We measure the distribution of lifetimes for UNIX processes and propose a functional form that fits this distribution well. We use this functional form to derive a policy for preemptive migration, and then use a trace-driven simulator to compare our proposed policy with other preemptive migration policies, and with a non-preemptive load balancing strategy. We find that, contrary to previous reports, the performance benefits of preemptive migration are significantly greater than those of non-preemptive migration, even when the memorytransfer cost is high. Using a model of migration costs representative of current systems, we find that preemptive migration reduces the mean delay (queueing and migration) by 35 -- 50%, compared to non-preemptive migration. 1 Introduction Most systems that perform load balancing use remote execution (i.e. non-preemptive migration) based on a priori knowledge of process behavior, often in the form of a list of process names eligible for migration. Althoug...

The Sprite operating system allows executing processes to be moved between hosts at any time. We use this process migration mechanism to offload work onto idle machines, and also to evict migrated processes when idle workstations are reclaimed by their owners. Sprite's migration mechanism provides a high degree of transparency both for migrated processes and for users. Transparency is ensured by managing shared data structures on a single site and redirecting operations on those structures to the host managing them. Idle machines are identified, and eviction is invoked, automatically by daemon processes. On Sprite it takes up to a few hundred milliseconds on SPARCstation 1 or DECstation 3100 workstations to perform a remote exec, while evictions typically occur in a few seconds. The pmake program uses remote invocation to invoke tasks concurrently. Compilations commonly obtain speedup factors in the range of three to six; they are limited primarily by contention for centralized resourc...

Abstract not found

Load sharing can improve performance in distributed systems by transferring work from heavily loaded nodes to lightly loaded nodes. We propose a filter component to be included in a load sharing algorithm to detect short-lived jobs not worth considering for remote execution. One filter, called History, detects short-lived jobs by using job names and statistics based on previous executions. Job traces were collected from diskless workstations connected by a local area network and supported by a distributed file system. Trace driven simulation was then used to evaluate History with respect to other filters. Two load sharing algorithms showed significant improvement of the mean job response ratio when the History filter was added. 1 Introduction In a computing environment that consists of workstations, a high-speed interprocessor communication network, and shared resources such as file servers and printers, users often observe very unsatisfactory performance. This is often due to the imb...

(or derived) decision metrics are exemplified by MinLoad, which denotes the least among all the Load values. ###################################################################################### SENDER-SIDE RULES (s) Possible-destinations = { site: Load(site) - Reference(s) < d(s) } Destination = Random(Possible-destinations) IF Load(s) - Reference(s) > q 1 (s) THEN Send RECEIVER-SIDE RULES (r) IF Load(r) < q 2 (r) THEN Receive Figure 3. The load-balancing policy considered in this thesis The sender-side rules are applied by the load-balancing software at the site of arrival (s) of a task. Reference can be either 0 or MinLoad; the other parameters --- d, q 1 , and q 2 --- take non-negative floating-point values. A remote destination (r) is chosen randomly from Destinations, a set of sites whose load index falls within a small neighborhood of Reference. If Destinations is the empty set, or if the rule for sending fails, then the task is executed locally at s, its site of arrival; ot...

Load balancing is often used to ensure that nodes in a distributed systems are equally loaded. In this paper, we showthatfor real-time systems, load balancing is not desirable. In particular,

Load-balancing systems use workload indices to dynamically schedule jobs. We present a novel method of automatically learning such indices. Our approach uses comparator neural networks, one per site, which learn to predict the relative speedup of an incoming job using only the resourceutilization patterns observed prior to the job's arrival. Our load indices combine information from the key resources of contention: CPU, disk, network, and memory. Our learning algorithm overcomes the lack of job-specific information by learning to compare the relative speedups of different sites with respect to the same job, rather than attempting to predict absolute speedups. We present conditions under which such learning is viable. Our results show that indices learnt using comparator networks correctly pick the best destination in most cases when incoming jobs are short; accuracy degrades as execution time increases. 1. INTRODUCTION This papers addresses the computation of workload measures in dis...

High-speed networks, such as ATM networks, are expected to support diverse Quality of Service (QoS) constraints, including real-time QoS guarantees. Real-time QoS is required by many applications such as those that involvevoice and video communication. To support such services, routing algorithms that allow applications to reserve the needed bandwidth over a Virtual Circuit (VC) have been proposed. Commonly, these bandwidth-reservation algorithms assign VCs to routes using the least-loaded concept, and thus result in balancing the load over the set of all candidate routes.

Abstract—Multiagent computing on a cluster of workstations is widely envisioned to be a powerful paradigm for building useful distributed applications. The agents of the system span across all the machines of a cluster. Just like the case of traditional distributed systems, load balancing becomes an area of concern. With different characteristics between ordinary processes and agents, it is both interesting and useful to investigate whether conventional load-balancing strategies are also applicable and sufficient to cope with the newly emerging needs, such as coping with temporally continuous agents, devising a performance metric for multiagent systems, and taking into account the vast amount of communication and interaction among agent. This paper discusses the above issues with reference to agent properties and load balancing techniques and outlines the space of load-balancing design choices in the arena of multiagent computing. In view of the special agent characteristics, a novel communication-based load-balancing algorithm is proposed, implemented, and evaluated. The proposed algorithm works by associating a credit value with each agent. The credit of an agent depends on its affinity to a machine, its current workload, its communication behavior, and mobility, etc. When a load imbalance occurs, the credits of all agents are examined and an agent with a lower credit value is migrated to relatively lightly loaded machine in the system. Quasi-simulated experiments of this algorithm show load-balancing improvement compared with conventional workloadoriented load-balancing schemes. Index Terms—Load balancing, distributed systems, cluster computing, multiagent computing, object-based systems, communication. 1

Abstract not found