ilooner commented on a change in pull request #1606: DRILL-6845: Semi-Hash-Join
to skip incoming build duplicates, automatically stop skipping if too few
URL: https://github.com/apache/drill/pull/1606#discussion_r248149480
##########
File path:
exec/java-exec/src/main/java/org/apache/drill/exec/physical/impl/join/HashJoinSpillControlImpl.java
##########
@@ -18,39 +18,211 @@
package org.apache.drill.exec.physical.impl.join;
+ import org.apache.drill.exec.ExecConstants;
import org.apache.drill.exec.memory.BufferAllocator;
+ import org.apache.drill.exec.ops.FragmentContext;
+ import org.apache.drill.exec.record.RecordBatch;
import org.apache.drill.exec.record.RecordBatchMemoryManager;
- import org.apache.drill.exec.record.RecordBatchSizer;
- import org.apache.drill.exec.record.VectorContainer;
+ import org.slf4j.Logger;
+ import org.slf4j.LoggerFactory;
+
+ import javax.annotation.Nullable;
+ import java.util.Set;
+
+ import static org.apache.drill.exec.record.JoinBatchMemoryManager.LEFT_INDEX;
+ import static
org.apache.drill.exec.record.JoinBatchMemoryManager.RIGHT_INDEX;
/**
* This class is currently used only for Semi-Hash-Join that avoids duplicates
by the use of a hash table
- * The method {@link
HashJoinMemoryCalculator.HashJoinSpillControl#shouldSpill(VectorContainer)}
returns true if the memory available now to the allocator if not enough
+ * The method {@link
HashJoinMemoryCalculator.HashJoinSpillControl#shouldSpill()} returns true if
the memory available now to the allocator if not enough
* to hold (a multiple of, for safety) a new allocated batch
*/
-public class HashJoinSpillControlImpl implements
HashJoinMemoryCalculator.HashJoinSpillControl {
+public class HashJoinSpillControlImpl implements
HashJoinMemoryCalculator.BuildSidePartitioning {
+ private static final Logger logger =
LoggerFactory.getLogger(HashJoinSpillControlImpl.class);
+
private BufferAllocator allocator;
private int recordsPerBatch;
private int minBatchesInAvailableMemory;
private RecordBatchMemoryManager batchMemoryManager;
+ private int initialPartitions;
+ private int numPartitions;
+ private int recordsPerPartitionBatchProbe;
+ private FragmentContext context;
- HashJoinSpillControlImpl(BufferAllocator allocator, int recordsPerBatch, int
minBatchesInAvailableMemory, RecordBatchMemoryManager batchMemoryManager) {
+ HashJoinSpillControlImpl(BufferAllocator allocator, int recordsPerBatch, int
minBatchesInAvailableMemory, RecordBatchMemoryManager batchMemoryManager,
FragmentContext context) {
this.allocator = allocator;
this.recordsPerBatch = recordsPerBatch;
this.minBatchesInAvailableMemory = minBatchesInAvailableMemory;
this.batchMemoryManager = batchMemoryManager;
+ this.context = context;
}
@Override
- public boolean shouldSpill(VectorContainer currentVectorContainer) {
- assert currentVectorContainer.hasRecordCount();
- assert currentVectorContainer.getRecordCount() == recordsPerBatch;
- // Expected new batch size like the current, plus the Hash Value vector (4
bytes per HV)
- long batchSize = new
RecordBatchSizer(currentVectorContainer).getActualSize() + 4 * recordsPerBatch;
+ public boolean shouldSpill() {
+ // Expected new batch size like the current, plus the Hash Values vector
(4 bytes per HV)
+ long batchSize = (
batchMemoryManager.getRecordBatchSizer(RIGHT_INDEX).getRowAllocWidth() + 4 ) *
recordsPerBatch;
long reserveForOutgoing = batchMemoryManager.getOutputBatchSize();
long memoryAvailableNow = allocator.getLimit() -
allocator.getAllocatedMemory() - reserveForOutgoing;
boolean needsSpill = minBatchesInAvailableMemory * batchSize >
memoryAvailableNow;
+ if ( needsSpill ) {
+ logger.debug("should spill now - batch size {}, mem avail {}, reserved
for outgoing {}", batchSize, memoryAvailableNow, reserveForOutgoing);
+ }
return needsSpill; // go spill if too little memory is available
}
+ @Override
+ public void initialize(boolean firstCycle,
+ boolean reserveHash,
+ RecordBatch buildSideBatch,
+ RecordBatch probeSideBatch,
+ Set<String> joinColumns,
+ boolean probeEmpty,
+ long memoryAvailable,
+ int initialPartitions,
+ int recordsPerPartitionBatchBuild,
+ int recordsPerPartitionBatchProbe,
+ int maxBatchNumRecordsBuild,
+ int maxBatchNumRecordsProbe,
+ int outputBatchSize,
+ double loadFactor) {
+ this.initialPartitions = initialPartitions;
+ this.recordsPerPartitionBatchProbe = recordsPerPartitionBatchProbe;
+
+ calculateMemoryUsage();
+ }
+
+ @Override
+ public void setPartitionStatSet(HashJoinMemoryCalculator.PartitionStatSet
partitionStatSet) {
+ // Do nothing
Review comment:
I have added a method to HashTable called getActualSize() which checks the
memory used by the HashTable so we do not need to compute it.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
