WeichenXu123 commented on code in PR #44294: URL: https://github.com/apache/spark/pull/44294#discussion_r1437960050
########## python/pyspark/sql/chunk_api.py: ########## @@ -0,0 +1,126 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +import os +from collections import namedtuple + +import pyarrow as pa + +from pyspark.rdd import _create_local_socket +from pyspark.sql import DataFrame +from pyspark.sql import SparkSession +from pyspark.serializers import read_with_length, write_with_length +from pyspark.sql.pandas.serializers import ArrowStreamSerializer +from pyspark.errors import PySparkRuntimeError + + +ChunkMeta = namedtuple("ChunkMeta", ["id", "row_count", "byte_count"]) + + +def persist_dataframe_as_chunks( + dataframe: DataFrame, max_records_per_batch: int +) -> list[ChunkMeta]: + """ + Persist and materialize the spark dataframe as chunks, each chunk is an arrow batch. + It tries to persist data to spark worker memory firstly, if memory is not sufficient, + then it fallbacks to persist spilled data to spark worker local disk. + Return the list of tuple (chunk_id, chunk_row_count, chunk_byte_count). + This function is only available when it is called from spark driver process. + """ + spark = dataframe.sparkSession + if spark is None: + raise PySparkRuntimeError("Active spark session is required.") + + sc = spark.sparkContext + if sc.getConf().get("spark.python.dataFrameChunkRead.enabled", "false").lower() != "true": Review Comment: Putting it in StaticSQLConf sounds good. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
