CBO: Use total size instead of bucket count to determine number of splits & parallelism

 final int parallelism = RelMetadataQuery.splitCount(join) == null
              ? 1 : RelMetadataQuery.splitCount(join);

2015-04-13 18:19:09,154 DEBUG [main]: cost.HiveCostModel (HiveCostModel.java:getJoinCost(62)) - COMMON_JOIN cost: {1600892.857142857 rows, 2.4463782008994658E7 cpu, 8.54445445875E10 io}
2015-04-13 18:19:09,155 DEBUG [main]: cost.HiveCostModel (HiveCostModel.java:getJoinCost(62)) - MAP_JOIN cost: {1600892.857142857 rows, 1601785.714285714 cpu, -1698787.4999999998 io}
2015-04-13 18:19:09,155 DEBUG [main]: cost.HiveCostModel (HiveCostModel.java:getJoinCost(72)) - MAP_JOIN selected
2015-04-13 18:19:09,157 DEBUG [main]: parse.CalcitePlanner (CalcitePlanner.java:apply(862)) - Plan After Join Reordering:
HiveSort(fetch=[100]): rowcount = 6006.726049749041, cumulative cost = {1.1468867492063493E8 rows, 1.166177684126984E8 cpu, -1.1757664816220238E9 io}, id = 3000
  HiveSort(sort0=[$0], dir0=[ASC]): rowcount = 6006.726049749041, cumulative cost = {1.1468867492063493E8 rows, 1.166177684126984E8 cpu, -1.1757664816220238E9 io}, id = 2998
    HiveProject(customer_id=[$4], customername=[concat($9, ', ', $8)]): rowcount = 6006.726049749041, cumulative cost = {1.1468867492063493E8 rows, 1.166177684126984E8 cpu, -1.1757664816220238E9 io}, id = 3136
      HiveJoin(condition=[=($1, $5)], joinType=[inner], joinAlgorithm=[map_join], cost=[{5.557820341269841E7 rows, 5.557840182539682E7 cpu, -4299694.122023809 io}]): rowcount = 6006.726049749041, cumulative cost = {1.1468867492063493E8 rows, 1.166177684126984E8 cpu, -1.1757664816220238E9 io}, id = 3132
        HiveJoin(condition=[=($0, $1)], joinType=[inner], joinAlgorithm=[map_join], cost=[{5.7498805E7 rows, 5.9419605E7 cpu, -1.15248E9 io}]): rowcount = 5.5578005E7, cumulative cost = {5.7498805E7 rows, 5.9419605E7 cpu, -1.15248E9 io}, id = 3100
          HiveProject(sr_cdemo_sk=[$4]): rowcount = 5.5578005E7, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 2992
            HiveTableScan(table=[[tpcds_bin_orc_200.store_returns]]): rowcount = 5.5578005E7, cumulative cost = {0}, id = 2878
          HiveProject(cd_demo_sk=[$0]): rowcount = 1920800.0, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 2978
            HiveTableScan(table=[[tpcds_bin_orc_200.customer_demographics]]): rowcount = 1920800.0, cumulative cost = {0}, id = 2868
        HiveJoin(condition=[=($10, $1)], joinType=[inner], joinAlgorithm=[map_join], cost=[{1787.9365079365077 rows, 1790.15873015873 cpu, -8000.0 io}]): rowcount = 198.4126984126984, cumulative cost = {1611666.507936508 rows, 1619761.5873015872 cpu, -1.89867875E7 io}, id = 3130
          HiveJoin(condition=[=($0, $4)], joinType=[inner], joinAlgorithm=[map_join], cost=[{8985.714285714286 rows, 16185.714285714286 cpu, -1.728E7 io}]): rowcount = 1785.7142857142856, cumulative cost = {1609878.5714285714 rows, 1617971.4285714284 cpu, -1.89787875E7 io}, id = 3128
            HiveProject(hd_demo_sk=[$0], hd_income_band_sk=[$1]): rowcount = 7200.0, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 2982
              HiveTableScan(table=[[tpcds_bin_orc_200.household_demographics]]): rowcount = 7200.0, cumulative cost = {0}, id = 2871
            HiveJoin(condition=[=($3, $6)], joinType=[inner], joinAlgorithm=[map_join], cost=[{1600892.857142857 rows, 1601785.714285714 cpu, -1698787.4999999998 io}]): rowcount = 1785.7142857142856, cumulative cost = {1600892.857142857 rows, 1601785.714285714 cpu, -1698787.4999999998 io}, id = 3105
              HiveProject(c_customer_id=[$1], c_current_cdemo_sk=[$2], c_current_hdemo_sk=[$3], c_current_addr_sk=[$4], c_first_name=[$8], c_last_name=[$9]): rowcount = 1600000.0, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 2970
                HiveTableScan(table=[[tpcds_bin_orc_200.customer]]): rowcount = 1600000.0, cumulative cost = {0}, id = 2862
              HiveProject(ca_address_sk=[$0], ca_city=[$6]): rowcount = 892.8571428571428, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 2974
                HiveFilter(condition=[=($6, 'Hopewell')]): rowcount = 892.8571428571428, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 2972
                  HiveTableScan(table=[[tpcds_bin_orc_200.customer_address]]): rowcount = 800000.0, cumulative cost = {0}, id = 2864
          HiveProject(ib_income_band_sk=[$0], ib_lower_bound=[$1], ib_upper_bound=[$2]): rowcount = 2.2222222222222223, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 2988
            HiveFilter(condition=[AND(>=($1, 32287), <=($2, +(32287, 50000)))]): rowcount = 2.2222222222222223, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 2986
              HiveTableScan(table=[[tpcds_bin_orc_200.income_band]]): rowcount = 20.0, cumulative cost = {0}, id = 2874