Server load management

• US 9,559,906 B2
• Filed: 01/11/2013
• Issued: 01/31/2017
• Est. Priority Date: 01/11/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Keskkula, Silver
• Primary Examiner(s): Khan, Aftab N.
• Assistant Examiner(s): Hackenberg, Rachel J.
• Application Number:
  US13/739,677
• Publication Number:
  US 20140201343A1
• Time in Patent Office: 1,481 Days
• Field of Search: 709/203, 709/204, 709/221, 709/223, 709/224
• US Class Current: 1/1
• CPC Class Codes: H04L 41/082 the condition being updates or upgrades of network functionality
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network
• CPC Class Codes: H04L 43/00 Arrangements for monitoring or testing data switching networks
• CPC Class Codes: H04L 43/08 Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
• CPC Class Codes: H04L 43/0829 Packet loss
• CPC Class Codes: H04L 43/0894 Packet rate
• CPC Class Codes: H04L 43/106 using time related information in packets, e.g. by adding timestamps
• CPC Class Codes: H04L 63/1408 by monitoring network traffic monitoring network traffic per se H04L43/00
• CPC Class Codes: H04L 67/01 Protocols
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04L 67/5682 Policies or rules for updating, deleting or replacing the stored data

Abstract

System and method for collecting values of one or more parameters of one or more clients that are communicatively connected to a server. A model is constructed based on the collected values of the one or more parameters to thereby model as a function of time the probability that the values of the one or more parameters of the one or more clients will change by an amount that is considered significant, e.g. at the server. An update of the one or more parameters is received from one of the clients. Responsive to receiving the update, the model is used to calculate a timing for the next update of the values from the one of the clients. The calculated timing for the next update is sent to the one of the clients.

Claims

1. A method, comprising:

collecting values, from one or more client devices, of one or more parameters of the one or more client devices that are communicatively connected to a server, the one or more parameters describing a current state of the respective one or more client devices;

constructing a model based on the collected values of the one or more parameters to thereby model as a function of time the probability that the values of the one or more parameters of the one or more client devices will change by an amount that is considered significant, wherein the amount that is considered significant is based on whether the amount will affect a decision that the server makes;

receiving, from one of the client devices, an update of the values of the one or more parameters of said one of the client devices, wherein the server maintains a record of the current state of the respective client device or receives the current state of the respective client device with the update of the values of the one or more parameters;

responsive to receiving said update, using the model to calculate a timing for the next update of the values from said one of the client devices, the timing including at least one of a time delay indicating a time that said one of the client devices should wait after receiving the timing before sending the next update of the values and a timestamp indicating an absolute time at which said one of the client devices should sent the next update of the values; and

sending the calculated timing for the next update to said one of the client devices.

2. The method of claim 1, wherein the sending comprises including the calculated timing in a response container that is sent back to said one of the client devices in response to receiving said update from said one of the client devices.

3. The method of claim 1, wherein said one of the client devices is configured to send the next update of the values according to the calculated timing.

4. The method of claim 1, wherein the update of the values is received from said one of the client devices with information describing user activity on an application of said one of the client devices.

5. The method of claim 1 wherein said parameters include one or more of:

(i) current bandwidth usage, (ii) historic packet loss rate, (iii) an address of the client device, (iv) a processing power, (v) a connection type of the client device to a network, (vi) cpu consumption, (vii) amount of cross traffic and (viii) number of relayed streams.

6. The method of claim 1 wherein said step of constructing the model comprises considering a combination of more than one of said parameters in order to model the probability that the values of the one or more parameters of the one or more client devices will change by an amount that is considered significant.

19. The method of claim 1, wherein each of the parameters of the one or more parameters is assigned a weight, and wherein the model uses the weights of each of the parameters of the one or more parameters to calculate the timing.

7. A system, comprising:

a server comprising one or more processors, the one or more processors configured to execute program code to communicate with a client device that is communicatively connected to the server, wherein the server is configured to receive, from the client device, an update of values of one or more parameters of the client device, the one or more parameters describing a current state of the client device, wherein the server maintains a record of the current state of the client device or receives the current state of the client device with the update of the values of the one or more parameters,

wherein the server is configured to;

(i) responsive to receiving said update, use a model to calculate a timing for the next update of the values from the client device, wherein the model is constructed based on the values of the one or more parameters to thereby model as a function of time the probability that the values of the one or more parameters of the client device will change by an amount that is considered significant, wherein the amount that is considered significant is based on whether routing decisions made by the server will change, and (ii) send the calculated timing for the next update to the client device, the calculated timing indicating when the client device should send the next update based on the received one or more parameters.

8. The system of claim 7, wherein the server is configured to send the calculated timing in a response container that is sent back to the client device in response to receiving said update from the client device.

9. The system of claim 7, wherein the server is configured to receive the next update of the values from the client device according to the calculated timing.

10. The system of claim 7, wherein the server is configured to receive the update of the values from the client device with information describing user activity on an application of the client device.

11. The system of claim 7 wherein said timing is either:

(i) a time delay indicating a time that the client device should wait after receiving the timing before sending the next update of the values, or (ii) a timestamp indicating an absolute time at which the client device should send the next update of the values.

12. The system of claim 7 wherein said parameters include one or more of:

(i) current bandwidth, (ii) historic packet loss rate, (iii) an address of the client device, (iv) a processing power, (v) a connection type of the client device to a network, (vi) cpu consumption, (vii) amount of cross traffic and (viii) number of relayed streams.

13. The system of claim 7 wherein the model is constructed by considering a combination of more than one of said parameters in order to model the probability that the values of the one or more parameters of the client device will change by an amount that is considered significant.

18. The system of claim 7, wherein the server is further configured to:

communicate with multiple other client devices that are communicatively connected to the server;

receive updates of values of one or more parameters of native applications of the multiple other client devices;

calculate timings for next updates of values from the multiple other client devices on a client-by-client basis; and

send the calculated timings for the next updates of values to the respective other client devices.

20. The system of claim 7, wherein each of the parameters of the one or more parameters is assigned a weight, and wherein the model uses the weights of each of the parameters of the one or more parameters to calculate the timing.

14. A server comprising:

a processor; and

a computer readable storage medium storing program code, the program code being executable by the processor of the server to implement operations comprising;

collecting values, from one or more client devices, of one or more parameters of the one or more client devices that are communicatively connected to the server, the one or more parameters describing a current state of the respective one or more client devices;

constructing a model based on the collected values of the one or more parameters to thereby model as a function of time the probability that the values of the one or more parameters of the one or more client devices will change by an amount that is considered significant, wherein the amount that is considered significant is based on whether the amount will affect a decision that the server makes;

receiving, from one of the client devices, an update of the values of the one or more parameters of said one of the client devices, wherein the server maintains a record of the current state of said one of the client devices or receives the current state of said one of the client devices with the update of the values of the one or more parameters;

responsive to receiving said update, using the model to calculate a timing indicating when the next update of the values from said one of the client devices should be sent by the client devices based on the updated values; and

sending the calculated timing for the next update to said one of the client devices.

15. The server of claim 14, wherein the sending comprises including the calculated timing in a response container that is sent back to said one of the client devices in response to receiving said update from the client device.

16. The server of claim 14, wherein the one or more of the plurality of client devices is configured to send the next update of the values according to the calculated timing.

17. The server of claim 14 wherein said timing is either:

(i) a time delay indicating a time that said one of the client devices should wait after receiving the timing before sending the next update of the values, or (ii) a timestamp indicating an absolute time at which said one of the client devices should send the next update of the values.