Pieter-Jan Maenhaut

Migrating legacy software to the cloud: approach and verification by means of two medical software use cases

Cloud computing is a technology that enables elastic, on‐demand resource provisioning, allowing application developers to build highly scalable systems. Multi‐tenancy, the hosting of multiple customers by a single application instance, leads to improved efficiency, improved scalability, and less costs. While these technologies make it possible to create many new applications, legacy applications can also benefit from the added flexibility and cost savings of cloud computing and multi‐tenancy. In this article, we describe the steps required to migrate existing applications to a public cloud environment, and the steps required to add multi‐tenancy to these applications. We present a generic approach and verify this approach by means of two case studies, a commercial medical communications software package mainly used within hospitals for nurse call systems and a schedule planner for managing medical appointments. Both case studies are subject to stringent security and performance constraints, which need to be taken into account during the migration. In our evaluation, we estimate the required investment costs and compare them to the long‐term benefits of the migration. Copyright

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

Multi-tenancy leads to improved efficiency, improved scalability, and lower costs. With the recent evolution of Cloud Computing and Software-as-a-Service (SaaS) in particular, a flexible and scalable multi-tenant architecture is becoming highly important. In multi-tenant applications, each tenant has its own users and administrators and tenants even tend to be divided into multiple subtenants. As the number of tenants grows, the number of users and amount of data grows, thus a scalable architecture for the access control system is needed. The question arises how to distribute the users and data over multiple database instances. In this paper we present a hierarchical data management approach, taking performance metrics into account, for structuring the storage of tenant data in large multi-tenant environments. We introduce a logical representation of the tenants, the tenant tree, and make a mapping to the physical storage by introducing three models for load-balancing. Next, we focus on how to efficiently locate the required data and introduce multiple search approaches. We characterize the impact on the performance both theoretically and experimentally. Experiments confirm that the theoretical analysis is in line with the experimental results. When the amount of data increases significantly, dividing the data over multiple datastores in an efficient way will eliminate the overhead and lead to a performance gain, especially if most of the data is located at the leaf nodes of the tenant tree.

Scalable user data management in multi-tenant cloud environments

The rise of cloud computing and its elastic, on-demand resource provisioning introduces the need for a flexible and scalable multi-tenant architecture. In a multi-tenant application every tenant (client) makes use of shared application instances, but each tenant typically has its own user data. The shared application instance behaves like a private instance by guaranteeing both data separation and performance separation for every tenant. As the number of tenants increases, the amount of data grows. A scalable solution for the storage is needed, allowing tenant data to be divided over multiple database instances, but taking into account performance isolation and custom data assurance policies. In this paper we introduce an abstraction layer for achieving high scalability for the storage of tenant data. This layer uses data allocation algorithms to determine an acceptable allocation of tenant data to different databases. We describe a mathematical model for the allocation of tenant data which can be optimized using existing linear programming techniques, and introduce the BDAA-n and FDAA, two algorithms that will find an optimal allocation of data by iterating over the possible permutations. The proposed solutions are evaluated based on their flexibility, complexity and efficiency. The flexibility of the BDAA and FDAA makes them easy to customize and extend to fit most scenarios, but the algorithms will achieve best results for tenants with a limited number of subtenants. Linear programming is an alternative for tenants with a higher number of subtenants, but the customizability of the algorithm for specific use cases is limited due to the need for linear functions.

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

Cloud computing is a technology that enables elastic, on-demand resource provisioning. Migrating applications to the cloud can increase their elasticity, allowing them to adapt to workload changes by dynamically allocating resources. In a multi-tenant application multiple client organizations, each referred to as tenants, make use of one or more shared application instances. These shared instances must however behave like a private instance by guaranteeing both data separation and performance isolation for every tenant. In order to achieve high scalability, a multi-tenant application running on the elastic cloud requires a flexible and scalable architecture for both the computational resources and the storage resources. In this paper we present and evaluate the design of a data management framework which can be used to extend existing multi-tenant cloud applications in order to achieve high scalability of the storage resources. We describe the most important components, and discuss important design choices. The framework invokes data allocation algorithms in order to find a feasible allocation of tenant data resulting in a minimal operating cost and a maximal performance, while taking no more than 10 ms to execute.

Design of a hierarchical software-defined storage system for data-intensive multi-tenant cloud applications

Software-Defined Storage (SDS) is an evolving concept in which the management and provisioning of data storage is decoupled from the physical storage hardware. Data-intensive multi-tenant SaaS applications running on the public cloud could benefit from the concepts introduced by SDS by managing the allocation of tenant data from the tenants perspective, taking custom tenant policies and preferences into account. In this paper, we propose the design of a scalable multi-tenant SDS system. In our approach, tenants are hierarchically clustered based on multiple scenario-specific characteristics. The storage elasticity component of the SDS system is responsible for the dynamic (re-)allocation of tenant data over the available storage resources. It invokes the Hierarchical Bin Packing algorithm introduced in this paper to determine an optimized distribution of tenant data based on the hierarchical tenant tree. We evaluate our system by means of two case studies based on real-life data sets. Experiments confirm that the Hierarchical Bin Packing algorithm achieves a good performance, with execution times below 100 ms to calculate the allocation for 1000 tenants in a worst-case scenario. Furthermore, our system achieves an average utilization of the storage resources close to the configured allocation factor, with reallocation of tenant data balanced over time.

A simulation tool for evaluating the constraint-based allocation of storage resources for multi-tenant cloud applications

Cloud computing is closely related to multi-tenancy, as it relies on resources that are shared among multiple clients. The provisioning and management of storage resources for cloud applications is an interesting research topic, as reallocation of data over time should be minimised, and the developed strategy should guarantee both data separation and performance isolation for every tenant. In this demo, we present a simulation tool for evaluating and comparing different data allocation strategies. Evaluation using real implementations can be very expensive and time consuming, and is not always possible, due to the scale and complexity of the infrastructure on which they are intended to run. The simulator aids as a tool for inexpensive and rapid evaluation of new techniques, and to validate and finetune new data allocation strategies.

Resource Allocation in the Cloud: From Simulation to Experimental Validation

With cloud computing, the efficient management of resources is of great importance as an increased utilization of the available resources can result in higher scalability and significant energy and cost reductions. Experimental validation of novel resource management strategies is costly and time consuming, and often requires in-depth knowledge of and control over the underlying cloud platform. As a result, many novel strategies are only evaluated by means of simulations, in which the whole cloud computing environment is modelled and simulated. Nonetheless, experimental validation should also be considered during the validation, as these types of experiments can often result in new insights or they can be used to fine-tune some specific parameters. In this paper we present a general approach for the experimental validation of cloud resource management strategies, together with the introduction of a cloud testbed adapter which was designed to facilitate the step from simulations towards experimental validation on physical cloud testbeds. We illustrate our solution by means of two case studies, focusing on two different types of testbeds. The adapter mainly acts as a dispatcher towards specific services of the evaluated cloud setup, and allows researchers to easily validate their ideas without having to dive deep into the complex details of the underlying cloud platform.

Demo abstract: RPiaaS: A raspberry pi testbed for validation of cloud resource management strategies

With cloud computing, efficient resource management is of great importance, as it has a direct impact on the scalability of the cloud application, and can result in significant energy and cost reductions. In recent years, a lot of research has been done regarding the management of cloud resources, resulting in multiple novel resource allocation strategies. Validation of these strategies however is often only based on simulations, as large experiments using real cloud infrastructure are both expensive and time-consuming. In this demo we present RPiaaS, a low-cost and energy-efficient cloud testbed built using Raspberry Pis. The testbed provides an easy-to-use environment for the initial evaluation of novel cloud resource management strategies, and is designed to facilitate the step from simulations towards experimental evaluations on larger cloud testbeds.

A dynamic Tenant-Defined Storage system for efficient resource management in cloud applications

Abstract Software-Defined Storage (SDS) is an evolving concept for the management of data storage from the softwares perspective. Multi-tenant applications running on the cloud can benefit from the concepts introduced by SDS by managing the allocation of data storage from the tenants perspective. A multi-tenant application should guarantee both data separation and performance isolation towards every tenant, and migration of tenant data over time should be minimized as this is both an expensive and time consuming operation. Furthermore, with cloud computing compliance with regulatory policies regarding the storage of data remains a key hurdle, as end users often have no way to specify their requirements. In this article, we present a dynamic and extensible system for the management of storage resources in multi-tenant cloud applications. In the presented approach, tenants are hierarchically clustered based on multiple scenario-specific characteristics, and allocated to storage resources using a hierarchical bin packing algorithm (static allocation). As the load changes over time, the system corresponds to these changes by reallocating storage resources when required (dynamic reallocation). We evaluate both the static and dynamic behavior of our system. Experiments confirm that the system achieves good results regarding the average bin usage, migrations over time and clustering of related tenants. On average, less than 0.01% of the total amount of data is reallocated during each migration using the dynamic Hierarchical First-Fit Decreasing (dHFFD) algorithm while achieving an average bin usage similar to First-Fit Decreasing (FFD). The dynamic Hierarchical Greedy Decreasing (dHGD) algorithm reduces the number of migrations by a factor 100 compared to dHFFD, but at the cost of provisioning additional storage instances.