Merge remote-tracking branch 'upstream/main' into include_vectors_source_option

Author: jimczi

.buildkite/hooks/pre-command

@@ -94,6 +94,18 @@ if [[ "${USE_PROD_DOCKER_CREDENTIALS:-}" == "true" ]]; then
   fi
 fi
 
+if [[ "${USE_PERF_CREDENTIALS:-}" == "true" ]]; then
+  PERF_METRICS_HOST=$(vault read -field=es_host /secret/ci/elastic-elasticsearch/esbench-metics)
+  PERF_METRICS_INDEX="dummy-micro-benchmarks"
+  PERF_METRICS_USERNAME=$(vault read -field=es_username /secret/ci/elastic-elasticsearch/esbench-metics)
+  PERF_METRICS_PASSWORD=$(vault read -field=es_password /secret/ci/elastic-elasticsearch/esbench-metics)
+
+  export PERF_METRICS_HOST
+  export PERF_METRICS_INDEX
+  export PERF_METRICS_USERNAME
+  export PERF_METRICS_PASSWORD
+fi
+
 # Authenticate to the Docker Hub public read-only registry
 if which docker > /dev/null 2>&1; then
   DOCKERHUB_REGISTRY_USERNAME="$(vault read -field=username secret/ci/elastic-elasticsearch/docker_hub_public_ro_credentials)"

.buildkite/pipelines/intake.yml

@@ -56,7 +56,7 @@ steps:
         timeout_in_minutes: 300
         matrix:
           setup:
-            BWC_VERSION: ["8.17.7", "8.18.3", "8.19.0", "9.0.2", "9.1.0"]
+            BWC_VERSION: ["8.17.8", "8.18.3", "8.19.0", "9.0.3", "9.1.0"]
         agents:
           provider: gcp
           image: family/elasticsearch-ubuntu-2004

.buildkite/pipelines/periodic-micro-benchmarks.yml

@@ -2,6 +2,9 @@ steps:
   - label: periodic-micro-benchmarks
     command: |
       .ci/scripts/run-gradle.sh :benchmarks:run --args 'org.elasticsearch.benchmark._nightly -rf json -rff build/result.json'
+      .buildkite/scripts/index-micro-benchmark-results.sh
+    env:
+      USE_PERF_CREDENTIALS: "true"
     timeout_in_minutes: 300
     agents:
       provider: gcp

.buildkite/pipelines/periodic-packaging.yml

@@ -303,8 +303,8 @@ steps:
         env:
           BWC_VERSION: 8.16.6
 
-      - label: "{{matrix.image}} / 8.17.7 / packaging-tests-upgrade"
-        command: ./.ci/scripts/packaging-test.sh -Dbwc.checkout.align=true destructiveDistroUpgradeTest.v8.17.7
+      - label: "{{matrix.image}} / 8.17.8 / packaging-tests-upgrade"
+        command: ./.ci/scripts/packaging-test.sh -Dbwc.checkout.align=true destructiveDistroUpgradeTest.v8.17.8
         timeout_in_minutes: 300
         matrix:
           setup:
@@ -317,7 +317,7 @@ steps:
           machineType: custom-16-32768
           buildDirectory: /dev/shm/bk
         env:
-          BWC_VERSION: 8.17.7
+          BWC_VERSION: 8.17.8
 
       - label: "{{matrix.image}} / 8.18.3 / packaging-tests-upgrade"
         command: ./.ci/scripts/packaging-test.sh -Dbwc.checkout.align=true destructiveDistroUpgradeTest.v8.18.3
@@ -351,8 +351,8 @@ steps:
         env:
           BWC_VERSION: 8.19.0
 
-      - label: "{{matrix.image}} / 9.0.2 / packaging-tests-upgrade"
-        command: ./.ci/scripts/packaging-test.sh -Dbwc.checkout.align=true destructiveDistroUpgradeTest.v9.0.2
+      - label: "{{matrix.image}} / 9.0.3 / packaging-tests-upgrade"
+        command: ./.ci/scripts/packaging-test.sh -Dbwc.checkout.align=true destructiveDistroUpgradeTest.v9.0.3
         timeout_in_minutes: 300
         matrix:
           setup:
@@ -365,7 +365,7 @@ steps:
           machineType: custom-16-32768
           buildDirectory: /dev/shm/bk
         env:
-          BWC_VERSION: 9.0.2
+          BWC_VERSION: 9.0.3
 
       - label: "{{matrix.image}} / 9.1.0 / packaging-tests-upgrade"
         command: ./.ci/scripts/packaging-test.sh -Dbwc.checkout.align=true destructiveDistroUpgradeTest.v9.1.0

.buildkite/pipelines/periodic.yml

@@ -325,8 +325,8 @@ steps:
             - signal_reason: agent_stop
               limit: 3
 
-      - label: 8.17.7 / bwc
-        command: .ci/scripts/run-gradle.sh -Dbwc.checkout.align=true v8.17.7#bwcTest
+      - label: 8.17.8 / bwc
+        command: .ci/scripts/run-gradle.sh -Dbwc.checkout.align=true v8.17.8#bwcTest
         timeout_in_minutes: 300
         agents:
           provider: gcp
@@ -335,7 +335,7 @@ steps:
           buildDirectory: /dev/shm/bk
           preemptible: true
         env:
-          BWC_VERSION: 8.17.7
+          BWC_VERSION: 8.17.8
         retry:
           automatic:
             - exit_status: "-1"
@@ -382,8 +382,8 @@ steps:
             - signal_reason: agent_stop
               limit: 3
 
-      - label: 9.0.2 / bwc
-        command: .ci/scripts/run-gradle.sh -Dbwc.checkout.align=true v9.0.2#bwcTest
+      - label: 9.0.3 / bwc
+        command: .ci/scripts/run-gradle.sh -Dbwc.checkout.align=true v9.0.3#bwcTest
         timeout_in_minutes: 300
         agents:
           provider: gcp
@@ -392,7 +392,7 @@ steps:
           buildDirectory: /dev/shm/bk
           preemptible: true
         env:
-          BWC_VERSION: 9.0.2
+          BWC_VERSION: 9.0.3
         retry:
           automatic:
             - exit_status: "-1"
@@ -486,7 +486,7 @@ steps:
           setup:
             ES_RUNTIME_JAVA:
               - openjdk21
-            BWC_VERSION: ["8.17.7", "8.18.3", "8.19.0", "9.0.2", "9.1.0"]
+            BWC_VERSION: ["8.17.8", "8.18.3", "8.19.0", "9.0.3", "9.1.0"]
         agents:
           provider: gcp
           image: family/elasticsearch-ubuntu-2004
@@ -529,7 +529,7 @@ steps:
             ES_RUNTIME_JAVA:
               - openjdk21
               - openjdk23
-            BWC_VERSION: ["8.17.7", "8.18.3", "8.19.0", "9.0.2", "9.1.0"]
+            BWC_VERSION: ["8.17.8", "8.18.3", "8.19.0", "9.0.3", "9.1.0"]
         agents:
           provider: gcp
           image: family/elasticsearch-ubuntu-2004

.buildkite/scripts/index-micro-benchmark-results.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+jq -c '.[]' "benchmarks/build/result.json" | while read -r doc; do
+  doc=$(echo "$doc" | jq --argjson timestamp "$(date +%s000)" '. + {"@timestamp": $timestamp}')
+  echo "Indexing $(echo "$doc" | jq -r '.benchmark')"
+  curl -s -X POST "https://$PERF_METRICS_HOST/$PERF_METRICS_INDEX/_doc" \
+    -u "$PERF_METRICS_USERNAME:$PERF_METRICS_PASSWORD" \
+    -H 'Content-Type: application/json' \
+    -d "$doc"
+done

.ci/bwcVersions

@@ -16,8 +16,8 @@ BWC_VERSION:
   - "8.14.3"
   - "8.15.5"
   - "8.16.6"
-  - "8.17.7"
+  - "8.17.8"
   - "8.18.3"
   - "8.19.0"
-  - "9.0.2"
+  - "9.0.3"
   - "9.1.0"

.ci/snapshotBwcVersions

@@ -1,6 +1,6 @@
 BWC_VERSION:
-  - "8.17.7"
+  - "8.17.8"
   - "8.18.3"
   - "8.19.0"
-  - "9.0.2"
+  - "9.0.3"
   - "9.1.0"

benchmarks/src/main/java/org/elasticsearch/benchmark/search/query/range/DateFieldMapperDocValuesSkipperBenchmark.java

@@ -21,14 +21,14 @@
 import org.apache.lucene.index.IndexWriterConfig;
 import org.apache.lucene.search.IndexOrDocValuesQuery;
 import org.apache.lucene.search.IndexSearcher;
-import org.apache.lucene.search.IndexSortSortedNumericDocValuesRangeQuery;
 import org.apache.lucene.search.Query;
 import org.apache.lucene.search.Sort;
 import org.apache.lucene.search.SortField;
 import org.apache.lucene.search.SortedNumericSortField;
 import org.apache.lucene.store.Directory;
 import org.apache.lucene.store.FSDirectory;
 import org.apache.lucene.util.BytesRef;
+import org.elasticsearch.lucene.search.XIndexSortSortedNumericDocValuesRangeQuery;
 import org.openjdk.jmh.annotations.Benchmark;
 import org.openjdk.jmh.annotations.BenchmarkMode;
 import org.openjdk.jmh.annotations.Fork;
@@ -295,7 +295,7 @@ public void rangeQueryWithDocValuesSkipper(final Blackhole bh) throws IOExceptio
     /**
      * Runs the actual Lucene range query, optionally combining a {@link LongPoint} index query
      * with doc values ({@link SortedNumericDocValuesField}) via {@link IndexOrDocValuesQuery},
-     * and then wrapping it with an {@link IndexSortSortedNumericDocValuesRangeQuery} to utilize the index sort.
+     * and then wrapping it with an {@link XIndexSortSortedNumericDocValuesRangeQuery} to utilize the index sort.
      *
      * @param searcher            the Lucene {@link IndexSearcher}
      * @param rangeStartTimestamp lower bound of the timestamp range
@@ -316,7 +316,7 @@ private long rangeQuery(final IndexSearcher searcher, long rangeStartTimestamp,
             )
             : SortedNumericDocValuesField.newSlowRangeQuery(TIMESTAMP_FIELD, rangeStartTimestamp, rangeEndTimestamp);
 
-        final Query query = new IndexSortSortedNumericDocValuesRangeQuery(
+        final Query query = new XIndexSortSortedNumericDocValuesRangeQuery(
             TIMESTAMP_FIELD,
             rangeStartTimestamp,
             rangeEndTimestamp,

benchmarks/src/main/java/org/elasticsearch/benchmark/xcontent/OptimizedTextBenchmark.java

@@ -0,0 +1,108 @@
+/*
+ * 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.xcontent;
+
+import org.elasticsearch.benchmark.index.mapper.MapperServiceFactory;
+import org.elasticsearch.common.UUIDs;
+import org.elasticsearch.common.bytes.BytesReference;
+import org.elasticsearch.common.logging.LogConfigurator;
+import org.elasticsearch.index.mapper.MapperService;
+import org.elasticsearch.index.mapper.SourceToParse;
+import org.elasticsearch.xcontent.XContentBuilder;
+import org.elasticsearch.xcontent.XContentFactory;
+import org.elasticsearch.xcontent.XContentType;
+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.Threads;
+import org.openjdk.jmh.annotations.Warmup;
+import org.openjdk.jmh.infra.Blackhole;
+
+import java.io.IOException;
+import java.util.Random;
+import java.util.concurrent.TimeUnit;
+
+/**
+ * Benchmark to measure indexing performance of keyword fields. Used to measure performance impact of skipping
+ * UTF-8 to UTF-16 conversion during document parsing.
+ */
+@BenchmarkMode(Mode.AverageTime)
+@OutputTimeUnit(TimeUnit.MILLISECONDS)
+@State(Scope.Benchmark)
+@Fork(1)
+@Threads(1)
+@Warmup(iterations = 1)
+@Measurement(iterations = 5)
+public class OptimizedTextBenchmark {
+    static {
+        // For Elasticsearch900Lucene101Codec:
+        LogConfigurator.loadLog4jPlugins();
+        LogConfigurator.configureESLogging();
+        LogConfigurator.setNodeName("test");
+    }
+
+    /**
+     * Total number of documents to index.
+     */
+    @Param("1048576")
+    private int nDocs;
+
+    private MapperService mapperService;
+    private SourceToParse[] sources;
+
+    private String randomValue(int length) {
+        final String CHARS = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789";
+        Random random = new Random();
+        StringBuilder builder = new StringBuilder(length);
+        for (int i = 0; i < length; i++) {
+            builder.append(CHARS.charAt(random.nextInt(CHARS.length())));
+        }
+        return builder.toString();
+    }
+
+    @Setup(Level.Trial)
+    public void setup() throws IOException {
+        mapperService = MapperServiceFactory.create("""
+            {
+                "_doc": {
+                    "dynamic": false,
+                    "properties": {
+                        "field": {
+                            "type": "keyword"
+                        }
+                    }
+                }
+            }
+            """);
+
+        sources = new SourceToParse[nDocs];
+        for (int i = 0; i < nDocs; i++) {
+            XContentBuilder b = XContentFactory.jsonBuilder();
+            b.startObject().field("field", randomValue(8)).endObject();
+            sources[i] = new SourceToParse(UUIDs.randomBase64UUID(), BytesReference.bytes(b), XContentType.JSON);
+        }
+    }
+
+    @Benchmark
+    public void indexDocuments(final Blackhole bh) {
+        final var mapper = mapperService.documentMapper();
+        for (int i = 0; i < nDocs; i++) {
+            bh.consume(mapper.parse(sources[i]));
+        }
+    }
+}