Fast dynamic measurement of connection bandwidth using a pair of packets, a packet-pair bandwidth calculation and a list of recent bandwidth measurements

• US 7,188,172 B2
• Filed: 12/09/2004
• Issued: 03/06/2007
• Est. Priority Date: 08/09/2000
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: del Val, David, Batterberry, Troy D., Schiefelbein, William F., Brown, Thomas B.
• Primary Examiner(s): Dharia; Rupal
• Assistant Examiner(s): Nguyen; Quang N.
• Application Number:
  US11/008,509
• Publication Number:
  US 20050097217A1
• Time in Patent Office: 817 Days
• Field of Search: 709/224, 709/227, 709/228, 709/225, 709/226, 709/233, 370/252, 370/473
• US Class Current: 709/224
• 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 41/509 wherein the managed service relates to media content delivery, e.g. audio, video or TV
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04L 43/0882 Utilisation of link capacity

Abstract

The fast dynamic measurement of connection bandwidth utilizes a single pair of packets to calculate bandwidth between two entities on a network (such as the Internet). This calculation is based upon the packet-pair technique. This bandwidth measurement is extremely quick. On its journey across a network, communication equipment and modems may compress a packet. This compression shrinks the size of the packet; thus, it can distort the bandwidth calculation using such a shrunken packet. To avoid this distortion, the fast dynamic measurement of connection bandwidth employs non-compressible packets. More specifically, it employs highly entropic packets. Therefore, a packet cannot be compressed during its journey. In addition, on its journey across a network, packets may be rerouted, delayed, misrouted, and the like. These momentary delays may result in a momentary bad bandwidth calculation. This problem is ameliorated by using a history list at the client that keeps track of recent measurements. The client returns the median of that list to the server. That median is the specified bandwidth.

Claims

1. A method of approximating a bandwidth between at least two entities on a communications network, the method comprising the acts of:

measuring bandwidth between the at least two entities and over the communications network, the measuring act being performed using a pair of packets and a Packet-Pair bandwidth calculation;

repeating the measuring act to produce multiple bandwidth measurements, wherein no two successive measuring acts being performed using a like pair of packets;

persisting each of the multiple bandwidth measurements into an entry in a list of bandwidth measurements entries;

finding a statistical derivation from the list of bandwidth measurements entries, such that the statistical derivation representing a most likely maximum sustainable bandwidth between the at least two entities over the communications network; and

assigning the statistical derivation to be the most likely maximum sustainable bandwidth between the at least two entities over the communications network.

2. A method as recited in claim 1 further comprising finding a median of the list, such median representing a most likely maximum sustainable bandwidth between the two entities.

3. A method as recited in claim 1, wherein during the repeating act, each performance of the measuring act employs a different pair of packets than all of the previous performances of the measuring act, wherein a pair of packets differs from another pair of packets in objectively measurable characteristics.

4. A method as recited in claim 1, wherein during the repeating act, each performance of the measuring act employs a different pair of packets than a previous ten performances of the measuring act, wherein a pair of packets differs from another pair of packets in objectively measurable characteristics.

5. A method as recited in claim 1, wherein during the repeating act, each performance of the measuring act employs a different pair of packets than a previous twenty performances of the measuring act, wherein a pair of packets differs from another pair of packets in objectively measurable characteristics.

6. A method as recited in claim 1 further comprising replacing a measurement in an entry with a most recently calculated measurement.

7. A method as recited in claim 1 further comprising clearing all of the entries in the list in response to a defined triggering event.

8. A method as recited in claim 1 further comprising clearing all of the entries in the list in response to an acquisition of a new communicative coupling to the communications network.

9. A method as recited in claim 1, wherein the packets employed by the measuring act are non-compressible.

10. A method as recited in claim 1, wherein the packets employed by the measuring act are highly entropic.

11. A method as recited in claim 1, wherein the communications network is dynamic, a dynamic network has no assurance that both packets of a pair of identical packets are handled in an identical manner while in transit over the communications network.

12. A method as recited in claim 1, wherein the communications network is the Internet.

13. A computer-readable storage medium having stored thereon a data structure, being used for performing a method of approximating a bandwidth between at least two entities on a communications network, comprising:

a list of bandwidth measurements entries, each entry being a recent bandwidth measurements between the at least two entities over the communications network;

each entry being based upon a Packet-Pair bandwidth calculation of different pairs of packets, wherein a pair of packets differs from another pair of packets in objectively measurable characteristics,

wherein the list of bandwidth measurements entries is used to find a statistical derivation representing a most likely maximum sustainable bandwidth between the at least two entities over the communications network, and

the statistical derivation is assigned to be the most likely maximum sustainable bandwidth between the at least two entities over the communications network.

14. One or more computer-readable storage media having computer-readable instructions stored thereon that, when executed by one or more computers, perform a method of approximating a bandwidth between at least two entities on a communications network, the method comprising the acts of:

measuring bandwidth between the at least two entities and over the communications network, the measuring act being performed using a pair of packets and a Packet-Pair bandwidth calculation;

repeating the measuring act to produce multiple bandwidth measurements, wherein no two successive measuring acts being performed using a like pair of packets;

persisting each of the multiple bandwidth measurements into an entry in a list of bandwidth measurements entries;

finding a statistical derivation from the list of bandwidth measurements entries, such that the statistical derivation representing a most likely maximum sustainable bandwidth between the at least two entities over the communications network; and

assigning the statistical derivation to be the most likely maximum sustainable bandwidth between the at least two entities over the communications network.

15. One or more media as recited in claim 14 further comprising finding a median of the list, such median representing a most likely maximum sustainable bandwidth between the two entities.

16. One or more media as recited in claim 14, wherein during the repeating act, each performance of the measuring act employs a different pair of packets than all of the previous performances of the measuring act, wherein a pair of packets differs from another pair of packets in objectively measurable characteristics.

17. One or more media as recited in claim 14, wherein during the repeating act, each performance of the measuring act employs a different pair of packets than a previous ten performances of the measuring act, wherein a pair of packets differs from another pair of packets in objectively measurable characteristics.

18. One or more media as recited in claim 14, wherein during the repeating act, each performance of the measuring act employs a different pair of packets than a previous twenty performances of the measuring act, wherein a pair of packets differs from another pair of packets in objectively measurable characteristics.

19. One or more media as recited in claim 14 further comprising replacing a measurement in an entry with a most recently calculated measurement.

20. One or more media as recited in claim 14 further comprising clearing all of the entries in the list in response to a defined triggering event.

21. One or more media as recited in claim 14 further comprising clearing all of the entries in the list in response to an acquisition of a new communicative coupling to the communications network.

22. One or more media as recited in claim 14, wherein the packets employed by the measuring act are non-compressible.

23. One or more media as recited in claim 14, wherein the packets employed by the measuring act are highly entropic.

24. One or more media as recited in claim 14, wherein the communications network is dynamic, a dynamic network has no assurance that both packets of a pair of identical packets are handled in an identical manner while in transit over the communications network.

25. One or more media as recited in claim 14, wherein the communications network is the Internet.