automated merge hbase 0.98+ - Bash script that will invoke hshell to query for regions and then perform a merge_region command but only within each regionserver (to avoid data copy/locality issues)

merge_regions.sh

#!/bin/bash

TABLE=$1
MAX=$2

echo "Examining Table $TABLE...."
echo "scan 'hbase:meta',{ COLUMNS => 'info:server', FILTER=>\"PrefixFilter('$TABLE')\"}" | hbase shell > "$TABLE.out" 2>&1

echo "Making splits $TABLE.splits"
echo "" > "$TABLE.splits"
while read p; do
  regex="$TABLE,[A-Z,0-9][A-Z,0-9],[0-9]+\.([^\s].+)\. column.+value=(.+)$"
  if [[ $p =~ $regex ]]
  then
    server="${BASH_REMATCH[2]}"
    region="${BASH_REMATCH[1]}"
    echo "$server,$region" >> "$TABLE.splits"
  fi
done < "$TABLE.out"

splits=$(wc -l < "$TABLE.splits")
echo "... total splits $splits"
if [[ $2 -ge $splits ]]
then
   echo "Region Size Threshold Already Met: $2 vs $splits"
   exit 0
fi

echo "-------- Merge ------"

while read p; do
    regex="$TABLE,[A-Z,0-9]+,[0-9]+\.([^\s].+)\. column.+value=(.+)$"

    if [[ $p =~ $regex ]]
    then
        i=$((i+1))
        region="${BASH_REMATCH[1]}"

        if (( $i % 2 == 0 ))
        then
            region2=$region
            echo "--- [+] $TABLE merge region $region1 <---> $region2"
            echo "merge_region '$region1', '$region2', true" | hbase shell > /dev/null 2>&1
        else
            region1=$region
        fi

    fi

done < "$TABLE.out"

# if we haven't compressed down run again
# note, depending on hbase, you could get in a situation
# were you physically can't compress down anymore than 
# what is allowed by hbase, in those cases this could get
# stuck in a loop, maybe need a fail-safe here to ensure
# we dont end up like that
./merge.sh $TABLE $MAX