Merge branch 'main' into cleanup_semantic_text

Author: ioanatia

.buildkite/pipelines/intake.yml

@@ -56,7 +56,7 @@ steps:
         timeout_in_minutes: 300
         matrix:
           setup:
-            BWC_VERSION: ["8.16.6", "8.17.4", "8.18.0", "8.19.0", "9.0.0", "9.1.0"]
+            BWC_VERSION: ["8.16.7", "8.17.5", "8.18.0", "8.19.0", "9.0.0", "9.1.0"]
         agents:
           provider: gcp
           image: family/elasticsearch-ubuntu-2004

.buildkite/pipelines/periodic-packaging.yml

@@ -287,8 +287,8 @@ steps:
         env:
           BWC_VERSION: 8.15.5
 
-      - label: "{{matrix.image}} / 8.16.6 / packaging-tests-upgrade"
-        command: ./.ci/scripts/packaging-test.sh -Dbwc.checkout.align=true destructiveDistroUpgradeTest.v8.16.6
+      - label: "{{matrix.image}} / 8.16.7 / packaging-tests-upgrade"
+        command: ./.ci/scripts/packaging-test.sh -Dbwc.checkout.align=true destructiveDistroUpgradeTest.v8.16.7
         timeout_in_minutes: 300
         matrix:
           setup:
@@ -301,10 +301,10 @@ steps:
           machineType: custom-16-32768
           buildDirectory: /dev/shm/bk
         env:
-          BWC_VERSION: 8.16.6
+          BWC_VERSION: 8.16.7
 
-      - label: "{{matrix.image}} / 8.17.4 / packaging-tests-upgrade"
-        command: ./.ci/scripts/packaging-test.sh -Dbwc.checkout.align=true destructiveDistroUpgradeTest.v8.17.4
+      - label: "{{matrix.image}} / 8.17.5 / packaging-tests-upgrade"
+        command: ./.ci/scripts/packaging-test.sh -Dbwc.checkout.align=true destructiveDistroUpgradeTest.v8.17.5
         timeout_in_minutes: 300
         matrix:
           setup:
@@ -317,7 +317,7 @@ steps:
           machineType: custom-16-32768
           buildDirectory: /dev/shm/bk
         env:
-          BWC_VERSION: 8.17.4
+          BWC_VERSION: 8.17.5
 
       - label: "{{matrix.image}} / 8.18.0 / packaging-tests-upgrade"
         command: ./.ci/scripts/packaging-test.sh -Dbwc.checkout.align=true destructiveDistroUpgradeTest.v8.18.0

.buildkite/pipelines/periodic.yml

@@ -306,8 +306,8 @@ steps:
             - signal_reason: agent_stop
               limit: 3
 
-      - label: 8.16.6 / bwc
-        command: .ci/scripts/run-gradle.sh -Dbwc.checkout.align=true v8.16.6#bwcTest
+      - label: 8.16.7 / bwc
+        command: .ci/scripts/run-gradle.sh -Dbwc.checkout.align=true v8.16.7#bwcTest
         timeout_in_minutes: 300
         agents:
           provider: gcp
@@ -316,7 +316,7 @@ steps:
           buildDirectory: /dev/shm/bk
           preemptible: true
         env:
-          BWC_VERSION: 8.16.6
+          BWC_VERSION: 8.16.7
         retry:
           automatic:
             - exit_status: "-1"
@@ -325,8 +325,8 @@ steps:
             - signal_reason: agent_stop
               limit: 3
 
-      - label: 8.17.4 / bwc
-        command: .ci/scripts/run-gradle.sh -Dbwc.checkout.align=true v8.17.4#bwcTest
+      - label: 8.17.5 / bwc
+        command: .ci/scripts/run-gradle.sh -Dbwc.checkout.align=true v8.17.5#bwcTest
         timeout_in_minutes: 300
         agents:
           provider: gcp
@@ -335,7 +335,7 @@ steps:
           buildDirectory: /dev/shm/bk
           preemptible: true
         env:
-          BWC_VERSION: 8.17.4
+          BWC_VERSION: 8.17.5
         retry:
           automatic:
             - exit_status: "-1"
@@ -486,7 +486,7 @@ steps:
           setup:
             ES_RUNTIME_JAVA:
               - openjdk21
-            BWC_VERSION: ["8.16.6", "8.17.4", "8.18.0", "8.19.0", "9.0.0", "9.1.0"]
+            BWC_VERSION: ["8.16.7", "8.17.5", "8.18.0", "8.19.0", "9.0.0", "9.1.0"]
         agents:
           provider: gcp
           image: family/elasticsearch-ubuntu-2004
@@ -533,7 +533,7 @@ steps:
             ES_RUNTIME_JAVA:
               - openjdk21
               - openjdk23
-            BWC_VERSION: ["8.16.6", "8.17.4", "8.18.0", "8.19.0", "9.0.0", "9.1.0"]
+            BWC_VERSION: ["8.16.7", "8.17.5", "8.18.0", "8.19.0", "9.0.0", "9.1.0"]
         agents:
           provider: gcp
           image: family/elasticsearch-ubuntu-2004

.ci/bwcVersions

@@ -15,8 +15,8 @@ BWC_VERSION:
   - "8.13.4"
   - "8.14.3"
   - "8.15.5"
-  - "8.16.6"
-  - "8.17.4"
+  - "8.16.7"
+  - "8.17.5"
   - "8.18.0"
   - "8.19.0"
   - "9.0.0"

.ci/snapshotBwcVersions

@@ -1,6 +1,6 @@
 BWC_VERSION:
-  - "8.16.6"
-  - "8.17.4"
+  - "8.16.7"
+  - "8.17.5"
   - "8.18.0"
   - "8.19.0"
   - "9.0.0"

benchmarks/src/main/java/org/elasticsearch/benchmark/vector/DistanceFunctionBenchmark.java

@@ -13,6 +13,8 @@
 import org.elasticsearch.common.logging.LogConfigurator;
 import org.elasticsearch.index.IndexVersion;
 import org.elasticsearch.script.field.vectors.BinaryDenseVector;
+import org.elasticsearch.script.field.vectors.BitBinaryDenseVector;
+import org.elasticsearch.script.field.vectors.BitKnnDenseVector;
 import org.elasticsearch.script.field.vectors.ByteBinaryDenseVector;
 import org.elasticsearch.script.field.vectors.ByteKnnDenseVector;
 import org.elasticsearch.script.field.vectors.DenseVector;
@@ -37,30 +39,30 @@
 import java.util.function.DoubleSupplier;
 
 /**
- * Various benchmarks for the distance functions
- * used by indexed and non-indexed vectors.
- * Parameters include element, dims, function, and type.
+ * Various benchmarks for the distance functions used by indexed and non-indexed vectors.
+ * Parameters include doc and query type, dims, function, and implementation.
  * For individual local tests it may be useful to increase
- * fork, measurement, and operations per invocation. (Note
- * to also update the benchmark loop if operations per invocation
- * is increased.)
+ * fork, measurement, and operations per invocation.
  */
 @Fork(1)
 @Warmup(iterations = 1)
 @Measurement(iterations = 2)
 @BenchmarkMode(Mode.AverageTime)
 @OutputTimeUnit(TimeUnit.NANOSECONDS)
-@OperationsPerInvocation(25000)
+@OperationsPerInvocation(DistanceFunctionBenchmark.OPERATIONS)
 @State(Scope.Benchmark)
 public class DistanceFunctionBenchmark {
 
+    public static final int OPERATIONS = 25000;
+
     static {
         LogConfigurator.configureESLogging();
     }
 
     public enum VectorType {
         FLOAT,
-        BYTE
+        BYTE,
+        BIT
     }
 
     public enum Function {
@@ -122,7 +124,7 @@ private static BytesRef generateVectorData(float[] vector) {
     }
 
     private static BytesRef generateVectorData(float[] vector, float mag) {
-        ByteBuffer buffer = ByteBuffer.allocate(vector.length * 4 + 4);
+        ByteBuffer buffer = ByteBuffer.allocate(vector.length * Float.BYTES + Float.BYTES);
         for (float f : vector) {
             buffer.putFloat(f);
         }
@@ -133,24 +135,29 @@ private static BytesRef generateVectorData(float[] vector, float mag) {
     private static BytesRef generateVectorData(byte[] vector) {
         float mag = calculateMag(vector);
 
-        ByteBuffer buffer = ByteBuffer.allocate(vector.length + 4);
+        ByteBuffer buffer = ByteBuffer.allocate(vector.length + Float.BYTES);
         buffer.put(vector);
         buffer.putFloat(mag);
         return new BytesRef(buffer.array());
     }
 
     @Setup
     public void findBenchmarkImpl() {
+        if (dims % 8 != 0) throw new IllegalArgumentException("Dims must be a multiple of 8");
         Random r = new Random();
 
         float[] floatDocVector = new float[dims];
         byte[] byteDocVector = new byte[dims];
+        byte[] bitDocVector = new byte[dims / 8];
 
         float[] floatQueryVector = new float[dims];
         byte[] byteQueryVector = new byte[dims];
+        byte[] bitQueryVector = new byte[dims / 8];
 
         r.nextBytes(byteDocVector);
+        r.nextBytes(bitDocVector);
         r.nextBytes(byteQueryVector);
+        r.nextBytes(bitQueryVector);
         for (int i = 0; i < dims; i++) {
             floatDocVector[i] = r.nextFloat();
             floatQueryVector[i] = r.nextFloat();
@@ -179,10 +186,11 @@ public void findBenchmarkImpl() {
             };
             case BYTE -> switch (type) {
                 case KNN -> new ByteKnnDenseVector(byteDocVector);
-                case BINARY -> {
-                    BytesRef vectorData = generateVectorData(byteDocVector);
-                    yield new ByteBinaryDenseVector(byteDocVector, vectorData, dims);
-                }
+                case BINARY -> new ByteBinaryDenseVector(byteDocVector, generateVectorData(byteDocVector), dims);
+            };
+            case BIT -> switch (type) {
+                case KNN -> new BitKnnDenseVector(bitDocVector);
+                case BINARY -> new BitBinaryDenseVector(bitDocVector, new BytesRef(bitDocVector), bitDocVector.length);
             };
         };
 
@@ -204,21 +212,28 @@ public void findBenchmarkImpl() {
                 case L2 -> () -> vectorImpl.l2Norm(byteQueryVector);
                 case HAMMING -> () -> vectorImpl.hamming(byteQueryVector);
             };
+            case BIT -> switch (function) {
+                case DOT -> () -> vectorImpl.dotProduct(bitQueryVector);
+                case COSINE -> throw new UnsupportedOperationException("Unsupported function " + function);
+                case L1 -> () -> vectorImpl.l1Norm(bitQueryVector);
+                case L2 -> () -> vectorImpl.l2Norm(bitQueryVector);
+                case HAMMING -> () -> vectorImpl.hamming(bitQueryVector);
+            };
         };
     }
 
     @Fork(1)
     @Benchmark
     public void benchmark(Blackhole blackhole) {
-        for (int i = 0; i < 25000; ++i) {
+        for (int i = 0; i < OPERATIONS; ++i) {
             blackhole.consume(benchmarkImpl.getAsDouble());
         }
     }
 
     @Fork(value = 1, jvmArgsPrepend = { "--add-modules=jdk.incubator.vector" })
     @Benchmark
     public void vectorBenchmark(Blackhole blackhole) {
-        for (int i = 0; i < 25000; ++i) {
+        for (int i = 0; i < OPERATIONS; ++i) {
             blackhole.consume(benchmarkImpl.getAsDouble());
         }
     }

build-tools-internal/src/main/java/org/elasticsearch/gradle/internal/RestrictedBuildApiService.java

@@ -61,7 +61,6 @@ private static ListMultimap<Class<?>, String> createLegacyRestTestBasePluginUsag
         map.put(LegacyRestTestBasePlugin.class, ":qa:smoke-test-ingest-with-all-dependencies");
         map.put(LegacyRestTestBasePlugin.class, ":qa:smoke-test-plugins");
         map.put(LegacyRestTestBasePlugin.class, ":qa:system-indices");
-        map.put(LegacyRestTestBasePlugin.class, ":qa:verify-version-constants");
         map.put(LegacyRestTestBasePlugin.class, ":test:external-modules:test-apm-integration");
         map.put(LegacyRestTestBasePlugin.class, ":test:external-modules:test-delayed-aggs");
         map.put(LegacyRestTestBasePlugin.class, ":test:external-modules:test-die-with-dignity");

docs/build.gradle

@@ -1,4 +1,5 @@
 import org.elasticsearch.gradle.Version
+import org.elasticsearch.gradle.VersionProperties
 import org.elasticsearch.gradle.internal.doc.DocSnippetTask
 import static org.elasticsearch.gradle.testclusters.TestDistribution.DEFAULT
 
@@ -2059,3 +2060,29 @@ setups['setup-snapshots'] = setups['setup-repository'] + '''
     setups['atomic_red_regsvr32'].replace('#atomic_red_data#', events)
   }
 }
+
+tasks.register('verifyDocsLuceneVersion') {
+  doFirst {
+    File docsVersionsFile = file('Versions.asciidoc')
+    List<String> versionLines = docsVersionsFile.readLines('UTF-8')
+    String docsLuceneVersion = null
+    for (String line : versionLines) {
+      if (line.startsWith(':lucene_version:')) {
+        docsLuceneVersion = line.split()[1]
+      }
+    }
+    if (docsLuceneVersion == null) {
+      throw new GradleException('Could not find lucene version in docs version file')
+    }
+    String expectedLuceneVersion = VersionProperties.lucene
+    // remove potential -snapshot-{gitrev} suffix
+    expectedLuceneVersion -= ~/-snapshot-[0-9a-f]+$/
+    if (docsLuceneVersion != expectedLuceneVersion) {
+      throw new GradleException("Lucene version in docs [${docsLuceneVersion}] does not match version.properties [${expectedLuceneVersion}]")
+    }
+  }
+}
+
+tasks.named('check') {
+  dependsOn 'verifyDocsLuceneVersion'
+}