A New Load Balancing Scheduling Algorithm Based on Linux Virtual Server

As the large amount of video surveillance data floods into cloud data center, achieving load balancing in a cloud network has become a challenging problem. Meanwhile, we hope the cloud data center maintains low latency, low consumption, and high throughput performance when transmitting massive amounts of data. OpenFlow enables a software-defined solution through programing to control the scheduling of data flow in the cloud data center. However, the existing scheduling algorithm of the data center cannot cope with the congestion of the network center effectively. Even for some dynamic scheduling algorithms, adjustments can only be made after congestion occurs. Hence, we propose a proactive and dynamically adjusted mixed-flow load-balanced scheduling (MFLBS) algorithm, which not only takes into account the different sizes of flows in the network but also maintains maximum throughput while balancing the load. In this paper, the MFLBS problem was formulated, along with a set of heuristic algorithms for real-time feedback and adjustment. Experiments with mesh and tree network models show that our MFLBS is significantly better than other dynamic scheduling algorithms, including one-hop DLBS and static scheduling algorithm FCFS. The MFLBS algorithm can effectively reduce the delay of small flows and average delay while maintaining high throughput.

Dear SCPE Reader, We present a selection of papers which are extensions of papers presented at the 7-th International Symposium on Parallel and Distributed Computing, 1–5 July 2008, in Krakow, Poland. The motivation for publishing the selection in the SCPE Journal was, on the one hand, to present the flavour of the research reported at the conference and on the other hand to present some of the most relevant topics currently focused on the research on parallel and distributed computing in general. The selection contains only 6 papers out of about 60 presented at the conference, and thus, is far from covering all relevant topics represented at the ISPDC 2008. This is because not all of the invited authors were patient enough to accept a fairly long paper publishing process. Nevertheless, we hope that the presented papers will bring you closer to the research covered by the ISPDC conferences and will encourage you to participate in future ISPDC editions. The first paper ``The Impact of Workload Variability on Load Balancing Algorithms'' is by Marta Beltran and Antonio Guzman from King Juan Carlos University in Spain. It concerns an important topic of load balancing in cluster systems, namely adaptativity of the load balancing algorithms to changes of the workload in the system. Adequate accounting for additional load in the hosting system is of great relevance for correct optimization effects. The paper presents a thorough formal analysis of the workload variability metrics and their influence on the quality of load balancing algorithms. Four basic activities appearing in load balancing algorithms are identified, and based on them some algorithmic solutions are proposed to correctly deal with workload variability in system load balancing. The problem of dynamic load balancing algorithms robustness has been discussed. Two different robustness metrics sensitive to the applied type of opimization: local task-oriented or a global one enable selecting task remote execution or migration as load balancing operations. The proposed approach is illustrated with experiments. The second paper ``Model-Driven Engineering and Formal Validation of High-Performance Embedded Systems'' is by Abdoulaye Gamatie, Eric Rutten, Huafeng Yu, Pierre Boulet, Jean-Luc Dekeyser, from University of Lille and INRIA in France. The paper is concerned with a very advanced methodology of designing correct parallel embedded systems for intensive data-parallel computing. In their previous research, the authors of the paper designed the GASPARD embedded system design framework. It is based on the hardware/software co-design approach through model-driven engineering. The framework is based on an UML-like model specification language in which hardware and software elements are modelled using a component approach with special mechanisms for repetitive structures. This paper tries to combine the modelling framework of GASPARD with the mechanisms of synchronous languages to achieve design verifiability provided for such languages. The paper shows how GASPARD models can be translated into synchronous models based on data flow equations in order to formally check their correctness. The proposed approach is illustrated with an example of a video processing system. The third paper ``Relations Between Several Parallel Computational Models'' is by Stephan Bruda and Yuanqiao Zhang from Bishop’s University in Canada. The paper is concerned with theoretical aspects of shared memory systems described by the parallel random access machine PRAM model and aims in studying performance properties of different types of PRAM systems. The attention is focussed on analysing the computational power of two more sophisticated PRAM models (Combining CRCW and Broadcast Selective Reduction), which include data reduction in case of concurrent writes. The paper shows that these two models have equivalent computational power, which is a new result comparing the existing literature. The performance of both models applied to reconfigurable multiple bus machines was studied as a possible architectural solution for current VLSI processor implementations. It was shown that in such systems under reasonable assumptions concurrent-write does not enhance performance comparing the exclusive-write model. Another result important for the VLSI technology is that the Combining CRCW PRAM model (in which data of concurrent writes are arthmetically or logically combined before write) and the exclusive-write on directed reconfigurable busses perform in equivalent way under strong real-time requirements. The fourth paper ``Experiences with Mesh-Like Computations Using Prediction Binary Trees'' is by Gennaro Cordasco, Biagio Cosenza, Rosario de Chiara, Ugo Erra and Vittorio Scarano from the University ``degli Studi'' of Salerno and the University ``degli Studi della Biasilicata'' of Potenza in Italy. The paper concerns optimization methods for mesh-like computations in clusters of processors. The computations are perfomed assuming a phase-like program execution control using a tiling approach which reduces inter-processor communication. A temporal coherence is also assumed, which means that task sizes provide similar execution times in consecutive phases. Temporary coherent computations are structured in a Prediction Binary Tree, in which leaves represent computing tiles to be mapped to processors. A phase-by-phase semi-static load balancing is introduced to the scheduling algorithm. The scheduling algorithm is equipped with a predictor, which estimates the computation time of next phase tiles based on previous execution times and modifies the tiles to achieve balanced execution in phases. For this, two heuristics are used to leverage on data locality in processors. The proposed approach is illustrated by the example of interactive rendering with Parallel Ray Tracing algorithm. The fifth paper ``The Influence of the IBM pSeries Servers Virtualization Mechanism on Dynamic Resource Allocation in AIX 5L'' is by Maciej Mlynski from ASpartner Limited in Poland. The paper concerns a very up-to-date problem of system virtualization and presents the results of research carried on IBM pSeries servers. IBM is strongly developing the virtualization technique especially on IBM pSeries servers enabling an improved and flexible sharing of system resources between applications. The paper investigates novel facilities for dynamic resource management such as micro-partitioning and partition load manager. They enable dynamic creation of workload logical partitions of system resources and their dynamic mangement. It includes run-time resource re-alocation between logical partitions including setting of sharing specifications as well as run-time adding/removing/setting parameters of resources in the system. It remains an open question how to properly tune parameters of the operating system using the provided virtualization facilities to obtain the best efficiency for a given application program. The paper presents the results of experiments which study the effects of tuning the disk subsystem parameters under the IBM AIX 5L operating system with the use of the provided virtualization facilities on the resulting application execution performance. The results show that even small deterioration in the resource pool status requires an immediate adaptation of the operating system parameters to maintain the required performance. The sixth paper ``HeteroPBLAS: A Set of Parallel Basic Linear Algebra Subprograms Optimized for Heterogeneous Computational Clusters'' is by Ravi Reddy, Alexey Lastovetsky and Pedro Alonso from University College Dublin in Ireland and Polytechnic University of Valencia in Spain. The paper concerns the methodology for parallelization of linear algebra computations for execution in heterogeneous cluster environments. The design of the HeteroPBLAS library (Parallel Basic Linear Algebra Subprograms) for heterogeneous computational clusters is presented. The main contribution of the paper is the automation of the parallelization and optimization of the PBLAS, which is done by means of a special user interface and the underlying set of functions. An important element is here a performance model that is based on program code instrumentation, which determines parameters of the application and the executive heterogeneous platform relevant for execution performance of parallel code. The parameter values specified for or returned by execution of the performance model functions are next used for generation and optimal mapping of the parallel code of the library subroutines. The proposed approach is illustrated by experimental results of execution of optimized HeteroPBLAS programs on homogeneous and heterogeneous computing clusters. Marek Tudruj

Ray tracing is an attractive technique for visualizing scientific data because it can produce high quality images that faithfully represent physically-based phenomena. Its embarrassingly parallel reputation makes it a natural candidate for visualizing large data sets on distributed memory clusters, especially for machines without specialized graphics hardware. Unfortunately, the traditional recursive ray tracing algorithm is exceptionally memory inefficient on large data, especially when using a shading model that generates incoherent secondary rays. As visualization moves through the petascale to the exascale, disk and memory efficiency will become increasingly important for performance, and traditional methods are inadequate. This paper presents a dynamic ray scheduling algorithm that effectively manages both ray state and data accesses. Our algorithm can render datasets that are larger than aggregate system memory, which existing statically scheduled ray tracers cannot render. For example, using 1024 cores of a supercomputing cluster, our unoptimized algorithm ray traces a 650GB dataset from an N-Body simulation with shadows and reflections, at about 1100 seconds per frame. For smaller problems that fit in aggregate memory, but are larger than typical shared memory, our algorithm is competitive with the best static scheduling algorithm.

Load balancing mechanisms and scheduling algorithms play a critical role in achieving efficient server utilization and providing robust delay performance in a wide range of networked systems. We will review some celebrated schemes and optimality results which typically assume that detailed state information, e.g. exact knowledge of queue lengths, is available in assigning jobs to queues or allocating a shared resource among competing users. In practice, however, obtaining such state information is non-trivial, and usually involves a significant communication overhead or delay, which is particularly a concern in large-scale networked systems with massive numbers of queues. These scalability issues have prompted increasing attention for the implementation complexity of load balancing and scheduling algorithms as a crucial design criterion, besides the traditional performance metrics. In this talk we examine the delay performance in such networks for various load balancing and scheduling algorithms, in conjunction with the associated implementation overhead. In the first part of the talk we focus on a scenario with a single dispatcher where jobs arrive that need to be assigned to one of several parallel queues. In the second part of the talk we turn to a system with a single resource, e.g. a shared wireless transmission medium, which is to be allocated among several nodes. We will specifically explore the delay scaling properties in a mean-field framework where the total load and service capacity grow large in proportion. The mean-field regime not only offers analytical tractability, but is also highly relevant given the immense numbers of servers in data centers and cloud networks, and dense populations of wireless devices and sensors in Internet-of-Things (IoT) applications. Time permitting, we will also discuss the impact of the underlying network structure and a few open research challenges.

Packet switching remains one of the bottlenecks in building fast Internet routers. Load balancing and switch scheduling are two important algorithms in the effort to maximize the throughput and minimize the latency of these packet switches. A load balancing algorithm regulates the traffic to conform to the service rates while a switch scheduling algorithm allocates the service rates adaptive to the arrival patterns. Many existing load balancing and switch scheduling algorithms are very similar. We show that load balancing and switch scheduling systems are dual systems based on the linear queue dynamics approximation. This allows us to cast a load balancing problem as a scheduling problem, and vice versa. We further show an example of designing a new algorithm for load balancing using an existing scheduling algorithm based on the duality. The duality perspective also allows us to solve unknown problems. We find the entropy rate of the randomized bandwidth allocation system with linear queue dynamics based on the knowledge of the entropy rate of the randomized load balancing system. For the general case, we find both an upper and a lower bound on the entropy rate. The joint use of dual load balancing and switch scheduling algorithms leads to performance gains as we show using mean field analysis.

In heterogeneous environments, dynamic scheduling algorithms are a powerful tool towards performance improvement of scientific applications via load balancing. However, these scheduling techniques employ heuristics that require prior knowledge about workload via profiling resulting in higher overhead as problem sizes and number of processors increase. In addition, load imbalance may appear only at run-time, making profiling work tedious and sometimes even obsolete. Recently, the integration of dynamic loop scheduling algorithms into a number of scientific applications has been proven effective. This paper reports on performance improvements obtained by integrating the Adaptive Weighted Factoring, a recently proposed dynamic loop scheduling technique that addresses these concerns, into two scientific applications: computational field simulation on unstructured grids, and N-Body simulations. Reported experimental results confirm the benefits of using this methodology, and emphasize its high potential for future integration into other scientific applications that exhibit substantial performance degradation due to load imbalance.

When the traditional heterogeneous multi-core scheduling algorithm performs tasks with high resource density, a large amount of idle time often occurs on the processor core. Therefore, based on the environment of heterogeneous multi-core processors, this paper studies the static heuristic table scheduling algorithm, and proposes an optimization approach for the problem of single priority assignment and too simple task assignment. We design optimization in the static heuristic scheduling algorithm list generation phase and task allocation phase, and propose a hybrid task allocation method with three strategies to improve the standby time utilization of processor core. Then, DVFS technology is used to optimize the scheduling results, so that the task can run with lower energy consumption without increasing makespan. Finally, the new algorithm is compared with three traditional scheduling algorithms through design experiments, and it is proved that the new algorithm has better performance when executing more tasks.

Load balancing algorithms are designed to achieve efficient resource utilisation in large-scale distributed systems. The primary goal of designing load balancing algorithms is to balance the overall workload among all the nodes in distributed systems to improve the performance. This paper presents an in-depth study and detailed comparative analysis of different load monitoring and balancing algorithms employing fuzzy logic and mobile agents. A detailed qualitative as well as quantitative analysis of algorithmic performances is included. The analytical survey presented in this paper would enable understanding of applications of different algorithms under different computing environments. Furthermore, this paper proposes a hybrid architecture combining fuzzy logic and mobile agents for load balancing and monitoring in distributed systems.

Nginx is a commonly used and free open-source web server that is used as a reverse proxy server, load balancer and HTTP cache. It consumes less memory and can handle more clients with less number of processes. Nginx provides users with five predefined load balancing algorithms. However, most of these algorithms are static and some of the load balancing rules are inefficient. In order to make the load of a cluster more stable under high concurrent requests, we developed a Dynamic Load Balancing (DLB) algorithm that uses Nginx as a network security control panel to provide load balancing for a cluster of backend servers. The DLB algorithm is based on the weighted round robin module of Nginx, Logistic Regression and Maximum Likelihood Estimation (MLE) algorithm. It handles the situation of high concurrent requests and reduces the probability of omitted or under-reported incident and status. We also propose a Hybrid Load Balance Method (HLBM) that incorporates the DLB algorithm and evolutionary computing to further improve the performance. We have conducted limited experiment by using dynamic load balancing algorithm. We will complete to develop the Hybrid Load Balance method and conduct experiments for HLBM.

Servers in data center networks handle heterogenous bulk loads. Load balancing, therefore, plays an important role in optimizing network bandwidth and minimizing response time. A complete knowledge of the current network status is needed to provide a stable load in the network. The process of network status catalog in a traditional network needs additional processing which increases complexity, whereas, in software defined networking, the control plane monitors the overall working of the network continuously. Hence it is decided to propose an efficient load balancing algorithm that adapts SDN. This paper proposes an efficient algorithm TA-ASLB-traffic-aware adaptive server load balancing to balance the flows to the servers in a data center network. It works based on two parameters, residual bandwidth, and server capacity. It detects the elephant flows and forwards them towards the optimal server where it can be processed quickly. It has been tested with the Mininet simulator and gave considerably better results compared to the existing server load balancing algorithms in the floodlight controller. After experimentation and analysis, it is understood that the method provides comparatively better results than the existing load balancing algorithms.

This article is about the ways of load balancing for server stations. The article contains most popular approaches and algorithms of load balancing in modern applications. The algorithm of round load balancing was described. This algorithm was chosen as the base for simulation model. This model was created by software tools MATLAB/SimulinkiSimEvents/Stateflow. The model takes into account the random nature of requests appearance and the variable time delay between the receiving of tasks. The process of model simulation provides numerical result of load balancing. It is possible to compare the modeling result with a real load balancing system. Finally, in this article the authors provided the idea of updating a round balancing algorithm for a simulation model as the way of future investigation.

Objectives: In this paper various task scheduling algorithm along with load distribution techniques investigated to ensure efficient mapping of tasks to resources and for coherent resource utilization in heterogeneous environment. Statistical Analysis: A detailed comparative approach is conferred for different job scheduling and load balancing algorithm available in the literature. Considered parameters for comparisons are scheduling approaches, techniques, findings, benefits, pros and cons. This study facilitates to identify the efficient scheduling and load balancing approach which optimizes resource use, minimizes completion time as well as task waiting time and balanced load among resources. Findings: Make span time and flow time are two important parameters to compute and minimize job execution time. This paper explores an intense survey of minimization of task execution time with minimum make span time and flow time. Apart from this a joint review on job scheduling, load balancing and minimizing job completion time using Expected Time to Compute (ETC) matrix is presented. At the end of this paper a research model is proposed which is a novel and hybrid approach with a combination of the efficiency of scheduling and load balancing. Application: The Load Balancing (LB) is an important feature of the grid environment. The efficient LB algorithm assures cost effective resource usage by the provisioning of resources to users on demand schedule in pay-as-you-say-manner.

An algorithm for load balancing in multiprocessor systems

With the development of economics and the globalization of trade, the Multimedia Conference System is now widely used and the number of its users increases exponentially. But a single server can't handle the high concurrent user requests effectively. In this paper, we improved the Multimedia Conference System with load balance technology. With the load balance technology, the robustness and availability of the system can be enhanced significantly. Keywords-load balance, cluster, Nginx, Multimedia Conference System I. INTRODUCTION With the explosive popularity of the Internet and the World Wide Web, most popular web sites confronted with a problem that the server overloaded caused by the increasing number of concurrent accesses. In order to process the user requests timely, increase the network throughput and improve the quality of service, it's necessary to upgrade the hardware and software of the sever. But the the hardware is expensive and non-scalability. In this case, server cluster system appears. The sever cluster system refers to a server group which is composed of more than one homogeneous or heterogeneous severs and can provides services that are transparent for the external users. And it becomes a key point that how to achieve a reasonable distribution of load between multiple servers and avoid appearing one server with full load while other servers with little load. In this situation, the load balance technology was born. In recent years, cluster technology and load balance technology got fully developed and they have significant effect on solving the problem of overloading. As a web service, the Multimedia Conference System also has to face the problem that the overload of the server and uneven distribution of resources when there are too many users access the system. Using cluster and load balance technology, the requests the system received can be evenly distributed on each server, thus we can reduce the response time of the requests and improve the resource utilization. The Multimedia Conference System proposed in this paper contains Client Layer, Load Balancer Layer, Server Cluster Layer and Media Server Layer. The Client Layer receives the requests of the user including creating a conference and joining an existing conference. The Load Balancer Layer redirect the user's request to one of the application servers in the cluster according to the load balance algorithm and the different parameters from the Client Layer. The application servers in Server Cluster Layer call the Media Server resources and return them to the Client Layer. This implements a basic process of the system. The Load Balancer Layer contains four modules including User Authentication, Decision-Making, Redirecting and Log Parsing. With the Load Balancer Layer and its load balance algorithm, the user's request can be distributed on different servers and those who want to join the same conference can be allocated to the same application server. Thus we can minimize the response time of the request, improve the resource utilization and also ensure the conference can be held correctly. The rest of this paper is organized as follows: we describe related work in section II. Section III presents the architecture of the Multimedia Conference System. In section IV, we display the implementation of the Load Balancer Layer in detail. Some experiments of key features of load balancer in section V. We conclude in section VI.

Infrastructure as a service (IaaS) is a type of cloud computing in which a third-party provider hosts virtualized computing resources over the Internet for executing tasks in the cloud computing. Whenever some VMs are overloaded and some VMs are under loaded, this situation may cause to SLA violation and leads to the reduction of customer satisfaction level and further affects the cloud provider leading to penalty. However, in this study, we propose a Multiple Agent-based Load Balancing Algorithm (MA) in which shift the load in the IaaS to achieve well dynamic load balancing across virtual machines for maximizing the utilization. The proposed algorithm with regard to changing environment and characteristics of the VMs, perform both of sender-initiated and receiver-initiated approach to balances the load of an IaaS in such a way that the amount of waiting time of the tasks in the queue is minimal and at the same time the SLA is guaranteed.We have compared the proposed algorithm with existing load balancing and scheduling algorithms via simulation. The simulation results show that the proposed algorithm is more effective and there is a good improvement in the load-balance, response time and makespan.