Ceph RADOS Gateway bucket index garbage collection

radosgw-gc-bucket-indexes.sh

#!/bin/bash
#
# Find orphaned bucket index objects in the RGW bucket index pool
# and clean them up if they do not belong to a bucket
#
# Author: Wido den Hollander <[email protected]>
#

INDEX_POOL=$1

if [ -z "$INDEX_POOL" ]; then
    echo "Usage: $0 <index pool>"
    exit 1
fi

INDEXES=$(mktemp)
METADATA=$(mktemp)

trap "rm -f ${INDEXES} ${METADATA}" EXIT

radosgw-admin metadata list bucket.instance|jq -r '.[]' > ${METADATA}
rados -p ${INDEX_POOL} ls > $INDEXES

for OBJECT in $(cat ${INDEXES}); do
    MARKER=$(echo ${OBJECT}|cut -d '.' -f 3,4,5)
    grep ${MARKER} ${METADATA} > /dev/null
    if [ "$?" -ne 0 ]; then
        echo $OBJECT
    fi    
done