1
0

Merge pull request #6154 from rahil-c/rahil-c/disable-emrSpark-properties

[HUDI-4434] Disable EmrFS file metadata caching and EMR Spark's data prefetcher feature
This commit is contained in:
wenningd
2022-07-21 11:35:52 -07:00
committed by GitHub

View File

@@ -57,6 +57,9 @@ 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])