use of io.prestosql.SystemSessionProperties.JOIN_MAX_BROADCAST_TABLE_SIZE in project hetu-core by openlookeng.
the class TestReorderJoins method testReplicatesWhenNotRestricted.
@Test
public void testReplicatesWhenNotRestricted() {
// variable width so that average row size is respected
Type 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
assertReorderJoins().setSystemProperty(JOIN_DISTRIBUTION_TYPE, AUTOMATIC.name()).setSystemProperty(JOIN_MAX_BROADCAST_TABLE_SIZE, "100MB").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 EquiJoinClause(a1, b1)), ImmutableList.of(a1, b1), Optional.empty());
}).overrideStats("valuesA", probeSideStatsEstimate).overrideStats("valuesB", buildSideStatsEstimate).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
assertReorderJoins().setSystemProperty(JOIN_DISTRIBUTION_TYPE, AUTOMATIC.name()).setSystemProperty(JOIN_MAX_BROADCAST_TABLE_SIZE, "100MB").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 EquiJoinClause(a1, b1)), ImmutableList.of(a1, b1), Optional.empty());
}).overrideStats("valuesA", probeSideStatsEstimate).overrideStats("valuesB", buildSideStatsEstimate).matches(join(INNER, ImmutableList.of(equiJoinClause("A1", "B1")), Optional.empty(), Optional.of(PARTITIONED), values(ImmutableMap.of("A1", 0)), values(ImmutableMap.of("B1", 0))));
}
use of io.prestosql.SystemSessionProperties.JOIN_MAX_BROADCAST_TABLE_SIZE in project hetu-core by openlookeng.
the class TestDetermineSemiJoinDistributionType method testReplicatesWhenNotRestricted.
@Test
public void testReplicatesWhenNotRestricted() {
// variable width so that average row size is respected
Type 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
assertDetermineSemiJoinDistributionType().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.semiJoin(p.values(new PlanNodeId("valuesA"), aRows, a1), p.values(new PlanNodeId("valuesB"), bRows, b1), a1, b1, p.symbol("output"), Optional.empty(), 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).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
assertDetermineSemiJoinDistributionType().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.semiJoin(p.values(new PlanNodeId("valuesA"), aRows, a1), p.values(new PlanNodeId("valuesB"), bRows, b1), a1, b1, p.symbol("output"), Optional.empty(), Optional.empty(), Optional.empty(), Optional.empty());
}).matches(semiJoin("A1", "B1", "output", Optional.of(PARTITIONED), values(ImmutableMap.of("A1", 0)), values(ImmutableMap.of("B1", 0))));
}
use of io.prestosql.SystemSessionProperties.JOIN_MAX_BROADCAST_TABLE_SIZE in project hetu-core by openlookeng.
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, 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, 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))));
}
use of io.prestosql.SystemSessionProperties.JOIN_MAX_BROADCAST_TABLE_SIZE in project hetu-core by openlookeng.
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).addSymbolStatistics(ImmutableMap.of(new Symbol("A1"), SymbolStatsEstimate.unknown())).build()).overrideStats("valuesB", PlanNodeStatsEstimate.builder().setOutputRowCount(bRows).addSymbolStatistics(ImmutableMap.of(new Symbol("B1"), SymbolStatsEstimate.unknown())).build()).on(p -> p.semiJoin(p.values(new PlanNodeId("valuesA"), aRows, p.symbol("A1", BIGINT)), p.values(new PlanNodeId("valuesB"), bRows, p.symbol("B1", BIGINT)), p.symbol("A1"), p.symbol("B1"), p.symbol("output"), Optional.empty(), Optional.empty(), Optional.empty(), Optional.empty())).matches(semiJoin("A1", "B1", "output", Optional.of(REPLICATED), values(ImmutableMap.of("A1", 0)), values(ImmutableMap.of("B1", 0))));
}
Aggregations