html_url,issue_url,id,node_id,user,created_at,updated_at,author_association,body,reactions,performed_via_github_app,issue https://github.com/pydata/xarray/issues/1189#issuecomment-269573421,https://api.github.com/repos/pydata/xarray/issues/1189,269573421,MDEyOklzc3VlQ29tbWVudDI2OTU3MzQyMQ==,306380,2016-12-29T02:36:08Z,2016-12-29T02:36:08Z,MEMBER,"Dask.distributed now creates a forkserver at startup. This seems to be working well so far. It nicely balances having a well defined environment and fast startup time. How much inter-worker data transfer would you expect? It might be worth running through a few classic algorithms with it instead of the threaded scheduler and looking at performance changes. The diagnostic pages would be a nice bonus here and might help to highlight some performance issues. If anyone is interested in this the thing to do is $ conda install -c conda-forge dask distributed >>> from dask.distributed import Client >>> c = Client() # sets global scheduler by default And then operate as normal.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",,197939448 https://github.com/pydata/xarray/issues/1189#issuecomment-269572088,https://api.github.com/repos/pydata/xarray/issues/1189,269572088,MDEyOklzc3VlQ29tbWVudDI2OTU3MjA4OA==,306380,2016-12-29T02:17:40Z,2016-12-29T02:17:40Z,MEMBER,"Can you remind me the motivation to use a spawning multiprocessing pool instead of a fork or forkserver solution? For mixed multi-threading/multi-processing would a local ""distributed"" scheduler suffice? This would be several single-threaded processes on a single machine. The scheduler would be aware of data locality and avoid inter-node communication when possible.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",,197939448