Skip to content

optimize driver memory #8

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

optimize driver memory #8

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
13 changes: 5 additions & 8 deletions service/src/main/scala/com/bytedance/css/service/deploy/master/ShuffleTaskManager.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@ class ShuffleTaskManager extends Logging {
// key appId-shuffleId
// store all reducerId-EpochId for a shuffleKey
private[deploy] val shuffleEpochSetMap =
new ConcurrentHashMap[String, ConcurrentHashMap[Int, util.List[PartitionInfo]]]()
new ConcurrentHashMap[String, util.HashSet[PartitionInfo]]()
private[deploy] val batchBlacklistMap =
new ConcurrentHashMap[String, ConcurrentHashMap[Int, util.List[FailedPartitionInfoBatch]]]()

Expand All @@ -48,7 +48,7 @@ class ShuffleTaskManager extends Logging {
numMappers: Int,
numPartitions: Int): Unit = {
shuffleMapperAttempts.putIfAbsent(shuffleKey, Array.fill(numMappers)(-1))
shuffleEpochSetMap.putIfAbsent(shuffleKey, new ConcurrentHashMap[Int, util.List[PartitionInfo]]())
shuffleEpochSetMap.putIfAbsent(shuffleKey, new util.HashSet[PartitionInfo]()))
reducerFileGroupsMap.putIfAbsent(shuffleKey, new Array[Array[CommittedPartitionInfo]](numPartitions))
}

Expand All @@ -71,9 +71,9 @@ class ShuffleTaskManager extends Logging {

// epochList not be null.
val epochSet = shuffleEpochSetMap.computeWhenAbsent(shuffleKey, _ => {
new ConcurrentHashMap[Int, util.List[PartitionInfo]]()
new util.HashSet[PartitionInfo]()
})
epochSet.put(mapId, epochList)
epochSet.addAll(epochList)

if (batchBlacklist != null) {
val blacklist = batchBlacklistMap.computeWhenAbsent(shuffleKey, _ => {
Expand Down Expand Up @@ -112,10 +112,7 @@ class ShuffleTaskManager extends Logging {
commitPieces: ConcurrentHashMap[String, ConcurrentSet[CommittedPartitionInfo]]): Boolean = {

// check for data lost
val allEpochSets = new util.HashSet[PartitionInfo]()
allEpochSets.addAll(
shuffleEpochSetMap.getOrDefault(shuffleKey, new ConcurrentHashMap[Int, util.List[PartitionInfo]]())
.values().asScala.flatMap(x => x.asScala.toSet[PartitionInfo]).toSet.asJava)
val allEpochSets = shuffleEpochSetMap.getOrDefault(shuffleKey, new util.HashSet[PartitionInfo]())

var dataLost = false
val validCommitted = allEpochSets.asScala
Expand Down