Arista Networks, Inc.

Simon Francis Capper

Navdeep Bhatia

Hugh Weber Holbrook

Tula Kraiser

Prashanth Krishnamurthy

Kenneth James Duda

Sebastian Sapa

Duncan Stuart Ritchie

Peter Lam

Sebastiano Borgione

Feng Zhu

Prasanna Parthasarathy

Kartik Chandran

Sriram Chidambaram

Di Wang

Michael Wang

Hemanth Murthy

A method and apparatus of a network element that manages a network interface controller on a device coupled to a network element is described. In an exemplary embodiment, the network element detects that the network interface controller is manageable, wherein the network interface controller is coupled to the network element by a link. In addition, the network element transmits a command packet to the network interface controller in-band, where the network interface controller determines a response to the command packet using the resources of the network interface controller and without communicating data between the network interface controller and the device. The network element receives the response from the network interface controller.

Remote in-band management of a network interface controller

Embodiments disclosed herein relate to method and systems for updating hardware tables. Such methods may include receiving a flexible pipeline definition from a controller at a compiler; generating, by the compiler, a hardware table update initial instruction set; and transmitting the hardware table update initial instruction set to a network device. The network device may use the hardware table initial instruction set to configure the network device to implement the flexible pipeline definition for a network chip.

Dynamic run time programming of hardware tables

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

In general, embodiments of the invention relate to processing network traffic data units (NTDUs). More specifically, embodiments of the invention relate to processing NTDUs transmitted between client device and the one or more protected resources. The protected resources are logically surrounded by a perimeter, which is implemented as a set of network devices that manage the flow of NTDUs between client devices and the protected resources. The perimeter works in conjunction with a set of filtering devices to determine whether a given NTDU can ultimately be transmitted to, and processed by, a protected resource.

System and method for protecting resources using network devices

Techniques for implementing history-based connection-server affinity on a network load balancer are provided. In one set of embodiments, the network load balancer can receive a network packet destined for a service, where the service is associated with a plurality of servers, and where the packet is part of a network connection between a client device and one of the plurality of servers. The network load balancer can further compute, using a portion of the packet, a bucket identifier of a bucket for the network connection, identify a first server in the plurality of servers that is currently mapped to the bucket identifier in a hash table, and send the packet to the first server. If the network load balancer receives the packet back from the first server, the network load balancer can determine, based on local history information, a second server that was previously mapped to the bucket identifier in the hash table and send the packet to that second server.

Implementing history-based connection-server affinity on a network load balancer

Techniques for implementing resilient hashing with multiple hashes are provided. In one set of embodiments, a network device can maintain a first hash table comprising mappings between a first set of hash indices and a set of bit values. The network device can also maintain a second hash table comprising mappings between a second set of hash indices and active next-hop destinations. Upon receiving a network packet, the network device can compute a first hash and can match the first hash value to a first mapping in the first hash table based on the first mapping's hash index. When the first mapping's bit value indicates that the first mapping's hash index corresponds to an active next-hop destination, the network device can further match the first hash value to a second mapping in the second hash table and send the network packet to the second mapping's active next-hop destination.

Resilient hashing with multiple hashes

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

Certain embodiments disclosed herein relate to method for egress maximum transmission unit (MTU) enforcement. The method may include receiving a protocol packet at an ingress interface of a network device; make a first determination of a protocol packet payload length; performing an ingress MTU identifier lookup in an ingress MTU identifier table using the protocol packet payload length to obtain an ingress MTU identifier; performing a packet propagation lookup to obtain an egress MTU identifier; performing an MTU enforcement lookup in an MTU enforcement table using the ingress MTU identifier and the egress MTU identifier to obtain an egress action; and performing the egress action.

Egress maximum transmission unit (MTU) enforcement

A method and apparatus of a device that updates a software image for a network element is described. In an exemplary embodiment, a device receives a signal to update the network element with the new software image, where the network element includes a plurality of hardware forwarding engines and a control plane. The device further boots the control plane with the new software image, where the booting is accomplished without restarting the control plane. In one embodiment, the device boots the control plane by chain booting from a current software image to the new software image. The device additionally restarts and reconfigures the plurality of hardware forwarding engines. In a further embodiment, the device additionally prefills one or more queues in the hardware forwarding engines with keep-alive messages. These keep-alive messages are transmitted during the time that the control plane is being restarted. In a further embodiment, the hardware forwarding engines are reconfigured without restarting them.

System and method for accelerated software upgrades

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

A method and apparatus of a network element that updates an interface list of a multi-link group of a network element is described. In an exemplary embodiment, a network element receives an indication that the interface list for the multi-link group on a network element is to change. In addition, the interface list includes a first set of interfaces. The network element further includes an address table having a plurality of address entries, where each of the plurality of address entries includes an address, a multi-link nexthop, and a tag group reference. The tag group reference references an entry in a tag group table, where a tag group entry includes a tag group identifier and a tag group set of interfaces. The network element further receives a second set of interfaces. The network element additionally updates the interface list for the tag group entry to include a second set of interfaces. Furthermore, the network element transmits data with the multi-link group using the second set of interfaces.

Updating interface list of multi-link group

A method and apparatus of a device that includes a shared memory hash table that notifies one or more readers of changes to the shared memory hash table is described. In an exemplary embodiment, a device modifies a value in the shared memory hash table, where the value has a corresponding key. The device further stores a notification in a notification queue that indicates the value has changed. In addition, the device invalidates a previous entry in the notification queue that indicates the value has been modified. The device signals to the reader that a notification is ready to be processed.

Growing community of inventors

San Jose, CA, United States of America

Simon Francis Capper