Mechanisms for reliable distributed real-time operating systems: The Alpha Kernel
Mechanisms for reliable distributed real-time operating systems: The Alpha Kernel
Some Results of the Earliest Deadline Scheduling Algorithm
IEEE Transactions on Software Engineering
Improved algorithms for synchronizing computer network clocks
IEEE/ACM Transactions on Networking (TON)
Unreliable failure detectors for reliable distributed systems
Journal of the ACM (JACM)
Replica Determinism and Flexible Scheduling in Hard Real-Time Dependable Systems
IEEE Transactions on Computers
Distributed Algorithms
On the Quality of Service of Failure Detectors
IEEE Transactions on Computers
On the Impact of Fast Failure Detectors on Real-Time Fault-Tolerant Systems
DISC '02 Proceedings of the 16th International Conference on Distributed Computing
A comparison of scheduling algorithms for real time distributed transactional systems
FTDCS '97 Proceedings of the 6th IEEE Workshop on Future Trends of Distributed Computing Systems
Best-effort decision-making for real-time scheduling
Best-effort decision-making for real-time scheduling
Scheduling dependent real-time activities
Scheduling dependent real-time activities
IEEE Transactions on Software Engineering
Distributed real-time specification for Java: a status report (digest)
JTRES '06 Proceedings of the 4th international workshop on Java technologies for real-time and embedded systems
SRDS '06 Proceedings of the 25th IEEE Symposium on Reliable Distributed Systems
Evolving mach 3.0 to a migrating thread model
WTEC'94 Proceedings of the USENIX Winter 1994 Technical Conference on USENIX Winter 1994 Technical Conference
On distributed real-time scheduling in networked embedded systems in the presence of crash failures
SEUS'07 Proceedings of the 5th IFIP WG 10.2 international conference on Software technologies for embedded and ubiquitous systems
Resource management policies for real-time Java remote invocations
Journal of Parallel and Distributed Computing
| Hi-index | 0.00 |
We demonstrate a consensus utility accrual scheduling algorithm for distributable threads with run-time uncertainties in execution time, arrival models, and node crash failures. The DUA-CLA algorithm's message complexity (O(fn)), lower time complexity bound (O(D+fd+nk)), and failure-free execution time (O(D+nk)) are established, where D is the worst-case communication delay, d is the failure detection bound, n is the number of nodes, and f is the number of failures. The "lazy-abort" property is shown -- abortion of currently-infeasible tasks is deferred until timely task completion is impossible. DUA-CLA also exhibits "schedule-safety" -- threads proposed as feasible for execution by a node which fails during the decision process will not cause an otherwise-feasible thread to be excluded. These properties mark improvements over earlier strategies in common- and worst-case performance. Quantitative results obtained from our Distributed Real-Time Java implementation validate properties of the algorithm.