Elastic Computing - a novel paradigm for distributed systems

This talk, which is based on our newest findings and experiences from research and industrial projects, addresses one of the most relevant challenges for a decade to come: How to integrate the Internet of Things with software, people, and processes, considering modern Cloud Computing and Elasticity principles. Elasticity is seen as one of the main characteristics of Cloud Computing today. Is elasticity simply scalability on steroids? This talk addresses the main principles of elasticity, presents a fresh look at this problem, and examines how to integrate people, software services, and things into one composite system, which can be modeled, programmed, and deployed on a large scale in an elastic way. This novel paradigm has major consequences on how we view, build, design, and deploy ultra-large scale distributed systems.

Towards a unified management of applications on heterogeneous clouds

The diversity in the way cloud providers o↵er their services, give their SLAs, present their QoS, or support di↵erent technologies, makes very difficult the portability and interoperability of cloud applications, and favours the well-known vendor lock-in problem. We propose a model to describe cloud applications and the required resources in an agnostic, and providers- and resources-independent way, in which individual application modules, and entire applications, may be re-deployed using different services without modification. To support this model, and after the proposal of a variety of cross-cloud application management tools by different authors, we propose going one step further in the unification of cloud services with a management approach in which IaaS and PaaS services are integrated into a unified interface. We provide support for deploying applications whose components are distributed on different cloud providers, indistinctly using IaaS and PaaS services.

Queueuing system with failures and priorities

Queueing theory provides models, structural insights, problem solutions and algorithms to many application areas. Due to its practical applicability to production, manufacturing, home automation, communications technology, etc, more and more complex systems requires more elaborated models, tech- niques, algorithm, etc. need to be developed. Discrete-time models are very suitable in many situations and a feature that makes the analysis of discrete time systems technically more involved than its continuous time counterparts. In this paper we consider a discrete-time queueing system were failures in the server can occur as-well as priority messages. The possibility of failures of the server with general life time distribution is considered. We carry out an extensive study of the system by computing generating functions for the steady-state distribution of the number of messages in the queue and in the system. We also obtain generating functions for the stationary distribution of the busy period and sojourn times of a message in the server and in the system. Performance measures of the system are also provided.

Insights into the Fallback Path of Best-Effort Hardware Transactional Memory Systems

Current industry proposals for Hardware Transactional Memory (HTM) focus on best-effort solutions (BE-HTM) where hardware limits are imposed on transactions. These designs may show a significant performance degradation due to high contention scenarios and different hardware and operating system limitations that abort transactions, e.g. cache overflows, hardware and software exceptions, etc. To deal with these events and to ensure forward progress, BE-HTM systems usually provide a software fallback path to execute a lock-based version of the code. In this paper, we propose a hardware implementation of an irrevocability mechanism as an alternative to the software fallback path to gain insight into the hardware improvements that could enhance the execution of such a fallback. Our mechanism anticipates the abort that causes the transaction serialization, and stalls other transactions in the system so that transactional work loss is mini- mized. In addition, we evaluate the main software fallback path approaches and propose the use of ticket locks that hold precise information of the number of transactions waiting to enter the fallback. Thus, the separation of transactional and fallback execution can be achieved in a precise manner. The evaluation is carried out using the Simics/GEMS simulator and the complete range of STAMP transactional suite benchmarks. We obtain significant performance benefits of around twice the speedup and an abort reduction of 50% over the software fallback path for a number of benchmarks.