Sanli Li

Virtualization-based autonomic resource management for multi-tier Web applications in shared data center

As large data centers emerge, which host multiple Web applications, it is critical to isolate different application environments for security reasons and to provision shared resources effectively and efficiently to meet different service quality targets at minimum operational cost. To address this problem, we developed a novel architecture of resource management framework for multi-tier applications based on virtualization mechanisms. Key techniques presented in this paper include (1) establishment of the analytic performance model which employs probabilistic analysis and overload management to deal with non-equilibrium states; (2) a general formulation of the resource management problem which can be solved by incorporating both deterministic and stochastic optimizing algorithms; (3) deployment of virtual servers to partition resource at a much finer level; and (4) investigation of the impact of the failure rate to examine the effect of application isolation. Simulation experiments comparing three resource allocation schemes demonstrate the advantage of our dynamic approach in providing differentiated service qualities, preserving QoS levels in failure scenarios and also improving the overall performance while reducing the resource usage cost.

An autonomic provisioning framework for outsourcing data center based on virtual appliances

As outsourcing data centers emerge to host applications and services from many different organizations, it is critical for data center owners to isolate different applications while dynamically and optimally allocate sharable resources among them. To address this issue, we propose a virtual-appliance-based autonomic resource provisioning framework for large virtualized data centers. We present the architecture of the data center with enriched autonomic features. We define a non-linear constrained optimization model for dynamic resource provisioning and present a novel analytic solution. Key factors, including virtualization overhead and reconfiguration delay, are incorporated into the model. Experimental results based on a prototype demonstrate that the system-level performance has been greatly improved by taking advantage of fine-grained server consolidation, and the whole system exhibits flexible adaptation in failure scenarios. Experiments with the impact of switching delay also show the efficiency of the framework due to significantly reduced provisioning time.

Design of an OGSA Based MetaService Architecture

This paper proposes a MetaService-based architecture for dealing with the problem of services management in grid systems. We introduce the basic idea of MetaService, and then discuss MetaService classification, new MetaService construction, and the MetaService working mechanism. A graph and a tree can be used for the optimization function of MetaService. An example from real life is used to explain the role of MetaService. We give an overview of a grid prototype system which has incorporated some of the ideas presented. A brief comparison is given between MetaService and other related work.

Computing Pool: A Simplified and Practical Computational Grid Model

Even though grid research is prosperous in an extensive context, few grid platforms for high performance computing are practical and in operation so far. Since most applications are moderate ones, trying to decompose these applications among distributed supercomputers will results in complexity in programming and optimizing, and heavy cost of communications. In this paper we advocate computing pool which shares distributed supercomputers but does not decompose applications. Analysis proves that it is a practicable computing platform, which can greatly improve quality of service and utilization of resources.

Multi-cluster load balancing based on process migration

Load balancing is important for distributed computing systems to achieve maximum resource utilization, and process migration is an efficient way to dynamically balance the load among multiple nodes. Due to limited capacity of a single cluster, its necessary to share the underutilized resources of other sites. This paper addresses the issues in multi-cluster load balancing based on process migration across separate clusters. Key technology and mechanisms are discussed and then the implementation of a prototype system is described in detail. Experimental results depict that by achieving multi-cluster load balance, surplus resources can be efficiently utilized and the makespan is also greatly reduced as a result.

Distributed grid resource registry meta-service: design and implementation

Grid is focused by the researchers theses years. In grid, resource registry meta-service assumes the responsibility for the register managing and indexing of resources in grid. Its very important for the running of grid. In this paper, we present a resource description system and provide its reference by XML schema first. Then, we design the distributed resource registry meta-service and implement it based on Java language. At last, the test and tryout indicate that it can provide high-performance and robust resource registering and indexing services.

Performance Analysis of the OGSA-DAI 3.0 Software

OGSA-DAI provides an extensible Web service- based framework that allows data resources to be incorporated into grid fabrics. The current OGSA- DAI release (OGSA-DAI GT 3.0), published in Sep. 2007, is a complete rewrite of its former version. In this paper we describe the performance of some key components. Under the predefined profiling environment, approach and tools, we conduct profiling from four perspectives: activity and resource performance, data query process performance, database connection and the pressure test. The profiling results would provide guides for the developers to make amendments in their future release, and for users to choose appropriate usages.

MyVIA: a design and implementation of the high performance Virtual Interface Architecture

Virtual Interface Architecture (VIA) established a communication model with low latency and high bandwidth, and defined the standard of user-level high-performance communication specification in cluster systems. This paper analyzes the current development, principle and implementations of VIA, and presents user-level high-performance communication software, MyVIA, based on Myrinet, which is comfortable with VIA specification. The paper first describes the design principle and framework of MyVIA, then proposes new technologies of MyVIA including User TLB, continued host physical memory and varied NIC buffer, the pipelining communication based on resource and DMA chain, and physical descriptor ring. Experimental results of performance comparisons and analysis are presented; the one-way bandwidth of MyVIA for a 4 KB message is 250 MB/s, and the lowest one-way latency is 8.46 /spl mu/s, which shows that the performance of MyVIA surpassed that of other implementations of VIA.

V3COCA: An effective clustering algorithm for complicated objects and its application in breast cancer research and diagnosis

Abstract In breast cancer studies, researchers often use clustering algorithms to investigate similarity/dissimilarity among different cancer cases. The clustering algorithm design becomes a key factor to provide intrinsic disease information. However, the traditional algorithms do not meet the latest multiple requirements simultaneously for breast cancer objects. The Variable parameters, Variable densities, Variable weights, and Complicated Objects Clustering Algorithm (V3COCA) presented in this paper can handle these problems very well. The V3COCA (1) enables alternative inputs of none or a series of objects for disease research and computer aided diagnosis; (2) proposes an automatic parameter calculation strategy to create clusters with different densities; (3) enables noises recognition, and generates arbitrary shaped clusters; and (4) defines a flexibly weighted distance for measuring the dissimilarity between two complicated medical objects, which emphasizes certain medically concerned issues in the objects. The experimental results with 10,000 patient cases from SEER database show that V3COCA can not only meet the various requirements of complicated objects clustering, but also be as efficient as the traditional clustering algorithms.

Grid Services Performance Tuning in OGSA

In the next generation of Open Grid Service Architecture – OGSA, Grid has become a Service Oriented environment which is more open, more scalable and more flexible. However, the increase of flexibility will inevitably bring performance decreasing. And the performance problem increasingly constitutes a great challenge to the Grid Researching field. In this paper, we propose a time-based model in order to analyze the performance of Grid Services. On the foundation of this model, we give two methods – Grid Service Instance Pool and Caching on Grid Server – both of them can enhance the performance of Grid Services prominently. Moreover, we not only give theoretic explanation of those methods, but also carry out some experiments by using Globus 3.0 alpha 2 for verification.