Merge branch 'main' into semantic-text_index-options_license-tests

Author: elasticmachine

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

@@ -43,7 +43,8 @@ public class OptimizedScalarQuantizerBenchmark {
 
     float[] vector;
     float[] centroid;
-    byte[] destination;
+    byte[] legacyDestination;
+    int[] destination;
 
     @Param({ "1", "4", "7" })
     byte bits;
@@ -54,7 +55,8 @@ public class OptimizedScalarQuantizerBenchmark {
     public void init() {
         ThreadLocalRandom random = ThreadLocalRandom.current();
         // random byte arrays for binary methods
-        destination = new byte[dims];
+        legacyDestination = new byte[dims];
+        destination = new int[dims];
         vector = new float[dims];
         centroid = new float[dims];
         for (int i = 0; i < dims; ++i) {
@@ -65,13 +67,20 @@ public void init() {
 
     @Benchmark
     public byte[] scalar() {
-        osq.scalarQuantize(vector, destination, bits, centroid);
-        return destination;
+        osq.legacyScalarQuantize(vector, legacyDestination, bits, centroid);
+        return legacyDestination;
+    }
+
+    @Benchmark
+    @Fork(jvmArgsPrepend = { "--add-modules=jdk.incubator.vector" })
+    public byte[] legacyVector() {
+        osq.legacyScalarQuantize(vector, legacyDestination, bits, centroid);
+        return legacyDestination;
     }
 
     @Benchmark
     @Fork(jvmArgsPrepend = { "--add-modules=jdk.incubator.vector" })
-    public byte[] vector() {
+    public int[] vector() {
         osq.scalarQuantize(vector, destination, bits, centroid);
         return destination;
     }

docs/reference/query-languages/esql/images/functions/knn.svg

@@ -258,4 +258,25 @@ public static float soarDistance(float[] v1, float[] centroid, float[] originalR
         }
         return IMPL.soarDistance(v1, centroid, originalResidual, soarLambda, rnorm);
     }
+
+    /**
+     * Optimized-scalar quantization of the provided vector to the provided destination array.
+     *
+     * @param vector the vector to quantize
+     * @param destination the array to store the result
+     * @param lowInterval the minimum value, lower values in the original array will be replaced by this value
+     * @param upperInterval the maximum value, bigger values in the original array will be replaced by this value
+     * @param bit the number of bits to use for quantization, must be between 1 and 8
+     *
+     * @return return the sum of all the elements of the resulting quantized vector.
+     */
+    public static int quantizeVectorWithIntervals(float[] vector, int[] destination, float lowInterval, float upperInterval, byte bit) {
+        if (vector.length > destination.length) {
+            throw new IllegalArgumentException("vector dimensions differ: " + vector.length + "!=" + destination.length);
+        }
+        if (bit <= 0 || bit > Byte.SIZE) {
+            throw new IllegalArgumentException("bit must be between 1 and 8, but was: " + bit);
+        }
+        return IMPL.quantizeVectorWithIntervals(vector, destination, lowInterval, upperInterval, bit);
+    }
 }

docs/reference/query-languages/esql/kibana/definition/functions/knn.json

@@ -269,4 +269,18 @@ public static float ipFloatByteImpl(float[] q, byte[] d) {
         }
         return ret;
     }
+
+    @Override
+    public int quantizeVectorWithIntervals(float[] vector, int[] destination, float lowInterval, float upperInterval, byte bits) {
+        float nSteps = ((1 << bits) - 1);
+        float step = (upperInterval - lowInterval) / nSteps;
+        int sumQuery = 0;
+        for (int h = 0; h < vector.length; h++) {
+            float xi = Math.min(Math.max(vector[h], lowInterval), upperInterval);
+            int assignment = Math.round((xi - lowInterval) / step);
+            sumQuery += assignment;
+            destination[h] = assignment;
+        }
+        return sumQuery;
+    }
 }

docs/reference/query-languages/esql/kibana/docs/functions/knn.md

@@ -39,4 +39,6 @@ public interface ESVectorUtilSupport {
 
     float soarDistance(float[] v1, float[] centroid, float[] originalResidual, float soarLambda, float rnorm);
 
+    int quantizeVectorWithIntervals(float[] vector, int[] quantize, float lowInterval, float upperInterval, byte bit);
+
 }

libs/simdvec/src/main/java/org/elasticsearch/simdvec/ESVectorUtil.java

@@ -791,4 +791,32 @@ public static float ipFloatByteImpl(float[] q, byte[] d) {
 
         return sum;
     }
+
+    @Override
+    public int quantizeVectorWithIntervals(float[] vector, int[] destination, float lowInterval, float upperInterval, byte bits) {
+        float nSteps = ((1 << bits) - 1);
+        float step = (upperInterval - lowInterval) / nSteps;
+        int sumQuery = 0;
+        int i = 0;
+        if (vector.length > 2 * FLOAT_SPECIES.length()) {
+            int limit = FLOAT_SPECIES.loopBound(vector.length);
+            FloatVector lowVec = FloatVector.broadcast(FLOAT_SPECIES, lowInterval);
+            FloatVector upperVec = FloatVector.broadcast(FLOAT_SPECIES, upperInterval);
+            FloatVector stepVec = FloatVector.broadcast(FLOAT_SPECIES, step);
+            for (; i < limit; i += FLOAT_SPECIES.length()) {
+                FloatVector v = FloatVector.fromArray(FLOAT_SPECIES, vector, i);
+                FloatVector xi = v.max(lowVec).min(upperVec); // clamp
+                IntVector assignment = xi.sub(lowVec).div(stepVec).add(0.5f).convert(VectorOperators.F2I, 0).reinterpretAsInts(); // round
+                sumQuery += assignment.reduceLanes(ADD);
+                assignment.intoArray(destination, i);
+            }
+        }
+        for (; i < vector.length; i++) {
+            float xi = Math.min(Math.max(vector[i], lowInterval), upperInterval);
+            int assignment = Math.round((xi - lowInterval) / step);
+            sumQuery += assignment;
+            destination[i] = assignment;
+        }
+        return sumQuery;
+    }
 }

libs/simdvec/src/main/java/org/elasticsearch/simdvec/internal/vectorization/DefaultESVectorUtilSupport.java

@@ -286,6 +286,29 @@ public void testSoarDistance() {
         assertEquals(expected, result, deltaEps);
     }
 
+    public void testQuantizeVectorWithIntervals() {
+        int vectorSize = randomIntBetween(1, 2048);
+        float[] vector = new float[vectorSize];
+
+        byte bits = (byte) randomIntBetween(1, 8);
+        for (int i = 0; i < vectorSize; ++i) {
+            vector[i] = random().nextFloat();
+        }
+        float low = random().nextFloat();
+        float high = random().nextFloat();
+        if (low > high) {
+            float tmp = low;
+            low = high;
+            high = tmp;
+        }
+        int[] quantizeExpected = new int[vectorSize];
+        int[] quantizeResult = new int[vectorSize];
+        var expected = defaultedProvider.getVectorUtilSupport().quantizeVectorWithIntervals(vector, quantizeExpected, low, high, bits);
+        var result = defOrPanamaProvider.getVectorUtilSupport().quantizeVectorWithIntervals(vector, quantizeResult, low, high, bits);
+        assertArrayEquals(quantizeExpected, quantizeResult);
+        assertEquals(expected, result, 0f);
+    }
+
     void testIpByteBinImpl(ToLongBiFunction<byte[], byte[]> ipByteBinFunc) {
         int iterations = atLeast(50);
         for (int i = 0; i < iterations; i++) {

libs/simdvec/src/main/java/org/elasticsearch/simdvec/internal/vectorization/ESVectorUtilSupport.java

@@ -236,6 +236,9 @@ tests:
 - class: org.elasticsearch.packaging.test.DockerTests
   method: test012SecurityCanBeDisabled
   issue: https://github.com/elastic/elasticsearch/issues/116636
+- class: org.elasticsearch.index.shard.StoreRecoveryTests
+  method: testAddIndices
+  issue: https://github.com/elastic/elasticsearch/issues/124104
 - class: org.elasticsearch.smoketest.MlWithSecurityIT
   method: test {yaml=ml/data_frame_analytics_crud/Test get stats on newly created config}
   issue: https://github.com/elastic/elasticsearch/issues/121726
@@ -455,6 +458,12 @@ tests:
 - class: org.elasticsearch.packaging.test.DockerTests
   method: test073RunEsAsDifferentUserAndGroupWithoutBindMounting
   issue: https://github.com/elastic/elasticsearch/issues/128996
+- class: org.elasticsearch.upgrades.UpgradeClusterClientYamlTestSuiteIT
+  method: test {p0=upgraded_cluster/70_ilm/Test Lifecycle Still There And Indices Are Still Managed}
+  issue: https://github.com/elastic/elasticsearch/issues/129097
+- class: org.elasticsearch.upgrades.UpgradeClusterClientYamlTestSuiteIT
+  method: test {p0=upgraded_cluster/90_ml_data_frame_analytics_crud/Get mixed cluster outlier_detection job}
+  issue: https://github.com/elastic/elasticsearch/issues/129098
 - class: org.elasticsearch.packaging.test.DockerTests
   method: test081SymlinksAreFollowedWithEnvironmentVariableFiles
   issue: https://github.com/elastic/elasticsearch/issues/128867
@@ -473,21 +482,27 @@ tests:
 - class: org.elasticsearch.entitlement.runtime.policy.FileAccessTreeTests
   method: testWindowsAbsolutPathAccess
   issue: https://github.com/elastic/elasticsearch/issues/129168
-- class: org.elasticsearch.xpack.esql.qa.multi_node.EsqlSpecIT
-  method: test {knn-function.KnnSearchWithKOption ASYNC}
-  issue: https://github.com/elastic/elasticsearch/issues/129447
 - class: org.elasticsearch.xpack.ml.integration.ClassificationIT
   method: testWithDatastreams
   issue: https://github.com/elastic/elasticsearch/issues/129457
 - class: org.elasticsearch.index.engine.ThreadPoolMergeExecutorServiceDiskSpaceTests
   method: testMergeTasksAreUnblockedWhenMoreDiskSpaceBecomesAvailable
   issue: https://github.com/elastic/elasticsearch/issues/129296
+- class: org.elasticsearch.xpack.security.PermissionsIT
+  method: testCanManageIndexWithNoPermissions
+  issue: https://github.com/elastic/elasticsearch/issues/129471
+- class: org.elasticsearch.xpack.security.PermissionsIT
+  method: testCanManageIndexAndPolicyDifferentUsers
+  issue: https://github.com/elastic/elasticsearch/issues/129479
+- class: org.elasticsearch.xpack.security.PermissionsIT
+  method: testCanViewExplainOnUnmanagedIndex
+  issue: https://github.com/elastic/elasticsearch/issues/129480
 - class: org.elasticsearch.xpack.profiling.action.GetStatusActionIT
   method: testWaitsUntilResourcesAreCreated
   issue: https://github.com/elastic/elasticsearch/issues/129486
-- class: org.elasticsearch.xpack.esql.qa.multi_node.EsqlSpecIT
-  method: test {knn-function.KnnSearchWithKOption SYNC}
-  issue: https://github.com/elastic/elasticsearch/issues/129512
+- class: org.elasticsearch.xpack.security.PermissionsIT
+  method: testWhenUserLimitedByOnlyAliasOfIndexCanWriteToIndexWhichWasRolledoverByILMPolicy
+  issue: https://github.com/elastic/elasticsearch/issues/129481
 - class: org.elasticsearch.index.engine.ThreadPoolMergeExecutorServiceTests
   method: testIORateIsAdjustedForAllRunningMergeTasks
   issue: https://github.com/elastic/elasticsearch/issues/129531
@@ -503,15 +518,24 @@ tests:
 - class: org.elasticsearch.search.query.VectorIT
   method: testFilteredQueryStrategy
   issue: https://github.com/elastic/elasticsearch/issues/129517
+- class: org.elasticsearch.snapshots.SnapshotShutdownIT
+  method: testSnapshotShutdownProgressTracker
+  issue: https://github.com/elastic/elasticsearch/issues/129752
 - class: org.elasticsearch.xpack.security.SecurityRolesMultiProjectIT
   method: testUpdatingFileBasedRoleAffectsAllProjects
   issue: https://github.com/elastic/elasticsearch/issues/129775
 - class: org.elasticsearch.qa.verify_version_constants.VerifyVersionConstantsIT
   method: testLuceneVersionConstant
   issue: https://github.com/elastic/elasticsearch/issues/125638
+- class: org.elasticsearch.index.store.FsDirectoryFactoryTests
+  method: testPreload
+  issue: https://github.com/elastic/elasticsearch/issues/129852
 - class: org.elasticsearch.xpack.rank.rrf.RRFRankClientYamlTestSuiteIT
   method: test {yaml=rrf/950_pinned_interaction/rrf with pinned retriever as a sub-retriever}
   issue: https://github.com/elastic/elasticsearch/issues/129845
+- class: org.elasticsearch.xpack.test.rest.XPackRestIT
+  method: test {p0=esql/60_usage/Basic ESQL usage output (telemetry) non-snapshot version}
+  issue: https://github.com/elastic/elasticsearch/issues/129888
 - class: org.elasticsearch.gradle.internal.InternalDistributionBwcSetupPluginFuncTest
   method: "builds distribution from branches via archives extractedAssemble [bwcDistVersion: 8.2.1, bwcProject: bugfix, expectedAssembleTaskName:
     extractedAssemble, #2]"
@@ -525,9 +549,14 @@ tests:
 - class: org.elasticsearch.xpack.esql.qa.multi_node.GenerativeIT
   method: test
   issue: https://github.com/elastic/elasticsearch/issues/130067
+- class: geoip.GeoIpMultiProjectIT
+  issue: https://github.com/elastic/elasticsearch/issues/130073
 - class: org.elasticsearch.xpack.esql.qa.single_node.GenerativeIT
   method: test
   issue: https://github.com/elastic/elasticsearch/issues/130067
+- class: org.elasticsearch.xpack.esql.action.EnrichIT
+  method: testTopN
+  issue: https://github.com/elastic/elasticsearch/issues/130122
 - class: org.elasticsearch.action.support.ThreadedActionListenerTests
   method: testRejectionHandling
   issue: https://github.com/elastic/elasticsearch/issues/130129