License: Creative Commons Attribution 3.0 Unported license (CC BY 3.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.ECRTS.2020.1
URN: urn:nbn:de:0030-drops-123648
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2020/12364/
Go to the corresponding LIPIcs Volume Portal

Schwäricke, Gero ; Kloda, Tomasz ; Gracioli, Giovani ; Bertogna, Marko ; Caccamo, Marco

Fixed-Priority Memory-Centric Scheduler for COTS-Based Multiprocessors

pdf-format:
LIPIcs-ECRTS-2020-1.pdf (0.6 MB)

Abstract

Memory-centric scheduling attempts to guarantee temporal predictability on commercial-off-the-shelf (COTS) multiprocessor systems to exploit their high performance for real-time applications. Several solutions proposed in the real-time literature have hardware requirements that are not easily satisfied by modern COTS platforms, like hardware support for strict memory partitioning or the presence of scratchpads. However, even without said hardware support, it is possible to design an efficient memory-centric scheduler.
In this article, we design, implement, and analyze a memory-centric scheduler for deterministic memory management on COTS multiprocessor platforms without any hardware support. Our approach uses fixed-priority scheduling and proposes a global "memory preemption" scheme to boost real-time schedulability. The proposed scheduling protocol is implemented in the Jailhouse hypervisor and Erika real-time kernel. Measurements of the scheduler overhead demonstrate the applicability of the proposed approach, and schedulability experiments show a 20% gain in terms of schedulability when compared to contention-based and static fair-share approaches.

BibTeX - Entry

@InProceedings{schwricke_et_al:LIPIcs:2020:12364,
  author =	{Gero Schw{\"a}ricke and Tomasz Kloda and Giovani Gracioli and Marko Bertogna and Marco Caccamo},
  title =	{{Fixed-Priority Memory-Centric Scheduler for COTS-Based Multiprocessors}},
  booktitle =	{32nd Euromicro Conference on Real-Time Systems (ECRTS 2020)},
  pages =	{1:1--1:24},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-152-8},
  ISSN =	{1868-8969},
  year =	{2020},
  volume =	{165},
  editor =	{Marcus V{\"o}lp},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2020/12364},
  URN =		{urn:nbn:de:0030-drops-123648},
  doi =		{10.4230/LIPIcs.ECRTS.2020.1},
  annote =	{Keywords: Schedulability Analysis, Scheduler Implementation, memory-centric Scheduling, Virtualization, Multiprocessor}
}

Keywords: Schedulability Analysis, Scheduler Implementation, memory-centric Scheduling, Virtualization, Multiprocessor
Collection: 32nd Euromicro Conference on Real-Time Systems (ECRTS 2020)
Issue Date: 2020
Date of publication: 30.06.2020

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI