Florian Jetter
Florian Jetter
> Thoughts about removing paused_or_retiring? I know this would be a breaking change in some sense, but it's also kinda a breaking change to have more non-exclusive states. I think...
> Instead, one would need logic that includes paused_or_retiring or [paused and retiring] but not both... which isn't very straightforward in Prometheus (I'm still thinking about how to do this)....
> There seem to be a lot of test failures but at least skimming through, t _Most_ of the failures have been resolved on main. I rebased the PR to...
I suspect the way this is aggregated here https://github.com/dask/distributed/blob/b1597b67a2d8b88497dd281da2bd6380296f566b/distributed/system_monitor.py#L199-L203 is not totally correct or interpreted poorly. I suspect that if the interpreter stands still for a minute, this will report...
I merged main. Assuming CI is not horribly broken, we can merge
I could see this happening if the task (or anything in https://github.com/dask/distributed/blob/b03efeeda5f17c48d020f4820ff89a752beeaf89/distributed/utils.py#L401-L408) is raising a `BaseException`. I don't know what `_dask_resubmit_failed_task` is doing but if this is cancelling the task,...
The reason why the ordering is hard to reason about is not because they are defined async but because we're not awaiting them individually here https://github.com/dask/distributed/blob/4425516f86d7de9aed06053fc3e21a17fe20efc4/distributed/scheduler.py#L4390-L4399 and https://github.com/dask/distributed/blob/4425516f86d7de9aed06053fc3e21a17fe20efc4/distributed/scheduler.py#L5192-L5213 I don't...
I think I do not understand exactly what problem this is solving and why this API is better than writing to and reading from an ordinary parquet dataset. OTOH I...
There are a couple of problems here that are introduced by the very small instance type. While the file itself appears to be small, deserializing it requires quite a bit...
> What is going on with the spilling and the runaway unmanaged memory when setting an index? unmanaged memory is often caused by the function you are running, spilling, network...