Method, a computer program product, and a carrier for indicating one-way latency in a data network

• US 10,178,009 B2
• Filed: 07/18/2017
• Issued: 01/08/2019
• Est. Priority Date: 09/22/2004
• Status: Active Grant

• Current Assignee: Accedian Networks Inc. (Cisco Systems, Inc.)
• Original Assignee: Accedian Networks Inc. (Cisco Systems, Inc.)
• Inventors: Hansson, Kjell, Hagsand, Olof
• Primary Examiner(s): Onamuti, Gbemileke J
• Application Number:
  US15/652,630
• Publication Number:
  US 20180006919A1
• Time in Patent Office: 539 Days
• CPC Class Codes: G06F 1/12 Synchronisation of different clock signals provided by a plurality of clock generators
• CPC Class Codes: H04J 3/0638 Clock or time synchronisation among nodes; Internode synchronisation synchronization for ring networks H04L12/422; data switching networks with synchronous transmission H04L12/43
• CPC Class Codes: H04J 3/0667 Bidirectional timestamps, e.g. NTP or PTP for compensation of clock drift and for compensation of propagation delays arrangements for monitoring round trip delays in packet switching networks H04L43/0864
• CPC Class Codes: H04J 3/0682 by delay compensation, e.g. by compensation of propagation delay or variations thereof, by ranging
• CPC Class Codes: H04L 2212/00 Encapsulation of packets
• CPC Class Codes: H04L 43/067 using time frame reporting
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04L 43/0858 One way delays
• CPC Class Codes: H04L 65/65 Network streaming protocols, e.g. real-time transport protocol [RTP] or real-time control protocol [RTCP]
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
• CPC Class Codes: H04L 7/10 Arrangements for initial synchronisation

Abstract

Disclosed herein is a method, a computer program product, and a carrier for indicating one-way latency in a data network (N) between a first node (A) and a second node (B), wherein the data network (N) lacks continuous clock synchronization, comprising: a pre-synchronisation step, a measuring step, a post-synchronisation step, an interpolation step, and generating a latency profile. The present invention also relates to a computer program product incorporating the method, a carrier comprising the computer program product, and a method for indicating server functionality based on the first aspect.

Claims

1. A method for generating a one-way latency profile in a network comprising:

transmitting a plurality of pre-synchronization messages between a requester node comprising a first clock and a responder node comprising a second clock;

calculating, a pre-synchronization offset value between said first clock and said second clock, using data in one of said pre-synchronization messages;

transmitting a plurality of measuring messages comprising a sending time between said requester node and said responder node;

recording, by said responder node, said sending time and a receiving time of each of said measuring messages;

transmitting a plurality of post-synchronization messages between said requester node and said responder node;

calculating, using a post-synchronization data set contained in one of said post-synchronization messages, a post-synchronization offset value between said first clock and said second clock;

interpolating said sending and receiving times of said measuring messages with said pre-synchronization offset value and said post-synchronization offset value to generate said one-way latency profile.

2. The method of claim 1, wherein each pre-synchronization message has a minimum round trip time.

3. The method of claim 2, wherein said round trip time is calculated according to T_i.4−

T_i.1−

(T_i.3−

T_i.2), where i is in an interval [1 . . . N], N is the number of said pre-synchronization messages sent by said requester node, T_i.1 is a first timestamp of said requester node sending said pre-synchronization messages, T_i.2 is a second timestamp of said responder node receiving said pre-synchronization messages, T_i.3 is a third timestamp of said responder node sending said pre-synchronization messages, and T_i.4 is a fourth timestamp of said requester node receiving said pre-synchronization messages.

4. The method of claim 1, wherein said pre-synchronization offset value is calculated according to ((T₂−

T₁)+(T₃−

T₄))/2, where T₁ is a first timestamp of said requester node sending said pre-synchronization messages, T₂ is a second timestamp of said responder node receiving said pre-synchronization messages, T₃ is a third timestamp of said responder node sending said pre-synchronization messages, and T₄ is a fourth timestamp of said requester node receiving said pre-synchronization messages.

5. The method of claim 4, further comprising:

setting a pre-synchronization absolute clock value as said fourth timestamp of said requester node receiving said pre-synchronization messages.

6. The method of claim 1, further comprising:

measuring an overhead of said requester node to send said measuring messages.

7. The method of claim 1 further comprising:

measuring an overhead of said responder node to receive said measuring messages.

8. The method of claim 1, wherein each post-synchronization message has a minimum round trip time.

9. The method of claim 8, wherein said round trip time is calculated according to T_i,4−

T_i,1−

(T_i,3−

T_i,2), where i is in an interval [1 . . . N], N is the number of said post-synchronization messages sent by said requester node, T_i.1 is a first timestamp of said requester node sending said post-synchronization messages, T_i.2 is a second timestamp of said responder node receiving said post-synchronization messages, T_i.3 is a third timestamp of said responder node sending said post-synchronization messages, and T_i.4 is a fourth timestamp of said requester node receiving said post-synchronization messages.

10. The method of claim 1, wherein said post-synchronization offset value is calculated according to ((T₂−

T₁)+(T₃−

T₄))/2, where T₁ is a first timestamp of said requester node sending said post-synchronization messages, T₂ is a second timestamp of said responder node receiving said post-synchronization messages, T₃ is a third timestamp of said responder node sending said post-synchronization messages and T₄ is a fourth timestamp of said requester node receiving said post-synchronization messages.

11. The method of claim 10, further comprising:

setting a post-synchronization absolute clock value as said fourth timestamp of said requester node receiving said post-synchronization messages.

12. The method of claim 1, wherein said interpolation comprises calculating a rate bias according to rate_bias=(CDIFF1−

CDIFF0)/(CABS1−

CABS0), where CDIFF1 is said post-synchronization offset value, CDIFF0 is said pre-synchronization offset value, CABS1 is said post-synchronization absolute clock value, and CABS0 is said pre-synchronization absolute clock value.

13. The method of claim 12, wherein said one-way latency profile between said requester node and said responder node is calculated according to Ti.₂−

Ti.₁+CDIFF0+rate_bias*(Ti.₁−

CABS0)−

Ks−

Kr, where i is in an interval [1 . . . N], N is the number of said measuring messages sent by said requester node, Ti.₁ is a first timestamp of said requester node sending said measuring messages, Ti.₂ is a second timestamp of said responder node receiving said measuring messages, CDIFF0 is said pre-synchronization offset value, rate_bias is said rate bias, CABS0 is said pre-synchronization absolute clock value, Ks is said overhead of said requester node, and Kr is said overhead of said responder node.

14. The method of claim 1, wherein said plurality of pre-synchronization messages, said plurality of measuring messages, and said plurality of post-synchronization messages are encapsulated using a UDP/IP protocol.

15. The method of claim 1 wherein said plurality of pre-synchronization messages, said plurality of measuring messages, and said plurality of post-synchronization messages are encoded using a RTP protocol.

16. A system to calculate a one-way latency profile between a requester node coupled to a first clock and a responder node coupled to a second clock, comprising:

a first network module executing on said responder node to calculate a pre-synchronization offset value between said first clock and second clock based on one or more of a plurality of pre-synchronization messages transmitted by a second network module executing on a second processor on said requester node to said first module;

said second network module transmitting a plurality of measuring messages comprising a sending time to said first network module;

said first network module recording the sending time and a receiving time of the measuring messages;

said first network module calculating a post-synchronization offset value between said first clock and second clock based on a plurality of post-synchronization messages transmitted between said requester node and a second network module executing on said responder node; and

said first network module interpolating said sending and receiving times with said pre-synchronization offset value and post-synchronization offset value to generate said one-way latency profile from said plurality of latency measurements.

17. The system of claim 16, wherein said pre-synchronization offset value and said pre-synchronization absolute clock value are calculated from said pre-synchronization messages.

18. The system of claim 17, wherein each pre-synchronization message has a minimum round trip time.

19. The system of claim 18, wherein said round trip time is calculated according to T_i.4−

T_i.1−

(T_i.3−

T_i.2), where i is in an interval [1 . . . N], N is the number of said pre-synchronization messages sent by said requester node, T_i.1 is a first timestamp of said requester node sending said pre-synchronization messages, T_i.2 is a second timestamp of said responder node receiving said pre-synchronization messages, T_i.3 is a third timestamp of said responder node sending said pre-synchronization messages, and T_i.4 is a fourth timestamp of said requester node receiving said pre-synchronization messages.

20. The system of claim 19, wherein said pre-synchronization absolute clock value is set as said fourth timestamp of said requester node receiving said pre-synchronization messages.

21. The system of claim 16, wherein said pre-synchronization offset value is calculated according to ((T₂−

T₁)+(T₃−

T₄))/2, where T₁ is a first timestamp of said requester node sending said pre-synchronization messages, T₂ is a second timestamp of said responder node receiving said pre-synchronization messages, T₃ is a third timestamp of said responder node sending said pre-synchronization messages, and T₄ is a fourth timestamp of said requester node receiving said pre-synchronization messages.

22. The system of claim 16, wherein said post-synchronization offset value and said post-synchronization absolute clock value are calculated from said post-synchronization messages.

23. The system of claim 22, wherein each post synchronization message has a minimum round trip time.

24. The system of claim 23, wherein said round trip time is calculated according to T_i.4−

T_i.1−

(T_i.3−

T_i.2), where i is in an interval [1 . . . N], N is the number of said post-synchronization messages sent by said requester node, T_i.1 is a first timestamp of said requester node sending said post-synchronization messages, T_i.2 is a second timestamp of said responder node receiving said post-synchronization messages, T_i.3 is a third timestamp of said responder node sending said post-synchronization messages, and T_i.4 is a fourth timestamp of said requester node receiving said post-synchronization messages.

25. The system of claim 23, wherein said post-synchronization absolute clock value is set as said fourth timestamp of said requester node receiving said post-synchronization messages.

26. The system of claim 16, wherein said post-synchronization offset value is calculated according to ((T₂−

T₁)+(T₃−

T₄))/2, where T₁ is a first timestamp of said requester node sending said post-synchronization messages, T₂ is a second timestamp of said responder node receiving said post-synchronization messages, T₃ is a third timestamp of said responder node sending said post-synchronization messages, and T₄ is a fourth timestamp of said requester node receiving said post-synchronization messages.

27. The system of claim 26, wherein said one-way latency profile between said requester node and said responder node is calculated according to Ti.₂−

Ti.₁+CDIFF0+rate_bias*(Ti.₁−

CABS0)−

Ks−

Kr, where i is in an interval [1 . . . N], N is the number of said predetermined number of measuring messages sent by said requester node, Ti.₁ is a first timestamp of said requester node sending said measuring messages, Ti.₂ is a second timestamp of said responder node receiving said measuring messages, CDIFF0 is said pre-synchronization offset value, rate_bias is said rate bias, CABS0 is said pre-synchronization absolute clock value, Ks is said overhead of said requester node, and Kr is said overhead of said responder node.

28. The system of claim 16, further comprising:

calculating a rate bias according to rate_bias=(CDIFF1−

CDIFF0)/(CABS1−

CABS0), where CDIFF1 is said post-synchronization offset value, CDIFF0 is said pre-synchronization offset value, CABS1 is said post-synchronization absolute clock value, and CABS0 is said pre-synchronization absolute clock value.

29. The system of claim 16, wherein said plurality of pre-synchronization messages, said predetermined number of measuring messages, and said plurality of post-synchronization messages are encapsulated using a UDP/IP protocol.

30. The system of claim 16 wherein said plurality of pre-synchronization messages, said predetermined number of measuring messages, and said plurality of post-synchronization messages are encoded using a RTP protocol.

31. A system to determine a one-way latency between nodes in a network, comprising:

a first node, wherein the first node is configured to send a first message and determine a first value T1 indicative of a time the first message is sent, and wherein the first node is configured to receive a second message and determine a second value indicative of a time T4 the second message is received;

a second node, wherein the second node is configured to receive the first message from the first node and determine a third value T2 indicative of a time the first message is received, and wherein the second node is configured to send the second message to the first node and determine a fourth value indicative of a time T3 the second message is sent;

a first clock, wherein the first clock determines time T1 and time T4;

second clock, wherein the second clock determines time T2 and time T4; and

said first node generating said one-way latency profile from a combination of the times, T1, T2, T3, and T4.

32. The system of claim 31, wherein the first clock and the second clock are not synchronized.