Search in sources :

Example 11 with BigIntVector

use of org.apache.drill.exec.vector.BigIntVector in project drill by apache.

the class TestSimpleTopN method sortOneKeyAscending.

@Test
public void sortOneKeyAscending() throws Throwable {
    RemoteServiceSet serviceSet = RemoteServiceSet.getLocalServiceSet();
    try (Drillbit bit1 = new Drillbit(CONFIG, serviceSet);
        Drillbit bit2 = new Drillbit(CONFIG, serviceSet);
        DrillClient client = new DrillClient(CONFIG, serviceSet.getCoordinator())) {
        bit1.run();
        bit2.run();
        client.connect();
        List<QueryDataBatch> results = client.runQuery(org.apache.drill.exec.proto.UserBitShared.QueryType.PHYSICAL, Files.toString(FileUtils.getResourceAsFile("/topN/one_key_sort.json"), Charsets.UTF_8));
        int count = 0;
        for (QueryDataBatch b : results) {
            if (b.getHeader().getRowCount() != 0) {
                count += b.getHeader().getRowCount();
            }
        }
        assertEquals(100, count);
        long previousBigInt = Long.MIN_VALUE;
        int recordCount = 0;
        int batchCount = 0;
        for (QueryDataBatch b : results) {
            if (b.getHeader().getRowCount() == 0) {
                continue;
            }
            batchCount++;
            RecordBatchLoader loader = new RecordBatchLoader(bit1.getContext().getAllocator());
            loader.load(b.getHeader().getDef(), b.getData());
            BigIntVector c1 = (BigIntVector) loader.getValueAccessorById(BigIntVector.class, loader.getValueVectorId(new SchemaPath("blue", ExpressionPosition.UNKNOWN)).getFieldIds()).getValueVector();
            BigIntVector.Accessor a1 = c1.getAccessor();
            for (int i = 0; i < c1.getAccessor().getValueCount(); i++) {
                recordCount++;
                assertTrue(previousBigInt <= a1.get(i));
                previousBigInt = a1.get(i);
            }
            loader.clear();
            b.release();
        }
        System.out.println(String.format("Sorted %,d records in %d batches.", recordCount, batchCount));
    }
}
Also used : QueryDataBatch(org.apache.drill.exec.rpc.user.QueryDataBatch) Drillbit(org.apache.drill.exec.server.Drillbit) SchemaPath(org.apache.drill.common.expression.SchemaPath) RemoteServiceSet(org.apache.drill.exec.server.RemoteServiceSet) RecordBatchLoader(org.apache.drill.exec.record.RecordBatchLoader) DrillClient(org.apache.drill.exec.client.DrillClient) BigIntVector(org.apache.drill.exec.vector.BigIntVector) Test(org.junit.Test)

Example 12 with BigIntVector

use of org.apache.drill.exec.vector.BigIntVector in project drill by apache.

the class TestSimpleSort method sortTwoKeysOneAscendingOneDescending.

@Test
public void sortTwoKeysOneAscendingOneDescending(@Injectable final DrillbitContext bitContext, @Injectable UserClientConnection connection) throws Throwable {
    mockDrillbitContext(bitContext);
    final PhysicalPlanReader reader = PhysicalPlanReaderTestFactory.defaultPhysicalPlanReader(c);
    final PhysicalPlan plan = reader.readPhysicalPlan(Files.toString(FileUtils.getResourceAsFile("/sort/two_key_sort.json"), Charsets.UTF_8));
    final FunctionImplementationRegistry registry = new FunctionImplementationRegistry(c);
    final FragmentContext context = new FragmentContext(bitContext, PlanFragment.getDefaultInstance(), connection, registry);
    final SimpleRootExec exec = new SimpleRootExec(ImplCreator.getExec(context, (FragmentRoot) plan.getSortedOperators(false).iterator().next()));
    int previousInt = Integer.MIN_VALUE;
    long previousLong = Long.MAX_VALUE;
    int recordCount = 0;
    int batchCount = 0;
    while (exec.next()) {
        batchCount++;
        final IntVector c1 = exec.getValueVectorById(new SchemaPath("blue", ExpressionPosition.UNKNOWN), IntVector.class);
        final BigIntVector c2 = exec.getValueVectorById(new SchemaPath("alt", ExpressionPosition.UNKNOWN), BigIntVector.class);
        final IntVector.Accessor a1 = c1.getAccessor();
        final BigIntVector.Accessor a2 = c2.getAccessor();
        for (int i = 0; i < c1.getAccessor().getValueCount(); i++) {
            recordCount++;
            assertTrue(previousInt <= a1.get(i));
            if (previousInt != a1.get(i)) {
                previousLong = Long.MAX_VALUE;
                previousInt = a1.get(i);
            }
            assertTrue(previousLong >= a2.get(i));
        //System.out.println(previousInt + "\t" + a2.get(i));
        }
    }
    System.out.println(String.format("Sorted %,d records in %d batches.", recordCount, batchCount));
    if (context.getFailureCause() != null) {
        throw context.getFailureCause();
    }
    assertTrue(!context.isFailed());
}
Also used : PhysicalPlan(org.apache.drill.exec.physical.PhysicalPlan) FragmentContext(org.apache.drill.exec.ops.FragmentContext) BigIntVector(org.apache.drill.exec.vector.BigIntVector) IntVector(org.apache.drill.exec.vector.IntVector) PhysicalPlanReader(org.apache.drill.exec.planner.PhysicalPlanReader) FragmentRoot(org.apache.drill.exec.physical.base.FragmentRoot) BigIntVector(org.apache.drill.exec.vector.BigIntVector) SimpleRootExec(org.apache.drill.exec.physical.impl.SimpleRootExec) SchemaPath(org.apache.drill.common.expression.SchemaPath) FunctionImplementationRegistry(org.apache.drill.exec.expr.fn.FunctionImplementationRegistry) ExecTest(org.apache.drill.exec.ExecTest) Test(org.junit.Test)

Example 13 with BigIntVector

use of org.apache.drill.exec.vector.BigIntVector in project drill by apache.

the class TestOrderedPartitionExchange method twoBitTwoExchangeRun.

/**
   * Starts two drillbits and runs a physical plan with a Mock scan, project, OrderedParititionExchange, Union Exchange,
   * and sort. The final sort is done first on the partition column, and verifies that the partitions are correct, in that
   * all rows in partition 0 should come in the sort order before any row in partition 1, etc. Also verifies that the standard
   * deviation of the size of the partitions is less than one tenth the mean size of the partitions, because we expect all
   * the partitions to be roughly equal in size.
   * @throws Exception
   */
@Test
public void twoBitTwoExchangeRun() throws Exception {
    RemoteServiceSet serviceSet = RemoteServiceSet.getLocalServiceSet();
    try (Drillbit bit1 = new Drillbit(CONFIG, serviceSet);
        Drillbit bit2 = new Drillbit(CONFIG, serviceSet);
        DrillClient client = new DrillClient(CONFIG, serviceSet.getCoordinator())) {
        bit1.run();
        bit2.run();
        client.connect();
        List<QueryDataBatch> results = client.runQuery(org.apache.drill.exec.proto.UserBitShared.QueryType.PHYSICAL, Files.toString(FileUtils.getResourceAsFile("/sender/ordered_exchange.json"), Charsets.UTF_8));
        int count = 0;
        List<Integer> partitionRecordCounts = Lists.newArrayList();
        for (QueryDataBatch b : results) {
            if (b.getData() != null) {
                int rows = b.getHeader().getRowCount();
                count += rows;
                DrillConfig config = DrillConfig.create();
                RecordBatchLoader loader = new RecordBatchLoader(new BootStrapContext(config, ClassPathScanner.fromPrescan(config)).getAllocator());
                loader.load(b.getHeader().getDef(), b.getData());
                BigIntVector vv1 = (BigIntVector) loader.getValueAccessorById(BigIntVector.class, loader.getValueVectorId(new SchemaPath("col1", ExpressionPosition.UNKNOWN)).getFieldIds()).getValueVector();
                Float8Vector vv2 = (Float8Vector) loader.getValueAccessorById(Float8Vector.class, loader.getValueVectorId(new SchemaPath("col2", ExpressionPosition.UNKNOWN)).getFieldIds()).getValueVector();
                IntVector pVector = (IntVector) loader.getValueAccessorById(IntVector.class, loader.getValueVectorId(new SchemaPath("partition", ExpressionPosition.UNKNOWN)).getFieldIds()).getValueVector();
                long previous1 = Long.MIN_VALUE;
                double previous2 = Double.MIN_VALUE;
                int partPrevious = -1;
                long current1 = Long.MIN_VALUE;
                double current2 = Double.MIN_VALUE;
                int partCurrent = -1;
                int partitionRecordCount = 0;
                for (int i = 0; i < rows; i++) {
                    previous1 = current1;
                    previous2 = current2;
                    partPrevious = partCurrent;
                    current1 = vv1.getAccessor().get(i);
                    current2 = vv2.getAccessor().get(i);
                    partCurrent = pVector.getAccessor().get(i);
                    Assert.assertTrue(current1 >= previous1);
                    if (current1 == previous1) {
                        Assert.assertTrue(current2 <= previous2);
                    }
                    if (partCurrent == partPrevious || partPrevious == -1) {
                        partitionRecordCount++;
                    } else {
                        partitionRecordCounts.add(partitionRecordCount);
                        partitionRecordCount = 0;
                    }
                }
                partitionRecordCounts.add(partitionRecordCount);
                loader.clear();
            }
            b.release();
        }
        double[] values = new double[partitionRecordCounts.size()];
        int i = 0;
        for (Integer rc : partitionRecordCounts) {
            values[i++] = rc.doubleValue();
        }
        StandardDeviation stdDev = new StandardDeviation();
        Mean mean = new Mean();
        double std = stdDev.evaluate(values);
        double m = mean.evaluate(values);
        System.out.println("mean: " + m + " std dev: " + std);
        //Assert.assertTrue(std < 0.1 * m);
        assertEquals(31000, count);
    }
}
Also used : Mean(org.apache.commons.math.stat.descriptive.moment.Mean) BigIntVector(org.apache.drill.exec.vector.BigIntVector) IntVector(org.apache.drill.exec.vector.IntVector) RecordBatchLoader(org.apache.drill.exec.record.RecordBatchLoader) Float8Vector(org.apache.drill.exec.vector.Float8Vector) BigIntVector(org.apache.drill.exec.vector.BigIntVector) QueryDataBatch(org.apache.drill.exec.rpc.user.QueryDataBatch) DrillConfig(org.apache.drill.common.config.DrillConfig) Drillbit(org.apache.drill.exec.server.Drillbit) SchemaPath(org.apache.drill.common.expression.SchemaPath) RemoteServiceSet(org.apache.drill.exec.server.RemoteServiceSet) BootStrapContext(org.apache.drill.exec.server.BootStrapContext) StandardDeviation(org.apache.commons.math.stat.descriptive.moment.StandardDeviation) DrillClient(org.apache.drill.exec.client.DrillClient) Test(org.junit.Test)

Example 14 with BigIntVector

use of org.apache.drill.exec.vector.BigIntVector in project drill by apache.

the class TestAgg method oneKeyAgg.

@Test
public void oneKeyAgg(@Injectable final DrillbitContext bitContext, @Injectable UserClientConnection connection) throws Throwable {
    final SimpleRootExec exec = doTest(bitContext, connection, "/agg/test1.json");
    while (exec.next()) {
        final BigIntVector cnt = exec.getValueVectorById(SchemaPath.getSimplePath("cnt"), BigIntVector.class);
        final IntVector key = exec.getValueVectorById(SchemaPath.getSimplePath("blue"), IntVector.class);
        final long[] cntArr = { 10001, 9999 };
        final int[] keyArr = { Integer.MIN_VALUE, Integer.MAX_VALUE };
        for (int i = 0; i < exec.getRecordCount(); i++) {
            assertEquals((Long) cntArr[i], cnt.getAccessor().getObject(i));
            assertEquals((Integer) keyArr[i], key.getAccessor().getObject(i));
        }
    }
    if (exec.getContext().getFailureCause() != null) {
        throw exec.getContext().getFailureCause();
    }
    assertTrue(!exec.getContext().isFailed());
}
Also used : SimpleRootExec(org.apache.drill.exec.physical.impl.SimpleRootExec) BigIntVector(org.apache.drill.exec.vector.BigIntVector) IntVector(org.apache.drill.exec.vector.IntVector) NullableBigIntVector(org.apache.drill.exec.vector.NullableBigIntVector) BigIntVector(org.apache.drill.exec.vector.BigIntVector) NullableBigIntVector(org.apache.drill.exec.vector.NullableBigIntVector) Test(org.junit.Test) ExecTest(org.apache.drill.exec.ExecTest)

Aggregations

BigIntVector (org.apache.drill.exec.vector.BigIntVector)14 Test (org.junit.Test)9 RecordBatchLoader (org.apache.drill.exec.record.RecordBatchLoader)8 QueryDataBatch (org.apache.drill.exec.rpc.user.QueryDataBatch)8 SchemaPath (org.apache.drill.common.expression.SchemaPath)6 IntVector (org.apache.drill.exec.vector.IntVector)5 SimpleRootExec (org.apache.drill.exec.physical.impl.SimpleRootExec)4 ExecTest (org.apache.drill.exec.ExecTest)3 FunctionImplementationRegistry (org.apache.drill.exec.expr.fn.FunctionImplementationRegistry)3 FragmentContext (org.apache.drill.exec.ops.FragmentContext)3 PhysicalPlan (org.apache.drill.exec.physical.PhysicalPlan)3 FragmentRoot (org.apache.drill.exec.physical.base.FragmentRoot)3 PhysicalPlanReader (org.apache.drill.exec.planner.PhysicalPlanReader)3 VarCharVector (org.apache.drill.exec.vector.VarCharVector)3 DrillClient (org.apache.drill.exec.client.DrillClient)2 Drillbit (org.apache.drill.exec.server.Drillbit)2 RemoteServiceSet (org.apache.drill.exec.server.RemoteServiceSet)2 NullableBigIntVector (org.apache.drill.exec.vector.NullableBigIntVector)2 Path (org.apache.hadoop.fs.Path)2 Mean (org.apache.commons.math.stat.descriptive.moment.Mean)1