[GitHub] [iceberg] singhpk234 commented on a diff in pull request #6622: push down min/max/count to iceberg

["singhpk234 (via GitHub)" <gi...@apache.org>]

singhpk234 commented on code in PR #6622:
URL: https://github.com/apache/iceberg/pull/6622#discussion_r1088284287


##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/SparkScanBuilder.java:
##########
@@ -158,6 +182,141 @@ public Filter[] pushedFilters() {
     return pushedFilters;
   }
 
+  @Override
+  public boolean pushAggregation(Aggregation aggregation) {
+    if (!pushDownAggregate(aggregation)) {
+      return false;
+    }
+
+    AggregateEvaluator aggregateEvaluator;
+    try {
+      List<Expression> aggregates =
+          Arrays.stream(aggregation.aggregateExpressions())
+              .map(agg -> SparkAggregates.convert(agg))
+              .collect(Collectors.toList());
+      aggregateEvaluator = AggregateEvaluator.create(schema, aggregates);
+    } catch (Exception e) {
+      LOG.info("Can't push down aggregates: " + e.getMessage());
+      return false;
+    }
+
+    if (!metricsModeSupportsAggregatePushDown(aggregateEvaluator.aggregates())) {
+      LOG.info("The MetricsMode doesn't support aggregate push down.");
+      return false;
+    }
+
+    List<ManifestFile> manifests = getSnapshot().allManifests(table.io());
+
+    for (ManifestFile manifest : manifests) {
+      try (ManifestReader<DataFile> reader = ManifestFiles.read(manifest, table.io())) {
+        for (DataFile dataFile : reader) {
+          aggregateEvaluator.update(dataFile.copy());
+        }
+      } catch (IOException e) {
+        LOG.info("Can't push down aggregates: " + e.getMessage());
+        return false;
+      }
+    }
+
+    Object[] res = aggregateEvaluator.result();
+    applyDataTypeConversionIfNecessary(res);
+
+    List<Object> valuesInSparkInternalRow = java.util.Arrays.asList(res);
+    this.pushedAggregateRows = new InternalRow[1];
+    pushedAggregateRows[0] =
+        InternalRow.fromSeq(JavaConverters.asScalaBuffer(valuesInSparkInternalRow).toSeq());
+    pushedAggregateSchema =
+        SparkSchemaUtil.convert(new Schema(aggregateEvaluator.resultType().fields()));
+    return true;
+  }
+
+  private boolean pushDownAggregate(Aggregation aggregation) {
+    if (!(table instanceof BaseTable)) {
+      return false;
+    }
+
+    if (!readConf.aggregatePushDown()) {
+      return false;
+    }
+
+    Snapshot snapshot = getSnapshot();
+    if (snapshot == null) {
+      return false;
+    } else {
+      Map<String, String> map = snapshot.summary();
+      // if there are row-level deletes in current snapshot, the statics
+      // maybe changed, so disable push down aggregate.
+      if (Integer.parseInt(map.getOrDefault("total-position-deletes", "0")) > 0
+          || Integer.parseInt(map.getOrDefault("total-equality-deletes", "0")) > 0) {

Review Comment:
   [minor] can use PropertyUtil#propertyAsInt



##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/SparkScanBuilder.java:
##########
@@ -158,6 +182,130 @@ public Filter[] pushedFilters() {
     return pushedFilters;
   }
 
+  @Override
+  public boolean pushAggregation(Aggregation aggregation) {
+    if (!pushDownAggregate(aggregation)) {
+      return false;
+    }
+
+    AggregateEvaluator aggregateEvaluator;
+    try {
+      List<Expression> aggregates =
+          Arrays.stream(aggregation.aggregateExpressions())
+              .map(agg -> SparkAggregates.convert(agg))
+              .collect(Collectors.toList());
+      aggregateEvaluator = AggregateEvaluator.create(schema, aggregates);
+    } catch (Exception e) {
+      LOG.info("Can't push down aggregates: " + e.getMessage());
+      return false;
+    }
+
+    if (!metricsModeSupportsAggregatePushDown(aggregateEvaluator.aggregates())) {
+      LOG.info("The MetricsMode doesn't support aggregate push down.");
+      return false;
+    }
+
+    List<ManifestFile> manifests = table.currentSnapshot().allManifests(table.io());
+
+    for (ManifestFile manifest : manifests) {
+      try (ManifestReader<DataFile> reader = ManifestFiles.read(manifest, table.io())) {
+        for (DataFile dataFile : reader) {
+          aggregateEvaluator.update(dataFile.copy());
+        }
+      } catch (IOException e) {
+        LOG.info("Can't push down aggregates: " + e.getMessage());
+        return false;
+      }
+    }

Review Comment:
   [doubt] can we parallelize reading the manifests here ? 



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org