[ 
https://issues.apache.org/jira/browse/HDFS-12861?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16432623#comment-16432623
 ] 

Íñigo Goiri commented on HDFS-12861:
------------------------------------

Thanks [~mf_borge].
For the patches, you should use the naming as HDFS-12861.000.patch and don't 
remove the old ones just to keep track of the progress.

Other minor comments before I go deeper:
* Do you mind fixing the checkstyle issues in  [^HDFS-12861-10-april-18.patch]?
* Do we need to make {{initThreadsNumForHedgedReads()}} non-static?
* startReadTime and endReadTime could be initialized where they get used.
* In DataStreamer we coudl just import 
org.apache.hadoop.hdfs.client.HdfsClientConfigKeys.
* Can we leave packetProcessingTimes in nanos as the other metric for writes 
already uses nanos?
* Can we add some unit tests?

> Track speed in DFSClient
> ------------------------
>
>                 Key: HDFS-12861
>                 URL: https://issues.apache.org/jira/browse/HDFS-12861
>             Project: Hadoop HDFS
>          Issue Type: Improvement
>            Reporter: Íñigo Goiri
>            Assignee: María Fernanda Borge
>            Priority: Major
>         Attachments: HDFS-12861-10-april-18.patch
>
>
> Sometimes we get slow jobs because of the access to HDFS. However, is hard to 
> tell what is the actual speed. We propose to add a log line with something 
> like:
> {code}
> 2017-11-19 09:55:26,309 INFO [main] hdfs.DFSClient: blk_1107222019_38144502 
> READ 129500B in 7ms 17.6MB/s
> 2017-11-27 19:01:04,141 INFO [DataStreamer for file 
> /hdfs-federation/stats/2017/11/27/1511838000000.json] hdfs.DFSClient: 
> blk_1135792057_86833357 WRITE 131072B in 10ms 12.5MB/s
> 2017-11-27 19:01:14,219 INFO [DataStreamer for file 
> /hdfs-federation/stats/2017/11/27/1511838000000.json] hdfs.DFSClient: 
> blk_1135792069_86833369 WRITE 131072B in 12ms 10.4MB/s
> 2017-11-27 19:01:24,282 INFO [DataStreamer for file 
> /hdfs-federation/stats/2017/11/27/1511838000000.json] hdfs.DFSClient: 
> blk_1135792081_86833381 WRITE 131072B in 11ms 11.4MB/s
> 2017-11-27 19:01:34,330 INFO [DataStreamer for file 
> /hdfs-federation/stats/2017/11/27/1511838000000.json] hdfs.DFSClient: 
> blk_1135792093_86833393 WRITE 131072B in 11ms 11.4MB/s
> 2017-11-27 19:01:44,408 INFO [DataStreamer for file 
> /hdfs-federation/stats/2017/11/27/1511838000000.json] hdfs.DFSClient: 
> blk_1135792105_86833405 WRITE 131072B in 11ms 11.4MB/s
> {code}



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

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

Reply via email to