[ https://issues.apache.org/jira/browse/HBASE-14920?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15284779#comment-15284779 ]
Eshcar Hillel commented on HBASE-14920: --------------------------------------- [~anoop.hbase] the FlushNonSloppyStoresFirstPolicy first looks for large non-sloppy stores to flush; if no large stores there, it looks for large sloppy stores (*by sloppy we mean with compacting memstore); and if it fails to find any then it flushes all the stores. When closing a region all segments in the pipeline are flushed one after the other. This is okay for now since most of the time there are one or two segments in the pipeline. At the context of the memory optimization done in HBASE-14921 the pipeline may consist more than two segments, there we can revise this solution, and apply a compaction to generate a single segment to be flushed to disk. Looks to me this is ready for commit :) > Compacting Memstore > ------------------- > > Key: HBASE-14920 > URL: https://issues.apache.org/jira/browse/HBASE-14920 > Project: HBase > Issue Type: Sub-task > Reporter: Eshcar Hillel > Assignee: Eshcar Hillel > Attachments: HBASE-14920-V01.patch, HBASE-14920-V02.patch, > HBASE-14920-V03.patch, HBASE-14920-V04.patch, HBASE-14920-V05.patch, > HBASE-14920-V06.patch, HBASE-14920-V07.patch, HBASE-14920-V08.patch, > HBASE-14920-V09.patch, HBASE-14920-V10.patch, move.to.junit4.patch > > > Implementation of a new compacting memstore with non-optimized immutable > segment representation -- This message was sent by Atlassian JIRA (v6.3.4#6332)