#!/usr/bin/env bash
# Watch the host recover after the orphan single-node containers were removed.
# 2 CPUs + ~92 containers means the 6 leftovers (one with 58 leaked chall.py
# processes) were the dominant load source; SLA timeouts on a healthy service
# were a symptom of that, not of the service.
for i in 1 2 3 4 5 6; do
  LOAD=$(cut -d' ' -f1-3 /proc/loadavg)
  IDLE=$(vmstat 1 2 | tail -1 | awk '{print $15}')
  CHALL=$(ps -eo args --no-headers | grep -c '[c]hall.py')
  echo "t+$((i * 20))s  load=$LOAD  idle=${IDLE}%  chall.py=$CHALL"
  sleep 20
done