[
https://issues.apache.org/jira/browse/HDFS-270?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12918747#action_12918747
]
Matt Foley commented on HDFS-270:
---------------------------------
Our datanodes take 5-15 minutes per volume to upgrade, and with four disks per
node, done serially, this is a 45 minute or so wait before the NN starts
getting registrations. In our environment the majority of restarts are for
upgrades, so this is important operationally.
I'll post a proposal in a few days to parallelize this, and possibly speed it
up.
> DFS Upgrade should process dfs.data.dirs in parallel
> ----------------------------------------------------
>
> Key: HDFS-270
> URL: https://issues.apache.org/jira/browse/HDFS-270
> Project: Hadoop HDFS
> Issue Type: Improvement
> Reporter: Stu Hood
> Assignee: Matt Foley
> Priority: Minor
>
> I just upgraded from 0.14.2 to 0.15.0, and things went very smoothly, if a
> little slowly.
> The main reason the upgrade took so long was the block upgrades on the
> datanodes. Each of our datanodes has 3 drives listed for the dfs.data.dir
> parameter. From looking at the logs, it is fairly clear that the upgrade
> procedure does not attempt to upgrade all listed dfs.data.dir's in parallel.
> I think even if all of your dfs.data.dir's are on the same physical device,
> there would still be an advantage to performing the upgrade process in
> parallel. The less downtime, the better: especially if it is potentially 20
> minutes versus 60 minutes.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
