Fix ByteBuffer.limit misuse

core/src/main/scala/org/apache/spark/executor/Executor.scala

@@ -253,7 +253,7 @@ private[spark] class Executor(
 
         val directResult = new DirectTaskResult(valueBytes, accumUpdates, task.metrics.orNull)
         val serializedDirectResult = ser.serialize(directResult)
-        val resultSize = serializedDirectResult.limit
+        val resultSize = serializedDirectResult.remaining()
 
         // directSend = sending directly back to the driver
         val serializedResult: ByteBuffer = {

core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala

@@ -166,7 +166,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
       combOp: (U, U) => U): RDD[(K, U)] = self.withScope {
     // Serialize the zero value to a byte array so that we can get a new clone of it on each key
     val zeroBuffer = SparkEnv.get.serializer.newInstance().serialize(zeroValue)
-    val zeroArray = new Array[Byte](zeroBuffer.limit)
+    val zeroArray = new Array[Byte](zeroBuffer.remaining())
     zeroBuffer.get(zeroArray)
 
     lazy val cachedSerializer = SparkEnv.get.serializer.newInstance()
@@ -216,7 +216,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
       partitioner: Partitioner)(func: (V, V) => V): RDD[(K, V)] = self.withScope {
     // Serialize the zero value to a byte array so that we can get a new clone of it on each key
     val zeroBuffer = SparkEnv.get.serializer.newInstance().serialize(zeroValue)
-    val zeroArray = new Array[Byte](zeroBuffer.limit)
+    val zeroArray = new Array[Byte](zeroBuffer.remaining())
     zeroBuffer.get(zeroArray)
 
     // When deserializing, use a lazy val to create just one instance of the serializer per task

core/src/main/scala/org/apache/spark/scheduler/TaskResultGetter.scala

@@ -51,14 +51,14 @@ private[spark] class TaskResultGetter(sparkEnv: SparkEnv, scheduler: TaskSchedul
         try {
           val (result, size) = serializer.get().deserialize[TaskResult[_]](serializedData) match {
             case directResult: DirectTaskResult[_] =>
-              if (!taskSetManager.canFetchMoreResults(serializedData.limit())) {
+              if (!taskSetManager.canFetchMoreResults(serializedData.remaining())) {
                 return
               }
               // deserialize "value" without holding any lock so that it won't block other threads.
               // We should call it here, so that when it's called again in
               // "TaskSetManager.handleSuccessfulTask", it does not need to deserialize the value.
               directResult.value()
-              (directResult, serializedData.limit())
+              (directResult, serializedData.remaining())
             case IndirectTaskResult(blockId, size) =>
               if (!taskSetManager.canFetchMoreResults(size)) {
                 // dropped by executor if size is larger than maxResultSize
@@ -105,7 +105,7 @@ private[spark] class TaskResultGetter(sparkEnv: SparkEnv, scheduler: TaskSchedul
         override def run(): Unit = Utils.logUncaughtExceptions {
           val loader = Utils.getContextOrSparkClassLoader
           try {
-            if (serializedData != null && serializedData.limit() > 0) {
+            if (serializedData != null && serializedData.remaining() > 0) {
               reason = serializer.get().deserialize[TaskEndReason](
                 serializedData, loader)
             }

core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala

@@ -469,11 +469,11 @@ private[spark] class TaskSetManager(
               abort(s"$msg Exception during serialization: $e")
               throw new TaskNotSerializableException(e)
           }
-          if (serializedTask.limit > TaskSetManager.TASK_SIZE_TO_WARN_KB * 1024 &&
+          if (serializedTask.remaining() > TaskSetManager.TASK_SIZE_TO_WARN_KB * 1024 &&
               !emittedTaskSizeWarning) {
             emittedTaskSizeWarning = true
             logWarning(s"Stage ${task.stageId} contains a task of very large size " +
-              s"(${serializedTask.limit / 1024} KB). The maximum recommended task size is " +
+              s"(${serializedTask.remaining() / 1024} KB). The maximum recommended task size is " +
               s"${TaskSetManager.TASK_SIZE_TO_WARN_KB} KB.")
           }
           addRunningTask(taskId)
@@ -483,7 +483,7 @@ private[spark] class TaskSetManager(
           // val timeTaken = clock.getTime() - startTime
           val taskName = s"task ${info.id} in stage ${taskSet.id}"
           logInfo(s"Starting $taskName (TID $taskId, $host, partition ${task.partitionId}," +
-            s"$taskLocality, ${serializedTask.limit} bytes)")
+            s"$taskLocality, ${serializedTask.remaining()} bytes)")
 
           sched.dagScheduler.taskStarted(task, info)
           return Some(new TaskDescription(taskId = taskId, attemptNumber = attemptNum, execId,

core/src/main/scala/org/apache/spark/scheduler/cluster/CoarseGrainedSchedulerBackend.scala

@@ -224,13 +224,13 @@ class CoarseGrainedSchedulerBackend(scheduler: TaskSchedulerImpl, val rpcEnv: Rp
     private def launchTasks(tasks: Seq[Seq[TaskDescription]]) {
       for (task <- tasks.flatten) {
         val serializedTask = ser.serialize(task)
-        if (serializedTask.limit >= akkaFrameSize - AkkaUtils.reservedSizeBytes) {
+        if (serializedTask.remaining() >= akkaFrameSize - AkkaUtils.reservedSizeBytes) {
           scheduler.taskIdToTaskSetManager.get(task.taskId).foreach { taskSetMgr =>
             try {
               var msg = "Serialized task %s:%d was %d bytes, which exceeds max allowed: " +
                 "spark.akka.frameSize (%d bytes) - reserved (%d bytes). Consider increasing " +
                 "spark.akka.frameSize or using broadcast variables for large values."
-              msg = msg.format(task.taskId, task.index, serializedTask.limit, akkaFrameSize,
+              msg = msg.format(task.taskId, task.index, serializedTask.remaining(), akkaFrameSize,
                 AkkaUtils.reservedSizeBytes)
               taskSetMgr.abort(msg)
             } catch {

core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosTaskLaunchData.scala

@@ -31,7 +31,7 @@ private[spark] case class MesosTaskLaunchData(
   attemptNumber: Int) extends Logging {
 
   def toByteString: ByteString = {
-    val dataBuffer = ByteBuffer.allocate(4 + serializedTask.limit)
+    val dataBuffer = ByteBuffer.allocate(4 + serializedTask.remaining())
     dataBuffer.putInt(attemptNumber)
     dataBuffer.put(serializedTask)
     dataBuffer.rewind

core/src/main/scala/org/apache/spark/storage/BlockManager.scala

@@ -522,12 +522,12 @@ private[spark] class BlockManager(
               /* We'll store the bytes in memory if the block's storage level includes
                * "memory serialized", or if it should be cached as objects in memory
                * but we only requested its serialized bytes. */
-              memoryStore.putBytes(blockId, bytes.limit, () => {
+              memoryStore.putBytes(blockId, bytes.remaining(), () => {
                 // https://issues.apache.org/jira/browse/SPARK-6076
                 // If the file size is bigger than the free memory, OOM will happen. So if we cannot
                 // put it into MemoryStore, copyForMemory should not be created. That's why this
                 // action is put into a `() => ByteBuffer` and created lazily.
-                val copyForMemory = ByteBuffer.allocate(bytes.limit)
+                val copyForMemory = ByteBuffer.allocate(bytes.remaining())
                 copyForMemory.put(bytes)
               })
               bytes.rewind()
@@ -607,7 +607,7 @@ private[spark] class BlockManager(
           return Some(new BlockResult(
             dataDeserialize(blockId, data),
             DataReadMethod.Network,
-            data.limit()))
+            data.remaining()))
         } else {
           return Some(data)
         }
@@ -951,10 +951,10 @@ private[spark] class BlockManager(
           try {
             val onePeerStartTime = System.currentTimeMillis
             data.rewind()
-            logTrace(s"Trying to replicate $blockId of ${data.limit()} bytes to $peer")
+            logTrace(s"Trying to replicate $blockId of ${data.remaining()} bytes to $peer")
             blockTransferService.uploadBlockSync(
               peer.host, peer.port, peer.executorId, blockId, new NioManagedBuffer(data), tLevel)
-            logTrace(s"Replicated $blockId of ${data.limit()} bytes to $peer in %s ms"
+            logTrace(s"Replicated $blockId of ${data.remaining()} bytes to $peer in %s ms"
               .format(System.currentTimeMillis - onePeerStartTime))
             peersReplicatedTo += peer
             peersForReplication -= peer
@@ -977,7 +977,7 @@ private[spark] class BlockManager(
       }
     }
     val timeTakeMs = (System.currentTimeMillis - startTime)
-    logDebug(s"Replicating $blockId of ${data.limit()} bytes to " +
+    logDebug(s"Replicating $blockId of ${data.remaining()} bytes to " +
       s"${peersReplicatedTo.size} peer(s) took $timeTakeMs ms")
     if (peersReplicatedTo.size < numPeersToReplicateTo) {
       logWarning(s"Block $blockId replicated to only " +

core/src/main/scala/org/apache/spark/storage/DiskStore.scala

@@ -54,8 +54,8 @@ private[spark] class DiskStore(blockManager: BlockManager, diskManager: DiskBloc
     }
     val finishTime = System.currentTimeMillis
     logDebug("Block %s stored as %s file on disk in %d ms".format(
-      file.getName, Utils.bytesToString(bytes.limit), finishTime - startTime))
-    PutResult(bytes.limit(), Right(bytes.duplicate()))
+      file.getName, Utils.bytesToString(bytes.remaining()), finishTime - startTime))
+    PutResult(bytes.remaining(), Right(bytes.duplicate()))
   }
 
   override def putArray(

core/src/main/scala/org/apache/spark/storage/ExternalBlockStore.scala

@@ -110,7 +110,7 @@ private[spark] class ExternalBlockStore(blockManager: BlockManager, executorId:
         val byteBuffer = bytes.duplicate()
         byteBuffer.rewind()
         externalBlockManager.get.putBytes(blockId, byteBuffer)
-        val size = bytes.limit()
+        val size = bytes.remaining()
         val data = if (returnValues) {
           Right(bytes)
         } else {

core/src/main/scala/org/apache/spark/storage/MemoryStore.scala

@@ -96,8 +96,8 @@ private[spark] class MemoryStore(blockManager: BlockManager, memoryManager: Memo
       putIterator(blockId, values, level, returnValues = true)
     } else {
       val droppedBlocks = new ArrayBuffer[(BlockId, BlockStatus)]
-      tryToPut(blockId, bytes, bytes.limit, deserialized = false, droppedBlocks)
-      PutResult(bytes.limit(), Right(bytes.duplicate()), droppedBlocks)
+      tryToPut(blockId, bytes, bytes.remaining(), deserialized = false, droppedBlocks)
+      PutResult(bytes.remaining(), Right(bytes.duplicate()), droppedBlocks)
     }
   }
 
@@ -114,7 +114,7 @@ private[spark] class MemoryStore(blockManager: BlockManager, memoryManager: Memo
     val putSuccess = tryToPut(blockId, () => bytes, size, deserialized = false, droppedBlocks)
     val data =
       if (putSuccess) {
-        assert(bytes.limit == size)
+        assert(bytes.remaining() == size)
         Right(bytes.duplicate())
       } else {
         null
@@ -134,8 +134,8 @@ private[spark] class MemoryStore(blockManager: BlockManager, memoryManager: Memo
       PutResult(sizeEstimate, Left(values.iterator), droppedBlocks)
     } else {
       val bytes = blockManager.dataSerialize(blockId, values.iterator)
-      tryToPut(blockId, bytes, bytes.limit, deserialized = false, droppedBlocks)
-      PutResult(bytes.limit(), Right(bytes.duplicate()), droppedBlocks)
+      tryToPut(blockId, bytes, bytes.remaining(), deserialized = false, droppedBlocks)
+      PutResult(bytes.remaining(), Right(bytes.duplicate()), droppedBlocks)
     }
   }
 

core/src/main/scala/org/apache/spark/util/SerializableBuffer.scala

@@ -45,8 +45,9 @@ class SerializableBuffer(@transient var buffer: ByteBuffer) extends Serializable
   }
 
   private def writeObject(out: ObjectOutputStream): Unit = Utils.tryOrIOException {
-    out.writeInt(buffer.limit())
-    if (Channels.newChannel(out).write(buffer) != buffer.limit()) {
+    val readableBytes = buffer.remaining()
+    out.writeInt(readableBytes)
+    if (Channels.newChannel(out).write(buffer) != readableBytes) {
       throw new IOException("Could not fully write buffer to output stream")
     }
     buffer.rewind() // Allow us to write it again later

core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala

@@ -154,8 +154,8 @@ class RDDSuite extends SparkFunSuite with SharedSparkContext {
     val ser = SparkEnv.get.closureSerializer.newInstance()
     val union = rdd1.union(rdd2)
     // The UnionRDD itself should be large, but each individual partition should be small.
-    assert(ser.serialize(union).limit() > 2000)
-    assert(ser.serialize(union.partitions.head).limit() < 2000)
+    assert(ser.serialize(union).remaining() > 2000)
+    assert(ser.serialize(union.partitions.head).remaining() < 2000)
   }
 
   test("aggregate") {

core/src/test/scala/org/apache/spark/serializer/KryoSerializerSuite.scala

@@ -185,7 +185,7 @@ class KryoSerializerSuite extends SparkFunSuite with SharedSparkContext {
     def check[T: ClassTag](t: T) {
       assert(ser.deserialize[T](ser.serialize(t)) === t)
       // Check that very long ranges don't get written one element at a time
-      assert(ser.serialize(t).limit < 100)
+      assert(ser.serialize(t).remaining() < 100)
     }
     check(1 to 1000000)
     check(1 to 1000000 by 2)

sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/UnsafeRowParquetRecordReader.java

@@ -332,7 +332,7 @@ private void decodeBinaryBatch(int col, int num) throws IOException {
     for (int n = 0; n < num; ++n) {
       if (columnReaders[col].next()) {
         ByteBuffer bytes = columnReaders[col].nextBinary().toByteBuffer();
-        int len = bytes.limit() - bytes.position();
+        int len = bytes.remaining();
         if (originalTypes[col] == OriginalType.UTF8) {
           UTF8String str = UTF8String.fromBytes(bytes.array(), bytes.position(), len);
           rowWriters[n].write(col, str);

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

@@ -88,7 +88,7 @@ private[columnar] trait CompressibleColumnBuilder[T <: AtomicType]
     }
 
     // Header = null count + null positions
-    val headerSize = 4 + nulls.limit()
+    val headerSize = 4 + nulls.remaining()
     val compressedSize = if (encoder.compressedSize == 0) {
       nonNullBuffer.remaining()
     } else {

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

@@ -328,7 +328,7 @@ private[parquet] class CatalystRowConverter(
       // it.
       val buffer = value.toByteBuffer
       val offset = buffer.position()
-      val numBytes = buffer.limit() - buffer.position()
+      val numBytes = buffer.remaining()
       updater.set(UTF8String.fromBytes(buffer.array(), offset, numBytes))
     }
   }