[ https://issues.apache.org/jira/browse/SPARK-3151?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16118347#comment-16118347 ]
Eyal Farago commented on SPARK-3151: ------------------------------------ created PR 18855: https://github.com/apache/spark/pull/18855 > DiskStore attempts to map any size BlockId without checking MappedByteBuffer > limit > ---------------------------------------------------------------------------------- > > Key: SPARK-3151 > URL: https://issues.apache.org/jira/browse/SPARK-3151 > Project: Spark > Issue Type: Bug > Components: Block Manager, Spark Core > Affects Versions: 1.0.2 > Environment: IBM 64-bit JVM PPC64 > Reporter: Damon Brown > Priority: Minor > > [DiskStore|https://github.com/apache/spark/blob/master/core/src/main/scala/org/apache/spark/storage/DiskStore.scala] > attempts to memory map the block file in {{def getBytes}}. If the file is > larger than 2GB (Integer.MAX_VALUE) as specified by > [FileChannel.map|http://docs.oracle.com/javase/7/docs/api/java/nio/channels/FileChannel.html#map%28java.nio.channels.FileChannel.MapMode,%20long,%20long%29], > then the memory map fails. > {code} > Some(channel.map(MapMode.READ_ONLY, segment.offset, segment.length)) # line > 104 > {code} -- This message was sent by Atlassian JIRA (v6.4.14#64029) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org