Apply the date histogram rewrite optimization to range aggregation (#…

…13865) (#14463) * Refactor the ranges representation * Refactor try fast filter * Main work finished; left the handling of different numeric data types * buildRanges accepts field type * first working draft probably * add change log * accommodate geo distance agg * Fix test support all numeric types minus one on the upper range * [Refactor] range is lower inclusive, right exclusive * adding test * Adding test and refactor * refactor * add test * add test and update the compare logic in tree traversal * fix test, add random test * refactor to address comments * small potential performance update * fix precommit * refactor * refactor * set refresh_interval to -1 * address comment * address comment * address comment * Fix test To understand fully about the double and bigdecimal usage in scaled float field will take more time. --------- (cherry picked from commit 57fb50b) Signed-off-by: bowenlan-amzn <[email protected]> Signed-off-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
opensearch-project · Jun 20, 2024 · e41162f · e41162f
1 parent be53dde
commit e41162f
Show file tree

Hide file tree

Showing 17 changed files with 902 additions and 232 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 ### Added
 - Add fingerprint ingest processor ([#13724](https://github.com/opensearch-project/OpenSearch/pull/13724))
 - [Remote Store] Rate limiter for remote store low priority uploads ([#14374](https://github.com/opensearch-project/OpenSearch/pull/14374/))
+- Apply the date histogram rewrite optimization to range aggregation ([#13865](https://github.com/opensearch-project/OpenSearch/pull/13865))
 
 ### Dependencies
 - Update to Apache Lucene 9.11.0 ([#14042](https://github.com/opensearch-project/OpenSearch/pull/14042))

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
@@ -35,6 +35,7 @@
 import com.fasterxml.jackson.core.JsonParseException;
 
 import org.apache.lucene.document.Field;
+import org.apache.lucene.document.LongPoint;
 import org.apache.lucene.index.DocValues;
 import org.apache.lucene.index.LeafReaderContext;
 import org.apache.lucene.index.NumericDocValues;
@@ -165,7 +166,7 @@ public ScaledFloatFieldMapper build(BuilderContext context) {
 
     public static final TypeParser PARSER = new TypeParser((n, c) -> new Builder(n, c.getSettings()));
 
-    public static final class ScaledFloatFieldType extends SimpleMappedFieldType {
+    public static final class ScaledFloatFieldType extends SimpleMappedFieldType implements NumericPointEncoder {
 
         private final double scalingFactor;
         private final Double nullValue;
@@ -188,6 +189,21 @@ public ScaledFloatFieldType(String name, double scalingFactor) {
             this(name, true, false, true, Collections.emptyMap(), scalingFactor, null);
         }
 
+        @Override
+        public byte[] encodePoint(Number value) {
+            assert value instanceof Double;
+            double doubleValue = (Double) value;
+            byte[] point = new byte[Long.BYTES];
+            if (doubleValue == Double.POSITIVE_INFINITY) {
+                LongPoint.encodeDimension(Long.MAX_VALUE, point, 0);
+            } else if (doubleValue == Double.NEGATIVE_INFINITY) {
+                LongPoint.encodeDimension(Long.MIN_VALUE, point, 0);
+            } else {
+                LongPoint.encodeDimension(Math.round(scale(value)), point, 0);
+            }
+            return point;
+        }
+
         public double getScalingFactor() {
             return scalingFactor;
         }

diff --git a/rest-api-spec/src/main/resources/rest-api-spec/test/search.aggregation/40_range.yml b/rest-api-spec/src/main/resources/rest-api-spec/test/search.aggregation/40_range.yml
@@ -14,6 +14,9 @@ setup:
                 date:
                   type: date
                   format: epoch_second
+                scaled_field:
+                  type: scaled_float
+                  scaling_factor: 100
 
   - do:
       cluster.health:
@@ -528,3 +531,139 @@ setup:
   - is_false:  aggregations.unsigned_long_range.buckets.2.to
 
   - match: { aggregations.unsigned_long_range.buckets.2.doc_count: 0 }
+
+---
+"Double range profiler shows filter rewrite info":
+  - skip:
+      version: " - 2.99.99"
+      reason: debug info for filter rewrite added in 3.0.0 (to be backported to 2.15.0)
+
+  - do:
+      indices.create:
+        index: test_profile
+        body:
+          settings:
+            number_of_replicas: 0
+            refresh_interval: -1
+          mappings:
+            properties:
+              ip:
+                type: ip
+              double:
+                type: double
+              date:
+                type: date
+                format: epoch_second
+
+  - do:
+      bulk:
+        index: test_profile
+        refresh: true
+        body:
+          - '{"index": {}}'
+          - '{"double" : 42}'
+          - '{"index": {}}'
+          - '{"double" : 100}'
+          - '{"index": {}}'
+          - '{"double" : 50}'
+
+  - do:
+      search:
+        index: test_profile
+        body:
+          size: 0
+          profile: true
+          aggs:
+            double_range:
+              range:
+                field: double
+                ranges:
+                  - to: 50
+                  - from: 50
+                    to: 150
+                  - from: 150
+
+  - length: { aggregations.double_range.buckets: 3 }
+
+  - match: { aggregations.double_range.buckets.0.key: "*-50.0" }
+  - is_false: aggregations.double_range.buckets.0.from
+  - match: { aggregations.double_range.buckets.0.to: 50.0 }
+  - match: { aggregations.double_range.buckets.0.doc_count: 1 }
+  - match: { aggregations.double_range.buckets.1.key: "50.0-150.0" }
+  - match: { aggregations.double_range.buckets.1.from: 50.0 }
+  - match: { aggregations.double_range.buckets.1.to: 150.0 }
+  - match: { aggregations.double_range.buckets.1.doc_count: 2 }
+  - match: { aggregations.double_range.buckets.2.key: "150.0-*" }
+  - match: { aggregations.double_range.buckets.2.from: 150.0 }
+  - is_false:  aggregations.double_range.buckets.2.to
+  - match: { aggregations.double_range.buckets.2.doc_count: 0 }
+
+  - match: { profile.shards.0.aggregations.0.debug.optimized_segments: 1 }
+  - match: { profile.shards.0.aggregations.0.debug.unoptimized_segments: 0 }
+  - match: { profile.shards.0.aggregations.0.debug.leaf_visited: 1 }
+  - match: { profile.shards.0.aggregations.0.debug.inner_visited: 0 }
+
+---
+"Scaled Float Range Aggregation":
+  - do:
+      index:
+        index: test
+        id: 1
+        body: { "scaled_field": 1 }
+
+  - do:
+      index:
+        index: test
+        id: 2
+        body: { "scaled_field": 1.53 }
+
+  - do:
+      index:
+        index: test
+        id: 3
+        body: { "scaled_field": -2.1 }
+
+  - do:
+      index:
+        index: test
+        id: 4
+        body: { "scaled_field": 1.53 }
+
+  - do:
+      indices.refresh: { }
+
+  - do:
+      search:
+        index: test
+        body:
+          size: 0
+          aggs:
+            my_range:
+              range:
+                field: scaled_field
+                ranges:
+                  - to: 0
+                  - from: 0
+                    to: 1
+                  - from: 1
+                    to: 1.5
+                  - from: 1.5
+
+  - length: { aggregations.my_range.buckets: 4 }
+
+  - match: { aggregations.my_range.buckets.0.key: "*-0.0" }
+  - is_false: aggregations.my_range.buckets.0.from
+  - match: { aggregations.my_range.buckets.0.to: 0.0 }
+  - match: { aggregations.my_range.buckets.0.doc_count: 1 }
+  - match: { aggregations.my_range.buckets.1.key: "0.0-1.0" }
+  - match: { aggregations.my_range.buckets.1.from: 0.0 }
+  - match: { aggregations.my_range.buckets.1.to: 1.0 }
+  - match: { aggregations.my_range.buckets.1.doc_count: 0 }
+  - match: { aggregations.my_range.buckets.2.key: "1.0-1.5" }
+  - match: { aggregations.my_range.buckets.2.from: 1.0 }
+  - match: { aggregations.my_range.buckets.2.to: 1.5 }
+  - match: { aggregations.my_range.buckets.2.doc_count: 1 }
+  - match: { aggregations.my_range.buckets.3.key: "1.5-*" }
+  - match: { aggregations.my_range.buckets.3.from: 1.5 }
+  - is_false:  aggregations.my_range.buckets.3.to
+  - match: { aggregations.my_range.buckets.3.doc_count: 2 }
diff --git a/server/src/main/java/org/opensearch/index/mapper/DateFieldMapper.java b/server/src/main/java/org/opensearch/index/mapper/DateFieldMapper.java
@@ -353,7 +353,7 @@ public DateFieldMapper build(BuilderContext context) {
      *
      * @opensearch.internal
      */
-    public static final class DateFieldType extends MappedFieldType {
+    public static final class DateFieldType extends MappedFieldType implements NumericPointEncoder {
         protected final DateFormatter dateTimeFormatter;
         protected final DateMathParser dateMathParser;
         protected final Resolution resolution;
@@ -554,6 +554,13 @@ public static long parseToLong(
             return resolution.convert(dateParser.parse(BytesRefs.toString(value), now, roundUp, zone));
         }
 
+        @Override
+        public byte[] encodePoint(Number value) {
+            byte[] point = new byte[Long.BYTES];
+            LongPoint.encodeDimension(value.longValue(), point, 0);
+            return point;
+        }
+
         @Override
         public Query distanceFeatureQuery(Object origin, String pivot, float boost, QueryShardContext context) {
             failIfNotIndexedAndNoDocValues();