Hierarchical scheduling over off- and on-chip deterministic networks

Abstract

In this paper we present a compositional model for distributed virtualized systems communicating over on-chip/off-chip deterministic networks implementing an end-to-end or partial time-triggered paradigm. We derive system-level constraints for combined task-, virtualization-and network-level static scheduling enabling the end-to-end composition of schedules for systems featuring table-driven (guest) operating systems. In the absence of a time-triggered run-time system, we analyze the composition problem with the aid of hierarchical scheduling methods for abstract resources. Moreover, we identify and discuss possible tradeoffs and optimization opportunities that arise when scheduling across multiple (virtualized) software layers in tandem with the deterministic network.