In order to be able to take full advantage of a distributed computing facility it is important not only to distribute the hardware but also to distribute the control of these resources. However, distributed control is very different from centralized control since at any time, several processes or several controllers may observe different and inconsistent views of the global system state. The task of scheduling jobs in a distributed system must also be done Without full knowledge of the system state. In this correspondence we define a totally new distributed scheduling algorithm LP (linear predictive). scheduling, which not only implements distributed control of task scheduling but is also able to adapt itself to workload fluctuations. Using a general-purpose distributed system simulator we have shown the performance rnitince advantages of this new algorithm.

article Free Access Share on An architecture for high volume transaction processing Authors: Robert W. Horst Tandem Computers Incorporated - 19333 Vallco Parkway - Cupertino, CA Tandem Computers Incorporated - 19333 Vallco Parkway - Cupertino, CAView Profile , Timothy C. K. Chou Tandem Computers Incorporated - 19333 Vallco Parkway - Cupertino, CA Tandem Computers Incorporated - 19333 Vallco Parkway - Cupertino, CAView Profile Authors Info & Claims ACM SIGARCH Computer Architecture NewsVolume 13Issue 3June 1985 pp 240–245https://doi.org/10.1145/327070.327226Published:01 June 1985Publication History 10citation459DownloadsMetricsTotal Citations10Total Downloads459Last 12 Months100Last 6 weeks25 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

In order to implement a distributed system with fail-soft capabilities it is necessary to specify algorithms which redistribute the work load of a failed processor to the remaining good processors. This paper develops a general model to analyze the behavior of these algorithms in a distributed system. Such algorithms should be used with caution as they have the capability of making the entire system Unstable. By unstable we mean that if a processor fails, and its workload is redistributed, then the increased workload directed towards the rest of the system could drive one or more of the processors into overload resulting in a serious degradation of system performance. Using the general model we have studied a class of load redistribution algorithms which use various techniques to redistribute workload. These techniques include: buffering jobs arriving to the failed processor, transmitting only the jobs in the queue of the failed processor, and rerouting all jobs around the failed processor. For this class of algorithms we have derived closed form expressions for the performance of the system as a function of job arrival rate, job service rate, processor failure rate, and processor service rate. In addition, we have defined a criterion which, if adhered to, will guarantee system stability in the event of failure.

In a distributed computing system made up of different types of processors each processor in the system may have different performance and reliability characteristics. In order to take advantage of this diversity of processing power, a modular distributed program should have its modules assigned in such a way that the applicable system performance index, such as execution time or cost, is optimized. This paper describes an algorithm for making an optimal module to processor assignment for a given performance criteria. We first propose a computational model to characterize distributed programs, consisting of tasks and an operational precedence relationship. This model alows us to describe probabilistic branching as well as concurrent execution in a distributed program. The computational model along with a set of seven program descriptors completely specifies a model for dynamic execution of a program on a distributed system. The optimal task to processor assignment is found by an algorithm based on results in Markov decision theory. The algorithm given in this paper is completely general and applicable to N-processor systems.