[
https://issues.apache.org/jira/browse/HDFS-3570?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14644720#comment-14644720
]
Allen Wittenauer commented on HDFS-3570:
----------------------------------------
bq. Setting the parameter for non-dfs used space is an ideal way to avoid the
problem
Not really. The "negative math" model just flat out doesn't work in practice.
It makes assumptions that whatever else is on the file system has a way to
contain how much space is used.... which is pretty much impossible. It's one
of the reasons why I've been advocated a dedicated partition per disk for HDFS
for years now. Those that do seem to have a lot less problems with HDFS at the
cost of some initial setup pain.
> Balancer shouldn't rely on "DFS Space Used %" as that ignores non-DFS used
> space
> --------------------------------------------------------------------------------
>
> Key: HDFS-3570
> URL: https://issues.apache.org/jira/browse/HDFS-3570
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: balancer & mover
> Affects Versions: 2.0.0-alpha
> Reporter: Harsh J
> Assignee: Akira AJISAKA
> Priority: Minor
> Attachments: HDFS-3570.003.patch, HDFS-3570.2.patch,
> HDFS-3570.aash.1.patch
>
>
> Report from a user here:
> https://groups.google.com/a/cloudera.org/d/msg/cdh-user/pIhNyDVxdVY/b7ENZmEvBjIJ,
> post archived at http://pastebin.com/eVFkk0A0
> This user had a specific DN that had a large non-DFS usage among
> dfs.data.dirs, and very little DFS usage (which is computed against total
> possible capacity).
> Balancer apparently only looks at the usage, and ignores to consider that
> non-DFS usage may also be high on a DN/cluster. Hence, it thinks that if a
> DFS Usage report from DN is 8% only, its got a lot of free space to write
> more blocks, when that isn't true as shown by the case of this user. It went
> on scheduling writes to the DN to balance it out, but the DN simply can't
> accept any more blocks as a result of its disks' state.
> I think it would be better if we _computed_ the actual utilization based on
> {{(100-(actual remaining space))/(capacity)}}, as opposed to the current
> {{(dfs used)/(capacity)}}. Thoughts?
> This isn't very critical, however, cause it is very rare to see DN space
> being used for non DN data, but it does expose a valid bug.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
