18–20 Sept 2024
Europe/Vienna timezone

Towards Programmable Memory Management with eBPF

20 Sept 2024, 13:00
30m
"Hall N1" (Austria Center)

"Hall N1"

Austria Center

180
eBPF Track eBPF Track

Speakers

Dimitrios Skarlatos (Carnegie Mellon University) Kaiyang Zhao (Carnegie Mellon University)

Description

The increase in memory capacity in datacenters, coupled with the proliferation of memory-intensive applications, has made memory management a significant performance bottleneck. This issue is poised to worsen due to several factors, such as the inherent hardware limits of TLB scaling and the advent of terabyte-scale memory capacity through technologies like CXL.

In this talk, I will present our vision of a programmable memory management interface with eBPF that can provide a pliable solution. Specifically, the discussion will cover our ongoing work on (a) ensuring contiguity for larger translations, such as huge pages, and (b) introducing learned virtual memory management, a novel solution based on lightweight machine learning, that can effectively address the bottleneck of address translation.

Primary author

Dimitrios Skarlatos (Carnegie Mellon University)

Co-author

Kaiyang Zhao (Carnegie Mellon University)

Presentation materials