zzcclp commented on pull request #1495:
URL: https://github.com/apache/kylin/pull/1495#issuecomment-738628576


   ## The Results of Testing Manually
   
   ### Test Env
   
   - Hadoop 2.7.0 on docker.
   - Commit : 
[3b3786c5c](https://github.com/apache/kylin/commit/3b3786c5c9602838cd4abd0a6d40574550ec8622)
   - Sparder Env : 
      spark.executor.cores=1
      spark.executor.instances=4
      spark.executor.memory=2G
      spark.executor.memoryOverhead=1G
      spark.sql.shuffle.partitions=4
   
   
   ### Before this patch
   The shuffle partition number of all querys is 4, which equals to the total 
cores number.
   
![image](https://user-images.githubusercontent.com/9430290/101136306-19016880-3648-11eb-8ae0-2e02d42a41ac.png)
   
   
![image](https://user-images.githubusercontent.com/9430290/101136373-32a2b000-3648-11eb-83dd-83b52e2d9980.png)
   
   
![image](https://user-images.githubusercontent.com/9430290/101136443-4e0dbb00-3648-11eb-8d31-ac721797ee94.png)
   
   
![image](https://user-images.githubusercontent.com/9430290/101136476-5a921380-3648-11eb-90f7-ec20faeca57b.png)
   
   
   ### After this patch
   The shuffle partition number of each query is calculated according to the 
scanned bytes of each query:
   
![image](https://user-images.githubusercontent.com/9430290/101136174-e3f51600-3647-11eb-99c9-290831bb30af.png)
   
   
![image](https://user-images.githubusercontent.com/9430290/101136210-f40cf580-3647-11eb-8eec-0b7bdef93c30.png)
   
   
![image](https://user-images.githubusercontent.com/9430290/101136227-fa02d680-3647-11eb-9001-128c0e3bd490.png)
   
   
![image](https://user-images.githubusercontent.com/9430290/101136249-05ee9880-3648-11eb-9267-c1cb44319697.png)
   
   


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
[email protected]


Reply via email to