The subject matter described herein relates to testing communications network equipment. More particularly, the subject matter described herein relates to methods, systems, and computer readable media for testing network devices using variable traffic burst profiles.
In testing network devices, such as switches, routers, firewalls, network address translators, servers, storage devices, etc., it is desirable to send a mix of traffic to the devices that simulates the traffic that the devices would experience in live networks. For network devices that are intended to operate in networks that carry traffic of different types, such as voice, data, and video traffic, it is desirable to generate a mix of simulated traffic that includes all of these types. In addition, because network devices will encounter streams of different packet sizes in real world deployments, it is desirable to test devices with a mix of different packet sizes. For example, when performing a stress test of a network device, such as a firewall, it may be desirable to see how the device performs when receiving a stream of small packets, such as 64 kilobyte packets versus how the device performs when receiving a stream of larger packets, such as 1500 kilobyte packets.
Because a realistic mix of packets sizes is desirable during testing, efforts have been made to standardize test traffic mixes. For Internet connected devices, a mix of packet sizes for which some standardization efforts have occurred is referred to as an Internet mix or IMIX of packets. There is no standard IMIX of packets that is valid for all network devices, as different network devices see different mixes of packet sizes. However, IETF RFC 6985, entitled IMIX Genome, describes a method for specifying different Internet mixes of traffic.
As a result of the need to test network devices using different mixes of traffic, some network equipment test devices, such as the Ixia Xcellon load modules with IxNetwork software, are capable of generating an IMIX of simulated traffic where the simulated packets have different sizes. However, one feature that is not known to be implemented by current network equipment test devices is the ability to easily specify and implement burst profiles that vary in time for simulated network traffic. Current network test devices allow specification of a traffic rate, e.g., in bits per second, and a fixed time between successive packet transmissions. However, there is currently a need for a test device that facilitates implementation of variable and realistic burst profiles for simulated test traffic.
In light of these difficulties, there exists a need for methods, systems, and computer readable media for testing network devices using variable traffic burst profiles.
A method for testing a network device using a variable traffic burst profile includes providing for user selection of at least one type of simulated traffic to be transmitted to a network device under test (DUT). The method further includes receiving user input regarding selection of the type of simulated traffic. The method further includes providing for user selection of a transmission rate for transmitting the simulated traffic to the DUT. The method further includes receiving user input regarding selection of the transmission rate. The method further includes transmitting the simulated traffic to the DUT according to the selected type, rate, and a variable traffic burst profile.
A system for testing a network device using a variable traffic burst profile includes a network equipment test device including at least one processor. The system further includes a user interface implemented by the at least one processor for providing for user selection of at least one type of simulated traffic to be transmitted to a network device under test (DUT), receiving user input regarding selection of the type of simulated traffic, providing for user selection of a transmission rate for transmitting the simulated traffic to the DUT, and receiving user input regarding selection of the transmission rate. The system further includes a simulated traffic generator for transmitting the simulated traffic to the DUT according to the selected type, rate, and a variable traffic burst profile.
The subject matter described herein for testing a network device using a variable burst profile may be implemented in hardware, software, firmware, or any combination thereof. As such, the terms “function” or “module” as used herein refer to hardware, software, and/or firmware for implementing the feature being described. In one exemplary implementation, the subject matter described herein may be implemented using a non-transitory computer readable medium having stored thereon computer executable instructions that when executed by the processor of a computer control the computer to perform steps. Exemplary computer readable media suitable for implementing the subject matter described herein include non-transitory computer-readable media, such as disk memory devices, chip memory devices, programmable logic devices, and application specific integrated circuits. In addition, a computer readable medium that implements the subject matter described herein may be located on a single device or computing platform or may be distributed across multiple devices or computing platforms.
Embodiments of the subject matter described herein will now be explained with reference to the accompanying drawings, wherein like reference numerals represent like parts, of which:
The subject matter described herein includes methods, systems, and computer readable media testing a network device using variable traffic burst profiles.
User interface 106 may be a graphical or command line interface that provides for user selection of at least one type of simulated traffic to be transmitted to DUT 110 and receives user input regarding selection of the type of simulated traffic. For example, user interface 106 may allow a user to define simulated traffic flows to be transmitted to DUT 110. A traffic flow is a group of packets that are transmitted to DUT 110 for test purposes. The traffic flow may include traffic of a single type, such as voice traffic or a mix of traffic types, such as voice, video, and/or data traffic.
User interface 106 may also include a third portion 204 for user selection of a transmission rate for transmitting simulated traffic to DUT 110. For example, user interface 106 may provide a drop-down menu or other graphical or textual device through which a user can select a transmission rate, e.g., in bits per second. The transmission rate may be the line rate or rate at which bits are transmitted if the transmission line or medium is fully utilized without considering inter-packet delays or burstiness. For example, if it is desirable to simulate 50 or 100 gigabit Ethernet, the transmission rate selections provided by user interface 106 may include 50 Gbps and 100 Gbps. Alternatively, rather than specifying a menu of transmission rates, user interface 106 may allow a user to define a customized transmission rate by providing a dialog box for the user to enter the packet transmission rate.
User interface 106 may also provide for user selection of frame sizes for the simulated traffic flow. For example, user interface 106 may include a fourth portion 206 that allows the user to select a frame size, such as 64 k or 1500 k or a frame size distribution, such as IMIX. The frame size distributions may be tailored to a test scenario. For example, to achieve maximum stress on the device under test, a frame size distribution with a higher percentage of smaller framer frames. If it is desirable to simulate a realistic mix of Internet traffic, a more even distribution of frame sizes may be selected for the simulated traffic flow.
Once the user has select the traffic type(s) and transmission for a particular flow, in one embodiment, simulated traffic generator 108 automatically selects at least one burst profile for varying burstiness of the simulated traffic transmitted to the DUT, e.g., based on the selected traffic type(s), based on a desired test scenario, a burst level standard, etc., and transmits the simulated traffic to the DUT according to the selected rate, traffic, and selected burst profile selected. For example, a user may select voice, video, and data traffic for a particular type via user interface 106 and simulated traffic generator 106 may select a different burst profile for each of the voice, video, and data traffic. Simulated traffic generator 108 may then transmit traffic to the DUT using the burst profile select for each traffic type. In an alternate example, simulated traffic generator may select and apply the same traffic burst profile to all traffic types to simulate burstiness that occurs at a particular time of day.
In one example, rather than transmitting traffic where the inter-packet delay is constant, the inter-packet delays of the burst profiles selected and/or generated by simulated traffic generator 108 may vary with time. For example, simulated traffic generator 108 may use a probability distribution function or a random number generator to vary the inter-packet delays of a given profile. Simulated traffic generator 108 may store data for implementing a given burst profile in memory 104 for subsequent use in generating the simulated traffic with the given burst profile. Table 1 shown below illustrates exemplary data that may be stored in memory 104 for generating a given traffic burst profile.
In Table 1, each delay value represents a number of units of packet delay between successive packet transmissions. In one example, each unit of packet delay may be a bit transmission time at line rate. For example, if the line rate is 100 Gbps, an inter-packet delay of 1 indicates 1/109 seconds. Multiple successive inter-packet delays of 0 may indicate a burst of data packets at line rate. Data such as that illustrated in Table 1 may be generated and stored in memory 104 to implement different burst profiles for different traffic types or for the same traffic types. The inter-packet delays used for each table may be generated using a random number generator or a probability distribution function.
The subject matter described herein is not limited to automatically selecting burst profiles based on traffic types selected by the user. In an alternate implementation, user interface 106 may provide for user selection of burst profiles and receive user input regarding the selection. Simulated traffic generator 106 may then generate simulated traffic using the burst profile selected by the user. For example, user interface 106 may provide a menu or other construct for selecting a burst profile.
User interface 106 may provide for user selection of burst profile and other parameters on a per port basis. For example, user interface 106 may allow the user to specify that all ports of network equipment test device 100 start with the same static transmission rate and then gradually ramp up to a new traffic rate. The different ports may be configurable to ramp up to the same or different traffic rate. The rate of ramping to the new transmission rate may be the same or different on each port. In addition, providing for selection or implementation of packet transmission rates that vary in time using functions other than ramp functions is intended to be within the scope of the subject matter described herein.
In one example, network equipment test device 100 generates and utilizes burst profiles that result in transmission of simulated traffic to DUT 110 with time varying inter-packet transmission times.
As illustrated in
In step 402, the process includes receiving user input regarding selection of the type of simulated traffic. For example, user interface 106 may receive input from the user that indicates the user desires to transmit simulated voice, video, and data traffic to DUT 110.
In step 404, the process includes providing for user selection of a transmission rate for transmitting the simulated traffic to the DUT. For example, user interface 106 may provide a menu or other construct that allows the user to select a line rate (e.g., in bits per second) for transmitting packets to DUT 110.
In step 406, the process includes receiving user input regarding selection the transmission rate. For example, user interface 106 may receive user input that indicates the user's selection of the transmission rate, such as 100 Gbps.
In step 408, the process includes selecting a burst profile for varying burstiness of the simulated traffic transmitted to the DUT. In one example, simulated traffic generator 108 may select the burst profile automatically based on traffic type(s) and standard or predefined burst profiles for each traffic type. In another example, simulated traffic generator 108 may select the same burst profile to be applied across multiple traffic types. In yet another example, user interface 106 may provide for user selection of the burst profile on an aggregate or per traffic type basis, and simulated traffic generator 108 may use the selected burst profile to generate the simulated traffic.
In step 410, the process includes transmitting the simulated traffic to the DUT according to the selected type, rate, and burst profile. For example, test traffic generator 108 may transmit the simulated traffic to DUT 110 using the automatically or manually selected traffic burst profile.
It will be understood that various details of the subject matter described herein may be changed without departing from the scope of the subject matter described herein. Furthermore, the foregoing description is for the purpose of illustration only, and not for the purpose of limitation.
Number | Name | Date | Kind |
---|---|---|---|
5526283 | Hershey et al. | Jun 1996 | A |
5557559 | Rhodes | Sep 1996 | A |
5568471 | Hershey et al. | Oct 1996 | A |
5586266 | Hershey et al. | Dec 1996 | A |
5671351 | Wild et al. | Sep 1997 | A |
5761486 | Watanabe et al. | Jun 1998 | A |
5787147 | Gundersen | Jul 1998 | A |
5812529 | Czarnik et al. | Sep 1998 | A |
5905713 | Anderson et al. | May 1999 | A |
6028847 | Beanland | Feb 2000 | A |
6137782 | Sharon et al. | Oct 2000 | A |
6148277 | Asava et al. | Nov 2000 | A |
6172989 | Yanagihara et al. | Jan 2001 | B1 |
6173333 | Jolitz et al. | Jan 2001 | B1 |
6252872 | Tzeng | Jun 2001 | B1 |
6321264 | Fletcher et al. | Nov 2001 | B1 |
6343078 | Bronstein et al. | Jan 2002 | B1 |
6414942 | Ito et al. | Jul 2002 | B1 |
6507923 | Wall et al. | Jan 2003 | B1 |
6526259 | Ho | Feb 2003 | B1 |
6580707 | Ikeda et al. | Jun 2003 | B1 |
6601020 | Myers | Jul 2003 | B1 |
6606721 | Gowin, Jr. et al. | Aug 2003 | B1 |
6621805 | Kondylis et al. | Sep 2003 | B1 |
6744783 | Tzeng | Jun 2004 | B1 |
6789100 | Nemirovsky et al. | Sep 2004 | B2 |
6798746 | Kloth et al. | Sep 2004 | B1 |
6950405 | Van Gerrevink | Sep 2005 | B2 |
6990529 | Yang et al. | Jan 2006 | B2 |
7002918 | Prieto, Jr. et al. | Feb 2006 | B1 |
7161902 | Carter et al. | Jan 2007 | B2 |
7257082 | Dugatkin | Aug 2007 | B2 |
9001688 | Dragulescu et al. | Apr 2015 | B2 |
20010039590 | Furukawa et al. | Nov 2001 | A1 |
20020015387 | Houh | Feb 2002 | A1 |
20020037008 | Tagami et al. | Mar 2002 | A1 |
20020080781 | Gustavsson | Jun 2002 | A1 |
20020093917 | Knobbe et al. | Jul 2002 | A1 |
20020105911 | Pruthi et al. | Aug 2002 | A1 |
20020138226 | Doane | Sep 2002 | A1 |
20020177977 | Scarlat et al. | Nov 2002 | A1 |
20030012141 | Gerrevink | Jan 2003 | A1 |
20030043434 | Brachmann et al. | Mar 2003 | A1 |
20030099243 | Oh et al. | May 2003 | A1 |
20030172177 | Kersley et al. | Sep 2003 | A1 |
20030179777 | Denton et al. | Sep 2003 | A1 |
20040083208 | Kroening | Apr 2004 | A1 |
20050025054 | D. | Feb 2005 | A1 |
20050027503 | Kumar et al. | Feb 2005 | A1 |
20070291650 | Ormazabal | Dec 2007 | A1 |
20090034596 | Chen et al. | Feb 2009 | A1 |
20090059804 | Fujikami | Mar 2009 | A1 |
20130074058 | Gounares | Mar 2013 | A1 |
20140160961 | Dragulescu | Jun 2014 | A1 |
20150032437 | Kumar | Jan 2015 | A1 |
20150092549 | Anand | Apr 2015 | A1 |
20160088499 | Logan | Mar 2016 | A1 |
20170061041 | Kumar | Mar 2017 | A1 |
Number | Date | Country |
---|---|---|
0 895 375 | Feb 1999 | EP |
1 465 367 | Oct 2004 | EP |
H11136288 | May 1999 | JP |
2002101128 | Apr 2002 | JP |
3902606 | Apr 2007 | JP |
Entry |
---|
“Ethernet Traffic Generation,” 2013, ALBEDO Telecom, 17 pages (Year: 2013). |
Notification of Transmittal of the International Search Report and the Written Opinion of the International Searching Authority, or the Declaration for International Application No. PCT/US2017/038201 (dated Sep. 18, 2017). |
Ixia Data Sheet, “Xcellon-Multis® QSFP 40/10GE Load Modules,” https://www.ixiacom.com/sites/default/files/2016-05/xcellon-multis-qsfp-4010ge-load-modules.pdf, pp. 1-14 (May 2016). |
Morton, “IMIX Genome: Specification of Variable Packet Sizes for Additional Testing,” IETF RFC 6985, pp. 1-10 (Jul. 2013). |
Ixia Solution Brief, “IxLoad,” pp. 1-4 (Feb. 2012). |
Commonly-assigned, co-pending U.S. Appl. No. 16/436,856 for “Methods, Systems, and Computer Readable Media for Generating and Using Statistically Varying Network Traffic Mixes to Test Network Devices,” (Unpublished, filed Jun. 10, 2019) |
“The World's Fastest & Most Programmable Networks,” Barefoot Networks, pp. 1-14 (Copyright 2019). |
“P416 Language Specification version 1.1.0,” The P4 Language Consortium, pp. 1-147 (Nov. 30, 2018). |
Notice of Allowance and Fee(s) Due for U.S. Appl. No. 13/962,666 (dated Feb. 9, 2015). |
“Traffic Generators for Internet Traffic,” https://www.icir.org/models/traficgenerators.html, pp. 1-3 (Sep. 2010). |
Notice of Allowance and Fee(s) Due for U.S. Appl. No. 10/404,864 (dated Apr. 5, 2007). |
Decision to grant a European patent pursuant to article 97(2) EPC for European Patent Application Serial No. 04251177.4 (dated Dec. 21, 2006). |
Summons to attend oral proceedings pursuant to Rule 71(1) EPC for European Patent Application Serial No. 04251177.4 (Dec. 19, 2005). |
Office Action for Japanese Patent Application Serial No. 2004-107997 (dated Apr. 25, 2006). |
“Load Modules—Multilayer Glglbit Ethernet for LM1000LX, LM1000SX, LM1000GBIC, LM1000T,” Ixia, Product Specification Sheet, 2 pages (Sep. 14, 2005). |
Communication pursuant to Article 96(2) EPC for European Patent Application Serial No. 04 251 177.4 (dated Jun. 2, 2005). |
European Search Report for European Patent Application Serial No. 04 25 1177 (dated Jun. 9, 2004). |
Zec et al., “Real-Time IP Network Simulation at Gigabit Data Rates,” Proceedings of the 7th International Conference on Telecommunications (ConTEL), pp. 1-8 (Jun. 2003) |
Ye et al., “Large-Scale Network Parameter Configuration Using an On-line Simulation Framework,” pp. 1-19 (2003). |
Delgado-Restituo et al., “Integrated Chaos Generators,” Proceedings of the IEEE, vol. 90, No. 5, pp. 747-767 (May 2002). |
Kramer et al., “Interleaved Polling with Adaptive Cycle Time (IPACT): A Dynamic Bandwidth Distribution Scheme in an Optical Access Network,” Photonic Network Communications, vol. 4, No. 1, pp. 89-107 (2002). |
Ulanovs et al., “Modeling Methods of Self-Similar Traffic for Network Performance Evaluation,” Scientific Proceeding of RTU, Series 7, Telecommunications and Electronics, pp. 40-49 (2002). |
Wallerich, “Self-Similarity and Heavy Tailed Distributions,” Design and Implementation of a WWW Workload Generator for the NS-2 Network Simulator (Chapter 2.2), NSWEB, 2 pages (Nov. 1, 2001). |
Guo et al, “How Does TCP Generate Pseudo-self-similarity?,” In Proceedings of the International Workshop on Analysis and Simulation of Computer and Telecommunications Systems, MASCOTS '01, 9 pages (Aug. 2001). |
Kramer et al, “Interleaved Polling with Adaptive Cycle Time (IPACT): Protocol Design and Performance Analysis,” pp. 1-37 (Jul. 2001). |
Kramer, “Self-similar Network Traffic: The notions and effects of self-similarity and long-range dependence,” http://wwwcsif.cs.ucdavis.edu/˜kramer/papers/ss_trf_present2.pdf>, pp. 1-10 (May 21, 2001). |
Kramer, “Generator of Self-Similar Network Traffic (version 2),” U.C. Davis, 3 pages (Apr. 4, 2001) |
Sikdar et al., “The Effect of TCP on the Self-Similarity of Network Traffic,” Proceeding of 35th Conference on Information Sciences and Systems, 6 pages (Mar. 2001). |
Mondragón et al., “Chaotic maps for traffic modelling and queueing performance analysis,” Performance Evaluatlon, vol. 43, pp. 223-240 (2001). |
Sikdar et al., “On the contribution of TCP to the Self-Similarity of Network Traffic,” Proceedings of IWDC, vol. 2170, pp. 596-613 (2001). |
Kramer, “Generator of Self-Similar Network Traffic,” U.C. Davis, 3 pages (Sep. 25, 2000). |
Mandeville et al., “Benchmarking Methodology for LAN Switching Devices,” RFC 2889, pp. 1-35 (Aug. 2000). |
Veres et al, “The Chaotic Nature of TCP Congestion Control,” Proceedings of IEEE INFOCOM, Tel-Aviv, 9 pages (Mar. 2000). |
Kramer, “On Generating Self-Similar Network Traffic Using Pseudo-Pareto Distribution,” Tutorial, U.C. Davis, 5 pages (2000). |
Zhang et al., “Fractal Network Traffic: From Understanding to Implications,” The 6th International Conference on Telecommunication Systems, Modeling and Analysis, 1 page (Mar. 1998). |
Crovella et al., “Long-Lasting Transient Conditions in Simulations with Heavy-Tailed Workloads,” Proceedings of the 1997 Winter Simulation Conference (WSC-97), pp. 1005-1012 (Dec. 1997). |
Paxson, “Fast, Approximate Synthesis of Fractional Gaussian Noise for Generating Self-Similar Network Traffic,” Computer Communication Review, vol. 27, No. 5, pp. 5-18 (Oct. 1997). |
Samuel et al., “Fast Self-Similar Traffic Generation,” Proceedings of the Fourteenth UK Teletraffic Symposium on Performance Engineering in Information Systems, Manchester UK, pp. 8/1-8/4 (Mar. 1997). |
Willinger et al., “Self-Similarity Through High-Variability: Statistical Analysis of Ethernet LAN Traffic at the Source Level,” IEEE/ACM Transactions on Networking, vol. 5, No. 1, pp. 71-86 (Feb. 1, 1997). |
Taqqu et al, “Proof of a Fundamental Result in Self-Similar Traffic Modeling,” 19 pages (1997). |
Brakmo et al., “Experiences with Network Simulation,” ACM Sigmetrics International Conference on Measurement and Modeling of Computer Systems, pp. 80-90 (May 23, 1996). |
Willinger et al., “Self-Similarity and Heavy Tails: Structural Modeling of Network Traffic,” pp. 1-26 (1996). |
Willinger et al., “Self-Similarity Through High-Variability: Statistical Analysis of Ethernet LAN Traffic at the Source Level,”Proc. of the ACM/Sigcomm '95, 14 pages (1995). |
Leland et al., “On the Self-Similar Nature of Ethernet Traffic (Extended Version),” IEEE/ACM Transactions on Networking, vol. 2, No. 1, pp. 1-15 (Feb. 1994). |
Notice of Allowance and Fee(s) Due and Interview Summary for U.S. Appl. No. 09/906,882 (dated May 31, 2005). |
Number | Date | Country | |
---|---|---|---|
20180011955 A1 | Jan 2018 | US |