Scaling PostgreSQL with persistent memory
In this talk, we describe how Persistent Memory (PMEM) can be used to vertically scale up PostgreSQL. We look at how PMEM can be used in both the storage and memory access paths of PostgreSQL. While persistent memory is traditionally used to store and speed up WAL in PostgreSQL, we look at other interesting possibilities. For example, we discuss using PMEM as a large persistent cache for the database, its impact on OLAP workloads, and the challenges in implementation. We look at how we can have configurations for performance and for local PMEM device failure redundancy. We also look at some of the challenges of adapting traditional databases like PostgreSQL to PMDK. We will discuss test results of case studies we have carried out with these options. Finally, we will explore how various operating parameters of the database like size of the database, sizes of available DRAM and PMEM all play a role in determining what is the best use of PMEM.
BY Naresh Kumar Inna and Keshav Prasad
- 2020 November 20 16:10 CST
- 40 min
- Virtual - English Sub-Conference B
- CHINA 2020 And PGConf.Asia 2020