pan3793 commented on code in PR #5591:
URL: https://github.com/apache/kyuubi/pull/5591#discussion_r1418562380
##########
externals/kyuubi-spark-sql-engine/src/main/scala/org/apache/kyuubi/engine/spark/operation/ExecuteStatement.scala:
##########
@@ -158,6 +171,24 @@ class ExecuteStatement(
override def iterator: Iterator[Any] =
incrementalCollectResult(resultDF)
})
} else {
+ val sparkSave = getSessionConf(OPERATION_RESULT_SAVE_TO_FILE, spark)
+ lazy val threshold =
getSessionConf(OPERATION_RESULT_SAVE_TO_FILE_THRESHOLD, spark)
+ if (hasResultSet && sparkSave && shouldSaveResultToHdfs(resultMaxRows,
threshold, result)) {
+ val sessionId = session.handle.identifier.toString
+ val savePath =
session.sessionManager.getConf.get(OPERATION_RESULT_SAVE_TO_FILE_PATH)
+ saveFileName = Some(s"$savePath/$engineId/$sessionId/$statementId")
+ val colName = range(0, result.schema.size).map(x => "col" + x)
+ if (resultMaxRows > 0) {
+ result.toDF(colName: _*).limit(resultMaxRows).write
+ .option("compression", "zstd").format("orc").save(saveFileName.get)
Review Comment:
IIRC, the zstd implementation of ORC is powered by aircompressor, I'm not
sure if it's powerful as zstd-jni does. Anyway, it's internal implementation
detail, we can change it latter if we have better solution
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
