Emc Corporation

Alacritech, Inc.

James Gregory Jones

Clive M Philbrick

John A Scott

Keith John Glidewell

Methods, systems, and computer program products for automatically determining locations of interconnected processing modules are disclosed. Physical identifiers are determined for each of a plurality of processing modules connected to each other in a linear topology. Communications are iteratively disabled with each of the processing modules. Discover messages are sent to active, reachable processing modules and responses are received from the active processing modules that receive the discover messages. Based on the number of responses, the location of each processing module is determined.

Methods, systems, and computer program products for determining locations of interconnected processing modules and for verifying consistency of interconnect wiring of processing modules

A host computer running a TCP connection transfers the connection to a TCP offload network interface device (NID) which performs certain network processes, thereby reducing the load on the host CPU. The NID later transfers the connection back to the host. The host and the NID maintain separate timestamp clocks which provide timestamp values for connections using the TCP Timestamp option. Synchronization of the host and NID timestamp clocks can be realized by transfer of a clock value. The NID or host receives the transferred TCP connection and the transferred clock value, and decides whether to update its own clock to equal the transferred clock value, the decision being guided by the requirement to never allow the timestamp clock to run backward. Acceleration of the timestamp clocks is prevented so that RTT measurements are accurate. Synchronization of the host and NID timestamp clocks improves performance and reduces erroneous connection drops.

TCP timestamp synchronization for network connections that are offloaded to network interface devices

Methods, systems, and computer program products for controlling communications between network applications and multiple network communications protocol stacks using deferred protocol stack association are disclosed. In one method, a socket creation function call is received from an application. A socket creation function call is terminated, a pseudo communications endpoint is created, and a socket descriptor corresponding to the pseudo communications endpoint is returned to the application. At least one subsequent sockets-related function call is received. Based on the subsequent sockets-related function call, it is determined whether the application is a client or a server. In response to determining that the application is a server, communications endpoints are created on each of the network communications protocol stacks and server-related sockets function calls are made to each of the underlying protocol stacks. In response to determining that the application is a client, a protocol stack is selected, a protocol-stack-specific communications endpoint is created, and client-related sockets function calls are made to the underlying protocol-stack.

Methods, systems, and computer program products for transparently controlling communications between network applications and a plurality of network communications protocol stacks using deferred protocol stack association

A communications passthrough mechanism for high availability network communications between a shared system resource and clients of the system resource. The system resource includes a control/processing sub-system including multiple peer blade processors. A port of each blade processor is connected to each client/server network path and each client is connected to a corresponding port of each blade processor. Each blade processor includes a network fault detector exchanging beacon transmissions with other blade processors through corresponding blade processor ports and network paths. Each blade processor includes response generator responsive to a failure to receive a beacon transmission from a failed port of an other blade processor for redirecting the client communications to the failed port on the other blade processor to the corresponding port of the blade processor. A path manager in the blade processor is responsive to operation of the response generator for modifying the communications routing table to correspond with the redirection message to route the client communications to the failed port of the other blade processor to the other blade processor through the inter-processor communications link. Each blade processor may also include an inter-blade communications monitor for detecting a failure in the inter-processor communications link between the blade processor and another blade processor, reading the communications routing table to select a functional network communications path to a port of the other blade processor, and modifying the communications routing table to redirect inter-processor communications to the selected functional network communications path.

Growing community of inventors

Raleigh, NC, United States of America

James Gregory Jones