tvalentyn opened a new issue, #39244: URL: https://github.com/apache/beam/issues/39244
### What would you like to happen? Beam has a codepath to append heap information into sdk status reports: [worker_status.py](https://github.com/apache/beam/blob/227bcded5aa2007cfb496378c876a75766f73b0d/sdks/python/apache_beam/runners/worker/worker_status.py#L111), enabled by the [--experiments=enable_heap_dump](https://github.com/apache/beam/blob/27d699eb7215ca4ebda8d61984c17507e2937e87/sdks/python/apache_beam/runners/worker/sdk_worker_main.py#L170) option see [description](https://docs.google.com/document/d/12IBAxfGgLbAWxyB5hEHDIwm821FiTA7csd9PhBR3icI/edit?tab=t.0#heading=h.li0h8ahbwaj) We can expand on the info we are currently collecting to allow more introspection into memory allocated by the process so that we can reason about whether memory is growing on in the native heap vs Python allocations; we could also try to print glibc stats to provide insights into possible memory fragmentation, see: https://bloomberg.github.io/memray/memory.html#memory-can-be-fragmented for ideas. ### Issue Priority Priority: 2 (default / most feature requests should be filed as P2) ### Issue Components - [ ] Component: Python SDK - [ ] Component: Java SDK - [ ] Component: Go SDK - [ ] Component: Typescript SDK - [ ] Component: IO connector - [ ] Component: Beam YAML - [ ] Component: Beam examples - [ ] Component: Beam playground - [ ] Component: Beam katas - [ ] Component: Website - [ ] Component: Infrastructure - [ ] Component: Spark Runner - [ ] Component: Flink Runner - [ ] Component: Prism Runner - [ ] Component: Twister2 Runner - [ ] Component: Hazelcast Jet Runner - [ ] Component: Google Cloud Dataflow Runner -- 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]
