[
https://issues.apache.org/jira/browse/HDFS-2148?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Eli Collins updated HDFS-2148:
------------------------------
Target Version/s: 0.23.1
Fix Version/s: (was: 0.24.0)
Looks like there are 4 issues remaining:
1. NNThroughputBenchmark doesn't support federation
2. There's a scalability issues with BlockPoolSlice ("a thread per DU is
needed")
3. FSDataSet#checkDirs is not correctly synhronized
4. NameNode#getAddress doesn't do the right thing?
Seems like 3 should be fixed in 23.x. Are 2 and 3 issues that need to be
addressed as well?
> Address all the federation TODOs
> --------------------------------
>
> Key: HDFS-2148
> URL: https://issues.apache.org/jira/browse/HDFS-2148
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Components: name-node
> Reporter: Eli Collins
> Assignee: Suresh Srinivas
>
> The federation merge introduced a bunch of todos marked "TODO:FEDERATION" and
> "TODO". We should have jiras for these and address the issues.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
