[ 
https://issues.apache.org/jira/browse/HDFS-16917?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Ravindra Dingankar updated HDFS-16917:
--------------------------------------
    Description: 
Currently we have the following metrics for datanode reads.
|BytesRead
BlocksRead
TotalReadTime|Total number of bytes read from DataNode
Total number of blocks read from DataNode
Total number of milliseconds spent on read operation|

We would like to add a new quantile metric calculating the transfer rate for 
datanode reads.
This will give us a distribution across a window of the read transfer rate for 
each datanode.

Quantiles for transfer rate per host will help in identifying issues like 
hotspotting of datasets as well as finding repetitive slow datanodes.

 

  was:
Currently we have the following metrics for datanode reads.
|BytesRead
BlocksRead
TotalReadTime|Total number of bytes read from DataNode
Total number of blocks read from DataNode
Total number of milliseconds spent on read operation|

We would like to add a new quantile metric calculating the transfer rate for 
datanode reads.
This will give us a distribution across a window of the read transfer rate for 
each datanode.

Percentiles for transfer rate will help in identifying issues like hotspotting 
of datasets as well as finding repetitive slow datanodes.

 


> Add transfer rate quantile metrics for DataNode reads
> -----------------------------------------------------
>
>                 Key: HDFS-16917
>                 URL: https://issues.apache.org/jira/browse/HDFS-16917
>             Project: Hadoop HDFS
>          Issue Type: Task
>          Components: datanode
>            Reporter: Ravindra Dingankar
>            Priority: Minor
>              Labels: pull-request-available
>
> Currently we have the following metrics for datanode reads.
> |BytesRead
> BlocksRead
> TotalReadTime|Total number of bytes read from DataNode
> Total number of blocks read from DataNode
> Total number of milliseconds spent on read operation|
> We would like to add a new quantile metric calculating the transfer rate for 
> datanode reads.
> This will give us a distribution across a window of the read transfer rate 
> for each datanode.
> Quantiles for transfer rate per host will help in identifying issues like 
> hotspotting of datasets as well as finding repetitive slow datanodes.
>  



--
This message was sent by Atlassian Jira
(v8.20.10#820010)

---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to