lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

Disable EmrFS file metadata caching and EMR Spark's data prefetcher feature

Browse Source
This commit is contained in:
Rahil Chertara
2022-07-20 17:04:00 -07:00
parent 2b828ccb98
commit 473be87aa5
1 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/DefaultSource.scala
View File

@@ -56,6 +56,9 @@ class DefaultSource extends RelationProvider
// Enable "passPartitionByAsOptions" to support "write.partitionBy(...)"
spark.conf.set("spark.sql.legacy.sources.write.passPartitionByAsOptions", "true")
}
// Revisit EMR Spark and EMRFS incompatibilities, for now disable
spark.conf.set("spark.sql.dataPrefetch.enabled", "false")
spark.sparkContext.hadoopConfiguration.set("fs.s3.metadata.cache.expiration.seconds", "0")
}
private val log = LogManager.getLogger(classOf[DefaultSource])