Github user sameeragarwal commented on a diff in the pull request:
https://github.com/apache/spark/pull/14412#discussion_r98604570
--- Diff:
core/src/main/scala/org/apache/spark/storage/BlockManagerMasterEndpoint.scala
---
@@ -188,24 +189,45 @@ class BlockManagerMasterEndpoint(
}
private def removeBlockManager(blockManagerId: BlockManagerId) {
+ val proactivelyReplicate =
conf.get("spark.storage.replication.proactive", "false").toBoolean
+
val info = blockManagerInfo(blockManagerId)
// Remove the block manager from blockManagerIdByExecutor.
blockManagerIdByExecutor -= blockManagerId.executorId
- // Remove it from blockManagerInfo and remove all the blocks.
- blockManagerInfo.remove(blockManagerId)
val iterator = info.blocks.keySet.iterator
while (iterator.hasNext) {
val blockId = iterator.next
val locations = blockLocations.get(blockId)
locations -= blockManagerId
if (locations.size == 0) {
blockLocations.remove(blockId)
+ logWarning(s"No more replicas available for $blockId !")
+ } else if ((blockId.isRDD || blockId.isInstanceOf[TestBlockId]) &&
proactivelyReplicate) {
+ // we only need to proactively replicate RDD blocks
--- End diff --
Also, might be nicer to make `proactivelyReplicate` the first check for
better short-circuiting.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
