trace-images.sh

#!/bin/bash

# forked from  shepmaster/trace-images.sh
# added some logic and made it cron-able (as little output as possible)

hash jq 2>/dev/null  ||   { echo >&2 "jq is required but was not found. Please run make sure it is in the path"; exit 1;}
shopt -s nullglob

# Reset all variables that might be set
interactive=0
verbose=0
dryrun=0

while [ "$#" -gt 0 ]; do
    case $1 in
        -h|-\?|--help)
            show_help
            exit
            ;;
        -r|--registry)
            if [ "$#" -gt 1 ]; then
                base_dir=$2
                shift 2
                continue
            else
                echo 'ERROR: Please specify the path to the registry with -r|-registry.' >&2
                exit 1
            fi
            ;;
        --registry=?*)
            base_dir=${1#*=}
            ;;
        -v|--verbose)
            verbose=1
            ;;
        -n|--dry-run)
            dryrun=1
            verbose=1
            ;;
        -i|--interactive)
            interactive=1
            verbose=1
            ;;
        *)               # Default case: If no more options then break out of the loop.
            break
    esac
    shift
done

if [ -z "$base_dir" ] ; then
   # should never happen, but anyway...
   echo 'ERROR: Please specify the path to the registry with -r|-registry.' >&2
   exit;
fi

readonly output_dir=$(mktemp -d -t cleanup_docker_images-XXXX)
readonly jq=$(which jq)

readonly repository_dir=$base_dir/repositories
readonly image_dir=$base_dir/images

readonly all_images=$output_dir/all
readonly used_images=$output_dir/used
readonly unused_images=$output_dir/unused

function cleanup() {
    [ $verbose -eq 1 ] && echo "Cleaning up $output_dir"
    rm -rf $output_dir
}
trap cleanup EXIT ERR INT

function image_history() {
    local readonly image_hash=$1
    $jq '.[]' $image_dir/$image_hash/ancestry | tr -d  '"'
}

[ $verbose -eq 1 ] && echo "Collecting orphan images at $repository_dir"
for library in $repository_dir/*; do
    [ $verbose -eq 1 ] && echo "Library $(basename $library)" >&2

    for repo in $library/*; do
        [ $verbose -eq 1 ] && echo " Repo $(basename $repo)" >&2

        for tag in $repo/tag_*; do
            [ $verbose -eq 1 ] && echo "  Tag $(basename $tag)" >&2

            tagged_image=$(cat $tag)
            image_history $tagged_image
        done
    done
done | sort | uniq > $used_images

[ $verbose -eq 1 ] && echo -n "used_images: " && cat $used_images | wc -l
ls $image_dir > $all_images
[ $verbose -eq 1 ] && echo -n "all_images: " && cat $all_images | wc -l

#
grep -v -F -f $used_images $all_images > $unused_images || true

readonly all_image_count=$(wc -l $all_images | awk '{print $1}')
readonly used_image_count=$(wc -l $used_images | awk '{print $1}')
readonly unused_image_count=$(wc -l $unused_images | awk '{print $1}')

readonly unused_image_size=$( if [ $unused_image_count -gt 0 ] ; then \
       cd $image_dir; du -hc $(cat $unused_images) | tail -n1 | cut -f1; \
       else echo 0;     fi
   )

if [  $unused_image_count -le 0 ] ; then
  [ $verbose -eq 1 ] && echo "no unused images.";
  exit;
fi

[ $verbose -eq 1 ] && echo -e "\nTrimming _index_images..."
readonly unused_images_flatten=$output_dir/unused.flatten
cat $unused_images | sed -e 's/\(.*\)/\"\1\" /' | tr -d "\n" > $unused_images_flatten

for library in $repository_dir/*; do
    echo "Library $(basename $library)" >&2

    for repo in $library/*; do
        [ $verbose -eq 1 ] && echo " Repo $(basename $repo)" >&2
        mkdir -p "$output_dir/$(basename $repo)"
        $jq '.' "$repo/_index_images" > "$output_dir/$(basename $repo)/_index_images.old"
        $jq -s '.[0] - [ .[1:][] | {id: .} ]' "$repo/_index_images" $unused_images_flatten > "$output_dir/$(basename $repo)/_index_images"
        if [ $dryrun -eq 1 ]; then
            echo "Dryrun - not overwriting $repo/_index_images"
        else
              cp "$output_dir/$(basename $repo)/_index_images" "$repo/_index_images"
        fi
    done
done

[ $verbose -eq 1 ] && echo "these are unused images:"
[ $verbose -eq 1 ] && cat $unused_images

[ $verbose -eq 1 ] && echo "${all_image_count} images, ${used_image_count} used, ${unused_image_count} unused"
[ $verbose -eq 1 ] && echo "Unused images consume ${unused_image_size}"

ok="N";
if [ $interactive -eq 1 ]; then
    echo -e "\nRemove images,are you sure?[Y=yes]"
    read ok;
else
    ok='Y'
fi

if [ "$ok" = "Y" ] ; then
  [ $verbose -eq 1 ] && echo "before cleanup:" && du -sm $base_dir
  if [ $dryrun -eq 1 ]; then
      echo "Dryrun - not deleting anything"
      cat $unused_images | xargs -I{} echo rm -rf $image_dir/{}
  else
      cat $unused_images | xargs -I{} rm -rf $image_dir/{}
  fi
  [ $verbose -eq 1 ] && echo "after cleanup:" &&  du -sm $base_dir
else
  [ $verbose -eq 1 ] && echo "do nothing"
fi