Я пытаюсь оптимизировать работу Glue / PySpark с помощью предикатов push down.
start = date(2019, 2, 13)
end = date(2019, 2, 27)
print(">>> Generate data frame for ", start, " to ", end, "... ")
relaventDatesDf = spark.createDataFrame([
Row(start=start, stop=end)
])
relaventDatesDf.createOrReplaceTempView("relaventDates")
relaventDatesDf = spark.sql("SELECT explode(generate_date_series(start, stop)) AS querydatetime FROM relaventDates")
relaventDatesDf.createOrReplaceTempView("relaventDates")
print("===LOG:Dates===")
relaventDatesDf.show()
flightsGDF = glueContext.create_dynamic_frame.from_catalog(database = "xxx", table_name = "flights", transformation_ctx="flights", push_down_predicate="""
querydatetime BETWEEN '%s' AND '%s'
AND querydestinationplace IN (%s)
""" % (start.strftime("%Y-%m-%d"), today.strftime("%Y-%m-%d"), ",".join(map(lambda s: str(s), arr))))
Однако, похоже, что Glue все еще пытается прочитать данные за пределами указанного диапазона дат?
INFO S3NativeFileSystem: Opening 's3://.../flights/querydestinationplace=12191/querydatetime=2019-03-01/part-00045-6cdebbb1-562c-43fa-915d-93b125aeee61.c000.snappy.parquet' for reading
INFO FileScanRDD: Reading File path: s3://.../flights/querydestinationplace=12191/querydatetime=2019-03-10/part-00021-34a13146-8fb2-43de-9df2-d8925cbe472d.c000.snappy.parquet, range: 0-11797922, partition values: [12191,17965]
WARN S3AbortableInputStream: Not all bytes were read from the S3ObjectInputStream, aborting HTTP connection. This is likely an error and may result in sub-optimal behavior. Request only the bytes you need via a ranged GET or drain the input stream after use.
INFO S3NativeFileSystem: Opening 's3://.../flights/querydestinationplace=12191/querydatetime=2019-03-10/part-00021-34a13146-8fb2-43de-9df2-d8925cbe472d.c000.snappy.parquet' for reading
WARN S3AbortableInputStream: Not all bytes were read from the S3ObjectInputStream, aborting HTTP connection. This is likely an error and may result in sub-optimal behavior. Request only the bytes you need via a ranged GET or drain the input stream after use.
Обратите внимание на querydatetime=2019-03-01
и querydatetime=2019-03-10
вне указанного диапазона 2019-02-13 - 2019-02-27
.Вот почему есть следующая строка "прерывание HTTP-соединения"?Далее говорится: «Это, вероятно, ошибка и может привести к неоптимальному поведению», что-то не так?
Интересно, проблема в том, что он не поддерживает МЕЖДУ предикатом или IN?
Таблица создания DDL
CREATE EXTERNAL TABLE `flights`(
`id` string,
`querytaskid` string,
`queryoriginplace` string,
`queryoutbounddate` string,
`queryinbounddate` string,
`querycabinclass` string,
`querycurrency` string,
`agent` string,
`quoteageinminutes` string,
`price` string,
`outboundlegid` string,
`inboundlegid` string,
`outdeparture` string,
`outarrival` string,
`outduration` string,
`outjourneymode` string,
`outstops` string,
`outcarriers` string,
`outoperatingcarriers` string,
`numberoutstops` string,
`numberoutcarriers` string,
`numberoutoperatingcarriers` string,
`indeparture` string,
`inarrival` string,
`induration` string,
`injourneymode` string,
`instops` string,
`incarriers` string,
`inoperatingcarriers` string,
`numberinstops` string,
`numberincarriers` string,
`numberinoperatingcarriers` string)
PARTITIONED BY (
`querydestinationplace` string,
`querydatetime` string)
ROW FORMAT SERDE
'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
STORED AS INPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
LOCATION
's3://pinfare-glue/flights/'
TBLPROPERTIES (
'CrawlerSchemaDeserializerVersion'='1.0',
'CrawlerSchemaSerializerVersion'='1.0',
'UPDATED_BY_CRAWLER'='pinfare-parquet',
'averageRecordSize'='19',
'classification'='parquet',
'compressionType'='none',
'objectCount'='623609',
'recordCount'='4368434222',
'sizeKey'='86509997099',
'typeOfData'='file')