Storage Intensive Applications Research Articles

Optimal Resource Provisioning and Task Offloading for Network-Aware and Federated Edge Computing.

Compared to cloud computing, mobile edge computing (MEC) is a promising solution for delay-sensitive applications due to its proximity to end users. Because of its ability to offload resource-intensive tasks to nearby edge servers, MEC allows a diverse range of compute- and storage-intensive applications to operate on resource-constrained devices. The optimal utilization of MEC can lead to enhanced responsiveness and quality of service, but it requires careful design from the perspective of user-base station association, virtualized resource provisioning, and task distribution. Also, considering the limited exploration of the federation concept in the existing literature, its impacts on the allocation and management of resources still remain not widely recognized. In this paper, we study the network and MEC resource scheduling problem, where some edge servers are federated, limiting resource expansion within the same federations. The integration of network and MEC is crucial, emphasizing the necessity of a joint approach. In this work, we present NAFEOS, a proposed solution formulated as a two-stage algorithm that can effectively integrate association optimization with vertical and horizontal scaling. The Stage-1 problem optimizes the user-base station association and federation assignment so that the edge servers can be utilized in a balanced manner. The following Stage-2 dynamically schedules both vertical and horizontal scaling so that the fluctuating task-offloading demands from users are fulfilled. The extensive evaluations and comparison results show that the proposed approach can effectively achieve optimal resource utilization.

NetStor: Network and Storage Traffic Management for Ensuring Application QoS in a Hyperconverged Data-Center

For the rapid increase in resource requirements in large scale Data Centers (DCs), enterprises have brought hyperconverged architecture where the storage pool is built up by the individual storage components associated with different servers, and it is shared among all the Virtual Machines (VMs) or containers through a common network infrastructure. Due to the sharing of network bandwidth among the application generated network traffic and the storage traffic from shared storage infrastructure, quality of service (QoS) performances of networking and storage intensive applications are affected, which further impacts VM or container migrations with dynamic workload scenarios. In this article, we propose NetStor to ensure QoS for various collocated network and storage intensive workloads over a hyperconverged architecture and ensure QoS during VM or container migration. NetStor uses a workload estimation strategy for VMs and containers, and applies the strategic decisions for resource allocation and migration based on environmental learning and workload characterization. NetStor supports a dynamic QoS provisioning that is workload-agnostic catering to both VMs and containers, and is unique to the best of our knowledge. We have implemented NetStor over a hyperconverged DC architecture on a testbed and found that NetStor can enhance network performance significantly compared to other related mechanisms discussed in the literature.

Supporting mobility-aware computational offloading in mobile cloud environment

Mobile Cloud Computing (MCC) enables resource-constrained smartphones to run high processing and storage intensive applications through public clouds or cloudlet code offloading. However, handover support in the MCC context has not been thoroughly explored, since most works do not address the devices mobility during the offloading operation. This paper presents the Mobile Offloading System (MOSys), which supports seamless offloading operations during user mobility between wireless networks. To this end, MOSys benefits from the software-defined networking (SDN) paradigm for mobility management and remote caching techniques to reduce the offloading response time. Also, middleware is responsible for ensuring code and data offloading, profiling service, cloud discovery and application deployment. To evaluate the proposed system and to analyze mobility impact on the offloading performance, several experiments were conducted using different smartphones categories and benchmark applications, on three scenarios. Our results have shown that the MOSys’ mobility management application is energy efficient, especially considering the low-cost smartphone category, while remote caching proved to be an attractive alternative for reducing the offloading response time.

Address generators for linear systolic array

Systolic arrays (SAs) are very efficient architectures for multimedia processing, database management, and scientific computing applications that are characterized by a high number of data access. However, in these data transfer and storage intensive applications, memory access is often the limiting factor to the computation speed. Since the memory subsystem dominates the cost (area), performance and power consumption of the SA, we have to pay a special attention to how memory subsystem can benefit from customization. In this paper we consider memory organization of linear systolic array with bi-directional links (called BLSA) suitable for implementation of broad class of algorithms. We assume that memory is organized into distributed smaller physical memory modules. In order to provide high bandwidth in data access we have designed special hardware, called address generator unit (AGU). The function of AGU is threefold. First, during the initialization, it transforms host address space into BLSA address space. Second, provides efficient memory data access during BLSA operation. Third, performs fast data transfer between BLSA and host at the end of the computation. In this article, we examine the impact on area and performance of memory access related circuity in eliminating computational intensive offset address calculations performed in software by implementing the needed address transformations with the AGUs. By involving hardware AGUs we achieved a speedup of approximately two, compared to the software implementation of address calculation, with a hardware overhead of only 7.6% in the worst case.

Reducing Replication Overhead for Data Durability in DHT Based P2P System

DHT based p2p systems appear to provide scalable storage services with idle resource from many unreliable clients. If a DHT is used in storage intensive applications where data loss must be minimized, quick replication is especially important to replace lost redundancy on other nodes in reaction to failures. To achieve this easily, a simple replication method directly uses a consistent set, such as a leaf set and a successor list. However, this set is tightly coupled to the current state of nodes and the traffic needed to support this replication can be high and bursty under churn. This paper explores efficient replication methods that only glimpse a consistent set to select a new replica. Replicas are loosely coupled to a consistent set and we can eliminate the compulsory replication under churn. Because of a complication of the new replication methods, the careful data management is needed under churn for the correct and efficient data lookup. Results from a simulation study suggest that our methods can reduce network traffic enormously for high data durability.

NETWORK STORAGE SYSTEMS AND APPLICATIONS

Ubiquitous access to large quantities of information content is one of the main benefits anticipated from the emerging global interconnection of computer networks. One of several major factors in achieving this objective is the cost and performance of the distributed storage systems which will act as the repositories for the information. This article presents an overview of the architecture, major components and requirements for storage systems which can support distributed storage intensive applications.