Examples with SymbolStatsEstimate io.trino.cost.SymbolStatsEstimate used on opensource projects

Example 16 with SymbolStatsEstimate

use of io.trino.cost.SymbolStatsEstimate in project trino by trinodb.

the class TestDetermineJoinDistributionType method testReplicateLeftOuterJoin.

@Test
public void testReplicateLeftOuterJoin() {
    int aRows = 10_000;
    int bRows = 10;
    assertDetermineJoinDistributionType(new CostComparator(75, 10, 15)).setSystemProperty(JOIN_DISTRIBUTION_TYPE, JoinDistributionType.AUTOMATIC.name()).overrideStats("valuesA", PlanNodeStatsEstimate.builder().setOutputRowCount(aRows).addSymbolStatistics(ImmutableMap.of(new Symbol("A1"), new SymbolStatsEstimate(0, 100, 0, 640000, 100))).build()).overrideStats("valuesB", PlanNodeStatsEstimate.builder().setOutputRowCount(bRows).addSymbolStatistics(ImmutableMap.of(new Symbol("B1"), new SymbolStatsEstimate(0, 100, 0, 640000, 100))).build()).on(p -> p.join(LEFT, p.values(new PlanNodeId("valuesA"), aRows, p.symbol("A1", BIGINT)), p.values(new PlanNodeId("valuesB"), bRows, p.symbol("B1", BIGINT)), ImmutableList.of(new JoinNode.EquiJoinClause(p.symbol("A1", BIGINT), p.symbol("B1", BIGINT))), ImmutableList.of(p.symbol("A1", BIGINT)), ImmutableList.of(p.symbol("B1", BIGINT)), Optional.empty())).matches(join(LEFT, ImmutableList.of(equiJoinClause("A1", "B1")), Optional.empty(), Optional.of(REPLICATED), values(ImmutableMap.of("A1", 0)), values(ImmutableMap.of("B1", 0))));
}

Example 17 with SymbolStatsEstimate

use of io.trino.cost.SymbolStatsEstimate in project trino by trinodb.

the class TestDetermineJoinDistributionType method testReplicatesWhenSourceIsSmall.

@Test
public void testReplicatesWhenSourceIsSmall() {
    // variable width so that average row size is respected
    VarcharType symbolType = createUnboundedVarcharType();
    int aRows = 10_000;
    int bRows = 10;
    // output size exceeds AUTOMATIC_RESTRICTED limit
    PlanNodeStatsEstimate aStatsEstimate = PlanNodeStatsEstimate.builder().setOutputRowCount(aRows).addSymbolStatistics(ImmutableMap.of(new Symbol("A1"), new SymbolStatsEstimate(0, 100, 0, 640000d * 10000, 10))).build();
    // output size exceeds AUTOMATIC_RESTRICTED limit
    PlanNodeStatsEstimate bStatsEstimate = PlanNodeStatsEstimate.builder().setOutputRowCount(bRows).addSymbolStatistics(ImmutableMap.of(new Symbol("B1"), new SymbolStatsEstimate(0, 100, 0, 640000d * 10000, 10))).build();
    // output size does not  exceed AUTOMATIC_RESTRICTED limit
    PlanNodeStatsEstimate bSourceStatsEstimate = PlanNodeStatsEstimate.builder().setOutputRowCount(bRows).addSymbolStatistics(ImmutableMap.of(new Symbol("B1"), new SymbolStatsEstimate(0, 100, 0, 64, 10))).build();
    // immediate join sources exceeds AUTOMATIC_RESTRICTED limit but build tables are small
    // therefore replicated distribution type is chosen
    assertDetermineJoinDistributionType().setSystemProperty(JOIN_DISTRIBUTION_TYPE, JoinDistributionType.AUTOMATIC.name()).setSystemProperty(JOIN_MAX_BROADCAST_TABLE_SIZE, "100MB").overrideStats("valuesA", aStatsEstimate).overrideStats("filterB", bStatsEstimate).overrideStats("valuesB", bSourceStatsEstimate).on(p -> {
        Symbol a1 = p.symbol("A1", symbolType);
        Symbol b1 = p.symbol("B1", symbolType);
        return p.join(INNER, p.values(new PlanNodeId("valuesA"), aRows, a1), p.filter(new PlanNodeId("filterB"), TRUE_LITERAL, p.values(new PlanNodeId("valuesB"), bRows, b1)), ImmutableList.of(new JoinNode.EquiJoinClause(a1, b1)), ImmutableList.of(a1), ImmutableList.of(b1), Optional.empty());
    }).matches(join(INNER, ImmutableList.of(equiJoinClause("A1", "B1")), Optional.empty(), Optional.of(REPLICATED), values(ImmutableMap.of("A1", 0)), filter("true", values(ImmutableMap.of("B1", 0)))));
    // same but with join sides reversed
    assertDetermineJoinDistributionType().setSystemProperty(JOIN_DISTRIBUTION_TYPE, JoinDistributionType.AUTOMATIC.name()).setSystemProperty(JOIN_MAX_BROADCAST_TABLE_SIZE, "100MB").overrideStats("valuesA", aStatsEstimate).overrideStats("filterB", bStatsEstimate).overrideStats("valuesB", bSourceStatsEstimate).on(p -> {
        Symbol a1 = p.symbol("A1", symbolType);
        Symbol b1 = p.symbol("B1", symbolType);
        return p.join(INNER, p.filter(new PlanNodeId("filterB"), TRUE_LITERAL, p.values(new PlanNodeId("valuesB"), bRows, b1)), p.values(new PlanNodeId("valuesA"), aRows, a1), ImmutableList.of(new JoinNode.EquiJoinClause(b1, a1)), ImmutableList.of(b1), ImmutableList.of(a1), Optional.empty());
    }).matches(join(INNER, ImmutableList.of(equiJoinClause("A1", "B1")), Optional.empty(), Optional.of(REPLICATED), values(ImmutableMap.of("A1", 0)), filter("true", values(ImmutableMap.of("B1", 0)))));
    // only probe side (with small tables) source stats are available, join sides should be flipped
    assertDetermineJoinDistributionType().setSystemProperty(JOIN_DISTRIBUTION_TYPE, JoinDistributionType.AUTOMATIC.name()).setSystemProperty(JOIN_MAX_BROADCAST_TABLE_SIZE, "100MB").overrideStats("valuesA", PlanNodeStatsEstimate.unknown()).overrideStats("filterB", PlanNodeStatsEstimate.unknown()).overrideStats("valuesB", bSourceStatsEstimate).on(p -> {
        Symbol a1 = p.symbol("A1", symbolType);
        Symbol b1 = p.symbol("B1", symbolType);
        return p.join(LEFT, p.filter(new PlanNodeId("filterB"), TRUE_LITERAL, p.values(new PlanNodeId("valuesB"), bRows, b1)), p.values(new PlanNodeId("valuesA"), aRows, a1), ImmutableList.of(new JoinNode.EquiJoinClause(b1, a1)), ImmutableList.of(b1), ImmutableList.of(a1), Optional.empty());
    }).matches(join(RIGHT, ImmutableList.of(equiJoinClause("A1", "B1")), Optional.empty(), Optional.of(PARTITIONED), values(ImmutableMap.of("A1", 0)), filter("true", values(ImmutableMap.of("B1", 0)))));
}

Example 18 with SymbolStatsEstimate

use of io.trino.cost.SymbolStatsEstimate in project trino by trinodb.

the class TestDetermineJoinDistributionType method testReplicatesWhenNotRestricted.

@Test
public void testReplicatesWhenNotRestricted() {
    // variable width so that average row size is respected
    VarcharType symbolType = createUnboundedVarcharType();
    int aRows = 10_000;
    int bRows = 10;
    PlanNodeStatsEstimate probeSideStatsEstimate = PlanNodeStatsEstimate.builder().setOutputRowCount(aRows).addSymbolStatistics(ImmutableMap.of(new Symbol("A1"), new SymbolStatsEstimate(0, 100, 0, 640000, 10))).build();
    PlanNodeStatsEstimate buildSideStatsEstimate = PlanNodeStatsEstimate.builder().setOutputRowCount(bRows).addSymbolStatistics(ImmutableMap.of(new Symbol("B1"), new SymbolStatsEstimate(0, 100, 0, 640000, 10))).build();
    // B table is small enough to be replicated in AUTOMATIC_RESTRICTED mode
    assertDetermineJoinDistributionType().setSystemProperty(JOIN_DISTRIBUTION_TYPE, JoinDistributionType.AUTOMATIC.name()).setSystemProperty(JOIN_MAX_BROADCAST_TABLE_SIZE, "100MB").overrideStats("valuesA", probeSideStatsEstimate).overrideStats("valuesB", buildSideStatsEstimate).on(p -> {
        Symbol a1 = p.symbol("A1", symbolType);
        Symbol b1 = p.symbol("B1", symbolType);
        return p.join(INNER, p.values(new PlanNodeId("valuesA"), aRows, a1), p.values(new PlanNodeId("valuesB"), bRows, b1), ImmutableList.of(new JoinNode.EquiJoinClause(a1, b1)), ImmutableList.of(a1), ImmutableList.of(b1), Optional.empty());
    }).matches(join(INNER, ImmutableList.of(equiJoinClause("A1", "B1")), Optional.empty(), Optional.of(REPLICATED), values(ImmutableMap.of("A1", 0)), values(ImmutableMap.of("B1", 0))));
    probeSideStatsEstimate = PlanNodeStatsEstimate.builder().setOutputRowCount(aRows).addSymbolStatistics(ImmutableMap.of(new Symbol("A1"), new SymbolStatsEstimate(0, 100, 0, 640000d * 10000, 10))).build();
    buildSideStatsEstimate = PlanNodeStatsEstimate.builder().setOutputRowCount(bRows).addSymbolStatistics(ImmutableMap.of(new Symbol("B1"), new SymbolStatsEstimate(0, 100, 0, 640000d * 10000, 10))).build();
    // B table exceeds AUTOMATIC_RESTRICTED limit therefore it is partitioned
    assertDetermineJoinDistributionType().setSystemProperty(JOIN_DISTRIBUTION_TYPE, JoinDistributionType.AUTOMATIC.name()).setSystemProperty(JOIN_MAX_BROADCAST_TABLE_SIZE, "100MB").overrideStats("valuesA", probeSideStatsEstimate).overrideStats("valuesB", buildSideStatsEstimate).on(p -> {
        Symbol a1 = p.symbol("A1", symbolType);
        Symbol b1 = p.symbol("B1", symbolType);
        return p.join(INNER, p.values(new PlanNodeId("valuesA"), aRows, a1), p.values(new PlanNodeId("valuesB"), bRows, b1), ImmutableList.of(new JoinNode.EquiJoinClause(a1, b1)), ImmutableList.of(a1), ImmutableList.of(b1), Optional.empty());
    }).matches(join(INNER, ImmutableList.of(equiJoinClause("A1", "B1")), Optional.empty(), Optional.of(PARTITIONED), values(ImmutableMap.of("A1", 0)), values(ImmutableMap.of("B1", 0))));
}

Example 19 with SymbolStatsEstimate

use of io.trino.cost.SymbolStatsEstimate in project trino by trinodb.

the class TestDetermineJoinDistributionType method testPartitionWhenRequiredBySession.

@Test
public void testPartitionWhenRequiredBySession() {
    // variable width so that average row size is respected
    VarcharType symbolType = createUnboundedVarcharType();
    int aRows = 100;
    int bRows = 10_000;
    assertDetermineJoinDistributionType().setSystemProperty(JOIN_DISTRIBUTION_TYPE, JoinDistributionType.AUTOMATIC.name()).overrideStats("valuesA", PlanNodeStatsEstimate.builder().setOutputRowCount(aRows).addSymbolStatistics(ImmutableMap.of(new Symbol("A1"), new SymbolStatsEstimate(0, 100, 0, 6400, 100))).build()).overrideStats("valuesB", PlanNodeStatsEstimate.builder().setOutputRowCount(bRows).addSymbolStatistics(ImmutableMap.of(new Symbol("B1"), new SymbolStatsEstimate(0, 100, 0, 640000, 100))).build()).on(p -> {
        Symbol a1 = p.symbol("A1", symbolType);
        Symbol b1 = p.symbol("B1", symbolType);
        return p.join(INNER, p.values(new PlanNodeId("valuesA"), aRows, a1), p.values(new PlanNodeId("valuesB"), bRows, b1), ImmutableList.of(new JoinNode.EquiJoinClause(a1, b1)), ImmutableList.of(a1), ImmutableList.of(b1), Optional.empty());
    }).setSystemProperty(JOIN_DISTRIBUTION_TYPE, JoinDistributionType.PARTITIONED.name()).matches(join(INNER, ImmutableList.of(equiJoinClause("B1", "A1")), Optional.empty(), Optional.of(PARTITIONED), values(ImmutableMap.of("B1", 0)), values(ImmutableMap.of("A1", 0))));
}

Example 20 with SymbolStatsEstimate

use of io.trino.cost.SymbolStatsEstimate in project trino by trinodb.

the class TestDetermineJoinDistributionType method testReplicatesWhenRequiredBySession.

@Test
public void testReplicatesWhenRequiredBySession() {
    // variable width so that average row size is respected
    VarcharType symbolType = createUnboundedVarcharType();
    int aRows = 10_000;
    int bRows = 10_000;
    assertDetermineJoinDistributionType().setSystemProperty(JOIN_DISTRIBUTION_TYPE, JoinDistributionType.AUTOMATIC.name()).overrideStats("valuesA", PlanNodeStatsEstimate.builder().setOutputRowCount(aRows).addSymbolStatistics(ImmutableMap.of(new Symbol("A1"), new SymbolStatsEstimate(0, 100, 0, 640000, 100))).build()).overrideStats("valuesB", PlanNodeStatsEstimate.builder().setOutputRowCount(bRows).addSymbolStatistics(ImmutableMap.of(new Symbol("B1"), new SymbolStatsEstimate(0, 100, 0, 640000, 100))).build()).on(p -> {
        Symbol a1 = p.symbol("A1", symbolType);
        Symbol b1 = p.symbol("B1", symbolType);
        return p.join(INNER, p.values(new PlanNodeId("valuesA"), aRows, a1), p.values(new PlanNodeId("valuesB"), bRows, b1), ImmutableList.of(new JoinNode.EquiJoinClause(a1, b1)), ImmutableList.of(a1), ImmutableList.of(b1), Optional.empty());
    }).setSystemProperty(JOIN_DISTRIBUTION_TYPE, JoinDistributionType.BROADCAST.name()).matches(join(INNER, ImmutableList.of(equiJoinClause("A1", "B1")), Optional.empty(), Optional.of(REPLICATED), values(ImmutableMap.of("A1", 0)), values(ImmutableMap.of("B1", 0))));
}