1
|
|
|
<?php |
2
|
|
|
declare(strict_types=1); |
3
|
|
|
|
4
|
|
|
namespace Level23\Druid\Context; |
5
|
|
|
|
6
|
|
|
/** |
7
|
|
|
* Class QueryContext |
8
|
|
|
* |
9
|
|
|
* The query context is used for various query configuration parameters. The following parameters apply to all queries. |
10
|
|
|
* |
11
|
|
|
* @package Level23\Druid\Context |
12
|
|
|
*/ |
13
|
|
|
class QueryContext extends Context implements ContextInterface |
14
|
|
|
{ |
15
|
|
|
/** |
16
|
|
|
* Query timeout in millis, beyond which unfinished queries will be cancelled. 0 timeout means no timeout. To set |
17
|
|
|
* the default timeout, see Broker configuration |
18
|
|
|
* |
19
|
|
|
* @param int $timeout |
20
|
|
|
* |
21
|
|
|
* @return $this; |
22
|
|
|
*/ |
23
|
8 |
|
public function setTimeout(int $timeout) |
24
|
|
|
{ |
25
|
8 |
|
$this->properties['timeout'] = $timeout; |
26
|
|
|
|
27
|
8 |
|
return $this; |
28
|
|
|
} |
29
|
|
|
|
30
|
|
|
/** |
31
|
|
|
* Query Priority. Queries with higher priority get precedence for computational resources. |
32
|
|
|
* |
33
|
|
|
* @param int $priority |
34
|
|
|
* |
35
|
|
|
* @return $this; |
36
|
|
|
*/ |
37
|
11 |
|
public function setPriority(int $priority) |
38
|
|
|
{ |
39
|
11 |
|
$this->properties['priority'] = $priority; |
40
|
|
|
|
41
|
11 |
|
return $this; |
42
|
|
|
} |
43
|
|
|
|
44
|
|
|
/** |
45
|
|
|
* Unique identifier given to this query. If a query ID is set or known, this can be used to cancel the query |
46
|
|
|
* |
47
|
|
|
* @param string $queryId |
48
|
|
|
* |
49
|
|
|
* @return $this; |
50
|
|
|
*/ |
51
|
5 |
|
public function setQueryId(string $queryId) |
52
|
|
|
{ |
53
|
5 |
|
$this->properties['queryId'] = $queryId; |
54
|
|
|
|
55
|
5 |
|
return $this; |
56
|
|
|
} |
57
|
|
|
|
58
|
|
|
/** |
59
|
|
|
* Flag indicating whether to leverage the query cache for this query. When set to false, it disables reading from |
60
|
|
|
* the query cache for this query. When set to true, Apache Druid (incubating) uses druid.broker.cache.useCache or |
61
|
|
|
* druid.historical.cache.useCache to determine whether or not to read from the query cache |
62
|
|
|
* |
63
|
|
|
* @param bool $useCache |
64
|
|
|
* |
65
|
|
|
* @return $this; |
66
|
|
|
*/ |
67
|
5 |
|
public function setUseCache(bool $useCache) |
68
|
|
|
{ |
69
|
5 |
|
$this->properties['useCache'] = $useCache; |
70
|
|
|
|
71
|
5 |
|
return $this; |
72
|
|
|
} |
73
|
|
|
|
74
|
|
|
/** |
75
|
|
|
* Flag indicating whether to save the results of the query to the query cache. Primarily used for debugging. When |
76
|
|
|
* set to false, it disables saving the results of this query to the query cache. When set to true, Druid uses |
77
|
|
|
* druid.broker.cache.populateCache or druid.historical.cache.populateCache to determine whether or not to save the |
78
|
|
|
* results of this query to the query cache |
79
|
|
|
* |
80
|
|
|
* @param bool $populateCache |
81
|
|
|
* |
82
|
|
|
* @return $this; |
83
|
|
|
*/ |
84
|
5 |
|
public function setPopulateCache(bool $populateCache) |
85
|
|
|
{ |
86
|
5 |
|
$this->properties['populateCache'] = $populateCache; |
87
|
|
|
|
88
|
5 |
|
return $this; |
89
|
|
|
} |
90
|
|
|
|
91
|
|
|
/** |
92
|
|
|
* Flag indicating whether to leverage the result level cache for this query. When set to false, it disables |
93
|
|
|
* reading from the query cache for this query. When set to true, Druid uses druid.broker.cache.useResultLevelCache |
94
|
|
|
* to determine whether or not to read from the result-level query cache |
95
|
|
|
* |
96
|
|
|
* @param bool $useResultLevelCache |
97
|
|
|
* |
98
|
|
|
* @return $this; |
99
|
|
|
*/ |
100
|
5 |
|
public function setUseResultLevelCache(bool $useResultLevelCache) |
101
|
|
|
{ |
102
|
5 |
|
$this->properties['useResultLevelCache'] = $useResultLevelCache; |
103
|
|
|
|
104
|
5 |
|
return $this; |
105
|
|
|
} |
106
|
|
|
|
107
|
|
|
/** |
108
|
|
|
* Flag indicating whether to save the results of the query to the result level cache. Primarily used for |
109
|
|
|
* debugging. When set to false, it disables saving the results of this query to the query cache. When set to true, |
110
|
|
|
* Druid uses druid.broker.cache.populateResultLevelCache to determine whether or not to save the results of this |
111
|
|
|
* query to the result-level query cache |
112
|
|
|
* |
113
|
|
|
* @param bool $populateResultLevelCache |
114
|
|
|
* |
115
|
|
|
* @return $this; |
116
|
|
|
*/ |
117
|
5 |
|
public function setPopulateResultLevelCache(bool $populateResultLevelCache) |
118
|
|
|
{ |
119
|
5 |
|
$this->properties['populateResultLevelCache'] = $populateResultLevelCache; |
120
|
|
|
|
121
|
5 |
|
return $this; |
122
|
|
|
} |
123
|
|
|
|
124
|
|
|
/** |
125
|
|
|
* Return "by segment" results. Primarily used for debugging, setting it to true returns results associated with |
126
|
|
|
* the data segment they came from |
127
|
|
|
* |
128
|
|
|
* @param bool $bySegment |
129
|
|
|
* |
130
|
|
|
* @return $this; |
131
|
|
|
*/ |
132
|
5 |
|
public function setBySegment(bool $bySegment) |
133
|
|
|
{ |
134
|
5 |
|
$this->properties['bySegment'] = $bySegment; |
135
|
|
|
|
136
|
5 |
|
return $this; |
137
|
|
|
} |
138
|
|
|
|
139
|
|
|
/** |
140
|
|
|
* Flag indicating whether to "finalize" aggregation results. Primarily used for debugging. For instance, the |
141
|
|
|
* hyperUnique aggregator will return the full HyperLogLog sketch instead of the estimated cardinality when this |
142
|
|
|
* flag is set to false |
143
|
|
|
* |
144
|
|
|
* @param bool $finalize |
145
|
|
|
* |
146
|
|
|
* @return $this; |
147
|
|
|
*/ |
148
|
9 |
|
public function setFinalize(bool $finalize) |
149
|
|
|
{ |
150
|
9 |
|
$this->properties['finalize'] = $finalize; |
151
|
|
|
|
152
|
9 |
|
return $this; |
153
|
|
|
} |
154
|
|
|
|
155
|
|
|
/** |
156
|
|
|
* At the Broker process level, long interval queries (of any type) may be broken into shorter interval queries to |
157
|
|
|
* parallelize merging more than normal. Broken up queries will use a larger share of cluster resources, but, if |
158
|
|
|
* you use groupBy "v1, it may be able to complete faster as a result. Use ISO 8601 periods. For example, if this |
159
|
|
|
* property is set to P1M (one month), then a query covering a year would be broken into 12 smaller queries. The |
160
|
|
|
* broker uses its query processing executor service to initiate processing for query chunks, so make sure |
161
|
|
|
* "druid.processing.numThreads" is configured appropriately on the broker. groupBy queries do not support |
162
|
|
|
* chunkPeriod by default, although they do if using the legacy "v1" engine. This context is deprecated since it's |
163
|
|
|
* only useful for groupBy "v1", and will be removed in the future releases. |
164
|
|
|
* |
165
|
|
|
* @param string $chunkPeriod |
166
|
|
|
* |
167
|
|
|
* @return $this; |
168
|
|
|
*/ |
169
|
5 |
|
public function setChunkPeriod(string $chunkPeriod) |
170
|
|
|
{ |
171
|
5 |
|
$this->properties['chunkPeriod'] = $chunkPeriod; |
172
|
|
|
|
173
|
5 |
|
return $this; |
174
|
|
|
} |
175
|
|
|
|
176
|
|
|
/** |
177
|
|
|
* Maximum number of bytes gathered from data processes such as historicals and realtime processes to execute a |
178
|
|
|
* query. This parameter can be used to further reduce maxScatterGatherBytes limit at query time. See Broker |
179
|
|
|
* configuration for more details. |
180
|
|
|
* |
181
|
|
|
* @param int $maxScatterGatherBytes |
182
|
|
|
* |
183
|
|
|
* @return $this; |
184
|
|
|
*/ |
185
|
5 |
|
public function setMaxScatterGatherBytes(int $maxScatterGatherBytes) |
186
|
|
|
{ |
187
|
5 |
|
$this->properties['maxScatterGatherBytes'] = $maxScatterGatherBytes; |
188
|
|
|
|
189
|
5 |
|
return $this; |
190
|
|
|
} |
191
|
|
|
|
192
|
|
|
/** |
193
|
|
|
* Maximum number of bytes queued per query before exerting back pressure on the channel to the data server. Similar |
194
|
|
|
* to maxScatterGatherBytes, except unlike that configuration, this one will trigger back pressure rather than query |
195
|
|
|
* failure. Zero means disabled. |
196
|
|
|
* |
197
|
|
|
* @param int $maxQueuedBytes |
198
|
|
|
* |
199
|
|
|
* @return $this; |
200
|
|
|
*/ |
201
|
5 |
|
public function setMaxQueuedBytes(int $maxQueuedBytes) |
202
|
|
|
{ |
203
|
5 |
|
$this->properties['maxQueuedBytes'] = $maxQueuedBytes; |
204
|
|
|
|
205
|
5 |
|
return $this; |
206
|
|
|
} |
207
|
|
|
|
208
|
|
|
/** |
209
|
|
|
* If true, DateTime is serialized as long in the result returned by Broker and the data transportation between |
210
|
|
|
* Broker and compute process |
211
|
|
|
* |
212
|
|
|
* @param bool $serializeDateTimeAsLong |
213
|
|
|
* |
214
|
|
|
* @return $this; |
215
|
|
|
*/ |
216
|
5 |
|
public function setSerializeDateTimeAsLong(bool $serializeDateTimeAsLong) |
217
|
|
|
{ |
218
|
5 |
|
$this->properties['serializeDateTimeAsLong'] = $serializeDateTimeAsLong; |
219
|
|
|
|
220
|
5 |
|
return $this; |
221
|
|
|
} |
222
|
|
|
|
223
|
|
|
/** |
224
|
|
|
* If true, DateTime is serialized as long in the data transportation between Broker and compute process |
225
|
|
|
* |
226
|
|
|
* @param bool $serializeDateTimeAsLongInner |
227
|
|
|
* |
228
|
|
|
* @return $this; |
229
|
|
|
*/ |
230
|
5 |
|
public function setSerializeDateTimeAsLongInner(bool $serializeDateTimeAsLongInner) |
231
|
|
|
{ |
232
|
5 |
|
$this->properties['serializeDateTimeAsLongInner'] = $serializeDateTimeAsLongInner; |
233
|
|
|
|
234
|
5 |
|
return $this; |
235
|
|
|
} |
236
|
|
|
|
237
|
|
|
/** |
238
|
|
|
* Enable parallel result merging on the Broker. |
239
|
|
|
* Note that druid.processing.merge.useParallelMergePool must be enabled for this setting to be |
240
|
|
|
* set to true. See Broker configuration for more details. |
241
|
|
|
* |
242
|
|
|
* @param bool $enableParallelMerge |
243
|
|
|
* |
244
|
|
|
* @return $this |
245
|
|
|
*/ |
246
|
5 |
|
public function setEnableParallelMerge(bool $enableParallelMerge) |
247
|
|
|
{ |
248
|
5 |
|
$this->properties['enableParallelMerge'] = $enableParallelMerge; |
249
|
|
|
|
250
|
5 |
|
return $this; |
251
|
|
|
} |
252
|
|
|
|
253
|
|
|
/** |
254
|
|
|
* Maximum number of parallel threads to use for parallel result merging on the Broker. |
255
|
|
|
* See Broker configuration for more details. |
256
|
|
|
* |
257
|
|
|
* @param int $parallelMergeParallelism |
258
|
|
|
* |
259
|
|
|
* @return $this |
260
|
|
|
*/ |
261
|
5 |
|
public function setParallelMergeParallelism(int $parallelMergeParallelism) |
262
|
|
|
{ |
263
|
5 |
|
$this->properties['parallelMergeParallelism'] = $parallelMergeParallelism; |
264
|
|
|
|
265
|
5 |
|
return $this; |
266
|
|
|
} |
267
|
|
|
|
268
|
|
|
/** |
269
|
|
|
* Number of rows to yield per ForkJoinPool merge task for parallel result merging on the Broker, |
270
|
|
|
* before forking off a new task to continue merging sequences. |
271
|
|
|
* See Broker configuration for more details. |
272
|
|
|
* |
273
|
|
|
* @param int $parallelMergeInitialYieldRows |
274
|
|
|
* |
275
|
|
|
* @return $this |
276
|
|
|
*/ |
277
|
5 |
|
public function setParallelMergeInitialYieldRows(int $parallelMergeInitialYieldRows) |
278
|
|
|
{ |
279
|
5 |
|
$this->properties['parallelMergeInitialYieldRows'] = $parallelMergeInitialYieldRows; |
280
|
|
|
|
281
|
5 |
|
return $this; |
282
|
|
|
} |
283
|
|
|
|
284
|
|
|
/** |
285
|
|
|
* Size of result batches to operate on in ForkJoinPool merge tasks for parallel result |
286
|
|
|
* merging on the Broker. See Broker configuration for more details. |
287
|
|
|
* |
288
|
|
|
* @param int $parallelMergeSmallBatchRows |
289
|
|
|
* |
290
|
|
|
* @return $this |
291
|
|
|
*/ |
292
|
5 |
|
public function setParallelMergeSmallBatchRows(int $parallelMergeSmallBatchRows) |
293
|
|
|
{ |
294
|
5 |
|
$this->properties['parallelMergeSmallBatchRows'] = $parallelMergeSmallBatchRows; |
295
|
|
|
|
296
|
5 |
|
return $this; |
297
|
|
|
} |
298
|
|
|
|
299
|
|
|
/** |
300
|
|
|
* If true, Druid will attempt to convert the query filter to Conjunctive Normal Form (CNF). |
301
|
|
|
* During query processing, columns can be pre-filtered by intersecting the bitmap indexes of |
302
|
|
|
* all values that match the eligible filters, often greatly reducing the raw number of rows |
303
|
|
|
* which need to be scanned. But this effect only happens for the top level filter, |
304
|
|
|
* or individual clauses of a top level 'and' filter. As such, filters in CNF potentially have |
305
|
|
|
* a higher chance to utilize a large amount of bitmap indexes on string columns during |
306
|
|
|
* pre-filtering. However, this setting should be used with great caution, as it can sometimes |
307
|
|
|
* have a negative effect on performance, and in some cases, the act of computing CNF of a |
308
|
|
|
* filter can be expensive. We recommend hand tuning your filters to produce an optimal form |
309
|
|
|
* if possible, or at least verifying through experimentation that using this parameter actually |
310
|
|
|
* improves your query performance with no ill-effects. |
311
|
|
|
* |
312
|
|
|
* @param bool $useFilterCNF |
313
|
|
|
* |
314
|
|
|
* @return $this |
315
|
|
|
*/ |
316
|
5 |
|
public function setUseFilterCNF(bool $useFilterCNF) |
317
|
|
|
{ |
318
|
5 |
|
$this->properties['useFilterCNF'] = $useFilterCNF; |
319
|
|
|
|
320
|
5 |
|
return $this; |
321
|
|
|
} |
322
|
|
|
|
323
|
|
|
/** |
324
|
|
|
* Enable secondary partition pruning on the Broker. The Broker will always prune |
325
|
|
|
* unnecessary segments from the input scan based on a filter on time intervals, |
326
|
|
|
* but if the data is further partitioned with hash or range partitioning, |
327
|
|
|
* this option will enable additional pruning based on a filter on secondary |
328
|
|
|
* partition dimensions. |
329
|
|
|
* |
330
|
|
|
* @param bool $secondaryPartitionPruning |
331
|
|
|
* |
332
|
|
|
* @return $this |
333
|
|
|
*/ |
334
|
5 |
|
public function setSecondaryPartitionPruning(bool $secondaryPartitionPruning) |
335
|
|
|
{ |
336
|
5 |
|
$this->properties['secondaryPartitionPruning'] = $secondaryPartitionPruning; |
337
|
|
|
|
338
|
5 |
|
return $this; |
339
|
|
|
} |
340
|
|
|
} |