The Charles Stark Draper Laboratory, Inc.

Samuel Beilin

David Crane

Seamus Tuohy

Neil Brock

Adam J Elbirt

Jeffrey Zinchuk

Eric T Antelman

M Jay Prizant

Roger Racine

In an embodiment of the present invention, a method receives, at a first node of multiple nodes, each node connected to a common network bus, a health message from a second node. The health message includes a log of health messages from other nodes. Each node sends health messages at a frequency known to the plurality of nodes. The method further compares, at the first node, the log of messages from other nodes in the received health message to a log of health messages previously received from other nodes stored by the first node. Based on the comparison, determining a health status of each node. Using embodiments of the present method and system, computing units can form dynamic fault-tolerant groups.

Fault-tolerant operational group on a distributed network

In an embodiment, a method includes assigning, based on a switch module of a particular node of one or more nodes of a fault-tolerant group, a channel to the particular node. The method further includes determining a number of nodes in the fault-tolerant group by exchanging handshake information between the channel assigned to the particular node and channels assigned to other nodes of the fault-tolerant group. The method further includes initializing the fault-tolerant group with the determined number of nodes based on the exchanged handshake information.

Self-configuring fault-tolerant operational group

Systems and methods are disclosed herein for a replicated fault-tolerant computer system. The system includes a triplet of network elements, which each maintain a clock signal, and a clock monitor at each network element for monitoring incoming clock signals. Each network interfaces with a fault containment region (FCR). The system provides the ability to transition from a duplex system to a triplex system if one of the previously offline FCRs can be brought back online. The network elements can determine or receive notification that the previously offline FCR can be brought back online, align their respective clock signals, and synchronize the memory state of the previously offline FCR. The system can then operate in a fault-tolerant, replicated triplex operating mode.

System and method for augmenting duplexed replicated computing

Systems and methods are disclosed herein for a replicated duplex computer system. The system includes a triplet of network elements, which each maintain a clock signal, and a monitor at each network element for monitoring incoming clock signals. Each network element interfaces with a fault containment region (FCR). The system provides the ability to transition to a duplex system if one of the fault containment regions fails. The three network elements are able to send their clock signals to the other network elements and receive their own clock signal and clock signals from the other elements. The monitors are configured to detect discrepancies in the clock signals of the network elements. If a monitor determines that an FCR has failed, each network element is reconfigured so that the FTPP system operates in a duplex mode without the faulty FCR by replacing the clock signal from the faulty element with its own clock signal.

Growing community of inventors

Brighton, MA, United States of America

Samuel Beilin