[ https://issues.apache.org/jira/browse/HBASE-9775?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13815341#comment-13815341 ]
stack commented on HBASE-9775: ------------------------------ bq, I've tried it myself (exactly the same approach), but I didn't see a real difference. Do you see one in your tests? Minor (Certain allocation hotspots went from 3% to 2.4% in my extreme allocation test which probably means close to zero diff). I left it in since on the face of it there are less allocations. I'll commit this since the rig can be useful. Want to do some comment/javadoc first though. > Client write path perf issues > ----------------------------- > > Key: HBASE-9775 > URL: https://issues.apache.org/jira/browse/HBASE-9775 > Project: HBase > Issue Type: Bug > Components: Client > Affects Versions: 0.96.0 > Reporter: Elliott Clark > Priority: Critical > Attachments: 9775.rig.txt, 9775.rig.v2.patch, 9775.rig.v3.patch, > Charts Search Cloudera Manager - ITBLL.png, Charts Search Cloudera > Manager.png, hbase-9775.patch, job_run.log, short_ycsb.png, ycsb.png, > ycsb_insert_94_vs_96.png > > > Testing on larger clusters has not had the desired throughput increases. -- This message was sent by Atlassian JIRA (v6.1#6144)