Advanced

Hard real-time guarantees in feedback-based resource reservations

Papadopoulos, Alessandro Vittorio LU ; Maggio, Martina LU ; Leva, Alberto and Bini, Enrico LU (2015) In Real-Time Systems 51(3). p.221-246
Abstract
Resource reservation is a technique that allows isolating applications from interfering among each other. In the most classic setting, this method requires the periodic allocation of a given budget of resource over time. However, in reality, the actual budget allocation may deviate from its ideal value. Examples of causes of this deviation are: the presence of a system tick, the usage of shared resources, the self-blocking on I/O operations, etc. Since control techniques are an effective mean to deal with uncertainties and disturbances, unknown at design time but bounded, in this paper we propose to use feedback to achieve the target budget allocation, which may have deviated due to on-line events. The proposed scheme, called Self-Adaptive... (More)
Resource reservation is a technique that allows isolating applications from interfering among each other. In the most classic setting, this method requires the periodic allocation of a given budget of resource over time. However, in reality, the actual budget allocation may deviate from its ideal value. Examples of causes of this deviation are: the presence of a system tick, the usage of shared resources, the self-blocking on I/O operations, etc. Since control techniques are an effective mean to deal with uncertainties and disturbances, unknown at design time but bounded, in this paper we propose to use feedback to achieve the target budget allocation, which may have deviated due to on-line events. The proposed scheme, called Self-Adaptive Server (SAS), is described and analyzed. We prove that the controller gain, which maximizes the resource delivered to the application, is (3−sqrt(5))/2. We also implemented the scheduler on a lightweight operating system for a microcontroller. Thanks to the extremely simple implementation, SAS servers are well suited for low-overhead resource isolation mechanisms with proved real-time guarantees. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Real-Time Systems
volume
51
issue
3
pages
221 - 246
publisher
Kluwer
external identifiers
  • wos:000355766400001
  • scopus:84930484171
ISSN
1573-1383
DOI
10.1007/s11241-015-9224-1
language
English
LU publication?
yes
id
10a72809-90c5-4165-b090-0c17c53a59be (old id 5276005)
date added to LUP
2015-04-17 11:14:16
date last changed
2017-01-01 03:13:07
@article{10a72809-90c5-4165-b090-0c17c53a59be,
  abstract     = {Resource reservation is a technique that allows isolating applications from interfering among each other. In the most classic setting, this method requires the periodic allocation of a given budget of resource over time. However, in reality, the actual budget allocation may deviate from its ideal value. Examples of causes of this deviation are: the presence of a system tick, the usage of shared resources, the self-blocking on I/O operations, etc. Since control techniques are an effective mean to deal with uncertainties and disturbances, unknown at design time but bounded, in this paper we propose to use feedback to achieve the target budget allocation, which may have deviated due to on-line events. The proposed scheme, called Self-Adaptive Server (SAS), is described and analyzed. We prove that the controller gain, which maximizes the resource delivered to the application, is (3−sqrt(5))/2. We also implemented the scheduler on a lightweight operating system for a microcontroller. Thanks to the extremely simple implementation, SAS servers are well suited for low-overhead resource isolation mechanisms with proved real-time guarantees.},
  author       = {Papadopoulos, Alessandro Vittorio and Maggio, Martina and Leva, Alberto and Bini, Enrico},
  issn         = {1573-1383},
  language     = {eng},
  number       = {3},
  pages        = {221--246},
  publisher    = {Kluwer},
  series       = {Real-Time Systems},
  title        = {Hard real-time guarantees in feedback-based resource reservations},
  url          = {http://dx.doi.org/10.1007/s11241-015-9224-1},
  volume       = {51},
  year         = {2015},
}