11–13 Dec 2025
Asia/Tokyo timezone

Memory Allocation Profiling upcoming features

Not scheduled
20m
Kernel Memory Management MC Kernel Memory Management MC

Speakers

Sourav Panda (Google) Suren Baghdasaryan

Description

Memory allocation profiling infrastructure provides a low-overhead
mechanism to make all kernel allocations in the system visible. This
allows for monitoring memory usage, tracking hotspots, detecting
leaks, and identifying regressions.

Over the past year there were a number of suggested new features from its users, including:
- NUMA awareness
- MEMCG awareness
- Context capture (initially part of the RFC)
- IOCTL as a mechanism for efficient data querying and filtering
- Reporting extra data like gfp_flags and unaccounted memory size
- Userspace tooling (grouping allocations by categories, issuing ioctl commands, etc).

We would like to gauge the level of interest in each feature to prioritize new development, discuss main challenges and options for implementing each feature, and share performance data associated with some of these features.

Primary author

Co-author

Presentation materials

There are no materials yet.