The Community for Technology Leaders
Green Image
<p><b>Abstract</b>—We rigorously analyze load sharing (LS) in a distributed real-time system, called HARTS (Hexagonal Architecture for Real-Time Systems), while considering LS-related communication activities, such as task transfers and state-change broadcasts.</p><p>First, we give an overview of the general distributed real-time LS approach described in [<ref rid="bibl07241" type="bib">1</ref>], [<ref rid="bibl07242" type="bib">2</ref>], and then adapt it to HARTS by exploiting the topological properties of HARTS. Second, we model task arrival/completion/transfer activities in HARTS as a continuous-time Markov chain from which we derive the distribution of queue length and the rate of generating LS-related traffic—task transfer-out rate and state-region change broadcast rate. Third, we derive the distribution of packet delivery time as a function of LS-related traffic rates by characterizing the hexagonal mesh topology and the virtual cut-through capability of HARTS. Finally, we derive the distribution of task waiting time (the time a task is queued for execution plus the time it would spend if the task is to be transferred), from which the probability of a task failing to complete in time, called the <it>probability of dynamic failure</it>, can be computed.</p><p>The results obtained from our analytic models are verified through event-driven simulations, and can be used to study the effects of varying various design parameters on the performance of LS while considering the details of LS-related communication activities.</p>
Dynamic failure, distributed real-time systems, wrapped hexagonal mesh, virtual cut-through, point-to-point broadcasts, adaptive load sharing, queuing models, performance analysis.
Kang G. Shin, Chao-Ju Hou, "Evaluation of Load Sharing in HARTS with Consideration of Its Communication Activities", IEEE Transactions on Parallel & Distributed Systems, vol. 7, no. , pp. 724-739, July 1996, doi:10.1109/71.508252
93 ms
(Ver 3.3 (11022016))