Method simulating data traffic on network in accordance with a client/sewer paradigm

• US 5,440,719 A
• Filed: 10/27/1992
• Issued: 08/08/1995
• Est. Priority Date: 10/27/1992
• Status: Expired due to Term

• Current Assignee: Cadence Design Systems Incorporated (Cadence Group)
• Original Assignee: Cadence Design Systems Incorporated (Cadence Group)
• Inventors: Mick, Colin K., Hanes, Charles F.
• Primary Examiner(s): Harrell, Robert B.
• Application Number:
  US07/967,636
• Time in Patent Office: 1,015 Days
• Field of Search: 364/DIG. 1, 364/ DIG. 2, 364/550, 364/551.01, 364/570, 364/578, 395/200, 395/275, 395/325, 395/500, 395/575, 395/550, 371/16.5, 371/19, 371/20.6, 371/13, 371/14, 371/58.3, 371/825.5, 371/60, 371/85.2, 371/85.4, 371/85.5
• US Class Current: 703/21
• CPC Class Codes: G06F 11/3414 Workload generation, e.g. scripts, playback
• CPC Class Codes: G06F 11/3447 Performance evaluation by modeling
• CPC Class Codes: G06F 11/3452 Performance evaluation by statistical analysis
• CPC Class Codes: G06F 11/3466 Performance evaluation by tracing or monitoring
• CPC Class Codes: G06F 2201/835 Timestamp
• CPC Class Codes: H04L 43/00 Arrangements for monitoring or testing data switching networks

Abstract

A method for modeling traffic on a network according to a Client/Server paradigm is disclosed, The method includes the steps of interacting the model parameters from known or measured interactions between a client node running a particular application and a server node with no other activity on the network, The method is repeated for each nodal configuration and for each application until the traffic for each node-application combination has been modeled with no other load on the network. Scripts are created from the paradigm parameters and are used in conjunction with a traffic generator to create discrete events mimicking the traffic which would be generated from each node, The model will insure that the traffic generated by each traffic source will be adjusted as a function of the response of the network under the load created by all of the traffic loading the network,

Claims

1. A method of simulating data traffic being transmitted over a network among a plurality of nodes interconnected by the network, the data traffic comprising a plurality of conversations among the plurality of nodes, one or more of the plurality of nodes being a client node and one or more of the plurality of nodes being a server node, said method comprising the steps of:

providing a model representative of the network;

characterizing one or more of the plurality of conversations as a series of one or more request/response interactions, each of the one or more interactions comprising transmission of a request message from one of the one or more client nodes to one of the one or more server nodes, and wherein none, some or all of the one or more interactions further comprise transmission of a response message associated with the request message, the associated response message transmitted from the one server node back to the one client node in response to receiving the request message; and

generating data representative of the one or more interactions of each of the characterized conversations, said step of generating further comprising the steps of;

inputting the generated data for each of the interactions into the network model to determine when the associated response message of each of the interactions having one are received by the one client; and

when the request message of one of the interactions is dependent on the one client node'"'"'s receipt of the response message associated with a previously generated request message, delaying the inputting of the data representative of the dependent interaction into the network model until the response message associated with the previously generated request message is received by the one client node as determined by the network model.

2. The method of claim 1 wherein said step of characterizing one or more of the plurality of conversations further comprises the steps of:

determining a peak level of data traffic over the network; and

defining the one or more of the plurality of conversations to characterize as those which are active when the network is at the peak traffic level.

3. The method of claim 2 wherein said step of characterizing further comprises the step of limiting the series of one or more request/response interactions for each of the characterized conversations to those interactions which are the most data intensive and the most exemplary of the conversation.

4. The method of claim 3 wherein said step of limiting is performed for each characterized conversation assuming no other of the plurality of conversations are present on the network.

5. The method of claim 3 wherein said step of limiting is performed using output from a network analyzer connected to the network, the output measured for each of the characterized conversations with minimal presence of other of the plurality of conversations present on the network.

6. The method of claim 4 wherein the extracted parameters are converted to scripts, the scripts capable of being read by a traffic generator to generate data traffic in accordance therewith.

7. The method of claim 11 wherein the extracted parameters are converted to scripts, the scripts capable of being read by a traffic generator to generate data traffic in accordance therewith.

8. The method of claim 2 wherein said step of determining the peak level of data traffic is performed by a network analyzer.

9. The method of claim 2 wherein said step of defining the one or more of the plurality of conversations is performed by a network analyzer.

10. The method of claim 1 wherein said step of inputting data to the network model further comprises the steps of:

determining when the request message arrives at the one server node for processing; and

determining when the associated response message is generated by the one server node.

11. The method of claim 10 wherein said characterizing step further comprises the step of extracting from each of the one or more request/response interactions a set of interaction parameters including a Client Waiting Time, a Client Request Size, a Server Response Time and a Server Response Size.

12. The method of claim 11 wherein said step of determining when the request message arrives further comprises the step of using the network model to determine the time necessary for the request message to traverse the network from the one client node to the one server node based on the Client Request Size.

13. The method of claim 12 wherein said step of determining when the request message arrives further comprises the step of using the network model to account for time associated with contention for access to the one server node.

14. The method of claim 11 wherein said step of inputting the generated data further comprises the step of using the network model to determine the time for the associated response message to traverse the network from the one server node to the one client node as a function of the Server Response Size.

15. The method of claim 11 wherein the one server node represents remote data processing resources and wherein the Server Response Time is a function of the throughput of the remote data processing resources.

16. The method of claim 11 wherein said step of generating further comprises the steps of:

for each of the one or more interactions, scheduling the generation of the request message upon expiration of the Client Waiting Time;

when transmission of the request message is dependent upon the receipt by the one client node of the response message associated with a previously generated request message, triggering the Client Waiting Time upon receipt; and

when transmission is not dependent, triggering the Client Waiting Time upon generation of the previous request message.

17. The method of claim 16 wherein the one client node represents local data processing resources and the Client Waiting Time is a function of the throughput of the local data processing resources and thinking time attributable to a user.

18. The method of claim 11 wherein the network model includes a model of the one server node, said step of determining when the associated response message is generated further comprises said step of using the one server node model to determine the time necessary to generate the associated response message based on the Server Response Time.