hou-rong opened a new pull request, #12186:
URL: https://github.com/apache/doris/pull/12186

   …rformance improvement
   
   # Proposed changes
   
   Issue Number: close #12185 
   
   ## Problem summary
   
   ### 变更位置
   
   - 删除如图所示的 aggregateConcurrency
   - reduceByKey 删除指定的分区数,使用 Stage 1 的分区数来进行计算
   
   
![image](https://user-images.githubusercontent.com/8758438/187402399-e4296f4f-8140-4642-9bbf-a8bc434737f3.png)
   
   ### 性能比对
   
   #### 【修改前】reduceByKey 中传入写死的 200 限制了分区数
   
   - Stage 2 处理数据时间 1 小时 30 分
   
   ![spark 
执行过程性能瓶颈描述](https://user-images.githubusercontent.com/8758438/187393221-b0eefcb9-3913-49c9-a5c0-d45e9fbbd4bc.png)
   
   
![image](https://user-images.githubusercontent.com/8758438/187398925-6111b419-54e2-45f8-9ebc-899d5c669177.png)
   
   ####【修改后】reduceByKey 过程使用前置节点的分区数
   
   - Stage 2 处理数据时间 1.8 分
   
   
![优化后效果截图](https://user-images.githubusercontent.com/8758438/187396454-461dc61e-1490-4ddc-b5f9-d4fbd0129cac.png)
   
   
![image](https://user-images.githubusercontent.com/8758438/187399488-157cbca7-88cd-4d28-97e6-7142c8229d68.png)
   
   
   ## Checklist(Required)
   
   1. Does it affect the original behavior: 
       - [ ] Yes
       - [x] No
       - [ ] I don't know
   2. Has unit tests been added:
       - [ ] Yes
       - [ ] No
       - [x] No Need
   3. Has document been added or modified:
       - [ ] Yes
       - [ ] No
       - [x] No Need
   4. Does it need to update dependencies:
       - [ ] Yes
       - [x] No
   5. Are there any changes that cannot be rolled back:
       - [ ] Yes (If Yes, please explain WHY)
       - [x] No
   
   ## Further comments
   
   If this is a relatively large or complex change, kick off the discussion at 
[[email protected]](mailto:[email protected]) by explaining why you 
chose the solution you did and what alternatives you considered, etc...
   
   


-- 
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.

To unsubscribe, e-mail: [email protected]

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


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to