~/talk

Beyond Software Estimates: Measured Per-Pod...

links:none on file
links:none on file
slides:none on file

A Kubernetes NRI plugin plus a Go resctrl library reads Linux 7.0 resctrl group counters and Intel AET core energy and activity metrics, binds each container PID at the runtime start-container hook so child forks never escape, and exports per-pod joules and work estimates via Prometheus or OTLP to Grafana. Live demo shows two 100% CPU pods using ~1.5 W versus ~3.3 W, requires CAP_SYS_ADMIN and host PID, open source in containers/nri-plugins.

AI-written summary · about

  1. 0:00Introduction
  2. 1:13Challenges in energy tracking
  3. 2:47Technological enablers
  4. 4:20Resctrl background
  5. 5:31Intel energy telemetry
  6. 6:53Overcoming the fork race
  7. 8:41NRI plugin implementation
  8. 11:18Pod lifecycle management
  9. 12:59Software architecture
  10. 14:56Observability integration
  11. 16:08Human-readable metrics
  12. 17:01Production readiness
  13. 18:43Live demonstration
  14. 23:32Deployment instructions
  15. 23:58Future work and conclusion
~/search
type to search 6,518 conferences, 143,918 speakers and 192,133 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
← →
on a talk: 5 seconds back / forward
0–9
on a talk: jump to 0%–90% of the recording
?
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.