DEUCON: Decentralized End-to-End Utilization Control for Distributed Real-Time Systems
IEEE Transactions on Parallel and Distributed Systems
End-to-end deadline control for aperiodic tasks in distributed real-time systems
The Journal of Supercomputing
Online adaptive utilization control for real-time embedded multiprocessor systems
CODES+ISSS '08 Proceedings of the 6th IEEE/ACM/IFIP international conference on Hardware/Software codesign and system synthesis
FCS/nORB: A feedback control real-time scheduling service for embedded ORB middleware
Microprocessors & Microsystems
Towards end-to-end quality of service: controlling I/O interference in shared storage servers
Proceedings of the 9th ACM/IFIP/USENIX International Conference on Middleware
End-to-end utilization control for aperiodic tasks in distributed real-time systems
Journal of Computer Science and Technology
Self-tuning schedulers for legacy real-time applications
Proceedings of the 5th European conference on Computer systems
Feedback scheduling for pipelines of tasks
HSCC'07 Proceedings of the 10th international conference on Hybrid systems: computation and control
Online adaptive utilization control for real-time embedded multiprocessor systems
Journal of Systems Architecture: the EUROMICRO Journal
A Robust Mechanism for Adaptive Scheduling of Multimedia Applications
ACM Transactions on Embedded Computing Systems (TECS)
Adaptive real-time scheduling for legacy multimedia applications
ACM Transactions on Embedded Computing Systems (TECS)
Hi-index | 0.00 |
Traditionally, real-time scheduling mechanismshave been used to provide predictable scheduling latency butthese mechanisms are difficult to use in general-purpose operatingsystems (OSs) because they require precise specification ofthread requirements in terms of low-level resources such as CPUcycles. In a general-purpose environment such a specificationmay not be statically available. In this paper, we present thedesign, implementation and evaluation of a novel feedback-basedreal-rate scheduler that automatically infers thread requirementsand thus makes it easier to use real-time scheduling mechanismsin general-purpose OSs. The real-rate controller uses thread-specifiedtime-stamps that indicate a threadýs progress to estimateresource requirements. The goal of the controller is to regulatethe overallocation of resources and the delay experienced by athread. It meets these goals by using gain compensation and bychoosing an appropriate sampling period for the controller thatdepends only on the granularity of thread time-stamps. A keybenefit of the real-rate approach is that it can be easily appliedin a general-purpose environment across different applicationsbecause the controller does not require any tuning.