Autoscale Console

simulator

Traffic pattern

Roughly constant load with light noise.

t = 00:00 · 40× wall time · 0% load · 2 active pods
Concurrency Threshold Active pods Schedule window Sooner than expected

Autoscale decision

The raw formula, recomputed every simulated second — before stabilization windows or rate limits are applied. See the ledger below for what actually happens.

Recent activity

Scaling ledger

Every scale event lands here. A rose flag means a scale-down was allowed sooner than its configured period implies — the effect described in Controlling the speed: Autoscaling Policy. Try the Flapping preset with a short scale-down period to trigger it on purpose.

No scaling events yet.
Advanced settingsclick to collapse · changes apply live, all 12 controls
Scaling parameters
Scaling metric Concurrency
Threshold 60 req
Min pods 1
Max pods 8
Schedule window
Window start 09:00
Window end 18:00
Guaranteed min pods 3
Scale to 0 outside window

One simulated day is 600s. Inside the window, pods never drop below the guaranteed minimum, whatever the metric says. Outside it, standard (or zero) scaling takes back over — this is the real Schedule-Based Autoscaling feature, not just a traffic shape.

Autoscaling policy
Scale-up stabilization 20s
Scale-down stabilization 60s
Scale-down step 1 pod
Scale-down period 90s

Scale-down period is shortened for the demo — real deployments allow up to 1800s. The math is identical.