class GpuAvroPartitionReader extends FilePartitionReaderBase with GpuAvroReaderBase
A PartitionReader that reads an AVRO file split on the GPU.
Linear Supertypes
Ordering
- Alphabetic
- By Inheritance
Inherited
- GpuAvroPartitionReader
- GpuAvroReaderBase
- FilePartitionReaderBase
- ScanWithMetrics
- Logging
- PartitionReader
- Closeable
- AutoCloseable
- AnyRef
- Any
- Hide All
- Show All
Visibility
- Public
- All
Instance Constructors
- new GpuAvroPartitionReader(conf: Configuration, partFile: PartitionedFile, blockMeta: AvroBlockMeta, readDataSchema: StructType, debugDumpPrefix: Option[String], debugDumpAlways: Boolean, maxReadBatchSizeRows: Integer, maxReadBatchSizeBytes: Long, execMetrics: Map[String, GpuMetric])
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
var
batchIter: Iterator[ColumnarBatch]
- Attributes
- protected
- Definition Classes
- FilePartitionReaderBase
-
val
cacheBufferSize: Int
- Definition Classes
- GpuAvroReaderBase
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
def
close(): Unit
- Definition Classes
- FilePartitionReaderBase → Closeable → AutoCloseable
-
val
conf: Configuration
- Definition Classes
- GpuAvroPartitionReader → GpuAvroReaderBase
-
final
def
copyBlocksData(blocks: Seq[BlockInfo], in: FSDataInputStream, out: OutputStream, sync: Option[Array[Byte]] = None): Seq[BlockInfo]
Copy the data specified by the blocks from
intooutCopy the data specified by the blocks from
intoout- Attributes
- protected
- Definition Classes
- GpuAvroReaderBase
-
def
currentMetricsValues(): Array[CustomTaskMetric]
- Definition Classes
- PartitionReader
-
val
debugDumpAlways: Boolean
- Definition Classes
- GpuAvroPartitionReader → GpuAvroReaderBase
-
val
debugDumpPrefix: Option[String]
- Definition Classes
- GpuAvroPartitionReader → GpuAvroReaderBase
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
estimateOutputSize(blocks: Seq[BlockInfo], headerSize: Long): Long
Estimate the total size from the given blocks and header
Estimate the total size from the given blocks and header
- Attributes
- protected
- Definition Classes
- GpuAvroReaderBase
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
def
get(): ColumnarBatch
- Definition Classes
- FilePartitionReaderBase → PartitionReader
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
- Attributes
- protected
- Definition Classes
- Logging
-
def
initializeLogIfNecessary(isInterpreter: Boolean): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
var
isDone: Boolean
- Attributes
- protected
- Definition Classes
- FilePartitionReaderBase
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
def
isTraceEnabled(): Boolean
- Attributes
- protected
- Definition Classes
- Logging
-
def
log: Logger
- Attributes
- protected
- Definition Classes
- Logging
-
def
logDebug(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logDebug(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logError(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logError(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logInfo(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logInfo(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logName: String
- Attributes
- protected
- Definition Classes
- Logging
-
def
logTrace(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logTrace(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logWarning(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logWarning(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
val
metrics: Map[String, GpuMetric]
- Definition Classes
- ScanWithMetrics
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
next(): Boolean
- Definition Classes
- GpuAvroPartitionReader → PartitionReader
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
populateCurrentBlockChunk(blockIter: BufferedIterator[BlockInfo], maxReadBatchSizeRows: Int, maxReadBatchSizeBytes: Long): Seq[BlockInfo]
Get the block chunk according to the max batch size and max rows.
Get the block chunk according to the max batch size and max rows.
- blockIter
blocks to be evaluated
- maxReadBatchSizeRows
soft limit on the maximum number of rows the reader reads per batch
- maxReadBatchSizeBytes
soft limit on the maximum number of bytes the reader reads per batch
- Attributes
- protected
- Definition Classes
- GpuAvroReaderBase
-
val
readDataSchema: StructType
- Definition Classes
- GpuAvroPartitionReader → GpuAvroReaderBase
-
final
def
readPartFile(partFilePath: Path, blocks: Seq[BlockInfo], headerSize: Long, conf: Configuration): (HostMemoryBuffer, Long)
Read a split into a host buffer, preparing for sending to GPU
Read a split into a host buffer, preparing for sending to GPU
- Attributes
- protected
- Definition Classes
- GpuAvroReaderBase
-
final
def
sendToGpu(hostBuf: HostMemoryBuffer, bufSize: Long, splits: Array[PartitionedFile]): Option[ColumnarBatch]
Send a host buffer to GPU for decoding, and return it as a ColumnarBatch.
Send a host buffer to GPU for decoding, and return it as a ColumnarBatch. The input hostBuf will be closed after returning, please do not use it anymore. 'splits' is used only for debugging.
- Attributes
- protected
- Definition Classes
- GpuAvroReaderBase
-
final
def
sendToGpuUnchecked(hostBuf: HostMemoryBuffer, bufSize: Long, splits: Array[PartitionedFile]): Table
Read the host data to GPU for decoding, and return it as a cuDF Table.
Read the host data to GPU for decoding, and return it as a cuDF Table. The input host buffer should contain valid data, otherwise the behavior is undefined. 'splits' is used only for debugging.
- Attributes
- protected
- Definition Classes
- GpuAvroReaderBase
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- AnyRef → Any
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()