The PSTR/SNS scheme for real-time fault tolerance via active object replication and network surveillance

Abstract

ÐThe time-triggered message-triggered object (TMO) scheme was formulated a few years ago as a major extension of the conventional object structuring schemes with the idealistic goal of facilitating general-form design and timeliness-guaranteed design of complex real-time application systems. Recently, as a new scheme for realizing TMO-structured distributed and parallel computer systems capable of both hardware and software fault tolerance, we have formulated and demonstrated the primary-shadow TMO replication (PSTR) scheme. An important new extension of the PSTR scheme discussed in this paper is an integration of the PSTR scheme and a network surveillance (NS) scheme. This extension results in a significant improvement in the fault coverage and recovery time bound achieved. The NS scheme adopted is a recently developed scheme effective in a wide range of point-to-point networks and it is called the supervisor-based NS (SNS) scheme. The integration of the PSTR scheme and the SNS scheme is called the PSTR/SNS scheme. The recovery time bound of the PSTR/SNS scheme is analyzed on the basis of an implementation model that can be easily adapted to various commercial operating system kernels.

Reliable Distributed Real-Time and Embedded Systems through Safe Middleware Adaptation

“…Real-time fault-tolerant systems: IFLOW [18] and MEAD [19] use fault-prediction techniques to reduce fault detection and client failover time to change the frequency of backup replica state synchronization to minimize state synchronization during failure recovery, and by determining the possibility of a primary replica failure and redirecting clients to alternate servers before failures occur, respectively. The Time-triggered Message-triggered Objects (TMO) project [20] considers replication schemes such as the primary-shadow TMO replication (PSTR) scheme, for which recovery time bounds can be quantitatively established, and real-time fault tolerance guarantees can be provided to applications. FC-ORB [21] is a real-time Object Request Broker (ORB) middleware that employs end-to-end utilization control to handle fluctuations in application workload and system resources by enforcing desired CPU utilization bounds on multiple processors by adapting the rates of end-to-end tasks within user-specified ranges.…”

Towards Middleware for Fault-Tolerance in Distributed Real-Time and Embedded Systems

“…MEAD [17] and its proactive recovery strategy for distributed CORBA applications can minimize the recovery time for DRE systems. The Time-triggered Message-triggered Objects (TMO) project [9] considers replication schemes such as the primary-shadow TMO replication (PSTR) scheme, for which recovery time bounds can be quantitatively established, and real-time fault tolerance guarantees can be provided to applications. DARX [11] provides adaptive fault-tolerance for multi-agent software platforms by dynamically changing replication styles in response to changing resource availabilities and application performance.…”

Detection of anomalies in software architecture with connectors

“…Time testing, referred to as heartbeating [3,9,10], can be used to check if a component or system is anomalous, but it may fail to locate where an anomaly is in a component or system. The detection mechanism depending on exceptions [7] may not handle unanticipated, state-dependent anomalies.…”

“…Several approaches to anomaly detection for dependable systems have been suggested in [3,[8][9][10]7,4], which may provide partial solutions from the perspective of quality factors of the mechanisms for anomaly detection-speed and accuracy. Time testing, referred to as heartbeating [3,9,10], can be used to check if a component or system is anomalous, but it may fail to locate where an anomaly is in a component or system.…”