Arista Networks, Inc.

Andre Pech

Gagandeep Singh Arneja

Justin Costa-Roberts

Hua Zhong

Ethan Barnett Rahn

Arturo Escaip

Anshul Sadana

Chandrashekhar Appanna

Fred Hsu

Aaron Delaney

Roy Magruder

Aparna Sushrut Karanjkar

Thejesh Ajjikariappla Panchappa

Fred Lo-Tze Hsu

Ritesh Kumar Sinha

Karthik Subraveti

A cluster data replication system includes a plurality of network elements and controllers. The controllers form a cluster that is able to elect one of the controllers as a master controller with the others being follower controllers. The elected controller updates, responsive to being elected the master controller, state information in a system database of the elected controller to indicate that the elected one of the controllers is the master controller. The master controller includes one or more objects that are enabled in reaction to the state information, and which coordinate replication of changes to the data, system database, and state information from the master to the follower controllers. Each follower controller includes one or more objects able to, in reaction to the state information, disable initiation of the replication of changes to the data, system database and state information by the one or more objects in each follower controller.

Cluster data replication

In some implementations, a method is provided. The method includes determining a physical topology of a network and monitoring network events based, at least in part, on control plane information received from one or more devices in the network. The method also includes monitoring the performance of each of a plurality of applications running on the network based, at least in part, on a set of application calls initiated by each application. When a drop in performance of an application is detected, the drop in performance is correlated with one or more of a plurality of detected network events to determine a cause of the drop in performance.

Determining the impact of network events on network applications

A method for distributing network services for a network device through a multi-tenant network service. An identification parameter is associated with the device and is stored in a database by an orders management system after the device is ordered. The method includes establishing a network connection between a network device and a multi-tenant network service and, in response to establishing the network connection, obtaining device-associated identification parameter from the network device. The identification parameter is used to query the database for at least one record associated with the network device identifying a tenant of the multi-tenant network service in which the tenant corresponds to the device. The service maps the network device to the identified tenant of the multi-tenant network service and distributes network services based upon the mapping of the network device to the identified tenant.

Device provisioning in a multi-tenant service

Network devices are securely provisioned through authenticated ZTP servers. In some approaches, a storage device local to the network device includes information for connecting with and authenticating a local or remote ZTP server. This information may include a root of trust to use when connecting with a designated ZTP server. The ZTP server may be identified using either a dynamic host configuration protocol (DHCP) server or a network address specified in the local memory storage. In an approach, the local memory storage is a removable USB flash memory device inserted into the network device when the device is booted up. In another approach, the ZTP authentication information is stored within memory integrated within the network device. Once a ZTP server is connected to the network device, a secure connection may be established such as a secure transport layer session (TLS) utilizing the root of trust.

Systems and methods for provisioning network devices

A method and apparatus of a device that automates a task over a network that includes a plurality of data centers is described. In an exemplary embodiment, the device receives state change information from a plurality of devices in the plurality of data centers. In addition, the device generates an overall state for the network. The device further receives a task to be performed over the plurality of data centers. The device additionally schedules the task to be performed using the overall network state.

System and method of a managing multiple data centers

A cluster file replication system is provided. Each controller of the plurality of controllers is configured to access a filesystem having a plurality of files including a system database of a controller having state information of the plurality of controllers. Each controller is further configured to have one or more service agents. The one or more service agents of each controller is configured to respond to one of the plurality of controllers becoming a master controller of the cluster. The one or more service agents of each controller is configured to set up one or more objects that react to the state information and coordinate replication of changes to the files, system database and state information from the master controller to follower controllers in the cluster. The one or more objects on each of the follower controllers is supportive of the follower controllers receiving the changes but disabled from initiating the replication. A method for cluster file replication is also provided.

Cluster file replication

A method and apparatus of a device that restricts data communicated between a plurality of computing management devices and a plurality of computing devices is described. In one embodiment, a gateway receives network connectivity information of a network for a plurality of computing management devices and a plurality of computing devices, where the plurality of computing devices is coupled to the plurality of computing management devices via a plurality of network elements. In addition, the gateway determines a plurality of sub-networks using at least the network connectivity information, wherein for each of the plurality of sub-networks, at least one of the plurality of computing management devices and a subset of the plurality of computing devices is associated with that sub-network. Furthermore, for each of the plurality of sub-networks and for each pair of computing devices in the associated subset of plurality of computing devices, the gateway determines a policy for data being communicated between this pair of computing devices and the gateway configures at least one of the plurality of network elements coupled to this pair of computing devices to allow data communicated between this pair of computing devices using at least the first policy.

System and method of a centralized gateway that coordinates between multiple external controllers without explicit awareness

A method and apparatus of a device that measures performance of a plurality of cloud service providers is described. In an exemplary embodiment, the device deploys a plurality of cloud agents to the plurality of cloud service providers. In addition, the device configures a controller to measure the performance of each of the plurality of cloud service providers using each plurality of cloud agents. The device further probes each of the plurality of cloud service providers by sending probe data to each of the plurality of cloud service providers. The device additionally receives response data from each of plurality of cloud agents, wherein the response data is indicative of performance measurements of the plurality of cloud service providers. Furthermore, the device measures the performance for each of the plurality of cloud service providers using the response data.

System and method of a cloud service provider tracer

A method and apparatus to bring up a network controller in a network of multiple network elements is described. In an exemplary embodiment, the network controller receives an indication that the network controller is booting up. The network controller is coupled to a plurality of network elements in a network, where the network controller maintains a controller database that supports a network-wide service used by the plurality of network elements. The network controller further receives state information from the plurality of network elements. In addition, the network controller builds the controller database from the state information. Furthermore, the network controller sends updates from the controller database to each of the plurality of network elements, where each of the plurality of network elements incorporates these updates into a respective network element database and the network element database is used to perform the network-wide service.

System and method of a graceful reboot of a network controller

A method for high-availability operation is provided. The method includes communicating state information from each of a plurality of network elements to at least a first master network controller. The method includes communicating transformed state information from the first master network controller to the plurality of network elements and to each of a plurality of follower network controllers. The method includes continuing the high-availability operation with a new master network controller selected from among the plurality of follower network controllers as a failover, using the transformed state information in the new master network controller and in the plurality of network elements, responsive to a failure of the first master network controller. A network controller system is also provided.

Growing community of inventors

San Francisco, CA, United States of America

Andre Pech