You are viewing a plain text version of this content. The canonical link for it is here.

Posted to hdfs-dev@hadoop.apache.org by "Todd Lipcon (Created) (JIRA)" <ji...@apache.org> on 2012/02/23 00:45:48 UTC

[jira] [Created] (HDFS-2989) HA: Optimize quota tracking for HA

HA: Optimize quota tracking for HA
----------------------------------

                 Key: HDFS-2989
                 URL: https://issues.apache.org/jira/browse/HDFS-2989
             Project: Hadoop HDFS
          Issue Type: Sub-task
          Components: ha, name-node
    Affects Versions: HA branch (HDFS-1623)
            Reporter: Todd Lipcon
            Priority: Minor


Currently after each segment we read in on the standby, we re-calculate all of the quota/usage information throughout the directory tree. This is inefficient. There are two potential optimizations: (a) we could maintain the quotas incrementally as edits are read, or (b) we could defer all quota computation until the node transitions to active mode. (b) is probably less bug-prone.

This is not a crucial optimization since in the worst case it might just delay failover by a few extra seconds (the time to traverse the in-memory FSDirectory)

--
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