[SPARK-33283][CORE] Remove useless externalBlockStoreSize from RDDInfo

### What changes were proposed in this pull request? "external block store" API was removed after SPARK-12667, `externalBlockStoreSize` in `RDDInfo` looks like always 0 and useless. So this pr just to remove this useless variable. ### Why are the changes needed? remove useless variable. ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? Pass the Jenkins or GitHub Action Closes #30179 from LuciferYang/SPARK-12667-FOLLOWUP. Authored-by: yangjie01 <[email protected]> Signed-off-by: Dongjoon Hyun <[email protected]>
apache · Oct 29, 2020 · fa63117 · fa63117
1 parent 056b622
commit fa63117
Show file tree

Hide file tree

Showing 3 changed files with 2 additions and 5 deletions.
diff --git a/core/src/main/scala/org/apache/spark/rdd/RDD.scala b/core/src/main/scala/org/apache/spark/rdd/RDD.scala
@@ -1919,9 +1919,8 @@ abstract class RDD[T: ClassTag](
 
       val persistence = if (storageLevel != StorageLevel.NONE) storageLevel.description else ""
       val storageInfo = rdd.context.getRDDStorageInfo(_.id == rdd.id).map(info =>
-        "    CachedPartitions: %d; MemorySize: %s; ExternalBlockStoreSize: %s; DiskSize: %s".format(
-          info.numCachedPartitions, bytesToString(info.memSize),
-          bytesToString(info.externalBlockStoreSize), bytesToString(info.diskSize)))
+        "    CachedPartitions: %d; MemorySize: %s; DiskSize: %s".format(
+          info.numCachedPartitions, bytesToString(info.memSize), bytesToString(info.diskSize)))
 
       s"$rdd [$persistence]" +: storageInfo
     }

diff --git a/core/src/main/scala/org/apache/spark/storage/BlockManagerMasterEndpoint.scala b/core/src/main/scala/org/apache/spark/storage/BlockManagerMasterEndpoint.scala
@@ -737,7 +737,6 @@ private[spark] class BlockManagerInfo(
     if (storageLevel.isValid) {
       /* isValid means it is either stored in-memory or on-disk.
        * The memSize here indicates the data size in or dropped from memory,
-       * externalBlockStoreSize here indicates the data size in or dropped from externalBlockStore,
        * and the diskSize here indicates the data size in or dropped to disk.
        * They can be both larger than 0, when a block is dropped from memory to disk.
        * Therefore, a safe way to set BlockStatus is to set its info in accurate modes. */

diff --git a/core/src/main/scala/org/apache/spark/storage/RDDInfo.scala b/core/src/main/scala/org/apache/spark/storage/RDDInfo.scala
@@ -38,7 +38,6 @@ class RDDInfo(
   var numCachedPartitions = 0
   var memSize = 0L
   var diskSize = 0L
-  var externalBlockStoreSize = 0L
 
   def isCached: Boolean = (memSize + diskSize > 0) && numCachedPartitions > 0