may I forward this report to spark list as well.
Thanks.
Wes Peng wrote:
Hello,
This weekend I made a test against a big dataset. spark, drill, mysql,
postgresql were involved.
This is the final report:
https://blog.cloudcache.net/handles-the-file-larger-than-memory/
The simple conclusion:
1. spark is the fastest for this scale of data and limited memory
2. drill is close to spark
3. postgresql has surprising behavior in query speed
4. mysql is really slow
If you have found any issue please let me know.
Thanks
Wes Peng wrote:
sure.I will take time to do it.
Sanel Zukan wrote:
Any chance you can try with Postgres >= 12, default configuration with
the same indexed columns as with MySQL?
---------------------------------------------------------------------
To unsubscribe e-mail: user-unsubscr...@spark.apache.org
