Cluster operating system support for parallel autonomic computing

The aim of this paper is to show a general design of autonomic elements and initial implementation of a cluster operating system that moves parallel processing on clusters to the computing mainstream using the autonomic computing vision. The significance of this solution is as follows. Autonomic Computing was identified by IBM as one of computing's Grand Challenges. The human body was used to illustrate an Autonomic Computing system that possesses self-knowledge, self-configuration, self optimization, self-healing, and self-protection, knowledge of its environment and user friendliness properties. One of the areas that could benefit from the comprehensive approach created by the autonomic computing vision is parallel processing on non-dedicated clusters. Many researchers and research groups have responded positively to the challenge by initiating research around one or two of the characteristics identified by IBM as the requirements for autonomic computing. We demonstrate here that it is possible to satisfy all Autonomic Computing characteristics.

Performance evaluation of the concurrent execution of NAS parallel benchmarks with BYTE sequential benchmarks on a cluster

Computers of a non-dedicated cluster are often idle (users attend meetings, have lunch or coffee breaks) or lightly loaded (users carry out simple computations). These underutilized computers can be employed to execute parallel applications not only during weekends and at nights but also during office hours. Thus, they have to be shared by parallel and sequential applications which could lead to the improvement of their execution performance. However, there is a lack of experimental study showing the behavior and performance of parallel and sequential applications executing concurrently on clusters. We present here the result of an experimental study into load balancing based scheduling of a mixture of parallel and sequential applications on a non-dedicated cluster.

Parallel I/O scheduling in the presence of data duplication on multiprogrammed cluster computing systems

The widespread adoption of cluster computing as a high performance computing platform has seen the growth of data intensive scientific, engineering and commercial applications such as digital libraries, climate modeling, computational chemistry, computational fluid dynamics and image repositories. However, I/O subsystem performance has not been keeping pace with processor and memory performance, and is fast becoming the dominant factor in overall system performance.  Thus, parallel I/O has become a necessity in the face of performance improvements in other areas of computing systems. This paper addresses the problem of parallel I/O scheduling on cluster computing systems in the presence of data replication.  We propose two new I/O scheduling algorithms and evaluate the relative performance of the proposed policies against two existing approaches.  Simulation results show that the proposed policies perform substantially better than the baseline policies.

Multi-cluster computing interconnection network performance modeling and analysis

The overall performance of a distributed system is often depends on the effectiveness of its interconnection network. Thus, the study of the communication networks for distributed systems is very important, which is the focus of this paper. In particular, we address the problem of fat-tree based interconnection networks performance modeling for multi-user heterogeneous multi-cluster computing systems. To this end, we present an analytical model and validate the model through comprehensive simulation. The results of the simulation demonstrated that the proposed model exhibits a good degree of accuracy for various system organizations and under different working conditions.

Methods for exploring implementation variation and local context within a cluster tandomised community intervention trial

Insignificant or modest findings in intervention trials may be attributable to poorly designed or theorised interventions, poorly implemented interventions, or inadequate evaluation methods. The pre-existing context may also account for the effects observed. A combination of qualitative and quantitative methods is outlined that will permit the determination of how context level factors might modify intervention effectiveness, within a cluster randomised community intervention trial to promote the health of mothers with new babies. The methods include written and oral narratives, key informant interviews, impact logs, and inter-organisational network analyses. Context level factors, which may affect intervention uptake, success, and sustainability are the density of inter-organisational ties within communities at the start of the intervention, the centrality of the primary care agencies expected to take a lead with the intervention, the extent of context-level adaptation of the intervention, and the amount of local resources contributed by the participating agencies. Investigation of how intervention effects are modified by context is a new methodological frontier in community intervention trial research.

Numerical modeling of interactions between a macro-crack and a cluster of micro-defects

The interactions between a macro-crack and a cluster of micro-defects are studied numerically by using a series of special finite elements each containing a defect. These special finite elements, which contain defects such as holes, cracks, and inhomogeneities, are developed based on the hybrid displacement, complex potential and conformal mapping techniques. These hybrid-type elements can be used together with the conventional finite elements without any difficulty. Thus, simple finite element models can be devised to study the interactions between a macro-crack and a cluster of micro-defects. In this paper, the mathematical and finite element modeling procedures for the study of the above-mentioned problems are presented.

Patient engagement and coaching for health: the PEACH study- a cluster randomised controlled trial using the telephone to coach people with type 2 diabetes to engage with their GPs to improve diabetes care: a study protocol.

Background
The PEACH study is based on an innovative 'telephone coaching' program that has been used effectively in a post cardiac event trial. This intervention will be tested in a General Practice setting in a pragmatic trial using existing Practice Nurses (PN) as coaches for people with type 2 diabetes (T2D). Actual clinical care often fails to achieve standards, that are based on evidence that self-management interventions (educational and psychological) and intensive pharmacotherapy improve diabetes control. Telephone coaching in our study focuses on both. This paper describes our study protocol, which aims to test whether goal focused telephone coaching in T2D can improve diabetes control and reduce the treatment gap between guideline based standards and actual clinical practice.
Methods/design
In a cluster randomised controlled trial, general practices employing Practice Nurses (PNs) are randomly allocated to an intervention or control group. We aim to recruit 546 patients with poorly controlled T2D (HbA1c >7.5%) from 42 General Practices that employ PNs in Melbourne, Australia. PNs from General Practices allocated to the intervention group will be trained in diabetes telephone coaching focusing on biochemical targets addressing both patient self-management and engaging patients to work with their General Practitioners (GPs) to intensify pharmacological treatment according to the study clinical protocol. Patients of intervention group practices will receive 8 telephone coaching sessions and one face-to-face coaching session from existing PNs over 18 months plus usual care and outcomes will be compared to the control group, who will only receive only usual care from their GPs. The primary outcome is HbA1c levels and secondary outcomes include cardiovascular disease risk factors, behavioral risk factors and process of care measures.
Discussion
Understanding how to achieve comprehensive treatment of T2D in a General Practice setting is the focus of the PEACH study. This study explores the potential role for PNs to help reduce the treatment and outcomes gap in people with T2D by using telephone coaching. The intervention, if found to be effective, has potential to be sustained and embedded within real world General Practice.

Improving infant sleep and maternal mental health: a cluster randomised trial

Objectives: To determine whether a community-delivered intervention targeting infant sleep problems improves infant sleep and maternal well-being and to report the costs of this approach to the healthcare system.

Design: Cluster randomised trial.

Setting: 49 Maternal and Child Health (MCH) centres (clusters) in Melbourne, Australia.

Participants: 328 mothers reporting an infant sleep problem at 7 months recruited during October–November 2003.

Intervention: Behavioural strategies delivered over individual structured MCH consultations versus usual care.

Main outcome measures: Maternal report of infant sleep problem, depression symptoms (Edinburgh Postnatal Depression Scale (EPDS)), and SF-12 mental and physical health scores when infants were 10 and 12 months old. Costs included MCH sleep consultations, other healthcare services and intervention costs.

Results: Prevalence of infant sleep problems was lower in the intervention than control group at 10 months (56% vs 68%; adjusted OR 0.58 (95% CI: 0.36 to 0.94)) and 12 months (39% vs 55%; adjusted OR 0.50 (0.31 to 0.80)). EPDS scores indicated less depression at 10 months (adjusted mean difference –1.4 (–2.3 to –0.4) and 12 months (–1.7 (–2.6 to –0.7)). SF-12 mental health scores indicated better health at 10 months (adjusted mean difference 3.7 (1.5 to 5.8)) and 12 months (3.9 (1.8 to 6.1)). Total mean costs including intervention design, delivery and use of non-MCH nurse services were £96.93 and £116.79 per intervention and control family, respectively.

Conclusions: Implementing this sleep intervention may lead to health gains for infants and mothers and resource savings for the healthcare system.

The performance of a parallel TSP program and byte sequential benchmarks executing on a shared cluster

Although individual PCs of a cluster are used by their owners to run sequential applications (local jobs), the cluster as a whole or its subset can also be employed to run parallel applications (cluster jobs) even during working hours. This implies that these computers have to be shared by parallel and sequential applications, which could lead to the improvement of the execution performance and resource utilization. However, there is a lack of experimental study showing the behavior and performance of executing parallel and sequential applications concurrently on a non-dedicated cluster. The result of such research would be beneficial for the development of new global scheduling algorithms. We present the result of an experimental study into scheduling of a mixture of parallel and sequential applications on a non-dedicated cluster. The aim of this study is to learn how the concurrent execution of a communication intensive parallel application and sequential applications influences their execution performance and utilization of the cluster.

Analytical modeling of interconnection networks in heterogeneous multi-cluster systems

In data-intensive distributed systems, replication is the most widely used approach to offer high data availability, low bandwidth consumption, increased fault-tolerance and improved scalability of the overall system. Replication-based systems implement replica control protocols that enforce a specified semantics of accessing the data. Also, the performance depends on a number of factors, the chief of which is the protocol used to maintain consistency among object replica. In this paper, we propose a new low-cost and high data availability protocol called the box-shaped grid structure for maintaining consistency of replicated data on networked distributed computing systems. We show that the proposed protocol provides high data availability, low communication costs, and increased fault-tolerance as compared to the baseline replica control protocols.

Does interpersonal psychotherapy improve clinical care for adolescents with depression attending a rural child and adolescent mental health service? Study protocol for a cluster randomised feasibility trial

Background: Depression amongst adolescents is a costly societal problem. Little research documents the effectiveness of public mental health services in mapping this problem. Further, it is not clear whether usual care in such services can be improved via clinician training in a relevant evidence based intervention. One such intervention, found to be effective and easily learned amongst novice clinicians, is Interpersonal Psychotherapy (IPT). The study described in the current paper has two main objectives. First, it aims to investigate the impact on clinical care of implementing Interpersonal Psychotherapy for Adolescents for the treatment of adolescent depression within a rural mental health service compared with Treatment as Usual (TAU). The second objective is to record the process and challenges (i.e. feasibility, acceptability, sustainability) associated with implementing and evaluating an evidence-based intervention within a community service. This paper outlines the study rationale and design for this community based research trial.

Methods/design: The study involves a cluster randomisation trial to be conducted within a Child and Adolescent Mental Health Service in rural Australia. All clinicians in the service will be invited to participate.  Participating clinicians will be randomised via block design at each of four sites to (a) training and delivery of IPT, or (b) TAU. The primary measure of impact on care will be a clinically significant change in depressive  symptomatology, with secondary outcomes involving treatment satisfaction and changes in other symptomatology. Participating adolescents with significant depressive symptomatology, aged 12 to 18 years, will complete assessment measures at Weeks 0, 12 and 24 of treatment. They will also complete a depression inventory once a month during that period. This study aims to recruit 60 adolescent participants and their parent/guardian/s. A power analysis is not indicated as an intra-class correlation coefficient will be calculated and used to inform sample size calculations for subsequent large-scale trials. Qualitative data regarding process implementation will be collected quarterly from focus groups with participating clinicians over 18 months, plus phone interviews with participating adolescents and parent/guardians at 12 weeks and 24 weeks of treatment. The focus group qualitative data will be analysed using a Fourth Generation Evaluation methodology that includes a constant comparative cyclic analysis method.

Discussion: This study protocol will be informative for researchers and clinicians interested in considering, designing and/or conducting cluster randomised trials within community practice such as mental health services.

Smart cluster bombs - control of multi-agent systems for military applications

This paper introduces an aggregation algorithm for airborne swarming guided weapon systems, which can aggregate munitions into a given shape while reaching the surface. The algorithm uses an artificial force based controller to navigate the members of the swarm into the desired geographical position and evenly distribute them inside the shape. Inter-member repulsion forces are used to avoid collisions among members, which is crucial for a weapon deployment system. Moreover, a lower bound for the release height was obtained which guarantee convergence of the complete weapon system into the target area. The proposed swarming guided weapon system was tested using computer simulations.

The design and implementation of an active replication scheme for distributing services in a cluster of workstations

Replication is the key to providing high availability, fault tolerance, and enhanced performance in a cluster of workstations (COWs). However, building such a system remains as a difficult and challenging task, mainly due to the difficulty of maintaining data consistency among replicas and the lack of easy and efficient tools supporting the development procedure. In this paper we propose an active replication scheme in which data consistency can be maintained. Based on the active replication scheme, we present an object-oriented design pattern and a constructing tool to simplify the design and implementation of service replications in COWs.

Optimal multicast tree routing for cluster computing in hypercube interconnection networks

Cluster computation has been used in the applications that demand performance, reliability, and availability, such as cluster server groups, large-scale scientific computations, distributed databases, distributed media-on-demand servers and search engines etc. In those applications, multicast can play the vital roles for the information dissemination among groups of servers and users. This paper proposes a set of novel efficient fault-tolerant multicast routing algorithms on hypercube interconnection of cluster computers using multicast shared tree approach. We present some new algorithms for selecting an optimal core (root) and constructing the shared tree so as to minimize the average delay for multicast messages. Simulation results indicate that our algorithms are efficient in the senses of short end-to-end average delay, load balance and less resource utilizations over hypercube cluster interconnection networks.