问在read_sql_table之后无法持久化dask数据帧

EN

import numpy as np
from sqlalchemy import create_engine, MetaData, Table, Column, Integer
import sqlite3

# function to create a list of dicts with chunkSize rows by 3columns
# except for the first column, the columns are filled with random integers

def getChunk(chunkSize, prevCount):
    x = np.random.randint(low=0, high=2**32, size=(chunkSize,3), dtype='int64')
    y = x.ravel().view(dtype=[('a', 'i8'), ('b', 'i8'), ('c', 'i8')])
    y['a'] = [k + prevCount for k in range(chunkSize)]
    names = y.dtype.names
    listOfDicts = [dict(zip(names, row)) for row in y] 
    return listOfDicts

# set up a SQLAlchemy engine to a sqlite DB

dbPath = "C:\\temp2\\test.db"
connString = "sqlite:///{}".format(dbPath)
engine = create_engine(connString)

# create a table with 3 Integer columns

metadata = MetaData()
testTable = Table('testTbl', metadata,
                  Column('a', Integer, primary_key='True'),
                  Column('b', Integer),
                  Column('c', Integer)
                 )

metadata.create_all(engine)
conn = engine.connect()

chunkSize = 25000
numberChunks = 1400

sqlite3.register_adapter(np.int64, lambda x: int(x))

# use the SQLAlchemy table insert method to load list of dicts into the table, one chunk at a time
prevCount = 0

with conn.begin():
    for i in range(0, numberChunks) :
        listOfDicts = getChunk(chunkSize, prevCount)
        conn.execute(testTable.insert(), listOfDicts)
        prevCount = prevCount + chunkSize

conn.close()

# default scheduler -- OOM
import dask.dataframe as ddf
from dask.distributed import Client
import dask
import chest

cache = chest.Chest(path='c:\\temp2', available_memory=8e9)
dask.set_options(cache=cache)
dbPath = "C:\\temp2\\test.db"
connString = "sqlite:///{}".format(dbPath)
df = ddf.read_sql_table('testTbl', connString, index_col = 'a')
df = df.persist() 

>>> tornado.application - ERROR - Exception in callback <bound method Nanny.memory_monitor of <Nanny: tcp://127.0.0.1:57522, threads: 1>>
Traceback (most recent call last):
  File "C:\Program Files\Python36\lib\site-packages\psutil\_pswindows.py", line 635, in wrapper
    return fun(self, *args, **kwargs)
  File "C:\Program Files\Python36\lib\site-packages\psutil\_pswindows.py", line 821, in create_time
    return cext.proc_create_time(self.pid)
ProcessLookupError: [Errno 3] No such process

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Program Files\Python36\lib\site-packages\psutil\__init__.py", line 368, in _init
    self.create_time()
  File "C:\Program Files\Python36\lib\site-packages\psutil\__init__.py", line 699, in create_time
    self._create_time = self._proc.create_time()
  File "C:\Program Files\Python36\lib\site-packages\psutil\_pswindows.py", line 640, in wrapper
    raise NoSuchProcess(self.pid, self._name)
psutil._exceptions.NoSuchProcess: psutil.NoSuchProcess process no longer exists (pid=14212)

import dask.dataframe as ddf
from dask.distributed import Client
import dask
import chest
cache = chest.Chest(path='c:\\temp2', available_memory=8e9)
dask.set_options(cache=cache)
client = Client(address="127.0.0.1:8786")
dbPath = "C:\\temp2\\test.db"
connString = "sqlite:///{}".format(dbPath)
df = ddf.read_sql_table('testTbl', connString, index_col = 'a')
df = client.persist(df)

distributed.worker - WARNING - Memory use is high but worker has no data to store to disk.  Perhaps some other process is leaking memory?  Process memory: 2.12 GB -- Worker memory limit: 3.00 GB
distributed.worker - WARNING - Memory use is high but worker has no data to store to disk.  Perhaps some other process is leaking memory?  Process memory: 2.16 GB -- Worker memory limit: 3.00 GB
distributed.worker - WARNING - Memory use is high but worker has no data to store to disk.  Perhaps some other process is leaking memory?  Process memory: 2.24 GB -- Worker memory limit: 3.00 GB
distributed.worker - WARNING - Memory use is high but worker has no data to store to disk.  Perhaps some other process is leaking memory?  Process memory: 2.31 GB -- Worker memory limit: 3.00 GB
distributed.worker - WARNING - Memory use is high but worker has no data to store to disk.  Perhaps some other process is leaking memory?  Process memory: 2.39 GB -- Worker memory limit: 3.00 GB
distributed.worker - WARNING - Worker is at 81% memory usage. Pausing worker.  Process memory: 2.46 GB -- Worker memory limit: 3.00 GB
distributed.worker - WARNING - Memory use is high but worker has no data to store to disk.  Perhaps some other process is leaking memory?  Process memory: 2.47 GB -- Worker memory limit: 3.00 GB
distributed.worker - WARNING - Memory use is high but worker has no data to store to disk.  Perhaps some other process is leaking memory?  Process memory: 2.54 GB -- Worker memory limit: 3.00 GB
distributed.worker - WARNING - Memory use is high but worker has no data to store to disk.  Perhaps some other process is leaking memory?  Process memory: 2.61 GB -- Worker memory limit: 3.00 GB
distributed.worker - WARNING - Memory use is high but worker has no data to store to disk.  Perhaps some other process is leaking memory?  Process memory: 2.66 GB -- Worker memory limit: 3.00 GB
distributed.worker - WARNING - Memory use is high but worker has no data to store to disk.  Perhaps some other process is leaking memory?  Process memory: 2.73 GB -- Worker memory limit: 3.00 GB
distributed.worker - WARNING - Memory use is high but worker has no data to store to disk.  Perhaps some other process is leaking memory?  Process memory: 2.81 GB -- Worker memory limit: 3.00 GB
distributed.nanny - WARNING - Worker exceeded 95% memory budget.  Restarting
distributed.nanny - WARNING - Worker process 17916 was killed by signal 15
distributed.nanny - WARNING - Restarting worker