for generating, by said data transmission server, a table that associates optimal packet sizes with frequencies of damaged packets in a one-to-one correspondence, each optimal packet size also associated with a length of a header of a packet of said plurality of packets;

computer-usable code for receiving, by said data transmission server, said first measurement; and

computer-usable code for determining, by said data transmission server, an optimal packet size for said data transmission, said optimal packet size being associated with said first measurement in said table.

31. A process for supporting computing infrastructure, said process comprising providing at least one support service for at least one of creating, integrating, hosting, maintaining, and deploying computer-readable code in a computing system, wherein the code in combination with the computing system is capable of performing a method of dynamically adjusting packet size to decrease a delay of a streaming data transmission, said method comprising:

obtaining a first measurement by a measuring computing unit, wherein said first measurement is selected from the group consisting of a delay of a streaming data transmission being sent from a data transmission server to a client computing unit via a plurality of packets and a frequency of damaged packets of said plurality of packets, said damaged packets contributing to said delay of said streaming data transmission, and wherein said measuring computing unit is said data transmission server or said client computing unit; and

adjusting a packet size by said data transmission server, said packet size being a size associated with each packet of said plurality of packets, said adjusting said packet size including utilizing said first measurement and facilitating a reduction of said delay,

wherein said delay results from noise on one or more communication link segments over which said streaming data transmission is sent from said data transmission server to said client computing unit.

32. The process of claim 31, wherein said first measurement is said delay of said streaming data transmission, and wherein said method further comprises:

obtaining a target value of said delay that indicates a tolerable delay that does not require an adjustment of any packet included in said streaming data transmission;

obtaining a first set of one or more measurements of said delay, said first set of one or more measurements obtained in response to one or more expirations of one or more predefined time intervals of a first plurality of predefined time intervals, and said first set of one or more measurements including said first measurement;

determining that said first measurement is greater than said target value; and

decreasing, by said data transmission server, said packet size by a first predefined amount, said decreasing said packet size including changing said packet size from a pre-decrease size to a decreased size, and said decreasing said packet size performed in response to said determining that said first measurement is greater than said target value.

33. The process of claim 32, wherein said method further comprises:

obtaining a new measurement of said delay, said obtaining said new measurement subsequent to said decreasing said packet size and subsequent to a predefined waiting period;

determining a characteristic of said new measurement, wherein said characteristic of said new measurement is selected from the group consisting of said new measurement is less than said target value, said new measurement is less than said first measurement but not less than said target value, and said new measurement is greater than or equal to said first measurement;

obtaining a second set of one or more measurements of said delay if said characteristic is said new measurement is less than said target value, said obtaining said second set of one or more measurements of said delay performed by said measuring computing unit, and said second set of one or more measurements obtained in response to one or more expirations of one or more predefined time intervals of a second plurality of predefined time intervals;

decreasing said packet size by an additional amount if said characteristic is said new measurement is less than said first measurement but not less than said target value, said decreasing said packet size by said additional amount performed by said data transmission server; and

restoring said packet size to said pre-decrease size if said characteristic is said new measurement is greater than or equal to said first measurement, said restoring performed by said data transmission server.

34. The process of claim 33, wherein said measuring computing unit is said data transmission server, and wherein said method further comprises:

sending, by said data transmission server and to said client computing unit over a primary connection, data of said streaming data transmission, said data of said streaming data transmission including a selected portion of said data of said streaming data transmission, and said primary connection being a Transmission Control Protocol (TCP) connection between said data transmission server and said client computing unit;

receiving, by said data transmission server and from said client computing unit, said selected portion via a pacing connection, said selected portion being received without substantial damage caused by said noise, said selected portion being substantially unique within said data of said streaming data transmission, and said pacing connection being a TCP connection or a User Datagram Protocol (UDP) connection;

identifying, by said data transmission server, an original position of said selected portion in said data of said streaming data transmission; and

computing, by said data transmission server, said delay, said computing including utilizing said original position.

35. The process of claim 33, wherein said measuring computing unit is said data transmission server, and wherein said method further comprises:

sending, by said data transmission server and to said client computing unit over a connection, data of said streaming data transmission, said data of said streaming data transmission including a selected portion of said data of said streaming data transmission, said connection being a TCP connection between said data transmission server and said client computing unit;

receiving, by said data transmission server and from said client computing unit, said selected portion of said data of said streaming data transmission via said connection, said selected portion being received without substantial damage caused by said noise, and said selected portion being substantially unique within said data of said streaming data transmission;

identifying, by said data transmission server, an original position of said selected portion in said data of said streaming data transmission; and

computing, by said data transmission server, said delay, said computing including utilizing said original position.

36. The process of claim 33, wherein said measuring computing unit is said data transmission server, and wherein said method further comprises:

receiving, by an application of said data transmission server and from a TCP stack, a first timestamp of a transmission of a portion of said streaming data transmission from said data transmission server to said client computing unit;

receiving, by said application of said data transmission server and from said TCP stack, a second timestamp of an acknowledgement packet indicating an acknowledgement of a receipt by said client computing unit of said portion; and

computing said delay, said computing including calculating, by said data transmission server, a difference between said first timestamp and said second timestamp.

37. The process of claim 33, wherein said measuring computing unit is said client computing unit, and wherein said method further comprises:

receiving, by said client computing unit and from said data transmission server over a primary connection, data of said streaming data transmission, said data of said streaming data transmission including a selected portion of said data of said streaming data transmission, and said primary connection being a TCP connection between said data transmission server and said client computing unit;

receiving, by said client computing unit and from said data transmission server, said selected portion via a pacing connection, said selected portion being substantially unique within said data of said streaming data transmission, and said pacing connection being a TCP connection or a UDP connection between said data transmission server and said client computing unit;

identifying, by said client computing unit, an original position of said selected portion in said data of said streaming data transmission; and

computing, by said client computing unit, said delay, said computing including utilizing said original position.

38. The process of claim 33, wherein said method further comprises:

increasing, by said data transmission server in response to one or more expirations of one or more predefined time intervals of a third plurality of predefined time intervals, said packet size by a second predefined amount, said increasing said packet size including changing said packet size from a pre-increase size to an increased size;

obtaining, by said data transmission server and subsequent to said increasing, a post-increase measurement of said delay;

determining, by said data transmission server, that said post-increase measurement is less than a pre-increase measurement associated with said pre-increase size, said pre-increase measurement being said first measurement or said new measurement; and

maintaining said packet size at said increased size in response to said determining that said post-increase measurement is less than said pre-increase measurement.

39. The process of claim 33, wherein said method further comprises:

increasing, by said data transmission server in response to one or more expirations of one or more predefined time intervals of a third plurality of predefined time intervals, said packet size by a second predefined amount, said increasing said packet size including changing said packet size from a pre-increase size to an increased size;

obtaining, by said data transmission server and subsequent to said increasing, a post-increase measurement of said delay;

determining, by said data transmission server, that said post-increase measurement is greater than or equal to a pre-increase measurement associated with said pre-increase size, said pre-increase measurement being said first measurement or said new measurement; and

reverting said packet size to said pre-increase size in response to said determining that said post-increase measurement is greater than or equal to said pre-increase measurement.

40. The process of claim 31, wherein said first measurement is said frequency of damaged packets, and wherein said method further comprises:

generating, by said data transmission server, a table that associates optimal packet sizes with frequencies of damaged packets in a one-to-one correspondence, each optimal packet size also associated with a length of a header of a packet of said plurality of packets;

receiving, by said data transmission server, said first measurement; and

determining, by said data transmission server, an optimal packet size for said data transmission, said optimal packet size being associated with said first measurement in said table.