hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Andrew Wang (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-10999) Use more generic "low redundancy" blocks instead of "under replicated" blocks
Date Mon, 17 Oct 2016 22:11:58 GMT

    [ https://issues.apache.org/jira/browse/HDFS-10999?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15583660#comment-15583660
] 

Andrew Wang commented on HDFS-10999:
------------------------------------

bq. Are we exposing how many blocks are EC blocks and how many blocks are normally replicated
blocks?

I don't think so, and you're right that we should in some fashion. Sounds like we want these
counts both for the whole filesystem as well as recovery-related metrics.

As a first-cut, I think these counts can ignore the EC policy. I think most clusters will
only use a single EC policy since it heavily depends on the # of racks. We can expand this
to per-policy metrics if we find it necessary.

bq. Most of the advanced admins I know do it several times a year, either because the NN was
too stupid to fix it's own replication problems and/or because it was simply faster for us
to do it rather than wait for the normal block replication process.

I choose to interpret this as HDFS needing better knobs for emergency replication :)

This has been great info, I'll file some JIRAs to track these work items. Sounds like:

* I/O based pending replication metrics / throttles
* EC block counts
* dynamically configurable replication throttles

> Use more generic "low redundancy" blocks instead of "under replicated" blocks
> -----------------------------------------------------------------------------
>
>                 Key: HDFS-10999
>                 URL: https://issues.apache.org/jira/browse/HDFS-10999
>             Project: Hadoop HDFS
>          Issue Type: Sub-task
>          Components: erasure-coding
>    Affects Versions: 3.0.0-alpha1
>            Reporter: Wei-Chiu Chuang
>            Assignee: Yuanbo Liu
>              Labels: supportability
>
> Per HDFS-9857, it seems in the Hadoop 3 world, people prefer the more generic term "low
redundancy" to the old-fashioned "under replicated". But this term is still being used in
messages in several places, such as web ui, dfsadmin and fsck. We should probably change them
to avoid confusion.
> File this jira to discuss it.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-help@hadoop.apache.org


Mime
View raw message