seddonm1 commented on pull request #9523: URL: https://github.com/apache/arrow/pull/9523#issuecomment-786904688
> > It appears to me (and I have only just started reading the tokio documentation) that these tokio::spawn calls are not yielding to the scheduler as that would normally happen via the .await call. > > @seddonm1 it is my understanding (and it may be wrong) that calls to `await` offer an opportunity to yield to the scheduler but the tokio scheduler will attempt to use the current thread execute whatever you are awaiting on and if that can proceed tokio will execute it -- it makes no attempt to be fair, it is trying to maximize throughput > > Putting a call to `tokio::task_yield_now()` sticks the current task at the back of the scheduling queue (rather than really "yielding" in the normal cooperative multi-threading sense Yes, this fits with my understanding. I would like to try to create a test for this as I have only observed this whilst running from within another `tokio::spawn` task - which will probably impact projects like Ballista more than DataFusion. ---------------------------------------------------------------- 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: us...@infra.apache.org
