[ https://issues.apache.org/jira/browse/HBASE-16417?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15932430#comment-15932430 ]
Eshcar Hillel commented on HBASE-16417: --------------------------------------- I can use the code of HBASE-17655 to run the mixed workload benchmark to see if parallel seek fixes the high percentiles degradation. However as I understand the code despite the fact that parallelSeekEnabled is set to true when StoreScanner is created, since isLazy = explicitColumnQuery && lazySeekEnabledGlobally and since lazySeekEnabledGlobally is set to true by default and explicitColumnQuery is set to numCol > 0 which is true in our case (I think it is always true) then parallelSeek() is never invoked. Am I missing anything? What was the original intention -- when would we not want to run parallel seek? > 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: 2.0.0 > > Attachments: 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 > > -- This message was sent by Atlassian JIRA (v6.3.15#6346)