Skip to content
Merged
Show file tree
Hide file tree
Changes from 22 commits
Commits
Show all changes
31 commits
Select commit Hold shift + click to select a range
2aa74e3
Skip indices that have an index refresh block
benchaplin Jun 4, 2025
12b6b81
Merge branch 'main' into skip_search_shards_with_index_block
benchaplin Jun 6, 2025
9c705cd
Construct the iterator skipped
benchaplin Jun 9, 2025
1c75721
Fix javadocs
benchaplin Jun 9, 2025
1ecc447
Add unit test
benchaplin Jun 9, 2025
cdb4bc1
[CI] Auto commit changes from spotless
Jun 9, 2025
b7ade2d
Merge branch 'main' into skip_search_shards_with_index_block
benchaplin Jun 9, 2025
cd991c2
Merge branch 'main' into skip_search_shards_with_index_block
drempapis Jun 11, 2025
5f50d5c
Merge branch 'main' into skip_search_shards_with_index_block
drempapis Jun 11, 2025
3f86fb8
Rewrite DFS if processing one or zero unskipped shard iterators
benchaplin Jun 11, 2025
0edc27c
Make can-match support already skipped shard iterators
benchaplin Jun 11, 2025
9de6f06
Add IT for executing search and PIT against refresh blocked indices
benchaplin Jun 11, 2025
be37bf6
Fix resource leak by using decRef assertion
benchaplin Jun 11, 2025
17706e2
[CI] Auto commit changes from spotless
Jun 11, 2025
8759a07
Merge branch 'main' into skip_search_shards_with_index_block
benchaplin Jun 11, 2025
bf8a2be
Improve names of valid shard check method and variables
benchaplin Jul 1, 2025
8887609
Merge branch 'main' into skip_search_shards_with_index_block
benchaplin Jul 1, 2025
0f0200a
Remove constructor used only in tests
benchaplin Jul 1, 2025
7689263
Fix missed merge conflict
benchaplin Jul 1, 2025
598e906
Remove ability to set INDEX_REFRESH_BLOCK from API, add directly to c…
benchaplin Jul 3, 2025
4cdfbd0
Merge branch 'main' into skip_search_shards_with_index_block
benchaplin Jul 3, 2025
76ecade
Merge branch 'main' into skip_search_shards_with_index_block
benchaplin Jul 3, 2025
86c9a5d
Rework change to ignore blocked indices before shard resolution
benchaplin Jul 15, 2025
7200edc
Merge branch 'main' into skip_search_shards_with_index_block
benchaplin Jul 15, 2025
d72600b
Clean up
benchaplin Jul 15, 2025
61d40c4
Add _msearch test case
benchaplin Jul 15, 2025
51d5196
Revert search type rewrite change
benchaplin Jul 18, 2025
24f2770
Merge branch 'main' into skip_search_shards_with_index_block
benchaplin Jul 18, 2025
b33a14f
Merge branch 'main' into skip_search_shards_with_index_block
benchaplin Jul 21, 2025
e10d59b
Add search shards test
benchaplin Jul 21, 2025
31d7dce
Oops remove Repeat
benchaplin Jul 21, 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
Original file line number Diff line number Diff line change
@@ -0,0 +1,129 @@
/*
* 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.search;

import org.elasticsearch.action.index.IndexRequestBuilder;
import org.elasticsearch.action.search.ClosePointInTimeRequest;
import org.elasticsearch.action.search.OpenPointInTimeRequest;
import org.elasticsearch.action.search.SearchRequest;
import org.elasticsearch.action.search.TransportClosePointInTimeAction;
import org.elasticsearch.action.search.TransportOpenPointInTimeAction;
import org.elasticsearch.cluster.ClusterState;
import org.elasticsearch.cluster.block.ClusterBlocks;
import org.elasticsearch.cluster.metadata.IndexMetadata;
import org.elasticsearch.cluster.metadata.ProjectId;
import org.elasticsearch.cluster.node.DiscoveryNode;
import org.elasticsearch.cluster.service.ClusterService;
import org.elasticsearch.common.bytes.BytesReference;
import org.elasticsearch.core.TimeValue;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.search.builder.PointInTimeBuilder;
import org.elasticsearch.search.builder.SearchSourceBuilder;
import org.elasticsearch.test.ESIntegTestCase;

import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import static org.elasticsearch.cluster.block.ClusterBlocks.EMPTY_CLUSTER_BLOCK;
import static org.elasticsearch.test.ClusterServiceUtils.setState;
import static org.elasticsearch.test.hamcrest.ElasticsearchAssertions.assertHitCount;

public class SearchWithIndexBlocksIT extends ESIntegTestCase {
Copy link
Contributor

Choose a reason for hiding this comment

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

Do we also want to have ESQL test for this case?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

I'm tracking that to be a followup task.


public void testSearchIndicesWithIndexRefreshBlocks() {
List<String> indices = createIndices();
Map<String, Integer> numDocsPerIndex = indexDocuments(indices);
List<String> unblockedIndices = addIndexRefreshBlockToSomeIndices(indices);

int expectedHits = 0;
for (String index : unblockedIndices) {
expectedHits += numDocsPerIndex.get(index);
}

assertHitCount(prepareSearch().setQuery(QueryBuilders.matchAllQuery()), expectedHits);
}

public void testOpenPITWithIndexRefreshBlock() {
List<String> indices = createIndices();
Map<String, Integer> numDocsPerIndex = indexDocuments(indices);
List<String> unblockedIndices = addIndexRefreshBlockToSomeIndices(indices);

int expectedHits = 0;
for (String index : unblockedIndices) {
expectedHits += numDocsPerIndex.get(index);
}

BytesReference pitId = null;
try {
OpenPointInTimeRequest openPITRequest = new OpenPointInTimeRequest(indices.toArray(new String[0])).keepAlive(
TimeValue.timeValueSeconds(10)
).allowPartialSearchResults(true);
pitId = client().execute(TransportOpenPointInTimeAction.TYPE, openPITRequest).actionGet().getPointInTimeId();
SearchRequest searchRequest = new SearchRequest().source(
new SearchSourceBuilder().pointInTimeBuilder(new PointInTimeBuilder(pitId).setKeepAlive(TimeValue.timeValueSeconds(10)))
);
assertHitCount(client().search(searchRequest), expectedHits);
} finally {
if (pitId != null) {
client().execute(TransportClosePointInTimeAction.TYPE, new ClosePointInTimeRequest(pitId)).actionGet();
}
}
}

private List<String> createIndices() {
int numIndices = randomIntBetween(1, 3);
List<String> indices = new ArrayList<>();
for (int i = 0; i < numIndices; i++) {
indices.add("test" + i);
createIndex("test" + i);
}
return indices;
}

private Map<String, Integer> indexDocuments(List<String> indices) {
Map<String, Integer> numDocsPerIndex = new HashMap<>();
List<IndexRequestBuilder> indexRequests = new ArrayList<>();
for (String index : indices) {
int numDocs = randomIntBetween(0, 10);
numDocsPerIndex.put(index, numDocs);
for (int i = 0; i < numDocs; i++) {
indexRequests.add(prepareIndex(index).setId(String.valueOf(i)).setSource("field", "value"));
}
}
indexRandom(true, indexRequests);

return numDocsPerIndex;
}

private List<String> addIndexRefreshBlockToSomeIndices(List<String> indices) {
List<String> unblockedIndices = new ArrayList<>();
var blocksBuilder = ClusterBlocks.builder().blocks(EMPTY_CLUSTER_BLOCK);
for (String index : indices) {
boolean blockIndex = randomBoolean();
if (blockIndex) {
blocksBuilder.addIndexBlock(ProjectId.DEFAULT, index, IndexMetadata.INDEX_REFRESH_BLOCK);
} else {
unblockedIndices.add(index);
}
}

var dataNodes = clusterService().state().getNodes().getAllNodes();
for (DiscoveryNode dataNode : dataNodes) {
ClusterService clusterService = internalCluster().getInstance(ClusterService.class, dataNode.getName());
ClusterState currentState = clusterService.state();
ClusterState newState = ClusterState.builder(currentState).blocks(blocksBuilder).build();
setState(clusterService, newState);
Copy link
Member

Choose a reason for hiding this comment

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

This method is not intended to be used in integration test as it overrides the current data node cluster state.

For testing the INDEX_REFRESH_BLOCK I think it makes sense to only have unit tests in stateful elasticsearch.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Sorry @tlrx, can you explain more the risks of doing this?

I like having fine-grained control over blocks so I can write tests that block some indices and allow others in one search - I think this is critical to test. If I can only 'set' the block by controlling active search nodes (like I do in the other PR), I can't think of a way to achieve what I want.

}

return unblockedIndices;
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -186,6 +186,12 @@ private void runCoordinatorRewritePhase() {
assert assertSearchCoordinationThread();
final List<SearchShardIterator> matchedShardLevelRequests = new ArrayList<>();
for (SearchShardIterator searchShardIterator : shardsIts) {
if (searchShardIterator.prefiltered() == false && searchShardIterator.skip()) {
// This implies the iterator was skipped due to an index level block,
// not a remote can-match run.
continue;
}

final CanMatchNodeRequest canMatchNodeRequest = new CanMatchNodeRequest(
request,
searchShardIterator.getOriginalIndices().indicesOptions(),
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -41,19 +41,28 @@ public final class SearchShardIterator implements Comparable<SearchShardIterator

/**
* Creates a {@link SearchShardIterator} instance that iterates over a subset of the given shards
* this the a given <code>shardId</code>.
* for a given <code>shardId</code>.
*
* @param clusterAlias the alias of the cluster where the shard is located
* @param shardId shard id of the group
* @param shards shards to iterate
* @param originalIndices the indices that the search request originally related to (before any rewriting happened)
* @param skip if true, then this group won't have matches (due to an index level block),
* and it can be safely skipped from the search
*/
public SearchShardIterator(@Nullable String clusterAlias, ShardId shardId, List<ShardRouting> shards, OriginalIndices originalIndices) {
this(clusterAlias, shardId, shards.stream().map(ShardRouting::currentNodeId).toList(), originalIndices, null, null, false, false);
public SearchShardIterator(
@Nullable String clusterAlias,
ShardId shardId,
List<ShardRouting> shards,
OriginalIndices originalIndices,
boolean skip
) {
this(clusterAlias, shardId, shards.stream().map(ShardRouting::currentNodeId).toList(), originalIndices, null, null, false, skip);
}

/**
* Creates a {@link SearchShardIterator} instance that iterates over a subset of the given shards
* for a given <code>shardId</code>.
*
* @param clusterAlias the alias of the cluster where the shard is located
* @param shardId shard id of the group
Expand All @@ -62,7 +71,8 @@ public SearchShardIterator(@Nullable String clusterAlias, ShardId shardId, List<
* @param searchContextId the point-in-time specified for this group if exists
* @param searchContextKeepAlive the time interval that data nodes should extend the keep alive of the point-in-time
* @param prefiltered if true, then this group already executed the can_match phase
* @param skip if true, then this group won't have matches, and it can be safely skipped from the search
* @param skip if true, then this group won't have matches (due to can match, or an index level block),
* and it can be safely skipped from the search
*/
public SearchShardIterator(
@Nullable String clusterAlias,
Expand All @@ -83,7 +93,6 @@ public SearchShardIterator(
assert searchContextKeepAlive == null || searchContextId != null;
this.prefiltered = prefiltered;
this.skip = skip;
assert skip == false || prefiltered : "only prefiltered shards are skip-able";
}

/**
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -148,6 +148,9 @@ public class TransportSearchAction extends HandledTransportAction<SearchRequest,
Property.NodeScope
);

// Marker to indicate this index's shards should be skipped in a search
private static final OriginalIndices SKIPPED_INDICES = new OriginalIndices(Strings.EMPTY_ARRAY, IndicesOptions.strictExpandOpen());

private final ThreadPool threadPool;
private final ClusterService clusterService;
private final TransportService transportService;
Expand Down Expand Up @@ -234,6 +237,10 @@ private Map<String, OriginalIndices> buildPerIndexOriginalIndices(
for (String index : indices) {
if (hasBlocks) {
blocks.indexBlockedRaiseException(projectId, ClusterBlockLevel.READ, index);
if (blocks.hasIndexBlock(projectState.projectId(), index, IndexMetadata.INDEX_REFRESH_BLOCK)) {
res.put(index, SKIPPED_INDICES);
continue;
}
}

String[] aliases = indexNameExpressionResolver.allIndexAliases(projectState.metadata(), index, indicesAndAliases);
Expand Down Expand Up @@ -589,7 +596,7 @@ public void onFailure(Exception e) {}
);
}

static void adjustSearchType(SearchRequest searchRequest, boolean singleShard) {
static void adjustSearchType(SearchRequest searchRequest, boolean oneOrZeroShardsToSearch) {
// if there's a kNN search, always use DFS_QUERY_THEN_FETCH
if (searchRequest.hasKnnSearch()) {
searchRequest.searchType(DFS_QUERY_THEN_FETCH);
Expand All @@ -604,7 +611,7 @@ static void adjustSearchType(SearchRequest searchRequest, boolean singleShard) {
}

// optimize search type for cases where there is only one shard group to search on
if (singleShard) {
if (oneOrZeroShardsToSearch) {
// if we only have one group, then we always want Q_T_F, no need for DFS, and no need to do THEN since we hit one shard
searchRequest.searchType(QUERY_THEN_FETCH);
}
Expand Down Expand Up @@ -1305,7 +1312,7 @@ private void executeSearch(

Map<String, Float> concreteIndexBoosts = resolveIndexBoosts(searchRequest, projectState.cluster());

adjustSearchType(searchRequest, shardIterators.size() == 1);
adjustSearchType(searchRequest, oneOrZeroShardsToSearch(shardIterators));

final DiscoveryNodes nodes = projectState.cluster().nodes();
BiFunction<String, String, Transport.Connection> connectionLookup = buildConnectionLookup(
Expand Down Expand Up @@ -1338,6 +1345,33 @@ private void executeSearch(
);
}

/**
* Determines if only one (or zero) search shard iterators will be searched.
* (At this point, iterators may be marked as skipped due to index level blockers).
* We expect skipped iterators to be unlikely, so returning fast after we see more
* than one "not skipped" is an intended optimization.
*
* @param searchShardIterators all the shard iterators derived from indices being searched
* @return true if there are no more than one shard iterators, or if there are no more than
* one not marked to skip
*/
private boolean oneOrZeroShardsToSearch(List<SearchShardIterator> searchShardIterators) {
if (searchShardIterators.size() <= 1) {
return true;
}

int notSkippedCount = 0;
for (SearchShardIterator searchShardIterator : searchShardIterators) {
if (searchShardIterator.skip() == false) {
notSkippedCount++;
if (notSkippedCount > 1) {
return false;
}
}
}
return true;
}

Executor asyncSearchExecutor(final String[] indices) {
boolean seenSystem = false;
boolean seenCritical = false;
Expand Down Expand Up @@ -1890,7 +1924,13 @@ List<SearchShardIterator> getLocalShardsIterator(
final ShardId shardId = shardRouting.shardId();
OriginalIndices finalIndices = originalIndices.get(shardId.getIndex().getName());
assert finalIndices != null;
list[i++] = new SearchShardIterator(clusterAlias, shardId, shardRouting.getShardRoutings(), finalIndices);
list[i++] = new SearchShardIterator(
clusterAlias,
shardId,
shardRouting.getShardRoutings(),
finalIndices,
finalIndices == SKIPPED_INDICES
);
}
// the returned list must support in-place sorting, so this is the most memory efficient we can do here
return Arrays.asList(list);
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -82,7 +82,7 @@ private AbstractSearchAsyncAction<SearchPhaseResult> createAction(
null,
request,
listener,
Collections.singletonList(new SearchShardIterator(null, new ShardId("index", "_na", 0), Collections.emptyList(), null)),
Collections.singletonList(new SearchShardIterator(null, new ShardId("index", "_na", 0), Collections.emptyList(), null, false)),
timeProvider,
ClusterState.EMPTY_STATE,
null,
Expand Down Expand Up @@ -153,7 +153,8 @@ public void testBuildShardSearchTransportRequest() {
clusterAlias,
new ShardId(new Index("name", "foo"), 1),
Collections.emptyList(),
new OriginalIndices(new String[] { "name", "name1" }, IndicesOptions.strictExpand())
new OriginalIndices(new String[] { "name", "name1" }, IndicesOptions.strictExpand()),
false
);
ShardSearchRequest shardSearchTransportRequest = action.buildShardSearchRequest(iterator, 10);
assertEquals(IndicesOptions.strictExpand(), shardSearchTransportRequest.indicesOptions());
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -640,7 +640,8 @@ public void testSkipUnavailableSearchShards() throws InterruptedException {
null,
new ShardId(index, 0),
Collections.emptyList(),
originalIndices
originalIndices,
false
);
// Skip all the shards
searchShardIterator.skip(true);
Expand Down Expand Up @@ -760,7 +761,7 @@ static List<SearchShardIterator> getShardsIter(
}
Collections.shuffle(started, random());
started.addAll(initializing);
list.add(new SearchShardIterator(null, new ShardId(index, i), started, originalIndices));
list.add(new SearchShardIterator(null, new ShardId(index, i), started, originalIndices, false));
}
return list;
}
Expand Down
Loading