Skip to content

[SPARK-7689] Remove TTL-based metadata cleaning in Spark 2.0 #10534

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
JoshRosen wants to merge 13 commits into from
Closed

[SPARK-7689] Remove TTL-based metadata cleaning in Spark 2.0 #10534

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
9427635
Remove MapOutputTracker cleaner.
JoshRosen Dec 31, 2015
23669a7
Remove from HttpBroadcast
JoshRosen Dec 31, 2015
f2c2f5d
Remove from BlockManager.
JoshRosen Dec 31, 2015
3940e97
Delete TimeStampedHashSet
JoshRosen Dec 31, 2015
98b732a
All of the rest of the changes.
JoshRosen Dec 31, 2015
5ffe30f
Merge remote-tracking branch 'origin/master' into remove-ttl-based-cl…
JoshRosen Jan 2, 2016
e6482fa
Thread-safety fixes.
JoshRosen Jan 2, 2016
1d96791
Update StreamingContextSuite tests.
JoshRosen Jan 3, 2016
08b026e
Merge remote-tracking branch 'origin/master' into remove-ttl-based-cl…
JoshRosen Jan 6, 2016
75ac218
Update tests to use dummy time config
JoshRosen Jan 6, 2016
8b7ca1c
Remove old todo
JoshRosen Jan 4, 2016
9704bc2
Add missing import.
JoshRosen Jan 6, 2016
2451963
Update configuration.md
JoshRosen Jan 6, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Remove from BlockManager.
  • Loading branch information
@JoshRosen
JoshRosen committed Dec 31, 2015
commit f2c2f5dd5820a41e31ef73b5b918299649f8cd72
39 changes: 1 addition & 38 deletions core/src/main/scala/org/apache/spark/storage/BlockManager.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,7 @@ private[spark] class BlockManager(

val diskBlockManager = new DiskBlockManager(this, conf)

private val blockInfo = new TimeStampedHashMap[BlockId, BlockInfo]
private val blockInfo = new HashMap[BlockId, BlockInfo]

private val futureExecutionContext = ExecutionContext.fromExecutorService(
ThreadUtils.newDaemonCachedThreadPool("block-manager-future", 128))
Expand Down Expand Up @@ -147,11 +147,6 @@ private[spark] class BlockManager(
private var asyncReregisterTask: Future[Unit] = null
private val asyncReregisterLock = new Object

private val metadataCleaner = new MetadataCleaner(
MetadataCleanerType.BLOCK_MANAGER, this.dropOldNonBroadcastBlocks, conf)
private val broadcastCleaner = new MetadataCleaner(
MetadataCleanerType.BROADCAST_VARS, this.dropOldBroadcastBlocks, conf)

// Field related to peer block managers that are necessary for block replication
@volatile private var cachedPeers: Seq[BlockManagerId] = _
private val peerFetchLock = new Object
Expand Down Expand Up @@ -1141,36 +1136,6 @@ private[spark] class BlockManager(
}
}

private def dropOldNonBroadcastBlocks(cleanupTime: Long): Unit = {
logInfo(s"Dropping non broadcast blocks older than $cleanupTime")
dropOldBlocks(cleanupTime, !_.isBroadcast)
}

private def dropOldBroadcastBlocks(cleanupTime: Long): Unit = {
logInfo(s"Dropping broadcast blocks older than $cleanupTime")
dropOldBlocks(cleanupTime, _.isBroadcast)
}

private def dropOldBlocks(cleanupTime: Long, shouldDrop: (BlockId => Boolean)): Unit = {
val iterator = blockInfo.getEntrySet.iterator
while (iterator.hasNext) {
val entry = iterator.next()
val (id, info, time) = (entry.getKey, entry.getValue.value, entry.getValue.timestamp)
if (time < cleanupTime && shouldDrop(id)) {
info.synchronized {
val level = info.level
if (level.useMemory) { memoryStore.remove(id) }
if (level.useDisk) { diskStore.remove(id) }
if (level.useOffHeap) { externalBlockStore.remove(id) }
iterator.remove()
logInfo(s"Dropped block $id")
}
val status = getCurrentBlockStatus(id, info)
reportBlockStatus(id, info, status)
}
}
}

private def shouldCompress(blockId: BlockId): Boolean = {
blockId match {
case _: ShuffleBlockId => compressShuffle
Expand Down Expand Up @@ -1248,8 +1213,6 @@ private[spark] class BlockManager(
if (externalBlockStoreInitialized) {
externalBlockStore.clear()
}
metadataCleaner.cancel()
broadcastCleaner.cancel()
futureExecutionContext.shutdownNow()
logInfo("BlockManager stopped")
}
Expand Down
3 changes: 1 addition & 2 deletions core/src/main/scala/org/apache/spark/util/MetadataCleaner.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,8 +62,7 @@ private[spark] class MetadataCleaner(

private[spark] object MetadataCleanerType extends Enumeration {

val SPARK_CONTEXT, BLOCK_MANAGER,
SHUFFLE_BLOCK_MANAGER, BROADCAST_VARS = Value
val SPARK_CONTEXT, SHUFFLE_BLOCK_MANAGER, BROADCAST_VARS = Value

type MetadataCleanerType = Value

Expand Down