[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13630149#comment-13630149 ] Ted Yu commented on HBASE-8119: --- @Enis: The following javadoc warnings appear in several QA test report: [WARNING] /home/jenkins/jenkins-slave/workspace/PreCommit-HBASE-Build/trunk/hbase-server/src/main/java/org/apache/hadoop/hbase/master/balancer/StochasticLoadBalancer.java:373: warning - @param argument initialRegionMapping is not a parameter name. [WARNING] /home/jenkins/jenkins-slave/workspace/PreCommit-HBASE-Build/trunk/hbase-server/src/main/java/org/apache/hadoop/hbase/master/balancer/StochasticLoadBalancer.java:373: warning - @param argument clusterState is not a parameter name. Please fix them. Thanks Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.98.0, 0.95.1 Attachments: hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13630434#comment-13630434 ] Enis Soztutar commented on HBASE-8119: -- Thanks Ted, I'll provide an addendum. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.98.0, 0.95.1 Attachments: hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13630613#comment-13630613 ] Enis Soztutar commented on HBASE-8119: -- Ted, I think the committed patch already has the warnings fixed. Where did you see the warnings? My local javadoc build does not show any warnings. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.98.0, 0.95.1 Attachments: hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13630623#comment-13630623 ] Ted Yu commented on HBASE-8119: --- {code} * @param initialRegionMapping Map of where the regions started. * @param clusterState Map of ServerName to list of regions. * @return a double of a cost associated with the proposed */ protected double computeCost(Cluster cluster) { {code} The first two parameters in javadoc above no longer apply to the method. You can see the javadoc warning in the most recent QA report, as of this writing: https://builds.apache.org/job/PreCommit-HBASE-Build/5297/console Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.98.0, 0.95.1 Attachments: hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13630634#comment-13630634 ] Elliott Clark commented on HBASE-8119: -- [~enis] I've got some code clean up in the balancer, I'll post an issue with the fix in a few mins. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.98.0, 0.95.1 Attachments: hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13630654#comment-13630654 ] Elliott Clark commented on HBASE-8119: -- Either way. I was just poking around the code so I did a really quick java doc pass in a different patch. We can do whatever you want. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.98.0, 0.95.1 Attachments: hbase-8119_addendum.patch, hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13630656#comment-13630656 ] Ted Yu commented on HBASE-8119: --- I think addendum should be checked in so that subsequent QA run doesn't have the javadoc warning. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.98.0, 0.95.1 Attachments: hbase-8119_addendum.patch, hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13630667#comment-13630667 ] Enis Soztutar commented on HBASE-8119: -- Ok, committed the addendum. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.98.0, 0.95.1 Attachments: hbase-8119_addendum.patch, hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13630802#comment-13630802 ] Hudson commented on HBASE-8119: --- Integrated in HBase-TRUNK #4059 (See [https://builds.apache.org/job/HBase-TRUNK/4059/]) HBASE-8119. Optimize StochasticLoadBalancer. Addendum patch for javadoc fixes (Revision 1467484) Result = SUCCESS enis : Files : * /hbase/trunk/hbase-server/src/main/java/org/apache/hadoop/hbase/master/balancer/StochasticLoadBalancer.java Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.98.0, 0.95.1 Attachments: hbase-8119_addendum.patch, hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13630907#comment-13630907 ] Hudson commented on HBASE-8119: --- Integrated in HBase-TRUNK-on-Hadoop-2.0.0 #496 (See [https://builds.apache.org/job/HBase-TRUNK-on-Hadoop-2.0.0/496/]) HBASE-8119. Optimize StochasticLoadBalancer. Addendum patch for javadoc fixes (Revision 1467484) Result = FAILURE enis : Files : * /hbase/trunk/hbase-server/src/main/java/org/apache/hadoop/hbase/master/balancer/StochasticLoadBalancer.java Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.98.0, 0.95.1 Attachments: hbase-8119_addendum.patch, hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13628717#comment-13628717 ] Hadoop QA commented on HBASE-8119: -- {color:red}-1 overall{color}. Here are the results of testing the latest attachment http://issues.apache.org/jira/secure/attachment/12578136/hbase-8119_v2.patch against trunk revision . {color:green}+1 @author{color}. The patch does not contain any @author tags. {color:green}+1 tests included{color}. The patch appears to include 6 new or modified tests. {color:red}-1 hadoop2.0{color}. The patch failed to compile against the hadoop 2.0 profile. Console output: https://builds.apache.org/job/PreCommit-HBASE-Build/5257//console This message is automatically generated. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.95.1 Attachments: hbase-8119_v2.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13629444#comment-13629444 ] Hadoop QA commented on HBASE-8119: -- {color:red}-1 overall{color}. Here are the results of testing the latest attachment http://issues.apache.org/jira/secure/attachment/12578278/hbase-8119_v3.patch against trunk revision . {color:green}+1 @author{color}. The patch does not contain any @author tags. {color:green}+1 tests included{color}. The patch appears to include 6 new or modified tests. {color:green}+1 hadoop2.0{color}. The patch compiles against the hadoop 2.0 profile. {color:red}-1 javadoc{color}. The javadoc tool appears to have generated 2 warning messages. {color:green}+1 javac{color}. The applied patch does not increase the total number of javac compiler warnings. {color:green}+1 findbugs{color}. The patch does not introduce any new Findbugs (version 1.3.9) warnings. {color:green}+1 release audit{color}. The applied patch does not increase the total number of release audit warnings. {color:red}-1 lineLengths{color}. The patch introduces lines longer than 100 {color:green}+1 site{color}. The mvn site goal succeeds with this patch. {color:green}+1 core tests{color}. The patch passed unit tests in . Test results: https://builds.apache.org/job/PreCommit-HBASE-Build/5273//testReport/ Findbugs warnings: https://builds.apache.org/job/PreCommit-HBASE-Build/5273//artifact/trunk/patchprocess/newPatchFindbugsWarningshbase-client.html Findbugs warnings: https://builds.apache.org/job/PreCommit-HBASE-Build/5273//artifact/trunk/patchprocess/newPatchFindbugsWarningshbase-examples.html Findbugs warnings: https://builds.apache.org/job/PreCommit-HBASE-Build/5273//artifact/trunk/patchprocess/newPatchFindbugsWarningshbase-protocol.html Findbugs warnings: https://builds.apache.org/job/PreCommit-HBASE-Build/5273//artifact/trunk/patchprocess/newPatchFindbugsWarningshbase-hadoop1-compat.html Findbugs warnings: https://builds.apache.org/job/PreCommit-HBASE-Build/5273//artifact/trunk/patchprocess/newPatchFindbugsWarningshbase-prefix-tree.html Findbugs warnings: https://builds.apache.org/job/PreCommit-HBASE-Build/5273//artifact/trunk/patchprocess/newPatchFindbugsWarningshbase-common.html Findbugs warnings: https://builds.apache.org/job/PreCommit-HBASE-Build/5273//artifact/trunk/patchprocess/newPatchFindbugsWarningshbase-hadoop-compat.html Findbugs warnings: https://builds.apache.org/job/PreCommit-HBASE-Build/5273//artifact/trunk/patchprocess/newPatchFindbugsWarningshbase-server.html Console output: https://builds.apache.org/job/PreCommit-HBASE-Build/5273//console This message is automatically generated. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.95.1 Attachments: hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13629553#comment-13629553 ] Elliott Clark commented on HBASE-8119: -- Thanks for the perf work. Next time we get a 0.95 rc out I'll make sure to test the balancer over a large cluster. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.98.0, 0.95.1 Attachments: hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13629625#comment-13629625 ] Hudson commented on HBASE-8119: --- Integrated in hbase-0.95-on-hadoop2 #66 (See [https://builds.apache.org/job/hbase-0.95-on-hadoop2/66/]) HBASE-8119 Optimize StochasticLoadBalancer (Revision 1467111) Result = FAILURE enis : Files : * /hbase/branches/0.95/hbase-client/src/main/java/org/apache/hadoop/hbase/HRegionInfo.java * /hbase/branches/0.95/hbase-server/src/main/java/org/apache/hadoop/hbase/master/HMaster.java * /hbase/branches/0.95/hbase-server/src/main/java/org/apache/hadoop/hbase/master/balancer/BaseLoadBalancer.java * /hbase/branches/0.95/hbase-server/src/main/java/org/apache/hadoop/hbase/master/balancer/StochasticLoadBalancer.java * /hbase/branches/0.95/hbase-server/src/test/java/org/apache/hadoop/hbase/master/balancer/BalancerTestBase.java * /hbase/branches/0.95/hbase-server/src/test/java/org/apache/hadoop/hbase/master/balancer/TestStochasticLoadBalancer.java Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.98.0, 0.95.1 Attachments: hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13629648#comment-13629648 ] Hudson commented on HBASE-8119: --- Integrated in HBase-TRUNK #4054 (See [https://builds.apache.org/job/HBase-TRUNK/4054/]) HBASE-8119 Optimize StochasticLoadBalancer (Revision 1467109) Result = FAILURE enis : Files : * /hbase/trunk/hbase-client/src/main/java/org/apache/hadoop/hbase/HRegionInfo.java * /hbase/trunk/hbase-server/src/main/java/org/apache/hadoop/hbase/master/HMaster.java * /hbase/trunk/hbase-server/src/main/java/org/apache/hadoop/hbase/master/balancer/BaseLoadBalancer.java * /hbase/trunk/hbase-server/src/main/java/org/apache/hadoop/hbase/master/balancer/StochasticLoadBalancer.java * /hbase/trunk/hbase-server/src/test/java/org/apache/hadoop/hbase/master/balancer/BalancerTestBase.java * /hbase/trunk/hbase-server/src/test/java/org/apache/hadoop/hbase/master/balancer/TestStochasticLoadBalancer.java Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.98.0, 0.95.1 Attachments: hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13629668#comment-13629668 ] Hudson commented on HBASE-8119: --- Integrated in hbase-0.95 #141 (See [https://builds.apache.org/job/hbase-0.95/141/]) HBASE-8119 Optimize StochasticLoadBalancer (Revision 1467111) Result = SUCCESS enis : Files : * /hbase/branches/0.95/hbase-client/src/main/java/org/apache/hadoop/hbase/HRegionInfo.java * /hbase/branches/0.95/hbase-server/src/main/java/org/apache/hadoop/hbase/master/HMaster.java * /hbase/branches/0.95/hbase-server/src/main/java/org/apache/hadoop/hbase/master/balancer/BaseLoadBalancer.java * /hbase/branches/0.95/hbase-server/src/main/java/org/apache/hadoop/hbase/master/balancer/StochasticLoadBalancer.java * /hbase/branches/0.95/hbase-server/src/test/java/org/apache/hadoop/hbase/master/balancer/BalancerTestBase.java * /hbase/branches/0.95/hbase-server/src/test/java/org/apache/hadoop/hbase/master/balancer/TestStochasticLoadBalancer.java Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.98.0, 0.95.1 Attachments: hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13629708#comment-13629708 ] Hudson commented on HBASE-8119: --- Integrated in HBase-TRUNK-on-Hadoop-2.0.0 #494 (See [https://builds.apache.org/job/HBase-TRUNK-on-Hadoop-2.0.0/494/]) HBASE-8119 Optimize StochasticLoadBalancer (Revision 1467109) Result = FAILURE enis : Files : * /hbase/trunk/hbase-client/src/main/java/org/apache/hadoop/hbase/HRegionInfo.java * /hbase/trunk/hbase-server/src/main/java/org/apache/hadoop/hbase/master/HMaster.java * /hbase/trunk/hbase-server/src/main/java/org/apache/hadoop/hbase/master/balancer/BaseLoadBalancer.java * /hbase/trunk/hbase-server/src/main/java/org/apache/hadoop/hbase/master/balancer/StochasticLoadBalancer.java * /hbase/trunk/hbase-server/src/test/java/org/apache/hadoop/hbase/master/balancer/BalancerTestBase.java * /hbase/trunk/hbase-server/src/test/java/org/apache/hadoop/hbase/master/balancer/TestStochasticLoadBalancer.java Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.98.0, 0.95.1 Attachments: hbase-8119_v2.patch, hbase-8119_v3.patch On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13627377#comment-13627377 ] Enis Soztutar commented on HBASE-8119: -- Thanks Elliot. I'll commit this unless objection by tomorrow. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Assignee: Enis Soztutar Priority: Critical Fix For: 0.95.1 On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13621200#comment-13621200 ] Elliott Clark commented on HBASE-8119: -- +1. Lets try this out on 0.95 releases. I'm still concerned about the one multiplier, but real world clusters will be the best judge. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Priority: Critical Fix For: 0.95.1 On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13613195#comment-13613195 ] Enis Soztutar commented on HBASE-8119: -- Stack, I've raised this to be critical, since w/o this or going back to the DefaultLB, LB becomes unusable even for mid-sized clusters. Bump it down if you think otherwise. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Priority: Critical Fix For: 0.95.0 On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13613218#comment-13613218 ] Elliott Clark commented on HBASE-8119: -- Looking at it right now. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Priority: Critical Fix For: 0.95.0 On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13613429#comment-13613429 ] stack commented on HBASE-8119: -- [~enis] Agree this critical. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Priority: Critical Fix For: 0.95.0 On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13609822#comment-13609822 ] Enis Soztutar commented on HBASE-8119: -- [~eclark] would you mind taking a look? Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Fix For: 0.95.0 On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13605827#comment-13605827 ] Enis Soztutar commented on HBASE-8119: -- bq. Per table load balancing runs the balancer once per table. The issue turned out to be not in the per-table load balancing, which was already defaulted to false. The issue is that for 500 regions, Load balancer takes 15 min, which makes it unusable. In it's current form, StochasticLoadBalancer can only work with clusters having ~20 nodes, and low hundreds of regions. bq. There's a lot of hashmap manipulation that should be optimized out if we wanted to worry about perf. If the balancer takes more than 15 min, there is a bug in HMaster.balance() that it breaks prematurely from assigning the region plans from the balancer. One more thing is that we do not do bulk assign to the regions generated by the load balancer plan. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Fix For: 0.95.0 On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (HBASE-8119) Optimize StochasticLoadBalancer
[ https://issues.apache.org/jira/browse/HBASE-8119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13605847#comment-13605847 ] Enis Soztutar commented on HBASE-8119: -- Quoting review at https://reviews.apache.org/r/9998/: Attaching a patch for improving the running time of StochasticLoadBalancer 200x times. TestStochasticLoadBalancer#testMidCluster() Current impl: //2013-03-15 17:28:25,495 DEBUG [main] balancer.StochasticLoadBalancer(256): Finished computing new laod balance plan. Computation took 172526ms to try 15000 different iterations. Found a solution that moves 600 regions; Going from a computed cost of 35.850001 to a new cost of 23.481578947368426 With patch: //2013-03-18 14:56:13,541 DEBUG [Thread-2] balancer.StochasticLoadBalancer(436): Finished computing new laod balance plan. Computation took 941ms to try 15000 different iterations. Found a solution that moves 600 regions; Going from a computed cost of 35.85 to a new cost of 23.48157894736842 The improvements come from: - Optimized array based data structures in Cluster class - Getting rid of hashmaps - Optimized region move and swap ops - Removing most of the computation to cluster initialization, and state change for the cluster, thus eliminating computing the same results over and over - Some profiling There should be further optimizations but this should be a good start. If we ran into more problems, we can investigate further. There are a lof of TODO's added in this patch. I'll create a jira for collecting some thoughts, but I wont have the time to work on those for now. There are (hopefully) minor semantic changes in the algo. I had to bump up loadMultiplier, and decrease moveCostMultiplier. See comments at TestStochasticLoadBalancer#testLargeCluster(). Please review carefully. As noted in testLargeCluster(), this does not work for large clusters 10 regions, 1000 nodes. This can be solved by smt like http://en.wikipedia.org/wiki/Simulated_annealing instead of random walk with eager selection. Optimize StochasticLoadBalancer --- Key: HBASE-8119 URL: https://issues.apache.org/jira/browse/HBASE-8119 Project: HBase Issue Type: Bug Components: Region Assignment Affects Versions: 0.95.0 Reporter: Enis Soztutar Fix For: 0.95.0 On a 5 node trunk cluster, I ran into a weird problem with StochasticLoadBalancer: server1 Thu Mar 14 03:42:50 UTC 20130.0 33 server2 Thu Mar 14 03:47:53 UTC 20130.0 34 server3 Thu Mar 14 03:46:53 UTC 2013465.0 42 server4 Thu Mar 14 03:47:53 UTC 201311455.0 282 server5 Thu Mar 14 03:47:53 UTC 20130.0 34 Total:5 11920 425 Notice that server4 has 282 regions, while the others have much less. Plus for one table with 260 regions has been super imbalanced: {code} Regions by Region Server Region Server Region Count http://server3:60030/ 10 http://server4:60030/ 250 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira