Jan-Jan Wu

Energy-Aware Virtual Machine Dynamic Provision and Scheduling for Cloud Computing

Power consumption is one of the most critical problems in data centers. One effective way to reduce power consumption is to consolidate the hosting workloads and shut down physical machines which become idle after consolidation. Server consolidation is a NP-hard problem. In this paper, a new algorithms Dynamic Round-Robin (DRR), is proposed for energy-aware virtual machine scheduling and consolidation. We compare this strategy with the GREEDY, ROUNDROBIN and POWERSAVE scheduling strategies implemented in the Eucalyptus Cloud system. Our experiment results show that the Dynamic Round-Robin algorithm reduce a significant amount of power consumption compared with the three strategies in Eucalyptus.

Optimal placement of replicas in data grid environments with locality assurance

Data replication is a typical strategy for increasing access performance and data availability in data grid systems. Work on data replication in grid systems focuses on infrastructure for replication and mechanisms for creating/deleting replicas. The important problem of choosing suitable locations for placing replicas in data grids has not been well studied. In this paper, we address the problem of data replica placement in data grids given the traffic pattern and locality requirements. We propose a new placement algorithm that finds the optimal locations for the replicas so that the workload among these replicas is balanced. We also propose a new algorithm to decide the minimum number of replicas required when the maximum workload capacity of each replica server is known. All these algorithms ensure that locality requirements from the users are satisfied

Energy-efficient Virtual Machine Provision Algorithms for Cloud Systems

Power consumption is one of the most critical problems in data centers. One effective way to reduce power consumption is to consolidate the hosting workloads and shut down physical machines which become idle after consolidation. Server consolidation is a NP-hard problem. In this paper, we propose two new algorithms, Dynamic Round-Robin (DRR) and Hybrid, which combines DRR and First-Fit, for energy aware virtual machine scheduling and consolidation. We also propose an accurate power model to estimate the power consumption resulted from each algorithm. Strategies we proposed are compared with GREEDY, ROUNDROBIN and POWERSAVE scheduling strategies implemented in the Eucalyptus Cloud system. Our experiment results show that our DRR and Hybrid algorithms reduce power consumption by 56.4% and 55.9% respectively, compared with the ROUNDROBIN scheduling strategy in Eucalyptus. DDR and Hybrid also result in 3% less power consumption on average, compared with the POWERSAVE scheduling strategy in Eucalyptus.

A QoS-Aware Heuristic Algorithm for Replica Placement

This paper studies the QoS-aware replica placement problem. Although there has been much work on replica placement problem, most of them concerns average system performance and ignores quality assurance issue. Quality assurance is very important, especially in heterogeneous environments. We propose a new heuristic algorithm that determines the positions of replicas in order to satisfy the quality requirements imposed by data requests. The experimental results indicate that the proposed algorithm finds a near-optimal solution effectively and efficiently for algorithm can also adapt to various parallel and distributed environments

Optimal replica placement in hierarchical Data Grids with locality assurance

In this paper, we address three issues concerning data replica placement in hierarchical Data Grids that can be presented as tree structures. The first is how to ensure load balance among replicas. To achieve this, we propose a placement algorithm that finds the optimal locations for replicas so that their workload is balanced. The second issue is how to minimize the number of replicas. To solve this problem, we propose an algorithm that determines the minimum number of replicas required when the maximum workload capacity of each replica server is known. Finally, we address the issue of service quality by proposing a new model in which each request must be given a quality-of-service guarantee. We describe new algorithms that ensure both workload balance and quality of service simultaneously. We conduct extensive simulation experiments to evaluate the effectiveness of our algorithms. The comparison with the previous Affinity Replica Location Policy demonstrates that our algorithms consistently outperform the heuristic algorithm both in terms of minimum number of replicas used and the actual data transmission time.

Exploiting Spectral Reuse in Routing, Resource Allocation, and Scheduling for IEEE 802.16 Mesh Networks

The IEEE 802.16 standard for wireless metropolitan area networks (WMANs) is defined to meet the need for wide-range broadband wireless access at low cost. The objective of this paper is to study how to exploit spectral reuse in resource allocation in an IEEE 802.16 mesh network, which includes routing tree construction (RTC), bandwidth allocation, time-slot assignment, and bandwidth guarantee of real-time flows. The proposed spectral reuse framework covers bandwidth allocation at the application layer, RTC and resource sharing at the medium access control (MAC) layer, and channel reuse at the physical layer. To the best of our knowledge, this is the first paper that formally quantifies spectral reuse in IEEE 802.16 mesh networks and exploits spectral efficiency under an integrated framework. Simulation results show that the proposed schemes significantly improve the throughput of IEEE 802.16 mesh networks.

SQLMR : A Scalable Database Management System for Cloud Computing

As the size of data set in cloud increases rapidly, how to process large amount of data efficiently has become a critical issue. MapReduce provides a framework for large data processing and is shown to be scalable and fault-tolerant on commondity machines. However, it has higher learning curve than SQL-like language and the codes are hard to maintain and reuse. On the other hand, traditional SQL-based data processing is familiar to user but is limited in scalability. In this paper, we propose a hybrid approach to fill the gap between SQL-based and MapReduce data processing. We develop a data management system for cloud, named SQLMR. SQLMR complies SQL-like queries to a sequence of MapReduce jobs. Existing SQL-based applications are compatible seamlessly with SQLMR and users can manage Tera to PataByte scale of data with SQL-like queries instead of writing MapReduce codes. We also devise a number of optimization techniques to improve the performance of SQLMR. The experiment results demonstrate both performance and scalability advantage of SQLMR compared to MySQL and two NoSQL data processing systems, Hive and HadoopDB.

Probability-Based Cloud Storage Providers Selection Algorithms with Maximum Availability

During recent years cloud service providers have successfully provided reliable and flexible resources to cloud users. For example Amazon Elastic Block Store (Amazon EBS) and Simple Storage Service (Amazon S3) provides users storage in the cloud. Despite the tremendous efforts cloud service providers have devoted to the availability of their services, the interruption is still inevitable. Therefore just as an Internet service provider will not count on a single network provider, a cloud user should not depend on a single cloud service provider either. However, cloud service providers provide different levels of services. A more costly service is usually more reliable. As a result it is an important and challenging problem to choose among a set of service providers to fit ones need, which could be budget, failure probability, or the amount of data that can survive failure. The goal of this paper is to select cloud service providers in order to maximize the benefits with a given budget. The contributions of this paper include a mathematical formulation of the cloud service provider selection problem in which both the object functions and cost measurements are clearly defined, algorithms that selects among cloud storage providers to maximize the data survival probability or the amount of surviving data, subject to a fixed budget, and a series of experiments that demonstrateDuring recent years cloud service providers have successfully provided reliable and flexible resources to cloud users. For example Amazon Elastic Block Store (Amazon EBS) and Simple Storage Service (Amazon S3) provides users storage in the cloud. Despite the tremendous efforts cloud service providers have devoted to the availability of their services, the interruption is still inevitable. Therefore just as an Internet service provider will not count on a single network provider, a cloud user should not depend on a single cloud service provider either. However, cloud service providers provide different levels of services. A more costly service is usually more reliable. As a result it is an important and challenging problem to choose among a set of service providers to fit ones need, which could be budget, failure probability, or the amount of data that can survive failure. The goal of this paper is to select cloud service providers in order to maximize the benefits with a given budget. The contributions of this paper include a mathematical formulation of the cloud service provider selection problem in which both the object functions and cost measurements are clearly defined, algorithms that selects among cloud storage providers to maximize the data survival probability or the amount of surviving data, subject to a fixed budget, and a series of experiments that demonstrate that the proposed algorithms are efficient enough to find optimal solutions in reasonable amount of time, using price and fail probability taken from real cloud providers. that the proposed algorithms are efficient enough to find optimal solutions in reasonable amount of time, using price and fail probability taken from real cloud providers.

Optimal Algorithms for Cross-Rack Communication Optimization in MapReduce Framework

MapReduce is a widely used data-parallel programming model for large-scale data analysis. The framework is shown to be scalable to thousand of computing nodes and reliable on commodity clusters. However, research has shown that there is room for performance improvement of the MapReduce framework. One of the main performance bottlenecks is caused by the all-to-all communication between mappers and reducers, which may saturate the top-of-rack switch and inflate job execution time. Reducing cross-rack communication will improve job performance. In current MapReduce implementation, the task assignment is based on the pull-model, in which cross-rack traffic is difficult to control. In contrast, the MapReduce framework allows more flexibility in assigning reducers to the computing nodes. In this paper, we investigate the reducer placement problem (RPP), which considers the placement of reducers to minimize cross-rack traffic. We devise two optimal algorithms to solve RPP and implement the algorithms in the Hadoop system. We also propose an analytical solution for this problem. Our experiment results with a set of MapReduce applications show that our optimization achieves 9\% to 32\%performance improvement compared with the unoptimized Hadoop.

An Empirical Study on Memory Sharing of Virtual Machines for Server Consolidation

Server consolidation presents numerous opportunities for sharing memory between virtual machines. To intelligently share RAM across VMs, modern hyper visors use a technique called content-based page sharing (CBPS), in which duplicate copies of a page resident on a host are detected and a single copy of the page is shared, thereby reducing the memory footprint of resident VMs. One widely used implementation of content-based page sharing is kernel same page merging (KSM). In this paper, we conduct empirical study on the effectiveness of KSM on various kinds of workload through extensive experiments. We classify memory sharing into two classes: static sharing for memory sharing after launching the VM and before executing the application, and dynamic sharing for memory sharing during the execution of the application. We found that KSM achieves very effective static memory sharing for various workload, evidenced by its ability to consolidate 50 Windows VMs on one physical machine. KSM achieves most significant memory saving for mixed CPU and I/O workload. For CPU-bound applications, the effect of KSM on dynamic memory sharing is not as significant and it also causes higher runtime overhead. For I/O-bound applications, dynamic memory sharing reduces memory use by around 50% with very little runtime overhead. Furthermore, KSM has more significant effect on Windows based VMs than on Linux based VMs.