DSS

Data Storage Systems

Objectives

Explore storage interfaces, libraries and abstractions used by data-centric applications (e.g., file systems, object stores, key-value stores).
Understand the different storage and data access patterns of these applications (e.g., random and sequential workloads, access distributions).
Understand the organization and management of storage resources in large-scale infrastructures.
Acquire knowledge about technologies, interfaces and architectures of local and distributed storage systems currently used in the state-of-practice (e.g., industry, production environments), while understanding their evolution and different purposes.
Design optimizations for accessing digital information on behalf of data-centric applications (e.g., for performance, reliability, resource management, security).

Program

Data-centric applications and respective storage requirements.
Interfaces, file formats and different I/O libraries (e.g., POSIX, block, key-value pairs).
Infrastructures and storage architectures.
Systems and hardware for local and distributed data storage.
Storage optimizations in terms of efficiency, scalability, reliability, resource management and data security (e.g., caching, tiering, compression, deduplication, replication, encryption).
Diagnosis of application I/O requests and evaluation of storage systems, in user-space and kernel-space.

Bibliography

Alexander Thomasian. Storage Systems, O’Reilly, 2021. Rajkumar Buyya, Toni Cortes, Hai Jin. High Performance Mass Storage and Parallel I/O: Technologies and Applications, Wiley-IEEE Press, 2001. Ricardo Macedo, João Paulo, José Pereira, Alysson Bessani. A Survey and Classification of Software-Defined Storage Systems, ACM Computing Surveys, 2020. Operating Systems: Three Easy Pieces, Remzi H. Arpaci-Dusseau, Andrea C. Arpaci-Dusseau, Arpaci-Dusseau. Books, 2018 Martin Kleppman. Designing Data-Intensive Applications: The big Ideas Behind Reliable, Scalable, and Maintainable Systems, O’Reilly, 2017.