Projet de recherche doctoral numero :4390

Description

Date depot: 1 janvier 1900
Titre: Software Defined Storage for Data Intensive Scalable Computing
Directeur de thèse: Pietro MICHIARDI (Eurecom)
Domaine scientifique: Sciences et technologies de l'information et de la communication
Thématique CNRS : Non defini

Resumé: Abstract. The objective of this Thesis is to design and create a software-defined storage layer for data-intensive scalable computing applications, leveraging the Apache OpenStack platform. Such software-defined layer will enable the 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). In order to achieve this objective, the Thesis will focus on the following topics: • Storage and compute disaggregation and virtualization. Virtualizing data analytics to reduce costs implies disaggregation of existing hardware resources. This requires the creation of a virtual model for compute, storage and networking components that allows orchestration tools to manage resources in an efficient manner. For the orchestration layer it is essential to define and implement innovative scheduling mechanisms so that the provisioning of virtual components for the analytics platform is made to achieve performance guarantees; • SDS Services for Analytics. An important objective of the Thesis is to define, design, and build a software stack of SDS data services enabling virtualized analytics with improved performance and usability. Among these services, we will consider native object store analytics that will allow running analytics close to the data without taxing initial migration. Data reduction services that will be optimized for the special requirements posed by virtualized analytics platforms, and specialized persistent caching mechanisms, advanced prefetching, and data placement will complement the resource allocation components.

Doctorant.e: Pace Francesco