Examples with REPLICATED com.facebook.presto.sql.planner.plan.SemiJoinNode.DistributionType.REPLICATED used on opensource projects

Example 1 with REPLICATED

use of com.facebook.presto.sql.planner.plan.SemiJoinNode.DistributionType.REPLICATED in project presto by prestodb.

the class TestDetermineSemiJoinDistributionType method testReplicatesWhenNotRestricted.

@Test
public void testReplicatesWhenNotRestricted() {
    int aRows = 10_000;
    int bRows = 10;
    PlanNodeStatsEstimate probeSideStatsEstimate = PlanNodeStatsEstimate.builder().setOutputRowCount(aRows).addVariableStatistics(ImmutableMap.of(new VariableReferenceExpression(Optional.empty(), "A1", BIGINT), new VariableStatsEstimate(0, 100, 0, 640000, 10))).build();
    PlanNodeStatsEstimate buildSideStatsEstimate = PlanNodeStatsEstimate.builder().setOutputRowCount(bRows).addVariableStatistics(ImmutableMap.of(new VariableReferenceExpression(Optional.empty(), "B1", BIGINT), new VariableStatsEstimate(0, 100, 0, 640000, 10))).build();
    // B table is small enough to be replicated in AUTOMATIC_RESTRICTED mode
    assertDetermineSemiJoinDistributionType().setSystemProperty(JOIN_DISTRIBUTION_TYPE, JoinDistributionType.AUTOMATIC.name()).setSystemProperty(JOIN_MAX_BROADCAST_TABLE_SIZE, "100MB").overrideStats("valuesA", probeSideStatsEstimate).overrideStats("valuesB", buildSideStatsEstimate).on(p -> p.semiJoin(p.values(new PlanNodeId("valuesA"), aRows, p.variable("A1", BIGINT)), p.values(new PlanNodeId("valuesB"), bRows, p.variable("B1", BIGINT)), p.variable("A1"), p.variable("B1"), p.variable("output"), Optional.empty(), Optional.empty(), Optional.empty())).matches(semiJoin("A1", "B1", "output", Optional.of(REPLICATED), values(ImmutableMap.of("A1", 0)), values(ImmutableMap.of("B1", 0))));
    probeSideStatsEstimate = PlanNodeStatsEstimate.builder().setOutputRowCount(aRows).addVariableStatistics(ImmutableMap.of(new VariableReferenceExpression(Optional.empty(), "A1", BIGINT), new VariableStatsEstimate(0, 100, 0, 640000d * 10000, 10))).build();
    buildSideStatsEstimate = PlanNodeStatsEstimate.builder().setOutputRowCount(bRows).addVariableStatistics(ImmutableMap.of(new VariableReferenceExpression(Optional.empty(), "B1", BIGINT), new VariableStatsEstimate(0, 100, 0, 640000d * 10000, 10))).build();
    // B table exceeds AUTOMATIC_RESTRICTED limit therefore it is partitioned
    assertDetermineSemiJoinDistributionType().setSystemProperty(JOIN_DISTRIBUTION_TYPE, JoinDistributionType.AUTOMATIC.name()).setSystemProperty(JOIN_MAX_BROADCAST_TABLE_SIZE, "100MB").overrideStats("valuesA", probeSideStatsEstimate).overrideStats("valuesB", buildSideStatsEstimate).on(p -> p.semiJoin(p.values(new PlanNodeId("valuesA"), aRows, p.variable("A1", BIGINT)), p.values(new PlanNodeId("valuesB"), bRows, p.variable("B1", BIGINT)), p.variable("A1"), p.variable("B1"), p.variable("output"), Optional.empty(), Optional.empty(), Optional.empty())).matches(semiJoin("A1", "B1", "output", Optional.of(PARTITIONED), values(ImmutableMap.of("A1", 0)), values(ImmutableMap.of("B1", 0))));
}

Example 2 with REPLICATED

use of com.facebook.presto.sql.planner.plan.SemiJoinNode.DistributionType.REPLICATED in project presto by prestodb.

the class TestDetermineSemiJoinDistributionType method testReplicatesWhenFilterMuchSmaller.

@Test
public void testReplicatesWhenFilterMuchSmaller() {
    int aRows = 10_000;
    int bRows = 100;
    assertDetermineSemiJoinDistributionType().setSystemProperty(JOIN_DISTRIBUTION_TYPE, JoinDistributionType.AUTOMATIC.name()).overrideStats("valuesA", PlanNodeStatsEstimate.builder().setOutputRowCount(aRows).addVariableStatistics(ImmutableMap.of(new VariableReferenceExpression(Optional.empty(), "A1", BIGINT), VariableStatsEstimate.unknown())).build()).overrideStats("valuesB", PlanNodeStatsEstimate.builder().setOutputRowCount(bRows).addVariableStatistics(ImmutableMap.of(new VariableReferenceExpression(Optional.empty(), "B1", BIGINT), VariableStatsEstimate.unknown())).build()).on(p -> p.semiJoin(p.values(new PlanNodeId("valuesA"), aRows, p.variable("A1", BIGINT)), p.values(new PlanNodeId("valuesB"), bRows, p.variable("B1", BIGINT)), p.variable("A1"), p.variable("B1"), p.variable("output"), Optional.empty(), Optional.empty(), Optional.empty())).matches(semiJoin("A1", "B1", "output", Optional.of(REPLICATED), values(ImmutableMap.of("A1", 0)), values(ImmutableMap.of("B1", 0))));
}

Example 3 with REPLICATED

use of com.facebook.presto.sql.planner.plan.SemiJoinNode.DistributionType.REPLICATED in project presto by prestodb.

the class TestDetermineSemiJoinDistributionType method testReplicatesWhenRequiredBySession.

@Test
public void testReplicatesWhenRequiredBySession() {
    int aRows = 10_000;
    int bRows = 10_000;
    assertDetermineSemiJoinDistributionType().setSystemProperty(JOIN_DISTRIBUTION_TYPE, JoinDistributionType.BROADCAST.name()).setSystemProperty(JOIN_MAX_BROADCAST_TABLE_SIZE, "1B").overrideStats("valuesA", PlanNodeStatsEstimate.builder().setOutputRowCount(aRows).addVariableStatistics(ImmutableMap.of(new VariableReferenceExpression(Optional.empty(), "A1", BIGINT), VariableStatsEstimate.unknown())).build()).overrideStats("valuesB", PlanNodeStatsEstimate.builder().setOutputRowCount(bRows).addVariableStatistics(ImmutableMap.of(new VariableReferenceExpression(Optional.empty(), "B1", BIGINT), VariableStatsEstimate.unknown())).build()).on(p -> p.semiJoin(p.values(new PlanNodeId("valuesA"), aRows, p.variable("A1", BIGINT)), p.values(new PlanNodeId("valuesB"), bRows, p.variable("B1", BIGINT)), p.variable("A1"), p.variable("B1"), p.variable("output"), Optional.empty(), Optional.empty(), Optional.empty())).matches(semiJoin("A1", "B1", "output", Optional.of(REPLICATED), values(ImmutableMap.of("A1", 0)), values(ImmutableMap.of("B1", 0))));
}