Intel Corporation

Cisco Technology, Inc.

Brocade Communications Systems, Inc.

Sanera Systems, Inc.

Joseph E Pelissier

Joseph I Chamdani

David Stewart Dunning

Ken Drottar

Gurumurthy D Ramkumar

Rajasekhar Cherabuddi

Claudio DeSanti

Richard D Reohr, Jr

Donald F Cameron

Richard S Jensen

Landon Curt Noll

Litko Chan

William H Swortwood

J Michel Metz

Vikas Deolaliker

A method is provided in one example embodiment and includes receiving by first network device a request for storage resources from a second network device; evaluating a willingness of the first network device to provide the requested storage resources and assigning a willingness score based on the evaluating; determining whether the willingness score is greater than a minimum value; and if the willingness score is greater than the minimum value, providing a response to the request from the first network device to the second network device, wherein the response comprises a bid by the first network device to provide the requested storage resources to the second network device.

Bid/ask protocol in scale-out NVMe storage

A computing system may be configured to receive a plurality of computing tasks for execution. The computing system may determine a first configuration setting for a first computing task and a second configuration setting, which is different from the first configuration setting, for a second computing task. A first computing node and a second computing node of the computing system may be booted according to the first and second configuration settings, and loaded with the first and second computing tasks for execution, respectively. After the first computing task finishes on the first computing node, the computing system may determine whether another computing task associated with the first configuration setting has not be executed, and when there is no such computing task remaining unexecuted, the computing system may reboot the first computing node according to a third configuration setting and load a third computing task into the first computing node for execution.

Method for optimizing performance of computationally intensive applications

An example method for direct data placement over User Datagram Protocol (UDP) in a network environment is provided and includes creating a queue pair (QP) for unreliable datagram transport in Infiniband according to an OpenFabrics Application Programming Interface (API) specification, mapping data generated by an application for transmission over the QP in a network environment to a UDP datagram, and passing the UDP datagram to a network interface for transmission.

Direct data placement over user datagram protocol in a network environment

Switching data packets includes forwarding first data packets to a first port that is associated with a first domain. Second data packets are forwarded to a second port that is associated with a second domain. The first data packets are managed using a first management subsystem of a service processor card, and the second data packets are managed using a second management subsystem of the service processor card.

Isolation of data, control, and management traffic in a storage area network

Processing a data packet in a multiple protocol system area network is disclosed. A paddle card comprising a first paddle card that supports a first communication protocol or a second paddle card that supports a second communication protocol is received. The communication protocol supported by the received paddle card is identified. Data packets from the received paddle card are processed according to the identified communication protocol.

Processing data packets in a multiple protocol system area network

A system and method of packet classification for advanced packet forwarding using a table-based classification method is implemented using a minimum of additional system hardware. The table-based search process implemented for basic packet forwarding is leveraged to accomplish advanced packet classification through the use of a classification table system and classification information stored in data packets. Packet forwarding decisions may be made based on the result of the classification table search.

Table-based packet classification

A method for detecting and discarding stale cells following route changes in a data communication network. The data communication network comprises a transmitter, which upon detection of a failure in a route of a network, retransmits data tagged as resent data along a different route of a multi-stage switch; and a receiver, which upon detection of tagged data from the transmitter via the different route of the multi-stage switch, utilizes tagged data for data communications while discarding previously transmitted data that are not tagged to avoid data duplication.

Method for detection of stale cells following route changes in a data communication

A method of device initialization in a network is provided. An explicitly routed management cell is received at a device. The management cell includes initialization information, such as an address or a forwarding database. The management cell also includes information specifying an explicit route for the cell to traverse to reach the device. The device is initialized based on the initialization information in the received management cell. One or more subsequent cells are routed through the device using the more efficient destination address routing technique after the device is initialized.

Device initialization and operation using directed routing

An error detection technique uses a cumulative error detecting code (such as a cumulative CRC checksum or the like). At the source node (transmitter side) an error detecting code of a previous cell is stored. The next cell to be transmitted is received and the error detecting code of the previous cell is appended to the next cell. A next error detecting code is calculated as a function of at least a portion of the next cell to be transmitted and the previous error detecting code appended thereto. The previous error detecting code appended to the next cell is replaced with the next error detecting code, and the next cell including the next error detecting code appended thereto is transmitted. In this manner, the cumulative error detecting code is calculated over the current cell and a previous error detecting code. Thus, the cumulative error detecting code can be used to detect bit errors in each individual cell as well as to detect one or more missing or dropped cells.

Growing community of inventors

Hillsboro, OR, United States of America

Joseph E Pelissier