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/1854#issuecomment-364498649,https://api.github.com/repos/pydata/xarray/issues/1854,364498649,MDEyOklzc3VlQ29tbWVudDM2NDQ5ODY0OQ==,2443309,2018-02-09T17:18:53Z,2018-02-09T17:18:53Z,MEMBER,"@rabernat - good points. @jamesstidard - perhaps you can a single files ncdump using the `ncdump -h -s filename.nc` syntax. That should tell us how the file is chunked on disk.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",,291332965 https://github.com/pydata/xarray/issues/1854#issuecomment-364491330,https://api.github.com/repos/pydata/xarray/issues/1854,364491330,MDEyOklzc3VlQ29tbWVudDM2NDQ5MTMzMA==,2443309,2018-02-09T16:53:57Z,2018-02-09T16:53:57Z,MEMBER,"@jamesstidard - let's see how the distributed scheduler plays: ```Python from distributed import Client client = Client() ds = xr.open_mfdataset('path/to/ncs/*.nc', chunks={'latitude': 50, 'longitude': 50}) recs = ds.sel(latitude=10, longitude=10).to_dataframe().to_records() ``` Also, it would be worth updating distributed before you use its scheduler.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",,291332965 https://github.com/pydata/xarray/issues/1854#issuecomment-364478761,https://api.github.com/repos/pydata/xarray/issues/1854,364478761,MDEyOklzc3VlQ29tbWVudDM2NDQ3ODc2MQ==,2443309,2018-02-09T16:12:22Z,2018-02-09T16:12:22Z,MEMBER,"@jamesstidard - it would be good to know a few more details here: - what dask scheduler you're using (you might also try with the distributed scheduler) - what versions of dask/distributed/etc you're using - how using a smaller chunk size in space (latitude and longitude) impacts performance","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",,291332965