~/talk

SIG Instrumentation Deep Dive

on YouTube 41m
Talkat KubeCon + CloudNativeCon Europe 2018 · 2018-05-02..05-04· B5-M2+4· [observability, kubernetes]

speakers

name:Frederic Branczyk
website:https://hachyderm.io/@brancz
name:Piotr Szczesniak
links:none on file

resources

video:https://youtu.be/SzLLzKWH2Gk
slides:none on file

summary

Covers concrete instrumentation work: Kubernetes ships a metric-server that scrapes kubelets, uses ~3–4 MB per node and needs ~20 GB memory to scale to 5,000 nodes, and exposes 1‑minute resource averages only; the custom metrics and external metrics APIs let third‑party systems plug in; kube-state-metrics moved from on‑scrape cache to registry to avoid stale labels, now has ~145 metrics, ~72 contributors and ~531 commits; integration points listed include ~15 Hipster adapters and first‑class Prometheus support for cluster and component state.

AI-written summary · about

chapters (7)

  1. 0:00Start
  2. 0:10SIG Instrumentation: Deep Dive
  3. 0:56Recap
  4. 4:31Architecture overview
  5. 11:05Metrics Server internals
  6. 14:39CM API adapters
  7. 27:53kube-state-metrics

related talks

~/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.