[
https://issues.apache.org/jira/browse/HAMA-990?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Behroz Sikander updated HAMA-990:
---------------------------------
Attachment: ver1.1_benchmark_script.sh
In the attachment you can find the updated version of script and it can now
work with Spark and Flink clusters.
The script requires the following
1- MRQL_INSTALL_FOLDER -> The path where MRQL should be downloaded
2- HDFS_ADDRESS -> HDFS URL that clients use to communicate
3- SPARK_MASTER -> Spark master URL or if Yarn is used then yarn-client can be
passed
4- MRQL_NODES -> Total workers on which the PageRank algorithm needs to be
executed.
It would be great if I can get a feedback on the script, so that I can improve
it. Further, currently, the output is shown on console directly. How do you
envision the final output of the 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
> Attachments: Benchmark_script.sh, ver1.1_benchmark_script.sh
>
>
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
