Skip to content

Use Lucene101 postings format by default #126080

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 11 commits into from
Apr 4, 2025
Merged

Use Lucene101 postings format by default #126080

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
994b83a
Use lucene 10.1 postings format in some cases
jordan-powers Apr 1, 2025
0b3e039
Enable lucene postings format feature flag for rest tests
jordan-powers Apr 1, 2025
2495aaa
Check feature flag in PerFieldMapperCodecTests
jordan-powers Apr 2, 2025
c642fb7
Merge remote-tracking branch 'upstream/main' into use-lucene-postings…
jordan-powers Apr 2, 2025
2637976
Remove USE_LUCENE101_POSTINGS_FORMAT index version
jordan-powers Apr 2, 2025
91f7ea8
Merge remote-tracking branch 'upstream/main' into use-lucene-postings…
jordan-powers Apr 2, 2025
375cf2d
Merge remote-tracking branch 'upstream/main' into use-lucene-postings…
jordan-powers Apr 2, 2025
c610ab8
Merge remote-tracking branch 'upstream/main' into use-lucene-postings…
jordan-powers Apr 3, 2025
a803d4c
Revert "Remove USE_LUCENE101_POSTINGS_FORMAT index version"
jordan-powers Apr 3, 2025
09aa306
Merge remote-tracking branch 'upstream/main' into use-lucene-postings…
jordan-powers Apr 3, 2025
9cfb46f
Merge remote-tracking branch 'upstream/main' into use-lucene-postings…
jordan-powers Apr 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions ...amlRestTest/java/org/elasticsearch/smoketest/SmokeTestMultiNodeClientYamlTestSuiteIT.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@ public class SmokeTestMultiNodeClientYamlTestSuiteIT extends ESClientYamlSuiteTe
.feature(FeatureFlag.TIME_SERIES_MODE)
.feature(FeatureFlag.SUB_OBJECTS_AUTO_ENABLED)
.feature(FeatureFlag.DOC_VALUES_SKIPPER)
.feature(FeatureFlag.USE_LUCENE101_POSTINGS_FORMAT)
.build();

public SmokeTestMultiNodeClientYamlTestSuiteIT(@Name("yaml") ClientYamlTestCandidate testCandidate) {
Expand Down
1 change: 1 addition & 0 deletions rest-api-spec/src/yamlRestTest/java/org/elasticsearch/test/rest/ClientYamlTestSuiteIT.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@ public class ClientYamlTestSuiteIT extends ESClientYamlSuiteTestCase {
.feature(FeatureFlag.TIME_SERIES_MODE)
.feature(FeatureFlag.SUB_OBJECTS_AUTO_ENABLED)
.feature(FeatureFlag.DOC_VALUES_SKIPPER)
.feature(FeatureFlag.USE_LUCENE101_POSTINGS_FORMAT)
.build();

public ClientYamlTestSuiteIT(@Name("yaml") ClientYamlTestCandidate testCandidate) {
Expand Down
1 change: 1 addition & 0 deletions server/src/main/java/org/elasticsearch/index/IndexVersions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -158,6 +158,7 @@ private static Version parseUnchecked(String version) {
public static final IndexVersion RESCORE_PARAMS_ALLOW_ZERO_TO_QUANTIZED_VECTORS = def(9_018_0_00, Version.LUCENE_10_1_0);
public static final IndexVersion SYNTHETIC_SOURCE_STORE_ARRAYS_NATIVELY_UNSIGNED_LONG = def(9_019_0_00, Version.LUCENE_10_1_0);
public static final IndexVersion SYNTHETIC_SOURCE_STORE_ARRAYS_NATIVELY_SCALED_FLOAT = def(9_020_0_00, Version.LUCENE_10_1_0);
public static final IndexVersion USE_LUCENE101_POSTINGS_FORMAT = def(9_021_0_00, Version.LUCENE_10_1_0);
/*
* STOP! READ THIS FIRST! No, really,
* ____ _____ ___ ____ _ ____ _____ _ ____ _____ _ _ ___ ____ _____ ___ ____ ____ _____ _
Expand Down
21 changes: 19 additions & 2 deletions server/src/main/java/org/elasticsearch/index/codec/PerFieldFormatSupplier.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,11 +12,14 @@
import org.apache.lucene.codecs.DocValuesFormat;
import org.apache.lucene.codecs.KnnVectorsFormat;
import org.apache.lucene.codecs.PostingsFormat;
import org.apache.lucene.codecs.lucene101.Lucene101PostingsFormat;
import org.apache.lucene.codecs.lucene90.Lucene90DocValuesFormat;
import org.apache.lucene.codecs.lucene99.Lucene99HnswVectorsFormat;
import org.elasticsearch.common.util.BigArrays;
import org.elasticsearch.common.util.FeatureFlag;
import org.elasticsearch.index.IndexMode;
import org.elasticsearch.index.IndexSettings;
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.es819.ES819TSDBDocValuesFormat;
Expand All @@ -31,19 +34,33 @@
* vectors.
*/
public class PerFieldFormatSupplier {
public static final FeatureFlag USE_LUCENE101_POSTINGS_FORMAT = new FeatureFlag("use_lucene101_postings_format");
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@jordan-powers @martijnvg Lucene 10.3 (still in development) will bring a new postings format. Is the intention that this feature flag to select the "latest" codec? Or is it really specific to 10.1? I ask only because we need to determine if a use_lucene101_postings_format is warranted or maybe make this flag more general?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The intent is the use the latest default lucene postings format. Unfortunately the name doesn't reflect that, but we want it to use the latest default postings format.


private static final DocValuesFormat docValuesFormat = new Lucene90DocValuesFormat();
private static final KnnVectorsFormat knnVectorsFormat = new Lucene99HnswVectorsFormat();
private static final ES819TSDBDocValuesFormat tsdbDocValuesFormat = new ES819TSDBDocValuesFormat();
private static final ES812PostingsFormat es812PostingsFormat = new ES812PostingsFormat();
private static final Lucene101PostingsFormat lucene101PostingsFormat = new Lucene101PostingsFormat();
private static final PostingsFormat completionPostingsFormat = PostingsFormat.forName("Completion101");

private final ES87BloomFilterPostingsFormat bloomFilterPostingsFormat;
private final MapperService mapperService;

private final PostingsFormat defaultPostingsFormat;

public PerFieldFormatSupplier(MapperService mapperService, BigArrays bigArrays) {
this.mapperService = mapperService;
this.bloomFilterPostingsFormat = new ES87BloomFilterPostingsFormat(bigArrays, this::internalGetPostingsFormatForField);

if (mapperService != null
&& USE_LUCENE101_POSTINGS_FORMAT.isEnabled()
&& mapperService.getIndexSettings().getIndexVersionCreated().onOrAfter(IndexVersions.USE_LUCENE101_POSTINGS_FORMAT)
&& mapperService.getIndexSettings().getMode() == IndexMode.STANDARD) {
defaultPostingsFormat = lucene101PostingsFormat;
} else {
// our own posting format using PFOR
defaultPostingsFormat = es812PostingsFormat;
}
}

public PostingsFormat getPostingsFormatForField(String field) {
Expand All @@ -60,8 +77,8 @@ private PostingsFormat internalGetPostingsFormatForField(String field) {
return completionPostingsFormat;
}
}
// return our own posting format using PFOR
return es812PostingsFormat;

return defaultPostingsFormat;
}

boolean useBloomFilter(String field) {
Expand Down
15 changes: 12 additions & 3 deletions server/src/test/java/org/elasticsearch/index/codec/PerFieldMapperCodecTests.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@

package org.elasticsearch.index.codec;

import org.apache.lucene.codecs.PostingsFormat;
import org.apache.lucene.codecs.lucene101.Lucene101PostingsFormat;
import org.elasticsearch.cluster.metadata.IndexMetadata;
import org.elasticsearch.common.compress.CompressedXContent;
import org.elasticsearch.common.settings.Settings;
Expand Down Expand Up @@ -86,11 +88,15 @@ public class PerFieldMapperCodecTests extends ESTestCase {
""";

public void testUseBloomFilter() throws IOException {
PerFieldFormatSupplier perFieldMapperCodec = createFormatSupplier(false, randomBoolean(), false);
boolean timeSeries = randomBoolean();
PerFieldFormatSupplier perFieldMapperCodec = createFormatSupplier(false, timeSeries, false);
assertThat(perFieldMapperCodec.useBloomFilter("_id"), is(true));
assertThat(perFieldMapperCodec.getPostingsFormatForField("_id"), instanceOf(ES87BloomFilterPostingsFormat.class));
assertThat(perFieldMapperCodec.useBloomFilter("another_field"), is(false));
assertThat(perFieldMapperCodec.getPostingsFormatForField("another_field"), instanceOf(ES812PostingsFormat.class));

Class<? extends PostingsFormat> expectedPostingsFormat = PerFieldFormatSupplier.USE_LUCENE101_POSTINGS_FORMAT.isEnabled()
&& timeSeries == false ? Lucene101PostingsFormat.class : ES812PostingsFormat.class;
assertThat(perFieldMapperCodec.getPostingsFormatForField("another_field"), instanceOf(expectedPostingsFormat));
}

public void testUseBloomFilterWithTimestampFieldEnabled() throws IOException {
Expand All @@ -104,7 +110,10 @@ public void testUseBloomFilterWithTimestampFieldEnabled() throws IOException {
public void testUseBloomFilterWithTimestampFieldEnabled_noTimeSeriesMode() throws IOException {
PerFieldFormatSupplier perFieldMapperCodec = createFormatSupplier(true, false, false);
assertThat(perFieldMapperCodec.useBloomFilter("_id"), is(false));
assertThat(perFieldMapperCodec.getPostingsFormatForField("_id"), instanceOf(ES812PostingsFormat.class));
Class<? extends PostingsFormat> expectedPostingsFormat = PerFieldFormatSupplier.USE_LUCENE101_POSTINGS_FORMAT.isEnabled()
? Lucene101PostingsFormat.class
: ES812PostingsFormat.class;
assertThat(perFieldMapperCodec.getPostingsFormatForField("_id"), instanceOf(expectedPostingsFormat));
}

public void testUseBloomFilterWithTimestampFieldEnabled_disableBloomFilter() throws IOException {
Expand Down
3 changes: 2 additions & 1 deletion test/test-clusters/src/main/java/org/elasticsearch/test/cluster/FeatureFlag.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,8 @@ public enum FeatureFlag {
TIME_SERIES_MODE("es.index_mode_feature_flag_registered=true", Version.fromString("8.0.0"), null),
FAILURE_STORE_ENABLED("es.failure_store_feature_flag_enabled=true", Version.fromString("8.12.0"), null),
SUB_OBJECTS_AUTO_ENABLED("es.sub_objects_auto_feature_flag_enabled=true", Version.fromString("8.16.0"), null),
DOC_VALUES_SKIPPER("es.doc_values_skipper_feature_flag_enabled=true", Version.fromString("8.18.1"), null);
DOC_VALUES_SKIPPER("es.doc_values_skipper_feature_flag_enabled=true", Version.fromString("8.18.1"), null),
USE_LUCENE101_POSTINGS_FORMAT("es.use_lucene101_postings_format_feature_flag_enabled=true", Version.fromString("9.1.0"), null);

public final String systemProperty;
public final Version from;
Expand Down
1 change: 1 addition & 0 deletions ...plugin/logsdb/src/yamlRestTest/java/org/elasticsearch/xpack/logsdb/LogsdbTestSuiteIT.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@ public class LogsdbTestSuiteIT extends ESClientYamlSuiteTestCase {
.setting("xpack.security.enabled", "false")
.setting("xpack.license.self_generated.type", "trial")
.feature(FeatureFlag.DOC_VALUES_SKIPPER)
.feature(FeatureFlag.USE_LUCENE101_POSTINGS_FORMAT)
.build();

public LogsdbTestSuiteIT(@Name("yaml") ClientYamlTestCandidate testCandidate) {
Expand Down
1 change: 1 addition & 0 deletions ...RestTest/java/org/elasticsearch/xpack/security/CoreWithSecurityClientYamlTestSuiteIT.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,6 +51,7 @@ public class CoreWithSecurityClientYamlTestSuiteIT extends ESClientYamlSuiteTest
.feature(FeatureFlag.TIME_SERIES_MODE)
.feature(FeatureFlag.SUB_OBJECTS_AUTO_ENABLED)
.feature(FeatureFlag.DOC_VALUES_SKIPPER)
.feature(FeatureFlag.USE_LUCENE101_POSTINGS_FORMAT)
.build();

public CoreWithSecurityClientYamlTestSuiteIT(@Name("yaml") ClientYamlTestCandidate testCandidate) {
Expand Down