Arista Networks, Inc.

Navdeep Bhatia

Simon Francis Capper

Michael Chih-Yen Wang

Sebastiano Borgione

Prasanna Parthasarathy

Hugh Weber Holbrook

Alton Lo

Hua Zhong

Peter Lam

Kalyan Chakravarthy Nidumolu

Ian McCloghrie

Hans Jonas Flodin

Victor Shih-Hua Wen

Michael Wang

A method for supporting virtual machine (VM) mobility between network devices connected to a network includes: selecting a first type of route for interconnecting VMs that are connected to the network devices; and adding a feature of a second type of route to the first type of route to enable the network devices to execute proxy address resolution protocol (ARP) for transmitting network traffic between the VMs without requiring each of the network devices to store a physical address of each of the VMs in respective ones of a network address table.

Host routing with virtual machine mobility

Operations include: identifying a first dataflow associated with a particular communications protocol; evaluating the first dataflow to determine that the first dataflow meets a hardware-based Network Address Translation (NAT) usage criteria; responsive to determining that the first dataflow meets the hardware-based NAT usage criteria, executing a set of hardware-based NAT operations to process a first set of packets corresponding to the first dataflow; identifying a second dataflow associated with the same particular communications protocol; evaluating the second dataflow to determine that the second dataflow does not meet the hardware-based NAT usage criteria; and responsive to determining that the second dataflow does not meet the hardware-based NAT usage criteria, executing a first set of software-based NAT operations to process a second set of packets corresponding to the second dataflow.

Dynamic implementation and tear-down of hardware network address translation pipelines for a dataflow

Systems, methods and products for associating arbitrary configuration tags to configuration item for a service so that items grouped by the tags can be unconfigured or manipulated as a group with minimal touchpoints. In one embodiment, a method is provided for managing the configuration of per-tenant features in a server system. The method includes identifying a configuration feature of the server system to be configured for a specific tenant. A configuration command is received to configure the configuration feature for the specific tenant, wherein the configuration command includes a configuration tag associated with the specific tenant. The configuration command is stored in a configuration of the server system and is applied to the server system. Tag-based commands are provided which are operable to modify a subset of configuration features corresponding to a designated configuration tag.

Associating tags to configuration items for tag-based configuration management

Systems and methods for increasing the speed with which a network device can process 'heartbeat' packets that are transmitted between the network device and its peers to verify that the communication links between them are active, or to detect when the communication links go down (i.e., are inactive). Received heartbeat packets are processed primarily by a switching application specific integrated circuit (ASIC) rather than a CPU of the network device. The switching ASIC identifies heartbeat sessions corresponding to received heartbeat packets and resets aging timers for these sessions if the timers have not already expired. The reduced processing and faster timing mechanism of the switching ASIC enables the network device to accommodate spikes in the received packet rate.

Systems and methods for processing heartbeat packets in switching hardware

A network device may include a packet processing pipeline. The packet processing pipeline may include a parser configured to parse packet information in a transit packet received at an input interface of the network device. The packet processing pipeline may include packet sampling information storage circuitry configured to store sampled packet information obtained based on the parsed packet information. The packet processing pipeline may include a processing engine configured to modify a payload of a sampling information accumulation packet to include the sampled packet information for the transit packet. The payload of the sampling information accumulation packet may include the sampled packet information for multiple transit packets.

Sampled packet information accumulation

Techniques for configuring shared routing tables for network devices are provided. In some embodiments, a shared routing context is configured to include common routes across several local routing contexts. When a first packet is received at a first local routing context that is to be routed using one of the common routes, NAT operations may be performed on the first packet and then the shared routing context is used to process the first packet. Similarly, when a second packet is received at a second local routing context that is to be routed using the same common route, NAT operations may be performed on the second packet and then the shared routing context is used to process the second packet.

Shared routing tables for network devices

Methods and systems are described for comparing values using an associative memory. An associative memory lookup is performed based on a key that comprises a first number, a second number, and a third number. The associative memory includes sets of mask rows that are configured such that the associative memory returns a result of true when the sum of the first number and the second number is equal to the third number. The result of the associative memory lookup is outputted. The associative memory configured in this manner may be used, for example, by a packet forwarding device to perform a zero-value boundary condition check or packet sequence check.

Boundary condition check using associative memory

A method and apparatus of a network element that processes data using a data processing pipeline with standby memory is described. In one embodiment, the network element prepares a new image for the data processing pipeline of the network element, where the data processing pipeline processes incoming network data received by the network element and the new image modifies a current set of functionalities of the data processing pipeline. The network element further writes the new image into a standby memory of the data processing pipeline, where the network element includes an active memory that programs the current set of functionalities of the data processing pipeline. In addition, the network element programs the data processing pipeline using the new image. The network element additionally processes the incoming network data received by using the data processing pipeline using modified current set of functionalities.

System and method of hitless reconfiguration of a data processing pipeline with standby pipeline

A method and apparatus of a network element that processes data by a network element with a data processing pipeline is described. In an exemplary embodiment, the network element prepares a new image for the data processing pipeline of the network element, where the data processing pipeline processes network data received by the network element and the new image modifies one or more functionalities of the data processing pipeline. In addition, the network element puts the data processing pipeline into a non-forwarding mode. Furthermore, the network element writes the new image into memory of the data processing pipeline. The network element additionally puts the data processing pipeline into a forwarding mode, where the data processing pipeline processes network data received by the network element using the new image.

System and method of hitless reconfiguration of a data processing pipeline

A method and apparatus of a network element that stores a lookup entry in a hardware table of a network element is described. In an exemplary embodiment, the network element receives a notification of a dirty lookup entry to be processed for a hardware table of a network element, where the hardware table includes a plurality of lookup entries. In addition, the network element determines a location for a table modification associated with the dirty lookup entry in the hardware table. Furthermore, the network element performs, with a hardware writer of the network element, the table modification associated with the lookup entry in a non-disruptive manner, where the hardware writer performs the table modification associated with the lookup entry in response to determining that the table modification associated with the lookup entry does not leave one of the plurality of lookup entries inconsistent after the table modification is performed.

System and method of coalescing writes to a hardware table in a non-disruptive fashion

Described herein are various embodiments of a network element to process routing entries in a forwarding information base (FIB) for hosts that are directly attached to a multi-layer network element to encode address resolution protocol (ARP) data into forwarding equivalence class (FEC) entries for the directly attached hosts. One embodiment provides for a network element comprising a control plane including a forwarding agent and a data plane coupled to the control plane. The data plane can include a forwarding engine to forward a unit of network data from an ingress interface to an egress interface. The forwarding agent can be configured to program the forwarding engine with a forwarding information base having data-link layer forwarding data encoded into a network-layer forwarding entry.

Growing community of inventors

Sunnyvale, CA, United States of America

Navdeep Bhatia