[ https://issues.apache.org/jira/browse/HBASE-16417?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16208246#comment-16208246 ]
Eshcar Hillel commented on HBASE-16417: --------------------------------------- bq. I do have concern over the 2% size threshold to make an in memory flush(flatten). That seems too less and very aggressive Anoop I understand your concern. This number also came as a surprise to us :) However, experiments show that with this small active fraction gc decreases and throughput increases as a result of using smaller skip list. The intention is that this becomes the new default. But note that the pipeline is also changed to carry more segments before performing the merge of their indices. > In-Memory MemStore Policy for Flattening and Compactions > -------------------------------------------------------- > > Key: HBASE-16417 > URL: https://issues.apache.org/jira/browse/HBASE-16417 > Project: HBase > Issue Type: Sub-task > Reporter: Anastasia Braginsky > Assignee: Eshcar Hillel > Fix For: 3.0.0 > > Attachments: HBASE-16417 - Adaptive Compaction Policy - 20171001.pdf, > HBASE-16417 - parameter tuning - 20171001.pdf, HBASE-16417-V01.patch, > HBASE-16417-benchmarkresults-20161101.pdf, > HBASE-16417-benchmarkresults-20161110.pdf, > HBASE-16417-benchmarkresults-20161123.pdf, > HBASE-16417-benchmarkresults-20161205.pdf, > HBASE-16417-benchmarkresults-20170309.pdf, > HBASE-16417-benchmarkresults-20170317.pdf, HBASE-16417.01.patch, > HBASE-16417.02.patch, HBASE-16417.03.patch, HBASE-16417.04.patch, > HBASE-16417.05.patch, HBASE-16417.06.patch > > -- This message was sent by Atlassian JIRA (v6.4.14#64029)