Skip to content

[SPARK-16802] [SQL] fix overflow in LongToUnsafeRowMap #14464

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
davies wants to merge 2 commits into from
Closed

[SPARK-16802] [SQL] fix overflow in LongToUnsafeRowMap #14464

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
97027f0
fix overflow in LongToUnsafeRowMap
Aug 2, 2016
24169ac
address comments
Aug 3, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 10 additions & 6 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -459,9 +459,11 @@ private[execution] final class LongToUnsafeRowMap(val mm: TaskMemoryManager, cap
*/
def getValue(key: Long, resultRow: UnsafeRow): UnsafeRow = {
if (isDense) {
val idx = (key - minKey).toInt
if (idx >= 0 && key <= maxKey && array(idx) > 0) {
return getRow(array(idx), resultRow)
if (key >= minKey && key <= maxKey) {
val value = array((key - minKey).toInt)
if (value > 0) {
return getRow(value, resultRow)
}
}
} else {
var pos = firstSlot(key)
Expand Down Expand Up @@ -497,9 +499,11 @@ private[execution] final class LongToUnsafeRowMap(val mm: TaskMemoryManager, cap
*/
def get(key: Long, resultRow: UnsafeRow): Iterator[UnsafeRow] = {
if (isDense) {
val idx = (key - minKey).toInt
if (idx >=0 && key <= maxKey && array(idx) > 0) {
return valueIter(array(idx), resultRow)
if (key >= minKey && key <= maxKey) {
val value = array((key - minKey).toInt)
if (value > 0) {
return valueIter(value, resultRow)
}
}
} else {
var pos = firstSlot(key)
Expand Down
45 changes: 45 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/execution/joins/HashedRelationSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,6 +152,51 @@ class HashedRelationSuite extends SparkFunSuite with SharedSQLContext {
}
}

test("LongToUnsafeRowMap with very wide range") {
val taskMemoryManager = new TaskMemoryManager(
new StaticMemoryManager(
new SparkConf().set("spark.memory.offHeap.enabled", "false"),
Long.MaxValue,
Long.MaxValue,
1),
0)
val unsafeProj = UnsafeProjection.create(Seq(BoundReference(0, LongType, false)))

{
// SPARK-16740
val keys = Seq(0L, Long.MaxValue, Long.MaxValue)
val map = new LongToUnsafeRowMap(taskMemoryManager, 1)
keys.foreach { k =>
map.append(k, unsafeProj(InternalRow(k)))
}
map.optimize()
val row = unsafeProj(InternalRow(0L)).copy()
keys.foreach { k =>
assert(map.getValue(k, row) eq row)
assert(row.getLong(0) === k)
}
map.free()
}


{
// SPARK-16802
val keys = Seq(Long.MaxValue, Long.MaxValue - 10)
val map = new LongToUnsafeRowMap(taskMemoryManager, 1)
keys.foreach { k =>
map.append(k, unsafeProj(InternalRow(k)))
}
map.optimize()
val row = unsafeProj(InternalRow(0L)).copy()
keys.foreach { k =>
assert(map.getValue(k, row) eq row)
assert(row.getLong(0) === k)
}
assert(map.getValue(Long.MinValue, row) eq null)
map.free()
}
}

test("Spark-14521") {
val ser = new KryoSerializer(
(new SparkConf).set("spark.kryo.referenceTracking", "false")).newInstance()
Expand Down