Cisco Technology, Inc.

Pensando Systems Inc.

Nvidia Corporation

Swaminathan Narayanan

Venkatesh Srinivasan

Ambrish Niranjan Mehta

Anand Kumar Singh

Natarajan Manthiramoorthy

Anulekha Chodey

Nataraj Bacthu

Ankan Ghosh

Apurup Reddy Chevuru

Laxmi Kant Agrawal

Varagur Chandrasekaran

Raghava Kodigenahalli Sivaramu

Ayan Banerjee

Vipin Jain

Mehak Mahajan

Nicholas Haemel

Shiv Saini

Ambrish Mehta

The present disclosure involves systems and methods for managing a trie routing table for a networking device of a communication or computer network. In one implementation, the networking device may utilize a dynamic algorithm for associating hashing functions with pivot tiles of the routing table to improve hash utilization and avoid hash collisions. Further, route prefixes may be relocated from pivot tiles in an attempt to free the tiles for reallocation to other prefix base width or may be relocated to other possible pivot tiles or to a general storage space when a hash collision is detected. This provides for even distribution of pivots within tiles which have base widths in range of a pivot route. The above implementations may occur together or separately to improve the operation of the networking device and provide faster route lookup.

Dynamic route profile storage in a hardware trie routing table

A network appliance having a control plane and a data plane can process substantially every input packet at wire speed in a programmable packet processing pipeline of the data plane. Sensors, which can be processes implemented within the pipeline, can measure parameters of the network traffic flows and of the network appliance in accordance with monitoring policies. Reporting policies can be triggered when any one of many criteria are met by the parameters. The reporting policy can result in a report being sent to an outside recipient. Alternatively, the reporting policy can result in the network appliance implementing additional monitoring or reporting policies.

Methods and systems for smart sensor implementation within a network appliance data plane

Methods and systems for exporting network information from an exporter to a collector are disclosed. Embodiments of the present technology may include updating a non-key field of a flow entry in a flow cache that corresponds to a flow, setting a field in a context-bitmap of the flow entry in response to updating the non-key field of the flow entry, identifying an export policy using the context-bitmap, and exporting information related to the flow to a collector according to the export policy.

Intelligent export of network information

Aspects of the present disclosure are directed to dynamically adjusting control plane policing throughput of low (or lower) priority control plane traffic to permit higher throughput. The drop rate for low or lower priority control plane traffic can be determined to be above a threshold value. The processor utilization can be determined to be operating under normal utilization (or at a utilization within a threshold utilization value). The control plane policing for control plane traffic for the low or lower class of service can be increased (or decreased) to permit lower class of service control traffic to be transmitted using higher class of service resources without adjusting the priority levels for the lower class of service control traffic.

Adapting control plane policing parameters dynamically

Systems, methods, and non-transitory computer-readable storage media for detecting network loops. In some embodiments, a system can identify a network path having multiple hops associated with respective nodes which are configured in a forwarding mode. The system can traverse the network path to identify, for each node from the respective nodes, a respective next hop. Based on the respective next hop for each node, the system can determine whether two or more nodes from the respective nodes have a same respective next hop. When the two or more nodes have the same respective next hop, the system can determine that the network path has a network loop.

Detecting and preventing network loops

Systems, methods, and non-transitory computer-readable storage media for detecting network loops. In some embodiments, a system can identify a port that is in a blocking state. The blocking state can be for dropping one or more types of packets and preventing the port from forwarding the one or more types of packets. The system can determine a number of packets transmitted through the port by a hardware layer on the system and a number of control packets transmitted through the port by a software layer on the system. The system can determine whether the number of packets is greater than the number of control packets. When the number of packets is greater than the number of control packets, the system can determine that the blocking state has failed to prevent the port from forwarding the one or more types of packets.

Systems, methods, and computer-readable storage media for detecting network loops. A system can identify, for each virtual tunnel endpoint (VTEP) from multiple VTEPs in a network, respective media access control address data including the respective local interface media access control addresses of the respective VTEP and respective media access control addresses learned by the respective VTEP. The system can determine whether the VTEPs are running spanning tree protocol (STP), and whether a media access control address learned by a first VTEP matches a respective local interface media access control address of a second VTEP. The system can detect a loop when the media access control address learned by the first VTEP matches the respective local interface media access control address of the second VTEP. The system can also detect a loop when the VTEPs are running STP and the first and second VTEPs see the same STP root bridge.

Systems, methods, and computer-readable media for preventing man-in-the-middle attacks within network, without the need to maintain trusted/un-trusted port listings on each network device. The solutions disclosed herein leverage a host database which can be present on controllers, thereby providing a centralized database instead of a per-node DHCP binding database. Systems configured according to this disclosure (1) use a flood list only for ARP packets received from the controller; and (2) unicast ARP packets to the controller before communicating the packets to other VTEPs.

Technologies for preventing man-in-the-middle attacks in software defined networks

In one embodiment an approach is provided to efficiently program routes on line cards and fabric modules in a modular router to avoid hot spots and thus avoid undesirable packet loss. Each fabric module includes two separate processors or application specific integrated circuits (ASICs). In another embodiment, each fabric module processor is replaced by a pair of fabric module processors arranged in series with each other, and each processor is responsible for routing only, e.g., IPv4 or IPv6 traffic. The pair of fabric module processors communicates with one another via a trunk line and any packet received at either one of the pair is passed to the other of the pair before being passed back to a line card.

Router table scaling in modular platforms

Mechanisms for switch upgrades using remote containers. An example system can export, to a server, a state of software processes associated with a first software container at the system. The system can generate a lightweight software container configured to forward traffic associated with the first software container to a second software container at the server, generated based on the state. The system can perform a switchover between the first software container and lightweight software container. The switchover can enable the lightweight software container to forward, to the second container, traffic associated with the first software container. The system can generate a fourth software container based on a snapshot of the second software container, and perform another switchover between the lightweight software container and fourth software container. The switchover can include enabling the fourth software container to handle traffic associated with the first software container, and disabling the lightweight software container.

Growing community of inventors

San Jose, CA, United States of America

Swaminathan Narayanan