Emerging high-speed networks will allow machines to access remote data nearly as quickly as they can access local data. This trend motivates the use of cooperative caching: coordinating the file caches of many machines distributed on a LAN to form a more effective overall file cache. In this paper we examine four cooperative caching algorithms using a trace-driven simulation study. These simulations indicate that for the systems studied cooperative caching can halve the number of disk accesses, improving file system read response time by as much as 73%. Based on these simulations we conclude that cooperative caching can significantly improve file system read response time and that relatively simple cooperative caching algorithms are sufficient to realize most of the potential performance gain.

This paper examines the plausibility of using a network of workstations (NOW) for a mixture of parallel and sequential jobs. Through simulations, our study examines issues that arise when combining these two workloads on a single platform. Starting from a dedicated NOW just for parallel programs, we incrementally relax uniprogramming restrictions until we have a multi-programmed, multi-user NOW for both interactive sequential users and parallel programs. We show that a number of issues associated with the distributed NOW environment (e.g., daemon activity, coscheduling skew) can have a small but noticeable effect on parallel program performance. We also find that efficient migration to idle workstations is necessary to maintain acceptable parallel application performance. Furthermore, we present a methodology for deriving an optimal delay time for recruiting idle machines for use by parallel programs; this recruitment threshold was just 3 minutes for the research cluster we measured. ...

It has been reported [26] that life holds but two certainties, death and taxes. And indeed, despite much effort devoted to circumventing both phenomena, it does appear that any society—and in the context of this paper, any large-scale distributed system—must address both death (failure) and the establishment and maintenance of infrastructure (which we assert is a major motivation for taxes, so as to

In this paper, we examine the utility of exploiting idle workstations for parallel computation. We attempt to answer the following questions. First, given a workstation pool, for what fraction of time can we expect to find a cluster of k workstations available? This provides an estimate of the opportunity for parallel computation. Second, how stable is a cluster of free machines and how does the stability vary with the size of the cluster? This indicates how frequently a parallel computation might have to stop for adapting to changes in processor availability. Third, what is the distribution of workstation idle-times? This information is useful for selecting workstations to place computation on. Fourth, how much benefit can a user expect? To state this in concrete terms, if I have a pool of size S, how big a parallel machine should I expect to get for free by harvesting idle machines. Finally, how much benefit can be achieved on a real machine and how hard does a parallel programmer ha...

In every production parallel processing environment, the set of resources potentially available to an application fluctuate due to changes in the load on the system. This is true for clusters of workstations which are an increasingly popular platform for parallel computing. Today's parallel programming environments have largely succeeded in making the communication aspect of parallel programming much easier, but they have not provided adequate resource management services which are needed to adapt to such changes in availability. To fill this need, we have developed CARMI, a resource management system, aimed at allowing a parallel application to make use of all available computing power. CARMI permits an application to grow as new resources become available, and shrink when resources are reclaimed. Building upon CARMI, we have also developed WoDi which provides a simple interface for writing master-workers programs in a dynamic resource environment. Both CARMI and WoDi are operational,...

Scheduling algorithms that use application and system knowledge have been shown to be more effective at scheduling parallel jobs on a multiprocessor than algorithms that do not. This paper focuses on obtaining such information for use by a scheduler in a network of workstations environment. The log files from three parallel systems are examined to determine both how to categorize parallel jobs for storage in a job database and what job information would be useful to a scheduler. A Historical Profiler is proposed that stores information about programs and users, and manipulates this information to provide schedulers with execution time predictions. Several preemptive and non-preemptive versions of the FCFS, EASY and Least Work First scheduling algorithms are compared to evaluate the utility of the profiler. It is found that both preemption and the use of application execution time predictions obtained from the Historical Profiler lead to improved performance.

This paper evaluates linear models for predicting the Digital Unix five-second host load average from 1 to 30 seconds into the future. A detailed statistical study of a large number of long, fine grain load traces from a variety of real machines leads to consideration of the Box-Jenkins models (AR, MA, ARMA, ARIMA), and the ARFIMA models (due to self-similarity.) We also consider a simple windowed-mean model. The computational requirements of these models span a wide range, making some more practical than others for incorporation into an online prediction system. We rigorously evaluate the predictive power of the models by running a large number of randomized testcases on the load traces and then data-mining their results. The main conclusions are that load is consistently predictable to a very useful degree, and that the simple, practical models such as AR are sufficient for host load prediction. We recommend AR(16) models or better for host load prediction. We implement an online host load prediction system around the AR(16) model and evaluate its overhead, finding that it uses miniscule amounts of CPU time and network bandwidth

In this thesis, we formalize the concept of an implicitly-controlled system, also referred to as an implicit system. In an implicit system, cooperating components do not explicitly contact other components for control or state information; instead, components infer remote state by observing naturally-occurring local events and their corresponding implicit information, i.e., information available outside of a defined interface. Many systems, particularly in distributed and networked environments, have leveraged implicit control to simplify the implementation of services with autonomous components. To concretely demonstrate the advantages of implicit control, we propose and implement implicit coscheduling, an algorithm for dynamically coordinating the time...

This paper evaluates linear models for predicting the Digital Unix five-second load average from 1 to 30 seconds into the future. A detailed statistical study of a large number of load traces leads to consideration of the Box-Jenkins models (AR, MA, ARMA, ARIMA), and the ARFIMA models (due to self-similarity.) These models, as well as a simple windowed-mean scheme, are evaluated by running a large number of randomized testcases on the load traces. The main conclusions are that load is consistently predictable to a useful degree, and that the simpler models such as AR are sufficient for doing this prediction.

Abstract not found