Skip to content

improve OnHeapSpillManager concurrency #990

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

Merged
lihao712 merged 1 commit into from
May 15, 2025
Merged

improve OnHeapSpillManager concurrency #990

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
10 changes: 9 additions & 1 deletion spark-extension/src/main/scala/org/apache/spark/sql/blaze/memory/OnHeapSpill.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,16 +28,24 @@ case class OnHeapSpill(hsm: OnHeapSpillManager, id: Int) extends Logging {
def diskIOTime: Long = spillBuf.diskIOTime

def write(buf: ByteBuffer): Unit = {
var needSpill = false
synchronized {
spillBuf match {
case _: MemBasedSpillBuf =>
val acquiredMemory = hsm.acquireMemory(buf.capacity())
if (acquiredMemory < buf.capacity()) { // cannot allocate memory, will spill buffer
hsm.freeMemory(acquiredMemory)
spillInternal()
needSpill = true
}
case _ =>
}
}

if (needSpill) {
spillInternal()
}

synchronized {
spillBuf.write(buf)
}
}
Expand Down
7 changes: 4 additions & 3 deletions spark-extension/src/main/scala/org/apache/spark/sql/blaze/memory/OnHeapSpillManager.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@ package org.apache.spark.sql.blaze.memory

import java.nio.ByteBuffer

import scala.collection.concurrent
import scala.collection.mutable
import scala.collection.mutable.ArrayBuffer

Expand Down Expand Up @@ -180,10 +181,10 @@ class OnHeapSpillManager(taskContext: TaskContext)
}

object OnHeapSpillManager extends Logging {
val all: mutable.Map[Long, OnHeapSpillManager] = mutable.Map()
val all: mutable.Map[Long, OnHeapSpillManager] = concurrent.TrieMap[Long, OnHeapSpillManager]()

def current: OnHeapSpillManager = {
val taskContext = TaskContext.get
all.getOrElseUpdate(taskContext.taskAttemptId(), new OnHeapSpillManager(taskContext))
val tc = TaskContext.get
all.getOrElseUpdate(tc.taskAttemptId(), new OnHeapSpillManager(tc))
}
}