mridulm commented on a change in pull request #34158:
URL: https://github.com/apache/spark/pull/34158#discussion_r720721989
##########
File path: core/src/main/scala/org/apache/spark/util/Utils.scala
##########
@@ -2603,18 +2603,28 @@ private[spark] object Utils extends Logging {
* - IO encryption disabled
* - serializer(such as KryoSerializer) supports relocation of serialized
objects
*/
- def isPushBasedShuffleEnabled(conf: SparkConf): Boolean = {
+ def isPushBasedShuffleEnabled(conf: SparkConf,
+ isDriver: Boolean,
+ checkSerializer: Boolean = true): Boolean = {
val pushBasedShuffleEnabled = conf.get(PUSH_BASED_SHUFFLE_ENABLED)
if (pushBasedShuffleEnabled) {
- val serializer =
Utils.classForName(conf.get(SERIALIZER)).getConstructor(classOf[SparkConf])
- .newInstance(conf).asInstanceOf[Serializer]
- val canDoPushBasedShuffle = conf.get(IS_TESTING).getOrElse(false) ||
- (conf.get(SHUFFLE_SERVICE_ENABLED) &&
- conf.get(SparkLauncher.SPARK_MASTER, null) == "yarn" &&
- // TODO: [SPARK-36744] needs to support IO encryption for push-based
shuffle
- !conf.get(IO_ENCRYPTION_ENABLED) &&
- serializer.supportsRelocationOfSerializedObjects)
-
+ val canDoPushBasedShuffle = {
+ val isTesting = conf.get(IS_TESTING).getOrElse(false)
+ val isShuffleServiceAndYarn = conf.get(SHUFFLE_SERVICE_ENABLED) &&
+ conf.get(SparkLauncher.SPARK_MASTER, null) == "yarn"
+ lazy val serializerIsSupported = {
+ if (checkSerializer) {
+ instantiateSerializerFromConf[Serializer](SERIALIZER, conf,
isDriver)
+ .supportsRelocationOfSerializedObjects
Review comment:
We should not be creating a new instance each time - if `SparkEnv.get`
is available, we should its serializer. Only during initialization of SparkEnv
itself should we need a new serializer to be created.
Looks like some badly configured tests which need update.
##########
File path: core/src/main/scala/org/apache/spark/util/Utils.scala
##########
@@ -2603,18 +2603,28 @@ private[spark] object Utils extends Logging {
* - IO encryption disabled
* - serializer(such as KryoSerializer) supports relocation of serialized
objects
*/
- def isPushBasedShuffleEnabled(conf: SparkConf): Boolean = {
+ def isPushBasedShuffleEnabled(conf: SparkConf,
+ isDriver: Boolean,
+ checkSerializer: Boolean = true): Boolean = {
val pushBasedShuffleEnabled = conf.get(PUSH_BASED_SHUFFLE_ENABLED)
if (pushBasedShuffleEnabled) {
- val serializer =
Utils.classForName(conf.get(SERIALIZER)).getConstructor(classOf[SparkConf])
- .newInstance(conf).asInstanceOf[Serializer]
- val canDoPushBasedShuffle = conf.get(IS_TESTING).getOrElse(false) ||
- (conf.get(SHUFFLE_SERVICE_ENABLED) &&
- conf.get(SparkLauncher.SPARK_MASTER, null) == "yarn" &&
- // TODO: [SPARK-36744] needs to support IO encryption for push-based
shuffle
- !conf.get(IO_ENCRYPTION_ENABLED) &&
- serializer.supportsRelocationOfSerializedObjects)
-
+ val canDoPushBasedShuffle = {
+ val isTesting = conf.get(IS_TESTING).getOrElse(false)
+ val isShuffleServiceAndYarn = conf.get(SHUFFLE_SERVICE_ENABLED) &&
+ conf.get(SparkLauncher.SPARK_MASTER, null) == "yarn"
+ lazy val serializerIsSupported = {
+ if (checkSerializer) {
+ instantiateSerializerFromConf[Serializer](SERIALIZER, conf,
isDriver)
+ .supportsRelocationOfSerializedObjects
Review comment:
We should not be creating a new instance each time - if `SparkEnv.get`
is available, we should use its serializer. Only during initialization of
SparkEnv itself should we need a new serializer to be created.
Looks like some badly configured tests which need update.
##########
File path: core/src/main/scala/org/apache/spark/util/Utils.scala
##########
@@ -2603,18 +2603,28 @@ private[spark] object Utils extends Logging {
* - IO encryption disabled
* - serializer(such as KryoSerializer) supports relocation of serialized
objects
*/
- def isPushBasedShuffleEnabled(conf: SparkConf): Boolean = {
+ def isPushBasedShuffleEnabled(conf: SparkConf,
+ isDriver: Boolean,
+ checkSerializer: Boolean = true): Boolean = {
val pushBasedShuffleEnabled = conf.get(PUSH_BASED_SHUFFLE_ENABLED)
if (pushBasedShuffleEnabled) {
- val serializer =
Utils.classForName(conf.get(SERIALIZER)).getConstructor(classOf[SparkConf])
- .newInstance(conf).asInstanceOf[Serializer]
- val canDoPushBasedShuffle = conf.get(IS_TESTING).getOrElse(false) ||
- (conf.get(SHUFFLE_SERVICE_ENABLED) &&
- conf.get(SparkLauncher.SPARK_MASTER, null) == "yarn" &&
- // TODO: [SPARK-36744] needs to support IO encryption for push-based
shuffle
- !conf.get(IO_ENCRYPTION_ENABLED) &&
- serializer.supportsRelocationOfSerializedObjects)
-
+ val canDoPushBasedShuffle = {
+ val isTesting = conf.get(IS_TESTING).getOrElse(false)
+ val isShuffleServiceAndYarn = conf.get(SHUFFLE_SERVICE_ENABLED) &&
+ conf.get(SparkLauncher.SPARK_MASTER, null) == "yarn"
+ lazy val serializerIsSupported = {
+ if (checkSerializer) {
+ instantiateSerializerFromConf[Serializer](SERIALIZER, conf,
isDriver)
+ .supportsRelocationOfSerializedObjects
Review comment:
We should not be creating a new instance each time - if `SparkEnv.get`
is available, we should use its serializer. Only during initialization of
`SparkEnv` itself should we need a new serializer to be created.
Looks like some badly configured tests which need update.
--
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]
