duanmeng created SPARK-33022: -------------------------------- Summary: partition length is wrong after merge partition segments in BypassMergeSortShuffleWriter Key: SPARK-33022 URL: https://issues.apache.org/jira/browse/SPARK-33022 Project: Spark Issue Type: Bug Components: Spark Core Affects Versions: 2.4.6 Reporter: duanmeng
A data file might be empty even after DiskBlockObjectWriter committing it in BypassMergeSortShuffleWriter, returned wrong lengths in writePartitionedFile, and then cause data lost. This is related to disk/kernel but we can avoid it in spark without any performance loss. We can compare partitionWriterSegments[i].length with the length[i] after Utils.copyStream. I added some logs and caught the failure, The log when this issue happened {code:java} 20/09/28 00:42:44 INFO sort.BypassMergeSortShuffleWriter: partitionWriterSegments[0]: (name=temp_shuffle_38244ef5-8e97-4428-97b8-feffc16fc9f7, offset=0, length=1462) 20/09/28 00:42:46 INFO sort.BypassMergeSortShuffleWriter: File length: 0 20/09/28 00:42:46 INFO sort.BypassMergeSortShuffleWriter: Copied stream length: 0{code} The peer log when this issue didn't happen {code:java} 20/09/28 10:11:45 INFO sort.BypassMergeSortShuffleWriter: partitionWriterSegments[0]: (name=temp_shuffle_f6937469-39fd-4576-b40e-69f4276cc8e4, offset=0, length=1462) 20/09/28 10:11:45 INFO sort.BypassMergeSortShuffleWriter: File length: 1462 20/09/28 10:11:45 INFO sort.BypassMergeSortShuffleWriter: Copied stream length: 1462 {code} -- This message was sent by Atlassian Jira (v8.3.4#803005) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org