Fix terms aggregation doc_count_error_upper_bound for already reduced results (batched query phase)

server/src/internalClusterTest/java/org/elasticsearch/search/aggregations/bucket/TermsDocCountErrorIT.java

@@ -13,15 +13,12 @@
 import org.elasticsearch.action.search.SearchResponse;
 import org.elasticsearch.cluster.metadata.IndexMetadata;
 import org.elasticsearch.common.settings.Settings;
-import org.elasticsearch.search.SearchService;
 import org.elasticsearch.search.aggregations.Aggregator.SubAggCollectionMode;
 import org.elasticsearch.search.aggregations.BucketOrder;
 import org.elasticsearch.search.aggregations.bucket.terms.Terms;
 import org.elasticsearch.search.aggregations.bucket.terms.Terms.Bucket;
 import org.elasticsearch.search.aggregations.bucket.terms.TermsAggregatorFactory.ExecutionMode;
 import org.elasticsearch.test.ESIntegTestCase;
-import org.junit.After;
-import org.junit.Before;
 
 import java.io.IOException;
 import java.util.ArrayList;
@@ -53,18 +50,6 @@ public static String randomExecutionHint() {
 
     private static int numRoutingValues;
 
-    @Before
-    public void disableBatchedExecution() {
-        // TODO: it's practically impossible to get a 100% deterministic test with batched execution unfortunately, adjust this test to
-        // still do something useful with batched execution (i.e. use somewhat relaxed assertions)
-        updateClusterSettings(Settings.builder().put(SearchService.BATCHED_QUERY_PHASE.getKey(), false));
-    }
-
-    @After
-    public void resetSettings() {
-        updateClusterSettings(Settings.builder().putNull(SearchService.BATCHED_QUERY_PHASE.getKey()));
-    }
-
     @Override
     public void setupSuiteScopeCluster() throws Exception {
         assertAcked(indicesAdmin().prepareCreate("idx").setMapping(STRING_FIELD_NAME, "type=keyword").get());

server/src/main/java/org/elasticsearch/action/search/QueryPhaseResultConsumer.java

@@ -221,6 +221,7 @@ public SearchPhaseController.ReducedQueryPhase reduce() throws Exception {
             batchedResults = this.batchedResults;
         }
         final int resultSize = buffer.size() + (mergeResult == null ? 0 : 1) + batchedResults.size();
+        final boolean hasBatchedResults = batchedResults.isEmpty() == false;
         final List<TopDocs> topDocsList = hasTopDocs ? new ArrayList<>(resultSize) : null;
         final Deque<DelayableWriteable<InternalAggregations>> aggsList = hasAggs ? new ArrayDeque<>(resultSize) : null;
 
@@ -252,6 +253,10 @@ public SearchPhaseController.ReducedQueryPhase reduce() throws Exception {
             if (aggsList != null) {
                 // Add an estimate of the final reduce size
                 breakerSize = addEstimateAndMaybeBreak(estimateRamBytesUsedForReduce(circuitBreakerBytes));
+                AggregationReduceContext aggReduceContext = performFinalReduce
+                    ? aggReduceContextBuilder.forFinalReduction()
+                    : aggReduceContextBuilder.forPartialReduction();
+                aggReduceContext.setHasBatchedResult(hasBatchedResults);
                 aggs = aggregate(buffer.iterator(), new Iterator<>() {
                     @Override
                     public boolean hasNext() {
@@ -262,10 +267,7 @@ public boolean hasNext() {
                     public DelayableWriteable<InternalAggregations> next() {
                         return aggsList.pollFirst();
                     }
-                },
-                    resultSize,
-                    performFinalReduce ? aggReduceContextBuilder.forFinalReduction() : aggReduceContextBuilder.forPartialReduction()
-                );
+                }, resultSize, aggReduceContext);
             } else {
                 aggs = null;
             }

server/src/main/java/org/elasticsearch/search/aggregations/AggregationReduceContext.java

@@ -47,6 +47,7 @@ public interface Builder {
     @Nullable
     private final AggregationBuilder builder;
     private final AggregatorFactories.Builder subBuilders;
+    private boolean hasBatchedResult;
 
     private AggregationReduceContext(
         BigArrays bigArrays,
@@ -136,6 +137,14 @@ public final AggregationReduceContext forAgg(String name) {
 
     protected abstract AggregationReduceContext forSubAgg(AggregationBuilder sub);
 
+    public boolean hasBatchedResult() {
+        return hasBatchedResult;
+    }
+
+    public void setHasBatchedResult(boolean hasBatchedResult) {
+        this.hasBatchedResult = hasBatchedResult;
+    }
+
     /**
      * A {@linkplain AggregationReduceContext} to perform a partial reduction.
      */
@@ -234,7 +243,9 @@ public PipelineTree pipelineTreeRoot() {
 
         @Override
         protected AggregationReduceContext forSubAgg(AggregationBuilder sub) {
-            return new ForFinal(bigArrays(), scriptService(), isCanceled(), sub, multiBucketConsumer, pipelineTreeRoot);
+            ForFinal subContext = new ForFinal(bigArrays(), scriptService(), isCanceled(), sub, multiBucketConsumer, pipelineTreeRoot);
+            subContext.setHasBatchedResult(hasBatchedResult());
+            return subContext;
         }
     }
 }

server/src/main/java/org/elasticsearch/search/aggregations/bucket/terms/AbstractInternalTerms.java

@@ -332,7 +332,10 @@ public InternalAggregation get() {
             }
             long docCountError = -1;
             if (sumDocCountError != -1) {
-                docCountError = size == 1 ? 0 : sumDocCountError;
+                // If we are reducing only one aggregation (size == 1), the doc count error should be 0.
+                // However, the presence of a batched query result implies a partial reduction with size > 1
+                // has already occurred on a data node. The doc count error should not be 0 in this case.
+                docCountError = size == 1 && reduceContext.hasBatchedResult() == false ? 0 : sumDocCountError;
             }
             return create(name, result, reduceContext.isFinalReduce() ? getOrder() : thisReduceOrder, docCountError, otherDocCount);
         }