Towards Elastic Operating Systems
نویسندگان
چکیده
Realizing elasticity in cloud applications today is often a cumbersome process, requiring applications to integrate with services like elastic load balancers and/or be rewritten to accommodate distributed frameworks like map/reduce or cluster-based operating systems. In this paper, we introduce the concept of ElasticOS, which enables a process (or even a single thread) to stretch its associated resource boundaries across multiple machines automatically, expanding and contracting on demand without requiring the application to be re-designed or configured with a complex combination of additional tools and frameworks. Our initial implementation within Linux 3.2 and a study of a MySQL execution trace provide hope that the ElasticOS vision is achievable.
منابع مشابه
Elastic Manycores - How to Bring the OS Back into the Scheduling Game?
By introducing asynchronous lambdas, many programming languages have leaped ahead in the race for programmable manycore systems, leaving the operating system and its scheduler behind. Instead of hiding application-inherent parallelism behind pools of threads with opaque behavior, asynchronous lambdas allow programmers to explicitly state which parts of a program can be executed in parallel and ...
متن کاملScalable Elastic Systems Architecture
Cloud computing has spurred the exploration and exploitation of elastic access to large scales of computing. To date the predominate building blocks by which elasticity has been exploited are applications and operating systems that are built around traditional computing infrastructure and programming models that are in-elastic or at best coarsely elastic. What would happen if application themse...
متن کاملElastic systems: Towards cyber-physical ecosystems of people, processes, and things
Pervasive mobility and an exponential increase in the number of connected devices are adding to IT complexity. Users are bypassing traditional IT to access cloud-based services. Boundaries between computing systems, people, and things are disappearing. New approaches are required to manage today’s and tomorrow’s increasingly connected and heterogeneous ecosystems of people, computing processes,...
متن کاملEvaluating Common Strategies for the Efficiency of Feature Selection in the Context of Microarray Analysis
The recent explosion of high-throughput technology has been accompanied by a corresponding rapid increase in the number of new statistical methods for developing prognostic and predictive signatures. Three commonly used feature selection techniques for time-to-event data: single gene testing (SGT), Elastic net and the Maximizing R Square Algorithm (MARSA) are evaluated on simulated datasets tha...
متن کاملCloud RAN challenges and solutions
In this paper we take an overall look at key technical challenges in the evolution of the Radio Access Network (RAN) architecture towards Cloud RAN, and solutions to overcome them. To address fronthaul limitations, we examine the implications and tradeoffs enabled by functional splits on fronthaul needs, system performance, and centralization scale. We examine the architecture of algorithms for...
متن کامل