Merge remote-tracking branch 'upstream/main' into ps250410-exposeMergeEvents

Author: pxsalehi

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

@@ -0,0 +1,78 @@
+/*
+ * 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", the "GNU Affero General Public License v3.0 only", 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", the "GNU Affero General Public
+ * License v3.0 only", or the "Server Side Public License, v 1".
+ */
+
+package org.elasticsearch.benchmark.vector;
+
+import org.apache.lucene.index.VectorSimilarityFunction;
+import org.elasticsearch.common.logging.LogConfigurator;
+import org.elasticsearch.index.codec.vectors.OptimizedScalarQuantizer;
+import org.openjdk.jmh.annotations.Benchmark;
+import org.openjdk.jmh.annotations.BenchmarkMode;
+import org.openjdk.jmh.annotations.Fork;
+import org.openjdk.jmh.annotations.Level;
+import org.openjdk.jmh.annotations.Measurement;
+import org.openjdk.jmh.annotations.Mode;
+import org.openjdk.jmh.annotations.OutputTimeUnit;
+import org.openjdk.jmh.annotations.Param;
+import org.openjdk.jmh.annotations.Scope;
+import org.openjdk.jmh.annotations.Setup;
+import org.openjdk.jmh.annotations.State;
+import org.openjdk.jmh.annotations.Warmup;
+
+import java.util.concurrent.ThreadLocalRandom;
+import java.util.concurrent.TimeUnit;
+
+@BenchmarkMode(Mode.Throughput)
+@OutputTimeUnit(TimeUnit.MILLISECONDS)
+@State(Scope.Benchmark)
+@Warmup(iterations = 3, time = 1)
+@Measurement(iterations = 5, time = 1)
+@Fork(value = 3)
+public class OptimizedScalarQuantizerBenchmark {
+    static {
+        LogConfigurator.configureESLogging(); // native access requires logging to be initialized
+    }
+    @Param({ "384", "702", "1024" })
+    int dims;
+
+    float[] vector;
+    float[] centroid;
+    byte[] destination;
+
+    @Param({ "1", "4", "7" })
+    byte bits;
+
+    OptimizedScalarQuantizer osq = new OptimizedScalarQuantizer(VectorSimilarityFunction.DOT_PRODUCT);
+
+    @Setup(Level.Iteration)
+    public void init() {
+        ThreadLocalRandom random = ThreadLocalRandom.current();
+        // random byte arrays for binary methods
+        destination = new byte[dims];
+        vector = new float[dims];
+        centroid = new float[dims];
+        for (int i = 0; i < dims; ++i) {
+            vector[i] = random.nextFloat();
+            centroid[i] = random.nextFloat();
+        }
+    }
+
+    @Benchmark
+    public byte[] scalar() {
+        osq.scalarQuantize(vector, destination, bits, centroid);
+        return destination;
+    }
+
+    @Benchmark
+    @Fork(jvmArgsPrepend = { "--add-modules=jdk.incubator.vector" })
+    public byte[] vector() {
+        osq.scalarQuantize(vector, destination, bits, centroid);
+        return destination;
+    }
+}

distribution/docker/build.gradle

@@ -590,7 +590,7 @@ for (final Architecture architecture : Architecture.values()) {
     }
     if(base == DockerBase.DEFAULT) {
       // Add additional docker hub specific context which we use solely for publishing to docker hub.
-      // At the moment it only differs in not labels added that we need for openshift certification
+      // At the moment it is exactly the same as the default context.
       addBuildDockerContextTask(architecture, base, 'DockerHubContext', "docker-hub-build-context")
     }
   }

distribution/docker/src/docker/Dockerfile.default

@@ -139,15 +139,13 @@ LABEL org.label-schema.build-date="${build_date}" \\
   org.opencontainers.image.vendor="Elastic" \\
   org.opencontainers.image.version="${version}"
 
-<% if (docker_context != 'docker-hub-build-context') { %>
 LABEL name="Elasticsearch" \\
   maintainer="[email protected]" \\
   vendor="Elastic" \\
   version="${version}" \\
   release="1" \\
   summary="Elasticsearch" \\
   description="You know, for search."
-<% } %>
 
 RUN mkdir /licenses && ln LICENSE.txt /licenses/LICENSE
 

docs/changelog/125570.yaml

@@ -0,0 +1,5 @@
+pr: 125570
+summary: ES|QL random sampling
+area: Machine Learning
+type: feature
+issues: []

docs/changelog/126990.yaml

@@ -0,0 +1,7 @@
+pr: 126990
+summary: "Fix: consider case sensitiveness differences in Windows/Unix-like filesystems\
+  \ for files entitlements"
+area: Infra/Core
+type: bug
+issues:
+ - 127047

docs/changelog/127118.yaml

@@ -0,0 +1,5 @@
+pr: 127118
+summary: Panama vector accelerated optimized scalar quantization
+area: Vector Search
+type: enhancement
+issues: []

docs/changelog/127267.yaml

@@ -0,0 +1,5 @@
+pr: 127267
+summary: Bypass competitive iteration in single filter bucket case
+area: "Aggregations"
+type: bug
+issues: [127262]

docs/reference/elasticsearch/index-settings/index-modules.md

@@ -49,39 +49,27 @@ $$$index-codec$$$ `index.codec`
 
 $$$index-mode-setting$$$ `index.mode`
 :   The `index.mode` setting is used to control settings applied in specific domains like ingestion of time series data or logs. Different mutually exclusive modes exist, which are used to apply settings or default values controlling indexing of documents, sorting and other parameters whose value affects indexing or query performance.
-
-```console
-PUT my-index-000001
-{
-  "settings": {
-    "index":{
-      "mode":"standard" <1>
-    }
-  }
-}
-```
-
-1. This index uses the `standard` index mode
-
-
-Index mode supports the following values:
-
-`null`
-:   Default value (same as `standard`).
-
-`standard`
-:   Standard indexing with default settings.
-
-`lookup`
-: Index that can be used for lookup joins in ES|QL. Limited to 1 shard.
-
-
-`time_series`
-:   *(data streams only)* Index mode optimized for storage of metrics. For more information, see [Time series index settings](time-series.md).
-
-`logsdb`
-:   *(data streams only)* Index mode optimized for [logs](docs-content://manage-data/data-store/data-streams/logs-data-stream.md).
-
+        
+        **Example**
+
+      ```console
+      PUT my-index-000001
+      {
+        "settings": {
+          "index":{
+            "mode":"standard" # This index uses the `standard` index mode
+          }
+        }
+      }
+      ```
+    **Supported values**
+
+    The `index.mode` setting supports the following values:
+       - `null`:   Default value (same as `standard`).
+       -  `standard`:   Standard indexing with default settings.
+       -  `lookup`: Index that can be used for [LOOKUP JOIN](/reference/query-languages/esql/esql-lookup-join.md) in ES|QL. Limited to 1 shard.
+       - `time_series`:   *(data streams only)* Index mode optimized for storage of metrics. For more information, see [Time series index settings](time-series.md).
+       - `logsdb`: *(data streams only)* Index mode optimized for [logs](docs-content://manage-data/data-store/data-streams/logs-data-stream.md).
 
 $$$routing-partition-size$$$ `index.routing_partition_size`
 :   The number of shards a custom routing value can go to. Defaults to 1 and can only be set at index creation time. This value must be less than the `index.number_of_routing_shards` unless the `index.number_of_routing_shards` value is also 1. for more details about how this setting is used, refer to [](/reference/elasticsearch/mapping-reference/mapping-routing-field.md#routing-index-partition).

libs/entitlement/src/main/java/org/elasticsearch/entitlement/runtime/policy/CaseInsensitiveComparison.java

@@ -0,0 +1,31 @@
+/*
+ * 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", the "GNU Affero General Public License v3.0 only", 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", the "GNU Affero General Public
+ * License v3.0 only", or the "Server Side Public License, v 1".
+ */
+
+package org.elasticsearch.entitlement.runtime.policy;
+
+class CaseInsensitiveComparison extends FileAccessTreeComparison {
+
+    CaseInsensitiveComparison(char separatorChar) {
+        super(CaseInsensitiveComparison::caseInsensitiveCharacterComparator, separatorChar);
+    }
+
+    private static int caseInsensitiveCharacterComparator(char c1, char c2) {
+        return Character.compare(Character.toLowerCase(c1), Character.toLowerCase(c2));
+    }
+
+    @Override
+    protected boolean pathStartsWith(String pathString, String pathPrefix) {
+        return pathString.regionMatches(true, 0, pathPrefix, 0, pathPrefix.length());
+    }
+
+    @Override
+    protected boolean pathsAreEqual(String path1, String path2) {
+        return path1.equalsIgnoreCase(path2);
+    }
+}

libs/entitlement/src/main/java/org/elasticsearch/entitlement/runtime/policy/CaseSensitiveComparison.java

@@ -0,0 +1,27 @@
+/*
+ * 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", the "GNU Affero General Public License v3.0 only", 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", the "GNU Affero General Public
+ * License v3.0 only", or the "Server Side Public License, v 1".
+ */
+
+package org.elasticsearch.entitlement.runtime.policy;
+
+class CaseSensitiveComparison extends FileAccessTreeComparison {
+
+    CaseSensitiveComparison(char separatorChar) {
+        super(Character::compare, separatorChar);
+    }
+
+    @Override
+    protected boolean pathStartsWith(String pathString, String pathPrefix) {
+        return pathString.startsWith(pathPrefix);
+    }
+
+    @Override
+    protected boolean pathsAreEqual(String path1, String path2) {
+        return path1.equals(path2);
+    }
+}