You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by "rangadi (via GitHub)" <gi...@apache.org> on 2024/01/01 00:11:49 UTC
Re: [PR] [SPARK-46547][SS] Fix deadlock between maintenance thread and streaming aggregation operator [spark]
rangadi commented on code in PR #44542:
URL: https://github.com/apache/spark/pull/44542#discussion_r1438942186
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/statefulOperators.scala:
##########
@@ -434,22 +434,26 @@ case class StateStoreRestoreExec(
numColsPrefixKey = 0,
session.sessionState,
Some(session.streams.stateStoreCoordinator)) { case (store, iter) =>
- val hasInput = iter.hasNext
- if (!hasInput && keyExpressions.isEmpty) {
- // If our `keyExpressions` are empty, we're getting a global aggregation. In that case
- // the `HashAggregateExec` will output a 0 value for the partial merge. We need to
- // restore the value, so that we don't overwrite our state with a 0 value, but rather
- // merge the 0 with existing state.
- store.iterator().map(_.value)
- } else {
- iter.flatMap { row =>
- val key = stateManager.getKey(row.asInstanceOf[UnsafeRow])
- val restoredRow = stateManager.get(store, key)
- val outputRows = Option(restoredRow).toSeq :+ row
- numOutputRows += outputRows.size
- outputRows
- }
+ val hasInput = iter.hasNext
+ val result = if (!hasInput && keyExpressions.isEmpty) {
+ // If our `keyExpressions` are empty, we're getting a global aggregation. In that case
+ // the `HashAggregateExec` will output a 0 value for the partial merge. We need to
+ // restore the value, so that we don't overwrite our state with a 0 value, but rather
+ // merge the 0 with existing state.
+ store.iterator().map(_.value)
+ } else {
+ iter.flatMap { row =>
+ val key = stateManager.getKey(row.asInstanceOf[UnsafeRow])
+ val restoredRow = stateManager.get(store, key)
+ val outputRows = Option(restoredRow).toSeq :+ row
+ numOutputRows += outputRows.size
+ outputRows
}
+ }
+ // SPARK-46547 - Release any locks/resources if required, to prevent
+ // deadlocks with the maintenance thread.
+ store.abort()
Review Comment:
Btw, why was this not an issue before? When are these locks/resources released before this PR?
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/statefulOperators.scala:
##########
@@ -434,22 +434,26 @@ case class StateStoreRestoreExec(
numColsPrefixKey = 0,
session.sessionState,
Some(session.streams.stateStoreCoordinator)) { case (store, iter) =>
- val hasInput = iter.hasNext
- if (!hasInput && keyExpressions.isEmpty) {
- // If our `keyExpressions` are empty, we're getting a global aggregation. In that case
- // the `HashAggregateExec` will output a 0 value for the partial merge. We need to
- // restore the value, so that we don't overwrite our state with a 0 value, but rather
- // merge the 0 with existing state.
- store.iterator().map(_.value)
- } else {
- iter.flatMap { row =>
- val key = stateManager.getKey(row.asInstanceOf[UnsafeRow])
- val restoredRow = stateManager.get(store, key)
- val outputRows = Option(restoredRow).toSeq :+ row
- numOutputRows += outputRows.size
- outputRows
- }
+ val hasInput = iter.hasNext
Review Comment:
Is this spurious change? Seems like indentation changed.
--
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: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org