HARTOS: a distributed real-time operating system

Abstract

This paper outlines the design objectives and research goals for HARTOS, a distributed real-time operating system being developed at The University of Michigan. This effort is part of a larger research project to design and implement an experimental distributed real-time system called the Hexagonal Architecture for Real-Time Systems (HARTS). An important feature of HARTS is the use of an intelligent network processor to handle many of the functions relating to communications. The paper focuses on the communications aspects of the operating system and the control software kernel of the network processor. The preliminary version of the kernel provides good support for inter-process communication and distributed control. Its performance has been measured and analyzed and found to be comparable to that of other message passing systems like the V system.

Statistical real-time channels on multiaccess bus networks

“…In our scheme, although the MTRT is defined to be the maximum time interval between two consecutive token allocations, it is approximately the same as the corresponding expected time, as the variance of actual token return time is negligibly small if MTRT >> RTHT (holds in most cases when the network is expected to support many real-time channels). Among the several models proposed to describe the traffic generated by a real-time channel, the linear bounded model-which was originally proposed by Cruz [8] and also adopted by other researchers [13], [14], [27]-is one of the most popular models. The traffic generated by a real-time channel is said to follow the linear bounded model if the number of packets generated in any interval T is bounded by a linear function of the interval length T, G max T + B max , where G max is the maximum packet-generation rate of this channel and B max is the maximum burst size.…”

“…The traffic generated by a real-time channel is said to follow the linear bounded model if the number of packets generated in any interval T is bounded by a linear function of the interval length T, G max T + B max , where G max is the maximum packet-generation rate of this channel and B max is the maximum burst size. Using the user-specified delivery-delay bound D, one can establish a hard real-time channel in a point-to-point network [13], [14], [27]. Here we adopt an even simpler model which requires only two parameters for establishing hard real-time channels:…”

“…Several researchers investigated the problem of supporting real-time communication with performance guarantees for given worst-case input traffic characteristics in wide-area point-to-point networks [9], [12], [13], [14], [23], [27]. Among these, the concept of "real-time channel" proposed by Ferrari and Verma [9], and refined by Kandlur, Shin, and Ferrari [13], is the most notable in explicitly addressing the problem of meeting delivery deadlines in wide-area point-to-point networks.…”

Uma arquitetura de nuvem em comunidade para aplicações de tempo real.

“…HARTOS is a distributed real-time operating system which was part of a larger research project developed at the University of Michigan called the Hexagonal Architecture for Real-Time Systems (HARTS) [KANDLUR, KISKIS and SHIN 1989]. An important aspect of this work is the attention given to network communications, whereas dedicated communication processors were employed while the distributed kernel were executed on dedicated application processors [KANDLUR, KISKIS and SHIN 1989].…”

“…An important aspect of this work is the attention given to network communications, whereas dedicated communication processors were employed while the distributed kernel were executed on dedicated application processors [KANDLUR, KISKIS and SHIN 1989]. Messages were delivered within a bounded time, with deadlines defined on both a hop-by-hop and end-to-end basis.…”