Skip to content

Commit

Permalink
[SPARK-26726] Synchronize the amount of memory used by the broadcast …
Browse files Browse the repository at this point in the history
…variable to the UI display

…not synchronized to the UI display

## What changes were proposed in this pull request?
The amount of memory used by the broadcast variable is not synchronized to the UI display.
I added the case for BroadcastBlockId and updated the memory usage.

## How was this patch tested?

We can test this patch with unit tests.

Closes #23649 from httfighter/SPARK-26726.

Lead-authored-by: 韩田田00222924 <han.tiantian@zte.com.cn>
Co-authored-by: han.tiantian@zte.com.cn <han.tiantian@zte.com.cn>
Signed-off-by: Marcelo Vanzin <vanzin@cloudera.com>
(cherry picked from commit f4a17e9)
Signed-off-by: Marcelo Vanzin <vanzin@cloudera.com>
  • Loading branch information
httfighter authored and Marcelo Vanzin committed Jan 31, 2019
1 parent ad18faa commit 94a4b46
Show file tree
Hide file tree
Showing 2 changed files with 53 additions and 9 deletions.
Expand Up @@ -678,6 +678,7 @@ private[spark] class AppStatusListener(
event.blockUpdatedInfo.blockId match { event.blockUpdatedInfo.blockId match {
case block: RDDBlockId => updateRDDBlock(event, block) case block: RDDBlockId => updateRDDBlock(event, block)
case stream: StreamBlockId => updateStreamBlock(event, stream) case stream: StreamBlockId => updateStreamBlock(event, stream)
case broadcast: BroadcastBlockId => updateBroadcastBlock(event, broadcast)
case _ => case _ =>
} }
} }
Expand Down Expand Up @@ -736,15 +737,7 @@ private[spark] class AppStatusListener(
// Update the executor stats first, since they are used to calculate the free memory // Update the executor stats first, since they are used to calculate the free memory
// on tracked RDD distributions. // on tracked RDD distributions.
maybeExec.foreach { exec => maybeExec.foreach { exec =>
if (exec.hasMemoryInfo) { updateExecutorMemoryDiskInfo(exec, storageLevel, memoryDelta, diskDelta)
if (storageLevel.useOffHeap) {
exec.usedOffHeap = addDeltaToValue(exec.usedOffHeap, memoryDelta)
} else {
exec.usedOnHeap = addDeltaToValue(exec.usedOnHeap, memoryDelta)
}
}
exec.memoryUsed = addDeltaToValue(exec.memoryUsed, memoryDelta)
exec.diskUsed = addDeltaToValue(exec.diskUsed, diskDelta)
} }


// Update the block entry in the RDD info, keeping track of the deltas above so that we // Update the block entry in the RDD info, keeping track of the deltas above so that we
Expand Down Expand Up @@ -846,6 +839,39 @@ private[spark] class AppStatusListener(
} }
} }


private def updateBroadcastBlock(
event: SparkListenerBlockUpdated,
broadcast: BroadcastBlockId): Unit = {
val executorId = event.blockUpdatedInfo.blockManagerId.executorId
liveExecutors.get(executorId).foreach { exec =>
val now = System.nanoTime()
val storageLevel = event.blockUpdatedInfo.storageLevel

// Whether values are being added to or removed from the existing accounting.
val diskDelta = event.blockUpdatedInfo.diskSize * (if (storageLevel.useDisk) 1 else -1)
val memoryDelta = event.blockUpdatedInfo.memSize * (if (storageLevel.useMemory) 1 else -1)

updateExecutorMemoryDiskInfo(exec, storageLevel, memoryDelta, diskDelta)
maybeUpdate(exec, now)
}
}

private def updateExecutorMemoryDiskInfo(
exec: LiveExecutor,
storageLevel: StorageLevel,
memoryDelta: Long,
diskDelta: Long): Unit = {
if (exec.hasMemoryInfo) {
if (storageLevel.useOffHeap) {
exec.usedOffHeap = addDeltaToValue(exec.usedOffHeap, memoryDelta)
} else {
exec.usedOnHeap = addDeltaToValue(exec.usedOnHeap, memoryDelta)
}
}
exec.memoryUsed = addDeltaToValue(exec.memoryUsed, memoryDelta)
exec.diskUsed = addDeltaToValue(exec.diskUsed, diskDelta)
}

private def getOrCreateStage(info: StageInfo): LiveStage = { private def getOrCreateStage(info: StageInfo): LiveStage = {
val stage = liveStages.computeIfAbsent((info.stageId, info.attemptNumber), val stage = liveStages.computeIfAbsent((info.stageId, info.attemptNumber),
new Function[(Int, Int), LiveStage]() { new Function[(Int, Int), LiveStage]() {
Expand Down
Expand Up @@ -875,6 +875,24 @@ class AppStatusListenerSuite extends SparkFunSuite with BeforeAndAfter {
intercept[NoSuchElementException] { intercept[NoSuchElementException] {
check[StreamBlockData](stream1.name) { _ => () } check[StreamBlockData](stream1.name) { _ => () }
} }

// Update a BroadcastBlock.
val broadcast1 = BroadcastBlockId(1L)
listener.onBlockUpdated(SparkListenerBlockUpdated(
BlockUpdatedInfo(bm1, broadcast1, level, 1L, 1L)))

check[ExecutorSummaryWrapper](bm1.executorId) { exec =>
assert(exec.info.memoryUsed === 1L)
assert(exec.info.diskUsed === 1L)
}

// Drop a BroadcastBlock.
listener.onBlockUpdated(SparkListenerBlockUpdated(
BlockUpdatedInfo(bm1, broadcast1, StorageLevel.NONE, 1L, 1L)))
check[ExecutorSummaryWrapper](bm1.executorId) { exec =>
assert(exec.info.memoryUsed === 0)
assert(exec.info.diskUsed === 0)
}
} }


test("eviction of old data") { test("eviction of old data") {
Expand Down

0 comments on commit 94a4b46

Please sign in to comment.