Hong Shen created SPARK-6738:
--------------------------------
Summary: EstimateSize is difference with spill file size
Key: SPARK-6738
URL: https://issues.apache.org/jira/browse/SPARK-6738
Project: Spark
Issue Type: Bug
Components: Spark Core
Affects Versions: 1.2.0
Reporter: Hong Shen
ExternalAppendOnlyMap spill 1100M data to disk:
15/04/07 16:39:48 INFO collection.ExternalAppendOnlyMap: Thread 51 spilling
in-memory map of 1106.5 MB to disk (12 times so far)
/data11/yarnenv/local/usercache/spark/appcache/application_1423737010718_40308573/spark-local-20150407163931-994b/30/temp_local_e4347165-6263-4678-9f1d-67ad4bcd8fb5
15/04/07 16:39:49 INFO collection.ExternalAppendOnlyMap: Thread 51 spilling
in-memory map of 1106.3 MB to disk (13 times so far)
/data6/yarnenv/local/usercache/spark/appcache/application_1423737010718_40308573/spark-local-20150407163931-1e29/26/temp_local_76f9900b-1b3d-4cef-b3a2-6afcde14bbd9
15/04/07 16:39:49 INFO collection.ExternalAppendOnlyMap: Thread 51 spilling
in-memory map of 1105.8 MB to disk (14 times so far)
/data7/yarnenv/local/usercache/spark/appcache/application_1423737010718_40308573/spark-local-20150407163931-f883/26/temp_local_3ade0aec-ac1d-469d-bc99-b6fa87cb649b
15/04/07 16:39:50 INFO collection.ExternalAppendOnlyMap: Thread 51 spilling
in-memory map of 1106.8 MB to disk (15 times so far)
But the file size is only 1.1M.
[tdwadmin@tdw-10-215-149-231
~/tdwenv/tdwgaia/logs/container-logs/application_1423737010718_40308573/container_1423737010718_40308573_01_000008]$
ll -h
/data7/yarnenv/local/usercache/spark/appcache/application_1423737010718_40308573/spark-local-20150407163931-f883/26/temp_local_3ade0aec-ac1d-469d-bc99-b6fa87cb649b
-rw-r----- 1 spark users 1.1M Apr 7 16:39
/data7/yarnenv/local/usercache/spark/appcache/application_1423737010718_40308573/spark-local-20150407163931-f883/26/temp_local_3ade0aec-ac1d-469d-bc99-b6fa87cb649b
The estimateSize is hugh difference with spill file size
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]