Skip to content

Added java system variable spark.hadoop.checkoutputspec. Set it to false... #958

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

Added java system variable spark.hadoop.checkoutputspec. Set it to false... #958

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: 9 additions & 3 deletions core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -688,10 +688,13 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
val wrappedConf = new SerializableWritable(job.getConfiguration)
val outfmt = job.getOutputFormatClass
val jobFormat = outfmt.newInstance
val env = SparkEnv.get

if (jobFormat.isInstanceOf[NewFileOutputFormat[_, _]]) {
// FileOutputFormat ignores the filesystem parameter
jobFormat.checkOutputSpecs(job)
if(env.conf.getBoolean("spark.hadoop.checkoutputspec", true)) {
jobFormat.checkOutputSpecs(job)
}
}

def writeShard(context: TaskContext, iter: Iterator[(K,V)]): Int = {
Expand Down Expand Up @@ -741,6 +744,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
val outputFormatInstance = conf.getOutputFormat
val keyClass = conf.getOutputKeyClass
val valueClass = conf.getOutputValueClass
val env = SparkEnv.get
if (outputFormatInstance == null) {
throw new SparkException("Output format class not set")
}
Expand All @@ -757,8 +761,10 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])

if (outputFormatInstance.isInstanceOf[FileOutputFormat[_, _]]) {
// FileOutputFormat ignores the filesystem parameter
val ignoredFs = FileSystem.get(conf)
conf.getOutputFormat.checkOutputSpecs(ignoredFs, conf)
if(env.conf.getBoolean("spark.hadoop.checkoutputspec", true)) {
val ignoredFs = FileSystem.get(conf)
conf.getOutputFormat.checkOutputSpecs(ignoredFs, conf)
}
}

val writer = new SparkHadoopWriter(conf)
Expand Down