CI caches that ate the disk

$bash Scripts/ci_cache_clean.sh /var/ci/workspaces 14 50

#!/usr/bin/env bash
# ci_cache_clean.sh - find old, large CI workspaces and caches, then delete
# only the ones you approve.
#
# Fixes: CI caches that ate the disk. Workspaces and dependency caches are
# created by every job and removed by none, so the runner fills up and the
# next build fails while unpacking. The script reports what is old and large
# enough to remove; dry-run is the default and --apply deletes.
#
# Usage:
#   ./ci_cache_clean.sh ROOT [DAYS] [MIN_MB] [options]
#
# Examples:
#   ./ci_cache_clean.sh /var/ci/workspaces
#   ./ci_cache_clean.sh /var/ci/workspaces 14 50
#   ./ci_cache_clean.sh /var/ci/workspaces 14 50 --apply
#   ./ci_cache_clean.sh /var/ci/caches 30 200 --name 'npm-*' --apply
#
# Arguments:
#   ROOT      directory whose immediate children are workspaces/caches
#   DAYS      minimum age in days (default 14)
#   MIN_MB    minimum size in megabytes (default 50)
#
# Options:
#   --name GLOB   only children matching this find -name pattern (default *)
#   --apply       delete the reported directories
#   -h, --help    print this help and exit 0
#
# Only direct children of ROOT are examined. A child is a candidate when its
# own mtime is older than DAYS and its size is at least MIN_MB. Paths are
# printed relative to ROOT, which the cron command names, so log lines stay
# short.
#
# Cron (weekly sweep, Sunday 04:00):
#   0 4 * * 0 /usr/local/bin/ci_cache_clean.sh /var/ci/workspaces 14 50 --apply
#
# Exit codes:
#   0  nothing to do, or every candidate was deleted
#   1  candidates were found (dry-run), or at least one delete failed
#   2  usage error or unreadable input
#
# Needs find, du and rm (GNU coreutils or BSD). IFS is set to newline and tab
# so directory names with spaces survive. Deletion is guarded: every resolved
# path must stay under ROOT, and ROOT itself is never deleted.
# By s0sta.com
$set -euo pipefail
$IFS=$'\n\t'
 
$usage() {
$    cat <<'EOF'
ci_cache_clean.sh - find old, large CI workspaces and caches, then delete
only the ones you approve.
 
Usage:
  ./ci_cache_clean.sh ROOT [DAYS] [MIN_MB] [options]
 
Arguments:
  ROOT      directory whose immediate children are workspaces/caches
  DAYS      minimum age in days (default 14)
  MIN_MB    minimum size in megabytes (default 50)
 
Options:
  --name GLOB   only children matching this find -name pattern (default *)
  --apply       delete the reported directories
  -h, --help    print this help and exit 0
 
Exit codes:
  0  nothing to do, or every candidate was deleted
  1  candidates were found (dry-run), or at least one delete failed
  2  usage error or unreadable input
 
By s0sta.com
EOF
$}
 
$root=""
$days=14
$min_mb=50
$name="*"
$apply=0
$positionals=0
 
$numeric() {
$    case "$1" in
$        ''|*[!0-9]*)
$            return 1
$            ;;
$    esac
$    return 0
$}
 
$need_value() {
$    if [ "$#" -lt 2 ]; then
$        printf 'ci_cache_clean: %s needs a value\n' "$1" >&2
$        exit 2
$    fi
$}
 
$while [ "$#" -gt 0 ]; do
$    case "$1" in
$        -h|--help)
$            usage
$            exit 0
$            ;;
$        --name)
$            need_value "$@"
$            name=$2
$            shift 2
$            ;;
$        --apply)
$            apply=1
$            shift
$            ;;
$        -*)
$            printf 'ci_cache_clean: unknown option %s\n' "$1" >&2
$            usage >&2
$            exit 2
$            ;;
$        *)
$            case "$positionals" in
$                0)
$                    root=$1
$                    ;;
$                1)
$                    days=$1
$                    ;;
$                2)
$                    min_mb=$1
$                    ;;
$                *)
$                    printf 'ci_cache_clean: unexpected argument %s\n' "$1" >&2
$                    exit 2
$                    ;;
$            esac
$            positionals=$((positionals + 1))
$            shift
$            ;;
$    esac
$done
 
$if [ -z "$root" ]; then
$    printf 'ci_cache_clean: ROOT is required\n' >&2
$    usage >&2
$    exit 2
$fi
 
$if ! numeric "$days" || [ "$days" -eq 0 ]; then
$    printf 'ci_cache_clean: DAYS must be a positive number\n' >&2
$    exit 2
$fi
 
$if ! numeric "$min_mb"; then
$    printf 'ci_cache_clean: MIN_MB must be a number\n' >&2
$    exit 2
$fi
 
$if [ ! -d "$root" ]; then
$    printf 'CACHE root %s is not a directory\n' "$root" >&2
$    exit 2
$fi
 
$root=$(cd "$root" && pwd -P)
$if [ "$root" = "/" ]; then
$    printf 'CACHE refusing to sweep /\n' >&2
$    exit 2
$fi
 
$candidates=0
$reclaimed=0
$freed=0
$failed=0
 
$while IFS= read -r dir; do
$    if [ -z "$dir" ]; then
$        continue
$    fi
 
$    old=$(find "$dir" -prune -mtime +"$days" -print 2>/dev/null) || old=""
$    if [ -z "$old" ]; then
$        continue
$    fi
 
$    size=$(du -sm "$dir" 2>/dev/null | cut -f1) || size=""
$    if ! numeric "$size"; then
$        printf 'SKIP cannot size %s\n' "${dir#"$root"/}" >&2
$        continue
$    fi
 
$    if [ "$size" -lt "$min_mb" ]; then
$        continue
$    fi
 
$    rel=${dir#"$root"/}
$    candidates=$((candidates + 1))
$    reclaimed=$((reclaimed + size))
 
$    if [ "$apply" -eq 0 ]; then
$        printf 'WOULD DELETE %dM %s\n' "$size" "$rel"
$        continue
$    fi
 
$    if ! abs=$(cd "$dir" && pwd -P); then
$        printf 'SKIP vanished before delete: %s\n' "$rel" >&2
$        failed=$((failed + 1))
$        continue
$    fi
 
$    if [ "$abs" = "$root" ]; then
$        printf 'SKIP refusing to delete the root itself\n' >&2
$        failed=$((failed + 1))
$        continue
$    fi
 
$    case "$abs" in
$        "$root"/*)
$            ;;
$        *)
$            printf 'SKIP resolved outside root: %s\n' "$rel" >&2
$            failed=$((failed + 1))
$            continue
$            ;;
$    esac
 
$    if rm -rf "$abs"; then
$        printf 'DELETED %dM %s\n' "$size" "$rel"
$        freed=$((freed + size))
$    else
$        printf 'FAIL could not delete %s\n' "$rel" >&2
$        failed=$((failed + 1))
$    fi
$done < <(find "$root" -mindepth 1 -maxdepth 1 -type d -name "$name" 2>/dev/null)
 
$if [ "$candidates" -eq 0 ]; then
$    printf 'CACHE clean: nothing older than %sd over %sM in %s\n' \
        "$days" "$min_mb" "$root"
$    exit 0
$fi
 
$unit=dirs
$if [ "$candidates" -eq 1 ]; then
$    unit=dir
$fi
 
$if [ "$apply" -eq 1 ]; then
$    if [ "$failed" -gt 0 ]; then
$        printf 'CACHE %d %s, %dM freed, %d failed\n' \
            "$candidates" "$unit" "$freed" "$failed"
$        exit 1
$    fi
$    printf 'CACHE %d %s, %dM freed\n' "$candidates" "$unit" "$freed"
$    exit 0
$fi
 
$printf 'CACHE %d %s, %dM reclaimable\n' "$candidates" "$unit" "$reclaimed"
$exit 1