Realizing Accelerated Cost-Effective Distributed RAID

The exponential growth in user and application data entails new means for providing fault tolerance and protection against data loss. High Performance Com- puting (HPC) storage systems, which are at the forefront of handling the data del- uge, typically employ hardware RAID at the backend. However, such solutions are costly, do not ensure end-to-end data integrity, and can become a bottleneck during data reconstruction. In this paper, we design an innovative solution to achieve a flex- ible, fault-tolerant, and high-performance RAID-6 solution for a parallel file system (PFS). Our system utilizes low-cost, strategically placed GPUs — both on the client and server sides — to accelerate parity computation. In contrast to hardware-based approaches, we provide full control over the size, length and location of a RAID array on a per file basis, end-to-end data integrity checking, and parallelization of RAID array reconstruction. We have deployed our system in conjunction with the widely-used Lustre PFS, and show that our approach is feasible and imposes ac- ceptable overhead.

A Framework for Prototyping and Reasoning about Distributed Systems

A framework supporting fast prototyping as well as tuning of distributed applications is presented. The approach is based on the adoption of a formal model that is used to describe the orchestration of distributed applications. The formal model (Orc by Misra and Cook) can be used to support semi-formal reasoning about the applications at hand. The paper describes how the framework can be used to derive and evaluate alternative orchestrations of a well know parallel/distributed computation pattern; and shows how the same formal model can be used to support generation of prototypes of distributed applications skeletons directly from the application description.

Management in distributed systems: A semi-formal approach

The reverse engineering of a skeleton based programming environment and redesign to distribute management activities of the system and thereby remove a potential single point of failure is considered. The Ore notation is used to facilitate abstraction of the design and analysis of its properties. It is argued that Ore is particularly suited to this role as this type of management is essentially an orchestration activity. The Ore specification of the original version of the system is modified via a series of semi-formally justified derivation steps to obtain a specification of the decentralized management version which is then used as a basis for its implementation. Analysis of the two specifications allows qualitative prediction of the expected performance of the derived version with respect to the original, and this prediction is borne out in practice.

Distribution Network Voltage Support Using Sensitivity-based Dispatch of Distributed Generation

This paper is concerned with the voltage and reactive power issues surrounding the connection of Distributed Generation (DG) on the low-voltage (LV) distribution network. The presented system-wide voltage control algorithm consists of three stages. Firstly available reactive power reserves are utilized. Then, if required, DG active power output is curtailed. Finally, curtailment of non-critical site demand is considered. The control methodology is tested on a variant of the 13-bus IEEE Node Radial Distribution Test Feeder. The presented control algorithm demonstrated that the distribution system operator (DSO) can maintain voltage levels within a desired statutory range by dispatching reactive power from DG or network devices. The practical application of the control strategy is discussed.

Performance analysis of switch-and-stay combining in two-way relay systems with analog network coding and time-division broadcast protocols

In this paper, weconsider switch-and-stay combining (SSC) in two-way relay systems with two amplify-and-forward relays, one of which is activated to assist the information exchange between the two sources. The system operates in either analog network coding (ANC) protocol where the communication is only achieved with the help of the active relay or timedivision broadcast (TDBC) protocol where the direct link between two sources can be utilized to exploit more diversity gain. In both cases, we study the outage probability and bit error rate (BER) for Rayleigh fading channels. In particular, we derive closed-form lower bounds for the outage probability and the average BER, which remain tight for different fading conditions. We also present asymptotic analysis for both the outage probability and the average BER at high signalto-noise ratio. It is shown that SSC can achieve the full diversity order in two-way relay systems for both ANC and TDBC protocols with proper switching thresholds. Copyright © 2014 John Wiley & Sons, Ltd.

Distributed Region-Based Memory Allocation and Synchronization

We present DRASync, a region-based allocator that implements a global address space abstraction for MPI programs with pointer-based data structures. The main features of DRASync are: (a) it amortizes communication among nodes to allow efficient parallel allocation in a global address space; (b) it takes advantage of bulk deallocation and good locality with pointer-based data structures; (c) it supports ownership semantics of regions by nodes akin to reader–writer locks, which makes for a high-level, intuitive synchronization tool in MPI programs, without sacrificing message-passing performance. We evaluate DRASync against a state-of-the-art distributed allocator and find that it produces comparable performance while offering a higher-level abstraction to programmers.