Guido Imperiale

Implementing this will have unpleasant consequences when the failure to get out of paused state is not due to memory leaks, but due to running out of disk space. e.g....

This ticket heavily interacts with: - AMM Rebalance (https://github.com/dask/distributed/issues/4906) - https://github.com/dask/distributed/issues/6002 - #6825 - #6826

Does this test include #6591? ### 1. I see that you ran on fjetter/distributed. I got a feeling that whenever I run on crusaderky/distributed I get a lot more random...

Closes #6864

> Ideally, we would only inform the workers that are fetching data from the departed worker. This is not that simple for pending AMM `acquire-replicas` requests, as the scheduler today...

See also #6421

I think that xarray should offer a "compatibility test toolkit" to any numpy-like, NEP18-compatible library that wants to integrate with it. Instead of having a module full of tests specifically...

Still relevant

I have the same need. I plan to use the LZF compressor which is standard in the HDF5 library. Could we have an authoritative direction on how the Python API...

@DennisHeimbigner ping