New RunLLM response generated: >>>*# Question* Hi everyone~ I am new in Flyte and currently struggle on setting up Spark in sandbox (flytectl demo cluster) for local usage. I tried to edit config map with

kubectl edit cm flyte-sandbox-config

, and add some spark configuration inside it (based on the config for flyte-sandbox here). The configuration I used is attached below. Then, I use

kubectl rollout restart flyte-sandbox

to restart the deployment. When running the pyspark_pi example in flytesnacks, the workflow status stuck in queuing. Does anyone know why this happens and how I can solve it? Thanks a lot for any help!🙏 # Answer To resolve the issue of the workflow status being stuck in "queuing" when running the

pyspark_pi

example in Flytesnacks, ensure that the Spark configuration is correctly set up in the Flyte sandbox. According to the Flyte documentation, you need to ensure that the Spark operator is properly installed and configured. Additionally, verify that the necessary permissions are granted to the service account used by Flyte to create Spark resources. Would you like more detailed steps on how to verify and configure these settings? Sources: - https://github.com/flyteorg/flyte/pull/3248 - https://discuss.flyte.org/t/15983401/having-some-difficulty-using-the-spark-plugin-for-flyte-in-p/ Slack Link https://flyte.slack.com/archives/CP2HDHKE1/p1733153547.132949 👍 0 button 👎 0 button 💡 Hint: Mention @runllm in the thread for followups.