devinjdangelo commented on issue #9493:
URL: 
https://github.com/apache/arrow-datafusion/issues/9493#issuecomment-1998593428

   Thank you @tustvold and @alamb for the additional context/comments on #9605. 
I understand now more what you are trying to facilitate on the influxdb side. I 
agree it will take some reworking to have parallel serialization happening on 
one runtime/pool while IO is happening on another runtime. I have some nascent 
ideas, but I would have to think through it more. I am interested to hear what 
you all come up with as well. 
   
   One easy but perhaps unsatisfying idea would be to run the parallel 
serialization entirely on the IO runtime, but just minor refactor to use spawn 
blocking as I did in #9605. I do think we can come up with better than this 
:smile: 
   
   


-- 
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