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
|
/*
* 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.fielddata.plain;
import org.apache.lucene.index.LeafReaderContext;
import org.apache.lucene.index.Terms;
import org.apache.lucene.index.TermsEnum;
import org.apache.lucene.util.BytesRef;
import org.elasticsearch.ElasticsearchException;
import org.elasticsearch.index.AbstractIndexComponent;
import org.elasticsearch.index.IndexSettings;
import org.elasticsearch.index.fielddata.AtomicFieldData;
import org.elasticsearch.index.fielddata.FieldDataType;
import org.elasticsearch.index.fielddata.IndexFieldData;
import org.elasticsearch.index.fielddata.IndexFieldDataCache;
import org.elasticsearch.index.fielddata.RamAccountingTermsEnum;
import org.elasticsearch.index.mapper.MappedFieldType;
import java.io.IOException;
/**
*/
public abstract class AbstractIndexFieldData<FD extends AtomicFieldData> extends AbstractIndexComponent implements IndexFieldData<FD> {
private final MappedFieldType.Names fieldNames;
protected final FieldDataType fieldDataType;
protected final IndexFieldDataCache cache;
public AbstractIndexFieldData(IndexSettings indexSettings, MappedFieldType.Names fieldNames, FieldDataType fieldDataType, IndexFieldDataCache cache) {
super(indexSettings);
this.fieldNames = fieldNames;
this.fieldDataType = fieldDataType;
this.cache = cache;
}
@Override
public MappedFieldType.Names getFieldNames() {
return this.fieldNames;
}
@Override
public FieldDataType getFieldDataType() {
return fieldDataType;
}
@Override
public void clear() {
cache.clear(fieldNames.indexName());
}
@Override
public FD load(LeafReaderContext context) {
if (context.reader().getFieldInfos().fieldInfo(fieldNames.indexName()) == null) {
// Some leaf readers may be wrapped and report different set of fields and use the same cache key.
// If a field can't be found then it doesn't mean it isn't there,
// so if a field doesn't exist then we don't cache it and just return an empty field data instance.
// The next time the field is found, we do cache.
return empty(context.reader().maxDoc());
}
try {
FD fd = cache.load(context, this);
return fd;
} catch (Throwable e) {
if (e instanceof ElasticsearchException) {
throw (ElasticsearchException) e;
} else {
throw new ElasticsearchException(e);
}
}
}
/**
* @param maxDoc of the current reader
* @return an empty field data instances for field data lookups of empty segments (returning no values)
*/
protected abstract FD empty(int maxDoc);
/**
* A {@code PerValueEstimator} is a sub-class that can be used to estimate
* the memory overhead for loading the data. Each field data
* implementation should implement its own {@code PerValueEstimator} if it
* intends to take advantage of the MemoryCircuitBreaker.
* <p>
* Note that the .beforeLoad(...) and .afterLoad(...) methods must be
* manually called.
*/
public interface PerValueEstimator {
/**
* @return the number of bytes for the given term
*/
public long bytesPerValue(BytesRef term);
/**
* Execute any pre-loading estimations for the terms. May also
* optionally wrap a {@link TermsEnum} in a
* {@link RamAccountingTermsEnum}
* which will estimate the memory on a per-term basis.
*
* @param terms terms to be estimated
* @return A TermsEnum for the given terms
*/
public TermsEnum beforeLoad(Terms terms) throws IOException;
/**
* Possibly adjust a circuit breaker after field data has been loaded,
* now that the actual amount of memory used by the field data is known
*
* @param termsEnum terms that were loaded
* @param actualUsed actual field data memory usage
*/
public void afterLoad(TermsEnum termsEnum, long actualUsed);
}
}
|
