Enabling Strong Isolation for Distributed Real-Time Applications in Edge Computing Scenarios

Abhishek Dubey, W. Emfinger, A. Gokhale, P. Kumar, D. McDermet, T. Bapty, G. Karsai

IEEE Aerospace and Electronic Systems Magazine 2019

PDF DOI

Why This Matters

Mixed-criticality applications require strong isolation to prevent failures in non-critical functions from affecting critical operations, while maximizing resource utilization in embedded systems. COSMOS is innovative because it provides operating system-level support for spatial and temporal partitioning with minimal overhead, enabling multiple applications to safely share computing resources. The architecture enables higher resource efficiency without sacrificing safety guarantees.

What We Did

This paper describes COSMOS, a distributed real-time managed systems operating system layer that enables temporal and spatial partitioning for mixed-criticality cyber-physical systems. The platform supports multiple applications with different criticality levels running on shared computing infrastructure while maintaining strong isolation and temporal predictability. COSMOS provides specialized scheduler concepts including CPU resource caps and priority-based scheduling to manage computing resources efficiently.

Key Results

COSMOS successfully supported execution of multiple mixed-criticality applications with CPU resource caps preventing higher priority tasks from starving lower priority ones. The system demonstrated effective implementation of temporal partitioning with minor frame scheduling enabling guaranteed execution of critical tasks. The framework proved capable of supporting various application configurations while maintaining isolation and predictability requirements.

Full Abstract

Cite This Paper

@article{Dubey2019c,
  author = {Dubey, Abhishek and {Emfinger}, W. and {Gokhale}, A. and {Kumar}, P. and {McDermet}, D. and {Bapty}, T. and {Karsai}, G.},
  journal = {IEEE Aerospace and Electronic Systems Magazine},
  title = {Enabling Strong Isolation for Distributed Real-Time Applications in Edge Computing Scenarios},
  year = {2019},
  issn = {1557-959X},
  month = {jul},
  number = {7},
  pages = {32-45},
  volume = {34},
  abstract = {Distributed coexisting applications found in the military and space domains, which operate over managed but shared computing resources at the edge require strong isolation from each other. The state of the art for computation sharing at the edge is traditionally based on Docker and similar pseudovirtualization features. Our team has been working on an end-to-end architecture that provides strong spatial and temporal isolation similar to what has become standard in avionics communities. In this paper, we describe an open-source extension to Linux that we have designed and implemented for our distributed real-time embedded managed systems (DREMS) architecture. The key concepts are the partitioning scheduler, strong security design, and a health management interface.},
  contribution = {lead},
  doi = {10.1109/MAES.2019.2905921},
  file = {:Dubey2019c-Enabling_Strong_Isolation_for_Distributed_Real-Time_Applications_in_Edge_Computing_Scenarios.pdf:PDF},
  keywords = {mixed-criticality systems, temporal partitioning, distributed real-time systems, resource management, operating systems, safety-critical applications},
  project = {cps-middleware,cps-reliability},
  tag = {platform},
  month_numeric = {7}
}
Quick Info
Year 2019
DOI 10.1109/MAES.2019.2905921
Keywords
mixed-criticality systems temporal partitioning distributed real-time systems resource management operating systems safety-critical applications
Research Areas
CPS middleware scalable AI
Search Tags

Enabling, Strong, Isolation, Distributed, Real, Time, Applications, Edge, Computing, Scenarios, mixed-criticality systems, temporal partitioning, distributed real-time systems, resource management, operating systems, safety-critical applications, CPS, middleware, scalable AI, 2019, Dubey, Emfinger, Gokhale, Kumar, McDermet, Bapty, Karsai