2003 · 84 citations · 15 references
AvailabilityEngineeringVerificationComputer ArchitectureFault ToleranceFault-tolerant MessagingHardware SystemsFormal VerificationSystems EngineeringActive ReplicationComputer EngineeringNetworked Computer SystemsDistributed SystemsDistributed TransactionActive ReplicasData ReplicationFault-tolerant NetworkDistributed ComputingFormal MethodsLocal Area NetworkReal-time SystemsInter Replica ProtocolAsynchronous SystemsSystem Software
Delta-4 is an open dependable distributed computing systems architecture, in which fault-tolerance is achieved by means of replication of run-time software components on host computers interconnected by a local area network. The authors discuss the coordination of active replicas executing either in a fail-silent host computer environment, or in a full-uncontrolled environment. This coordination is carried out by a specific protocol, the inter replica protocol (IRp). The IRp was implemented in various Delta-4 prototypes. The protocol, the service it delivers, and the environment assumptions were formally specified. The specifications were formally verified for consistency by model checking techniques. The formal specification and verification of IRp are considered. Some implementation details and results of performance tests are given.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
15
Why Do Computers Stop and What Can Be Done About It?
Jim Gray · 2024 · 671 citations
Anita Borg, Wolfgang Blau, Wolfgang Graetsch et al. · ACM Transactions on Computer Systems · 1989 · 230 citations · Full text