Google Inc.

Philip Michael Wells

Michael Roger Marty

Peter Michael Klausler

Hong Liu

Dennis Charles Abts

Bikash Koley

Xiaoxue Zhao

Edward Crabbe

Vijay Vusirikala

Paul Germano

Junlan Zhou

Angela Chen

Ashish Naik

Adi Avidor

The expansion of a network by converting the network from a 2-stage folded Clos network to a 3-stage folded Clos network can be cost prohibitive. The system and methods described herein relate to a hybrid network topology. More particularly, the disclosure describes a hybrid topology having internal switches configured in a multidimensional topology configuration. Each of the internal switches are connected to the network hosts with a folded Clos topology.

Hybrid Clos-multidimensional topology for data center networks

A network may be configured to route traffic in such a way as to avoid packet loss in an event of link failure. The network may include a plurality of inner switches and a plurality of outer switches coupled to the plurality of inner switches. Each inner switch may be configured to receive traffic, determine whether a link to a next hop for the traffic is down, and forward the traffic to another outer switch if the link to the next hop is down. Each outer switch may be configured to bounce traffic received from the first inner switch to a second inner switch if the traffic is received as a result of determining that the link from the inner switch to the next hop is down. The second inner switch may then deliver the traffic, or further bounce the traffic off another outer switch.

System and method for bouncing traffic in deadlock safe manner

Systems and methods are provided for congestion notification in mixed-fabric InfiniBand networks. In one aspect, a system and apparatus is provided wherein a receiving endpoint receives, from a sending endpoint, InfiniBand messages over a mixed-fabric network. The mixed-fabric network may include an InfiniBand transport layer and a non-InfiniBand messaging fabric. The non-InfiniBand massaging fabric may be any type of non-InfiniBand data-link-layer and network-layer network (e.g. Ethernet, IP). For example, the receiving endpoint may receive a non-InfiniBand protocol data unit (PDU) that contains at least a part of a first InfiniBand PDU as payload. The receiving endpoint may extract signaling from the received non-InfiniBand PDU that indicates whether congestion has been detected in the non-InfiniBand layers of the mixed-fabric network. The receiving endpoint may include the same or similar signaling in the header portion of a second InfiniBand PDU, and transmit the second InfiniBand PDU to the sending endpoint.

Explicit congestion notification in mixed fabric networks

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 method and apparatus are provided for communicating congestions that area detected in a communications network. According to the method and apparatus, a first Ethernet frame encapsulating a first PDU is transmitted across an Ethernet network. Congestion in the network is then detected, and an indication of the congestion is inserted in a predetermined header field of the first Ethernet frame. Once the first Ethernet frame is received by an endpoint in the network, the indication of congestion is transferred into a second PDU that is associated with the first PDU. The second PDU is then encapsulated in a second Ethernet frame and transmitted towards the sender of the first PDU.

Explicit congestion notification in mixed fabric network communications

Energy proportional solutions are provided for computer networks such as datacenters. Congestion sensing heuristics are used to adaptively route traffic across links. Traffic intensity is sensed and links are dynamically activated as they are needed. As the offered load is decreased, the lower channel utilization is sensed and the link speed is reduced to save power. Flattened butterfly topologies can be used in a further power saving approach. Switch mechanisms are exploit the topology's capabilities by reconfiguring link speeds on-the-fly to match bandwidth and power with the traffic demand. For instance, the system may estimate the future bandwidth needs of each link and reconfigure its data rate to meet those requirements while consuming less power. In one configuration, a mechanism is provided where the switch tracks the utilization of each of its links over an epoch, and then makes an adjustment at the end of the epoch.

Systems and methods for energy proportional multiprocessor networks

Adaptive packet routing is employed in a multiprocessor network configuration such as an InfiniBand switch architecture. Packets are routed from host to host through one or more switches. Upon receipt of a packet at a switch, the packet header is inspected to determine the destination host. A destination field in the header is used to index into a lookup table or other memory, which produces a route type and an output port grouping. Depending on the route type, one or more primary and secondary output port candidates are identified. An output port arbitration module chooses an output port from which to send a given packet, using congestion sensing inputs for the specified ports. A heuristic may include the congestion information that is provided to the arbitration module. Switching may be performed among minimal or non-minimal routes along each hop in the path, depending upon link and packet injection information.

Growing community of inventors

Madison, WI, United States of America

Philip Michael Wells