Cisco Technology, Inc.

Mingzhe Li

Chih-Tsung Huang

Putu Harry Subagio

Alessandro Fulli

Thomas James Edsall

Christopher A Wildman

Wei-Jen Huang

Yichou Lin

A network device receives a packet that includes a plurality of header fields. The packet is parsed to sequentially obtain the plurality of header fields. One or more header fields not yet available at the network device are predicted based on one or more header fields that are available at the network device. A network processing decision is generated for the packet based on the predicted one or more header fields and the one or more header fields that are available at the network device.

Low latency networking device using header prediction

A network device receives a packet that includes a plurality of sets of fields. Sets of fields of the packet are parsed and the field sets are evaluated as soon as they are available to determine whether a processing decision can be made on the packet. Additional field sets may be parsed from the packet and obtained in parallel with determining whether a processing decision can be made, but once it is determined that a processing decision can be made, the evaluating of field sets is terminated such that any further field sets of the packet are ignored for purposes of making a processing decision for the packet.

Scalable low latency multi-protocol networking device

Presented herein are techniques to achieve ultra low latency determination of processing decisions for packets in a network device. A packet is received at a port of a network device. A processing decision is determined in a first processing decision path based on content of the packet and one or more network policies. A processing decision is determined in a second processing decision path, in parallel with the first processing path, by accessing a table storing processing decisions. The second processing decision path can output a processing decision faster than the first processing decision path for packets that match one or more particular packet flow parameters contained in the table. A processing decision determined by the second processing decision path, if one can be made, is used, and otherwise a processing decision determined by the first processing decision path is used.

Ultra low latency multi-protocol network device

A multi-destination expansion table is stored that comprises a first database containing data representing all nodes in a singly linked list that is a superset of nodes for a plurality of multi-destination groups and a second database storing data representing multi-destination group specific arcs across one or more nodes. The singly linked list is traversed to determine how to replicate a packet for a particular multi-destination group. The packet is replicated based on interface data stored in the first database associated with the current node address. When a match is found in the second database, a next node address is determined from the second database. When a match is not found in the second database, a next node address determined from accessing the first database. Traversing of the singly linked list is terminated when the next node address is determined to be invalid or null.

Compressing singly linked lists sharing common nodes for multi-destination group expansion

A method in an example embodiment includes creating a first search key from variable data of a message received in a network environment, creating a second search key from constant data of the message, identifying a first database entry in a first database based on the first search key, and identifying a second database entry in a second database based on the second search key. The method can also include performing an action associated with the first database entry when a correlation is identified between the first and second database entries. In specific embodiments, the variable data are modified and the constant data are not modified. The first search key can be created prior or subsequent to forwarding the message. In further embodiments, the correlation is identified when an offset of the first database entry is the same as an offset of the second database entry.

Growing community of inventors

Fremont, CA, United States of America

Mingzhe Li