jerqi commented on issue #186:
URL: 
https://github.com/apache/incubator-uniffle/issues/186#issuecomment-1225306182

   > Thank you for your detailed explanation. I have no doubt about the first 
two points, but the third point is that I want to know what you mean by the 
retry of HDFS cluster. And the fourth point is that we really have no way to 
know the amount of shuffle data, so the current idea is that if there are no 
files at the beginning, we can only compare the remaining capacity of the 
namespace. If there are already shuffle files, Then we can compare the ratio of 
the size of all the shuffle files and the remaining capacity of the namespace 
under different HDFS paths.
   
   Third point, sorry... I should give more explanation. If shuffle server fail 
to  write data to HDFS because HDFS high load, shuffle will retry. If there are 
many retries about HDFS, it means that HDFS have bad status, we should avoid 
using it.
   Fourth, your solution is  not a perfect solution, it must depend data in the 
production environment  to prove the  effectiveness. 


-- 
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]

Reply via email to