MULTI-SCALE NETWORK TRAFFIC GENERATOR

Abstract

Embodiments of the present invention provide a method, system and computer program product for multi-scale network traffic generation. In one embodiment of the invention, a network traffic generation method can be provided. The method can include defining multiple, different scales in an n-state MMPP model to accommodate a full characteristic response of a modeled traffic scenario. The method further can include establishing a transition window for each of the scales and determining a state through the transition window for selected ones of the scales. Finally, the method can include computing an inter-packet time according to the determined state for each of the selected ones of the scales and generating and transmitting packets for the selected ones of the scales utilizing a correspondingly computed inter-packet time.

Description

BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

The accompanying drawings, which are incorporated in and constitute part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention. The embodiments illustrated herein are presently preferred, it being understood, however, that the invention is not limited to the precise arrangements and instrumentalities shown, wherein:

FIG. 1 is a pictorial illustration of a computer communications network configured with a multi-scale, multi-window network traffic generator;

FIG. 2 is a schematic illustration of a multi-scale, multi-window network traffic generator;

FIG. 3 is a block diagram illustrating a multi-scale, multi-window network traffic generator; and,

FIG. 4 is a flow chart illustrating a process for the multi-scale, multi-window generation of network traffic.

DETAILED DESCRIPTION OF THE INVENTION

Embodiments of the present invention provide a method, system and computer program product for multi-scale, multi-window network traffic generation. In accordance with an embodiment of the present invention, a multi-scale, multi-window network traffic generator can simulate the self-similar characteristics of an inter-arrival time distribution for packets simulated for arrival across multiple time scales. The traffic generator can operate upon an adapted, n-state MMPP model with transition windows to identify state transitions in each of the time scales. Specifically, each of the transition windows can map a gap between multiple scales of a self-similar inter-packet time distribution to facilitate the selection of parameter values when generating packets within a particular time scale.

In illustration, FIG. 1 is a pictorial illustration of a computer communications network configured with a multi-scale, multi-window network traffic generator. The system can include one or more client computing devices 120 coupled to a server host 110 over a computer communications network 130. The server host 110 can include a multi-scale, multi-window network traffic generator 140 configured to generate packets 170 emulating the self-similar nature of network traffic. An application 150 further can be coupled to the server host 110 (or to another server host) and an application monitor 160 can monitor the performance characteristics of the application 150 in response to the packets 170 of the network traffic generated by the multi-scale, multi-window network traffic generator 140.

The multi-scale, multi-window network traffic generator 140, as shown in FIG. 2, can include a control point 210 coupled to each of an MMPP model 240, parameter computation logic 220 and a packet transmitter 260. The MMPP model 240 in turn can be coupled to a packet scheduler 250 also coupled to the transmitter. The MMPP model 240 can include a multiplicity of states, each calibrated to represent a scale range in a time range. Each state can be exponentially distributed with transition probabilities for transitioning from an idle state to a burst state, and from a burst state to an idle state.

The transition probabilities can be organized into a probability transition matrix and when provided a desired traffic pattern, the matrix can produce a selected one of the transition windows 230 for use generating real-time network traffic. In this regard, the parameter computation logic 220 can compute an inter-arrival time for each of the burst of bursts that varies from one burst of bursts to the next. In this regard, multiple transition windows 230 can be provided as τ_i=[ρ_minⁱ,ρ_maxⁱ⁺¹], each iteration of the multiple transition windows 230 providing for three possible cases: (1) ρ_i>ρ_min¹ in consequence of which a packet is to be generated with an inter-packet time in the bursty state; (2) ρ_i<ρ_max² in consequence of which a packet is to be generated with an inter-packet time in the idle state; and ρ_max²<ρ_i<ρ_min¹—the gap between two states within the transition window in consequence of which no packet is to be generated.

Thus, each of the transition windows 230 can generate packets with an inter-packet time distribution determined by the parameters μ₁, μ₂, . . . , μ_n corresponding to each of the states P₁, P₂, . . . P_n where μ is the mean parameter and P is the distribution for a burst of bursts. Each burst of bursts can be scheduled within the packet scheduler 250 for a different scale of self-similar traffic and transmitted by the transmitter 260 into the target network. Thereafter, the pattern of burst of bursts can repeat for the number of scales selected.

In more particular illustration, FIG. 3 is a block diagram illustrating a multi-scale, multi-window network traffic generator. As shown in FIG. 3, the traffic generator can include a burst generator 320 driven from a spread generator 310 which provides for variability within a packet burst 340. A burst window generator 330 further can be provided that can define the duration (width) of a packet burst 340. Finally, one or more idle state generators 350A, 350B, 350N can provide one or more idle state generators 360A, 360B, 360N that provide idle state gaps for n-scales of long-range dependent traffic in a packet burst 340. More importantly, each of the idle state generators 360A, 360B, 360N provide the mean parameters with some variability included for realism and the probability distribution for the packet burst 340.

In even yet further illustration, FIG. 4 is a flow chart illustrating a process for the multi-scale, multi-window generation of network traffic. Beginning in block 405, a first scale can be selected for processing. In block 410, a transition window can be defined for the scale. In decision block 415, if additional scales remain to be processed, in block 420 a next scale can be selected for processing an a new transition window can be established for the next scale. This portion of the process can repeat until a set of transition windows have been established for the desired set of scales. Thereafter, the process can continue through block 425.

In block 425, a scale within the set of scales can be selected for processing. In block 430, a window can be retrieved for the selected scale and in block 435, a state can be determined according to the retrieved window. Thereafter, in block 440, the packet generation parameters can be generated for the determined state and in block 445, a burst of bursts can be generated utilizing the parameters. Finally, in block 450 the burst of bursts can be transmitted and in decision block 455, if the process has not completed, in decision block 460 it can be determined whether to change scale. If so, a new scale can be selected in block 425 and the process can repeat through block 430. When no additional traffic is to be generated, the process can terminate in block 465.

Embodiments of the invention can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment containing both hardware and software elements. In a preferred embodiment, the invention is implemented in software, which includes but is not limited to firmware, resident software, microcode, and the like. Furthermore, the invention can take the form of a computer program product accessible from a computer-usable or computer-readable medium providing program code for use by or in connection with a computer or any instruction execution system.

For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The medium can be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device) or a propagation medium. Examples of a computer-readable medium include a semiconductor or solid state memory, magnetic tape, a removable computer diskette, a random access memory (RAM), a read-only memory (ROM), a rigid magnetic disk and an optical disk. Current examples of optical disks include compact disk—read only memory (CD-ROM), compact disk—read/write (CD-R/W) and DVD.

A data processing system suitable for storing and/or executing program code will include at least one processor coupled directly or indirectly to memory elements through a system bus. The memory elements can include local memory employed during actual execution of the program code, bulk storage, and cache memories which provide temporary storage of at least some program code in order to reduce the number of times code must be retrieved from bulk storage during execution. Input/output or I/O devices (including but not limited to keyboards, displays, pointing devices, etc.) can be coupled to the system either directly or through intervening I/O controllers. Network adapters may also be coupled to the system to enable the data processing system to become coupled to other data processing systems or remote printers or storage devices through intervening private or public networks. Modems, cable modem and Ethernet cards are just a few of the currently available types of network adapters.

Claims

1. A network traffic generation method comprising: defining multiple, different scales in an n-state Markov modified Poisson process (MMPP) model to accommodate a full characteristic response of a modeled traffic scenario;establishing a transition window for each of the scales;determining a state through the transition window for selected ones of the scales;computing an inter-packet time according to the determined state for each of the selected ones of the scales; and,generating and transmitting packets for the selected ones of the scales utilizing a correspondingly computed inter-packet time.

2. The method of claim 1, wherein establishing a transition window for each of the scales, comprises establishing a transition window for each of the scales according to τi=[ρmini,ρmaxi+1].

3. The method of claim 1, wherein determining a state through the transition window for selected ones of the scales, comprises comparing a random probability distribution to the transition window to determine the state.

4. The method of claim 2, wherein determining a state through the transition window for selected ones of the scales, comprises comparing a random probability distribution ρi to the transition window τi=[ρmini,ρmaxi+1] to determine the state according to ρi>ρmin1 consequence of which a packet is to be generated with an inter-packet time in a bursty state, ρi<ρmax2 in consequence of which a packet is to be generated with an inter-packet time in an idle state; and ρmax2<ρi<ρmin1 in consequence of which no packet is to be generated.

5. A network traffic generation system comprising: a Markov modified Poisson process (MMPP) model;a packet scheduler coupled to the MMP model;a data store of transition windows defined for different defined scales;traffic generation parameter computing logic comprising program code enabled to compute traffic generation parameters for different scales according to respective states identified within different transition windows in the data store for the different scales; and,a packet transmitter coupled to the packet scheduler.

6. A computer program product comprising a computer usable medium embodying computer usable program code for network traffic generation, the computer program product including: computer usable program code for defining multiple, different scales in an n-state Markov modified Poisson process (MMPP) model to accommodate a full characteristic response of a modeled traffic scenario;computer usable program code for establishing a transition window for each of the scales;computer usable program code for determining a state through the transition window for selected ones of the scales;computer usable program code for computing an inter-packet time according to the determined state for each of the selected ones of the scales; and,computer usable program code for generating and transmitting packets for the selected ones of the scales utilizing a correspondingly computed inter-packet time.

7. The computer program product of claim 6, wherein the computer usable program code for establishing a transition window for each of the scales, comprises computer usable program code for establishing a transition window for each of the scales according to τi=[ρmini,ρmaxi+1].

8. The computer program product of claim 6, wherein the computer usable program code for determining a state through the transition window for selected ones of the scales, comprises computer usable program code for comparing a random probability distribution to the transition window to determine the state.

9. The computer program product of claim 7, wherein the computer usable program code for determining a state through the transition window for selected ones of the scales, comprises computer usable program code for comparing a random probability distribution ρi to the transition window τi=[ρmini,ρmaxi+1] to determine the state according to ρi>ρmin1 in consequence of which a packet is to be generated with an inter-packet time in a bursty state, ρi<ρmax2 in consequence of which a packet is to be generated with an inter-packet time in an idle state; and ρmax2<ρi<ρmin1 consequence of which no packet is to be generated.