ahmedabu98 commented on PR #31392: URL: https://github.com/apache/beam/pull/31392#issuecomment-2174852500
Looks like populating the data did have an effect. Pipelines used a lot more workers but finished in roughly the same amount of time. Write ([2024-06-17_18_21_14-2727804973398206918](https://pantheon.corp.google.com/dataflow/jobs/us-central1/2024-06-17_18_21_14-2727804973398206918)) <img width="884" alt="image" src="https://github.com/apache/beam/assets/65791736/65ab4b6b-ca5f-45e8-8fa4-2dae11f9218b";> - Wrote 1 billion records - Autoscaled to 373 workers - Total elapsed time: ~59 min (Actual write finished in 14 min. Took a long time to clean up and stop worker pool) Read ([2024-06-17_19_20_46-7349681781857878664](https://pantheon.corp.google.com/dataflow/jobs/us-central1/2024-06-17_19_20_46-7349681781857878664)) <img width="899" alt="image" src="https://github.com/apache/beam/assets/65791736/eaaa7733-fddf-4ed2-9199-ccbbc5adcf1b";> - Read 1 billion records - Autoscaled to 204 workers - Total elapsed time: 13 min -- 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]
