Fixes Numeric exact match queries to use range queries internally (op…

…ensearch-project#11209) * Updating numeric term and terms queries to use IODVQ Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Addressing comments Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Fix formatting Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Fix changelog Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Addressing more comments + adding tests Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * renaming yaml test Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Adding skip for bwc Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Adding new SortedUnsignedLongDocValuesSetQuery to allow for BitInteger Terms query Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Fixing some tests Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Remove duplicate skip Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Remove unused points declaration Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Change unsigned exact query to be consistent Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Use slowExactQuery from Unsigned Set Query Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Merging different yaml tests into a single test Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Updating test case for main Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Fix changelog Signed-off-by: Harsha Vamsi Kalluri <[email protected]> --------- Signed-off-by: Harsha Vamsi Kalluri <[email protected]>
harshavamsi · Jan 4, 2024 · 178a7a0 · 178a7a0
1 parent f647515
commit 178a7a0
Show file tree

Hide file tree

Showing 11 changed files with 1,795 additions and 131 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -176,6 +176,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 - Performance improvement for date histogram aggregations without sub-aggregations ([#11083](https://github.com/opensearch-project/OpenSearch/pull/11083))
 - Disable concurrent aggs for Diversified Sampler and Sampler aggs ([#11087](https://github.com/opensearch-project/OpenSearch/issues/11087))
 - Made leader/follower check timeout setting dynamic ([#10528](https://github.com/opensearch-project/OpenSearch/pull/10528))
+- Improved performance of numeric exact-match queries ([#11209](https://github.com/opensearch-project/OpenSearch/pull/11209))
 - Change error message when per shard document limit is breached ([#11312](https://github.com/opensearch-project/OpenSearch/pull/11312))
 - Improve boolean parsing performance ([#11308](https://github.com/opensearch-project/OpenSearch/pull/11308))
 - Interpret byte array as primitive using VarHandles ([#11362](https://github.com/opensearch-project/OpenSearch/pull/11362))

diff --git a/modules/mapper-extras/src/main/java/org/opensearch/index/mapper/ScaledFloatFieldMapper.java b/modules/mapper-extras/src/main/java/org/opensearch/index/mapper/ScaledFloatFieldMapper.java
@@ -199,9 +199,9 @@ public String typeName() {
 
         @Override
         public Query termQuery(Object value, QueryShardContext context) {
-            failIfNotIndexed();
+            failIfNotIndexedAndNoDocValues();
             long scaledValue = Math.round(scale(value));
-            Query query = NumberFieldMapper.NumberType.LONG.termQuery(name(), scaledValue);
+            Query query = NumberFieldMapper.NumberType.LONG.termQuery(name(), scaledValue, hasDocValues(), isSearchable());
             if (boost() != 1f) {
                 query = new BoostQuery(query, boost());
             }
@@ -210,13 +210,18 @@ public Query termQuery(Object value, QueryShardContext context) {
 
         @Override
         public Query termsQuery(List<?> values, QueryShardContext context) {
-            failIfNotIndexed();
+            failIfNotIndexedAndNoDocValues();
             List<Long> scaledValues = new ArrayList<>(values.size());
             for (Object value : values) {
                 long scaledValue = Math.round(scale(value));
                 scaledValues.add(scaledValue);
             }
-            Query query = NumberFieldMapper.NumberType.LONG.termsQuery(name(), Collections.unmodifiableList(scaledValues));
+            Query query = NumberFieldMapper.NumberType.LONG.termsQuery(
+                name(),
+                Collections.unmodifiableList(scaledValues),
+                hasDocValues(),
+                isSearchable()
+            );
             if (boost() != 1f) {
                 query = new BoostQuery(query, boost());
             }
@@ -225,7 +230,7 @@ public Query termsQuery(List<?> values, QueryShardContext context) {
 
         @Override
         public Query rangeQuery(Object lowerTerm, Object upperTerm, boolean includeLower, boolean includeUpper, QueryShardContext context) {
-            failIfNotIndexed();
+            failIfNotIndexedAndNoDocValues();
             Long lo = null;
             if (lowerTerm != null) {
                 double dValue = scale(lowerTerm);
@@ -242,7 +247,7 @@ public Query rangeQuery(Object lowerTerm, Object upperTerm, boolean includeLower
                 }
                 hi = Math.round(Math.floor(dValue));
             }
-            Query query = NumberFieldMapper.NumberType.LONG.rangeQuery(name(), lo, hi, true, true, hasDocValues(), context);
+            Query query = NumberFieldMapper.NumberType.LONG.rangeQuery(name(), lo, hi, true, true, hasDocValues(), isSearchable(), context);
             if (boost() != 1f) {
                 query = new BoostQuery(query, boost());
             }

diff --git a/...es/mapper-extras/src/test/java/org/opensearch/index/mapper/ScaledFloatFieldTypeTests.java b/...es/mapper-extras/src/test/java/org/opensearch/index/mapper/ScaledFloatFieldTypeTests.java
@@ -34,11 +34,13 @@
 
 import org.apache.lucene.document.Document;
 import org.apache.lucene.document.DoublePoint;
+import org.apache.lucene.document.LongField;
 import org.apache.lucene.document.LongPoint;
 import org.apache.lucene.document.SortedNumericDocValuesField;
 import org.apache.lucene.index.DirectoryReader;
 import org.apache.lucene.index.IndexWriter;
 import org.apache.lucene.index.IndexWriterConfig;
+import org.apache.lucene.search.IndexOrDocValuesQuery;
 import org.apache.lucene.search.IndexSearcher;
 import org.apache.lucene.search.Query;
 import org.apache.lucene.store.Directory;
@@ -63,7 +65,9 @@ public void testTermQuery() {
         );
         double value = (randomDouble() * 2 - 1) * 10000;
         long scaledValue = Math.round(value * ft.getScalingFactor());
-        assertEquals(LongPoint.newExactQuery("scaled_float", scaledValue), ft.termQuery(value, null));
+        Query dvQuery = SortedNumericDocValuesField.newSlowExactQuery("scaled_float", scaledValue);
+        Query query = new IndexOrDocValuesQuery(LongPoint.newExactQuery("scaled_float", scaledValue), dvQuery);
+        assertEquals(query, ft.termQuery(value, null));
     }
 
     public void testTermsQuery() {
@@ -75,7 +79,7 @@ public void testTermsQuery() {
         long scaledValue1 = Math.round(value1 * ft.getScalingFactor());
         double value2 = (randomDouble() * 2 - 1) * 10000;
         long scaledValue2 = Math.round(value2 * ft.getScalingFactor());
-        assertEquals(LongPoint.newSetQuery("scaled_float", scaledValue1, scaledValue2), ft.termsQuery(Arrays.asList(value1, value2), null));
+        assertEquals(LongField.newSetQuery("scaled_float", scaledValue1, scaledValue2), ft.termsQuery(Arrays.asList(value1, value2), null));
     }
 
     public void testRangeQuery() throws IOException {
@@ -112,7 +116,16 @@ public void testRangeQuery() throws IOException {
             Double u = randomBoolean() ? null : (randomDouble() * 2 - 1) * 10000;
             boolean includeLower = randomBoolean();
             boolean includeUpper = randomBoolean();
-            Query doubleQ = NumberFieldMapper.NumberType.DOUBLE.rangeQuery("double", l, u, includeLower, includeUpper, false, MOCK_QSC);
+            Query doubleQ = NumberFieldMapper.NumberType.DOUBLE.rangeQuery(
+                "double",
+                l,
+                u,
+                includeLower,
+                includeUpper,
+                false,
+                true,
+                MOCK_QSC
+            );
             Query scaledFloatQ = ft.rangeQuery(l, u, includeLower, includeUpper, MOCK_QSC);
             assertEquals(searcher.count(doubleQ), searcher.count(scaledFloatQ));
         }