Jinlei Jiang

Liquid: A Scalable Deduplication File System for Virtual Machine Images

A virtual machine (VM) has been serving as a crucial component in cloud computing with its rich set of convenient features. The high overhead of a VM has been well addressed by hardware support such as Intel virtualization technology (VT), and by improvement in recent hypervisor implementation such as Xen, KVM, etc. However, the high demand on VM image storage remains a challenging problem. Existing systems have made efforts to reduce VM image storage consumption by means of deduplication within a storage area network (SAN) cluster. Nevertheless, an SAN cannot satisfy the increasing demand of large-scale VM hosting for cloud computing because of its cost limitation. In this paper, we propose Liquid, a scalable deduplication file system that has been particularly designed for large-scale VM deployment. Its design provides fast VM deployment with peer-to-peer (P2P) data transfer and low storage consumption by means of deduplication on VM images. It also provides a comprehensive set of storage features including instant cloning for VM images, on-demand fetching through a network, and caching with local disks by copy-on-read techniques. Experiments show that Liquids features perform well and introduce minor performance overhead.

DABGPM: a double auction Bayesian game-based pricing model in cloud market

Recently IT giants such as Google, Amazon, Microsoft, and IBM are gearing up to be a part of the Cloud and begin to sell their cloud services. However, the current market trading mechanism is inflexible, and the price is not reasonable enough in some situation. Therefore, we first propose a cloud market framework for people to build a uniform and fully competitive cloud market where users can buy resources from different companies and exchange their idle resources in a more flexible way. Then we define a double auction Bayesian Game-based pricing model (DABGPM) for the suggested cloud market and discuss how to develop an optimal pricing strategy for this model. Our work, we think, makes a good example of more flexible and more reasonable cloud resources trading.

Build grid-enabled large-scale collaboration environment in e-Learning grid

Abstract As a new branch of grid computing, e-Learning grid is emerging as a nationwide e-Learning infrastructure, which can provide innovative learning experience for learners. In such a grid environment, collaboration services will be the key elements due to the pervasive requirement for cooperative work and collaborative learning. Although there exist enormous research efforts on grid-based collaboration technologies, most of them have many limitations. In this paper, with the findings from the computer support cooperative work (CSCW)/computer support collaborative learning (CSCL) and advantages provided by grid, we propose to build grid-enabled large-scale collaboration environment (GLCE). GLCE focuses on distributed, large-scale, and cross-organizational collaboration through creating group-centered next generation collaboration environment, where both intra-group and inter-group collaboration could be supported. With this idea in mind, we present a grid-based cooperative work framework (GCWF), which aims to implement GLCE with an “upper layer” collaboration middleware based on the special-purpose grid infrastructure designed by our team. The preliminary results of our research on GLCE have been applied to build the learning assessment grid (LAGrid). The goal of LAGrid is to support the formative assessment business in China Radio and TV University (CRTVU) and large-scale collaboration within virtual organization (VO) has been realized.

A Knowledge-based Continuous Double Auction Model for Cloud Market

Recently, the Storage Networking Industry Association (SNIA) has released the first standard for cloud interoperability. With more and more standards for interoperability emerging, it can be expected that a global cloud resource exchange market will form. In such a market, it is challenging to present a dynamic pricing scheme to meet different requirements. To cope with the challenge, in this paper we first present a framework for constructing global cloud resource markets and then propose a knowledge-based continuous double auction (CDA) model that determines the price of cloud resources using a learning algorithm based on historical trading information. Experimental result shows that our model can attain high market efficiency as well as stable trading price.

A Context Model for Collaborative Environment

Context awareness, context sharing and context processing are key requirements for the future CSCW, HCI and ubiquitous computing systems. Until now, the collaborative context factors have been seldom specifically addressed. This paper argues that a generic context model is very important for building context-aware collaborative applications. A new semantic rich context model for collaborative environment is proposed. The conceptual model for context is described as ontology for contextual collaborative applications (OCCA). The model for context query & memory service, context matching service and control policies is illustrated. Information space, interaction space and collaboration control mechanisms are built up or implemented based on this context model

CovaTM: a transaction model for cooperative applications

It has been widely recognized that traditional transaction models with ACID(Atomicity, Consistency, Isolation and Durability) properties generally are not applicable to cooperative applications. Though many advanced transaction models have been proposed to address the problems, they are too database-centered or too rigid to be useful in real environments. This paper presents a new transaction model named CovaTM, which provides sophisticated but flexible control over cooperative process as well as support for error recovery and exception handling. The most distinguished feature of this model is that user intervention is explicitly introduced into transaction processing. This paper details the features and structural elements of this model. An example is also given to illustrate how it works in real world settings.

Online Video Playing on Smartphones: A Context-Aware Approach Based on Cloud Computing

As the device holding great promise to realize the vision of pervasive computing, smartphones with Internet access and video playing capability have become commercial off the shelf products today. As one of the most popular applications on smartphones, online video playing, however, still faces some problems. From the perspective of service providers, they have to provide video files of different formats and qualities to meet the diverse needs of various consumers. From the perspective of service consumers, if one or more codecs required to open a video file supplied by a certain service provider are not available on their smartphones, they just cannot watch that video or have to install new codecs-both cases give users bad experience. To deal with such a situation, this paper puts forward a context-aware approach for online video playing based on cloud computing. Our experience demonstrates that the combination of cloud computing and smartphones creates a lot of new opportunities for more advanced services.

Modeling contexts in collaborative environment: a new approach

Context awareness, context sharing and context processing are key requirements for the future CSCW, HCI and Ubiquitous computing systems. However, research issues of collaborative context have not been completely addressed till now. While arguing that a generic context model is very important for building context-aware collaborative applications, this paper proposes a new semantic rich context modeling approach, Ontology for Contextual Collaborative Applications (OCCA), for collaborative environments. Based on OCCA, mechanisms for context query, context matching and collaboration awareness control are devised using semantic query and reasoning technology to support the three perspectives of a context model, i.e., information space, interaction space and collaboration control. We present an evaluation study on the features and performance of OCCA and context query services.

A Scalable Framework for Large-Scale Distributed Collaboration

There is an increasing need for computer-supported cooperative work (CSCW) in recent years. However, most of existing collaborative systems are not scalable enough, thus leading to bad usability. In this paper we propose a scalable framework for large-scale distributed collaboration which aims to support a wide range of collaboration requirements. The framework comprises a set of geographically dispersed collaborative servers (co-servers) specially deployed by participant organizations. The set of co-servers constitutes an overlay network which provides an infrastructural supporting environment for large-scale distributed collaboration. The framework is scalable in terms of the geographic distribution of participant organizations, size of groups, and total number of groups. The framework will be used to build the next-generation collaborative e-learning platform. A prototype system is being developed to demonstrate the application of the framework

ActCap: Accelerating MapReduce on heterogeneous clusters with capability-aware data placement

As a widely used programming model and implementation for processing large data sets, MapReduce performs poorly on heterogeneous clusters, which, unfortunately, are common in current computing environments. To deal with the problem, this paper: 1) analyzes the causes of performance degradation and identifies the key one as the large volume of inter-node data transfer resulted from even data distribution among nodes of different computing capabilities, and 2) proposes ActCap, a solution that uses a Markov chain based model to do node-capability-aware data placement for the continuously incoming data. ActCap has been incorporated into Hadoop and evaluated on a 24-node heterogeneous cluster by 13 benchmarks. The experimental results show that ActCap can reduce the percentage of inter-node data transfer from 32.9% to 7.7% and gain an average speedup of 49.8% when compared with Hadoop, and achieve an average speedup of 9.8% when compared with Tarazu, the latest related work.