System and method for determining a data flow path in an overlay network

By collecting and analyzing underlying stream data and overlay stream data, combined with EVPN database technology, the problem of operation and management of virtualized data center networks is solved, and efficient troubleshooting and analysis of virtualized networks is achieved.

CN114884773BActive Publication Date: 2024-11-08HEWLETT PACKARD ENTERPRISE DEV LP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210591965.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2020-07-07
Filing Date
2020-08-14
Publication Date
2024-11-08
Estimated Expiration
2040-08-14

AI Technical Summary

Technical Problem

The prior art is difficult to effectively manage and analyze network operations in virtualized data centers, especially in the combination of physical and virtual networks, and it is difficult to identify data flow paths when tracking network problems, and existing tools are difficult to understand, resulting in inaccurate troubleshooting efficiency.

Method used

By collecting and correlating underlying stream data and overlay stream data, forming rich data flow records, utilizing technologies such as EVPN databases, identifying and analyzing network devices, providing data path visualization to support troubleshooting.

Benefits of technology

It realizes effective troubleshooting and analysis of virtualized networks, reduces the number of underlying network devices, improves the efficiency of solving connectivity problems, and provides insight into virtualized networks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114884773B_ABST
    Figure CN114884773B_ABST
Patent Text Reader

Abstract

Embodiments of the present disclosure relate to systems and methods for determining data flow paths in an overlay network. The present disclosure describes techniques that include collecting underlying flow data within a network and associating the underlying flow data with a source virtual network and a destination virtual network to enable insight into network operation and performance. In one example, the present disclosure describes a method that includes the steps of identifying, for each underlying data flow, a source overlay network and a destination overlay network associated with the underlying data flow, wherein the identifying includes retrieving information identifying the source overlay network and the destination overlay network from one or more Ethernet virtual private network (EVPN) databases.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] This application is a divisional application of an invention patent application with an application date of August 14, 2020, application number 202010820327.9, and invention name “System and method for determining a data flow path in an overlay network”.

[0002] The original application of this application claims priority to U.S. patent application No. 16 / 922,915 filed on July 7, 2020 and priority to U.S. application No. 16 / 541,947 filed on August 15, 2019, the former being a partial continuation application of the latter, and their entire contents are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to the analysis of computer networks, including the analysis of the paths taken by data through the network. Background Art

[0004] Virtualized data centers are becoming a core foundation of modern information technology (IT) infrastructure. Modern data centers rely on virtualized environments, where virtual hosts (eg, virtual machines or containers) deployed within the virtualized environments execute on underlying computing platforms of physical computing devices.

[0005] Current network infrastructure is often a combination of physical and virtual networks. The combination of physical and virtual networks can make it difficult to track down network problems. When identifying network problems, it is convenient for network administrators to see the path that packets take into the network. There are command-line tools that can display the routes, but such tools are difficult to understand. Summary of the invention

[0006] The present disclosure describes technologies, which include collecting information about data services on physical network infrastructure (e.g., underlying flow data) and information about data services on virtual networks (e.g., overlay flow data), and associated data, so as to enable insight into network operations and performance. In some examples, samples of both underlying flow data and overlay flow data are collected and stored in a manner that not only achieves high availability and high-capacity flow data collection but also enables analysis of such data in response to analytical queries. The underlying flow data can be enriched, expanded and / or supplemented with overlay flow data to enable insight into, identification and / or analysis of the underlying network infrastructure that can correspond to the overlay data flow. For example, a network analysis system can collect samples of the underlying flow data, identify the underlying data flow associated with each sample, and identify the overlay network associated with each corresponding underlying data flow. The results can be used to identify the underlying network infrastructure that supports the overlay data flow. In one such example method, the results can also be used to illustrate the components of the underlying network infrastructure corresponding to various overlay data flows or underlying data flows via schematic diagrams and other information displayed on a user interface.

[0007] The technology described herein can provide one or more technical advantages. For example, IT personnel can use information showing how the underlying network infrastructure is related to various overlay data flows to perform effective and simplified troubleshooting and analysis of virtualized networks. As an example, the technology described herein can allow more effective troubleshooting of connectivity by reducing the number of underlying network devices that may be related to connectivity problems. As another example, the technology described herein can allow more effective troubleshooting via data path visualization.

[0008] In some examples, this disclosure describes operations performed by a network analysis system or other network system according to one or more aspects of this disclosure. In one particular example, the present disclosure describes a method comprising: receiving underlying flow data from an underlying network, the underlying network comprising a plurality of network devices, the underlying flow data comprising information identifying an underlying network source, an underlying network destination, an overlay network source, and an overlay network destination for each underlying data flow; identifying, for each underlying data flow, a source overlay network and a destination overlay network associated with the underlying data flow, wherein the identification comprises retrieving information identifying the source overlay network and the destination overlay network from one or more Ethernet virtual private network (EVPN) databases; forming an enriched data flow record for each underlying data flow, the enriched data flow record comprising information identifying, for each underlying data flow, an underlying network source, an underlying network destination, a source overlay network, and a destination overlay network associated with each corresponding underlying data flow; receiving, by a network analysis system, an information request regarding a selected overlay data flow, wherein the information request comprises an overlay source identifier and an overlay destination identifier for the selected overlay data flow; and querying a data repository with the overlay source identifier and the overlay destination identifier to identify, based on the enriched data flow record, one or more network devices from a plurality of network devices in the underlying network that processed at least one packet in the selected overlay data flow.

[0009] In another specific example, the present disclosure describes a system having: a network having a plurality of network devices and one or more virtual networks executed on the network devices; and a processing circuit connected to the network, the processing circuit being configured to perform operations, the operations comprising: receiving underlying flow data from the network, the underlying flow data comprising information identifying an underlying source, an underlying destination, an overlay source, and an overlay destination for each underlying data flow; identifying, for each underlying data flow, a source virtual network and a destination virtual network associated with the underlying data flow, wherein the identifying comprises retrieving a virtual network identifier for the source virtual network and a virtual network identifier for the destination virtual network from an Ethernet VPN (EVPN) database; a virtual network identifier of a network; forming an enriched data flow record for each underlying data flow, the enriched data flow record including information identifying an underlying source, an underlying destination, and virtual network identifiers for a source virtual network and a destination virtual network associated with each underlying data flow; receiving, by a network analysis system, an information request regarding a selected overlay data flow, wherein the information request includes an overlay source identifier and an overlay destination identifier for the overlay data flow; and querying a data repository with the overlay source identifier and the overlay destination identifier to identify, based on the enriched data flow record, one or more network devices among a plurality of network devices that processed at least one packet in the selected overlay data flow.

[0010] In yet another example, the present disclosure describes a non-transitory computer-readable storage medium, the medium including instructions that, when executed, configure a processing circuit of a computing system to perform operations, the operations including: receiving underlying flow data from an underlying network, the underlying network including a plurality of network devices, the underlying flow data including information identifying an underlying network source, an underlying network destination, an overlay network source, and an overlay network destination for each underlying data flow; identifying, for each underlying data flow, a source overlay network and a destination overlay network associated with the underlying data flow, wherein the identifying includes retrieving information identifying the source overlay network and the destination overlay network from one or more Ethernet virtual private network (EVPN) databases; for each underlying The method comprises: forming an enriched data flow record for the layer data flow, the enriched data flow record including information identifying, for each underlying data flow, an underlying network source, an underlying network destination, a source overlay network, and a destination overlay network associated with each corresponding underlying data flow; receiving, by a network analysis system, an information request regarding a selected overlay data flow, wherein the information request includes an overlay source identifier and an overlay destination identifier for the selected overlay data flow; and querying a data repository with the overlay source identifier and the overlay destination identifier to identify, based on the enriched data flow record, one or more network devices from a plurality of network devices in the underlying network that processed at least one packet in the selected overlay data flow. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1A and Figure 1B is a conceptual diagram illustrating an example system including a data center and a network analysis system used to analyze traffic flows across and / or within a data center according to one or more aspects of the present disclosure.

[0012] Figure 2 is a block diagram illustrating an example system including a data center and a network analysis system used to analyze traffic flows across and / or within a data center according to one or more aspects of the present disclosure.

[0013] Figure 3 is a conceptual diagram illustrating example queries performed on stored underlay flow data and overlay flow data according to one or more aspects of the present disclosure.

[0014] Figure 4 is a conceptual diagram illustrating an example user interface presented by a user interface device according to one or more aspects of the present disclosure.

[0015] Figure 5A and Figure 5B is a flow diagram illustrating operations for enriching an underlying data stream in accordance with one or more aspects of the present disclosure.

[0016] Figure 6 is a flow diagram illustrating other operations performed by an example network analysis system according to one or more aspects of the present disclosure.

[0017] Figure 7 is a conceptual diagram illustrating another example user interface presented by a user interface device to display an underlying data path corresponding to an overlay data service according to one or more aspects of the present disclosure. DETAILED DESCRIPTION

[0018] Data centers use virtualized environments in which virtual hosts, such as virtual machines or virtual containers, are deployed and then executed on the underlying computing platform of physical computing devices. As mentioned above, this approach provides efficiency, cost savings, and organizational advantages when deploying data centers. However, this approach can present challenges when analyzing, evaluating, and / or troubleshooting network operations in a data center. IT staff trying to manage a data center still need to have meaningful insights into application workloads. The underlying flow data collected from networked devices can be used to provide this insight.

[0019] Current network infrastructure is often a combination of physical and virtual networks. The combination of physical and virtual networks can make it difficult to track down network problems. For identifying network problems, it is convenient for network administrators to see the path that packets take into the network. There are command-line tools that can show the route taken by packets, but such tools are difficult to understand. Visualizing it on a topology map along with the traffic allows administrators to narrow down the scope of the problem.

[0020] In general, a flow is "a collection of packets that share common properties." Very common flows are based on a 5-tuple: source IP address, destination IP address, source port, destination port, and IP protocol. When a virtual machine sends or receives IP traffic, forward and reverse flow entries are set. An overlay flow entry is created, and the packet is sent to a vRouter agent (such as a Contrail vRouter agent). If relevant, the agent can also create an overlay flow entry for the reverse direction. The vRouter agent then sends the flow to a collector to be stored in an analysis database for further analysis. In one example method, the overlay flow entry includes all information about the source virtual machine IP address and the destination virtual machine IP address and the virtual network. In one example method, each virtual network uses a network to create logical partitions between tenants.

[0021] In various examples described herein, a network analysis system collects underlying traffic samples and overlay traffic samples associated with a flow, and processes the traffic samples via an analysis algorithm to correlate information about overlay traffic with information about the underlying infrastructure. In some examples, a user interface can be used to show how the underlying infrastructure is related to various overlay networks. Thus, the user interface can provide insight into the network and can provide users, administrators, and / or other personnel with tools for network discovery, investigation, and troubleshooting.

[0022] Figure 1A is a conceptual diagram illustrating an example system including a data center and a network analysis system used to analyze traffic flows across and / or within a data center according to one or more aspects of the present disclosure. Figure 1A An example implementation of a network system 100 is illustrated having a data center 101 that hosts one or more computing networks, computing domains, and / or cloud-based computing networks, which are generally referred to herein as cloud-based computing clusters. Cloud-based computing clusters can be co-located in a common overall computing environment (such as a single data center 101) or can be distributed across environments (such as across different data centers 101). Cloud-based computing clusters can, for example, be a combination of different cloud environments, such as an OpenStack cloud environment, a Kubernetes cloud environment, or various combinations of other computing clusters, domains, networks, etc. Other implementations of the network system 100 and data center 101 may include Figure 1A A subset of the components included in the examples and / or may include components not included in Figure 1A Additional components shown in .

[0023] exist Figure 1A In the example of FIG. 1 , data center 101 provides an operating environment for applications and services for customers 104 coupled to data center 101 via service provider network 106. Figure 1A The functions and operations described in the network system 100 may be illustrated as in Figure 1A distributed across multiple devices, but in other examples attributed to Figure 1A The features and techniques of one or more devices in the present invention may be performed internally by local components of one or more such devices. Similarly, one or more such devices may include specific components and perform various techniques that may otherwise be attributed to one or more other devices in the description herein. Further, specific operations, techniques, features, and / or functions may be combined with Figure 1AIn some embodiments, the present invention may be described as being performed by a particular component, device, and / or module. In other examples, such operations, techniques, features, and / or functions may be performed by other components, devices, or modules. Therefore, some operations, techniques, features, and / or functions attributed to one or more components, devices, or modules may be attributed to other components, devices, and / or modules, even if not specifically described in this manner herein.

[0024] Data center 101 hosts infrastructure equipment, such as networking and storage systems, redundant power supplies, and environmental controls.Service provider network 106 may be coupled to one or more networks managed by other providers, and thus may form part of a large-scale public network infrastructure such as the Internet.

[0025] In some examples, data center 101 may represent one of many geographically distributed network data centers. Figure 1A As shown in the example of , data center 101 is a facility that provides network services to customers 104. Customers 104 can be collective entities such as businesses and governments or can be individuals. For example, a network data center can host web services for multiple businesses and end users. Other exemplary services may include data storage, virtual private networks, business engineering, file services, data mining, scientific computing or supercomputing, etc. In some examples, data center 101 is a separate network server, network peer, or other.

[0026] exist Figure 1A In the example of FIG. 1 , data center 101 includes a group of storage systems, application servers, computing nodes, or other devices, including network devices 110A to 110N (collectively referred to as “network devices 110”). In some examples, such as Figure 1A As shown, the devices 110 are interconnected via a high-speed switching structure 121 provided by one or more layers of physical network switches and routers. In some examples, the network device 110 may be included in the structure 121, but is shown separately here for ease of illustration. The network device 110 can be any of many different types of network devices (core switches, backbone network devices, leaf network devices, edge network devices, or other network devices), but in some examples, one or more devices 110 can act as a physical computing node in a data center. For example, one or more of the devices 110 can provide an operating environment for executing one or more customer-specific virtual machines or other virtualized instances (such as containers). In this example, one or more of the devices 110 may alternatively be referred to as host computing devices or more simply as hosts. The network device 110 can thereby execute one or more virtualized instances, such as virtual machines, containers, or other virtual execution environments for running one or more services such as virtualized network functions (VNFs).

[0027] In general, each network device 110 can be any type of device that can operate on a network and can generate data (e.g., flow data or sFlow data) that is accessible via telemetry or other means, which can include any type of computing device, sensor, camera, node, monitoring device, or other device. Further, some or all of the network devices 110 can represent components of another device, where such components can generate data that can be collected via telemetry or other means. For example, some or all of the network devices 110 can represent physical or virtual network devices, such as switches, routers, hubs, gateways, security devices (such as firewalls), intrusion detection and / or intrusion prevention devices.

[0028] Although not specifically shown, the switch fabric 121 may include a top-of-rack (TOR) switch coupled to a distribution layer of chassis switches, and the data center 101 may include one or more non-edge switches, routers, hubs, gateways, security devices (such as firewalls), intrusion detection and / or intrusion prevention devices, servers, computer terminals, laptops, printers, databases, wireless mobile devices (such as cellular phones or personal digital assistants), wireless access points, bridges, cable modems, application accelerators, or other network devices. The switch fabric 121 may perform layer 3 routing to route network traffic between the data center 101 and the customer 104 via the service provider network 106. In an example approach, the gateway 108 is used to forward and receive packets between the switch fabric 121 and the service provider network 106.

[0029] exist Figure 1A In the illustrated example, data center 101 includes a network analysis system 140, a software defined networking (“SDN”) controller 132, and an orchestration engine 130. According to one or more examples of the present disclosure, SDN controller 132 provides a logically (and in some cases physically) centralized controller for facilitating the operation of one or more virtual networks within data center 101. In some examples, SDN controller 132 operates in response to configuration input received via northbound application programming interface (API) 131 from orchestration engine 130, which in turn may operate in response to configuration input received from administrator 128 interacting with and / or operating user interface device 129.

[0030] The user interface device 129 may be implemented as any suitable device for presenting output and / or accepting user input. For example, the user interface device 129 may include a display. The user interface device 129 may be a computing system, such as a mobile or non-mobile computing device operated by a user and / or administrator 128. According to one or more aspects of the present disclosure, the user interface device 129 may, for example, represent a workstation, a laptop or notebook computer, a desktop computer, a tablet computer, or any other computing device that can be operated by a user and / or present a user interface. In some examples, the user interface device 129 may be physically separated from the network analysis system 140, the SDN controller 132, and the orchestration engine 130 and / or be in a different location from the network analysis system 140, the SDN controller 132, and the orchestration engine 130. In such an example, the user interface device 129 may communicate with the network analysis system 140, the SDN controller 132, and the orchestration engine 130 via a network or other communication means. In other examples, user interface device 129 may be a local peripheral device to network analysis system 140 , SDN controller 132 , or orchestration engine 130 , or may be integrated into network analysis system 140 , SDN controller 132 , or orchestration engine 130 .

[0031] In some examples, orchestration engine 130 manages functions of data center 101, such as computing, storage, networking, and application resources. For example, orchestration engine 130 can create a virtual network for a tenant within data center 101 or across two or more data centers 101. Orchestration engine 130 can also attach a virtual machine (VM) to a tenant's virtual network. Orchestration engine 130 can also connect a tenant's virtual network to an external network, such as the Internet or a VPN. Orchestration engine 130 can also implement security policies across a group of VMs or to the boundaries of a tenant network, and / or can deploy network services (e.g., load balancers) in a tenant's virtual network.

[0032] In some examples, the SDN controller 132 manages the network within the data center 101 and manages networking services such as load balancing, security, and can allocate resources from the device 110 acting as a host device to various applications via the southbound API 133. In one example approach, the southbound API 133 represents a set of communication protocols that the SDN controller 132 utilizes to make the actual state of the network within the data center 101 equal to the desired state as specified by the orchestration engine 130. For example, the SDN controller 132 can implement high-level requests from the orchestration engine 130 by configuring the following: physical switches, such as top-of-rack (TOR) switches, chassis switches, and switch fabrics 121; physical routers; physical service nodes, such as firewalls and load balancers; and virtual services such as virtual firewalls in VMs. In one such example approach, the SDN controller 132 maintains routing, networking, and configuration information in a state database.

[0033] In one example method, the network analysis system 140 interacts with one or more of the network devices 110 (and / or other devices) to collect flow data across the data center 101 and / or the network system 100. In one such example method, the network device 110 is configured as an underlying infrastructure for supporting one or more overlay networks. In this example method, the flow data may include underlying flow data and overlay flow data. In some examples, the underlying flow data may be collected with the aid of samples of flow data collected at layer 2 of the OSI model. The overlay flow data may be data (e.g., data samples) derived from overlay services across one or more virtual networks established within the network system 100. The overlay flow data may, for example, include information identifying a source virtual network and a destination virtual network.

[0034] In one example method, devices 110 are configured to collect flow data. In one such example method, one or more devices, such as network analysis system 140 and / or SDN controller 132, output a configuration signal to each device 110 that configures the device 110 to collect flow data (including underlying flow data and / or overlay flow data). Thereafter, as data packets are processed by each device 110, each device 110 transmits the underlying flow data and / or overlay flow data to network analysis system 140. Network analysis system 140 receives the flow data, prepares it for use in response to analysis queries, and stores the flow data. Figure 1A In the example of FIG. 1 , other network devices including network devices (not specifically shown) within switch fabric 121 may also be configured to collect underlay and / or overlay flow data.

[0035] As mentioned above, the network analysis system 140 processes queries about the flow data. For example, in one example, the user interface device 129 detects an input and passes information about the input to the network analysis system 140. The network analysis system 140 determines that the information corresponds to a request for information about the network system 100 from a user of the user interface device 129. The network analysis system 140 processes the request by querying the stored flow data. The network analysis system 140 generates a response to the query based on the stored flow data and outputs information about the response to the user interface device 129.

[0036] In some examples, the request received from user interface device 129 may include source and / or destination virtual network identifiers. In such examples, network analysis system 140 may, in response to such a request, identify one or more possible data paths on underlying network devices that packets traveling from the source virtual network to the destination virtual network may have taken. To identify the possible data paths, network analysis system 140 may correlate the collected overlay flow data with the collected underlying flow data so that the underlying network devices used by the overlay data flow may be identified.

[0037] Figure 1B is a conceptual diagram illustrating an example system including a data center and a network analysis system used to analyze traffic flows across and / or within a data center according to one or more aspects of the present disclosure. Figure 1B Including combination Figure 1A Many of the same elements described; Figure 1A The same reference numerals as in Figure 1B The components shown are similar. Generally speaking, such same numbered components can be combined with Figure 1A The descriptions of corresponding elements are provided to be implemented in a consistent manner, but in some examples, such elements may relate to alternative implementations having more, fewer and / or different capabilities and attributes.

[0038] Figure 1B Various components of the network analysis system 140 are illustrated. Figure 1BIn the example shown, the network analysis system 140 includes a load balancer 141, a flow collector 142, a queue and event repository 143, a topology and metric source 144, a data repository 145, and a flow API 146. In general, the network analysis system 140 and the components 141 to 146 of the network analysis system 140 are designed and configured to ensure high availability and the ability to handle large volumes of flow data. In some examples, multiple instances of the components 141 to 146 of the network analysis system 140 can be orchestrated (e.g., by the orchestration engine 130) to execute on different physical servers to ensure that there is no single point of failure for any component of the network analysis system 140. In some examples, the network analysis system 140 or its components can be independently and horizontally scaled to enable efficient and / or effective processing of expected volumes of traffic (e.g., flow data).

[0039] and Figure 1A Same as in Figure 1B The network analysis system 140 may configure each device 110 to collect flow data. For example, the network analysis system 140 may output a signal to each device 110 to configure each device 110 to collect flow data, the flow data including underlying flow data and overlay flow data. Thereafter, one or more of the devices 110 may collect the underlying flow data and overlay flow data, and report such flow data to the network analysis system 140.

[0040] exist Figure 1B In the example shown, load balancer 141 receives flow data from each device 110. In one such example approach, load balancer 141 can distribute traffic across multiple flow collectors 142 to ensure an active / active failover strategy for flow collectors 142. In some examples, multiple load balancers 141 may be required to ensure high availability and scalability.

[0041] exist Figure 1BIn the example shown, the flow collector 142 collects data from the load balancer 141. For example, the flow collector 142 of the network analysis system 140 receives and processes flow packets from each device 110 (after being processed by the load balancer 141). The flow collector 142 sends the flow packets upstream to the queue and event repository 143. In some examples, the flow collector 142 can address, process and / or accommodate unified data from sFlow, NetFlow v9, IPFIX, jFlow, Contrail Flow, and other formats. sFlow technology is a monitoring technology for high-speed switching networks or high-speed routing networks. The sFlow monitoring technology collects samples of network packets and sends them to the flow collector 142 in the form of UDP datagrams. For example, the flow collector 142 may be able to parse the internal headers from sFlow packets and other data flow packets. The flow collector 142 may also be able to handle message overflow, rich flow records with topology information (e.g., AppFormix topology information), and other aspects of flow data analysis. In one example approach, flow collector 142 converts the data to a binary format before writing or otherwise sending the data to queue and event repository 143. The underlying flow data of type "sFlow" (referring to "sampled flow") is a standard for packet export at layer 2 of the OSI model. It provides a means for exporting truncated packets, as well as interface counters for network monitoring purposes.

[0042] In one example approach, queue and event store 143 processes data processed by stream collector(s) 142. For example, queue and event store 143 may receive data from one or more stream collectors 142, store the data, and make the data available for ingestion in data store 145. In some examples, this enables separation of the tasks of receiving and storing large volumes of data from the tasks of indexing the data and preparing it for analytical queries.

[0043] In some examples, the queue and event repository 143 also allows independent users to directly consume the stream of the flow record. In some examples, the queue and event repository 143 can be used to discover anomalies and generate alarms in real time. In some examples, the flow data can be parsed by reading encapsulated packets (including VXLAN, MPLS on UDP, and MPLS on GRE) to extract additional information. In one such example method, the queue and event repository 143 parses the internal (bottom layer) packet to obtain the source IP address, destination IP address, source port, destination port, and protocol. Some types of flow data (including sFlow data) only include fragments of sampled network services (e.g., the first 128 bytes in sFlow), so in some cases, the flow data may not include all internal fields. In an example method, such a field is marked as missing.

[0044] The topology and metric sources 144 may enrich or augment the data with topology information and / or metric information. For example, the topology and metric sources 144 may provide network topology metadata, which may include identified nodes or network devices, configuration information, configurations, established links, and other information about such nodes and / or network devices. In some examples, the topology and metric sources 144 may use AppFormix topology data, or may include an executing AppFormix module. The information received from the topology and metric sources 144 may be used to enrich the flow data collected by the flow collector 142 and to support the flow API 146 in processing queries of the data repository 145.

[0045] In one example, data repository 145 is configured to store data received from queue and event repository 143 and from topology and metric sources 144 in an indexed format, thereby enabling fast aggregate queries and fast random access data retrieval. In some examples, data repository 145 can achieve fault tolerance and high availability by sharding and replicating data.

[0046] The flow API 146 can process query requests sent by one or more user interface devices 129. For example, in some examples, the flow API 146 can receive the query request from the user interface device 129 via an HTTP POST request. In this example, the flow API 146 converts the information included in the request into a query to the data repository 145. In order to create the query, the flow API 146 can use the topology information from the topology and metric source 144. In some example methods, the flow API 146 can use one or more of such queries to perform analysis on behalf of the user interface device 129. Such analysis may include business deduplication, overlay-underlay correlation, business path identification, and / or heatmap business calculation. Such analysis may also involve correlating the underlying flow data with the overlay flow data, thereby identifying which underlying network devices are related to the business flowing on the virtual network and / or between two virtual machines.

[0047] With the techniques according to one or more aspects of the present disclosure, network analysis system 140 may be able to determine, for a given data flow, to which tenant the data flow belongs in a multi-tenant data center, such as by correlating underlying flow data with overlay flow data. Further, network analysis system 140 may also be able to determine which virtual computing instances (e.g., virtual machines or containers) are the source and / or destination virtual computing instances for such a flow. Still further, correlating underlying flow data with overlay flow data, such as by enriching the underlying flow data with overlay flow data, may facilitate troubleshooting of performance or other issues that may arise in network system 100.

[0048] For example, in some cases, connectivity issues may occur during a specific time frame when limited information is available but information about the source and destination virtual networks is known. Solving such problems may be challenging because it may be difficult to ascertain the physical path taken by the data flow through the network given the source virtual network and the destination virtual network. Because the actual physical path through the underlying infrastructure may not otherwise be easily known, there may be many network devices or physical links that are potential causes of connectivity issues. However, by collecting underlying flow data and overlay flow data and enriching the underlying flow data with overlay flow data collected during the same time period, it is possible to identify which underlying network devices processed the data flow and identify the physical links traversed by the data flow, thereby enabling the data path of the data flow through the data center 101 to be determined, or at least the possible data path for such data flow to be determined. Therefore, solving such connectivity problems can be done more efficiently, at least because the number of underlying network devices 110 associated with the connectivity problem can be greatly reduced through such analysis.

[0049] Figure 2is a block diagram illustrating an example system including a data center and a network analysis system used to analyze traffic flows across and / or within a data center according to one or more aspects of the present disclosure. Figure 2 The network system 200 can be described as Figure 1A The network system 100 or Figure 1B An example or alternative implementation of the network system 100 of FIG. Figure 1A and Figure 1B Described in the context of Figure 2 one or more aspects of .

[0050] Although data centers such as Figure 1A , Figure 1B as well as Figure 2 The data centers shown may be operated by any entity, but some data centers 101 are operated by service providers whose business model is to provide computing power to their clients. For this reason, data centers 101 typically contain a large number of computing nodes or host devices. To operate efficiently, these hosts may need to be connected to each other and the outside world; this capability is achieved by, for example, Figure 1A and Figure 1B The physical network devices 110 shown are provided, and these physical network devices 110 can be interconnected in a leaf-spine topology. The collection of these physical devices (such as network devices and hosts) forms an underlying network.

[0051] Each host device in such a data center can have two or more virtual machines running on that device; the combination of the virtual machines and other tasks performed on each host device 210 is the device's workload. Clients in the data center typically have access to these workloads and can use such workloads to install applications and perform other operations. Workloads running on different host devices but accessible by one client are organized into virtual networks. Each client typically has at least one virtual network. These virtual networks are also called overlay networks. In some cases, clients in the data center may experience connectivity issues between two applications running on different workloads. Solving this problem is often complicated due to the deployment of workloads in large multi-tenant data centers.

[0052] exist Figure 2 In the example of FIG. 2 , network analysis system 240 is connected to host devices 210A to 210N via network 205. In some example methods, network analysis system 240 may correspond to Figure 1A and Figure 1BThe network analysis system 140 shown is an example or alternative implementation. The host devices 210A, 210B through 210N may be collectively referred to as "host devices 210" to represent any number of host devices 210. Each host device 210 may be Figure 1A and Figure 1B An example of device 110, but in Figure 2 In the example of FIG. 1 , each host device 210 is implemented as a server or host device operating as a computing node of a virtualized data center, as opposed to being a mere network device. Figure 2 In the example of FIG. 1 , each host device 210 executes multiple virtual computing instances, such as virtual machines 228A through 228N, collectively referred to as “virtual machines 228 ”.

[0053] In one example, network 205 is implemented as a leaf-spine topology, where network devices designated as leaf devices 203 are connected to network devices designated as spine devices 202. In one such example method, such as Figure 2 As shown, spine devices 202A and 202B (collectively referred to as "spine devices 202", and any number of spine devices 202 are represented) are connected to leaf devices 203A, 203B, and leaf devices 203C (collectively referred to as "leaf devices 203", and any number of leaf devices 203 are represented). Although network 205 is illustrated as having spine devices 202 and leaf devices 203, other types of network devices may be included in network 205, including core switches, edge network devices, top-of-rack devices, and other network devices.

[0054] exist Figure 2 In the example shown, Figure 1A and Figure 1B Similarly, user interface device 129, which may be operated by administrator 128, is also connected to network analysis system 240 via network 205. In some examples, user interface device 129 may present one or more graphical user interfaces at a display device associated with user interface device 129, some of which may have a form similar to that shown in user interface 400.

[0055] Figure 2 The underlying flow data 204 and overlay flow data 206 are illustrated flowing through the network 205 to the network analysis system 240. In this example, the underlying flow data 204 is shown leaving the backbone 202A of the network 205 and flowing to the network analysis system 240. Similarly, the overlay flow data 206 is shown leaving the host device 210A and flowing through the network 205 to the network analysis platform 240. For simplicity, Figure 2A single instance of underlying flow data 204 and a single instance of overlay flow data 206 are illustrated. However, it should be understood that each of the spine devices 202 and leaf devices 203 can generate underlying flow data 204 and transmit it to the network analysis system 240, and in some examples, each host device 210 (and / or other devices) can generate underlying flow data 204 and transmit such data across the network 205 to the network analysis system 240. Further, each host device 210 (and / or other devices) can generate overlay flow data 206 and transmit such data to the network analysis system 240 via the network 205.

[0056] Network 205 may correspond to Figure 1A and Figure 1B The network 205 may include any one of the switch fabric 121 and / or the service provider network 106, or alternatively, may correspond to a combination of the switch fabric 121, the service provider network 106, and / or another network. Figure 1A and Figure 1B Some components of include gateway 108, SDN controller 132 and orchestration engine 130.

[0057] In general, network 205 may be the Internet, or may include or represent any public or private communications network or other network. For example, network 205 may be a cellular network, ZigBee, Bluetooth, Near Field Communication (NFC), satellite, enterprise, service provider, and / or other types of networks that enable the transfer of data between computing systems, servers, and computing devices. One or more of the client devices, server devices, or other devices may transmit and receive data, commands, control signals, and / or other information across the network 205 using any suitable communication technology. The network 205 may include one or more network hubs, network switches, network routers, satellite dishes, or any other network devices. Such devices or components may be operatively coupled to each other to provide information exchange between computers, devices, or other components (e.g., between one or more client devices or systems and one or more server devices or systems). Figure 2 Each device or system shown may be operatively coupled to the network 205 using one or more network links. The links coupling such devices or systems to the network 205 may be Ethernet, asynchronous transfer mode (ATM), or other types of network connections, and such connections may be wireless and / or wired connections. Figure 2 One or more devices or systems shown or otherwise on network 205 may be in a remote location relative to one or more other shown devices or systems.

[0058] The network analysis system 240 may be implemented as any suitable computing system, such as one or more server computers, workstations, mainframes, appliances, cloud computing systems, and / or other computing systems that may be capable of performing operations and / or functions described according to one or more aspects of the present disclosure. In some examples, the network analysis system 240 represents a cloud computing system, a server farm, and / or a server cluster (or a portion thereof) that provides services to client devices and other devices or systems. In other examples, the network analysis system 240 may represent or be implemented with the aid of one or more virtualized computing instances (e.g., virtual machines, containers) of a data center, cloud computing system, server farm, and / or server cluster.

[0059] exist Figure 2 In the example of , the network analysis system 240 may include a power supply 241, one or more processors 243, one or more communication units 245, one or more input devices 246, and one or more output devices 247. The storage device 250 may include one or more collector modules 252, a user interface module 254, a stream API 256, and a data repository 259.

[0060] One or more of the devices, modules, storage areas, or other components of network analysis system 240 may be interconnected to enable inter-component communication (physically, communicatively, and / or operationally.) In some examples, such connectivity may be provided via a communication channel (e.g., communication channel 242), a system bus, a network connection, an inter-process communication data structure, or any other method for transferring data.

[0061] Power supply 241 can provide power to one or more components of network analysis system 240. Power supply 241 can receive power from a main alternating current (AC) power source in a data center, building, home, or other location. In other examples, power supply 241 can be a battery or a device that supplies direct current (DC). In yet other examples, network analysis system 240 and / or power supply 241 can receive power from another source. One or more devices or components illustrated within network analysis system 240 can be connected to power supply 241, and / or can receive power from power supply 241. Power supply 241 can have intelligent power management or consumption capabilities, and such features can be controlled, accessed, or adjusted by one or more modules of network analysis system 240 and / or by one or more processors 243 to intelligently consume, distribute, supply, or otherwise manage power.

[0062] The one or more processors 243 of the network analysis system 240 can implement functionality and / or execute instructions associated with the network analysis system 240 or associated with one or more modules illustrated and / or described herein. The one or more processors 243 can be, can be a part of, and / or can include processing circuitry that performs operations in accordance with one or more aspects of the present disclosure. Examples of processors 243 include microprocessors, application processors, display controllers, auxiliary processors, one or more sensor hubs, and any other hardware configured to function as a processor, processing unit, or processing device. The network analysis system 240 can use one or more processors 243 to perform operations in accordance with one or more aspects of the present disclosure using software, hardware, firmware, or a mixture of hardware, software, and firmware resident in and / or executed at the network analysis system 240.

[0063] One or more communication units 245 of network analysis system 240 can communicate with devices external to network analysis system 240 by transmitting and / or receiving data, and in some aspects can operate as both an input device and an output device. In some examples, communication unit 245 can communicate with other devices over a network. In other examples, communication unit 245 can send and / or receive radio signals over a radio network, such as a cellular radio network. Examples of communication unit 245 include a network interface card (e.g., such as an Ethernet card), an optical transceiver, a radio frequency transceiver, a GPS receiver, or any other type of device that can send and / or receive information. Other examples of communication unit 245 can include: a device that can transmit and / or receive information over a network. Devices that communicate with GPS, NFC, ZigBee, and cellular networks (e.g., 3G, 4G, 5G), and found in mobile devices and Universal Serial Bus (USB) controllers, etc. Radio transceiver. Such communications may follow, implement or comply with appropriate protocols, including Transmission Control Protocol / Internet Protocol (TCP / IP), Ethernet, Bluetooth, NFC or other technologies or protocols.

[0064] The one or more input devices 246 may represent any input device of the network analysis system 240 not otherwise separately described herein. The one or more input devices 246 may generate, receive, and / or process input from any type of device capable of detecting input from a person or a machine. For example, the one or more input devices 246 may generate, receive, and / or process input in the form of electrical, physical, audio, image, and / or visual input (e.g., peripherals, keyboards, microphones, cameras).

[0065] The one or more output devices 247 may represent any output device of the network analysis system 240 not otherwise separately described herein. The one or more output devices 247 may generate, receive, and / or process input from any type of device capable of detecting input from a person or a machine. For example, the one or more output devices 247 may generate, receive, and / or process output in the form of electrical and / or physical output (e.g., peripheral devices, actuators).

[0066] One or more storage devices 250 within the network analysis system 240 may store information for processing during operation of the network analysis system 240. The storage device 250 may also store program instructions and / or data associated with one or more modules described according to one or more aspects of the present disclosure. One or more processors 243 and one or more storage devices 250 may provide an operating environment or platform for such modules, which may be implemented as software, but in some examples may include any combination of hardware, firmware, and software. One or more processors 243 may execute instructions, and one or more storage devices 250 may store instructions and / or data for one or more modules. The combination of the processor 243 and the storage device 250 may retrieve, store, and / or execute instructions and / or data for one or more applications, modules, or software. The processor 243 and / or the storage device 250 may also be operably coupled to one or more other software and / or hardware components, including but not limited to one or more components of the network analysis system 240 and / or one or more devices or systems illustrated as being connected to the network analysis system 240.

[0067] In some examples, one or more storage devices 250 are implemented with temporary storage, which may mean that the primary purpose of one or more storage devices is not long-term storage. The storage device 250 of the network analysis system 240 may be configured to perform short-term information storage as a volatile memory, so that the stored content is not retained when deactivated. Examples of volatile memory include random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), and other forms of volatile memory known in the art. In some examples, the storage device 250 also includes one or more computer-readable storage media. The storage device 250 may be configured to store a larger amount of information than a volatile memory. The storage device 250 may also be configured to perform long-term information storage as a non-volatile memory space and retain information after an activation / deactivation cycle. Examples of non-volatile memory include magnetic hard disks, optical disks, flash memory, or electrically programmable memory (EPROM) or electrically erasable programmable (EEPROM) memory.

[0068] In one example approach, the collector module 252 can perform functions related to receiving both the underlying flow data 204 and the overlay flow data 206, and perform load balancing as needed to ensure high availability, throughput, and scalability for collecting such flow data. The collector module 252 can process the data to prepare the data for storage in the data repository 259. In some examples, the collector module 252 can store the data in the data repository 259.

[0069] User interface module 254 may perform functions related to generating a user interface for presenting the results of an analytical query executed by stream API 256. In some examples, user interface module 254 may generate information sufficient to generate a set of user interfaces and cause communication unit 215 to output such information over network 205 for use by user interface device 129 to present one or more user interfaces at a display device associated with user interface device 129.

[0070] The stream API 256 may perform analytical queries involving data stored in the data repository 259 that originates from the collection collected by the collector module 252 of the underlying stream data 204 and the overlay stream data 206. In some examples, the stream API 256 may receive a request in the form of information originating from an HTTP POST request, and in response, may convert the request into a query to be performed on the data stored in the data repository 259. Further, in some examples, the stream API 256 may obtain topology information related to the device 110 and perform analysis including data deduplication, overlay-underlay correlation, traffic path identification, and heat map traffic calculation.

[0071] The data repository 259 may represent any suitable data structure or storage medium for storing information related to data stream information, including storage of data derived from the underlying stream data 204 and the overlay stream data 206. The data repository 259 may be used to store data in an indexed format, thereby enabling fast data retrieval and query execution. The information stored in the data repository 259 may be searchable and / or categorized, so that one or more modules within the network analysis system 240 may provide an input requesting information from the data repository 259, and in response to the input, receive information stored in the data repository 259. The data repository 259 may be primarily maintained by the collector module 252. The data repository 259 may be implemented with the aid of multiple hardware devices, and may achieve fault tolerance and high availability by sharding and replicating data. In some examples, various aspects of the data repository 259 may be implemented using the open source ClickHouse column-oriented database management system.

[0072] As mentioned above, each host device 210 represents a physical computing device or computing node that provides an execution environment for a virtual host, virtual machine, container, and / or other virtualized computing resources. In some examples, each host device 210 can be a component of a cloud computing system, server farm, and / or server cluster (or a portion thereof) that provides services to client devices and other devices or systems.

[0073] Certain aspects of host device 210 are described herein with respect to host device 210A. Other host devices 210 (e.g., host devices 210B to 210N) may be similarly described and may also include the same, similar, or corresponding components, devices, modules, functionalities, and / or other features. Therefore, the description herein with respect to host device 210A may be correspondingly applied to one or more other host devices 210 (e.g., any one of host devices 210B to 210N).

[0074] exist Figure 2 In the example of , host device 210A includes basic physical computing hardware, which includes power supply 211, one or more processors 213, one or more communication units 215, one or more input devices 216, one or more output devices 217, and one or more storage devices 220. Storage device 220 may include hypervisor 221, which includes kernel module 222, virtual router module 224, and agent module 226. Virtual machines 228A to 228N (collectively referred to as "virtual machines 228", and representing any number of virtual machines 228) are executed on hypervisor 221 or controlled by hypervisor 221. Similarly, virtual router agent 229 can be executed on hypervisor 221 or under the control of hypervisor 221. One or more of the devices, modules, storage areas, or other components of host device 210 can be interconnected to enable inter-component communication (physically, communicatively, and / or operationally). In some examples, such connectivity can be provided by a communication channel (e.g., communication channel 212), a system bus, a network connection, an inter-process communication data structure, or any other method for transmitting data.

[0075] The power supply 211 may provide power to one or more components of the host device 210. The processor 213 may implement functionality and / or execute instructions associated with the host device 210 and the hypervisor 221. The communication unit 215 may communicate with other devices or systems on behalf of the host device 210. One or more input devices 216 and output devices 217 may represent any other input and / or output devices associated with the host device 210. The storage device 220 may store information for processing during operation of the host device 210A. Each of such components may be implemented in a manner similar to that described herein in conjunction with the network analysis system 240 or otherwise.

[0076] The hypervisor 221 can act as a module or system that instantiates, creates, and / or executes one or more virtual machines 228 on an underlying host hardware device. In some contexts, the hypervisor 221 can be referred to as a virtual machine manager (VMM). The hypervisor 221 can execute within an execution environment provided by the storage device 220 and the processor 213 or on an operating system kernel (e.g., kernel module 222). In some examples, the hypervisor 221 is an operating system-level component that executes on a hardware platform (e.g., host 210) to provide a virtualized operating environment and orchestration controller for virtual machines 228 and / or other types of virtual computing instances. In other examples, the hypervisor 221 can be a software and / or firmware layer that provides a lightweight kernel and operates to provide a virtualized operating environment and orchestration controller for virtual machines 228 and / or other types of virtual computing instances. The hypervisor 221 can incorporate the functionality of the kernel module 222 (e.g., as a "type 1 hypervisor"), such as Figure 2 In other examples, hypervisor 221 can execute on a core (eg, as a "type 2 hypervisor").

[0077] The virtual router module 224 can execute multiple routing instances for corresponding virtual networks within the data center 101, and can transmit packet routing to appropriate virtual machines executed within the operating environment provided by the device 110. The virtual router module 224 can also be responsible for collecting overlay flow data, such as Contrail Flow data when used in an infrastructure that adopts Contrail SDN. Therefore, each host device 210 may include a virtual router. The packet received by the virtual router module 224 of the host device 210A, for example, from the underlying physical network structure may include an outer header to allow the physical network structure to tunnel the payload or "inner packet" to the physical network address of the network interface for the host device 210A. The outer header may include not only the physical network address of the server network interface, but also a virtual network identifier, such as a VxLAN tag or a multi-protocol label switching (MPLS) label that identifies one of the virtual networks and the corresponding routing instance executed by the virtual router. The inner packet includes an inner header having a destination network address that conforms to the virtual network addressing space for the virtual network identified by the virtual network identifier.

[0078] In one example approach, the agent module 226 may be executed as part of the hypervisor 221. In another example approach, the agent module 226 may be executed in kernel space or as part of the kernel module 222. The agent module 226 may monitor some or all performance metrics associated with the host device 210A and may implement and / or execute actions that may be taken from the policy controller ( Figure 2 The proxy module 226 may configure the virtual router module 224 to transmit the overlay flow data to the network analysis system 240.

[0079] Virtual machines 228A through 228N (collectively referred to as "virtual machines 228" and representing any number of virtual machines 228) may represent example instances of virtual machines 228. Host device 210A may divide the virtual and / or physical address space provided by storage device 220 into a user space for running user processes. Host device 210A may also divide the virtual and / or physical address space provided by storage device 220 into a kernel space, which is protected and may not be accessible to user processes.

[0080] In general, each virtual machine 228 may be any type of software application, and each virtual machine may be assigned a virtual address for use within a corresponding virtual network, where each virtual network may be a different virtual subnet provided by virtual router module 224. For example, each virtual machine 228 may be assigned its own virtual layer three (L3) IP address for sending and receiving communications, but each virtual machine is unaware of the IP address of the physical server on which the virtual machine is executing. In this manner, a "virtual address" is an address for an application that is different from the address for the underlying physical computer system (e.g., Figure 2 The logical address of the host device 210A in the example.

[0081] Each virtual machine 228 may represent a tenant virtual machine that runs a client application (such as a web server, a database server, an enterprise application) or hosts a virtualized service for creating a service chain. In some cases, any one or more of the host device 210 or another computing device directly (i.e., not as a virtual machine) hosts the client application. Although one or more aspects of the present disclosure are described in terms of a virtual machine or a virtual host, the techniques described herein for such a virtual machine or a virtual host according to one or more aspects of the present disclosure may also be applied to containers, applications, processes, or other execution units (virtualized or non-virtualized) executed on the host device 210.

[0082] Virtual Router Agent 229 Figure 2 In the example of , the virtual router agent 229 is included in the host device 210A and can communicate with the SDN controller 132 and the virtual router module 224 to control the overlay of the virtual network and coordinate the routing of data packets within the host device 210A. In general, the virtual router agent 229 communicates with the SDN controller 132, which generates commands to control the routing of packets through the data center 101. The virtual router agent 229 can be executed in user space and operate as a proxy for control plane messages between the virtual machine 228 and the SDN controller 132. For example, the virtual machine 228A can request to send a message using its virtual address via the virtual router agent 229, and the virtual router agent 229 can then send a message and request to receive a response to the message for the virtual address of the virtual machine 228A, which initiated the first message. In some cases, the virtual machine 228A can call a procedure or function call presented by the application programming interface of the virtual router agent 229, and in this example, the virtual router agent 229 also handles the encapsulation of the message, including addressing.

[0083] The network analysis system 240 can configure each of the backbone devices 202 and the leaf devices 203 to collect the underlying flow data 204. For example, in the example of Figure 2In the described example, the collector module 252 of the network analysis system 240 causes the communication unit 215 to output one or more signals through the network 205. Each of the backbone device 202 and the leaf device 203 detects the signal and interprets the signal as a command to implement the collection of the underlying flow data 204. For example, after detecting the signal from the network analysis system 240, the backbone device 202A configures itself to collect sFlow data and transmits the sFlow data (as the underlying flow data 204) to the network analysis system 240 through the network 205. As another example, after detecting the signal from the network analysis system 240, the leaf device 203A detects the signal and configures itself to collect sFlow data and transmits the sFlow data to the network analysis system 240 through the network 205. Further, in some examples, each host device 210 can detect the signal from the network analysis system 240 and interpret the signal as a command to implement the collection of sFlow data. Therefore, in some examples, the sFlow data can be collected by the collector module executed on the host device 210.

[0084] Thus, in the described example, the backbone devices 202, the leaf devices 203 (and possibly one or more of the host devices 210) collect sFlow data. However, in other examples, one or more of such devices may collect other types of underlying flow data 204, such as IPFIX and / or NetFlow data. Collecting any such underlying flow data may involve collecting five-tuple data including source and destination IP addresses, source and destination port numbers, and the network protocol used.

[0085] The network analysis system 240 can configure each host device 210 to collect overlay flow data 206. For example, referring to Figure 2 In the depicted example, the collector module 252 causes the communication unit 215 to output one or more signals through the network 205. Each host device 210 detects the signal, which is interpreted as a command to collect the overlay flow data 206 and transmit the overlay flow data 206 to the network analysis system 240. For example, referring to the host device 210A, the communication unit 215 of the host device 210A detects the signal through the network 205 and outputs information about the signal to the hypervisor 221. The hypervisor 221 outputs the information to the agent module 226. The agent module 226 interprets the information from the hypervisor 221 as a command to collect the overlay flow data 206. The agent module 226 configures the virtual router module 224 to collect the overlay flow data 206 by sampling the network traffic and transmit the overlay flow data 206 to the network analysis system 240.

[0086] In at least some examples, overlay flow data 206 includes five-tuple information about source and destination addresses, source and destination ports, and protocols. Additionally, overlay flow data 206 may include information about virtual networks associated with the overlay data flow, including a source virtual network and a destination virtual network. In some examples, particularly for networks configured using ContrailSDN available from Juniper Networks, Inc. of Sunnyvale, California, overlay flow data 206 may correspond to Contrail Flow data.

[0087] In the depicted example, agent module 226 configures virtual router module 224 to collect overlay flow data 206. However, in other examples, hypervisor 221 may configure virtual router module 224 to collect overlay flow data 206. Further, in other examples, overlay flow data 206 may be collected by another module (alternatively or additionally), such as agent module 226, or even by hypervisor 221 or kernel module 222. Thus, in some examples, host device 210 may collect both underlying flow data (sFlow data) and overlay flow data (e.g., Contrail Flow data).

[0088] The network analysis system 240 can receive both the underlying flow data 204 and the overlay flow data 206. For example, continuing with the example and referring to Figure 2 , backbone device 202A samples, detects, senses and / or collects underlying flow data 204. Backbone device 202A outputs a signal through network 205. Communication unit 215 of network analysis system 240 detects the signal from backbone device 202A and outputs information about the signal to collector module 252. Collector module 252 determines that the signal includes information about underlying flow data 204.

[0089] Similarly, in some example methods, the virtual router module 224 of the host device 210A samples, detects, senses, and / or collects the overlay flow data 206 at the host device 210A. The virtual router module 224 causes the communication unit 215 of the host device 210A to output a signal through the network 205. The communication unit 215 of the network analysis system 240 detects the signal from the host device 210A and outputs information about the signal to the collector module 252. The collector module 252 determines that the signal includes information about the overlay flow data 206.

[0090] The network analysis system 240 can process both the underlying flow data 204 and the overlay flow data 206 received from various devices within the network system 200. For example, continuing with the same example, the collector module 252 processes signals received from the backbone device 202A, the host device 210A, and other devices by distributing the signals across multiple collector modules 252. In some examples, each collector module 252 can be executed on a different physical server and can be independently and horizontally scaled to handle the expected capacity or peak capacity of the flow traffic from the backbone device 202, the leaf device 203, and the host device 210. Each collector module 252 stores each instance of the underlying flow data 204 and the overlay flow data 206, and makes the stored data available for ingestion in the data repository 259. In some example methods, the collector module 252 indexes the data and prepares the data for use by analytical queries.

[0091] Network analysis system 240 can store underlying flow data 204 and overlay flow data 206 in data repository 259. For example, Figure 2 , the collector module 252 outputs the information to the data repository 259. The data repository 259 determines that the information corresponds to the underlying stream data 204 and the overlay stream data 206. The data repository 259 stores the data in an indexed format, thereby enabling fast aggregate queries and fast random access data retrieval. In some examples, the data repository 145 can achieve fault tolerance and high availability by sharding and replicating data across multiple storage devices, which can be located between multiple physical hosts.

[0092] The network analysis system 240 can receive the query. For example, still continuing the same example and referring to Figure 2 , the user interface device 129 detects the input and outputs a signal derived from the input over the network 205. The communication unit 215 of the network analysis system 240 detects the signal and outputs information about the signal to the flow API 256. The flow API 256 determines that the signal corresponds to a query for information about the network system 200 from a user of the user interface device 129 within a given time window. For example, a user of the user interface device 129 (e.g., the administrator 128) may have noticed that a particular virtual machine within a particular virtual network appears to be dropping packets at an abnormal rate and may seek to resolve the problem. One way to resolve the problem is to identify which network devices (e.g., which underlying routers) are on the data path that appears to be dropping packets. Therefore, the administrator 128 may seek to identify possible paths taken between the source virtual machine and the destination virtual machine by querying the network analysis system 240.

[0093] The network analysis system 240 can process the query. For example, continue again at Figure 2In the example described in the context of , the stream API 256 determines that the signal received from the user interface device 129 includes information about the source virtual network and / or the destination virtual network. The stream API 256 queries the data repository 259 by enriching the underlying stream data stored in the data repository 259 from the time window identified in the query to include virtual network data from the overlay stream data. To perform the query, the stream API 256 narrows the data to the specified time window, and for each relevant underlying stream data 204 record, the stream API 256 adds any source virtual network and / or destination virtual network information from the overlay stream data 206 record that has a value that matches the value of the corresponding underlying stream data 204 record. The stream API 256 identifies one or more network devices identified by the enriched underlying stream data. The stream API 256 determines one or more possible paths taken between the specified source virtual network and the destination virtual network based on the identified network devices. In some examples, global join techniques (e.g., available in the ClickHouse database management system) can be used for enrichment. In this example, the stream API 256 collects the coverage stream data and broadcasts this data to all nodes. The data is then used as a lookup table independently for each node. To minimize the size of the table, the stream API 256 can perform predicate pushdown of the filter criteria to the subquery.

[0094] The network analysis system 240 may generate and display a user interface 400 illustrating possible paths 402 between the source virtual network and the destination virtual network to be presented at the user interface device 129. The flow API 256 outputs information about the determined possible paths to the user interface module 254. The user interface module 254 uses the information from the flow API 256 to generate data sufficient to create a user interface that presents information about possible paths between the source virtual network and the destination virtual network. The user interface module 254 causes the communication unit 215 to output a signal through the network 205. The user interface device 129 detects the signal through the network 205 and determines that the signal includes information sufficient to generate a user interface. The user interface device 129 generates a user interface (e.g., user interface 400) and presents it at a display associated with the user interface device 129. In some examples, the user interface 400 presents information illustrating one or more possible paths 402 between the virtual machines 228, and may include information about how much data is or has been transferred between these virtual machines 228.

[0095] Figure 2The modules shown (e.g., virtual router module 224, proxy module 226, collector module 252, user interface module 254, flow API 256) and / or the modules illustrated or described elsewhere in this disclosure can perform operations described using software, hardware, firmware, or a mixture of hardware, software, and firmware that resides in and / or executes at one or more computing devices. For example, a computing device can execute one or more such modules with multiple processors or multiple devices. A computing device can execute one or more such modules as a virtual machine executed on basic hardware. One or more such modules can be executed as one or more services of an operating system or computing platform. One or more such modules can be executed as one or more executable programs at the application layer of a computing platform. In other examples, the functionality provided by the modules can be implemented by dedicated hardware devices.

[0096] Although can be illustrated respectively the specific module, data repository, component, program, executable file, data item, functional unit and / or other item that is included in one or more storage devices, one or more of such items can be combined and operated as a single module, component, program, executable file, data item or functional unit.For example, one or more modules or data repository can be combined or partially combined so that they operate as a single module or provide functionality.Further, one or more modules can interact and / or cooperate with each other so that, for example, a module serves as a service or extension of another module.And, each module, data repository, component, program, executable file, data item, functional unit or other item illustrated in the storage device can include multiple components, subcomponents, modules, submodules, data repository and / or other components or modules or data repository that are not illustrated.

[0097] Further, each module, data repository, component, program, executable file, data item, functional unit, or other item illustrated in the storage device may be implemented in various ways. For example, each module, data repository, component, program, executable file, data item, functional unit, or other item illustrated in the storage device may be implemented as a downloadable or pre-installed application or "app". In other examples, each module, data repository, component, program, executable file, data item, functional unit, or other item illustrated in the storage device may be implemented as part of an operating system executed on a computing device.

[0098] As mentioned above, administrators need tools that allow them to identify underlying network devices associated with traffic flowing on a virtual network and / or between two virtual machines. However, tools such as sFlow that sample underlying data flows fail to provide information sufficient to bind the sampled underlying data flows to a specific overlay network. For example, although the outer header in an sFlow sample can identify a virtual network in a virtual network, it does not indicate whether the identified virtual network is a source virtual network or a destination virtual network. Therefore, the network analysis system 240 is unable to identify segments of the path between the network device and the host. Next, techniques for identifying overlay networks associated with underlying data flows will be discussed. The first method adds information to the overlay flow data that identifies the source virtual network and destination virtual network for each overlay data flow. The second method uses encapsulation attributes to identify virtual networks between a host and a network device.

[0099] As mentioned above, a method for identifying an overlay network associated with an underlying data flow adds information to overlay flow data that identifies the source virtual network and the destination virtual network for each overlay data flow. In an example method, the virtual router adds a VXLAN network ID (VNI) identifying the source virtual network and the VNI identifying the destination virtual network to the overlay flow data. The overlay flow data is then correlated with the underlying flow data to identify the source virtual network and the destination virtual network for each underlying data flow. The combination of the underflow flow data and the source overlay network information and the destination overlay network information can then be used to determine a complete path through the underlying network from the source overlay network to the destination overlay network. In an example method, the network analysis system 240 adds the identity of the source virtual network and the destination virtual network to each sFlow data sample to form an enriched underlying data flow sample before storing the enriched underlying data flow sample in a database.

[0100] Figure 3 is a conceptual diagram illustrating example queries performed on stored underlay flow data and overlay flow data according to one or more aspects of the present disclosure. Figure 3 The diagram shows a data table 301, a query 302, and an output table 303. The data table 301 shows a table that can be stored in Figure 2 Query 302 represents a query that can be generated by stream API 256 in response to a request received by network analysis system 240 from user interface device 129. Output table 303 represents data generated from data table 301 in response to executing query 302.

[0101] As mentioned above, packets received by the virtual router module 224 from the underlying physical network fabric may include an outer header that is used to allow the physical network fabric to tunnel a payload or "inner packet" to a physical network address for a physical interface of the host device 210 hosting the virtual router module 224. The inner packet includes an inner header with a destination network address that conforms to the virtual network addressing space for the virtual network identified by the virtual network identifier. In one example approach, the flow collector 142 is capable of parsing both the inner header and the outer header from sFlow packets and other data flow packets.

[0102] exist Figure 3 In the example shown, data table 301 displays only a subset of the information received from sFlow packets and other data flow packets. For example, for each sFlow, Figure 2 The data store 259 may include the underlying source IP address and destination IP address, the underlying source port and destination port, and the source VXLAN network ID (VNI) or destination VXLAN network ID (VNI) (if any), which are not shown in the data table 301.

[0103] exist Figure 3 In the example, and according to one or more aspects of the present disclosure, Figure 2 The network analysis system 240 can populate the data table 301. For example, referring to Figure 2 and Figure 3 In both, the network analysis system 240 collects both the underlying flow data 204 and the overlay flow data 206 from various devices within the network system 200. The collector module 252 of the network analysis system 240 stores the collected data in a memory such as the storage device 250, the data repository 259, or a cache. Figure 3 In the example of , the data stored in the memory corresponds to the data table 301 .

[0104] In one example method, the flow API 256 selects rows that identify network devices from the data table 301, such as row 1, row 3, and row 5. The flow API 256 then attempts to find an overlay flow data record that matches the underlying flow data. In one example method, the flow API 256 of the network analysis system 240 determines whether any of the overlay flow data rows (e.g., row 2, row 4, row 6, and row 7) have the same five-tuple data (i.e., overlay source and destination addresses and port numbers and protocols) as rows 1, 3, and 5. For example, the flow API 256 determines that the overlay data from row 6 has five-tuple data that matches the five-tuple data of row 3. Therefore, the flow API 256 determines that the source virtual network of device "a7" is the source virtual network "e" (see the "src vn" column of row 1 of the output table 303). Similarly, flow API 256 can determine that the overlay data from row 4 of data table 301 has five-tuple data that matches the five-tuple data of row 5 of data table 301. Therefore, flow API 256 can determine that the source virtual network for device "a8" is source virtual network "c" (see row 2 of output table 303).

[0105] In one example approach, the stream API 256 selects rows from the data table 301 that have timestamps within a certain range and matches the underlying data rows with overlay data streams that fall within the same time frame (such as greater than or equal to 7 and less than or equal to 9). Figure 3 In the example illustrated in , flow API 256 identifies two network devices that meet the criteria: network device "a7" (from row 3 of data table 301) and network device "a8" (from row 5 of data table 301).

[0106] In the event that more than one instance (row) of overlay flow data is available, any or all of this data may be used to identify the source virtual network. This assumes that the virtual network configuration does not change frequently. Figure 3 In the example shown, for example, the flow API 256 determines that the source virtual network for device "a8" can be the source virtual network "c" (see row 4 of data table 301) or the source virtual network "g" (see row 7 of data table 301). Then, the flow API 256 can select the source virtual network "c" or "g" as the source virtual network.

[0107] In some examples, the outer header in the sFlow sample may include not only the physical network address of the network interface of the host device 210, but also a virtual network identifier that identifies one of the virtual networks, such as a VxLAN tag or a multi-protocol label switching (MPLS) label. In one such example method, the network analysis system 240 uses the overlay flow information generated by the vRouter agent 229 and the underlying flow information received via sFlow to find the path of the flow between any one virtual machine 228 and another virtual machine 228.

[0108] In one example approach, the vRouter agent 229 in each host device 210 generates overlay flow data associated with flows generated by and / or received by the VMs 228 in the corresponding host device. In one such example approach, the vRouter agent 229 operates as a compute node within the corresponding host device 210. The VMs 228 in each host device 210 are started on the compute node; therefore, any overlay traffic generated by the VMs 228 hosted on the host device 210 passes through the compute node. Therefore, the vRouter agent 229 has knowledge about the traffic and can identify the virtual network associated with each overlay flow. Therefore, the vRouter agent 229 sends the overlay flow data (including information identifying the virtual network) to the flow collector 124. In some example approaches, such as Figure 3 As shown, the overlay flow data includes information identifying a source virtual network and a destination virtual network for each overlay data flow. In one such example method, the overlay flow data identifies the source virtual network and the destination virtual network using a source VNI and a destination VNI, respectively.

[0109] The source VN information and the destination VN information associated with each underlying data stream can be used to associate the source VN and the destination VN with the new underlying data stream. In one example, five overlay tuples (that is, overlay source IP, destination IP, source port, destination port and protocol) are used as keys, and overlay source VN and destination VN are used as values. This key-value mapping is stored in a cache (such as a Redis cache). Then, when stream API 256 receives a new underlying data stream, the five overlay tuples in the header can be used to identify the source virtual network and the destination virtual network. In a kind of this example method, stream API 256 uses five overlay tuples as keys to access the cache, and obtains a source virtual network identifier and a destination virtual network identifier, which are then added to the underlying stream datagram of the new stream. In one example method, system 240 improves performance by using Redis cache and enriching the underlying flow data in memory before writing the enriched underlying process data to a database in data repository 259, rather than storing the flow data and VN information directly in a database in data repository 259 and then reading both from the database to enrich the flow data in the database.

[0110] As mentioned above, a second method for identifying source and destination virtual networks associated with an underlying data flow uses encapsulation attributes to identify virtual networks between a host and a network device. For example, an Ethernet VPN (EVPN) with Virtual Extensible Local Area Network (VXLAN) encapsulation can be used for layer 2 connectivity between a virtual machine and a TOR switch. In an example method, virtual networks for both source and destination VNs between a host and a network device can be identified by querying an appropriate EVPN database.

[0111] As in the first approach, the combination of the underflow flow data and the source overlay network information and the destination overlay network information can then be used to determine the complete path through the underlying network from the source overlay network to the destination overlay network. In one example approach, the network analysis system 240 adds the identity of the source virtual network and the destination virtual network to each sFlow data sample to form an enriched underlying data flow sample before storing the enriched underlying data flow sample in a database.

[0112] The enrichment process described herein can be used for queries that request the "top N" network attributes. Figure 4 and Figure 7 As illustrated in , this enrichment process can also be used to identify overlay flow paths through the underlying network.

[0113] Figure 4is a conceptual diagram illustrating an example user interface presented by a user interface device according to one or more aspects of the present disclosure. Figure 4 An example of a user interface 400 is illustrated. Although the user interface 400 is shown as a graphical user interface, other types of interfaces may be presented in other examples, including a text-based user interface, a console or command-based user interface, a voice prompt user interface, or any other suitable user interface. Figure 4 The illustrated user interface 400 may correspond to a user interface generated by the user interface module 254 of the network analysis system 240 and may be displayed on the Figure 2 The user interface 400 is presented at the user interface device 129. One or more aspects related to the generation and / or presentation of the user interface 400 may be presented at Figure 2 is described herein within the context of.

[0114] According to one or more aspects of the present disclosure, the network analysis system 240 can perform a query to identify a path. Figure 2 In the depicted example, the user interface device 129 detects the input and outputs the signal via the network 205. The communication unit 215 of the network analysis system 240 detects the signal that the stream API 256 determines corresponds to a query for network information. The stream API 256 executes the query (e.g., in conjunction with Figure 3 24) and outputs information about the results to the user interface module 254. To find a path between two virtual machines, the flow API 256 can determine the most likely path (and the traffic traveling through the determined path). In addition, the flow API 256 can perform additional queries to exclusively evaluate the overlay data flow to identify the traffic registered on the virtual router module 224, thereby enabling the traffic between the relevant virtual machines and the host device to be identified and displayed. The flow API 256 can use this technique to identify a host-virtual machine path or a virtual machine-host path.

[0115] Network analysis system 240 may generate a user interface for presentation at a display device, such as user interface 400. For example, still referring to Figure 2 and Figure 4 , the user interface module 254 generates information about the underlying user interface 400 and causes the communication unit 215 to output a signal through the network 205. The user interface device 129 detects the signal and determines that the signal includes information sufficient to present the user interface. Figure 4 The illustrated manner presents user interface 400 at a display device associated with user interface device 129 .

[0116] exist Figure 4In the example user interface 400 of FIG. 4 , the user interface 400 is presented within a display window 401. The user interface 400 includes a sidebar area 404, a main display area 406, and an options area 408. The sidebar area 404 provides an indication of which user interface mode is being presented within the user interface 400, and the options area 408 is displayed in the main display area 406. Figure 4 In the example of , this mode corresponds to the "fabric" mode. Other modes may be used for other network analysis scenarios as appropriate. Above the top of the main display area 406 is a navigation interface component 427, which can be used to select the type or mode of network analysis to be performed. Status notification display element 428 can provide information about alarms or other status information related to one or more networks, users, elements, or resources.

[0117] The main display area 406 presents a network diagram and may provide a topology of the various network devices included within the network being analyzed. Figure 4 In the example shown, the network is illustrated as having network devices, edge network devices, hosts, and instances, as indicated by the “legend” shown along the bottom of the main display area 406. Actual or potential data paths 402 between network devices and other components are illustrated within the main display area 406. Figure 4 A limited number of different types of network devices and components are shown in the user interface 400, but in other examples, other types of devices or components or elements may be presented and / or specifically illustrated, including core switch devices, spine devices, leaf devices, physical or virtual routers, virtual machines, containers, and / or other devices, components or elements. Further, some data paths or components (e.g., instances) of the network may be hidden or minimized within the user interface 400 to facilitate the illustration and / or presentation of the components or data paths that are most relevant to a given network analysis.

[0118] An options area 408 provides a plurality of input fields related to the underlay network being analyzed (e.g., an underlay five-tuple input field) and a plurality of input fields related to the overlay network being analyzed (e.g., source and destination virtual network and IP address input fields) along the right-hand side of the user interface 400. The user interface 400 accepts input via user interaction with one or more of the displayed input fields, and based on the data entered into the input fields, the user interface module 254 presents responsive information about the network being analyzed.

[0119] For example, in Figure 4In the example of , the user interface 400 accepts input in the options area 408 regarding: a particular time frame (e.g., a time range), source and destination virtual networks, and source and destination IP addresses. In the example shown, the underlying information has not yet been specified by user input. Using the input that has been provided in the options area 408, the network analysis system 240 determines information about one or more possible data paths (e.g., data paths or most likely data paths) that traverse the underlying network devices. The network analysis system 240 determines such possible data paths based on data collected by the network analysis system 240 (e.g., the collector module 252) during the time range specified in the options area 408. The user interface module 254 of the network analysis system 240 generates data that implements the presentation of the user interface 400, in which one possible data path 402 is highlighted (by drawing each segment of the data path with a thick line), such as Figure 4 In some examples, more than one data path 402 from a source virtual network to a destination virtual network may be highlighted. Further, in some examples, one or more data paths 402 in the main display area 406 may be presented using a heat map color scheme, meaning that the data paths are illustrated with a color (or gray shade) corresponding to the amount of data being transferred through the path or the degree to which the corresponding path is being used. Figure 4 The traffic level for the highlighted data path is illustrated using a grayscale shading scheme (as seen in the traffic level legend 429, from light gray shading for low-level traffic to dark gray shading for high traffic), but in other examples, a color scheme can be used to demonstrate changes in traffic level. In other examples, data about utilization or traffic on a data path or traversing a network device can be presented in other appropriate ways (e.g., applying color to other elements of the main display area 406, presenting a pop-up window, or presenting other user interface elements).

[0120] In some examples, the options region 408 (or other regions of the user interface 400) may include graphics 430 or other indicators that provide information about utilization or traffic on one or more paths. In such examples, these graphics may be related to or may be generated in response to user input entered into an input field within the options region 408.

[0121] Figure 5A and Figure 5B is a flow chart illustrating operations for enriching underlying stream data according to one or more aspects of the present disclosure. Figure 2 The network analysis system 240 is described in the context of Figure 5A and Figure 5B In other examples, Figure 5A and Figure 5B The operations described may be performed by one or more other components, modules, systems, or devices. Figure 5A and Figure 5B The operations described may be combined, performed in a different order, omitted, or may include additional operations not specifically illustrated or described.

[0122] Figure 5A A method for using overlay flow data to enrich underlying flow data with source virtual network information and destination virtual network information is illustrated. Figure 5A In the example illustrated in , and in accordance with one or more aspects of the present disclosure, the network analysis system 240 can collect underlying flow data (501) and overlay flow data (502). Figure 2 , each spine device 202 and each leaf device 203 outputs a corresponding signal (e.g., sFlow data) over network 205. Communication unit 215 of network analysis system 240 detects a signal that collector module 252 determines includes underlying flow data 204. Similarly, virtual router module 224 within each host device 210 outputs a signal over network 205. Communication unit 215 of network analysis system 240 detects an additional signal that collector module 252 determines includes overlay flow data 206. In some examples, collector module 252 can load balance the reception of signals across multiple collector modules 252 to ensure that a large number of signals can be processed without delay and / or without data loss.

[0123] In one example method, the network analysis system 240 can store the overlay flow data stream in the data repository 259 (505). The network analysis system 240 can determine the virtual network associated with the underlying flow data (503), and store the enriched underlying flow data (including the virtual network identity extracted from the stored overlay flow data) in the data repository 259 (504). For example, the collector module 252 can output information about the collected flow data (e.g., the underlying flow data 204 and the overlay flow data 206) to the data repository 259. The data repository 259 stores the flow data in an indexed format, and in some examples, stores the flow data in a structure that enables fast aggregation, querying, and / or fast random access data retrieval. In some example methods, the underlying flow data is stored in a cache until the underlying flow data is enriched.

[0124] Network analysis system 240 may receive a request for information about a data flow ("yes" path from 506). For example, user interface device 129 detects an input. In one such example, user interface device 129 outputs a signal over network 205. Communication unit 215 of network analysis system 240 detects a signal that flow API 256 determines corresponds to an information request from a user of user interface device 129. Alternatively, network analysis system 240 may continue to collect and store underlying flow data 204 and overlay flow data 206 until a request for information about a data flow is received ("no" path from 506).

[0125] The network analysis system 240 may perform a query (507) identifying information about a data flow. For example, when the network analysis system 240 receives a request for information, the flow API 256 parses the request and identifies information that can be used to perform the query. In some cases, the information may include source and destination virtual networks and / or associated time frames. In other examples, the information may include other information, such as underlying source or destination IP addresses or source or destination port numbers. The flow API 256 uses the information included in the request to query the data repository 259 for information about one or more related data flows. The data repository 259 processes the query and outputs the identities of one or more network devices used by the traffic between the source virtual network and the destination virtual network to the flow API 256. In some examples, the identities of the network devices may enable the flow API 256 to determine one or more possible data paths traversed by the traffic between the source virtual network and the destination virtual network.

[0126] To determine the identity of the network device used by the traffic between the source virtual network and the destination virtual network, in one example approach, the flow API 256 may query the data repository 259 for underlying flow data for network devices having the same five-tuple data (i.e., source and destination addresses and port numbers and protocols) as the virtual network or virtual IP address specified in the query. Network devices identified in the underlying flow data that match the five-tuple data are identified as possible network devices used by the traffic between the source virtual network and the destination virtual network. The network analysis system 240 may output information about the data flow (508). For example, again referring to Figure 2, the stream API 256 may output information about the data path 402 determined by the stream API 256 to the user interface module 254 in response to the query. The user interface module 254 generates information sufficient to present a user interface including information about the data flow. The user interface module 254 causes the communication unit 215 to output a signal over the network 205, the signal including information sufficient to present the user interface. In some examples, the user interface device 129 receives the signal, parses the information, and presents a user interface illustrating the information about the data flow.

[0127] In another example method, to determine the identity of a network device used by traffic between a source virtual network and a destination virtual network, the flow API 256 may query the data repository 259 for underlying flow data for network devices that have the same five-tuple data (i.e., source and destination addresses and port numbers and protocols) as the virtual network or virtual IP address specified in the query and have information identifying the virtual network as the virtual network or virtual IP address specified in the query. Network devices identified in the underlying flow data that match the five-tuple data and the virtual network are identified as possible network devices used by traffic between the source virtual network and the destination virtual network. The network analysis system 240 may output information about the data flow (508).

[0128] Figure 5B A method for enriching underlying flow data with source virtual network information and destination virtual network information using one or more EVPN databases is illustrated. Figure 5B In the example illustrated in , and in accordance with one or more aspects of the present disclosure, network analysis system 240 can collect underlying flow data (521). For example, in Figure 2 , each spine device 202 and each leaf device 203 outputs a corresponding signal (e.g., sFlow data) over network 205. Communication unit 215 of network analysis system 240 detects a signal that collector module 252 determines includes underlying flow data 204. Similarly, virtual router module 224 within each host device 210 outputs a signal over network 205. Communication unit 215 of network analysis system 240 detects an additional signal that collector module 252 determines includes overlay flow data 206. In some examples, collector module 252 can load balance the reception of signals across multiple collector modules 252 to ensure that a large number of signals can be processed without delay and / or without data loss.

[0129] In one example method, network analysis system 240 may query one or more EVPN databases to obtain the identities of the source virtual network and the destination virtual network (522). Network analysis system 240 may receive the identities of the source virtual network and the destination virtual network and enrich the underlying flow data with the identities of the virtual networks before storing the enriched underlying flow data in data repository 259 (524) (523). In one example method, data repository 259 stores the flow data in an indexed format and, in some examples, stores the flow data in a structure that enables fast aggregation, querying, and / or fast random access data retrieval. In some example methods, the underlying flow data is stored in a cache until the underlying flow data is enriched.

[0130] The network analysis system 240 may receive a request for information about the data flow (the "yes" path from 526). For example, the user interface device 129 detects an input. In one such example, the user interface device 129 outputs a signal over the network 205. The communication unit 215 of the network analysis system 240 detects the signal that the flow API 256 determines corresponds to an information request from a user of the user interface device 129. Alternatively, the network analysis system 240 may continue to collect and store the enriched underlying flow data until a request for information about the data flow is received (the "no" path from 526).

[0131] The network analysis system 240 may perform a query (527) identifying information about a data flow. For example, when the network analysis system 240 receives a request for information, the flow API 256 parses the request and identifies information that can be used to perform the query. In some cases, the information may include source and destination virtual networks and / or associated time frames. In other examples, the information may include other information, such as underlying source or destination IP addresses or source or destination port numbers. The flow API 256 uses the information included in the request to query the data repository 259 for information about one or more related underlying data flows. The data repository 259 processes the query and outputs the identities of one or more network devices used by the traffic between the source virtual network and the destination virtual network to the flow API 256. In some examples, the identities of the network devices may enable the flow API 256 to determine one or more possible data paths traversed by the traffic between the source virtual network and the destination virtual network.

[0132] To determine the identity of the network device used by the traffic between the source virtual network and the destination virtual network, in one example approach, the flow API 256 may query the data repository 259 for underlying flow data for network devices having the same five-tuple data (i.e., source and destination addresses and port numbers and protocols) as the virtual network or virtual IP address specified in the query. Network devices identified in the underlying flow data that match the five-tuple data are identified as possible network devices used by the traffic between the source virtual network and the destination virtual network. The network analysis system 240 may output information about the data flow (528). For example, again referring to Figure 2 , the stream API 256 may output information about the data path 402 determined by the stream API 256 to the user interface module 254 in response to the query. The user interface module 254 generates information sufficient to present a user interface including information about the data flow. The user interface module 254 causes the communication unit 215 to output a signal over the network 205, the signal including information sufficient to present the user interface. In some examples, the user interface device 129 receives the signal, parses the information, and presents a user interface illustrating the information about the data flow.

[0133] In another example method, to determine the identity of a network device used by traffic between a source virtual network and a destination virtual network, the flow API 256 may query the data repository 259 for underlying flow data for network devices that have the same five-tuple data (i.e., source and destination addresses and port numbers and protocols) as the virtual network or virtual IP address specified in the query and have information identifying the virtual network as the virtual network or virtual IP address specified in the query. Network devices identified in the underlying flow data that match the five-tuple data and the virtual network are identified as possible network devices used by traffic between the source virtual network and the destination virtual network. The network analysis system 240 may output information about the data flow (528).

[0134] As mentioned above, it may be helpful to determine the virtual network associated with a given underlying data flow. For example, it may be easier to associate an underlying data flow with an overlay data flow when each of the underlying data flow and the overlay data flow identifies the same virtual network. Therefore, in one example method, the network analysis system 240 uses network information received from other sources to select a path between the network device 110 and the host device 210. In one such method, the virtual router 229 stores the source virtual network identifier and the destination virtual network identifier as part of the overlay flow data. In another example method, in a system 200 that uses an Ethernet virtual private network (EVPN) and a virtual extensible local area network (VXLAN) for layer 2 connectivity between virtual machines and TOR switches, the network analysis system 240 retrieves information identifying a path between a host and a leaf network device 203 or a TOR switch from an EVPN database. The EVPN database method will be discussed in more detail below.

[0135] Figure 6 is a flow chart illustrating operations performed by an example network analysis system according to one or more aspects of the present disclosure. Figure 2 The network analysis system 240 is described in the context of Figure 6 In other examples, Figure 6 The operations described in the above may be performed by one or more other components, modules, systems, or devices. Figure 6 The operations described may be combined, performed in a different order, omitted, or may include additional operations not specifically illustrated or described.

[0136] exist Figure 6 , the network analysis system 240 retrieves records from the EVPN database. In one such example method, the user interface device 129 includes a command line interface (CLI) for querying the EVPN database via a CLI command such as "show evpn database" (602). The CLI command queries the EVPN database. In one example, the EVPN database returns the physical interface (the "yes" path from 604). For example, in one example method, the network analysis system 240 transmits the "show evpn database" CLI command and receives back the following information about the physical interfaces of the network device:

[0137]

[0138] Where interface ge-2 / 3 / 0.0 is a physical interface on a network device connected to host device 210, the IP address of host device 210 is 55.55.55.5, and its VxLAN network identifier (VNI) is 14. The VNI can then be mapped to a specific virtual network (606). The network analysis system 240 then stores the virtual network name with the underlying data flow information as underlying flow data (608).

[0139] When the "show evpn database" CLI command returns information on an interface other than a single physical interface ("no" path from 604), the system 240 may need to derive additional information. For example, in one example approach, the interface is a link aggregation group (LAG) interface. A LAG interface is a collection of physical ports that are used as a single interface. The "show evpn database" CLI command for a LAG interface may return the following information:

[0140]

[0141] Here, instead of the active source returning the name of the physical interface, the active source returns the Ethernet segment value of the LAG interface (610). In this example, network analysis system 240 receives the Ethernet segment value 00:92:ce:17:e8:56:c5:3c:f1:00 and determines that the Ethernet segment value belongs to interface ae0 (612).

[0142] Root#5c2-qfx1>display interface ae0

[0143] Physical interface: ae0, enabled, physical link is uplink

[0144] Interface index: 154, SNMP ifIndex: 557

[0145] Description: Virtual port group: 5clsl1-node2-EMS

[0146] Link Level Type: Ethernet, MTV: 9192, Speed: 10Gbps, BPDU Errors: None, Ethernet Switch Errors: None, MAC-REWRITE Errors: None, Loopback: Disabled, Source Filtering: Disabled

[0147] Flow Control: Disabled, Minimum Links Required: 1, Minimum Bandwidth Required: 1bps

[0148] Device Tags: Currently Running

[0149] Interface Label: Internal SNMP Trap: 0x4000

[0150] Current address: e4:fc:82:c2:0e:38, hardware address: e4:fc:82:c2:0e:38

[0151] Ethernet segment value: 00:92:ce:17:e8:56:c5:3c:f1:00, mode: all active

[0152] Last tap: 2020-05-01 16:04:20UTC (before 11:14:33)

[0153] Input rate: 0bps (0pps)

[0154] Output rate: 1008bps (0pps)

[0155] Logical interface ae0.0 (index 558) (SNMP ifIndex 558)

[0156] Tag: Uplink SNMP-Traps 0x24024000 Encapsulation: Ethernet-Bridge

[0157] Statistics packet pps bytes bps

[0158] Bundle:

[0159] Input: 4 0 660 0

[0160] Output: 74380 0 8778306 1016

[0161] Adaptive Statistics:

[0162] Adaptive adjustment: 0

[0163] Adaptive Scan: 0

[0164] Adaptive adjustment: 0

[0165] Protocol eth-switch, MTU: 9192

[0166] Tags: Is-Primary,Trunk-Mode

[0167] Here, the network device is connected on LAG interface ae0 and has IP address 55.55.55.100 on VNI 14. Network analysis system 240 can then query an orchestration model, such as a Contrail ConfigObject, to obtain the corresponding virtual network name (614). In one example approach, such a query returns the following information:

[0168]

[0169] In this example, the VNI of 14 is mapped to a virtual network named "blue-vn", which shows one way to map information retrieved from the EVPN database to a virtual network name even when the interface is not a single physical interface. The network analysis system 240 then stores the virtual network name with the underlying data flow information as underlying flow data (608).

[0170] Figure 7 is a conceptual diagram illustrating an example user interface presented by a user interface device to display an underlying data path corresponding to an overlay data service according to one or more aspects of the present disclosure. Figure 7 In the example shown, user interface 400 demonstrates the EVPN database example described above. Figure 7 4, the user interface 400 is presented in a display window 451. The user interface 400 includes a sidebar area 454, a main display area 456, and an options area 458. The sidebar area 454 provides an indication of which user interface mode is being presented in the user interface 400, and the options area 458 is displayed in the main display area 456. Figure 7 In the example, this mode corresponds to the "Structure" mode. Figure 7 Other modes are shown in , and may be used for other network analysis scenarios as appropriate. Above the top of the main display area 456 is a navigation interface component 477, which may also be used to select the type or mode of network analysis to be performed. Status notification display element 478 may provide information about the user, or may provide other status information related to one or more networks, users, elements, or resources.

[0171] The main display area 456 presents a network diagram and may provide a topology of the various network devices included within the network being analyzed. Figure 7 In the example shown, the network is illustrated as having network devices, edge network devices, hosts, and instances, as indicated by the “Legend” shown along the bottom of the main display area 456. Figure 7 In the example shown, the network devices, edge network devices, hosts, and instances shown in the main display area 456 correspond to Figure 2 The backbone device 202, leaf device 203, host device 210 and virtual machine 228 of the system 200.

[0172] Actual or potential data paths 480 between network devices and other components are illustrated in the main display area 456. Figure 7A limited number of different types of network devices and components are illustrated in the user interface 400, but in other examples, other types of devices or components or elements may be presented and / or specifically illustrated, including core switch devices, spine devices, leaf devices, physical or virtual routers, virtual machines, containers, and / or other devices, components, or elements. Further, some data paths or components (e.g., instances) of the network may be hidden or minimized within the user interface 400 to facilitate the illustration and / or presentation of the components or data paths that are most relevant to a given network analysis.

[0173] exist Figure 7 , options area 458 provides a plurality of input fields related to the underlay network being analyzed (e.g., an underlay five-tuple input field) and a plurality of input fields related to the overlay network being analyzed (e.g., source and destination virtual network fields, source and destination IP address fields, source and destination port fields, and a protocol field) along the right-hand side of user interface 400. User interface 400 accepts input via user interaction with one or more of the displayed fields, and based on the data entered into the input fields, user interface module 254 presents responsive information about the network being analyzed.

[0174] For example, in Figure 7 In the example of FIG. 4 , the user interface 400 accepts input parameters in the options area 458. Figure 7 In the example shown, the input parameters include information about a particular time frame (e.g., a time range, entered in time range input 460), source and destination underlying IP addresses 462, source and destination virtual networks in overlay virtual network input 464, and overlay source and destination IP addresses 466. Figure 7 In the illustrated example, the underlying information has not been specified by user input. Instead, overlay information in the form of source and destination virtual network fields and source and destination IP address fields is provided to guide the search for the data path. The network analysis system 240 uses the provided input to determine information about one or more possible data paths 480 (e.g., a data path or the most likely one or more data paths) that traverse the underlying network devices. In the illustrated example, the network analysis system 240 determines such possible data paths based on data collected by the network analysis system 240 (e.g., the collector module 252) during the time range 460 specified in the options area 458. The user interface module 254 of the network analysis system 240 generates data that implements the presentation of the user interface 400, in which one possible data path is highlighted (by drawing each segment of the data path with a thick line), such as Figure 7 In some examples, more than one data path 480 from a source virtual network to a destination virtual network may be highlighted.

[0175] In some examples, one or more data paths 480 in the main display area 456 may be presented using a heat map color scheme, meaning that the data paths are illustrated with a color (or shade of gray) corresponding to the amount of data being communicated through the path or the degree to which the corresponding path is being used. As mentioned above, although Figure 7 The traffic level for the highlighted data path 480 is illustrated using a grayscale shading scheme (as seen in the traffic level legend 479, from light gray shading for low-level traffic to dark gray shading for high traffic), but in other examples, a color scheme may be used to demonstrate changes in traffic level. In other examples, data about utilization or traffic on a data path or across a network device may be presented in other appropriate ways (e.g., applying color to other elements of the main display area 456, presenting a pop-up window, or presenting other user interface elements).

[0176] In one example method, the network analysis system 240 can be used to select other parameters, such as time frame, bottom layer or overlay parameters, and draw the path between two nodes on the topology based on the selected parameters. For example, the historical path can be visualized by selecting a time range via the date and time input box in the time range input 460.

[0177] In some examples, options region 458 (or other regions of user interface 400) may include graphics (not shown) or other indicators that provide information about utilization or traffic on one or more paths. In such examples, these graphics may be related to or may be generated in response to user input entered into an input field within options region 458.

[0178] For the processes, devices and other examples or diagrams described herein, including in any flow chart, the specific operations, actions, steps or events included in any technology described herein can be performed in different orders, can be added, merged or completely ignored (for example, not all described actions or events are necessary for practicing these technologies). In addition, in specific examples, operations, actions, steps or events can be performed simultaneously rather than sequentially, for example, by means of multithreading, interrupt processing or multiple processors. Even if not specifically identified as automatically executed, other specific operations, actions, steps or events can also be automatically executed. Moreover, the specific operations, actions, steps or events described as automatically executed can alternatively not be automatically executed, but in some examples, such operations, actions, steps or events can be performed in response to input or another event.

[0179] For ease of explanation, only a limited number of devices (e.g., user interface device 129, backbone device 202, leaf device 203, host device 210, network analysis system 240, and other devices) are shown in the drawings and / or other illustrations referenced herein. However, more such systems, components, devices, modules, and / or other items may be used to perform techniques according to one or more aspects of the present disclosure, and collective references to such systems, components, devices, modules, and / or other items may represent any number of such systems, components, devices, modules, and / or other items.

[0180] The drawings included herein each illustrate at least one example implementation of aspects of the present disclosure. However, the scope of the present disclosure is not limited to such implementations. Therefore, other examples or alternative implementations of the systems, methods, or techniques described herein that exceed the systems, methods, or techniques illustrated in the drawings may be appropriate in other instances. Such implementations may include a subset of the devices and / or components included in the drawings and / or may include additional devices and / or components not shown in the drawings.

[0181] The detailed description set forth above is intended to be a description of various configurations and is not intended to represent the only configuration in which the concepts described herein can be practiced. The detailed description includes specific details for the purpose of providing a full understanding of the various concepts. However, these concepts can be practiced without these specific details. In some instances, in order to avoid blurring such concepts, well-known structures and components are shown in block diagram form in the accompanying drawings.

[0182] Thus, although one or more implementations of various systems, devices, and / or components may be described with reference to specific figures, such systems, devices, and / or components may be implemented in a variety of different ways. For example, in the figures herein (e.g., FIG. 1 and / or Figure 2 ) may alternatively be implemented as a single device; one or more components illustrated as separate components may alternatively be implemented as a single component. Moreover, in some examples, one or more devices illustrated in the figures herein as a single device may alternatively be implemented as multiple devices; one or more components illustrated as a single component may alternatively be implemented as multiple components. Each of such multiple devices and / or components may be directly coupled via wired or wireless communications and / or remotely coupled via one or more networks. Moreover, one or more devices or components that may be illustrated in various figures herein may alternatively be implemented as part of another device or component not shown in such figures. In this and other ways, some functions described herein may be performed via distributed processing of two or more devices or components.

[0183] Further, specific operations, techniques, features and / or functions may be described herein as being performed by specific components, devices and / or modules. In other examples, such operations, techniques, features and / or functions may be performed by different components, devices or modules. Therefore, some operations, techniques, features and / or functions that may be described herein as being attributed to one or more components, devices or modules may be attributed to other components, devices and / or modules in other examples, even if not specifically described in this manner herein.

[0184] Although specific advantages have been identified with respect to the description of some examples, various other examples may include some of the listed advantages, none of the listed advantages, or all of the listed advantages. From this disclosure, other advantages, technical or otherwise, may become apparent to one of ordinary skill in the art. Further, although specific examples have been disclosed herein, various aspects of the disclosure may be implemented using any number of technologies, whether currently known or not, and therefore, the disclosure is not limited to the examples specifically described and / or illustrated in this disclosure.

[0185] In one or more examples, the described functions can be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions can be stored on a computer-readable medium and / or transmitted via a computer-readable medium and executed by a hardware-based processing unit as one or more instructions or codes. A computer-readable medium may include a computer-readable storage medium corresponding to a tangible medium such as a data storage medium, or a communication medium including any medium that facilitates transferring a computer program from one place to another (e.g., according to a communication protocol). In this way, a computer-readable medium may generally correspond to (1) a non-transient tangible computer-readable storage medium or (2) a communication medium such as a signal or carrier wave. A data storage medium may be any available medium that can be accessed by one or more computers or one or more processors to retrieve instructions, codes, and / or data structures to implement the technology described in this disclosure. A computer program product may include a computer-readable medium.

[0186] By way of example and not limitation, such computer-readable storage media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage devices, disk storage devices or other magnetic storage devices, flash memory, or any other medium that can be used to store the desired program code in the form of an instruction or data structure and that can be accessed by a computer. Moreover, any connection is appropriately referred to as a computer-readable medium. For example, if an instruction is transmitted from a website, a server or other remote source using a coaxial cable, an optical fiber cable, a twisted pair, a digital subscriber line (DSL), or a wireless technology (such as infrared, radio, and microwave), then the coaxial cable, optical fiber cable, twisted pair, DSL, or a wireless technology (such as infrared, radio, and microwave) is included in the definition of the medium. However, it should be understood that computer-readable storage media and data storage media do not include connection, carrier wave, signal, or other transient media, but are dedicated to non-transient tangible storage media. Disks and optical disks such as those used include compact discs (CDs), laser optical disks, optical optical disks, digital versatile optical disks (DVDs), floppy disks, and blue-ray optical disks, wherein disks usually copy data magnetically, and optical disks copy data optically with lasers. The combination of the foregoing should also be included in the scope of computer-readable media.

[0187] Instructions may be executed by one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Therefore, the terms "processor" or "processing circuitry" as used herein may refer to any of the aforementioned structures or any other structure suitable for the implementation of the described techniques, respectively. In addition, in some examples, the described functionality may be provided within dedicated hardware and / or software modules. Moreover, these techniques may be fully implemented in one or more circuits or logic elements.

[0188] The techniques of the present disclosure may be implemented in a variety of devices or apparatuses, including wireless handsets, mobile or non-mobile computing devices, wearable or non-wearable computing devices, integrated circuits (ICs), or a set of ICs (e.g., chipsets). Various components, modules, or units are described in the present disclosure to emphasize functional aspects of devices configured to perform the disclosed techniques, but do not necessarily need to be implemented by different hardware units. Instead, as described above, the various units may be combined in a hardware unit or provided by a collection of interoperable hardware units (including one or more processors as described above, in combination with appropriate software and / or firmware).

Claims

1. A computer networking method, comprising: retrieving, from one or more Ethernet virtual private network (EVPN) databases, an overlay flow record for an overlay packet flow among a plurality of overlay packet flows for a plurality of overlay networks; identifying, based on the overlay flow record, an overlay network among the plurality of overlay networks associated with the overlay packet flow; correlating the overlay packet flow with an underlying packet flow among a plurality of underlying packet flows of an underlying network; as well as An underlying flow record is stored for the underlying packet flow, wherein the underlying network includes a plurality of network devices, wherein the underlying flow record includes, for the underlying packet flow, information identifying: an underlying network source device among the plurality of network devices, an underlying network destination device among the plurality of network devices, and an indication of the overlay network associated with the overlay packet flow.

2. The method of claim 1 , wherein based on the overlay flow record, identifying the overlay network comprises: identifying, from the overlay flow record, a physical interface associated with the overlay packet flow; determining a VxLAN network identifier (VNI) associated with the physical interface; and The overlay network is determined based on the VNI.

3. The method of claim 1 , wherein based on the overlay flow record, identifying the overlay network comprises: identifying, from the overlay flow record, an Ethernet segmentation value of a link aggregation group (LAG) interface associated with the overlay packet flow; determining a physical interface associated with the Ethernet segmentation value; determining a VxLAN network identifier (VNI) associated with the physical interface; and The overlay network is determined based on the VNI.

4. The method of claim 3, wherein determining the overlay network based on the VNI comprises: An orchestration model is queried using the VNI to identify the overlay network.

5. The method according to claim 1, further comprising: receiving a query specifying the overlay network; as well as Based on the underlay flow record, an indication of the underlay network source device or the underlay network destination device for the underlay packet flow associated with the overlay packet flow of the overlay network specified by the query is output for display.

6. The method of claim 1 , further comprising outputting the following items for display based on the underlying flow record: an indication of the underlying network source device; an indication of the underlying network destination device; and A representation of one or more data paths between the underlying network source device and the underlying network destination device through which packets of the underlying packet flow associated with the overlay packet flow are forwarded. The method of claim 6 , wherein the representation of the one or more data paths comprises a heat map of the one or more data paths.

8. The method of any one of claims 1 to 7, wherein correlating the overlay packet flow with the underlay packet flow comprises: It is determined that packets of the overlay packet flow and packets of the underlay packet flow are processed during a same time window.

9. The method of any one of claims 1 to 7, wherein correlating the overlay packet flow with the underlay packet flow comprises: The source address, source port, destination address, destination port, and protocol of the packets of the overlay packet flow are determined to match the source address, source port, destination address, destination port, and protocol of the packets of the underlying packet flow.

10. The method of any one of claims 1 to 7, wherein the overlay network associated with the overlay packet flow comprises a source overlay network for the overlay packet flow.

11. The method of any one of claims 1 to 7, wherein the overlay network associated with the overlay packet flow comprises a destination overlay network for the overlay packet flow.

12. A computing network system, comprising: a processing circuit having access to a storage device, the storage device comprising instructions to cause the processing circuit to: retrieving, from one or more Ethernet virtual private network (EVPN) databases, an overlay flow record for an overlay packet flow among a plurality of overlay packet flows for a plurality of overlay networks; identifying, based on the overlay flow record, an overlay network among the plurality of overlay networks associated with the overlay packet flow; correlating the overlay packet flow with an underlying packet flow among a plurality of underlying packet flows of an underlying network; as well as An underlying flow record is stored for the underlying packet flow, wherein the underlying network includes a plurality of network devices, wherein the underlying flow record includes, for the underlying packet flow, information identifying: an underlying network source device among the plurality of network devices, an underlying network destination device among the plurality of network devices, and an indication of the overlay network associated with the overlay packet flow.

13. The computing system of claim 12, wherein to identify the overlay network based on the overlay flow record, the processing circuit is configured to: identifying, from the overlay flow record, a physical interface associated with the overlay packet flow; determining a VxLAN network identifier (VNI) associated with the physical interface; and The overlay network is determined based on the VNI.

14. The computing system of claim 12, wherein to identify the overlay network based on the overlay flow record, the processing circuit is configured to: identifying, from the overlay flow record, an Ethernet segmentation value of a link aggregation group (LAG) interface associated with the overlay packet flow; determining a physical interface associated with the Ethernet segmentation value; determining a VxLAN network identifier (VNI) associated with the physical interface; and The overlay network is determined based on the VNI.

15. The computing system of claim 12, wherein the processing circuit is further configured to: receiving a query specifying the overlay network; and Based on the underlay flow record, an indication of the underlay network source device or the underlay network destination device for the underlay packet flow associated with the overlay packet flow of the overlay network specified by the query is output for display.

16. The computing system of claim 12, wherein the processing circuit is further configured to output the following items for display based on the underlying flow record: an indication of the underlying network source device; an indication of the underlying network destination device; and A representation of one or more data paths between the underlying network source device and the underlying network destination device through which packets of the underlying packet flow associated with the overlay packet flow are forwarded.

17. The computing system of any one of claims 12 to 16, wherein in order to correlate the overlay packet flow with the underlying packet flow, the processing circuit is configured to: determine that packets of the overlay packet flow and packets of the underlying packet flow are processed during the same time window.

18. A computing system according to any one of claims 12 to 16, wherein in order to correlate the overlay packet flow with the underlying packet flow, the processing circuit is configured to: determine the source address, source port, destination address, destination port and protocol of the packets of the overlay packet flow to match the source address, source port, destination address, destination port and protocol of the packets of the underlying packet flow.

19. The computing system of any one of claims 12 to 16, wherein the overlay network associated with the overlay packet flow comprises one of: a source overlay network for the overlay packet flow or a destination overlay network for the overlay packet flow.

20. A computer readable storage medium encoded with instructions for causing one or more programmable processors to perform the method of any one of claims 1 to 11.