问如何更改pysark中DataFrame的hdfs块大小

EN

##########
# init
##########
from pyspark import SparkContext, SparkConf
from pyspark.sql import SparkSession

import hdfs
from hdfs import InsecureClient
import os

import numpy as np
import pandas as pd
import logging

os.environ['SPARK_HOME'] = '/opt/spark-2.2.1-bin-hadoop2.7'

block_size = 512 * 1024

conf = SparkConf().setAppName("myapp").setMaster("spark://spark1:7077").set('spark.cores.max', 20).set("spark.executor.cores", 10).set("spark.executor.memory", "10g").set("spark.hadoop.dfs.blocksize", str(block_size)).set("spark.hadoop.dfs.block.size", str(block_size))

spark = SparkSession.builder.config(conf=conf).getOrCreate()
spark.sparkContext._jsc.hadoopConfiguration().setInt("dfs.blocksize", block_size)
spark.sparkContext._jsc.hadoopConfiguration().setInt("dfs.block.size", block_size)

##########
# main
##########

# create DataFrame
df_txt = spark.createDataFrame([\{'temp': "hello"}, \{'temp': "world"}, \{'temp': "!"}])

# save using DataFrameWriter, resulting 128MB-block-size

df_txt.write.mode('overwrite').format('parquet').save('hdfs://spark1/tmp/temp_with_df')

# save using rdd, resulting 512k-block-size
client = InsecureClient('http://spark1:50070')
client.delete('/tmp/temp_with_rrd', recursive=True)
df_txt.rdd.saveAsTextFile('hdfs://spark1/tmp/temp_with_rrd')