线上环境的Delta Lake数据湖小文件太多了怎么办？

val conf = new SparkConf()
conf.set("spark.sql.extensions", "io.delta.sql.DeltaSparkSessionExtension")
conf.set("spark.sql.catalog.spark_catalog", "org.apache.spark.sql.delta.catalog.DeltaCatalog")
val session = SparkSession.builder().appName("DeltaLakeDemo").master("local[1]").config(conf).getOrCreate();
val df = session.read.parquet("deltalakefile/data/")
df.repartition(1).write.format("delta").mode("overwrite").save("deltalakefile/data/")
df.show()
session.conf.set("spark.databricks.delta.retentionDurationCheck.enabled", "false")
DeltaTable.forPath("deltalakefile/data/").vacuum()