[ https://issues.apache.org/jira/browse/HBASE-14636?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14962183#comment-14962183 ]
ramkrishna.s.vasudevan commented on HBASE-14636: ------------------------------------------------ bq.Is btw By-The-Way? Here it is Between. bq.The YCSB suite worked fine when all was onheap with 16G. If I offheap, even though I leave heap at 16, it OOMEs pretty quickly. I really doubt this. Onheap or offheap we should have the same implications except that we don't do the final ref counting. Seeing the logs that you attached I can see frequent compactions and every compaction creating a 11 to 13 G files. > Clear HFileScannerImpl#prevBlocks in btw Compaction flow > -------------------------------------------------------- > > Key: HBASE-14636 > URL: https://issues.apache.org/jira/browse/HBASE-14636 > Project: HBase > Issue Type: Sub-task > Components: regionserver, Scanners > Reporter: Anoop Sam John > Assignee: Anoop Sam John > Priority: Blocker > Fix For: 2.0.0 > > -- This message was sent by Atlassian JIRA (v6.3.4#6332)