Matt R. Hogstrom

Software defined environments: an introduction

During the past few years, enterprises have been increasingly aggressive in moving mission-critical and performance-sensitive applications to the cloud, while at the same time many new mobile, social, and analytics applications are directly developed and operated on cloud computing platforms. These two movements are encouraging the shift of the value proposition of cloud computing from cost reduction to simultaneous agility and optimization. These requirements (agility and optimization) are driving the recent disruptive trend of software defined computing, for which the entire computing infrastructure--compute, storage and network--is becoming software defined and dynamically programmable. The key elements within software defined environments include capability-based resource abstraction, goal-based and policy-based workload definition, and outcome-based continuous mapping of the workload to the available resources. Furthermore, software defined environments provide the tooling and capabilities to compose workloads from existing components that are then continuously and autonomously mapped onto the underlying programmable infrastructure. These elements enable software defined environments to achieve agility, efficiency, and continuous outcome-optimized provisioning and management, plus continuous assurance for resiliency and security. This paper provides an overview and introduction to the key elements and challenges of software defined environments.

Benchmarking autonomic capabilities: promises and pitfalls

Benchmarks provide a way to quantify progress in a field. Our goal is to produce a suite of benchmarks covering the four categories of autonomic capabilities: self-configuring, self-healing, self-optimizing, and self-protecting (IBM, 2003). This is not an easy task, however, and in this paper we identify several of the challenges and pitfalls that must be confronted to extend benchmarking technology beyond its traditional basis in performance evaluation.

Sizing multi-space in heap for application isolation

In this paper, we present a sizing algorithm using resonant model based on a proposed novel heap structure - multiple spaces in heap. Experiments using the algorithm and selected GC method show that, in average, the performance overhead from managing multi-spaces in heap can be reduced from 8.38% to 4.25% when CPU utilization of server is 40% and from 42.42% to 3.52% when CPU utilization of the server is 70%.

Partition-based heap memory management in an application server

Heap is an important shared resource in Java virtual machine. A problem with memory management in one component can affect the whole system and even result in crashing the virtual machine. In this paper, we propose an partition-based approach to manage heap in an application server. In our approach, the shared heap is divided into logical partitions, in which instances of application components and server components are allocated separately.