[
https://issues.apache.org/jira/browse/HDFS-6982?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14131039#comment-14131039
]
Maysam Yabandeh commented on HDFS-6982:
---------------------------------------
Thanks [~andrew.wang]. Yeah the main reason for starting nntop as a separate
process was to be able to freely ship the tool without tying it to the entire
hadoop release. We also wanted the tool to be available even in the worst case
scenario that nn is not responding. However by plotting the reported metrics,
in my opinion that is not a concern any more since even when nn is not
responding we still have the traffic of the last minute(s) that lead nn to such
state.
> nntop: top-like tool for name node users
> -----------------------------------------
>
> Key: HDFS-6982
> URL: https://issues.apache.org/jira/browse/HDFS-6982
> Project: Hadoop HDFS
> Issue Type: New Feature
> Reporter: Maysam Yabandeh
> Assignee: Maysam Yabandeh
> Attachments: HDFS-6982.patch, HDFS-6982.v2.patch, nntop-design-v1.pdf
>
>
> In this jira we motivate the need for nntop, a tool that, similarly to what
> top does in Linux, gives the list of top users of the HDFS name node and
> gives insight about which users are sending majority of each traffic type to
> the name node. This information turns out to be the most critical when the
> name node is under pressure and the HDFS admin needs to know which user is
> hammering the name node and with what kind of requests. Here we present the
> design of nntop which has been in production at Twitter in the past 10
> months. nntop proved to have low cpu overhead (< 2% in a cluster of 4K
> nodes), low memory footprint (less than a few MB), and quite efficient for
> the write path (only two hash lookup for updating a metric).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
