mirrors
/
elasticsearch
mirror of https://mirror.osredm.com/root/elasticsearch.git
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Cleanup swapSourceProvider(...) workaround (#118480) 

This reverts the workaround that was introduced in #117792 to avoid EOF error when an es|ql query uses multiple runtime fields that fallback to source when source mode is synthetic. This is now covered by the ReinitializingSourceProvider workaround that covers that and the concurrency problem. With this change, the main code for the required workarounds are now in isolated in ReinitializingSourceProvider.

Additional another in `ReinitializingSourceProvider` was fixed, the issue was the lastSeenDoc field was reused overwritten by different threads, the latest commit moves the lastSeenDoc field to PerThreadSourceProvider so that each thread gets its own place to store the last seen docid.
This commit is contained in:
Martijn van Groningen 2025-01-14 10:28:59 +01:00 committed by GitHub
parent 1be9253779
commit d953079380
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 14 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
server/src/main/java/org/elasticsearch/search/lookup/SearchLookup.java
View File

@ -102,14 +102,6 @@ public class SearchLookup implements SourceProvider {
this.fieldLookupProvider = searchLookup.fieldLookupProvider;
}
private SearchLookup(SearchLookup searchLookup, SourceProvider sourceProvider, Set<String> fieldChain) {
this.fieldChain = Collections.unmodifiableSet(fieldChain);
this.sourceProvider = sourceProvider;
this.fieldTypeLookup = searchLookup.fieldTypeLookup;
this.fieldDataLookup = searchLookup.fieldDataLookup;
this.fieldLookupProvider = searchLookup.fieldLookupProvider;
}
/**
* Creates a copy of the current {@link SearchLookup} that looks fields up in the same way, but also tracks field references
* in order to detect cycles and prevent resolving fields that depend on more than {@link #MAX_FIELD_CHAIN_DEPTH} other fields.
@ -153,7 +145,4 @@ public class SearchLookup implements SourceProvider {
return sourceProvider.getSource(ctx, doc);
}
public SearchLookup swapSourceProvider(SourceProvider sourceProvider) {
return new SearchLookup(this, sourceProvider, fieldChain);
}
}

12
x-pack/plugin/esql/src/main/java/org/elasticsearch/xpack/esql/planner/EsPhysicalOperationProviders.java
View File

@ -33,7 +33,6 @@ import org.elasticsearch.index.mapper.BlockLoader;
import org.elasticsearch.index.mapper.FieldNamesFieldMapper;
import org.elasticsearch.index.mapper.MappedFieldType;
import org.elasticsearch.index.mapper.NestedLookup;
import org.elasticsearch.index.mapper.SourceFieldMapper;
import org.elasticsearch.index.mapper.SourceLoader;
import org.elasticsearch.index.query.QueryBuilder;
import org.elasticsearch.index.query.QueryBuilders;
@ -339,16 +338,7 @@ public class EsPhysicalOperationProviders extends AbstractPhysicalOperationProvi
@Override
public SearchLookup lookup() {
boolean syntheticSource = SourceFieldMapper.isSynthetic(indexSettings());
var searchLookup = ctx.lookup();
if (syntheticSource) {
// in the context of scripts and when synthetic source is used the search lookup can't always be reused between
// users of SearchLookup. This is only an issue when scripts fallback to _source, but since we can't always
// accurately determine whether a script uses _source, we should do this for all script usages.
// This lookup() method is only invoked for scripts / runtime fields, so it is ok to do here.
searchLookup = searchLookup.swapSourceProvider(ctx.createSourceProvider());
}
return searchLookup;
return ctx.lookup();
}
@Override

20
x-pack/plugin/esql/src/main/java/org/elasticsearch/xpack/esql/plugin/ReinitializingSourceProvider.java
View File

@ -28,10 +28,6 @@ final class ReinitializingSourceProvider implements SourceProvider {
private PerThreadSourceProvider perThreadProvider;
private final Supplier<SourceProvider> sourceProviderFactory;
// Keeping track of last seen doc and if current doc is before last seen doc then source provider is initialized:
// (when source mode is synthetic then _source is read from doc values and doc values don't support going backwards)
private int lastSeenDocId;
ReinitializingSourceProvider(Supplier<SourceProvider> sourceProviderFactory) {
this.sourceProviderFactory = sourceProviderFactory;
}
@ -40,15 +36,25 @@ final class ReinitializingSourceProvider implements SourceProvider {
public Source getSource(LeafReaderContext ctx, int doc) throws IOException {
var currentThread = Thread.currentThread();
PerThreadSourceProvider provider = perThreadProvider;
if (provider == null || provider.creatingThread != currentThread || doc < lastSeenDocId) {
if (provider == null || provider.creatingThread != currentThread || doc < provider.lastSeenDocId) {
provider = new PerThreadSourceProvider(sourceProviderFactory.get(), currentThread);
this.perThreadProvider = provider;
}
lastSeenDocId = doc;
provider.lastSeenDocId = doc;
return provider.source.getSource(ctx, doc);
}
private record PerThreadSourceProvider(SourceProvider source, Thread creatingThread) {
private static final class PerThreadSourceProvider {
final SourceProvider source;
final Thread creatingThread;
// Keeping track of last seen doc and if current doc is before last seen doc then source provider is initialized:
// (when source mode is synthetic then _source is read from doc values and doc values don't support going backwards)
int lastSeenDocId;
private PerThreadSourceProvider(SourceProvider source, Thread creatingThread) {
this.source = source;
this.creatingThread = creatingThread;
}
}
}