ray: RayWorkerError: The worker died unexpectedly while executing this task.
Describe the problem
A Modin user has reported a RayWorkerError with running df.head(), which involves some ray.get calls.
Source code / logs
See https://github.com/modin-project/modin/issues/746
cc @masoodimran
About this issue
- Original URL
- State: closed
- Created 5 years ago
- Comments: 38 (13 by maintainers)
I have the same problem while reading csv. Just simple pd.read_csv()
Recently, I also faced a similar issue with an error “ray.exception.WorkerCrashedError. The worker died unexpectedly while executing this task.”.
But the issue arose only when I use many cores. For example, if I generate jobs for 20 cores to calculate, ray gave me the error. However, if I reduce the core counts (but the same task) down to 10, the error disappears.
Currently, I am okay with 10 cores so this issue is not that urgent, but I am wondering this is a known issue or not.
Thank you in advance!
Just checked it is typing 3.7.4
On Mon, 12 Aug 2019, 20:34 Simon Mo, notifications@github.com wrote:
I had the same problem. I uninstalled the
typingpackage after reading this issue https://github.com/ray-project/ray/issues/4929 and it worked for me.With the
typingpackage installed, when I ran the tests on ray using this commandpython -m pytest -v ray/tests/test_mini.pythey all failed.