[ https://issues.apache.org/jira/browse/BEAM-5036?focusedWorklogId=150766&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-150766 ]
ASF GitHub Bot logged work on BEAM-5036: ---------------------------------------- Author: ASF GitHub Bot Created on: 03/Oct/18 14:41 Start Date: 03/Oct/18 14:41 Worklog Time Spent: 10m Work Description: timrobertson100 commented on issue #6289: [BEAM-5036] Optimize the FileBasedSink WriteOperation.moveToOutput() URL: https://github.com/apache/beam/pull/6289#issuecomment-426662992 I've run some PerfKit tests for [HDFS with this PR](https://builds.apache.org/job/beam_PerformanceTests_TextIOIT_HDFS/744/console) and [GCS with this PR](https://builds.apache.org/job/beam_PerformanceTests_TextIOIT/1086/console). The last 6 timings for each are: ### HDFS ``` 08:33:54 run_time 530.203248 seconds 14:33:30 run_time 509.528935 seconds 20:32:50 run_time 442.749163 seconds 02:31:21 run_time 402.220293 seconds 08:31:30 run_time 413.367303 seconds -- and with this PR: 14:30:40 run_time 378.867292 seconds ``` ### GCS ``` 14:32:25 run_time 390.459900 seconds 20:32:06 run_time 424.058663 seconds 02:31:45 run_time 412.350028 seconds 08:33:19 run_time 524.147186 seconds 14:31:16 run_time 364.864536 seconds -- and with this PR: 16:19:23 run_time 387.196383 seconds ``` Given these are using 1 million records only and small clusters I don't they tell us all that much, but thought it worth capturing here regardless. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org Issue Time Tracking ------------------- Worklog Id: (was: 150766) Time Spent: 9h 40m (was: 9.5h) > Optimize FileBasedSink's WriteOperation.moveToOutput() > ------------------------------------------------------ > > Key: BEAM-5036 > URL: https://issues.apache.org/jira/browse/BEAM-5036 > Project: Beam > Issue Type: Improvement > Components: io-java-files > Affects Versions: 2.5.0 > Reporter: Jozef Vilcek > Assignee: Tim Robertson > Priority: Major > Time Spent: 9h 40m > Remaining Estimate: 0h > > moveToOutput() methods in FileBasedSink.WriteOperation implements move by > copy+delete. It would be better to use a rename() which can be much more > effective for some filesystems. > Filesystem must support cross-directory rename. BEAM-4861 is related to this > for the case of HDFS filesystem. > Feature was discussed here: > http://mail-archives.apache.org/mod_mbox/beam-dev/201807.mbox/%3CCAF9t7_4Mp54pQ+vRrJrBh9Vx0=uaknupzd_qdh_qdm9vxll...@mail.gmail.com%3E -- This message was sent by Atlassian JIRA (v7.6.3#76005)