Keysight Technologies, Inc.

Christian Paul Sommers

Peter Joseph Marsico

Matthew Ryan Bergeron

Razvan Ionut Stan

Lyle Eugene Thompson

Russil Wvong

Jonathan Glenn Stroud

Thomas Ameling

Kingshuk Mandal

Diana Galan

One example method for network test configuration and execution using brokered communications with a large language model (LLM) comprises receiving, at an LLM communication broker and from a user, input regarding a network test objective for a network test; generating, by the LLM communication broker, based on the input regarding the network test objective, and using an application programming interface (API) of the LLM, input for invoking the LLM to produce configuration instructions for the network test; providing, by the LLM communication broker and to the LLM, the input for invoking the LLM to produce the configuration instructions; receiving, by a network test system, the configuration instructions for the network test; using, by the network test system, the configuration instructions to configure a network test system to conduct the network test; and conducting, by the network test system, the network test.

Methods, systems, and computer readable media for network test configuration and execution using brokered communications with a large language model (LLM)

Methods, systems, and computer readable media for networking testing. In some examples, a system includes a test controller and a training data collector. The test controller is configured for receiving a test case including test case definition information defining a network test for a system under test (SUT); determining test system resource information for test system resources configured to execute the test case; and executing the test case on the SUT. The training data collector is configured for collecting at least a portion of the test case definition information; collecting SUT status information or SUT configuration information or both for the SUT; collecting metadata associated with the test case including at least one test context label; and processing collected data to produce artificial intelligence training data.

Methods, systems, and computer readable media for network testing and collecting generative artificial intelligence training data

Methods, systems, and computer readable media for smartswitch service chaining are disclosed. One example method occurs at a smartswitch controller implemented using at least one processor, the method comprising: receiving service chain configuration information indicating a service chain involving services performed using data processing units (DPUs) in at least one smartswitch; generating, using the service chain configuration information, one or more switching rules for causing traffic at the at least one smartswitch to be directed to one or more of the DPUs associated with the service chain; and providing the one or more switching rules to the at least one smartswitch or a management entity for implementing the one or more switching rules at the at least one smartswitch.

Methods, systems, and computer readable media for smartswitch service chaining

A method for customizing data plane pipeline processing to generate test packets using Berkeley packet filter (BPF) hook entry points is disclosed. The method includes receiving a program code script for customizing a performance of one or more stages of a multistage processing pipeline platform configured for conducting a network operation process, wherein the multistage processing pipeline platform includes one or more predefined hook entry points and compiling the program code script to generate a customized plug-in component that is deployed in at least one of the one or more predefined hook entry points of the multistage processing pipeline platform. The method further includes initiating execution of the customized plug-in component in response to a triggering of the at least one of the one or more predefined hook entry points of a stage element of the multistage processing pipeline platform, wherein the execution of the customized plug-in component dynamically configures at least one feature of the network operation process at runtime.

Methods, systems, and computer readable media for customizing data plane pipeline processing using Berkeley packet filter (BPF) hook entry points

One example method occurs at a testbed transpiler of a network test system. The method comprises: receiving test configuration information associated with a test session for configuring a test infrastructure, wherein the test infrastructure includes a switching fabric emulator comprising at least one switching application-specific integrated circuit (ASIC) or programmable switching chip, wherein the test configuration information includes information for configuring the switching fabric emulator to emulate one or more emulated switches; generating, using input regarding an updated test infrastructure and the test configuration information, updated test configuration information for configuring the updated test infrastructure, wherein generating the updated test configuration information includes transpiling or translating a portion of the test configuration information to generate configuration instructions for configuring a physical or non-emulated testbed element; and providing the updated test configuration information to the updated test infrastructure or a related test configuration manager.

Methods, systems, and computer readable media for using a testbed transpiler

Methods, systems, and computer readable media for testing a system under test (SUT). An example system includes a fabric emulation device configured for emulating a data center switching fabric using emulated switch queues and for emulating one or more congestion control mechanisms for network traffic on the data center switching fabric from the SUT. The system includes a test execution manager configured for: executing a test case causing the fabric emulation device to invoke at least a first congestion control mechanism; logging one or more metrics characterizing the first congestion control mechanism in response to invoking the first congestion control mechanism, wherein logging the one or more metrics comprises logging at least one performance metric from at least one emulated switch queue of the fabric emulation device; and outputting a test report based on logging the one or more metrics.

Methods, systems, and computer readable media for testing a system under test using congestion control monitoring

One example method occurs in a test environment comprising network emulation platforms (NEPs), wherein the NEPs implement an emulated switching fabric comprising emulated switches, wherein the NEPs are connected via at least one physical cable. The method includes determining, using a network test system controller, at least one routing path group for communications between the emulated switches, wherein each of the at least one routing path group includes or uses virtual links utilizing one or more lanes of the at least one physical cable; configuring, using the network test system controller, physical ports of the NEPs to assign traffic during a test session to one of the virtual links based on a routing path group identifier associated with the traffic; and initiating, using the network test system controller, the test session involving the test environment.

Methods, systems, and computer readable media for implementing routing path groups between emulated switches

Methods, systems, and computer readable media for test system agent deployment in a smartswitch computing environment are disclosed. One example method occurs at a test system, the method comprising: obtaining test information indicating a smartswitch or a data processing unit (DPU) of the smartswitch for testing in a smartswitch computing environment or at least one test system agent deployment factor, wherein the smartswitch includes a switch processor and DPUs; determining, using the test information and topology information about the smartswitch computing environment, at least one location for deploying at least one test system agent; and providing placement information indicating the at least one location for deploying the at least one test system agent to a target system or to a test system agent controller.

Methods, systems, and computer readable media for test system agent deployment in a smartswitch computing environment

One example method occurs at an impairment configuration manager of a network test system implemented using at least one processor, the method comprising: receiving impairment definition information for defining one or more impairments associated with a test session involving a test infrastructure connecting at least one test application and a system under test (SUT), wherein the impairment definition information includes information for indicating attributes of the one or more impairments using a common data model or data format; generating, using the impairment definition information, at least one set of instructions for configuring at least one impairment element to implement the one or more impairments during the test session; and providing the at least one set of instructions to the at least one impairment element or another entity.

Methods, systems, and computer readable media for using an impairment configuration manager

Methods, systems, and computer readable media for testing a network system under test (SUT). An example system includes physical application-specific integrated circuit (ASIC) switching resources and a switching environment emulator configured for emulating, using the physical ASIC switching resources, data center switching fabric comprising a plurality of data center fabric switching elements. The system includes a first control plane daemon implemented on at least one processor; the first control plane daemon is configured for processing control plane messages for a first data center fabric switching element. The system includes a first port for communicating at least a first control plane message for processing by the first control plane daemon.

Methods, systems, and computer readable media for processing control plane messages for emulated data center switching fabric

A method for testing a link allocation (LA) implementation, the method comprising: at a test system for testing a system under test (SUT): determining at least one LA implementation parameter usable for modifying an LA implementation of the SUT; generating a test session plan for testing the SUT, wherein generating the test session plan includes determining a first plurality of test values for the at least one LA implementation parameter; and initiating, using the test session plan, a test session involving the SUT, wherein, during the test session, the test system causes the SUT to modify the LA implementation using at least one of the first plurality of test values.

Methods, systems and computer readable media for testing link allocation (LA) implementations

Methods, systems, and computer readable media for a collection of distributed highly available (HA) data processing units (DPUs) in a data center. An example system includes a test packet generator configured for generating test traffic and transmitting the test traffic towards an HA DPU pair. The system includes a test controller configured for executing, while the data center is operating with live traffic, a test case and controlling the test packet generator to cause a failover test event at the HA DPU pair. The system includes a monitoring module, deployed on at least one DPU of the HA DPU pair, and configured for monitoring the HA DPU pair during the failover test event and reporting one or more metrics characterizing the failover test event to the test controller.

Methods, systems, and computer readable media for testing data processing units in high availability configurations

Methods, systems, and computer readable media for exposing data processing unit (DPU) traffic in a smartswitch are disclosed. One example method occurs at a smartswitch controller implemented using at least one processor, the method comprising: receiving connection information for communicating with an in-line traffic processing agent; generating, using the connection information, one or more switching rules for causing traffic associated with a target DPU of a smartswitch to be directed to the in-line traffic processing agent; and providing the one or more switching rules to the smartswitch or another entity.

Methods, systems, and computer readable media for exposing data processing unit (DPU) traffic in a smartswitch

According to one method, the method occurs at a first impairment device comprising at least one programmable data plane processor. The method includes receiving, via an application programming interface (API) and from a test controller, command and control instructions for configuring a packet processing pipeline for facilitating traffic impairments; configuring, using the command and control instructions, the packet processing pipeline implemented using the at least one programmable data plane processor; and applying, via the packet processing pipeline, at least one impairment to one or more test packets for testing a system under test (SUT).

Methods, systems, and computer readable media for programmable data plane processor based traffic impairment

Methods, systems, and computer readable media for smart network interface card testing are disclosed. One example method occurs at a network interface card (NIC) comprising a network processing unit executing a monitoring agent for monitoring data traversing the NIC. The method includes obtaining, from a test system or a test traffic generator, at least one test packet; generating, using the monitoring agent, NIC processing information associated with processing the at least one test packet, wherein generating the NIC processing information includes monitoring application layer events, presentation layer events, session layer events, transport layer events, network layer events, driver layer events, kernel layer events, or other events involving the NIC and generating the NIC processing information using the monitored events; and storing or providing the NIC processing information for data analysis.

Growing community of inventors

Bangor, CA, United States of America

Christian Paul Sommers