[ https://issues.apache.org/jira/browse/HBASE-3507?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12991605#comment-12991605 ]
Ted Yu commented on HBASE-3507: ------------------------------- In rebalance(), regions_table maps request count to region. However, we should consider regions with same number of requests - hash collision. Also, we should consider the current region assignment before calling admin.move() e.g. consider the top two most heavily read regions A (on RS1) and B (on RS2) If later requests for B get higher than requests for A, current patch would shuffle region A (to RS2) with region B - an unnecessary action. Using more complex logic, we should balance the sum of requests landed on each region server. > requests count per HRegion and rebalance command > ------------------------------------------------ > > Key: HBASE-3507 > URL: https://issues.apache.org/jira/browse/HBASE-3507 > Project: HBase > Issue Type: Improvement > Components: performance, regionserver > Reporter: Sebastian Bauer > Priority: Trivial > Attachments: hbase-requestsCount-2.patch, hbase-requestsCount.patch > > > Path-1 add another mertic for HRegion to count request made to region. > Path-2 add another command to hbase shell to grab all regions, sort by > requests from Path-1 and move in round-robin algorithm to servers -- This message is automatically generated by JIRA. - For more information on JIRA, see: http://www.atlassian.com/software/jira