Clean up script for ecs containers when container using High memory

ecs-pgmajfault-cleaner.sh

#!/bin/bash -e

##
# Use this annotated script as base for killing container misbehaving on reaching memory limit
#
# Requirements:
# - `jq` must be installed on both the client and server
##

# don't kill containers using these images even if they're misbehaving
EXCLUDES_PATTERN=$(cat <<'EOF' | xargs | sed 's/ /|/g'
amazon/amazon-ecs-agent
EOF
)

# list all the candidate containers
targets=$(docker ps --no-trunc --format '{{.ID}} {{.Image}}' | grep -Ev "$EXCLUDES_PATTERN" | awk '{ print $1; }' | xargs)
for target in $targets; do

  # get taskid and dockerid from ecs
  task=$(curl -s http://localhost:51678/v1/tasks?dockerid=$target)
  taskId=$(echo $task | jq -r ".Arn" | cut -d "/" -f 2)
  dockerId=$(echo $task | jq -r ".Containers[0] .DockerId")
  memoryStatsFile="/cgroup/memory/ecs/$taskId/$dockerId/memory.stat"

  # skip current target if cannot find memory stats file, might not be managed by ecs
  if ! [ -f $memoryStatsFile ]
  then echo "Memory stats not found for taskId=$taskid dockerId=$target" && continue
  fi

  info="id=$target $(docker inspect --format 'image={{.Config.Image}} StartedAt="{{.State.StartedAt}}"' "$target") pgmajfault=$(grep total_pgmajfault $memoryStatsFile | awk '{print $2;}')"
  majorPageFaults=$(echo "$info" | awk '{ print $4;}' | sed 's/pgmajfault=//g')
  startedAt=$(echo "$info" | awk '{ print $3;}' | sed 's/StartedAt=//g' | sed 's/"//g')
  startedSecs=$(date -d $startedAt +%s)
  stoppingSecs=$(date +%s)
  duration=$(($stoppingSecs - $stoppingSecs))
  duration="$(($duration / 60))m$(($duration % 60))s"
  info=$(echo "duration=$duration $info")

  if [ "$majorPageFaults" -gt 5000 ]; then
    echo "Stopping Container: timestamp=$(date -Iseconds) [$info]"
    docker stop "$target"
  fi
done