EVALUATION OF LOAD SHARING IN HARTS WITH CONSIDERATION OF ITS COMMUNICATION ACTIVITIES

We rigorously analyze load sharing (LS) in a distributed real-time sys tem, called HARTS (Hexagonal Architecture for Real-Time Systems), whil e considering LS-related communication activities, such as task transf ers and state-change broadcasts. First, we give an overview of the gen eral distributed real-time LS approach described in [1], [2], 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 distributio n of queue length and the rate of generating LS-related traffic-task t ransfer-out rate and state-region change broadcast rate. Third, we der ive the distribution of packet delivery time as a function of LS-relat ed traffic rates by characterizing the hexagonal mesh topology and the virtual cut-through capability of HARTS. Finally, we derive the distr ibution 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 w hich the probability of a task failing to complete in time, called the probability of dynamic failure, can be computed. The results obtained from our analytic models are verified through event-driven simulation s, and can be used to study the effects of varying various design para meters on the performance of LS while considering the details of LS-re lated communication activities.