Google Inc.

Edward Crabbe

Navindra Yadav

Daniel Todd Cohn

Hong Liu

Bikash Koley

Xiaoxue Zhao

Philip Michael Wells

Vijay Vusirikala

Paul Germano

Steven Padgett

Paul Robert Schultz

Methods, systems, and apparatus are described for network encapsulation and routing. In one aspect, a method includes receiving, from source network and at an edge device a first network packet including a first inner header including i) a first source address, and ii) a first destination address; selecting a source network identifier for the source network from a plurality of routable network identifiers; encapsulating the first network packet within a first encapsulation packet; routing the first encapsulation packet to the destination server; receiving, from the destination server, a second encapsulation packet; extracting the second network packet from the second encapsulation packet; and routing the second network packet to the source network.

Network packet encapsulation and routing

A Hardware Abstraction Layer (HAL) for a target computing device that is equipped with an Application Specific Integrated Circuit (ASIC) or other hardware element that provides forwarding and/or switching capability is used to analyze an abstract candidate device model. The abstract candidate device model is received from a controller and specifies intended forwarding behavior for the target device. The HAL analyzes the abstract candidate device model based on its knowledge of the architecture of the ASIC or other hardware element providing forwarding or switching capability to the target device. If the behavior is supported by the target device's architecture, the model may be implemented in a specific manner supported by that architecture and used to control forwarding behavior on the target device.

Target mapping and implementation of abstract device model

A packet switch/router including a first stage switch fabric receiving an electrical signal, a mid-stage buffer receiving and storing the electrical signal from the first stage switch fabric, and a second stage switch fabric receiving the electrical signal from the mid-stage buffer. Each switch fabric includes N layers of N&#xd7;N arrayed waveguide gratings (AWGs), and each AWG has ingress ports and egress ports. A wavelength tunable device, such as a tunable laser, communicates with a source ingress port of an AWG and converts the received electrical signal to an optical signal having a wavelength selected for routing a packet from the source ingress port to a target egress port of the arrayed waveguide grating. A photoreceiver, such as a burst-mode photoreceiver, receives the propagated optical signal from the target egress port and converts the optical signal to the electrical signal.

Optoelectronic packet switch/routers

A controller in a communication network may be responsible for generating a device model that defines intended forwarding behavior of a network. The device model may be generated using a target-independent universal language of network primitives. The controller may assign a first set of parameters to the device model to generate a first parameterized device model. The controller may assign a second set of parameters to the device model to generate a second parameterized device model. The controller may send the first parameterized device model or the second parameterized device model to a target device. The target device may statically or dynamically translate the received parameterized device model(s) to implementation. The controller is not required to generate a new device model for each modification made to the network: the controller may parameterized a generic device model to reflect the modifications.

Parameterized device models for openflow

A negotiation process is conducted between a controller and a target forwarding or switching device with respect to an abstract candidate device model for a forwarding plane. The abstract candidate device model is provided by a controller and indicates intended forwarding or switching behavior for the target device that a controller desires to have implemented on the target device. The intended behavior is specified in terms of mandatory and non-mandatory behavior. A hardware abstraction layer (HAL) for the target device analyzes the abstract candidate device model and decides whether the mandatory and optional behavior that is specified by the model is supported given the architecture of the target. The HAL informs the controller whether the intended behavior is supported by the target. Additional behavior may be proposed and accepted or not before the model is finalized. The finalized model may then be implemented and used to control forwarding behavior on the target device.

Growing community of inventors

San Francisco, CA, United States of America

Edward Crabbe