use of io.prestosql.SystemSessionProperties.JOIN_DISTRIBUTION_TYPE 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_DISTRIBUTION_TYPE in project hetu-core by openlookeng.
the class TestLogicalPlanner method testBroadcastCorrelatedSubqueryAvoidsRemoteExchangeBeforeAggregation.
@Test
public void testBroadcastCorrelatedSubqueryAvoidsRemoteExchangeBeforeAggregation() {
Session broadcastJoin = Session.builder(this.getQueryRunner().getDefaultSession()).setSystemProperty(JOIN_DISTRIBUTION_TYPE, JoinDistributionType.BROADCAST.name()).setSystemProperty(FORCE_SINGLE_NODE_OUTPUT, Boolean.toString(false)).build();
// make sure there is a remote exchange on the build side
PlanMatchPattern joinBuildSideWithRemoteExchange = anyTree(node(JoinNode.class, anyTree(node(TableScanNode.class)), anyTree(exchange(REMOTE, REPLICATE, anyTree(node(TableScanNode.class))))));
// validates that there exists only one remote exchange
Consumer<Plan> validateSingleRemoteExchange = plan -> assertEquals(countOfMatchingNodes(plan, node -> node instanceof ExchangeNode && ((ExchangeNode) node).getScope() == REMOTE), 1);
Consumer<Plan> validateSingleStreamingAggregation = plan -> assertEquals(countOfMatchingNodes(plan, node -> node instanceof AggregationNode && ((AggregationNode) node).getGroupingKeys().contains(new Symbol("unique")) && ((AggregationNode) node).isStreamable()), 1);
// region is unpartitioned, AssignUniqueId should provide satisfying partitioning for count(*) after LEFT JOIN
assertPlanWithSession("SELECT (SELECT count(*) FROM region r2 WHERE r2.regionkey > r1.regionkey) FROM region r1", broadcastJoin, false, joinBuildSideWithRemoteExchange, validateSingleRemoteExchange.andThen(validateSingleStreamingAggregation));
// orders is naturally partitioned, AssignUniqueId should not overwrite its natural partitioning
assertPlanWithSession("SELECT count(count) " + "FROM (SELECT o1.orderkey orderkey, (SELECT count(*) FROM orders o2 WHERE o2.orderkey > o1.orderkey) count FROM orders o1) " + "GROUP BY orderkey", broadcastJoin, false, joinBuildSideWithRemoteExchange, validateSingleRemoteExchange.andThen(validateSingleStreamingAggregation));
}
use of io.prestosql.SystemSessionProperties.JOIN_DISTRIBUTION_TYPE in project hetu-core by openlookeng.
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), 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))));
}
use of io.prestosql.SystemSessionProperties.JOIN_DISTRIBUTION_TYPE in project hetu-core by openlookeng.
the class TestDetermineJoinDistributionType method testFlipAndReplicateRightOuterJoin.
@Test
public void testFlipAndReplicateRightOuterJoin() {
int aRows = 10;
int bRows = 1_000_000;
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(RIGHT, 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), 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))));
}
use of io.prestosql.SystemSessionProperties.JOIN_DISTRIBUTION_TYPE 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))));
}
Aggregations