[ https://issues.apache.org/jira/browse/HBASE-10624?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13919491#comment-13919491 ]
Jean-Marc Spaggiari commented on HBASE-10624: --------------------------------------------- On 4 nodes cluster, with Hadoop 2.2.0. 80%tile. One client, non-mapred. v2 = 24055 writes/seconds (Std Dev 1.8%) v4 = 23899 writes/seconds (Std Dev 3.26%) v2 is 0.65% faster than v4. Not that much of a difference. > Fix 2 new findbugs warnings > --------------------------- > > Key: HBASE-10624 > URL: https://issues.apache.org/jira/browse/HBASE-10624 > Project: HBase > Issue Type: Bug > Reporter: Ted Yu > Assignee: Ted Yu > Fix For: 0.96.2, 0.98.1, 0.99.0, 0.94.18 > > Attachments: 10624-v1.txt, 10624-v2.txt, 10624-v4.txt > > > Inconsistent synchronization of > org.apache.hadoop.hbase.regionserver.TimeRangeTracker.maximumTimestamp; > locked 66% of time > {code} > In class org.apache.hadoop.hbase.regionserver.TimeRangeTracker > Field org.apache.hadoop.hbase.regionserver.TimeRangeTracker.maximumTimestamp > Synchronized 66% of the time > {code} > Inconsistent synchronization of > org.apache.hadoop.hbase.regionserver.TimeRangeTracker.minimumTimestamp; > locked 62% of time > {code} > In class org.apache.hadoop.hbase.regionserver.TimeRangeTracker > Field org.apache.hadoop.hbase.regionserver.TimeRangeTracker.minimumTimestamp > Synchronized 62% of the time > {code} -- This message was sent by Atlassian JIRA (v6.2#6252)