Examples with ColumnSize org.apache.drill.exec.record.RecordBatchSizer.ColumnSize used on opensource projects

Example 6 with ColumnSize

use of org.apache.drill.exec.record.RecordBatchSizer.ColumnSize in project drill by apache.

the class TestRecordBatchSizer method testEmptyBatchFixedWidth.

@Test
public void testEmptyBatchFixedWidth() {
    TupleMetadata schema = new SchemaBuilder().add("a", MinorType.BIGINT).add("b", MinorType.FLOAT8).buildSchema();
    RowSetBuilder builder = fixture.rowSetBuilder(schema);
    RowSet rows = builder.build();
    // Run the record batch sizer on the resulting batch.
    RecordBatchSizer sizer = new RecordBatchSizer(rows.container());
    assertEquals(2, sizer.columns().size());
    ColumnSize aColumn = sizer.columns().get("a");
    /**
     * stdDataSize:8, stdNetSize:8, dataSizePerEntry:0, netSizePerEntry:0,
     * totalDataSize:0, totalNetSize:0, valueCount:0,
     * elementCount:0, cardinality:0, isVariableWidth:false
     */
    verifyColumnValues(aColumn, 8, 8, 0, 0, 0, 0, 0, 0, 0, false);
    ColumnSize bColumn = sizer.columns().get("b");
    verifyColumnValues(bColumn, 8, 8, 0, 0, 0, 0, 0, 0, 0, false);
    // Verify memory allocation is done correctly based on std size for empty batch.
    SingleRowSet empty = fixture.rowSet(schema);
    VectorAccessible accessible = empty.vectorAccessible();
    for (VectorWrapper<?> vw : accessible) {
        ValueVector v = vw.getValueVector();
        RecordBatchSizer.ColumnSize colSize = sizer.getColumn(v.getField().getName());
        // Allocates to nearest power of two.
        colSize.allocateVector(v, testRowCount);
        assertEquals((Integer.highestOneBit(testRowCount) << 1), v.getValueCapacity());
        v.clear();
        // Allocates the same as value passed since it is already power of two.
        colSize.allocateVector(v, testRowCountPowerTwo);
        assertEquals(testRowCountPowerTwo, v.getValueCapacity());
        v.clear();
        // Allocate for max rows.
        colSize.allocateVector(v, ValueVector.MAX_ROW_COUNT);
        assertEquals(ValueVector.MAX_ROW_COUNT, v.getValueCapacity());
        v.clear();
        // Allocate for 0 rows. should atleast do allocation for 1 row.
        colSize.allocateVector(v, 0);
        assertEquals(ValueVector.MIN_ROW_COUNT, v.getValueCapacity());
        v.clear();
    }
    rows.clear();
    empty.clear();
}

Example 7 with ColumnSize

use of org.apache.drill.exec.record.RecordBatchSizer.ColumnSize in project drill by apache.

the class TestRecordBatchSizer method testSizerRepeatedVariableWidth.

@Test
public void testSizerRepeatedVariableWidth() {
    TupleMetadata schema = new SchemaBuilder().addArray("b", MinorType.VARCHAR).buildSchema();
    RowSetBuilder builder = fixture.rowSetBuilder(schema);
    // size = (5*6)/2 = 15
    String[] newString = new String[] { "a", "aa", "aaa", "aaaa", "aaaaa" };
    for (long i = 0; i < 10; i++) {
        builder.addRow((Object) (newString));
    }
    RowSet rows = builder.build();
    // Run the record batch sizer on the resulting batch.
    RecordBatchSizer sizer = new RecordBatchSizer(rows.container());
    assertEquals(1, sizer.columns().size());
    ColumnSize bColumn = sizer.columns().get("b");
    /**
     * stdDataSize:50*5, stdNetSize:50*5+4*5+4, dataSizePerEntry:(5*6)/2, netSizePerEntry:(5*6)/2+5*4+4,
     * totalDataSize:(5*6)/2 * 10, totalNetSize: ((5*6)/2+5*4+4)*10, valueCount:10,
     * elementCount:50, cardinality:5, isVariableWidth:true
     */
    verifyColumnValues(bColumn, 250, 274, 15, 39, 150, 390, 10, 50, 5, true);
    SingleRowSet empty = fixture.rowSet(schema);
    VectorAccessible accessible = empty.vectorAccessible();
    for (VectorWrapper<?> vw : accessible) {
        ValueVector v = vw.getValueVector();
        RecordBatchSizer.ColumnSize colSize = sizer.getColumn(v.getField().getName());
        // Allocates to nearest power of two
        colSize.allocateVector(v, testRowCount - 1);
        UInt4Vector offsetVector = ((RepeatedValueVector) v).getOffsetVector();
        assertEquals(Integer.highestOneBit(testRowCount) << 1, offsetVector.getValueCapacity());
        VariableWidthVector vwVector = ((VariableWidthVector) ((RepeatedValueVector) v).getDataVector());
        offsetVector = vwVector.getOffsetVector();
        assertEquals((Integer.highestOneBit((testRowCount - 1) * 5) << 1), offsetVector.getValueCapacity());
        assertEquals(Integer.highestOneBit((testRowCount - 1) * 5 << 1) - 1, vwVector.getValueCapacity());
        v.clear();
        // Allocates the same as value passed since it is already power of two.
        colSize.allocateVector(v, testRowCountPowerTwo);
        offsetVector = ((RepeatedValueVector) v).getOffsetVector();
        assertEquals((Integer.highestOneBit(testRowCountPowerTwo) << 1), offsetVector.getValueCapacity());
        vwVector = ((VariableWidthVector) ((RepeatedValueVector) v).getDataVector());
        offsetVector = vwVector.getOffsetVector();
        assertEquals((Integer.highestOneBit(testRowCountPowerTwo * 5) << 1), offsetVector.getValueCapacity());
        assertEquals(Integer.highestOneBit(testRowCountPowerTwo * 5 << 1) - 1, vwVector.getValueCapacity());
        v.clear();
        // Allocate for max rows.
        colSize.allocateVector(v, ValueVector.MAX_ROW_COUNT);
        offsetVector = ((RepeatedValueVector) v).getOffsetVector();
        assertEquals(ValueVector.MAX_ROW_COUNT << 1, offsetVector.getValueCapacity());
        vwVector = ((VariableWidthVector) ((RepeatedValueVector) v).getDataVector());
        offsetVector = vwVector.getOffsetVector();
        assertEquals((Integer.highestOneBit(ValueVector.MAX_ROW_COUNT * 5) << 1), offsetVector.getValueCapacity());
        assertEquals(Integer.highestOneBit(ValueVector.MAX_ROW_COUNT * 5 << 1) - 1, vwVector.getValueCapacity());
        v.clear();
        // Allocate for 0 rows. should atleast do allocation for 1 row.
        colSize.allocateVector(v, 0);
        offsetVector = ((RepeatedValueVector) v).getOffsetVector();
        assertEquals(ValueVector.MIN_ROW_COUNT + 1, offsetVector.getValueCapacity());
        vwVector = ((VariableWidthVector) ((RepeatedValueVector) v).getDataVector());
        offsetVector = vwVector.getOffsetVector();
        assertEquals(ValueVector.MIN_ROW_COUNT + 1, offsetVector.getValueCapacity());
        assertEquals(ValueVector.MIN_ROW_COUNT, vwVector.getValueCapacity());
        v.clear();
    }
    empty.clear();
    rows.clear();
}

Example 8 with ColumnSize

use of org.apache.drill.exec.record.RecordBatchSizer.ColumnSize in project drill by apache.

the class TestShortArrays method testSizer.

@Test
public void testSizer() {
    // Create a row set with less than one item, on
    // average, per array.
    TupleMetadata schema = new SchemaBuilder().add("a", MinorType.INT).addArray("b", MinorType.INT).buildSchema();
    RowSetBuilder builder = fixture.rowSetBuilder(schema).addRow(1, intArray(10));
    for (int i = 2; i <= 10; i++) {
        builder.addRow(i, intArray());
    }
    RowSet rows = builder.build();
    // Run the record batch sizer on the resulting batch.
    RecordBatchSizer sizer = new RecordBatchSizer(rows.container());
    assertEquals(2, sizer.columns().size());
    ColumnSize bCol = sizer.columns().get("b");
    assertEquals(0.1, bCol.getCardinality(), 0.01);
    assertEquals(1, bCol.getElementCount());
    // Create a vector initializer using the sizer info.
    VectorInitializer vi = sizer.buildVectorInitializer();
    AllocationHint bHint = vi.hint("b");
    assertNotNull(bHint);
    assertEquals(bHint.elementCount, bCol.getCardinality(), 0.001);
    // Create a new batch, and new vector, using the sizer and
    // initializer inferred from the previous batch.
    SingleRowSet empty = fixture.rowSet(schema);
    vi.allocateBatch(empty.container(), 100);
    assertEquals(2, empty.container().getNumberOfColumns());
    ValueVector bVector = empty.container().getValueVector(1).getValueVector();
    assertTrue(bVector instanceof RepeatedIntVector);
    assertEquals(16, ((RepeatedIntVector) bVector).getDataVector().getValueCapacity());
    rows.clear();
    empty.clear();
}

Example 9 with ColumnSize

use of org.apache.drill.exec.record.RecordBatchSizer.ColumnSize in project drill by axbaretto.

the class TestShortArrays method testSizer.

@Test
public void testSizer() {
    // Create a row set with less than one item, on
    // average, per array.
    BatchSchema schema = new SchemaBuilder().add("a", MinorType.INT).addArray("b", MinorType.INT).build();
    RowSetBuilder builder = fixture.rowSetBuilder(schema).addRow(1, intArray(10));
    for (int i = 2; i <= 10; i++) {
        builder.addRow(i, intArray());
    }
    RowSet rows = builder.build();
    // Run the record batch sizer on the resulting batch.
    RecordBatchSizer sizer = new RecordBatchSizer(rows.container());
    assertEquals(2, sizer.columns().size());
    ColumnSize bCol = sizer.columns().get("b");
    assertEquals(0.1, bCol.getCardinality(), 0.01);
    assertEquals(1, bCol.getElementCount());
    // Create a vector initializer using the sizer info.
    VectorInitializer vi = sizer.buildVectorInitializer();
    AllocationHint bHint = vi.hint("b");
    assertNotNull(bHint);
    assertEquals(bHint.elementCount, bCol.getCardinality(), 0.001);
    // Create a new batch, and new vector, using the sizer and
    // initializer inferred from the previous batch.
    SingleRowSet empty = fixture.rowSet(schema);
    vi.allocateBatch(empty.container(), 100);
    assertEquals(2, empty.container().getNumberOfColumns());
    @SuppressWarnings("resource") ValueVector bVector = empty.container().getValueVector(1).getValueVector();
    assertTrue(bVector instanceof RepeatedIntVector);
    assertEquals(16, ((RepeatedIntVector) bVector).getDataVector().getValueCapacity());
    rows.clear();
    empty.clear();
}

Example 10 with ColumnSize

use of org.apache.drill.exec.record.RecordBatchSizer.ColumnSize in project drill by axbaretto.

the class TestRecordBatchSizer method testSizerRepeatedVariableWidth.

@Test
public void testSizerRepeatedVariableWidth() {
    BatchSchema schema = new SchemaBuilder().addArray("b", MinorType.VARCHAR).build();
    RowSetBuilder builder = fixture.rowSetBuilder(schema);
    // size = (5*6)/2 = 15
    String[] newString = new String[] { "a", "aa", "aaa", "aaaa", "aaaaa" };
    for (long i = 0; i < 10; i++) {
        builder.addRow((Object) (newString));
    }
    RowSet rows = builder.build();
    // Run the record batch sizer on the resulting batch.
    RecordBatchSizer sizer = new RecordBatchSizer(rows.container());
    assertEquals(1, sizer.columns().size());
    ColumnSize bColumn = sizer.columns().get("b");
    /**
     * stdDataSize:50*10, stdNetSize:50*10+4*10+4, dataSizePerEntry:(5*6)/2, netSizePerEntry:(5*6)/2+5*4+4,
     * totalDataSize:(5*6)/2 * 10, totalNetSize: ((5*6)/2+5*4+4)*10, valueCount:10,
     * elementCount:50, estElementCountPerArray:5, isVariableWidth:true
     */
    verifyColumnValues(bColumn, 500, 544, 15, 39, 150, 390, 10, 50, 5, true);
    SingleRowSet empty = fixture.rowSet(schema);
    VectorAccessible accessible = empty.vectorAccessible();
    for (VectorWrapper<?> vw : accessible) {
        ValueVector v = vw.getValueVector();
        RecordBatchSizer.ColumnSize colSize = sizer.getColumn(v.getField().getName());
        // Allocates to nearest power of two
        colSize.allocateVector(v, testRowCount - 1);
        UInt4Vector offsetVector = ((RepeatedValueVector) v).getOffsetVector();
        assertEquals(Integer.highestOneBit(testRowCount) << 1, offsetVector.getValueCapacity());
        VariableWidthVector vwVector = ((VariableWidthVector) ((RepeatedValueVector) v).getDataVector());
        offsetVector = vwVector.getOffsetVector();
        assertEquals((Integer.highestOneBit((testRowCount - 1) * 5) << 1), offsetVector.getValueCapacity());
        assertEquals(Integer.highestOneBit((testRowCount - 1) * 5 << 1) - 1, vwVector.getValueCapacity());
        v.clear();
        // Allocates the same as value passed since it is already power of two.
        colSize.allocateVector(v, testRowCountPowerTwo);
        offsetVector = ((RepeatedValueVector) v).getOffsetVector();
        assertEquals((Integer.highestOneBit(testRowCountPowerTwo) << 1), offsetVector.getValueCapacity());
        vwVector = ((VariableWidthVector) ((RepeatedValueVector) v).getDataVector());
        offsetVector = vwVector.getOffsetVector();
        assertEquals((Integer.highestOneBit(testRowCountPowerTwo * 5) << 1), offsetVector.getValueCapacity());
        assertEquals(Integer.highestOneBit(testRowCountPowerTwo * 5 << 1) - 1, vwVector.getValueCapacity());
        v.clear();
        // Allocate for max rows.
        colSize.allocateVector(v, ValueVector.MAX_ROW_COUNT);
        offsetVector = ((RepeatedValueVector) v).getOffsetVector();
        assertEquals(ValueVector.MAX_ROW_COUNT << 1, offsetVector.getValueCapacity());
        vwVector = ((VariableWidthVector) ((RepeatedValueVector) v).getDataVector());
        offsetVector = vwVector.getOffsetVector();
        assertEquals((Integer.highestOneBit(ValueVector.MAX_ROW_COUNT * 5) << 1), offsetVector.getValueCapacity());
        assertEquals(Integer.highestOneBit(ValueVector.MAX_ROW_COUNT * 5 << 1) - 1, vwVector.getValueCapacity());
        v.clear();
        // Allocate for 0 rows. should atleast do allocation for 1 row.
        colSize.allocateVector(v, 0);
        offsetVector = ((RepeatedValueVector) v).getOffsetVector();
        assertEquals(ValueVector.MIN_ROW_COUNT + 1, offsetVector.getValueCapacity());
        vwVector = ((VariableWidthVector) ((RepeatedValueVector) v).getDataVector());
        offsetVector = vwVector.getOffsetVector();
        assertEquals(ValueVector.MIN_ROW_COUNT + 1, offsetVector.getValueCapacity());
        assertEquals(ValueVector.MIN_ROW_COUNT, vwVector.getValueCapacity());
        v.clear();
    }
    empty.clear();
    rows.clear();
}