Application Of Resources Research Articles

Towards Proactive Risk-Aware Cloud Cost Optimization Leveraging Transient Resources

Low-cost transient resources such as Amazon's Elastic Compute Cloud (EC2) Spot instances can be opportunistically leveraged to reduce the ongoing costs of cloud applications. However, they are susceptible to unilateral revocations by the vendor making them a risky proposition for long-running applications with strict performance requirements. It is challenging to effectively balance the cost savings that transient resources provide with the associated revocation risk which, if realised, can impact application performance. To address this challenge, we propose an approach for risk-aware cloud cost optimization that is inspired by the concept of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">portfolio diversification</i> . <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Contract diversification</i> mitigates the revocation risk by procuring the required compute capacity as a mixed portfolio of transient and non-transient resources. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Resource diversification</i> further diversifies the risk by using multiple transient resource types. Using our approach, consumers can leverage contract and resource diversification to proactively (re-)configure their application's resource portfolio to handle workload and resource price fluctuations while minimizing ongoing cost and keeping ongoing revocation risk within tolerable limits. Simulative evaluation using three real-world workload traces and Amazon's EC2 offerings demonstrate that our proposed approach can achieve meaningful cost savings compared to the baseline costs, while significantly reducing the portfolio's exposure to revocation risk.

The matrices and constraints of GT/AG splice sites of more than 1000 species/lineages

To provide a resource for the splice sites (SS) of different species, we calculated the matrices of nucleotide compositions of about 38 million splice sites from >1000 species/lineages. The matrices are enriched of aGGTAAGT (5′SS) or (Y)6N(C/t)AG(g/a)t (3′SS) overall; however, they are quite diverse among hundreds of species. The diverse matrices remain prominent even under sequence selection pressures, suggesting the existence of diverse constraints as well as U snRNAs and other spliceosomal factors and/or their interactions with the splice sites. Using an algorithm to measure and compare the splice site constraints across all species, we demonstrate their distinct differences quantitatively. As an example of the resource's application to answering specific questions, we confirm that high constraints of particular positions are significantly associated with transcriptome-wide, increased occurrences of alternative splicing when uncommon nucleotides are present. More interestingly, the abundance of alternative splicing in 16 species correlates with the average constraint index of splice sites in a bell curve. This resource will allow users to assess specific sequences/splice sites against the consensus of every Ensembl-annotated species, and to explore the evolutionary changes or relationship to alternative splicing and transcriptome diversity. Web-search or update features are also included.

Fuzzy logic-based elasticity controller for autonomic resource provisioning in parallel scientific applications: A cloud computing perspective

Parallel scientific applications generate internal workload (in terms of threads and data structures) during its execution life-cycle, which requires adequate amount of computing resources to meet the service-level-agreements. In this paper, we propose a novel elasticity controller for autonomic resource provisioning which is a combination of fuzzy logic control and autonomic computing. This controller computes the required amount of processor core(s) considering the information about application's internal workload and resource utilization of the virtual machine. Finally, the application's application program interface (API) call performs operation (request and release) of virtual resources to the cloud. To the best of our knowledge, this is the first study that uses CloudSim toolkit to address: (a) execution of parallel application, and (b) fine-grained resource provisioning. The experimental results show that the proposed approach minimizes the finish time by up to 64% and increases the resource utilization by up to 36% compared with other approaches.

Exploration of energy efficient memory organisations for dynamic multimedia applications using system scenarios

We propose a memory-aware system scenario approach that exploits variations in memory needs during the lifetime of an application in order to optimize energy usage. Different system scenarios capture the application's different resource requirements that change dynamically at run-time. In addition to computational resources, the many possible memory platform configurations and data-to-memory assignments are important system scenario parameters. In this work we focus on clustering of different memory requirements into groups and presenting the system scenario generation in detail. The clustering is a non-trivial problem due to the many different memory requirements, which leads to a very large exploration space. An extended memory model is used as a practical enabler, in order to evaluate the methodology. The memory models include existing state-of-the-art memories, available from industry and academia, and we show how they are employed during the system design exploration phase. Both commercial SRAM and standard cell based memory models are explored in this study. The effectiveness of the proposed methodology is demonstrated and tested using a large set of multimedia benchmarks published in the Polybench, Mibench and Mediabench suites, representative for the domain of multimedia applications. Reduction in energy consumption in the memory subsystem ranges from 35 to 55 % for the chosen set of benchmarks.

Scalable problem-oriented approach for dynamic verification of embedded systems

A model-based problem-oriented approach for the dynamic verification of functional properties of embedded systems is presented. It is a generic and scalable approach, especially useful in systems where embedded devices are tightly coupled to physical processes. A set of modeling guidelines and abstraction layers are proposed that provide a better understanding and visibility of an application's behavior and resource usage, and of the interactions between the different components of an embedded device and the physical process it interacts with. An application example is given for the design and verification of a digital PID controller that integrates Simulink models, SystemC models and an ARM Cortex-M3 processor emulator.

Resource overbooking and application profiling in a shared Internet hosting platform

In this article, we present techniques for provisioning CPU and network resources in shared Internet hosting platforms running potentially antagonistic third-party applications. The primary contribution of our work is to demonstrate the feasibility and benefits of overbooking resources in shared Internet platforms. Since an accurate estimate of an application's resource needs is necessary when overbooking resources, we present techniques to profile applications on dedicated nodes, possibly while in service, and use these profiles to guide the placement of application components onto shared nodes. We then propose techniques to overbook cluster resources in a controlled fashion. We outline an empirical appraoch to determine the degree of overbooking that allows a platform to achieve improvements in revenue while providing performance guarantees to Internet applications. We show how our techniques can be combined with commonly used QoS resource allocation mechanisms to provide application isolation and performance guarantees at run-time. We implement our techniques in a Linux cluster and evaluate them using common server applications. We find that the efficiency (and consequently revenue) benefits from controlled overbooking of resources can be dramatic. Specifically, we find that overbooking resources by as little as 1% we can increase the utilization of the cluster by a factor of two, and a 5% overbooking yields a 300--500% improvement, while still providing useful resource guarantees to applications.

Overshadow

Commodity operating systems entrusted with securing sensitive data are remarkably large and complex, and consequently, frequently prone to compromise. To address this limitation, we introduce a virtual-machine-based system called Overshadow that protects the privacy and integrity of application data, even in the event of a total OScompromise. Overshadow presents an application with a normal view of its resources, but the OS with an encrypted view. This allows the operating system to carry out the complex task of managing an application's resources, without allowing it to read or modify them. Thus, Overshadow offers a last line of defense for application data. Overshadow builds on multi-shadowing, a novel mechanism that presents different views of "physical" memory, depending on the context performing the access. This primitive offers an additional dimension of protection beyond the hierarchical protection domains implemented by traditional operating systems and processor architectures. We present the design and implementation of Overshadow and show how its new protection semantics can be integrated with existing systems. Our design has been fully implemented and used to protect a wide range of unmodified legacy applications running on an unmodified Linux operating system. We evaluate the performance of our implementation, demonstrating that this approach is practical.

Overshadow

Commodity operating systems entrusted with securing sensitive data are remarkably large and complex, and consequently, frequently prone to compromise. To address this limitation, we introduce a virtual-machine-based system called Overshadow that protects the privacy and integrity of application data, even in the event of a total OScompromise. Overshadow presents an application with a normal view of its resources, but the OS with an encrypted view. This allows the operating system to carry out the complex task of managing an application's resources, without allowing it to read or modify them. Thus, Overshadow offers a last line of defense for application data. Overshadow builds on multi-shadowing, a novel mechanism that presents different views of "physical" memory, depending on the context performing the access. This primitive offers an additional dimension of protection beyond the hierarchical protection domains implemented by traditional operating systems and processor architectures. We present the design and implementation of Overshadow and show how its new protection semantics can be integrated with existing systems. Our design has been fully implemented and used to protect a wide range of unmodified legacy applications running on an unmodified Linux operating system. We evaluate the performance of our implementation, demonstrating that this approach is practical.

Overshadow

Commodity operating systems entrusted with securing sensitive data are remarkably large and complex, and consequently, frequently prone to compromise. To address this limitation, we introduce a virtual-machine-based system called Overshadow that protects the privacy and integrity of application data, even in the event of a total OScompromise. Overshadow presents an application with a normal view of its resources, but the OS with an encrypted view. This allows the operating system to carry out the complex task of managing an application's resources, without allowing it to read or modify them. Thus, Overshadow offers a last line of defense for application data. Overshadow builds on multi-shadowing, a novel mechanism that presents different views of "physical" memory, depending on the context performing the access. This primitive offers an additional dimension of protection beyond the hierarchical protection domains implemented by traditional operating systems and processor architectures. We present the design and implementation of Overshadow and show how its new protection semantics can be integrated with existing systems. Our design has been fully implemented and used to protect a wide range of unmodified legacy applications running on an unmodified Linux operating system. We evaluate the performance of our implementation, demonstrating that this approach is practical.

Specification and support of adaptable networked multimedia

Accessing multimedia information in a networked environment introduces problems that do not exist when the same information is accessed locally. These problems include: (1) competing for network resources within and across applications, (2) synchronizing data arrivals from various sources within an application, and (3) supporting multiple data representations across heterogeneous hosts. Often, special purpose algorithms can be defined to deal with these problems, but these solutions are usually restricted to the context of a single application. A more general approach is to define an adaptable infrastructure that can be used to manage resources flexibly for all currently active applications. This paper describes such an approach. We begin by introducing a general framework for partitioning control responsibilities among a number of cooperating system and application components. We then describe a specification formalism that can be used to encode an application's resource requirements, synchronization needs, and interaction control. This specification can be used to coordinate the activities of the application, the operating system(s) and a set of adaptive information objects in matching the (possibly flexible) needs of an application to the resources available in an environment at run time. The benefits of this approach are that it allows adaptable application support with respect to system resources and that it provides a natural way to support heterogeneity in multimedia networks and multimedia data.

Viewpoint

To provide a resource for the splice sites (SS) of different species, we calculated the matrices of nucleotide compositions of about 38 million splice sites from >1000 species/lineages. The matrices are enriched of aGGTAAGT (5′SS) or (Y)6N(C/t)AG(g/a)t (3′SS) overall; however, they are quite diverse among hundreds of species. The diverse matrices remain prominent even under sequence selection pressures, suggesting the existence of diverse constraints as well as U snRNAs and other spliceosomal factors and/or their interactions with the splice sites. Using an algorithm to measure and compare the splice site constraints across all species, we demonstrate their distinct differences quantitatively. As an example of the resource's application to answering specific questions, we confirm that high constraints of particular positions are significantly associated with transcriptome-wide, increased occurrences of alternative splicing when uncommon nucleotides are present. More interestingly, the abundance of alternative splicing in 16 species correlates with the average constraint index of splice sites in a bell curve. This resource will allow users to assess specific sequences/splice sites against the consensus of every Ensembl-annotated species, and to explore the evolutionary changes or relationship to alternative splicing and transcriptome diversity. Web-search or update features are also included.