spark + carbondata vs. spark + parquet performance test under benchmark tpc-ds

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

spark + carbondata vs. spark + parquet performance test under benchmark tpc-ds

李寅威
Hi all,


  I've made a simple performance test under benchmark tpc-ds using spark 2.1.0+carbondata 1.0.0 and spark 2.1.0+parquet, and I've make a note of the whole process.


  Considering the massive words and codes and tables & for the convenience of the updating of the note, I put the details on my YoudaoNote( not ad, not ad, not ad. Important things should be repeated 3 times~~),




the address is:


  http://note.youdao.com/noteshare?id=d574c28f15c09dbba2091cccebb75805&sub=89F8B96BC0C64F859B40F794898CAC5A
Reply | Threaded
Open this post in threaded view
|

RE: spark + carbondata vs. spark + parquet performance test under benchmark tpc-ds

Jihong Ma
Thank you for sharing with all of us!

To make it easily accessible by people from different region around the globe, please upload to a google doc.

Thanks!

Jihong

-----Original Message-----
From: Yinwei Li [mailto:[hidden email]]
Sent: Wednesday, March 01, 2017 11:46 PM
To: dev
Subject: spark + carbondata vs. spark + parquet performance test under benchmark tpc-ds

Hi all,


  I've made a simple performance test under benchmark tpc-ds using spark 2.1.0+carbondata 1.0.0 and spark 2.1.0+parquet, and I've make a note of the whole process.


  Considering the massive words and codes and tables & for the convenience of the updating of the note, I put the details on my YoudaoNote( not ad, not ad, not ad. Important things should be repeated 3 times~~),




the address is:


  http://note.youdao.com/noteshare?id=d574c28f15c09dbba2091cccebb75805&sub=89F8B96BC0C64F859B40F794898CAC5A