From 77106df69147aba5eb1784adb84e2b574927c6de Mon Sep 17 00:00:00 2001 From: Yanbo Liang Date: Sat, 10 Jan 2015 14:16:37 -0800 Subject: SPARK-4963 [SQL] Add copy to SQL's Sample operator https://issues.apache.org/jira/browse/SPARK-4963 SchemaRDD.sample() return wrong results due to GapSamplingIterator operating on mutable row. HiveTableScan make RDD with SpecificMutableRow and SchemaRDD.sample() will return GapSamplingIterator for iterating. override def next(): T = { val r = data.next() advance r } GapSamplingIterator.next() return the current underlying element and assigned it to r. However if the underlying iterator is mutable row just like what HiveTableScan returned, underlying iterator and r will point to the same object. After advance operation, we drop some underlying elments and it also changed r which is not expected. Then we return the wrong value different from initial r. To fix this issue, the most direct way is to make HiveTableScan return mutable row with copy just like the initial commit that I have made. This solution will make HiveTableScan can not get the full advantage of reusable MutableRow, but it can make sample operation return correct result. Further more, we need to investigate GapSamplingIterator.next() and make it can implement copy operation inside it. To achieve this, we should define every elements that RDD can store implement the function like cloneable and it will make huge change. Author: Yanbo Liang Closes #3827 from yanbohappy/spark-4963 and squashes the following commits: 0912ca0 [Yanbo Liang] code format keep 65c4e7c [Yanbo Liang] import file and clear annotation 55c7c56 [Yanbo Liang] better output of test case cea7e2e [Yanbo Liang] SchemaRDD add copy operation before Sample operator e840829 [Yanbo Liang] HiveTableScan return mutable row with copy --- .../org/apache/spark/sql/hive/execution/SQLQuerySuite.scala | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'sql/hive') diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala index 5d0fb72370..c1c3683f84 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala @@ -21,6 +21,7 @@ import org.apache.spark.sql.QueryTest import org.apache.spark.sql.Row import org.apache.spark.sql.hive.test.TestHive._ +import org.apache.spark.util.Utils case class Nested1(f1: Nested2) case class Nested2(f2: Nested3) @@ -202,4 +203,15 @@ class SQLQuerySuite extends QueryTest { checkAnswer(sql("SELECT sum( distinct key) FROM src group by key order by key"), sql("SELECT distinct key FROM src order by key").collect().toSeq) } + + test("SPARK-4963 SchemaRDD sample on mutable row return wrong result") { + sql("SELECT * FROM src WHERE key % 2 = 0") + .sample(withReplacement = false, fraction = 0.3) + .registerTempTable("sampled") + (1 to 10).foreach { i => + checkAnswer( + sql("SELECT * FROM sampled WHERE key % 2 = 1"), + Seq.empty[Row]) + } + } } -- cgit v1.2.3