Evaluating the Impact of Memory Allocation in Persistent Memory Systems

• Otávio Scarparo Souza UNESP
• Bruno Honorio UNESP
• Alexandro Baldassin UNESP

DOI: https://doi.org/10.5753/eradsp.2024.239930

Abstract

Persistent Memory allocators can improve the performance of applications that use them. However, due to the differences between Persistent Memory and traditional, volatile memory, they must employ error handling and mitigation techniques. Features such as the presence of NUMA and the techniques aforementioned may impact the performance of those allocators. In this paper we are going to present how those factors may impact memory allocation.

References

Baldassin, A., Barreto, J. a., Castro, D., and Romano, P. (2021). Persistent memory: A survey of programming support and implementations. ACM Comput. Surv., 54(7).

Bhandari, K., Chakrabarti, D. R., and Boehm, H.-J. (2016). Makalu: fast recoverable allocation of non-volatile memory. SIGPLAN Not., 51(10):677–694.

Cai, W., Wen, H., Beadle, H. A., Kjellqvist, C., Hedayati, M., and Scott, M. L. (2020). Understanding and optimizing persistent memory allocation. In Proceedings of the 2020 ACM SIGPLAN International Symposium on Memory Management, ISMM 2020, page 60–73, New York, NY, USA. Association for Computing Machinery.

Scargall, S. (2020). Programming Persistent Memory - A Comprehensive Guide for Developers. Apress, 1st edition.