Github user mridulm commented on a diff in the pull request:
https://github.com/apache/spark/pull/17024#discussion_r102607469
--- Diff:
core/src/main/scala/org/apache/spark/rdd/ReliableCheckpointRDD.scala ---
@@ -169,14 +174,24 @@ private[spark] object ReliableCheckpointRDD extends
Logging {
val bufferSize = env.conf.getInt("spark.buffer.size", 65536)
val fileOutputStream = if (blockSize < 0) {
- fs.create(tempOutputPath, false, bufferSize)
+ val checkpointCodec =
env.conf.get("spark.checkpoint.compress.codec", "none")
+ val fileStream = fs.create(tempOutputPath, false, bufferSize)
+ if
(CompressionCodec.ALL_COMPRESSION_CODECS_SHORT.contains(checkpointCodec)) {
+ val compressionCodec = CompressionCodec.createCodec(env.conf,
checkpointCodec)
+ logInfo(s"Compressing using $checkpointCodec.")
+ compressionCodec.compressedOutputStream(fileStream)
+ } else {
+ fileStream
+ }
} else {
// This is mainly for testing purpose
fs.create(tempOutputPath, false, bufferSize,
fs.getDefaultReplication(fs.getWorkingDirectory), blockSize)
}
val serializer = env.serializer.newInstance()
val serializeStream = serializer.serializeStream(fileOutputStream)
+ logInfo(s"Starting to write to checkpoint file $tempOutputPath.")
--- End diff --
logDebug should be fine too.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
