ppadma commented on a change in pull request #1324: DRILL-6310: limit batch
size for hash aggregate
URL: https://github.com/apache/drill/pull/1324#discussion_r198910755
##########
File path:
exec/java-exec/src/main/java/org/apache/drill/exec/physical/impl/aggregate/HashAggBatch.java
##########
@@ -84,6 +97,63 @@
"htRowIdx" /* workspace index */, "incoming" /* read container */,
"outgoing" /* write container */,
"aggrValuesContainer" /* workspace container */, UPDATE_AGGR_INSIDE,
UPDATE_AGGR_OUTSIDE, UPDATE_AGGR_INSIDE);
+ public int getOutputRowCount() {
+ return hashAggMemoryManager.getOutputRowCount();
+ }
+
+ public RecordBatchMemoryManager getRecordBatchMemoryManager() {
+ return hashAggMemoryManager;
+ }
+
+ private class HashAggMemoryManager extends RecordBatchMemoryManager {
+ private int valuesRowWidth = 0;
+
+ HashAggMemoryManager(int outputBatchSize) {
+ super(outputBatchSize);
+ }
+
+ @Override
+ public void update() {
+ // Get sizing information for the batch.
+ setRecordBatchSizer(new RecordBatchSizer(incoming));
+
+ int fieldId = 0;
+ int newOutgoingRowWidth = 0;
+ for (VectorWrapper<?> w : container) {
+ if (w.getValueVector() instanceof FixedWidthVector) {
+ newOutgoingRowWidth += ((FixedWidthVector)
w.getValueVector()).getValueWidth();
+ if (fieldId >= numGroupByExprs) {
+ valuesRowWidth += ((FixedWidthVector)
w.getValueVector()).getValueWidth();
+ }
+ } else {
+ RecordBatchSizer.ColumnSize columnSize =
getRecordBatchSizer().getColumn(columnMapping.get(w.getValueVector().getField().getName()));
+ newOutgoingRowWidth += columnSize.getAllocSizePerEntry();
+ if (fieldId >= numGroupByExprs) {
+ valuesRowWidth += columnSize.getAllocSizePerEntry();
+ }
+ }
+ fieldId++;
+ }
+
+ updateIncomingStats();
+ if (logger.isDebugEnabled()) {
+ logger.debug("BATCH_STATS, incoming: {}", getRecordBatchSizer());
+ }
+
+ // We do not want to keep adjusting batch holders target row count
Review comment:
ok. made the change.
----------------------------------------------------------------
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:
us...@infra.apache.org
With regards,
Apache Git Services
