Cisco Technology, Inc.

Other

Cortina Systems Corporation

Raymond Kloth

Thomas James Edsall

Dinesh Ganapathy Dutt

Yiren Huang

Michael Fine

Umesh Mahajan

Ramana Mellacheruvu

Maurilio Cometto

Kalyan Ghosh

Venkateshwar Rao Pullela

Mark Andrew Gustlin

Gaurav Rastogi

Oded Trainin

Ryan Patrick Donohue

Robert Hoffman

Med Belhadj

Sebastian H Ziesler

Kevin D Morishige

Jason Alexander Jones

Pawan Agrawal

Sujatha Sundararaman

James Brian Mckeon

Fredrick Karl Olive Olsson

Rami Zecharia

Matthew Cressa

Fabio Rodolfo Maino

Dipankar Bhattacharya

Sachin Jain

Alessandro Fulli

Guglielmo Marco Morandin

Sriharsha Jayanarayana

Ketan Arun Padwekar

Jonathan M Parlan

Nitin Garg

Ravi K Nimmagadda

Ying Huang

Deepak Goel

Yiren R Huang

A mechanism for combining plurality of point-to-point data channels to provide a high-bandwidth data channel having an aggregated bandwidth equivalent to the sum of the bandwidths of the data channels used is provided. A mechanism for scattering segments of incoming data packets, called data chunks, among available point-to-point data channel interfaces is further provided. A decision as to the data channel interface over which to send a data chunk to can be made by examining a fullness status of a FIFO coupled to each interface. An identifier of a data channel on which to expect a subsequent data chunk can be provided in a control word associated with a present chunk of data. Using such information in control words, a receive-end interface can reassemble packets by looking to the control word in a currently processing data chunk to find a subsequent data chunk.

Scatter and gather scheme for aggregating multiple high speed point-to-point interfaces

A high speed multi-lane serial interface and method for constructing frames for such an interface are provided. Frames are constructed for transmission on a multi-lane serial interface. For each of a plurality of transmit channels, packets are fragmented into fragments. Meta-frames are generated having a size defined by a constant meta-frame length&#xd7;number of lanes, each frame having a meta-frame separator and a payload. Per-transmit channel flow control information is received. Each payload has a plurality of bursts, each burst comprising a burst control word and an associated data burst, the burst control word identifying one of said transmit channels to be transmitted on the associated data burst, each data burst comprising one of the fragments for the transmit channel identified in the associated burst control word. The channels to transmit in a given meta-frame are selected as a function of the received flow control information.

High speed packet interface and method

Provided are methods and apparatus that enforce zoning rules by separately employing source and destination information. In certain embodiments, information uniquely identifying network destinations is provided on a destination CAM. In these embodiments, each destination identified in the destination CAM has an associated zoning decision vector provided in a results memory. The vector provides specific zoning decisions (permit or deny transmission) for specific sources on the network. The specific zoning decision to be applied to a frame under consideration is selected from a zoning decision vector by using source information taken from the frame.

Hardware based zoning in fibre channel networks

Methods and apparatus for performing encryption for data at rest at a port of a network device such as a switch are disclosed. Specifically, when data is received from a host during a write to a storage medium such as a disk, the data is encrypted by the port prior to transmitting the encrypted data to the storage medium. Similarly, when a host attempts to read data from the storage medium, the port of the network device receives the encrypted data from the storage medium, decrypts the data, and transmits the decrypted data to the host. In this manner, encryption and decryption of data at rest are supported by the port of the network device.

Method and apparatus for performing encryption of data at rest at a port of a network device

Methods and devices are provided for the efficient allocation and deletion of virtual output queues. According to some implementations, incoming packets are classified according to a queue in which the packet (or classification information for the packet) will be stored, e.g., according to a 'Q' value. For example, a Q value may be a Q number defined as {Egress port number&#x2225;Priority number&#x2225;Ingress port number}. Only a single physical queue is allocated for each classification. When a physical queue is empty, the physical queue is preferably de-allocated and added to a 'free list' of available physical queues. Accordingly, the total number of allocated physical queues preferably does not exceed the total number of classified packets. Because the input buffering requirements of Fiber Channel (&#x201c;FC&#x201d;) and other protocols place limitations on the number of incoming packets, the dynamic allocation methods of the present invention result in a sparse allocation of physical queues.

Scalable approach to large scale queuing through dynamic resource allocation

Methods and devices are provided for non-disruptive monitoring of network traffic through one or more ports of a Fibre Channel network device. Preferred embodiments of the invention are used in conjunction with the switched port analyzer ('SPAN') and/or remote SPAN ('RSPAN') features. SPAN mode operation allows traffic through any Fibre Channel interface of a network device to be replicated and delivered to a single port on the same network device. Ingress SPAN allows the monitoring of some or all packets that ingress a specified port or ports. Egress SPAN allows the monitoring of some or all packets that egress a specified port or ports. RSPAN allows the delivery of the replicated traffic to a port on a remote network device. Filtering may be applied, for example, to SPAN packets having selected virtual storage area network numbers.

Switch port analyzers

A system enables efficient flow control in computer network. In the preferred embodiment, when an entity detects an impending full condition, it cuts short its transmission of the current frame that is being sent, and immediately sends a pause signal. The entity also deliberately corrupts the error detection signature of the cut-off frame to ensure that whatever portion of it that may have been sent is discarded. After sending the pause signal, the entity re-sends the cut-off frame in its entirety. Upon receiving a pause signal, the receiving entity cuts short the current frame being transmitted to the entity that sent the pause signal. The receiving entity also corrupts the correction value of this cut-off frame. The receiving entity suspends its transmission of frames to the entity that sent the pause signal for a period of time. When the pause period expires, the receiving entity re-sends the cut-off frame in its entirety, and resumes the transmission of frames.

System and method for efficient network flow control

Methods and apparatus are provided for controlling congestion in a network such as a fibre channel network. Techniques are provided for characterizing traffic flow at a congested network node. The congested network node can generate various instructions such as quench messages to control traffic flow towards the congested network node. The quench messages can optionally include information about the characteristics of the congestion. The instructions are distributed to other nodes in the network. The other network nodes can interpret the instructions and control traffic flow towards the congested node.

Methods and apparatus for network congestion control

A method of operating a switch for frames in a computer network uses one or more indicia of frame type designation found in the received frame to derive a virtual local area network (derived VLAN) value. Also, an indicia of the receiving port may be used in constructing the derived VLAN value. The switch then uses the derived VLAN value in making forwarding decisions. Broadcast domains in the computer network may then be controlled by forwarding in response to the derived VLAN value.

Derived VLAN mapping technique

According to the present invention, methods and apparatus are provided to improve the techniques and mechanisms for forwarding packets at a fiber channel switch. A combined area table/domain table (ATDT) is accessed using destination information associated with a fiber channel packet. Area/port or domain information can be used to address entries in the ATDT. Each entry provides one or more paths to a given destination. Traffic shaping, load balancing, and other policy based forwarding considerations can be applied.

Fibre channel forwarding information base

Methods and apparatus are provided for controlling congestion in a network such as a fiber channel network. Techniques are provided for detecting congestion at a shared resource such as a network node. When a controller sends data to a shared resource, the delay between sending the data and receiving a credit is measured. If the delay is significant, it is assumed that the path towards the destination associated with the data is congested and subsequent traffic from the port associated with the data is blocked.

Methods and apparatus are provided for alleviating deadlock and controlling congestion in a network such as a fibre channel network. Techniques are provided for detecting stalled frames at a fibre channel switch. Reserve credits are released when stalled frames are detected. In some instances, reserve credits are released after a predetermined period of time. Reserve credits allow transmission to effectively reduce deadlock and congestion. Reserve credits are particularly effective in reducing deadlock resulting from transient loops in a fibre channel network.

Methods and apparatus for alleviating deadlock in a fibre channel network

Growing community of inventors

Saratoga, CA, United States of America

Raymond Kloth