IOStack - Software Defined Storage for Big Data
The main objective is to create IOStack: a Software-defined Storage toolkit for Big Data on top of the OpenStack platform. IOStack will enable efficient execution of virtualized analytics applications over virtualized storage resources thanks to flexible, automated, and low cost data management models based on software-defined storage (SDS).
The user need is to reduce the costs of Big Data Analytics thanks to Software Defined Storage Automation techniques. It is very complex to deploy and operate big data storage and analytic clusters. We will enable the virtualization of analytic technologies (OpenStack Sahara) and the automation and cost reduction of storage with SDS techniques.
Problems solved: optimization of virtualized data analytics services such as Spark/Hadoop, solving I/O Bottlenecks with SDS techniques, storage cost reduction thanks to data reduction techniques.
An example end-user who could benefit from IOSTACK is be a medium IaaS provider or companies offering/operating advanced storage and data analytics services at a low cost.
Our end-users are normally IaaS providers or companies operating big data storage and analytics resources. They will benefit mainly in simplicity, administration and cost reduction. Instead of operating dedicated clusters, they can virtualize and automate these services thanks to IOStack platform. The advantages of this include high return on investment, cost reduction, and automation.
The IOStack platform will provide a solution in the OpenStack platform to the automated management and deployment of virtualized storage and analytic services. Nowadays, the complexity of the tools imply that medium IaaS providers and companies must operate dedicated storage and computing platforms. Or then resort to the major American players in the industry like Amazon or Microsoft. Our solution will lower the barrier for Big Data storage and analytics to a variety of small and medium providers.