A Permission-Based Distributed Mutual Exclusion Algorithm allowing Quality of Service (PBDMEAQoS)
Journal Title: EAI Endorsed Transactions on Cloud Systems - Year 2017, Vol 3, Issue 10
Abstract
The main purpose of mutual exclusion in a distributed environment is to control access to a shared resource. Large-scale distributed systems such as clouds or grids provide shared informatics resources to its clients. In this type of environment, Service Level Agreement (SLA) allows for the definition of a type of quality of service (QoS) between a resource provider and a client. This means that some constraints like priority, response time or reliability must be taken into consideration to maintain a good QoS. Permission-based algorithms are costly in messages, not easily extensible and naturally more robust, pertaining to failures when compared to token algorithms. In this paper, we propose two mutual exclusion algorithms, integrating priority and time constraints for each request, via deadline and execution time in the critical section, with the aim of ensuring a proper service quality. The proposed algorithms are based on a logical structure of nodes in complete binary trees. The algorithms named PBDMEAQoSα and PBDMEAQoSβ are SLA (Service Level Agreement) based. They integrate priority dynamics, which cumulates with the age of a request. PBDMEAQoSα requires 3log2N messages per access to critical section and a synchronization delay of 2log2N for a set of N nodes competing for the critical resource. PBDMEAQoSβ requires 2log2N messages per access to critical section and a synchronization delay of log2N.
Authors and Affiliations
E. D. Ngounou Ntoukam, V. C. Kamla, J. C. Kamgang
A Fair Cloud Resource Allocation using Data Envelopment Analysis
Internet technology is advancing with each passing day, the user's demand is also increasing. Of course the users will more concern to quality of service. The vendors must find out a win win method of resource allocation...
CloudTUI-FTS: a user-friendly and powerful tool to manage Cloud Computing Platforms
The NIST defines Cloud Computing as a model for en-abling ubiquitous network access to a shared pool of con-figurable computing resources. Thanks to the popularity of Cloud Computing and its various area of applicability...
A New QoE-Driven Video Cache Allocation Scheme for Mobile Cloud Server
With the advent of mobile cloud computing, video cache technologies at local cellular networks have attracted extensive attention. Nevertheless, existing video cache allocation schemes mostly made decisions only accordin...
Database Migration on Premises to AWS RDS
For the past four decades, the traditional relational databases have been in use in Information Technology industry. There was a phenomenal conversion in the IT industry in terms of commercial applications in the previou...
Savant: A Framework for Supporting Content Accountability in Information Centric Networks
The Information Centric Networking (ICN) paradigm offers solutions to some of the functional and performance limitations of the current Internet architecture by offering secure, efficient and scalable mechanisms for the...