You are here: Home / RTLWS 1999-2017 / RTLWS Submitted Papers / 
2022-07-05 - 11:17

Dates and Events:

OSADL Articles:

2022-01-13 12:00

Phase #3 of OSADL project on OPC UA PubSub over TSN successfully completed

Another important milestone on the way to interoperable Open Source real-time Ethernet has been reached


2021-02-09 12:00

Open Source OPC UA PubSub over TSN project phase #3 launched

Letter of Intent with call for participation is now available


2016-11-12 12:00

Raspberry Pi and real-time Linux

Let's have a look at the OSADL QA Farm data


2016-09-17 12:00

Preemption latency of real-time Linux systems

How to measure it – and how to fix it, if it's too high?



Real Time Linux Workshops

1999 - 2000 - 2001 - 2002 - 2003 - 2004 - 2005 - 2006 - 2007 - 2008 - 2009 - 2010 - 2011 - 2012 - 2013 - 2014 - 2015

Twelfth Real-Time Linux Workshop on October 25 to 27, in Nairobi, Kenya

A Latency Model of Linux 2.6 for Digital Signal Processing in Real Time

Sergio A. Rodríguez and Phillip M. S. Burt, Escola Politécnica, University of São Paulo, Brazil

This paper develops a new qualitative latency model of the Linux 2.6 OS for the Intel x86 architecture. The proposed model analyses aspects related to digital signal processing in real time. In this context, the study identifies all latency sources since the arrival of a signal sample (or block of samples) up to the execution of the first instruction related to processing that sample. The interrupt latency is divided into seven components, including hardware latency sources such as microprocessor operation and interrupt controller queue. The dispatch latency is divided into six components, adding new components such as interrupts stack latency and deferrable functions latency to the known sources such as scheduler latency and switch context latency. The paper also identifies further overhead sources such as memory allocation by demand paging. Finally, some of the new latency components are measured using an instrumented kernel. The measures are obtained with and without computational load for the purpose of analyzing its influence in the latency components.