Dynamic Load-Sharing Using Predicted Process Resource Requirements
Kumar K. Goswami, Ravishankar K. Iyer · NASA STI Repository (National Aeronautics and Space Administration) · 1990
Continue on reverse if necessary a n d identify by block number)distributed systems, load sharing, s t a t is t ic a l clustering resource prediction, dynamic scheduling and trace-driven qimulatinn 19.ABSTRACT (Continue o n reverse if necessary a n d identify by block num ber) Ï In the paper, heuristics which use predicted process resource requirements to make scheduling decisions are proposed.Four heuristics are presented.The first two, MINQ and SMPL, employ centralized scheduling and the remaining two, DMINQ and FDMINQ, use distributed scheduling.These heuristics are first compared against random scheduling and then against two conventional heuristics, CENTEX and DISTED, which schedule processes solely based on system state information.Results based on trace-driven simulations show that the proposed centralized heuristics offer significantly improved mean response times and, they require fewer status update messages.In experiments using the same status update rates, SMPL response times were, on the average, 22% lower than those for CENTEX and, MINQ response times were, on the average, 18% lower.The simulations also showed that MINQ and SMPL can perform as well as, or better than, CENTEX while using up to 70% fewer status update messages.The use of fewer status update messages imposes less overhead on the system.The use of prediction for distributed scheduling produced similar results.When prediction was used to filter small processes and execute them locally a 50% improvement in response times was obtained.