1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
|
/*
* Licensed to Elasticsearch under one or more contributor
* license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright
* ownership. Elasticsearch 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.elasticsearch.index.cache.bitset;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StringField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.LeafReaderContext;
import org.apache.lucene.index.LogByteSizeMergePolicy;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.MatchAllDocsQuery;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.join.BitSetProducer;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Accountable;
import org.apache.lucene.util.BitSet;
import org.apache.lucene.util.IOUtils;
import org.elasticsearch.common.lucene.index.ElasticsearchDirectoryReader;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.index.Index;
import org.elasticsearch.index.IndexSettings;
import org.elasticsearch.index.shard.ShardId;
import org.elasticsearch.indices.IndicesWarmer;
import org.elasticsearch.test.ESTestCase;
import org.elasticsearch.test.IndexSettingsModule;
import java.io.IOException;
import java.util.concurrent.atomic.AtomicInteger;
import java.util.concurrent.atomic.AtomicLong;
import static org.hamcrest.Matchers.equalTo;
public class BitSetFilterCacheTests extends ESTestCase {
private static final IndexSettings INDEX_SETTINGS = IndexSettingsModule.newIndexSettings("test", Settings.EMPTY);
private final IndicesWarmer warmer = new IndicesWarmer(Settings.EMPTY, null);
private static int matchCount(BitSetProducer producer, IndexReader reader) throws IOException {
int count = 0;
for (LeafReaderContext ctx : reader.leaves()) {
final BitSet bitSet = producer.getBitSet(ctx);
if (bitSet != null) {
count += bitSet.cardinality();
}
}
return count;
}
public void testInvalidateEntries() throws Exception {
IndexWriter writer = new IndexWriter(
new RAMDirectory(),
new IndexWriterConfig(new StandardAnalyzer()).setMergePolicy(new LogByteSizeMergePolicy())
);
Document document = new Document();
document.add(new StringField("field", "value", Field.Store.NO));
writer.addDocument(document);
writer.commit();
document = new Document();
document.add(new StringField("field", "value", Field.Store.NO));
writer.addDocument(document);
writer.commit();
document = new Document();
document.add(new StringField("field", "value", Field.Store.NO));
writer.addDocument(document);
writer.commit();
DirectoryReader reader = DirectoryReader.open(writer, false);
reader = ElasticsearchDirectoryReader.wrap(reader, new ShardId("test", "_na_", 0));
IndexSearcher searcher = new IndexSearcher(reader);
BitsetFilterCache cache = new BitsetFilterCache(INDEX_SETTINGS, warmer, new BitsetFilterCache.Listener() {
@Override
public void onCache(ShardId shardId, Accountable accountable) {
}
@Override
public void onRemoval(ShardId shardId, Accountable accountable) {
}
});
BitSetProducer filter = cache.getBitSetProducer(new TermQuery(new Term("field", "value")));
assertThat(matchCount(filter, reader), equalTo(3));
// now cached
assertThat(matchCount(filter, reader), equalTo(3));
// There are 3 segments
assertThat(cache.getLoadedFilters().weight(), equalTo(3L));
writer.forceMerge(1);
reader.close();
reader = DirectoryReader.open(writer, false);
reader = ElasticsearchDirectoryReader.wrap(reader, new ShardId("test", "_na_", 0));
searcher = new IndexSearcher(reader);
assertThat(matchCount(filter, reader), equalTo(3));
// now cached
assertThat(matchCount(filter, reader), equalTo(3));
// Only one segment now, so the size must be 1
assertThat(cache.getLoadedFilters().weight(), equalTo(1L));
reader.close();
writer.close();
// There is no reference from readers and writer to any segment in the test index, so the size in the fbs cache must be 0
assertThat(cache.getLoadedFilters().weight(), equalTo(0L));
}
public void testListener() throws IOException {
IndexWriter writer = new IndexWriter(
new RAMDirectory(),
new IndexWriterConfig(new StandardAnalyzer()).setMergePolicy(new LogByteSizeMergePolicy())
);
Document document = new Document();
document.add(new StringField("field", "value", Field.Store.NO));
writer.addDocument(document);
writer.commit();
final DirectoryReader writerReader = DirectoryReader.open(writer, false);
final IndexReader reader = ElasticsearchDirectoryReader.wrap(writerReader, new ShardId("test", "_na_", 0));
final AtomicLong stats = new AtomicLong();
final AtomicInteger onCacheCalls = new AtomicInteger();
final AtomicInteger onRemoveCalls = new AtomicInteger();
final BitsetFilterCache cache = new BitsetFilterCache(INDEX_SETTINGS, warmer, new BitsetFilterCache.Listener() {
@Override
public void onCache(ShardId shardId, Accountable accountable) {
onCacheCalls.incrementAndGet();
stats.addAndGet(accountable.ramBytesUsed());
if (writerReader != reader) {
assertNotNull(shardId);
assertEquals("test", shardId.getIndexName());
assertEquals(0, shardId.id());
} else {
assertNull(shardId);
}
}
@Override
public void onRemoval(ShardId shardId, Accountable accountable) {
onRemoveCalls.incrementAndGet();
stats.addAndGet(-accountable.ramBytesUsed());
if (writerReader != reader) {
assertNotNull(shardId);
assertEquals("test", shardId.getIndexName());
assertEquals(0, shardId.id());
} else {
assertNull(shardId);
}
}
});
BitSetProducer filter = cache.getBitSetProducer(new TermQuery(new Term("field", "value")));
assertThat(matchCount(filter, reader), equalTo(1));
assertTrue(stats.get() > 0);
assertEquals(1, onCacheCalls.get());
assertEquals(0, onRemoveCalls.get());
IOUtils.close(reader, writer);
assertEquals(1, onRemoveCalls.get());
assertEquals(0, stats.get());
}
public void testSetNullListener() {
try {
new BitsetFilterCache(INDEX_SETTINGS, warmer, null);
fail("listener can't be null");
} catch (IllegalArgumentException ex) {
assertEquals("listener must not be null", ex.getMessage());
// all is well
}
}
public void testRejectOtherIndex() throws IOException {
BitsetFilterCache cache = new BitsetFilterCache(INDEX_SETTINGS, warmer, new BitsetFilterCache.Listener() {
@Override
public void onCache(ShardId shardId, Accountable accountable) {
}
@Override
public void onRemoval(ShardId shardId, Accountable accountable) {
}
});
Directory dir = newDirectory();
IndexWriter writer = new IndexWriter(
dir,
newIndexWriterConfig()
);
writer.addDocument(new Document());
DirectoryReader reader = DirectoryReader.open(writer, true);
writer.close();
reader = ElasticsearchDirectoryReader.wrap(reader, new ShardId("test2", "_na_", 0));
BitSetProducer producer = cache.getBitSetProducer(new MatchAllDocsQuery());
try {
producer.getBitSet(reader.leaves().get(0));
fail();
} catch (IllegalStateException expected) {
assertEquals("Trying to load bit set for index [test2] with cache of index [test]", expected.getMessage());
} finally {
IOUtils.close(reader, dir);
}
}
}
|
