Skip to content

[SPARK-25753][CORE]fix reading small files via BinaryFileRDD #22725

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
wants to merge 1 commit into from
Closed

[SPARK-25753][CORE]fix reading small files via BinaryFileRDD #22725

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
12 changes: 12 additions & 0 deletions core/src/main/scala/org/apache/spark/input/PortableDataStream.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,6 +52,18 @@ private[spark] abstract class StreamFileInputFormat[T]
val totalBytes = files.filterNot(_.isDirectory).map(_.getLen + openCostInBytes).sum
val bytesPerCore = totalBytes / defaultParallelism
val maxSplitSize = Math.min(defaultMaxSplitBytes, Math.max(openCostInBytes, bytesPerCore))

// For small files we need to ensure the min split size per node & rack <= maxSplitSize
val jobConfig = context.getConfiguration
val minSplitSizePerNode = jobConfig.getLong(CombineFileInputFormat.SPLIT_MINSIZE_PERNODE, 0L)
val minSplitSizePerRack = jobConfig.getLong(CombineFileInputFormat.SPLIT_MINSIZE_PERRACK, 0L)

if (maxSplitSize < minSplitSizePerNode) {
super.setMinSplitSizeNode(maxSplitSize)
}
if (maxSplitSize < minSplitSizePerRack) {
super.setMinSplitSizeRack(maxSplitSize)
}
super.setMaxSplitSize(maxSplitSize)
}

Expand Down
13 changes: 13 additions & 0 deletions core/src/test/scala/org/apache/spark/FileSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -320,6 +320,19 @@ class FileSuite extends SparkFunSuite with LocalSparkContext {
}
}

test("minimum split size per node and per rack should be less than or equal to maxSplitSize") {
sc = new SparkContext("local", "test")
val testOutput = Array[Byte](1, 2, 3, 4, 5)
val outFile = writeBinaryData(testOutput, 1)
sc.hadoopConfiguration.setLong(
"mapreduce.input.fileinputformat.split.minsize.per.node", 5123456)
sc.hadoopConfiguration.setLong(
"mapreduce.input.fileinputformat.split.minsize.per.rack", 5123456)

val (_, data) = sc.binaryFiles(outFile.getAbsolutePath).collect().head
assert(data.toArray === testOutput)
}

test("fixed record length binary file as byte array") {
sc = new SparkContext("local", "test")
val testOutput = Array[Byte](1, 2, 3, 4, 5, 6)
Expand Down