Scientific workloads often require scalable computing resources. The traditional HPC paradigm provides large scale computing resources but requires IT specialists to buy and maintain large computer infrastructure in their organization. With the emergence of cloud computing, more and more scientists and engineers are moving their computing workloads from local clusters to public cloud. However, such a migration often requires experience both in understanding cloud architecture and cloud development skills, which can impede the efficiency and success of migration. This paper presents a cloud-based parallel and distributed computing platform to support scientific computing. With the Simulation Runner, scientists only need to submit their embarrassingly parallel scientific applications with appropriate arguments or parameters. There is no need to rebuild migrate cloud applications or purchase large computer infrastructures by themselves. The system also uses a file caching mechanism to improve performance and reduce the costs of data-intensive computing tasks. A 44X speedup was resulted from using 128 computing instances compared with premise high performance desktop computers. A comparison study on the performance of file cache is given at the end of the paper.

Traditional computer forensic tools suffer from several drawbacks: 1) information recorded by the operating system and application may not be enough for performing exact forensics, because such information is not tailored for forensic purpose; 2) evidence extraction is based on single computer; 3) evidence is vulnerable to be tampered; 4) volatile yet important evidence may not be recorded for forensic analysis. To overcome these limitations, this paper proposes a cloud-based proactive forensics framework to record state information across a set of computers (such as the cluster of computers that consist a cloud) for cross forensic analysis. Our forensic framework is built on Microsoft Azure and can be scaled easily to accommodate the increase or decrease of forensic targets. The information recorded by our proposed forensics framework may be volatile and the recording frequency can be customized. When a digital crime occurs, there is no need to speculate what happened, instead we can analyze and cross reference the recorded information to reconstruct the events occurred. We have conducted an experiment to assess the feasibility of our framework and found the result to be satisfactory.

While commercial off-the-shelf (COTS) operating systems (OS) have long been widely used, the issue regarding their robustness is far from being solved. Although many efforts have been made in this research domain, people still find it difficult to make choices among various OSs for robustness concerns. This paper proposes a reference model for OS robustness forecast and selection that aims to forecast the robustness of specific OSs under given operational profiles. At the same time, the model can select appropriate OSs as development/operating platforms that meet the particular robustness requirements of the target workloads. Our model combines OSspsila overall robustness with operational profiles and uses extensive tests on OS APIs to make our calculation. We have measured 255 APIs and C-library functions on windows XP and Vista, and 197 C-library functions on Linux 2.6.22 (Ubuntu 7.10). Our results show that on average Windows XP and Vista are more robust than Linux, but their performances are comparable under compute-intensive workloads. A demonstration of how these results are used in the proposed reference model for OSs robustness forecast and selection is given at the end.

Rollup, a key operation in OLAP queries, is to aggregate multidimensional data on dimensional hierarchies. While the operation can be efficiently implemented on regular hierarchies in data warehouse, its application to recursive hierarchies proved to be problematic. Due to the stratification restriction, aggregate is not permitted to be wrapped within SQL recursion. Representing rollup operations on recursive hierarchies as SQL recursive queries will cause considerable overhead and is thus inefficient. This paper proposes an iteration-based evaluation strategy that aims to solve this inefficiency problem in OLAP queries. In our solution, aggregation on recursive hierarchies is modeled as a binary operator tree that is stored in its postfix notation and executed by a push down stack. We also demonstrate how to seamlessly embed this novel strategy into data warehouse that is based on ORDBMS. Experiment results show that our proposed solution is quite efficient compared with the SQL recursive evaluation strategy

This paper presents a real-time primary-backup replication scheme to support fault-tolerant data access in a real-time environment. The main features of the system are fast response to client requests, bounded inconsistency between primary and backup, temporal consistency guarantee for replicated data, and quick recovery from failures. The paper defines external and interobject temporal consistency, the notion of phase variance, and builds a computation model that ensures such consistencies for replicated data deterministically where the underlying communication mechanism provides deterministic message delivery semantics and probabilistically where no such support is available. It also presents an optimization of the system and an analysis of the failover process which includes failover consistency and failure recovery time. An implementation of the proposed scheme is built within the x-kernel architecture on the MK 7.2 microkernel from the Open Group. The results of a detailed performance evaluation of this implementation are also discussed.

The paper presents a real-time primary-backup (RTPB) replication scheme for supporting fault-tolerant real-time applications. It formally defines two types of temporal consistency, namely external temporal consistency and inter-object temporal consistency. By introducing a key concept called phase variance, the authors are able to build temporal consistency models and derive necessary and sufficient conditions that can be used as the basis for update and transmission scheduling that achieve temporal consistency guarantees. Furthermore, they prove that the term phase variance used in the models can be bounded under various scheduling algorithms, namely EDF, rate monotonic and distance-constrained scheduling. A RTPB implementation was developed within the x-kernel architecture on the MK 7.2 microkernel and the results of a detailed performance evaluation is also discussed.

The primary-backup replication model is one of the commonly adopted approaches to providing fault tolerant data services. Its extension to the real time environment, however, imposes the additional constraint of timing predictability, which requires a bounded overhead for managing redundancy. The paper discusses the trade-off between reducing system overhead and increasing (temporal) consistency between the primary and backup, and explores ways to optimize such a system to minimize either the inconsistency or the system overhead while maintaining the temporal consistency guarantees of the system. An implementation built on top of the existing RTPB model (H. Zou and F. Jahanian, 1998) was developed within the x-kernel architecture on the Mach OSF platform running MK 7.2. Results of an experimental evaluation of the proposed optimization techniques are discussed.