如果我继续修改n_workers
和threads_per_client
,我想看看性能是否有任何改善。
import dask.dataframe as dd
from dask.distributed import Client, LocalCluster
cluster = LocalCluster(n_workers=8, threads_per_worker=5)
client = Client(cluster)
...
cluster = LocalCluster(n_workers=5, threads_per_worker=8)
client = Client(cluster)
...
我尝试使用client.restart()
和client.shutdown()
,然后在簇变量中导入了新的组合,但是没有用。
https://github.com/dask/distributed/issues/3605
我们在Github中讨论了此用法问题,以上链接提供了详细信息