[
https://issues.apache.org/jira/browse/HAMA-990?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15292519#comment-15292519
]
Behroz Sikander commented on HAMA-990:
--------------------------------------
>> With this, we may able to derive insight from the results (this should be
>> our goal)
Ok. What kind of insights are you interested in ?
>>I think I heard that flink uses own serialization techniques and shows good
>>performance but unstable.
Ok
>> Just FYI, MRQL also can be used for K-Means and PageRank.
Yea we can use that. Good idea.
>> If you can write some scripts that make it possible to auto-produce
>> benchmark results on clouds such as Amazon or Google cloud, I can help.
I have never written a script like this before but I am interested in learning
it. The script would install HDFS/Hama/Spark/Flink and then execute the
commands for the job (K-Mean/PageRank etc) and in the end copy results back to
local directory ? Further, should it be a simple bash script or CHEF/Puppet
script ?
> GSoC'16: Apache Hama benchmark against Spark and Flink
> ------------------------------------------------------
>
> Key: HAMA-990
> URL: https://issues.apache.org/jira/browse/HAMA-990
> Project: Hama
> Issue Type: Documentation
> Reporter: Behroz Sikander
> Priority: Minor
>
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
