org.apache.lucene.index.ThreadedIndexingAndSearchingTestCase Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of lucene-test-framework Show documentation
Show all versions of lucene-test-framework Show documentation
Apache Lucene (module: test-framework)
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.lucene.index;
import java.io.IOException;
import java.nio.file.Path;
import java.util.*;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.atomic.AtomicBoolean;
import java.util.concurrent.atomic.AtomicInteger;
import org.apache.lucene.analysis.MockAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.Sort;
import org.apache.lucene.search.SortField;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.BaseDirectoryWrapper;
import org.apache.lucene.store.Directory;
import org.apache.lucene.util.Bits;
import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.FailOnNonBulkMergesInfoStream;
import org.apache.lucene.util.IOUtils;
import org.apache.lucene.util.LineFileDocs;
import org.apache.lucene.util.LuceneTestCase;
import org.apache.lucene.util.NamedThreadFactory;
import org.apache.lucene.util.PrintStreamInfoStream;
import org.apache.lucene.util.TestUtil;
// TODO
// - mix in forceMerge, addIndexes
// - randomly mix in non-congruent docs
/** Utility class that spawns multiple indexing and
* searching threads. */
public abstract class ThreadedIndexingAndSearchingTestCase extends LuceneTestCase {
protected final AtomicBoolean failed = new AtomicBoolean();
protected final AtomicInteger addCount = new AtomicInteger();
protected final AtomicInteger delCount = new AtomicInteger();
protected final AtomicInteger packCount = new AtomicInteger();
protected Directory dir;
protected IndexWriter writer;
private static class SubDocs {
public final String packID;
public final List subIDs;
public boolean deleted;
public SubDocs(String packID, List subIDs) {
this.packID = packID;
this.subIDs = subIDs;
}
}
// Called per-search
protected abstract IndexSearcher getCurrentSearcher() throws Exception;
protected abstract IndexSearcher getFinalSearcher() throws Exception;
protected void releaseSearcher(IndexSearcher s) throws Exception {
}
// Called once to run searching
protected abstract void doSearching(ExecutorService es, long stopTime) throws Exception;
protected Directory getDirectory(Directory in) {
return in;
}
protected void updateDocuments(Term id, List> docs) throws Exception {
writer.updateDocuments(id, docs);
}
protected void addDocuments(Term id, List> docs) throws Exception {
writer.addDocuments(docs);
}
protected void addDocument(Term id, Iterable doc) throws Exception {
writer.addDocument(doc);
}
protected void updateDocument(Term term, Iterable doc) throws Exception {
writer.updateDocument(term, doc);
}
protected void deleteDocuments(Term term) throws Exception {
writer.deleteDocuments(term);
}
protected void doAfterIndexingThreadDone() {
}
private Thread[] launchIndexingThreads(final LineFileDocs docs,
int numThreads,
final long stopTime,
final Set delIDs,
final Set delPackIDs,
final List allSubDocs) {
final Thread[] threads = new Thread[numThreads];
for(int thread=0;thread toDeleteIDs = new ArrayList<>();
final List toDeleteSubDocs = new ArrayList<>();
while(System.currentTimeMillis() < stopTime && !failed.get()) {
try {
// Occasional longish pause if running
// nightly
if (LuceneTestCase.TEST_NIGHTLY && random().nextInt(6) == 3) {
if (VERBOSE) {
System.out.println(Thread.currentThread().getName() + ": now long sleep");
}
Thread.sleep(TestUtil.nextInt(random(), 50, 500));
}
// Rate limit ingest rate:
if (random().nextInt(7) == 5) {
Thread.sleep(TestUtil.nextInt(random(), 1, 10));
if (VERBOSE) {
System.out.println(Thread.currentThread().getName() + ": done sleep");
}
}
Document doc = docs.nextDoc();
if (doc == null) {
break;
}
// Maybe add randomly named field
final String addedField;
if (random().nextBoolean()) {
addedField = "extra" + random().nextInt(40);
doc.add(newTextField(addedField, "a random field", Field.Store.YES));
} else {
addedField = null;
}
if (random().nextBoolean()) {
if (random().nextBoolean()) {
// Add/update doc block:
final String packID;
final SubDocs delSubDocs;
if (toDeleteSubDocs.size() > 0 && random().nextBoolean()) {
delSubDocs = toDeleteSubDocs.get(random().nextInt(toDeleteSubDocs.size()));
assert !delSubDocs.deleted;
toDeleteSubDocs.remove(delSubDocs);
// Update doc block, replacing prior packID
packID = delSubDocs.packID;
} else {
delSubDocs = null;
// Add doc block, using new packID
packID = packCount.getAndIncrement() + "";
}
final Field packIDField = newStringField("packID", packID, Field.Store.YES);
final List docIDs = new ArrayList<>();
final SubDocs subDocs = new SubDocs(packID, docIDs);
final List docsList = new ArrayList<>();
allSubDocs.add(subDocs);
doc.add(packIDField);
docsList.add(TestUtil.cloneDocument(doc));
docIDs.add(doc.get("docid"));
final int maxDocCount = TestUtil.nextInt(random(), 1, 10);
while(docsList.size() < maxDocCount) {
doc = docs.nextDoc();
if (doc == null) {
break;
}
docsList.add(TestUtil.cloneDocument(doc));
docIDs.add(doc.get("docid"));
}
addCount.addAndGet(docsList.size());
final Term packIDTerm = new Term("packID", packID);
if (delSubDocs != null) {
delSubDocs.deleted = true;
delIDs.addAll(delSubDocs.subIDs);
delCount.addAndGet(delSubDocs.subIDs.size());
if (VERBOSE) {
System.out.println(Thread.currentThread().getName() + ": update pack packID=" + delSubDocs.packID + " count=" + docsList.size() + " docs=" + docIDs);
}
updateDocuments(packIDTerm, docsList);
} else {
if (VERBOSE) {
System.out.println(Thread.currentThread().getName() + ": add pack packID=" + packID + " count=" + docsList.size() + " docs=" + docIDs);
}
addDocuments(packIDTerm, docsList);
}
doc.removeField("packID");
if (random().nextInt(5) == 2) {
if (VERBOSE) {
System.out.println(Thread.currentThread().getName() + ": buffer del id:" + packID);
}
toDeleteSubDocs.add(subDocs);
}
} else {
// Add single doc
final String docid = doc.get("docid");
if (VERBOSE) {
System.out.println(Thread.currentThread().getName() + ": add doc docid:" + docid);
}
addDocument(new Term("docid", docid), doc);
addCount.getAndIncrement();
if (random().nextInt(5) == 3) {
if (VERBOSE) {
System.out.println(Thread.currentThread().getName() + ": buffer del id:" + doc.get("docid"));
}
toDeleteIDs.add(docid);
}
}
} else {
// Update single doc, but we never re-use
// and ID so the delete will never
// actually happen:
if (VERBOSE) {
System.out.println(Thread.currentThread().getName() + ": update doc id:" + doc.get("docid"));
}
final String docid = doc.get("docid");
updateDocument(new Term("docid", docid), doc);
addCount.getAndIncrement();
if (random().nextInt(5) == 3) {
if (VERBOSE) {
System.out.println(Thread.currentThread().getName() + ": buffer del id:" + doc.get("docid"));
}
toDeleteIDs.add(docid);
}
}
if (random().nextInt(30) == 17) {
if (VERBOSE) {
System.out.println(Thread.currentThread().getName() + ": apply " + toDeleteIDs.size() + " deletes");
}
for(String id : toDeleteIDs) {
if (VERBOSE) {
System.out.println(Thread.currentThread().getName() + ": del term=id:" + id);
}
deleteDocuments(new Term("docid", id));
}
final int count = delCount.addAndGet(toDeleteIDs.size());
if (VERBOSE) {
System.out.println(Thread.currentThread().getName() + ": tot " + count + " deletes");
}
delIDs.addAll(toDeleteIDs);
toDeleteIDs.clear();
for(SubDocs subDocs : toDeleteSubDocs) {
assert !subDocs.deleted;
delPackIDs.add(subDocs.packID);
deleteDocuments(new Term("packID", subDocs.packID));
subDocs.deleted = true;
if (VERBOSE) {
System.out.println(Thread.currentThread().getName() + ": del subs: " + subDocs.subIDs + " packID=" + subDocs.packID);
}
delIDs.addAll(subDocs.subIDs);
delCount.addAndGet(subDocs.subIDs.size());
}
toDeleteSubDocs.clear();
}
if (addedField != null) {
doc.removeField(addedField);
}
} catch (Throwable t) {
System.out.println(Thread.currentThread().getName() + ": hit exc");
t.printStackTrace();
failed.set(true);
throw new RuntimeException(t);
}
}
if (VERBOSE) {
System.out.println(Thread.currentThread().getName() + ": indexing done");
}
doAfterIndexingThreadDone();
}
};
threads[thread].start();
}
return threads;
}
protected void runSearchThreads(final long stopTimeMS) throws Exception {
final int numThreads = TestUtil.nextInt(random(), 1, 5);
final Thread[] searchThreads = new Thread[numThreads];
final AtomicInteger totHits = new AtomicInteger();
// silly starting guess:
final AtomicInteger totTermCount = new AtomicInteger(100);
// TODO: we should enrich this to do more interesting searches
for(int thread=0;thread diagnostics = segReader.getSegmentInfo().info.getDiagnostics();
assertNotNull(diagnostics);
String source = diagnostics.get("source");
assertNotNull(source);
if (source.equals("merge")) {
assertTrue("sub reader " + sub + " wasn't warmed: warmed=" + warmed + " diagnostics=" + diagnostics + " si=" + segReader.getSegmentInfo(),
!assertMergedSegmentsWarmed || warmed.containsKey(segReader.core));
}
}
if (s.getIndexReader().numDocs() > 0) {
smokeTestSearcher(s);
Fields fields = MultiFields.getFields(s.getIndexReader());
Terms terms = fields.terms("body");
if (terms == null) {
continue;
}
TermsEnum termsEnum = terms.iterator();
int seenTermCount = 0;
int shift;
int trigger;
if (totTermCount.get() < 30) {
shift = 0;
trigger = 1;
} else {
trigger = totTermCount.get()/30;
shift = random().nextInt(trigger);
}
while (System.currentTimeMillis() < stopTimeMS) {
BytesRef term = termsEnum.next();
if (term == null) {
totTermCount.set(seenTermCount);
break;
}
seenTermCount++;
// search 30 terms
if ((seenTermCount + shift) % trigger == 0) {
//if (VERBOSE) {
//System.out.println(Thread.currentThread().getName() + " now search body:" + term.utf8ToString());
//}
totHits.addAndGet(runQuery(s, new TermQuery(new Term("body", BytesRef.deepCopyOf(term)))));
}
}
//if (VERBOSE) {
//System.out.println(Thread.currentThread().getName() + ": search done");
//}
}
} finally {
releaseSearcher(s);
}
} catch (Throwable t) {
System.out.println(Thread.currentThread().getName() + ": hit exc");
failed.set(true);
t.printStackTrace(System.out);
throw new RuntimeException(t);
}
}
}
};
searchThreads[thread].start();
}
for(Thread thread : searchThreads) {
thread.join();
}
if (VERBOSE) {
System.out.println("TEST: DONE search: totHits=" + totHits);
}
}
protected void doAfterWriter(ExecutorService es) throws Exception {
}
protected void doClose() throws Exception {
}
protected boolean assertMergedSegmentsWarmed = true;
private final Map warmed = Collections.synchronizedMap(new WeakHashMap());
public void runTest(String testName) throws Exception {
failed.set(false);
addCount.set(0);
delCount.set(0);
packCount.set(0);
final long t0 = System.currentTimeMillis();
Random random = new Random(random().nextLong());
final LineFileDocs docs = new LineFileDocs(random);
final Path tempDir = createTempDir(testName);
dir = getDirectory(newMockFSDirectory(tempDir)); // some subclasses rely on this being MDW
if (dir instanceof BaseDirectoryWrapper) {
((BaseDirectoryWrapper) dir).setCheckIndexOnClose(false); // don't double-checkIndex, we do it ourselves.
}
MockAnalyzer analyzer = new MockAnalyzer(random());
analyzer.setMaxTokenLength(TestUtil.nextInt(random(), 1, IndexWriter.MAX_TERM_LENGTH));
final IndexWriterConfig conf = newIndexWriterConfig(analyzer).setCommitOnClose(false);
conf.setInfoStream(new FailOnNonBulkMergesInfoStream());
if (conf.getMergePolicy() instanceof MockRandomMergePolicy) {
((MockRandomMergePolicy)conf.getMergePolicy()).setDoNonBulkMerges(false);
}
if (LuceneTestCase.TEST_NIGHTLY) {
// newIWConfig makes smallish max seg size, which
// results in tons and tons of segments for this test
// when run nightly:
MergePolicy mp = conf.getMergePolicy();
if (mp instanceof TieredMergePolicy) {
((TieredMergePolicy) mp).setMaxMergedSegmentMB(5000.);
} else if (mp instanceof LogByteSizeMergePolicy) {
((LogByteSizeMergePolicy) mp).setMaxMergeMB(1000.);
} else if (mp instanceof LogMergePolicy) {
((LogMergePolicy) mp).setMaxMergeDocs(100000);
}
// when running nightly, merging can still have crazy parameters,
// and might use many per-field codecs. turn on CFS for IW flushes
// and ensure CFS ratio is reasonable to keep it contained.
conf.setUseCompoundFile(true);
mp.setNoCFSRatio(Math.max(0.25d, mp.getNoCFSRatio()));
}
conf.setMergedSegmentWarmer(new IndexWriter.IndexReaderWarmer() {
@Override
public void warm(LeafReader reader) throws IOException {
if (VERBOSE) {
System.out.println("TEST: now warm merged reader=" + reader);
}
warmed.put(((SegmentReader) reader).core, Boolean.TRUE);
final int maxDoc = reader.maxDoc();
final Bits liveDocs = reader.getLiveDocs();
int sum = 0;
final int inc = Math.max(1, maxDoc/50);
for(int docID=0;docID delIDs = Collections.synchronizedSet(new HashSet());
final Set delPackIDs = Collections.synchronizedSet(new HashSet());
final List allSubDocs = Collections.synchronizedList(new ArrayList());
final long stopTime = System.currentTimeMillis() + RUN_TIME_SEC*1000;
final Thread[] indexThreads = launchIndexingThreads(docs, NUM_INDEX_THREADS, stopTime, delIDs, delPackIDs, allSubDocs);
if (VERBOSE) {
System.out.println("TEST: DONE start " + NUM_INDEX_THREADS + " indexing threads [" + (System.currentTimeMillis()-t0) + " ms]");
}
// Let index build up a bit
Thread.sleep(100);
doSearching(es, stopTime);
if (VERBOSE) {
System.out.println("TEST: all searching done [" + (System.currentTimeMillis()-t0) + " ms]");
}
for(Thread thread : indexThreads) {
thread.join();
}
if (VERBOSE) {
System.out.println("TEST: done join indexing threads [" + (System.currentTimeMillis()-t0) + " ms]; addCount=" + addCount + " delCount=" + delCount);
}
final IndexSearcher s = getFinalSearcher();
if (VERBOSE) {
System.out.println("TEST: finalSearcher=" + s);
}
assertFalse(failed.get());
boolean doFail = false;
// Verify: make sure delIDs are in fact deleted:
for(String id : delIDs) {
final TopDocs hits = s.search(new TermQuery(new Term("docid", id)), 1);
if (hits.totalHits != 0) {
System.out.println("doc id=" + id + " is supposed to be deleted, but got " + hits.totalHits + " hits; first docID=" + hits.scoreDocs[0].doc);
doFail = true;
}
}
// Verify: make sure delPackIDs are in fact deleted:
for(String id : delPackIDs) {
final TopDocs hits = s.search(new TermQuery(new Term("packID", id)), 1);
if (hits.totalHits != 0) {
System.out.println("packID=" + id + " is supposed to be deleted, but got " + hits.totalHits + " matches");
doFail = true;
}
}
// Verify: make sure each group of sub-docs are still in docID order:
for(SubDocs subDocs : allSubDocs) {
TopDocs hits = s.search(new TermQuery(new Term("packID", subDocs.packID)), 20);
if (!subDocs.deleted) {
// We sort by relevance but the scores should be identical so sort falls back to by docID:
if (hits.totalHits != subDocs.subIDs.size()) {
System.out.println("packID=" + subDocs.packID + ": expected " + subDocs.subIDs.size() + " hits but got " + hits.totalHits);
doFail = true;
} else {
int lastDocID = -1;
int startDocID = -1;
for(ScoreDoc scoreDoc : hits.scoreDocs) {
final int docID = scoreDoc.doc;
if (lastDocID != -1) {
assertEquals(1+lastDocID, docID);
} else {
startDocID = docID;
}
lastDocID = docID;
final Document doc = s.doc(docID);
assertEquals(subDocs.packID, doc.get("packID"));
}
lastDocID = startDocID - 1;
for(String subID : subDocs.subIDs) {
hits = s.search(new TermQuery(new Term("docid", subID)), 1);
assertEquals(1, hits.totalHits);
final int docID = hits.scoreDocs[0].doc;
if (lastDocID != -1) {
assertEquals(1+lastDocID, docID);
}
lastDocID = docID;
}
}
} else {
// Pack was deleted -- make sure its docs are
// deleted. We can't verify packID is deleted
// because we can re-use packID for update:
for(String subID : subDocs.subIDs) {
assertEquals(0, s.search(new TermQuery(new Term("docid", subID)), 1).totalHits);
}
}
}
// Verify: make sure all not-deleted docs are in fact
// not deleted:
final int endID = Integer.parseInt(docs.nextDoc().get("docid"));
docs.close();
for(int id=0;id © 2015 - 2025 Weber Informatics LLC | Privacy Policy