Dask 简单聚合期间工作进程崩溃

我试图在一个4.5亿行的数据集中聚合各种列。当我使用Dask的内置聚合时，比如“min”、“max”、“std”、“mean”会在这个过程中不断地使一个工作人员崩溃

我正在使用的文件可以在这里找到：查找test_set.csv

我有一个google kubernetes集群，它由3台8核机器组成，总内存为22GB

因为这些只是内置的聚合函数，所以我没有尝试过太多其他功能

它也没有使用太多的RAM，它的总容量保持在6GB左右，而且我没有看到任何表示内存不足的错误

以下是我的基本代码和被驱逐工人的错误日志：

from dask.distributed import Client, progress
client = Client('google kubernetes cluster address')

test_df = dd.read_csv('gs://filepath/test_set.csv', blocksize=10000000)

def process_flux(df):
flux_ratio_sq = df.flux / df.flux_err
flux_by_flux_ratio_sq = (df.flux * flux_ratio_sq)
df_flux = dd.concat([df, flux_ratio_sq, flux_by_flux_ratio_sq], axis=1)
df_flux.columns = ['object_id', 'mjd', 'passband', 'flux', 'flux_err', 'detected', 'flux_ratio_sq', 'flux_by_flux_ratio_sq']
return df_flux

aggs = {
'flux': ['min', 'max', 'mean', 'std'],

'detected': ['mean'],
'flux_ratio_sq': ['sum'],
'flux_by_flux_ratio_sq': ['sum'],
'mjd' : ['max', 'min'],
}

def featurize(df):

start_df = process_flux(df)
agg_df = start_df.groupby(['object_id']).agg(aggs)
return agg_df

overall_start = timer()
final_df = featurize(test_df).compute()
overall_end = timer()

错误日志：

 distributed.core - INFO - Event loop was unresponsive in Worker for 74.42s.  This is often caused by long-running GIL-holding functions or moving large chunks of data. This can cause timeouts and instability.
 distributed.core - INFO - Event loop was unresponsive in Worker for 3.30s.  This is often caused by long-running GIL-holding functions or moving large chunks of data. This can cause timeouts and instability.
 distributed.core - INFO - Event loop was unresponsive in Worker for 3.75s.  This is often caused by long-running GIL-holding functions or moving large chunks of data. This can cause timeouts and instability.

出现了许多这样的情况，然后：

 distributed.core - INFO - Event loop was unresponsive in Worker for 65.16s.  This is often caused by long-running GIL-holding functions or moving large chunks of data. This can cause timeouts and instability.
 distributed.worker - ERROR - Worker stream died during communication: tcp://hidden address
 Traceback (most recent call last):
 File "/opt/conda/lib/python3.6/site-packages/distributed/comm/tcp.py", line 180, in read
n_frames = yield stream.read_bytes(8)
 File "/opt/conda/lib/python3.6/site-packages/tornado/iostream.py", line 441, in read_bytes
self._try_inline_read()
 File "/opt/conda/lib/python3.6/site-packages/tornado/iostream.py", line 911, in _try_inline_read
self._check_closed()
 File "/opt/conda/lib/python3.6/site-packages/tornado/iostream.py", line 1112, in _check_closed
raise StreamClosedError(real_error=self.error)
tornado.iostream.StreamClosedError: Stream is closed

response = yield comm.read(deserializers=deserializers)
File "/opt/conda/lib/python3.6/site-packages/tornado/gen.py", line 1133, in run
value = future.result()
File "/opt/conda/lib/python3.6/site-packages/tornado/gen.py", line 326, in wrapper
yielded = next(result)
File "/opt/conda/lib/python3.6/site-packages/distributed/comm/tcp.py", line 201, in read
convert_stream_closed_error(self, e)
File "/opt/conda/lib/python3.6/site-packages/distributed/comm/tcp.py", line 127, in     convert_stream_closed_error
raise CommClosedError("in %s: %s: %s" % (obj, exc.__class__.__name__, exc))
distributed.comm.core.CommClosedError: in <closed TCP>: TimeoutError: [Errno 110] Connection timed out

distributed.core-INFO-Event循环在Worker中的响应时间为65.16秒。这通常是由于长期运行GIL保持函数或移动大块数据造成的。这可能导致超时和不稳定。
distributed.worker-错误-工作流在通信过程中死亡：tcp://hidden 地址
回溯（最近一次呼叫最后一次）：
文件“/opt/conda/lib/python3.6/site packages/distributed/comm/tcp.py”，第180行，已读
n_frames=产生流。读取字节（8）
文件“/opt/conda/lib/python3.6/site packages/tornado/iostream.py”，第441行，以读取字节为单位
self.\u try\u inline\u read（）
文件“/opt/conda/lib/python3.6/site-packages/tornado/iostream.py”，第911行，输入
自我检查关闭（）
文件“/opt/conda/lib/python3.6/site packages/tornado/iostream.py”，第1112行，在检查中关闭
raise StreamClosedError（实际错误=self.error）
tornado.iostream.StreamClosedError:流已关闭
响应=产生comm.read（反序列化程序=反序列化程序）
文件“/opt/conda/lib/python3.6/site packages/tornado/gen.py”，第1133行，运行中
value=future.result（）
包装器中的文件“/opt/conda/lib/python3.6/site packages/tornado/gen.py”，第326行
产生=下一个（结果）
文件“/opt/conda/lib/python3.6/site packages/distributed/comm/tcp.py”，第201行，已读
转换流关闭错误（self，e）
文件“/opt/conda/lib/python3.6/site packages/distributed/comm/tcp.py”，第127行，在convert\u stream\u closed\u error中
raise CommClosedError（“在%s中：%s:%s”%（对象，exc.\uuuuuu类\uuuuuu名称，exc））
distributed.comm.core.CommClosedError:in:TimeoutError:[Errno 110]连接超时

它运行得相当快，我只是希望在不让员工崩溃的情况下获得一致的性能

---

谢谢

你有什么收获吗？