Characterizing the performance of tenant data management in multi-tenant cloud authorization systems

Abstract

The cloud computing is an Internet-based computing emerging as a new architecture which aims to give reliable, customizable and QoS guaranteed dynamic environment for end-users. As multi-tenancy is one of the key features of cloud computing where service providers and users have scalable and economic benefits on same cloud platforms. In cloud computing environment the execution process requires resource management due to the processing capability is high to the resource ratio. The aim of the system is to handle resource management by executing scientific workflows. The locating and assigning of free resources is handled through the Cloud-based Workflow Scheduling Algorithm (CWSA) policy. The simulation results shows that the scheduling algorithm improves the performance of scientific workflows and helps in minimization of workflow completion time, tardiness, execution cost and use of idle resources of cloud using simulator Workflowsim.

Design and evaluation of a hierarchical multi-tenant data management framework for cloud applications

“…The work presented in this paper extends previous work as described in [1], [2]. In [1] we introduced a hierarchical method for organizing tenants and storage of tenant data, and characterized the impact on the performance in a theoretical way.…”

“…In [1] we introduced a hierarchical method for organizing tenants and storage of tenant data, and characterized the impact on the performance in a theoretical way. In [2], we presented multiple data allocation algorithms for finding an acceptable allocation of tenant data to different database instances.…”

“…In a multi-tenant application, the tenants and subtenants can be logically represented using a tree structure, the tenant tree [1]. In this tree, every node represents a tenant or subtenant, and the root represents the application provider.…”

“…A first possible metric is the number of database instances as more instances will result in a higher cost. A second possible metric is the average response time for each tenant and for the whole system, which can be calculated using the equations introduced in [1]. The cost function can also take into account the current load on the different database instances.…”

A Systematic Mapping Study on the Multi-tenant Architecture of SaaS Systems

“…Maenhaut et al [34] developed an approach for data management in a hierarchical way and taking into account some performance metrics. The main question addressed concerned the distribution of users and data into multiple instances of database.…”