Examples with DrillCostFactory org.apache.drill.exec.planner.cost.DrillCostBase.DrillCostFactory used on opensource projects

Example 16 with DrillCostFactory

use of org.apache.drill.exec.planner.cost.DrillCostBase.DrillCostFactory in project drill by apache.

the class DrillJoinRelBase method computeHashJoinCostWithKeySize.

/**
   *
   * @param planner  : Optimization Planner.
   * @param keySize  : the # of join keys in join condition. Left key size should be equal to right key size.
   * @return         : RelOptCost
   */
private RelOptCost computeHashJoinCostWithKeySize(RelOptPlanner planner, int keySize, RelMetadataQuery mq) {
    double probeRowCount = mq.getRowCount(this.getLeft());
    double buildRowCount = mq.getRowCount(this.getRight());
    // cpu cost of hashing the join keys for the build side
    double cpuCostBuild = DrillCostBase.HASH_CPU_COST * keySize * buildRowCount;
    // cpu cost of hashing the join keys for the probe side
    double cpuCostProbe = DrillCostBase.HASH_CPU_COST * keySize * probeRowCount;
    // cpu cost of evaluating each leftkey=rightkey join condition
    double joinConditionCost = DrillCostBase.COMPARE_CPU_COST * keySize;
    double factor = PrelUtil.getPlannerSettings(planner).getOptions().getOption(ExecConstants.HASH_JOIN_TABLE_FACTOR_KEY).float_val;
    long fieldWidth = PrelUtil.getPlannerSettings(planner).getOptions().getOption(ExecConstants.AVERAGE_FIELD_WIDTH_KEY).num_val;
    // table + hashValues + links
    double memCost = ((fieldWidth * keySize) + IntHolder.WIDTH + IntHolder.WIDTH) * buildRowCount * factor;
    double cpuCost = // probe size determine the join condition comparison cost
    joinConditionCost * (probeRowCount) + cpuCostBuild + cpuCostProbe;
    DrillCostFactory costFactory = (DrillCostFactory) planner.getCostFactory();
    return costFactory.makeCost(buildRowCount + probeRowCount, cpuCost, 0, 0, memCost);
}

Example 17 with DrillCostFactory

use of org.apache.drill.exec.planner.cost.DrillCostBase.DrillCostFactory in project drill by apache.

the class DrillProjectRelBase method computeSelfCost.

@Override
public RelOptCost computeSelfCost(RelOptPlanner planner, RelMetadataQuery mq) {
    if (PrelUtil.getSettings(getCluster()).useDefaultCosting()) {
        return super.computeSelfCost(planner, mq).multiplyBy(.1);
    }
    // cost is proportional to the number of rows and number of columns being projected
    double rowCount = nonSimpleFieldCount > 0 ? mq.getRowCount(this) : 0;
    double cpuCost = DrillCostBase.PROJECT_CPU_COST * rowCount * nonSimpleFieldCount;
    DrillCostFactory costFactory = (DrillCostFactory) planner.getCostFactory();
    return costFactory.makeCost(rowCount, cpuCost, 0, 0);
}

Example 18 with DrillCostFactory

use of org.apache.drill.exec.planner.cost.DrillCostBase.DrillCostFactory in project drill by apache.

the class DrillScreenRelBase method computeSelfCost.

@Override
public RelOptCost computeSelfCost(RelOptPlanner planner, RelMetadataQuery mq) {
    if (PrelUtil.getSettings(getCluster()).useDefaultCosting()) {
        return super.computeSelfCost(planner, mq).multiplyBy(.1);
    }
    // by default, assume cost is proportional to number of rows
    double rowCount = mq.getRowCount(this);
    DrillCostFactory costFactory = (DrillCostFactory) planner.getCostFactory();
    return costFactory.makeCost(rowCount, rowCount, 0, 0).multiplyBy(0.1);
}

Example 19 with DrillCostFactory

use of org.apache.drill.exec.planner.cost.DrillCostBase.DrillCostFactory in project drill by apache.

the class TopNPrel method computeSelfCost.

/**
   * Cost of doing Top-N is proportional to M log N where M is the total number of
   * input rows and N is the limit for Top-N.  This makes Top-N preferable to Sort
   * since cost of full Sort is proportional to M log M .
   */
@Override
public RelOptCost computeSelfCost(RelOptPlanner planner, RelMetadataQuery mq) {
    if (PrelUtil.getSettings(getCluster()).useDefaultCosting()) {
        //We use multiplier 0.05 for TopN operator, and 0.1 for Sort, to make TopN a preferred choice.
        return super.computeSelfCost(planner, mq).multiplyBy(0.05);
    }
    RelNode child = this.getInput();
    double inputRows = mq.getRowCount(child);
    int numSortFields = this.collation.getFieldCollations().size();
    double cpuCost = DrillCostBase.COMPARE_CPU_COST * numSortFields * inputRows * (Math.log(limit) / Math.log(2));
    // assume in-memory for now until we enforce operator-level memory constraints
    double diskIOCost = 0;
    DrillCostFactory costFactory = (DrillCostFactory) planner.getCostFactory();
    return costFactory.makeCost(inputRows, cpuCost, diskIOCost, 0);
}

Example 20 with DrillCostFactory

use of org.apache.drill.exec.planner.cost.DrillCostBase.DrillCostFactory in project drill by apache.

the class ScanPrel method computeSelfCost.

@Override
public RelOptCost computeSelfCost(final RelOptPlanner planner, RelMetadataQuery mq) {
    final PlannerSettings settings = PrelUtil.getPlannerSettings(planner);
    final ScanStats stats = this.groupScan.getScanStats(settings);
    final int columnCount = this.getRowType().getFieldCount();
    if (PrelUtil.getSettings(getCluster()).useDefaultCosting()) {
        return planner.getCostFactory().makeCost(stats.getRecordCount() * columnCount, stats.getCpuCost(), stats.getDiskCost());
    }
    // double rowCount = RelMetadataQuery.getRowCount(this);
    double rowCount = stats.getRecordCount();
    // As DRILL-4083 points out, when columnCount == 0, cpuCost becomes zero,
    // which makes the costs of HiveScan and HiveDrillNativeParquetScan the same
    // For now, assume cpu cost is proportional to row count.
    double cpuCost = rowCount * Math.max(columnCount, 1);
    // If a positive value for CPU cost is given multiply the default CPU cost by given CPU cost.
    if (stats.getCpuCost() > 0) {
        cpuCost *= stats.getCpuCost();
    }
    // Even though scan is reading from disk, in the currently generated plans all plans will
    // need to read the same amount of data, so keeping the disk io cost 0 is ok for now.
    // In the future we might consider alternative scans that go against projections or
    // different compression schemes etc that affect the amount of data read. Such alternatives
    // would affect both cpu and io cost.
    double ioCost = 0;
    DrillCostFactory costFactory = (DrillCostFactory) planner.getCostFactory();
    return costFactory.makeCost(rowCount, cpuCost, ioCost, 0);
}