~/talk

PMR: Fast Application Response via Parallel Memory Reclaim on Mobile Devices

Talkat USENIX ATC '25 · 2025-07-07..07-09
links:none on file
links:none on file
name:Yu Mao
links:none on file
name:Liang Shi
links:none on file
slides:none on file

PMR is a kernel patch that decouples page shrinking from writeback and implements proactive page shrinking (PPS) plus storage-friendly page writeback (SPW) to batch unmaps and drive bulk I/O. Implemented and measured on Pixel 6 Pro, Pixel 5 and Redmi Note 11 with 36 real apps, it doubles reclaim throughput (previous peaks ~120 MB/s), cuts app response latency up to 43.6%, and further reduces latency 38% when combined with FLEET.

AI-written summary · about

  1. 0:00Introduction
  2. 1:01Talk structure and background
  3. 2:33Android memory reclaim methods
  4. 4:22Low memory killer problems
  5. 6:12Bottlenecks in memory reclaim
  6. 8:02Page shrinking inefficiencies
  7. 9:26Memory reclaim challenges
  8. 9:48PMR parallel reclaim scheme
  9. 10:32PMR design details
  10. 11:33Experimental results
  11. 12:59Sensitivity study
  12. 13:19Conclusion
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.