[SPARK-24850][SQL] fix str representation of CachedRDDBuilder

## What changes were proposed in this pull request?
As of #21018, InMemoryRelation includes its cacheBuilder when logging query plans. This PR changes the string representation of the CachedRDDBuilder to not include the cached spark plan.

## How was this patch tested?

spark-shell, query:
```
var df_cached = spark.read.format("csv").option("header", "true").load("test.csv").cache()
0 to 1 foreach { _ =>
df_cached = df_cached.join(spark.read.format("csv").option("header", "true").load("test.csv"), "A").cache()
}
df_cached.explain
```
as of master results in:
```
== Physical Plan ==
InMemoryTableScan [A#10, B#11, B#35, B#87]
+- InMemoryRelation [A#10, B#11, B#35, B#87], CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1 replicas),*(2) Project [A#10, B#11, B#35, B#87]
+- *(2) BroadcastHashJoin [A#10], [A#86], Inner, BuildRight
:- *(2) Filter isnotnull(A#10)
: +- InMemoryTableScan [A#10, B#11, B#35], [isnotnull(A#10)]
: +- InMemoryRelation [A#10, B#11, B#35], CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1 replicas),*(2) Project [A#10, B#11, B#35]
+- *(2) BroadcastHashJoin [A#10], [A#34], Inner, BuildRight
:- *(2) Filter isnotnull(A#10)
: +- InMemoryTableScan [A#10, B#11], [isnotnull(A#10)]
: +- InMemoryRelation [A#10, B#11], CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1 replicas),*(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
,None)
: +- *(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
+- BroadcastExchange HashedRelationBroadcastMode(List(input[0, string, false]))
+- *(1) Filter isnotnull(A#34)
+- InMemoryTableScan [A#34, B#35], [isnotnull(A#34)]
+- InMemoryRelation [A#34, B#35], CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1 replicas),*(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
,None)
+- *(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
,None)
: +- *(2) Project [A#10, B#11, B#35]
: +- *(2) BroadcastHashJoin [A#10], [A#34], Inner, BuildRight
: :- *(2) Filter isnotnull(A#10)
: : +- InMemoryTableScan [A#10, B#11], [isnotnull(A#10)]
: : +- InMemoryRelation [A#10, B#11], CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1 replicas),*(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
,None)
: : +- *(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
: +- BroadcastExchange HashedRelationBroadcastMode(List(input[0, string, false]))
: +- *(1) Filter isnotnull(A#34)
: +- InMemoryTableScan [A#34, B#35], [isnotnull(A#34)]
: +- InMemoryRelation [A#34, B#35], CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1 replicas),*(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
,None)
: +- *(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
+- BroadcastExchange HashedRelationBroadcastMode(List(input[0, string, false]))
+- *(1) Filter isnotnull(A#86)
+- InMemoryTableScan [A#86, B#87], [isnotnull(A#86)]
+- InMemoryRelation [A#86, B#87], CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1 replicas),*(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
,None)
+- *(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
,None)
+- *(2) Project [A#10, B#11, B#35, B#87]
+- *(2) BroadcastHashJoin [A#10], [A#86], Inner, BuildRight
:- *(2) Filter isnotnull(A#10)
: +- InMemoryTableScan [A#10, B#11, B#35], [isnotnull(A#10)]
: +- InMemoryRelation [A#10, B#11, B#35], CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1 replicas),*(2) Project [A#10, B#11, B#35]
+- *(2) BroadcastHashJoin [A#10], [A#34], Inner, BuildRight
:- *(2) Filter isnotnull(A#10)
: +- InMemoryTableScan [A#10, B#11], [isnotnull(A#10)]
: +- InMemoryRelation [A#10, B#11], CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1 replicas),*(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
,None)
: +- *(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
+- BroadcastExchange HashedRelationBroadcastMode(List(input[0, string, false]))
+- *(1) Filter isnotnull(A#34)
+- InMemoryTableScan [A#34, B#35], [isnotnull(A#34)]
+- InMemoryRelation [A#34, B#35], CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1 replicas),*(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
,None)
+- *(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
,None)
: +- *(2) Project [A#10, B#11, B#35]
: +- *(2) BroadcastHashJoin [A#10], [A#34], Inner, BuildRight
: :- *(2) Filter isnotnull(A#10)
: : +- InMemoryTableScan [A#10, B#11], [isnotnull(A#10)]
: : +- InMemoryRelation [A#10, B#11], CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1 replicas),*(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
,None)
: : +- *(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
: +- BroadcastExchange HashedRelationBroadcastMode(List(input[0, string, false]))
: +- *(1) Filter isnotnull(A#34)
: +- InMemoryTableScan [A#34, B#35], [isnotnull(A#34)]
: +- InMemoryRelation [A#34, B#35], CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1 replicas),*(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
,None)
: +- *(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
+- BroadcastExchange HashedRelationBroadcastMode(List(input[0, string, false]))
+- *(1) Filter isnotnull(A#86)
+- InMemoryTableScan [A#86, B#87], [isnotnull(A#86)]
+- InMemoryRelation [A#86, B#87], CachedRDDBuilder(true,10000,StorageLevel(disk, memory, deserialized, 1 replicas),*(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
,None)
+- *(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
```
with this patch results in:
```
== Physical Plan ==
InMemoryTableScan [A#10, B#11, B#35, B#87]
   +- InMemoryRelation [A#10, B#11, B#35, B#87], CachedRDDBuilder(true, 10000, StorageLevel(disk, memory, deserialized, 1 replicas))
         +- *(2) Project [A#10, B#11, B#35, B#87]
            +- *(2) BroadcastHashJoin [A#10], [A#86], Inner, BuildRight
               :- *(2) Filter isnotnull(A#10)
               :  +- InMemoryTableScan [A#10, B#11, B#35], [isnotnull(A#10)]
               :        +- InMemoryRelation [A#10, B#11, B#35], CachedRDDBuilder(true, 10000, StorageLevel(disk, memory, deserialized, 1 replicas))
               :              +- *(2) Project [A#10, B#11, B#35]
               :                 +- *(2) BroadcastHashJoin [A#10], [A#34], Inner, BuildRight
               :                    :- *(2) Filter isnotnull(A#10)
               :                    :  +- InMemoryTableScan [A#10, B#11], [isnotnull(A#10)]
               :                    :        +- InMemoryRelation [A#10, B#11], CachedRDDBuilder(true, 10000, StorageLevel(disk, memory, deserialized, 1 replicas))
               :                    :              +- *(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
               :                    +- BroadcastExchange HashedRelationBroadcastMode(List(input[0, string, false]))
               :                       +- *(1) Filter isnotnull(A#34)
               :                          +- InMemoryTableScan [A#34, B#35], [isnotnull(A#34)]
               :                                +- InMemoryRelation [A#34, B#35], CachedRDDBuilder(true, 10000, StorageLevel(disk, memory, deserialized, 1 replicas))
               :                                      +- *(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
               +- BroadcastExchange HashedRelationBroadcastMode(List(input[0, string, false]))
                  +- *(1) Filter isnotnull(A#86)
                     +- InMemoryTableScan [A#86, B#87], [isnotnull(A#86)]
                           +- InMemoryRelation [A#86, B#87], CachedRDDBuilder(true, 10000, StorageLevel(disk, memory, deserialized, 1 replicas))
                                 +- *(1) FileScan csv [A#10,B#11] Batched: false, Format: CSV, Location: InMemoryFileIndex[file:test.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<A:string,B:string>
```

Author: Onur Satici <osatici@palantir.com>

Closes #21805 from onursatici/os/inmemoryrelation-str.

Author: onursatici

sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryRelation.scala

@@ -29,7 +29,7 @@ import org.apache.spark.sql.catalyst.plans.logical
 import org.apache.spark.sql.catalyst.plans.logical.{HintInfo, LogicalPlan, Statistics}
 import org.apache.spark.sql.execution.SparkPlan
 import org.apache.spark.storage.StorageLevel
-import org.apache.spark.util.LongAccumulator
+import org.apache.spark.util.{LongAccumulator, Utils}
 
 
 /**
@@ -207,4 +207,7 @@ case class InMemoryRelation(
   }
 
   override protected def otherCopyArgs: Seq[AnyRef] = Seq(statsOfPlanToCache)
+
+  override def simpleString: String =
+    s"InMemoryRelation [${Utils.truncatedString(output, ", ")}], ${cacheBuilder.storageLevel}"
 }

sql/core/src/test/scala/org/apache/spark/sql/DatasetCacheSuite.scala

@@ -206,4 +206,15 @@ class DatasetCacheSuite extends QueryTest with SharedSQLContext with TimeLimits
     // first time use, load cache
     checkDataset(df5, Row(10))
   }
+
+  test("SPARK-24850 InMemoryRelation string representation does not include cached plan") {
+    val df = Seq(1).toDF("a").cache()
+    val outputStream = new java.io.ByteArrayOutputStream()
+    Console.withOut(outputStream) {
+      df.explain(false)
+    }
+    assert(outputStream.toString.replaceAll("#\\d+", "#x").contains(
+      "InMemoryRelation [a#x], StorageLevel(disk, memory, deserialized, 1 replicas)"
+    ))
+  }
 }