You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by GitBox <gi...@apache.org> on 2021/09/01 09:20:03 UTC
[GitHub] [spark] gengliangwang commented on a change in pull request #33870: [SPARK-36619][SS] Fix bugs around prefix-scan for HDFS backed state store and RocksDB state store
gengliangwang commented on a change in pull request #33870:
URL: https://github.com/apache/spark/pull/33870#discussion_r699309363
##########
File path: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreMap.scala
##########
@@ -129,7 +129,11 @@ class PrefixScannableHDFSBackedStateStoreMap(
other match {
case o: PrefixScannableHDFSBackedStateStoreMap =>
map.putAll(o.map)
- prefixKeyToKeysMap.putAll(o.prefixKeyToKeysMap)
+ o.prefixKeyToKeysMap.asScala.foreach { case (prefixKey, keySet) =>
+ val newSet = new mutable.HashSet[UnsafeRow]()
Review comment:
This looks confusing to me. Shall we do the following?
##########
File path: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreMap.scala
##########
@@ -129,7 +129,11 @@ class PrefixScannableHDFSBackedStateStoreMap(
other match {
case o: PrefixScannableHDFSBackedStateStoreMap =>
map.putAll(o.map)
- prefixKeyToKeysMap.putAll(o.prefixKeyToKeysMap)
+ o.prefixKeyToKeysMap.asScala.foreach { case (prefixKey, keySet) =>
+ val newSet = new mutable.HashSet[UnsafeRow]()
Review comment:
```
val cloneMap = new java.util.concurrent.ConcurrentHashMap
[UnsafeRow, mutable.Set[UnsafeRow]](o.prefixKeyToKeysMap)
prefixKeyToKeysMap.putAll(cloneMap)
```
##########
File path: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreMap.scala
##########
@@ -129,7 +129,11 @@ class PrefixScannableHDFSBackedStateStoreMap(
other match {
case o: PrefixScannableHDFSBackedStateStoreMap =>
map.putAll(o.map)
- prefixKeyToKeysMap.putAll(o.prefixKeyToKeysMap)
+ o.prefixKeyToKeysMap.asScala.foreach { case (prefixKey, keySet) =>
+ val newSet = new mutable.HashSet[UnsafeRow]()
Review comment:
```
val cloneMap = new java.util.concurrent.ConcurrentHashMap
[UnsafeRow, mutable.Set[UnsafeRow]](o.prefixKeyToKeysMap)
prefixKeyToKeysMap.putAll(cloneMap)
```
##########
File path: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreMap.scala
##########
@@ -129,7 +129,11 @@ class PrefixScannableHDFSBackedStateStoreMap(
other match {
case o: PrefixScannableHDFSBackedStateStoreMap =>
map.putAll(o.map)
- prefixKeyToKeysMap.putAll(o.prefixKeyToKeysMap)
+ o.prefixKeyToKeysMap.asScala.foreach { case (prefixKey, keySet) =>
+ val newSet = new mutable.HashSet[UnsafeRow]()
Review comment:
This looks confusing to me. Shall we do the following?
##########
File path: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreMap.scala
##########
@@ -129,7 +129,11 @@ class PrefixScannableHDFSBackedStateStoreMap(
other match {
case o: PrefixScannableHDFSBackedStateStoreMap =>
map.putAll(o.map)
- prefixKeyToKeysMap.putAll(o.prefixKeyToKeysMap)
+ o.prefixKeyToKeysMap.asScala.foreach { case (prefixKey, keySet) =>
+ val newSet = new mutable.HashSet[UnsafeRow]()
Review comment:
```
val cloneMap = new java.util.concurrent.ConcurrentHashMap
[UnsafeRow, mutable.Set[UnsafeRow]](o.prefixKeyToKeysMap)
prefixKeyToKeysMap.putAll(cloneMap)
```
##########
File path: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreMap.scala
##########
@@ -129,7 +129,11 @@ class PrefixScannableHDFSBackedStateStoreMap(
other match {
case o: PrefixScannableHDFSBackedStateStoreMap =>
map.putAll(o.map)
- prefixKeyToKeysMap.putAll(o.prefixKeyToKeysMap)
Review comment:
Let's add one comment here.
--
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