peter-toth commented on code in PR #59916:
URL: https://github.com/apache/spark/pull/59916#discussion_r4479182497
##########
sql/core/src/test/scala/org/apache/spark/sql/InjectRuntimeFilterSuite.scala:
##########
@@ -1034,19 +1093,627 @@ class InjectRuntimeFilterSuite extends
SharedSparkSession
test("Runtime bloom filter join: do not add bloom filter if dpp filter
exists " +
"on the same column") {
-
withSQLConf(SQLConf.RUNTIME_BLOOM_FILTER_APPLICATION_SIDE_SCAN_SIZE_THRESHOLD.key
-> "3000",
- SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "2000") {
- assertDidNotRewriteWithBloomFilter("select * from bf5part join bf2 on " +
- "bf5part.f5 = bf2.c2 where bf2.a2 = 62")
+ withDppTestConf(SQLConf.DYNAMIC_PARTITION_PRUNING_REUSE_BROADCAST_ONLY.key
-> "false") {
+ val query = "select * from bf5part join bf2 on bf5part.f5 = bf2.c2 where
bf2.a2 = 62"
+ assertDidNotRewriteWithBloomFilter(query)
+ assert(dynamicPruningFilters(query) == Seq(classOf[SubqueryExec]))
}
}
test("Runtime bloom filter join: add bloom filter if dpp filter exists on " +
"a different column") {
-
withSQLConf(SQLConf.RUNTIME_BLOOM_FILTER_APPLICATION_SIDE_SCAN_SIZE_THRESHOLD.key
-> "3000",
- SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "2000") {
- assertRewroteWithBloomFilter("select * from bf5part join bf2 on " +
- "bf5part.c5 = bf2.c2 and bf5part.f5 = bf2.f2 where bf2.a2 = 62")
+ withDppTestConf(SQLConf.DYNAMIC_PARTITION_PRUNING_REUSE_BROADCAST_ONLY.key
-> "false") {
+ val query = "select * from bf5part join bf2 on " +
+ "bf5part.c5 = bf2.c2 and bf5part.f5 = bf2.f2 where bf2.a2 = 62"
+ assertRewroteWithBloomFilter(query)
+ assert(dynamicPruningFilters(query) == Seq(classOf[SubqueryExec]))
+ }
+ }
+
+ test("SPARK-60702: add bloom filter if the dpp filter needs a broadcast that
the shuffle " +
+ "join lacks") {
+ // `bf2.a2 = 36` keeps a row of `bf2` that joins, so the bloom filter is
not empty when it meets
+ // the partition values of `bf5part`.
+ Seq(
+ "select * from bf5part join bf2 on bf5part.f5 = bf2.c2 where bf2.a2 =
36",
+ "select * from bf2 join bf5part on bf2.c2 = bf5part.f5 where bf2.a2 =
36").foreach { query =>
+ withDppTestConf() {
+ assertRewroteWithBloomFilterForDroppedDpp(query)
+ assert(sql(query).collect().nonEmpty)
+ }
+ }
+ }
+
+ test("SPARK-60702: do not add bloom filter if the dpp filter reuses the
broadcast of " +
+ "the join") {
+ // The aggregate shuffles below the broadcast join, so the join may get a
bloom filter. The
+ // join broadcasts `bf2` by a hint, with the partitioned table on either
side, or by its size.
+ // Without DPP, or without exchange reuse to give the DPP filter the
broadcast, the join gets
+ // the bloom filter.
+ Seq(
+ "select /*+ broadcast(bf2) */ * from (select f5, sum(a5) from bf5part
group by f5) t " +
+ "join bf2 on t.f5 = bf2.c2 where bf2.a2 = 62" -> "2000",
+ "select /*+ broadcast(bf2) */ * from bf2 join (select f5, sum(a5) from
bf5part " +
+ "group by f5) t on bf2.c2 = t.f5 where bf2.a2 = 62" -> "2000",
+ "select * from (select f5, sum(a5) from bf5part group by f5) t " +
+ "join bf2 on t.f5 = bf2.c2 where bf2.a2 = 62" -> "5000"
+ ).foreach { case (query, threshold) =>
+ withDppTestConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> threshold) {
+ withSQLConf(SQLConf.DYNAMIC_PARTITION_PRUNING_ENABLED.key -> "false") {
+ assertRewroteWithBloomFilter(query)
+ }
+ withSQLConf(SQLConf.EXCHANGE_REUSE_ENABLED.key -> "false") {
+ assertRewroteWithBloomFilterForDroppedDpp(query)
+ }
+ assertDidNotRewriteWithBloomFilter(query)
+ assert(dynamicPruningFilters(query) ==
Seq(classOf[SubqueryBroadcastExec]))
+ }
+ }
+ }
+
+ test("SPARK-60702: do not add bloom filter if another join broadcasts the
build plan of " +
+ "the dpp filter") {
+ // The first join is a shuffle join, and its DPP filter reuses the
broadcast of the second.
+ val query = "select p.f5, p.a5, d.* from bf5part p join bf2 d on p.f5 =
d.c2 " +
+ "where d.a2 = 62 union all select /*+ broadcast(d) */ t.f5, t.s, d.*
from " +
+ "(select f5, sum(a5) s from bf5part group by f5) t join bf2 d on t.f5 =
d.c2 " +
+ "where d.a2 = 62"
+ withDppTestConf() {
+ // Without DPP, both `p.f5` and `t.f5` get a bloom filter.
+ assertBloomFilterWithoutDpp(query, 2)
+ assertDidNotRewriteWithBloomFilter(query)
+ // One of the DPP filters can read the broadcast through a reused
subquery.
+ val reuses = Set[Any](classOf[SubqueryBroadcastExec],
classOf[ReusedSubqueryExec])
+ val filters = dynamicPruningFilters(query)
+ assert(filters.size == 2 && filters.forall(reuses.contains), filters)
+ }
+ }
+
+ test("SPARK-60702: do not add bloom filter that takes a broadcast from a dpp
filter") {
+ // The DPP filter on `q.f5` cannot reuse a broadcast, so it does not keep
the bloom filter off
+ // its key. That bloom filter would go into `r`, the broadcast that the
DPP filter on `p.f5`
+ // reuses. `q` is on either side of its join.
+ Seq(
+ "select /*+ broadcast(r) */ * from bf5part p join (select q.f5 rf, q.a5
ra from " +
+ "bf5filtered q join bf2 on q.f5 = bf2.c2 where bf2.a2 = 62) r on p.f5
= r.rf",
+ "select /*+ broadcast(r) */ * from bf5part p join (select q.f5 rf, q.a5
ra from " +
+ "bf2 join bf5filtered q on bf2.c2 = q.f5 where bf2.a2 = 62) r on p.f5
= r.rf"
+ ).foreach { query =>
+ withDppTestConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "500",
+ SQLConf.ADAPTIVE_EXECUTION_ENABLED.key -> "false") {
+ withSQLConf(SQLConf.DYNAMIC_PARTITION_PRUNING_ENABLED.key -> "false") {
+ assertRewroteWithBloomFilter(query)
+ }
+ assertDidNotRewriteWithBloomFilter(query)
+
assert(dynamicPruningFilters(query).contains(classOf[SubqueryBroadcastExec]))
+ }
+ }
+ }
+
+ test("SPARK-60702: do not add bloom filter that takes a broadcast from a dpp
filter in " +
+ "another union branch") {
+ // The DPP filter on `u.k` cannot reuse a broadcast, so it does not keep
the bloom filter off
+ // its key. Pushdown would move that bloom filter into both branches, and
so into `d`, the
+ // broadcast that the DPP filter on `q.f5` reuses. Over the cache of `d`,
cleanup drops the
+ // copy of the DPP filter on `u.k`, but not the bloom filter.
+ val query = "select * from (select p.f5 k, p.a5 v from bf5part p union all
select " +
+ "/*+ broadcast(d) */ d.c2 k, q.a5 v from bf5part q join bf2c d on q.f5 =
d.c2 " +
+ "where d.a2 = 62) u join bf3 on u.k = bf3.c3 where bf3.a3 = 62"
+ withTempView("bf2c") {
+ withCache("bf2c") {
+ spark.table("bf2").createOrReplaceTempView("bf2c")
+ spark.catalog.cacheTable("bf2c")
+ withDppTestConf(SQLConf.ADAPTIVE_EXECUTION_ENABLED.key -> "false") {
+ // Without DPP, pushdown puts a bloom filter into each branch.
+ assertBloomFilterWithoutDpp(query, 2)
+ assertDidNotRewriteWithBloomFilter(query)
+
assert(dynamicPruningFilters(query).contains(classOf[SubqueryBroadcastExec]))
+ }
+ }
+ }
+ }
+
+ test("SPARK-60702: keep the bloom filter off a key whose dpp filter reuses a
broadcast side " +
+ "that has a dpp filter of its own") {
+ // The DPP filter on `q.f5` sits on top of `q` when the rule runs, and
cleanup drops it later
+ // because of `q.f5 = 51`. Then the DPP filter on `t.f5` reuses the
broadcast of `q`, so `t.f5`
+ // gets no bloom filter. `t.c5` gets one, since the DPP filter on its key
is gone. `q` is on
+ // either side of the join.
+ Seq(
+ "select /*+ broadcast(q) */ * from (select f5, c5, sum(a5) s from
bf5part " +
+ "where b5 > 0 group by f5, c5) t join bf5filtered q on t.f5 = q.c5 and
t.c5 = q.f5 " +
+ "where q.a5 > 50 and q.f5 = 51",
+ "select /*+ broadcast(q) */ * from bf5filtered q join (select f5, c5,
sum(a5) s from " +
+ "bf5part where b5 > 0 group by f5, c5) t on q.c5 = t.f5 and q.f5 =
t.c5 " +
+ "where q.a5 > 50 and q.f5 = 51"
+ ).foreach { query =>
+ withDppTestConf() {
+ assertRewroteWithBloomFilter(query)
+ assert(dynamicPruningFilters(query) ==
Seq(classOf[SubqueryBroadcastExec]))
+ }
+ }
+ }
+
+ test("SPARK-60702: do not add bloom filter that takes a broadcast from a dpp
filter that is " +
+ "not only in broadcast") {
+ // With `reuseBroadcastOnly` off, the DPP filter on `p.f5` has a benefit,
so it can run as its
+ // own subquery, but physical planning reuses the broadcast of `r` first.
The DPP filter on
+ // `q.f5` has none, so it is only in broadcast and cannot reuse a
broadcast. A bloom filter on
+ // `q.f5` would go into `r`.
+ withTable("bf5big") {
+ sql("select a5 + id * 100 as a5, b5, c5, d5, e5, f5 from bf5part cross
join range(400)")
+ .write.partitionBy("f5").saveAsTable("bf5big")
+ val query = "select /*+ broadcast(r) */ * from bf5big p join (select
q.f5 rf, q.a5 ra " +
+ "from bf5filtered q join bf5part d on q.f5 = d.c5 where d.a5 = 62) r
on p.f5 = r.rf"
+ withDppTestConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "500",
+ SQLConf.DYNAMIC_PARTITION_PRUNING_REUSE_BROADCAST_ONLY.key ->
"false",
+ SQLConf.DYNAMIC_PARTITION_PRUNING_FALLBACK_FILTER_RATIO.key -> "1.0",
+ SQLConf.ADAPTIVE_EXECUTION_ENABLED.key -> "false") {
+ assertBloomFilterWithoutDpp(query)
+ assertDidNotRewriteWithBloomFilter(query)
+
assert(dynamicPruningFilters(query).contains(classOf[SubqueryBroadcastExec]))
+ }
+ }
+ }
+
+ test("SPARK-60702: keep the bloom filter of a key without a dpp filter") {
+ // Pushdown moves the bloom filter on `s.k` into `x`, the broadcast that
the DPP filter on
+ // `p.f5` reuses. The key has no DPP filter, so the rule adds the bloom
filter all the same.
+ val query = "select * from (select x.c2 k, count(*) from bf5part p join
(select c2 from bf2 " +
+ "where a2 = 62) x on p.f5 = x.c2 group by x.c2) s join bf3 on s.k =
bf3.c3 " +
+ "where bf3.a3 = 62"
+ withDppTestConf() {
+ assertRewroteWithBloomFilter(query)
+ }
+ }
+
+ test("SPARK-60702: keep the dropped dpp filter of the key out of the bloom
filter's creation " +
+ "side") {
+ // `q` is too small to take the bloom filter, so `b` takes it, and `q` is
its creation side.
+ // The DPP filter on `q.f5` stays out of the bloom filter's subquery. `q`
is on either side of
+ // the join.
+ withTable("bigapp") {
+ sql("select a5 + id * 100 as k, b5 from bf5part cross join range(400)")
+ .write.saveAsTable("bigapp")
+ Seq(
+ "select * from bf5filtered q join bigapp b on q.f5 = b.k where q.a5 >
50 and b.b5 = 1",
+ "select * from bigapp b join bf5filtered q on b.k = q.f5 where q.a5 >
50 and b.b5 = 1"
+ ).foreach { query =>
+ withDppTestConf(
+
SQLConf.RUNTIME_BLOOM_FILTER_APPLICATION_SIDE_SCAN_SIZE_THRESHOLD.key ->
"20000") {
+ assertRewroteWithBloomFilterForDroppedDpp(query)
+ val bloomFilterPlans =
sql(query).queryExecution.optimizedPlan.collect {
+ case Filter(condition, _) => condition.collect {
+ case subquery: ScalarSubquery => subquery.plan
+ }
+ }.flatten
+ assert(bloomFilterPlans.size == 1)
+ val creationSide = bloomFilterPlans.head
+ assert(creationSide.collectLeaves().exists {
+ case LogicalRelationWithTable(_, Some(table)) =>
+ table.identifier.table == "bf5filtered"
+ case _ => false
+ }, creationSide)
+ assert(!creationSide.exists {
+ case Filter(_: DynamicPruningSubquery, _) => true
+ case _ => false
+ }, creationSide)
+ }
+ }
+ }
+ }
+
+ test("SPARK-60702: do not add bloom filter if physical planning keeps the
dpp filter over the " +
+ "build plan of a null-aware anti join") {
+ // The join is a shuffle join. The `not in` subquery broadcasts the build
plan of its DPP
+ // filter. Without AQE, physical planning keeps the filter, though it
builds its own
+ // broadcast. AQE plans the filter as `true`, so there the key gets the
bloom filter.
+ val query = "select * from bf5part p join (select c2 from bf2 where a2 =
62 and c2 is not " +
+ "null) d on p.f5 = d.c2 where p.a5 not in (select c2 from bf2 where a2 =
62 and c2 is not " +
+ "null)"
+ withDppTestConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "500",
+ SQLConf.NULL_AWARE_ANTI_JOIN_BROADCAST_THRESHOLD.key -> "-1") {
+ withSQLConf(SQLConf.DYNAMIC_PARTITION_PRUNING_ENABLED.key -> "false") {
+ assertRewroteWithBloomFilter(query)
+ }
+ if (conf.adaptiveExecutionEnabled) {
+ assertRewroteWithBloomFilterForDroppedDpp(query)
+ } else {
+ assertDidNotRewriteWithBloomFilter(query)
+ assert(dynamicPruningFilters(query) ==
Seq(classOf[SubqueryBroadcastExec]))
+ }
+ }
+ }
+
+ test("SPARK-60702: add bloom filter if the join type rules out the broadcast
the dpp filter " +
+ "needs") {
+ // `bf2` is small enough to broadcast, but a right outer join cannot
broadcast its right side,
+ // so the DPP filter does not count. The aggregate shuffles below the
join, so the join can get
+ // the bloom filter.
+ val query = "select * from (select f5, sum(a5) s from bf5part group by f5)
t " +
+ "right join bf2 on t.f5 = bf2.c2 where bf2.a2 = 62"
+ withDppTestConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "5000") {
+ assertRewroteWithBloomFilterForDroppedDpp(query)
+ }
+ }
+
+ test("SPARK-60702: add bloom filter if a shuffle hash hint rules out the
broadcast the dpp " +
+ "filter needs") {
+ // `bf2` is small enough to broadcast, but the hint asks for a shuffle
hash join. The aggregate
+ // shuffles below the join, so the join can get the bloom filter.
+ val query = "select /*+ shuffle_hash(bf2) */ * from (select f5, sum(a5) s
from bf5part " +
+ "group by f5) t join bf2 on t.f5 = bf2.c2 where bf2.a2 = 62"
+ withDppTestConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "5000") {
+ assertRewroteWithBloomFilterForDroppedDpp(query)
+ }
+ }
+
+ test("SPARK-60702: do not add bloom filter if the creation side that the
subquery reads is not " +
+ "deterministic") {
+ // The build plan of the DPP filter would be the creation side of the
bloom filter. A bloom
+ // filter would evaluate it again, apart from the join, and could drop
rows (SPARK-60808).
+ // Cleanup drops such a DPP filter.
+ val query = "select * from bf5part join (select * from bf2 where a2 = 36
and " +
+ "cast(reflect('java.lang.Math', 'random') as double) < 2.0) d on
bf5part.f5 = d.c2"
+ withDppTestConf() {
+ assertBloomFilterWithoutDpp(query)
+ assertDidNotRewriteWithBloomFilter(query)
+ assert(dynamicPruningFilters(query).isEmpty)
+ }
+ }
+
+ test("SPARK-60702: do not add bloom filter whose creation side is a
non-deterministic pruned " +
+ "side") {
+ // The DPP filter on `d.k` has the deterministic build plan `f`, so it is
dropped. `d` is too
+ // small to take a bloom filter, so `f` would take one, built from `d`,
which is not
+ // deterministic (SPARK-60808).
+ withTable("ndd", "ndf") {
+ spark.range(40).selectExpr("id as k", "id as
w").write.partitionBy("k").saveAsTable("ndd")
+ spark.range(40000).selectExpr("id % 40 as k", "id as
v").write.saveAsTable("ndf")
+ sql("analyze table ndd compute statistics")
+ sql("analyze table ndf compute statistics")
+ val nddSize =
spark.table("ndd").queryExecution.optimizedPlan.stats.sizeInBytes
+ val query = "select count(*) from (select k from ndd " +
+ "where cast(reflect('java.lang.Math', 'random') as double) < 0.5) d " +
+ "join ndf f on d.k = f.k where f.v >= 0"
+ withDppTestConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "-1",
+
SQLConf.RUNTIME_BLOOM_FILTER_APPLICATION_SIDE_SCAN_SIZE_THRESHOLD.key ->
+ (nddSize + 1).toString) {
+ assertBloomFilterWithoutDpp(query)
+ assert(bloomFilterKeys(query).isEmpty)
+ }
+ }
+ }
+
+ test("SPARK-60702: do not add bloom filter if the key of the dropped dpp
filter can fail") {
+ // On a partition column, the bloom filter would become a partition
filter, which evaluates
+ // the key on every partition before the data filters (SPARK-60809). An
alias hides the key only
+ // at the join, since pushdown rewrites the bloom filter through it. And
`coalesce` cannot be
+ // null, so no inferred `isnotnull` evaluates the key on every partition
first.
+ // Through a union, every branch counts, and without DPP each gets a bloom
filter. A narrowing
+ // cast can fail too.
+ Seq(
+ "select * from bf5part join bf2 on bf5part.f5 + 1 = bf2.c2 where bf2.a2
= 36" -> 1,
+ "select * from (select coalesce(f5 + 1, 0) as k, a5 from bf5part) p " +
+ "join bf2 on p.k = bf2.c2 where bf2.a2 = 36" -> 1,
+ "select * from (select f5 k, a5 v from bf5part union all " +
+ "select coalesce(f5 + 1, 0) k, a5 v from bf5filtered) u " +
+ "join bf2 on u.k = bf2.c2 where bf2.a2 = 36" -> 2,
+ "select * from bf5part join bf2 on cast(bf5part.f5 as tinyint) = bf2.c2
" +
+ "where bf2.a2 = 36" -> 1
+ ).foreach { case (query, numBloomFilters) =>
+ withDppTestConf() {
+ assertBloomFilterWithoutDpp(query, numBloomFilters)
+ assertDidNotRewriteWithBloomFilter(query)
+ val filters = dynamicPruningFilters(query)
+ assert(filters.nonEmpty && filters.forall(_ == Literal.TrueLiteral),
filters)
+ }
+ }
+ }
+
+ test("SPARK-60702: do not add bloom filter in an in subquery whose dpp
filter reuses a " +
+ "broadcast outside it") {
+ // The optimizer runs on the subquery on its own, where the broadcast of
`x` is not visible.
+ // The DPP filter on `p.f5` reuses it once the subquery is joined with the
rest of the query.
+ val query = "select /*+ broadcast(x) */ * from bf3 join (select c2 from
bf2 where a2 = 62) x " +
+ "on bf3.c3 = x.c2 where bf3.a3 in (select p.a5 from bf5part p join
(select c2 from bf2 " +
+ "where a2 = 62) d on p.f5 = d.c2)"
+ def keysOnF5(query: String): Seq[Expression] =
+ bloomFilterKeys(query).filter(_.references.exists(_.name == "f5"))
+ withDppTestConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "500") {
+ assert(keysOnF5(query).isEmpty)
+ assert(dynamicPruningFilters(query) ==
Seq(classOf[SubqueryBroadcastExec]))
+ // Without the hint, nothing broadcasts `x`, and `p.f5` gets the bloom
filter.
+ val withoutHint = query.replace("/*+ broadcast(x) */ ", "")
+ assert(keysOnF5(withoutHint).nonEmpty)
+ assert(dynamicPruningFilters(withoutHint) == Seq(Literal.TrueLiteral))
+ }
+ }
+
+ test("SPARK-60702: add bloom filter for a key with a dropped dpp filter
under a numeric " +
+ "up-cast") {
+ // Type coercion casts `f5` to `bigint`, which cannot fail.
+ val query = "select * from bf5part join (select cast(c2 as bigint) k, a2
from bf2) d " +
+ "on bf5part.f5 = d.k where d.a2 = 36"
+ withDppTestConf() {
+ assertRewroteWithBloomFilterForDroppedDpp(query)
+ }
+ }
+
+ test("SPARK-60702: add bloom filter for a key with a dropped dpp filter of a
floating point " +
+ "type") {
+ // `NormalizeFloatingNumbers` wraps the `double` join keys, which cannot
fail.
+ val query = "select * from bf5part join (select cast(c2 as double) k, a2
from bf2) d " +
+ "on bf5part.f5 = d.k where d.a2 = 36"
+ withDppTestConf() {
+ assertRewroteWithBloomFilterForDroppedDpp(query)
+ }
+ }
+
+ test("SPARK-60702: add bloom filter whose creation filter has a coalesce,
which cannot fail") {
+ val query = "select * from bf5part join bf2 on bf5part.f5 = bf2.c2 " +
+ "where coalesce(bf2.a2, 0) = 36"
+ withDppTestConf() {
+ assertRewroteWithBloomFilterForDroppedDpp(query)
+ }
+ }
+
+ test("SPARK-60702: do not add bloom filter for a key with a dropped dpp
filter under a " +
+ "decimal to bigint cast") {
+ // `Cast.canUpCast` takes `DECIMAL(19,0)` to `BIGINT`, but
`9999999999999999999` overflows. The
+ // query casts it only on rows with `v > 0`, which that partition does not
have.
+ withTable("fd") {
+ sql("create table fd (v int, d decimal(19,0)) using parquet partitioned
by (d)")
+ sql("insert into fd select cast(id as int) + 1, 36 from range(100)")
+ sql("insert into fd select -cast(id as int), cast('9999999999999999999'
as decimal(19,0)) " +
+ "from range(100)")
+ val query = "select * from fd join bf2 on cast(fd.d as bigint) = bf2.c2
" +
+ "where fd.v > 0 and bf2.a2 = 36"
+ withDppTestConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "-1",
+
SQLConf.RUNTIME_BLOOM_FILTER_APPLICATION_SIDE_SCAN_SIZE_THRESHOLD.key -> "1") {
+ assertBloomFilterWithoutDpp(query)
+ assertDidNotRewriteWithBloomFilter(query)
+ }
+ }
+ }
+
+ test("SPARK-60702: do not add bloom filter whose key can fail in a union
branch the lineage " +
+ "does not reach") {
+ // The lineage of `u.k` stops at the inner union of the second branch, but
pushdown moves the
+ // bloom filter into both inner branches, where it would cast `p` on every
partition. Each
+ // row of `p = 'abc'` has `v <= 0`, so the query itself never casts
`'abc'`.
+ withTable("sp") {
+ sql("create table sp (v int, p string) using parquet partitioned by (p)")
+ sql("insert into sp select cast(id as int) + 1, '36' from range(100)")
+ sql("insert into sp select -cast(id as int), 'abc' from range(100)")
+ val query = "select * from (select f5 as k, a5 as v from bf5part union
all " +
+ "select coalesce(cast(x as int), 0) as k, sum(v) as v from (select p
as x, v from sp " +
+ "where v > 0 union all select p, v from sp where v > 0) group by x) u
" +
+ "join bf2 on u.k = bf2.c2 where bf2.a2 = 36"
+ withDppTestConf() {
+ // Without DPP, pushdown puts a bloom filter into each of the three
branches.
+ assertBloomFilterWithoutDpp(query, 3)
+ assertDidNotRewriteWithBloomFilter(query)
+ }
+ }
+ }
+
+ test("SPARK-60702: add bloom filter whose creation side has a
non-deterministic column that " +
+ "the bloom filter does not read") {
+ // The bloom filter's subquery reads only `c2` of `d`, so `src` does not
change its keys. The
+ // DPP filter is not deterministic, so cleanup removes it.
+ val query = "select * from bf5part p join (select c2, input_file_name()
src from bf2 " +
+ "where a2 = 36) d on p.f5 = d.c2"
+ withDppTestConf(SQLConf.ADAPTIVE_EXECUTION_ENABLED.key -> "false") {
+ assert(bloomFilterKeyNames(query) == Seq("f5"))
+ val expected = withSQLConf(SQLConf.RUNTIME_BLOOM_FILTER_ENABLED.key ->
"false") {
+ sql(query).collect()
+ }
+ checkAnswer(sql(query), expected)
+ }
+ }
+
+ test("SPARK-60702: do not add bloom filter whose creation side reads a cache
that can give " +
+ "other rows when scanned again") {
+ // A cache that is not materialized can compute a partition twice, once
for the join and once
+ // for the bloom filter's subquery. A materialized cache gives the same
rows again.
+ val query = "select * from bf5part p join bf2c d on p.f5 = d.c2 where d.a2
= 36"
+ withTempView("bf2c") {
+ withCache("bf2c") {
+ spark.table("bf2").createOrReplaceTempView("bf2c")
+ spark.catalog.cacheTable("bf2c")
+ val confs = Seq(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "-1",
Review Comment:
Done, with item 3. The test has one block now.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
