sjvanrossum commented on PR #36028: URL: https://github.com/apache/beam/pull/36028#issuecomment-3247171743
This change was motivated by the CPU overhead incurred by `MemoizingPerInstantiationSerializableSupplier#get()`, not the recent OoMs. :) Here's the 50th percentile of CPU time over a 10 minute window of a recent pipeline (500 partitions, 10 vCPUs) I ran: <img width="896" height="200" alt="image" src="https://github.com/user-attachments/assets/68a4039f-ff7a-4885-b027-6ac8beac8f32"; /> I'll note that this was a test pipeline, so this finding may not be representative of real workloads. -- 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]
