[jira] [Commented] (HDFS-2171) Changes to balancer bandwidth should not require datanode restart.

2011-07-27 Thread Eric Payne (JIRA)
[ https://issues.apache.org/jira/browse/HDFS-2171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13071837#comment-13071837 ] Eric Payne commented on HDFS-2171: -- Hey Todd, Is it ever appropriate to merge a patch to

[jira] [Commented] (HDFS-2171) Changes to balancer bandwidth should not require datanode restart.

2011-07-27 Thread Todd Lipcon (JIRA)
[ https://issues.apache.org/jira/browse/HDFS-2171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13071858#comment-13071858 ] Todd Lipcon commented on HDFS-2171: --- In my opinion, the work should always be done on

[jira] [Commented] (HDFS-2171) Changes to balancer bandwidth should not require datanode restart.

2011-07-27 Thread Suresh Srinivas (JIRA)
[ https://issues.apache.org/jira/browse/HDFS-2171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13072067#comment-13072067 ] Suresh Srinivas commented on HDFS-2171: --- there are some seemingly unrelated test

[jira] [Commented] (HDFS-2171) Changes to balancer bandwidth should not require datanode restart.

2011-07-26 Thread Hadoop QA (JIRA)
[ https://issues.apache.org/jira/browse/HDFS-2171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13071217#comment-13071217 ] Hadoop QA commented on HDFS-2171: - -1 overall. Here are the results of testing the latest

[jira] [Commented] (HDFS-2171) Changes to balancer bandwidth should not require datanode restart.

2011-07-26 Thread Eric Payne (JIRA)
[ https://issues.apache.org/jira/browse/HDFS-2171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13071223#comment-13071223 ] Eric Payne commented on HDFS-2171: -- Hadoop QA PreCommitHDFS-Build is trying to apply patch

[jira] [Commented] (HDFS-2171) Changes to balancer bandwidth should not require datanode restart.

2011-07-26 Thread Eric Payne (JIRA)
[ https://issues.apache.org/jira/browse/HDFS-2171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13071242#comment-13071242 ] Eric Payne commented on HDFS-2171: -- Unit Tests: I added

[jira] [Commented] (HDFS-2171) Changes to balancer bandwidth should not require datanode restart.

2011-07-26 Thread Todd Lipcon (JIRA)
[ https://issues.apache.org/jira/browse/HDFS-2171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13071247#comment-13071247 ] Todd Lipcon commented on HDFS-2171: --- This needs to be fixed for trunk before it can be

[jira] [Commented] (HDFS-2171) Changes to balancer bandwidth should not require datanode restart.

2011-07-26 Thread Eric Payne (JIRA)
[ https://issues.apache.org/jira/browse/HDFS-2171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13071483#comment-13071483 ] Eric Payne commented on HDFS-2171: -- OK. The changes were slightly different on trunk, but

[jira] [Commented] (HDFS-2171) Changes to balancer bandwidth should not require datanode restart.

2011-07-23 Thread Eric Payne (JIRA)
[ https://issues.apache.org/jira/browse/HDFS-2171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13070042#comment-13070042 ] Eric Payne commented on HDFS-2171: -- In my tests, the dfsadmin solution (option 3) seems to

[jira] [Commented] (HDFS-2171) Changes to balancer bandwidth should not require datanode restart.

2011-07-21 Thread Eric Payne (JIRA)
[ https://issues.apache.org/jira/browse/HDFS-2171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13068990#comment-13068990 ] Eric Payne commented on HDFS-2171: -- There are some concerns surrounding the solution

[jira] [Commented] (HDFS-2171) Changes to balancer bandwidth should not require datanode restart.

2011-07-21 Thread Eric Payne (JIRA)
[ https://issues.apache.org/jira/browse/HDFS-2171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13068999#comment-13068999 ] Eric Payne commented on HDFS-2171: -- +*Proposed Solutions*+: 4. Add a new opcode that is

[jira] [Commented] (HDFS-2171) Changes to balancer bandwidth should not require datanode restart.

2011-07-20 Thread Eric Payne (JIRA)
[ https://issues.apache.org/jira/browse/HDFS-2171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13068437#comment-13068437 ] Eric Payne commented on HDFS-2171: -- Thanks Aaron and Todd. If the solutions between

[jira] [Commented] (HDFS-2171) Changes to balancer bandwidth should not require datanode restart.

2011-07-20 Thread Aaron T. Myers (JIRA)
[ https://issues.apache.org/jira/browse/HDFS-2171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13068578#comment-13068578 ] Aaron T. Myers commented on HDFS-2171: -- bq. If the solutions between 0.20.205.0 and

[jira] [Commented] (HDFS-2171) Changes to balancer bandwidth should not require datanode restart.

2011-07-19 Thread Aaron T. Myers (JIRA)
[ https://issues.apache.org/jira/browse/HDFS-2171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13068028#comment-13068028 ] Aaron T. Myers commented on HDFS-2171: -- Just thinking out loud - another option would

[jira] [Commented] (HDFS-2171) Changes to balancer bandwidth should not require datanode restart.

2011-07-19 Thread Todd Lipcon (JIRA)
[ https://issues.apache.org/jira/browse/HDFS-2171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13068032#comment-13068032 ] Todd Lipcon commented on HDFS-2171: --- On trunk I think we should do the protocol change -