Skip to content

ES|QL: Count all docs in a single getOutput call in LuceneCountOperator #136362

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+24 −15
Open

ES|QL: Count all docs in a single getOutput call in LuceneCountOperator #136362

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
32 changes: 22 additions & 10 deletions ...ugin/esql/compute/src/main/java/org/elasticsearch/compute/lucene/LuceneCountOperator.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,11 +13,11 @@
import org.apache.lucene.search.ScoreMode;
import org.apache.lucene.search.Weight;
import org.elasticsearch.compute.data.Block;
import org.elasticsearch.compute.data.BlockFactory;
import org.elasticsearch.compute.data.BlockUtils;
import org.elasticsearch.compute.data.ElementType;
import org.elasticsearch.compute.data.LongVector;
import org.elasticsearch.compute.data.Page;
import org.elasticsearch.compute.operator.Driver;
import org.elasticsearch.compute.operator.DriverContext;
import org.elasticsearch.compute.operator.SourceOperator;
import org.elasticsearch.core.RefCounted;
Expand Down Expand Up @@ -64,7 +64,7 @@ public Factory(

@Override
public SourceOperator get(DriverContext driverContext) {
return new LuceneCountOperator(shardRefCounters, driverContext.blockFactory(), sliceQueue, tagTypes, limit);
return new LuceneCountOperator(shardRefCounters, driverContext, sliceQueue, tagTypes, limit);
}

@Override
Expand All @@ -76,17 +76,19 @@ public String describe() {
private final List<ElementType> tagTypes;
private final Map<List<Object>, PerTagsState> tagsToState = new HashMap<>();
private int remainingDocs;
private final DriverContext driverContext;

public LuceneCountOperator(
List<? extends RefCounted> shardRefCounters,
BlockFactory blockFactory,
DriverContext driverContext,
LuceneSliceQueue sliceQueue,
List<ElementType> tagTypes,
int limit
) {
super(shardRefCounters, blockFactory, Integer.MAX_VALUE, sliceQueue);
super(shardRefCounters, driverContext.blockFactory(), Integer.MAX_VALUE, sliceQueue);
this.tagTypes = tagTypes;
this.remainingDocs = limit;
this.driverContext = driverContext;
}

@Override
Expand All @@ -107,17 +109,27 @@ protected Page getCheckedOutput() throws IOException {
}
long start = System.nanoTime();
try {
final LuceneScorer scorer = getCurrentOrLoadNextScorer();
if (scorer == null) {
remainingDocs = 0;
} else {
count(scorer);
while (remainingDocs > 0) {
final LuceneScorer scorer = getCurrentOrLoadNextScorer();
if (scorer == null) {
remainingDocs = 0;
} else {
count(scorer);
}

// Check if the query has been cancelled.
driverContext.checkForEarlyTermination();
// Even if this should almost never happen, we want to update the driver status even when a query runs "forever".
if (System.nanoTime() - start > Driver.DEFAULT_STATUS_INTERVAL.getNanos()) {
break;
}
}

if (remainingDocs <= 0) {
return buildResult();
} else {
return null;
}
return null;
} finally {
processingNanos += System.nanoTime() - start;
}
Expand Down
7 changes: 2 additions & 5 deletions ...esql/compute/src/main/java/org/elasticsearch/compute/lucene/LuceneTopNSourceOperator.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@
import org.elasticsearch.compute.data.IntBlock;
import org.elasticsearch.compute.data.IntVector;
import org.elasticsearch.compute.data.Page;
import org.elasticsearch.compute.operator.Driver;
import org.elasticsearch.compute.operator.DriverContext;
import org.elasticsearch.compute.operator.SourceOperator;
import org.elasticsearch.core.Releasables;
Expand All @@ -40,7 +41,6 @@
import java.util.Arrays;
import java.util.List;
import java.util.Optional;
import java.util.concurrent.TimeUnit;
import java.util.function.Function;
import java.util.stream.Collectors;

Expand Down Expand Up @@ -124,9 +124,6 @@ public String describe() {
// We use the same value as the INITIAL_INTERVAL from CancellableBulkScorer
private static final int NUM_DOCS_INTERVAL = 1 << 12;

// The max time we should be spending scoring docs in one getOutput call, before we return to update the driver status
private static final long MAX_EXEC_TIME = TimeUnit.SECONDS.toNanos(1);

private final DriverContext driverContext;
private final List<SortBuilder<?>> sorts;
private final long estimatedPerRowSortSize;
Expand Down Expand Up @@ -236,7 +233,7 @@ private Page collect() throws IOException {

// When it takes a long time to start emitting pages we need to return back to the driver so we can update its status.
// Even if this should almost never happen, we want to update the driver status even when a query runs "forever".
if (System.nanoTime() - start > MAX_EXEC_TIME) {
if (System.nanoTime() - start > Driver.DEFAULT_STATUS_INTERVAL.getNanos()) {
return null;
}
}
Expand Down