Google Inc.

Juniper Networks, Inc.

Hewlett-packard Company

Balakrishna Raghunath

Prashant R Chandra

Uday Ramakrishna Naik

Michael Dalton

Umesh Krishnaswamy

Systems and methods of offloading multicast virtual network packet processing to a network interface card are provided. In an example implementation, a network interface card can route packets in a virtual network. The network interface card can be configured to receive a data packet having a multicast header for transmission to a plurality of destination virtual machines. The network interface card can retrieve a list of next hop destinations for the data packet. The network interface card can replicate the packet for each next hop destination. The network interface card can encapsulate each replicated packet with a unicast header that includes a next hop destination virtual IP address indicating the next hop destination and a source virtual IP address, and transmit the encapsulated packets.

Offloads for multicast virtual network packet processing in a network interface card

A network device having a distributed, multi-stage forwarding architecture uses a two-stage process for planned orderly offlining of switch fabric components. The process includes a prepare stage in which preparations are made from downstream components to upstream components for offlining and new spray weights are calculated but not applied, and a commit stage in which new spray weights are committed and applied to traffic from upstream components to downstream components.

Orderly offlining in a distributed, multi-stage switch fabric architecture

A device facilitates offset independent message filtering, and receives a filter registration request from a control software element, where the filter registration request includes at least a field name and a filter value. The device also identifies an offset value associated with the received field name, and filters a message based on the filter value and the identified offset value.

Offset independent filtering

A router includes a detection module to detect a presence of the network attack, such as a denial of service (DOS) attack. The detection module may, for example, include counters indicating a number of packets processed for various network protocols supported by the router. The detection module enables a rate-limiting operating mode for the router when one or more of the counters exceed a protocol-specific threshold. Under normal traffic levels, the router receives inbound packets using interrupt-driven service routines. When a network attack is detected, however, the router dynamically switches modes and processes the patents using a finely controlled software process. This allows the software process to control the computing resources allocated to servicing packets during a network attack, thereby reserving sufficient resources for lower priority software processes to process the packets and service other tasks.

Dynamically controlling packet processing

A router includes a detection module to detect a presence of the network attack, such as a denial of service (DOS) attack. The detection module may, for example, include counters indicating a number of packets processed for various network protocols supported by the router. The detection module enables a rate-limiting operating mode for the router when one or more of the counters exceed a protocol-specific threshold. Under normal traffic levels, the router receives inbound packets using interrupt-driven service routines. When a network attack is detected, however, the router dynamically switches modes and processes the packets using a finely controlled software process. This allows the software process to control the computing resources allocated to servicing packets during a network attack, thereby reserving sufficient resources for lower priority software processes to process the packets and service other tasks.

A method and apparatus that improves the efficiency of outbound data management for information transmitted over a communication network protocol by eliminating unnecessary operations related to the checksum when associated data has not changed since the last determination of the checksum. Overall computer system costs are reduced by eliminating checksum functionality on computer networking cards and thereby minimizing overall checksum functionality requirements in the computer system. The checksum that is derived on the first instance of data transmittal is cached. Thereafter, on subsequent transmissions of the data, the cached checksum may be re-used. Further, partial checksums can be calculated for portions of data that will be transmitted. The partial checksums may be combined to create a checksum that represents the aggregate of the data that will be transmitted.

Growing community of inventors

San Jose, CA, United States of America

Balakrishna Raghunath