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-5320) Add datanode caching metrics
Date Wed, 23 Oct 2013 02:15:42 GMT

    [ https://issues.apache.org/jira/browse/HDFS-5320?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13802527#comment-13802527
] 

Andrew Wang commented on HDFS-5320:
-----------------------------------

Maybe I missed something here; {{numBlocksFailedToCache}} is in {{FsDatasetCache}} and is
incremented if it's either rejected immediately or fails in the worker. A code snippet would
help if I missed a case.

I agree that some kind of rolling metric would be nice here, but we don't have that right
now in Hadoop besides {{MutableQuantiles}}. It'd be easy enough to do though, but maybe as
a follow-on (say, post trunk merge).

> Add datanode caching metrics
> ----------------------------
>
>                 Key: HDFS-5320
>                 URL: https://issues.apache.org/jira/browse/HDFS-5320
>             Project: Hadoop HDFS
>          Issue Type: Sub-task
>          Components: datanode
>    Affects Versions: HDFS-4949
>            Reporter: Andrew Wang
>            Assignee: Andrew Wang
>            Priority: Minor
>         Attachments: hdfs-5320-1.patch, hdfs-5320-2.patch
>
>
> It'd be good to hook up datanode metrics for # (blocks/bytes) (cached/uncached/failed
to cache) over different time windows (eternity/1hr/10min/1min).



--
This message was sent by Atlassian JIRA
(v6.1#6144)

Mime
View raw message