Load Balancing a Cluster of Web Servers using Distributed Packet Rewriting

In this paper, we propose and evaluate an implementation of a prototype scalable web server. The prototype consists of a load-balanced cluster of hosts that collectively accept and service TCP connections. The host IP addresses are advertised using the Round Robin DNS technique, allowing any host to receive requests from any client. Once a client attempts to establish a TCP connection with one of the hosts, a decision is made as to whether or not the connection should be redirected to a different host---namely, the host with the lowest number of established connections. We use the low-overhead Distributed Packet Rewriting (DPR) technique to redirect TCP connections. In our prototype, each host keeps information about connections in hash tables and linked lists. Every time a packet arrives, it is examined to see if it has to be redirected or not. Load information is maintained using periodic broadcasts amongst the cluster hosts.

Cerebellar Learning in an Opponent Motor Controller for Adaptive Load Compensation and Synergy Formation

This paper shows how a minimal neural network model of the cerebellum may be embedded within a sensory-neuro-muscular control system that mimics known anatomy and physiology. With this embedding, cerebellar learning promotes load compensation while also allowing both coactivation and reciprocal inhibition of sets of antagonist muscles. In particular, we show how synaptic long term depression guided by feedback from muscle stretch receptors can lead to trans-cerebellar gain changes that are load-compensating. It is argued that the same processes help to adaptively discover multi-joint synergies. Simulations of rapid single joint rotations under load illustrates design feasibility and stability.

Anti-cholinergic load, health care utilization, and survival in people with advanced cancer: a pilot study.

INTRODUCTION: Anti-cholinergic medications have been associated with increased risks of cognitive impairment, premature mortality and increased risk of hospitalisation. Anti-cholinergic load associated with medication increases as death approaches in those with advanced cancer, yet little is known about associated adverse outcomes in this setting. METHODS: A substudy of 112 participants in a randomised control trial who had cancer and an Australia modified Karnofsky Performance Scale (AKPS) score (AKPS) of 60 or above, explored survival and health service utilisation; with anti-cholinergic load calculated using the Clinician Rated Anti-cholinergic Scale (modified version) longitudinally to death. A standardised starting point for prospectively calculating survival was an AKPS of 60 or above. RESULTS: Baseline entry to the sub-study was a mean 62 +/- 81 days (median 37, range 1-588) days before death (survival), with mean of 4.8 (median 3, SD 4.18, range 1 - 24) study assessments in this time period. Participants spent 22% of time as an inpatient. There was no significant association between anti-cholinergic score and time spent as an inpatient (adjusted for survival time) (p = 0.94); or survival time. DISCUSSION: No association between anti-cholinergic load and survival or time spent as an inpatient was seen. Future studies need to include cognitively impaired populations where the risks of symptomatic deterioration may be more substantial.

Suppression of the Hepatitis C viral load by Phyllanthus niruri extracts

Gemstone Team ANTIDOTE

Multi-touch and keyboard/mouse devices comparison in an information search task: influence on cognitive load and task engagement

Nowadays multi-touch devices (MTD) can be found in all kind of contexts. In the learning context, MTD availability leads many teachers to use them in their class room, to support the use of the devices by students, or to assume that it will enhance the learning processes. Despite the raising interest for MTD, few researches studying the impact in term of performance or the suitability of the technology for the learning context exist. However, even if the use of touch-sensitive screens rather than a mouse and keyboard seems to be the easiest and fastest way to realize common learning tasks (as for instance web surfing behaviour), we notice that the use of MTD may lead to a less favourable outcome. The complexity to generate an accurate fingers gesture and the split attention it requires (multi-tasking effect) make the use of gestures to interact with a touch-sensitive screen more difficult compared to the traditional laptop use. More precisely, it is hypothesized that efficacy and efficiency decreases, as well as the available cognitive resources making the users’ task engagement more difficult. Furthermore, the presented study takes into account the moderator effect of previous experiences with MTD. Two key factors of technology adoption theories were included in the study: familiarity and self-efficacy with the technology.Sixty university students, invited to a usability lab, are asked to perform information search tasks on an online encyclopaedia. The different tasks were created in order to execute the most commonly used mouse actions (e.g. right click, left click, scrolling, zooming, key words encoding…). Two different conditions were created: (1) MTD use and (2) laptop use (with keyboard and mouse). The cognitive load, self-efficacy, familiarity and task engagement scales were adapted to the MTD context. Furthermore, the eye-tracking measurement would offer additional information about user behaviours and their cognitive load.Our study aims to clarify some important aspects towards the usage of MTD and the added value compared to a laptop in a student learning context. More precisely, the outcomes will enhance the suitability of MTD with the processes at stakes, the role of previous knowledge in the adoption process, as well as some interesting insights into the user experience with such devices.

Exploring the benefits of using multi-touch devices in performing information search tasks: An analysis in terms of performance, cognitive load and task engagement

Over the last decade, multi-touch devices (MTD) have spread in a range of contexts. In the learning context, MTD accessibility leads more and more teachers to use them in their classroom, assuming that it will improve the learning activities. Despite a growing interest, only few studies have focused on the impacts of MTD use in terms of performance and suitability in a learning context.However, even if the use of touch-sensitive screens rather than a mouse and keyboard seems to be the easiest and fastest way to realize common learning tasks (as for instance web surfing), we notice that the use of MTD may lead to a less favorable outcome. More precisely, tasks that require users to generate complex and/or less common gestures may increase extrinsic cognitive load and impair performance, especially for intrinsically complex tasks. It is hypothesized that task and gesture complexity will affect users’ cognitive resources and decrease task efficacy and efficiency. Because MTD are supposed to be more appealing, it is assumed that it will also impact cognitive absorption. The present study also takes into account user’s prior knowledge concerning MTD use and gestures by using experience with MTD as a moderator. Sixty university students were asked to perform information search tasks on an online encyclopedia. Tasks were set up so that users had to generate the most commonly used mouse actions (e.g. left/right click, scrolling, zooming, text encoding…). Two conditions were created: MTD use and laptop use (with mouse and keyboard) in order to make a comparison between the two devices. An eye tracking device was used to measure user’s attention and cognitive load. Our study sheds light on some important aspects towards the use of MTD and the added value compared to a laptop in a student learning context.

An automatable generic strategy for dynamic load balancing in parallel structured mesh CFD codes

Parallel computing is now widely used in numerical simulation, particularly for application codes based on finite difference and finite element methods. A popular and successful technique employed to parallelize such codes onto large distributed memory systems is to partition the mesh into sub-domains that are then allocated to processors. The code then executes in parallel, using the SPMD methodology, with message passing for inter-processor interactions. In order to improve the parallel efficiency of an imbalanced structured mesh CFD code, a new dynamic load balancing (DLB) strategy has been developed in which the processor partition range limits of just one of the partitioned dimensions uses non-coincidental limits, as opposed to coincidental limits. The ‘local’ partition limit change allows greater flexibility in obtaining a balanced load distribution, as the workload increase, or decrease, on a processor is no longer restricted by the ‘global’ (coincidental) limit change. The automatic implementation of this generic DLB strategy within an existing parallel code is presented in this chapter, along with some preliminary results.

Shape-optimized mesh partitioning and load balancing for parallel adaptive FEM

We present a dynamic distributed load balancing algorithm for parallel, adaptive Finite Element simulations in which we use preconditioned Conjugate Gradient solvers based on domain-decomposition. The load balancing is designed to maintain good partition aspect ratio and we show that cut size is not always the appropriate measure in load balancing. Furthermore, we attempt to answer the question why the aspect ratio of partitions plays an important role for certain solvers. We define and rate different kinds of aspect ratio and present a new center-based partitioning method of calculating the initial distribution which implicitly optimizes this measure. During the adaptive simulation, the load balancer calculates a balancing flow using different versions of the diffusion algorithm and a variant of breadth first search. Elements to be migrated are chosen according to a cost function aiming at the optimization of subdomain shapes. Experimental results for Bramble's preconditioner and comparisons to state-of-the-art load balancers show the benefits of the construction.

Dynamic load-balancing of finite element applications with the DRAMA library

The DRAMA library, developed within the European Commission funded (ESPRIT) project DRAMA, supports dynamic load-balancing for parallel (message-passing) mesh-based applications. The target applications are those with dynamic and solution-adaptive features. The focus within the DRAMA project was on finite element simulation codes for structural mechanics. An introduction to the DRAMA library will illustrate that the very general cost model and the interface designed specifically for application requirements provide simplified and effective access to a range of parallel partitioners. The main body of the paper will demonstrate the ability to provide dynamic load-balancing for parallel FEM problems that include: adaptive meshing, re-meshing, the need for multi-phase partitioning.

Load-balancing for mesh-based applications on heterogeneous cluster computers

This paper discusses load-balancing issues when using heterogeneous cluster computers. There is a growing trend towards the use of commodity microprocessor clusters. Although today's microprocessors have reached a theoretical peak performance in the range of one GFLOPS/s, heterogeneous clusters of commodity processors are amongst the most challenging parallel systems to programme efficiently. We will outline an approach for optimising the performance of parallel mesh-based applications for heterogeneous cluster computers and present case studies with the GeoFEM code. The focus is on application cost monitoring and load balancing using the DRAMA library.

Dynamic mesh partitioning and load-balancing for parallel computational mechanics codes

In this Chapter we discuss the load-balancing issues arising in parallel mesh based computational mechanics codes for which the processor loading changes during the run. We briefly touch on geometric repartitioning ideas and then focus on different ways of using a graph both to solve the load-balancing problem and the optimisation problem, both locally and globally. We also briefly discuss whether repartitioning is always valid. Sample illustrative results are presented and we conclude that repartitioning is an attractive option if the load changes are not too dramatic and that there is a certain trade-off between partition quality and volume of data that the underlying application needs to migrate.

Load sharing in cluster service provision

The factors that are driving the development and use of grids and grid computing, such as size, dynamic features, distribution and heterogeneity, are also pushing to the forefront service quality issues. These include performance, reliability and security. Although grid middleware can address some of these issues on a wider scale, it has also become imperative to ensure adequate service provision at local level. Load sharing in clusters can contribute to the provision of a high quality service, by exploiting both static and dynamic information. This paper is concerned with the presentation of a load sharing scheme, that can satisfy grid computing requirements. It follows a proactive, non preemptive and distributed approach. Load information is gathered continuously before it is needed, and a task is allocated to the most appropriate node for execution. Performance and reliability are enhanced by the decentralised nature of the scheme and the symmetric roles of the nodes. In addition, the scheme exhibits transparency characteristics that facilitate integration with the grid.

Implementation of a proactive load sharing scheme

This paper presents a proactive approach to load sharing and describes the architecture of a scheme, Concert, based on this approach. A proactive approach is characterized by a shift of emphasis from reacting to load imbalance to avoiding its occurrence. In contrast, in a reactive load sharing scheme, activity is triggered when a processing node is either overloaded or underloaded. The main drawback of this approach is that a load imbalance is allowed to develop before costly corrective action is taken. Concert is a load sharing scheme for loosely-coupled distributed systems. Under this scheme, load and task behaviour information is collected and cached in advance of when it is needed. Concert uses Linux as a platform for development. Implemented partially in kernel space and partially in user space, it achieves transparency to users and applications whilst keeping the extent of kernel modifications to a minimum. Non-preemptive task transfers are used exclusively, motivated by lower complexity, lower overheads and faster transfers. The goal is to minimize the average response-time of tasks. Concert is compared with other schemes by considering the level of transparency it provides with respect to users, tasks and the underlying operating system.