Use binary doc values lz4 compressed

benchmarks/src/main/java/org/elasticsearch/benchmark/_nightly/esql/ValuesSourceReaderBenchmark.java

@@ -222,7 +222,8 @@ private static BlockLoader blockLoader(String name) {
                 Lucene.KEYWORD_ANALYZER,
                 Lucene.KEYWORD_ANALYZER,
                 new KeywordFieldMapper.Builder(name, IndexVersion.current()).docValues(ft.docValuesType() != DocValuesType.NONE),
-                syntheticSource
+                syntheticSource,
+                false
             ).blockLoader(new MappedFieldType.BlockLoaderContext() {
                 @Override
                 public String indexName() {

benchmarks/src/main/java/org/elasticsearch/benchmark/index/codec/tsdb/TSDBDocValuesMergeBenchmark.java

@@ -27,6 +27,7 @@
 import org.elasticsearch.cluster.metadata.DataStream;
 import org.elasticsearch.common.logging.LogConfigurator;
 import org.elasticsearch.index.codec.Elasticsearch92Lucene103Codec;
+import org.elasticsearch.index.codec.tsdb.BinaryDVCompressionMode;
 import org.elasticsearch.index.codec.tsdb.es819.ES819TSDBDocValuesFormat;
 import org.openjdk.jmh.annotations.Benchmark;
 import org.openjdk.jmh.annotations.BenchmarkMode;
@@ -257,7 +258,7 @@ private static IndexWriterConfig createIndexWriterConfig(boolean optimizedMergeE
         );
         config.setLeafSorter(DataStream.TIMESERIES_LEAF_READERS_SORTER);
         config.setMergePolicy(new LogByteSizeMergePolicy());
-        var docValuesFormat = new ES819TSDBDocValuesFormat(4096, 512, optimizedMergeEnabled);
+        var docValuesFormat = new ES819TSDBDocValuesFormat(4096, 512, optimizedMergeEnabled, BinaryDVCompressionMode.COMPRESSED_WITH_LZ4);
         config.setCodec(new Elasticsearch92Lucene103Codec() {
             @Override
             public DocValuesFormat getDocValuesFormatForField(String field) {

modules/mapper-extras/src/test/java/org/elasticsearch/index/mapper/extras/MatchOnlyTextFieldTypeTests.java

@@ -298,7 +298,8 @@ public void testBlockLoaderDoesNotUseSyntheticSourceDelegateWhenIgnoreAboveIsSet
             mock(NamedAnalyzer.class),
             mock(NamedAnalyzer.class),
             builder,
-            true
+            true,
+            false
         );
 
         MatchOnlyTextFieldMapper.MatchOnlyTextFieldType ft = new MatchOnlyTextFieldMapper.MatchOnlyTextFieldType(
@@ -346,7 +347,8 @@ public void testBlockLoaderDoesNotUseSyntheticSourceDelegateWhenIgnoreAboveIsSet
             mock(NamedAnalyzer.class),
             mock(NamedAnalyzer.class),
             builder,
-            true
+            true,
+            false
         );
 
         MatchOnlyTextFieldMapper.MatchOnlyTextFieldType ft = new MatchOnlyTextFieldMapper.MatchOnlyTextFieldType(

server/src/main/java/org/elasticsearch/common/settings/IndexScopedSettings.java

@@ -243,6 +243,7 @@ public final class IndexScopedSettings extends AbstractScopedSettings {
         if (IndexSettings.DOC_VALUES_SKIPPER) {
             settings.add(IndexSettings.USE_DOC_VALUES_SKIPPER);
         }
+        settings.add(IndexSettings.USE_BINARY_DOC_VALUES);
         settings.add(IndexSettings.INDEX_MAPPING_EXCLUDE_SOURCE_VECTORS_SETTING);
         BUILT_IN_INDEX_SETTINGS = Collections.unmodifiableSet(settings);
     };

server/src/main/java/org/elasticsearch/index/IndexSettings.java

@@ -675,6 +675,13 @@ public boolean isES87TSDBCodecEnabled() {
         Property.Final
     );
 
+    public static final Setting<Boolean> USE_BINARY_DOC_VALUES = Setting.boolSetting(
+        "index.mapping.use_binary_doc_values",
+        false,
+        Property.IndexScope,
+        Property.Final
+    );
+
     /**
      * The {@link IndexMode "mode"} of the index.
      */

server/src/main/java/org/elasticsearch/index/codec/PerFieldFormatSupplier.java

@@ -20,9 +20,11 @@
 import org.elasticsearch.index.IndexVersions;
 import org.elasticsearch.index.codec.bloomfilter.ES87BloomFilterPostingsFormat;
 import org.elasticsearch.index.codec.postings.ES812PostingsFormat;
+import org.elasticsearch.index.codec.tsdb.BinaryDVCompressionMode;
 import org.elasticsearch.index.codec.tsdb.es819.ES819TSDBDocValuesFormat;
 import org.elasticsearch.index.mapper.CompletionFieldMapper;
 import org.elasticsearch.index.mapper.IdFieldMapper;
+import org.elasticsearch.index.mapper.KeywordFieldMapper;
 import org.elasticsearch.index.mapper.Mapper;
 import org.elasticsearch.index.mapper.MapperService;
 import org.elasticsearch.index.mapper.SeqNoFieldMapper;
@@ -57,7 +59,10 @@ public class PerFieldFormatSupplier {
 
     private static final DocValuesFormat docValuesFormat = new Lucene90DocValuesFormat();
     private static final KnnVectorsFormat knnVectorsFormat = new Lucene99HnswVectorsFormat();
-    private static final ES819TSDBDocValuesFormat tsdbDocValuesFormat = new ES819TSDBDocValuesFormat();
+    private static final ES819TSDBDocValuesFormat tsdbDocValuesFormat = new ES819TSDBDocValuesFormat(BinaryDVCompressionMode.NO_COMPRESS);
+    private static final DocValuesFormat compressedBinaryDocValuesFormat = new ES819TSDBDocValuesFormat(
+        BinaryDVCompressionMode.COMPRESSED_WITH_LZ4
+    );
     private static final ES812PostingsFormat es812PostingsFormat = new ES812PostingsFormat();
     private static final PostingsFormat completionPostingsFormat = PostingsFormat.forName("Completion101");
 
@@ -127,6 +132,13 @@ public KnnVectorsFormat getKnnVectorsFormatForField(String field) {
     }
 
     public DocValuesFormat getDocValuesFormatForField(String field) {
+        if (mapperService != null) {
+            Mapper mapper = mapperService.mappingLookup().getMapper(field);
+            if (mapper != null && KeywordFieldMapper.CONTENT_TYPE.equals(mapper.typeName())) {
+                return compressedBinaryDocValuesFormat;
+            }
+        }
+
         if (useTSDBDocValuesFormat(field)) {
             return tsdbDocValuesFormat;
         }

server/src/main/java/org/elasticsearch/index/codec/tsdb/BinaryDVCompressionMode.java

@@ -0,0 +1,29 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the Elastic License
+ * 2.0 and the Server Side Public License, v 1; you may not use this file except
+ * in compliance with, at your election, the Elastic License 2.0 or the Server
+ * Side Public License, v 1.
+ */
+
+package org.elasticsearch.index.codec.tsdb;
+
+public enum BinaryDVCompressionMode {
+
+    NO_COMPRESS((byte) 0),
+    COMPRESSED_WITH_LZ4((byte) 1);
+
+    public final byte code;
+
+    BinaryDVCompressionMode(byte code) {
+        this.code = code;
+    }
+
+    public static BinaryDVCompressionMode fromMode(byte mode) {
+        return switch (mode) {
+            case 0 -> NO_COMPRESS;
+            case 1 -> COMPRESSED_WITH_LZ4;
+            default -> throw new IllegalStateException("unknown compression mode [" + mode + "]");
+        };
+    }
+}