Determining client latencies over a network

• US 7,676,570 B2
• Filed: 08/30/2006
• Issued: 03/09/2010
• Est. Priority Date: 06/14/2002
• Status: Active Grant

• Current Assignee: Zarbana Digital Fund LLC (Intellectual Ventures LLC)
• Original Assignee: Khorsabad Lockdown LLC (Intellectual Ventures LLC)
• Inventors: Marshak, Marik, Levy, Hanoch
• Primary Examiner(s): Winder; Patrice
• Assistant Examiner(s): AILES, BENJAMIN A
• Application Number:
  US11/514,378
• Publication Number:
  US 20070073873A1
• Time in Patent Office: 1,287 Days
• Field of Search: 709/224, 370/229, 370/232, 702/176, 702/186
• US Class Current: 709/224
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04L 43/0864 Round trip delays
• CPC Class Codes: H04L 43/0888 Throughput
• CPC Class Codes: H04L 43/10 Active monitoring, e.g. heartbeat, ping or trace-route
• CPC Class Codes: H04L 69/16 Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
• CPC Class Codes: H04L 69/163 In-band adaptation of TCP data exchange; In-band control procedures
• CPC Class Codes: H04L 69/28 Timers or timing mechanisms used in protocols

Abstract

A network latency estimation apparatus for estimating latency in network communications between a server and a client. The apparatus comprises an event observer for observing occurrences of pre-selected events. The events associated with the communication occurring at the server. A logging device associated with the event observer for logging into a data store the occurrence of the events together with respective time information. A latency estimator associated with the logging device for using the logged occurrences with the respective time information to arrive at an estimation of a client'"'"'s latency for the communication.

Claims

1. A method comprising:

estimating a round trip time for communication between a server and a client over a network;

receiving, at the server, a first request for data from the client over the network;

sending, from the server, a response to the client over the network responsive to the first request;

receiving, at the server, a second request for data from the client over the network;

estimating, at the server, a transmission latency of the response over the network based, at least in part, on the estimated round trip time and a determined delay between sending the response to the client and receiving the second request for data from the client, wherein the transmission latency of the response over the network is a time period between the sending of the response to the client and the client receiving the response from the server; and

determining a data transmission rate according to an amount of data sent in the response to the client and the estimated transmission latency of the response over the network.

2. The method of claim 1 wherein estimating the round trip time further comprises subtracting a first time when data is sent to the client from the server from a second time when the server receives a subsequent request for data from the client.

3. The method of claim 1 wherein estimating the round trip time further comprises identifying a time period between when a ping is sent from the server to the client and when a response to the ping is received from the client at the server.

4. The method of claim 1 wherein estimating the round trip time further comprises identifying a time period between when the server sends a response to a request from the client on a first channel and the server receives a subsequent request from the client on the first channel.

5. The method of claim 1 further comprising determining a mai1 page latency by identifying a time period between when a request for a web page is sent from the client to the server and when an HTML portion of the web page is received at the client.

6. The method of claim 1 further comprising determining a web page latency by identifying a time period between when a request for a web page is sent from the client to the server and when the entire web page is received at the client.

7. The method of claim 1 further comprising logging, in a data storage device associated with the server, an occurrence of events associated with communication over the network and corresponding time information associated with the occurrence of each event.

8. The method of claim 7 wherein the logging further comprises logging a time when the server begins processing at least one request from the client.

9. The method of claim 7 wherein the logging further comprises logging one or more times when the server begins writing responses corresponding to requests received from the client.

10. The method of claim 9 wherein the logging further comprises logging one or more times when the server finishes writing responses to the corresponding requests received from the client.

11. The method of claim 1 further comprising averaging together a plurality of successively estimated data transmission rates for the client to estimate an overall data transmission rate for the client.

12. The method of claim 1 further comprising averaging together all of the data transmission rates for the client wherein the corresponding data transmissions meet a specific size criteria.

13. The method of claim 1 further comprising averaging together successive data transmission rates to estimate a global data transmission rate.

14. The method of claim 1 further comprising averaging together a series of successively determined data transmission rates wherein respective data transmissions meet a pre-determined size criteria.

15. The method of claim 1 further comprising averaging together all of the data transmission rates for each data transmission on a channel that couples the client to the server.

16. The method of claim 1 wherein the estimated round trip time is dependent on available bandwidth between the server and the client.

17. The method of claim 1 wherein the amount of data sent is measured by a number of data packets transmitted by the server to the client.

18. The method of claim 1, further comprising inserting a sentry in the response, wherein the sentry is configured to prompt the client to transmit the second request for data to the server.

19. A system comprising:

a network interface to communicate with a client over a network, wherein the network interface is configured to receive one or more requests for data from the client, and to send the requested data to the client in one or more corresponding responses;

means for estimating a round trip time for network communication between a server and the client;

means for estimating a transmission time for the response to reach the client based, at least in part, on the estimated round trip time and a delay determined between sending the response to the client and receiving a subsequent request for data from the client, wherein the transmission time of the response is a time period between the sending of the response to the client and the client receiving the response from the server; and

means for determining a data transmission rate according to an amount of data sent in the response to the client and the estimated transmission time of the response.

20. The system of claim 19 further comprising means for determining a main page latency by identifying a time period between when a request for a web page is sent from the client to the server and when an HTML portion of the web page is received at the client.

21. The system of claim 19 further comprising means for determining a web page latency by identifying a time period between when a request for a web page is sent from the client to the server and when the entire web page is received at the client.

22. The system of claim 19 further comprising means for logging, in a data storage device associated with the server, an occurrence of events associated with the communication over the network and time information associated with the occurrence of each event.

23. The system of claim 19 further comprising means for averaging multiple estimated data transmission rates for the client to estimate an overall data transmission rate for the client.

24. The system of claim 23 wherein the means for averaging multiple estimated data transmission rates when multiple estimated data transmission rates meet a pre-determined size criteria.

25. The system of claim 19 wherein the transmission time for the response corresponds to a time period between the sending of the response and a reception of the response by the client.

26. The system of claim 19 wherein the means for estimating the transmission latency of the sent response further comprises means for subtracting half of the estimated round trip time from the determined delay.

27. The system of claim 19, further comprising means for inserting a sentry in the response, wherein the sentry is configured to prompt the client to transmit the second request for data to the server.

28. A device comprising:

a network interface to exchange data with a client over a network;

a round trip time estimator to estimate a round trip time for communications with the client over the network; and

a data rate estimator to determine a delay between sending a response to the client over the network and receiving a subsequent request for data from the client over the network, the data rate estimator to estimate a transmission latency of the sent response based, at least in part, on the estimated round trip time and the determined delay, wherein the transmission latency of the sent response is a time period between the sending of the response to the client and the client receiving the response from the server, and wherein the data rate estimator is configured to determine a data transmission rate according to an amount of data sent in the response to the client and the estimated transmission latency of the sent response.

29. The system of claim 28 further comprising a storage device to log one or more events associated with the communication over the network and corresponding time information associated with the events.

30. The system of claim 28 wherein the data rate estimator includes a connection rate estimator to determine a connection data rate for each network connection with the client, the network interface to exchange one or more packets with the client in each network connection, wherein the connection rate estimator is configured to determine the connection data rate from one or more data transmission rates determined for each packet sent to the client.

31. The system of claim 30 wherein the data rate estimator includes a transaction rate estimator to determine a transaction data rate with the client over the network, the transaction rate estimator to average multiple connection data rates to determine the transaction data rate.

32. The system of claim 28 wherein the data rate estimator includes a client rate estimator to determine a data rate for each client receiving packets over the network, the transaction rate estimator to average one or more data transmission rates for each client.

33. The system of claim 32 wherein the client rate estimator is configured to average multiple data transmission rates associated with packets having a pre-determined data size.

34. The system of claim 28 wherein the transmission latency for the response corresponds to a time period between the sending of the response and a reception of the response by the client.

35. The system of claim 28 wherein the data rate estimator is configured to estimate the transmission latency of the sent response by subtracting half of the estimated round trip time from the determined delay.

36. The device of claim 28, further comprising a sentry inserter to insert a sentry in the response, wherein the sentry is configured to prompt the client to transmit the second request for data to the server.