Combating unpredictability in multicores through the multi-resource server

Abstract

In this paper we present challenges that hinder the predictable integration and execution of real-time applications on multicore platforms. We investigate how shared resources, like CPU, memory-bus bandwidth, caches, and memory cause unpredictability and interference. We propose to adapt the traditional server-based scheduling approach on the multicore platforms with additional resource-reservations to control the shared access to such resources and present the multi-resource server as a solution such that the execution of real-time applications becomes predictable.Keywords-Hierarchical scheduling, memory-bus bandwidth, cache coloring, memory-bank partitioning.• We examine the shared resources that are specific to multicore architectures, causing predictability bottlenecks/hindrances.

Memory-Aware Scheduling for Fixed Priority Hard Real-Time Computing Systems

“…In particular, we can extend our research to include and test additional aspects or parameters of different platforms and real-time systems in our proposed scheduling mechanisms. First, our set of scheduling mechanisms proposed in chapter 3 can be extended to partition not only cache memories but also DRAM memories using bank partitioning [196]. The interaction between both methodologies of cache and bank partitioning when maximizing the schedulability of the system can be further explored.…”