Disables page-level CRC checksums by default.

Author: wangyum

sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala

@@ -127,6 +127,9 @@ class ParquetFileFormat
       conf.setEnum(ParquetOutputFormat.JOB_SUMMARY_LEVEL, JobSummaryLevel.NONE)
     }
 
+    // PARQUET-1580: Disables page-level CRC checksums by default.
+    conf.setBooleanIfUnset(ParquetOutputFormat.PAGE_WRITE_CHECKSUM_ENABLED, false)
+
     if (ParquetOutputFormat.getJobSummaryLevel(conf) != JobSummaryLevel.NONE
       && !classOf[ParquetOutputCommitter].isAssignableFrom(committerClass)) {
       // output summary is requested, but the class is not a Parquet Committer

sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamSuite.scala

@@ -29,7 +29,6 @@ import scala.util.control.ControlThrowable
 import com.google.common.util.concurrent.UncheckedExecutionException
 import org.apache.commons.io.FileUtils
 import org.apache.hadoop.conf.Configuration
-import org.apache.parquet.hadoop.ParquetOutputFormat
 import org.scalatest.time.SpanSugar._
 
 import org.apache.spark.{SparkConf, SparkContext, TaskContext, TestUtils}
@@ -226,9 +225,7 @@ class StreamSuite extends StreamTest {
 
     val df = spark.readStream.format(classOf[FakeDefaultSource].getName).load()
     Seq("", "parquet").foreach { useV1Source =>
-      withSQLConf(
-        SQLConf.USE_V1_SOURCE_LIST.key -> useV1Source,
-        ParquetOutputFormat.PAGE_WRITE_CHECKSUM_ENABLED -> "false") {
+      withSQLConf(SQLConf.USE_V1_SOURCE_LIST.key -> useV1Source) {
         assertDF(df)
         assertDF(df)
       }