Chenlin Huang

Modeling and analyzing the impact of authorization on workflow executions

It has been a subject of a significant amount of research to automate the execution of workflows (or business processes) on computer resources. However, many workflow scenarios still require human involvement, which introduces additional security and authorization concerns. This paper presents a novel mechanism for modeling the execution of workflows with human involvement under Role-based Authorization Control. Our modeling approach applies Colored Timed Petri-Nets to allow various authorization constraints to be modeled, including role, temporal, cardinality, BoD (Binding of Duty), SoD (Separation of Duty), role hierarchy constraints etc. We also model the execution of tasks with different levels of human involvement and as such allow the interactions between workflow authorization and workflow execution to be captured. The modeling mechanism is developed in such a way that the construction of the authorization model for a workflow can be automated. This feature is very helpful for modeling large collections of authorization policies and/or complex workflows. A Petri-net toolkit, the CPN Tools, is utilized in the development of the modeling mechanism and to simulate the constructed models. This paper also presents the methods to analyze and calculate the authorization overhead as well as the performance data in terms of various metrics through the model simulations. Based on the simulation results, this paper further proposes the approaches to improving performance given the deployed authorization policies. This work can be used for investigating the impact of authorization, for capacity planning, for the design of workload management strategies, and also to estimate execution performance, when human resources and authorization policies are employed in tandem.

Efficient and fine-grained sharing of encrypted files

Current applications often need frequent collaboration with related users, which result in more and more confidential data sharing on application server. Accordingly, assuring the security of shared data is one of the hot issues. A prevalent technology, referred to as encryption file systems, has been proposed for solving the storage security problem, such as EFS[1], eCryptfs[2]. Encryption file systems are often integrated into the corresponding operating systems and run in the kernel mode. With encryption file systems, data are encrypted and decrypted transparently. While most existing encryption file systems support either no sharing or only file-level sharing, it is impractical for use and cannot afford operation demand.

Developing the Cloud-integrated data replication framework in decentralized online social networks

Decentralized Online Social Network (DOSN) services have been proposed to protect data privacy. In DOSN, the data published by a user and their replicas are only stored in the friend circle of the user. Although full replication can improve Data Availability (DA), pure DOSNs may not deliver sustainable DA. This paper proposes a Cloud-assisted data replication and storage scheme, called Cadros, to improve the DA in DOSN. This paper conducts quantitative analysis about the storage capacity of Cadros, and further models and predicts the level of DA that Cadros can achieve. The data in Cadros are partitioned in such a way that the overhead caused by storing the data in the Cloud is minimized while satisfying the desired DA. This paper also proposes the data placement strategies to realize the desired DA and improve other performance. Experiments have been conducted to verify the effectiveness of Cadros. This work conducts the quantitative analysis about the storage capacity of a hybrid system combining DOSN and the Cloud.This work analyzes and predicts the probabilistic behavior of the friend circle in the DOSN.This work develops a data partition scheme in terms of replication techniques.This work develops the placement strategy for data replicas to realize the predicted data availability.

Performance Optimization for Managing Massive Numbers of Small Files in Distributed File Systems

The processing of massive numbers of small files is a challenge in the design of distributed file systems. Currently, the combined-block-storage approach is prevalent. However, the approach employs the traditional file systems such as ExtFS and may cause inefficiency when accessing small files randomly located in the disk. This paper focuses on optimizing the performance of data servers in accessing massive numbers of small files. We present a Flat Lightweight File System (iFlatLFS) to manage small files, which is based on a simple metadata scheme and a flat storage architecture. iFlatLFS is designed to substitute the traditional file system on data servers and can be deployed underneath distributed file systems that store massive numbers of small files. iFlatLFS can greatly simplify the original data access procedure. The new metadata proposed in this paper occupies only a fraction of the metadata size based on traditional file systems. We have implemented iFlatLFS in CentOS 5.5 and integrated it into an open source Distributed File System (DFS), called Taobao FileSystem (TFS), which is developed by a top B2C service provider, Alibaba, in China and is managing over 28.6 billion small photos. We have conducted extensive experiments to verify the performance of iFlatLFS. The results show that when the file size ranges from 1 to 64 KB, iFlatLFS is faster than Ext4 by 48 and 54 percent on average for random read and write in the DFS environment, respectively. Moreover, after iFlatLFS is integrated into TFS, iFlatLFS-based TFS is faster than the existing Ext4-based TFS by 45 and 49 percent on average for random read access and hybrid access (the mix of read and write accesses), respectively.

Modelling and Predicting the Data Availability in Decentralized Online Social Networks

Maintaining data availability is one of the biggest challenges in Decentralized Online Social Networks (DOSN). In the existing work of improving data availability in DOSN, it is often assumed that the friends of a user are always capable of contributing sufficient storage capacity to store all the data published by the user. However, this assumption is not always true for todays Online Social Networks (OSNs) for the following reasons. On one hand, the increasingly more data are being generated on the OSNs nowadays. On the other hand, current users often use the smart mobile devices to access the OSNs. These two factors cause the shortage of the storage capacity in DOSN, where the published data are supposed to be stored within a friend circle. The limitation of the storage capacity may jeopardize the data availability. Therefore, it is desired to know the relation between the storage capacity contributed by the OSN users and the level of data availability that the OSN can achieve. This paper addresses this issue. In this paper, the data availability model over storage capacity is established. Further, a novel method is proposed to predict the data availability on the fly. Extensive simulation experiments have been conducted to evaluate the effectiveness of the data availability model and the on-the-fly prediction. The data availability model can be used by the OSN designers to determine the storage capacity for the published data in order to achieve the desired data availability. The on-the-fly prediction method can help the data replication and storage policies make judicious decisions at runtime.

Analyzing the Impact of Storage Shortage on Data Availability in Decentralized Online Social Networks

Maintaining data availability is one of the biggest challenges in decentralized online social networks (DOSNs). The existing work often assumes that the friends of a user can always contribute to the sufficient storage capacity to store all data. However, this assumption is not always true in todays online social networks (OSNs) due to the fact that nowadays the users often use the smart mobile devices to access the OSNs. The limitation of the storage capacity in mobile devices may jeopardize the data availability. Therefore, it is desired to know the relation between the storage capacity contributed by the OSN users and the level of data availability that the OSNs can achieve. This paper addresses this issue. In this paper, the data availability model over storage capacity is established. Further, a novel method is proposed to predict the data availability on the fly. Extensive simulation experiments have been conducted to evaluate the effectiveness of the data availability model and the on-the-fly prediction.

Developing an Efficient Pattern Discovery Method for CPU Utilizations of Computers

Mining repeated patterns (often called motifs) in CPU utilization of computers (also called CPU host load) is of fundamental importance. Many recently emerging applications running on high performance computing systems rely on motif discovery for various purposes, including efficient task scheduling, energy saving, etc. In this paper, we propose an efficient motif discovery framework for CPU host load. The framework is elaborately designed to take into account the important properties in host load data. The framework benefits from its ability of on-line discovery and the adaptivity to work with massive data. The experiments are conducted in this paper and the experimental results show that the proposed method is effective and efficient.

Cadros: The Cloud-Assisted Data Replication in Decentralized Online Social Networks

Online Social Network (OSN) services are very popular nowadays. In order to protect the data privacy, Decentralized Online Social Network (DOSN) services have been proposed. In DOSN, the data published by a user and the data replicas are only stored in the friend circle of the user. Although full replication can improve Data Availability (DA), pure DOSNs may not be able to deliver sustainable data availability. This paper proposes a Cloud-Assisted scheme, called Cadros, to improve the DA in DOSN. This paper conducts quantitative analysis about the storage capacity of Cadros as the result of integrating the Cloud into DOSN, and further models and predicts the level of DA that Cadros can achieve. Extensive simulation experiments have been conducted to verify the effectiveness of Cadros.

An efficient method for motif discovery in CPU host load

Mining repeated patterns, or motifs, in CPU host load is of fundamental importance. Many recently emerging applications running on high performance computing systems rely on motif discovery for various purposes, including efficient task scheduling, energy saving, etc.. In this paper, we propose an efficient motif discovery framework for CPU host load. The framework is elaborately designed to take into account the important properties in host load data. The framework benefits from its ability of on-line discovery and the adaptivity to work with massive data. The experiments are conducted in this paper and the experimental results show that the proposed method is effective and efficient.

Analyzing and Boosting the Data Availability in Decentralized Online Social Networks

Maintaining Data Availability DA is a big challenge in Decentralized Online Social Networks DOSN. Nowadays, the limitation of the storage capacity in DOSN becomes a critical factor that jeopardizes the DA. Therefore, it is desired to determine the relation between the storage capacity of DOSN and the level of DA, and develop an approach to mitigating the limitation of storage capacity. This paper addresses these issues. In this paper, a probabilistic DA model over storage capacity is established. A novel method is then proposed to predict the DA on the fly. Further, a Cloud-assisted DOSN CDOSN framework is proposed to enhance the storage capacity and the DA in DOSN. This paper conducts the detailed quantitative analysis about the storage capacity and the DA in CDOSN. Extensive simulation experiments have been conducted to evaluate the effectiveness of the DA model, the on-the-fly prediction and the CDOSN framework.