HyukjinKwon commented on a change in pull request #24712: [SPARK-27843][SQL]
Remove duplicate logic of calculate table size
URL: https://github.com/apache/spark/pull/24712#discussion_r287628774
##########
File path:
sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveStrategies.scala
##########
@@ -118,21 +118,12 @@ class DetermineTableStats(session: SparkSession) extends
Rule[LogicalPlan] {
if DDLUtils.isHiveTable(relation.tableMeta) &&
relation.tableMeta.stats.isEmpty =>
val table = relation.tableMeta
val sizeInBytes = if
(session.sessionState.conf.fallBackToHdfsForStatsEnabled) {
- try {
- val hadoopConf = session.sessionState.newHadoopConf()
- val tablePath = new Path(table.location)
- val fs: FileSystem = tablePath.getFileSystem(hadoopConf)
- fs.getContentSummary(tablePath).getLength
- } catch {
- case e: IOException =>
- logWarning("Failed to get table size from hdfs.", e)
- session.sessionState.conf.defaultSizeInBytes
- }
+ CommandUtils.calculateTotalSize(session, table)
Review comment:
Looks if getting size is failed, previously, it used `defaultSizeInBytes`
but now `0`. Can you check if it still behaves identically?
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
