HyukjinKwon commented on a change in pull request #33748:
URL: https://github.com/apache/spark/pull/33748#discussion_r689991000
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala
##########
@@ -154,11 +155,18 @@ class OrcFileFormat
(file: PartitionedFile) => {
val conf = broadcastedConf.value.value
+ val metaCacheEnabled =
+ conf.getBoolean(SQLConf.FILE_META_CACHE_ORC_ENABLED.key, false)
val filePath = new Path(new URI(file.filePath))
val fs = filePath.getFileSystem(conf)
- val readerOptions = OrcFile.readerOptions(conf).filesystem(fs)
+ val readerOptions = if (metaCacheEnabled) {
+ val tail = OrcFileMeta.readTailFromCache(filePath, conf)
+ OrcFile.readerOptions(conf).filesystem(fs).orcTail(tail)
Review comment:
What happen if the file is replaced?
--
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]
