TLA Line data Source code
1 : /*-------------------------------------------------------------------------
2 : *
3 : * array_typanalyze.c
4 : * Functions for gathering statistics from array columns
5 : *
6 : * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
7 : * Portions Copyright (c) 1994, Regents of the University of California
8 : *
9 : *
10 : * IDENTIFICATION
11 : * src/backend/utils/adt/array_typanalyze.c
12 : *
13 : *-------------------------------------------------------------------------
14 : */
15 : #include "postgres.h"
16 :
17 : #include "access/detoast.h"
18 : #include "commands/vacuum.h"
19 : #include "utils/array.h"
20 : #include "utils/builtins.h"
21 : #include "utils/datum.h"
22 : #include "utils/lsyscache.h"
23 : #include "utils/typcache.h"
24 :
25 :
26 : /*
27 : * To avoid consuming too much memory, IO and CPU load during analysis, and/or
28 : * too much space in the resulting pg_statistic rows, we ignore arrays that
29 : * are wider than ARRAY_WIDTH_THRESHOLD (after detoasting!). Note that this
30 : * number is considerably more than the similar WIDTH_THRESHOLD limit used
31 : * in analyze.c's standard typanalyze code.
32 : */
33 : #define ARRAY_WIDTH_THRESHOLD 0x10000
34 :
35 : /* Extra data for compute_array_stats function */
36 : typedef struct
37 : {
38 : /* Information about array element type */
39 : Oid type_id; /* element type's OID */
40 : Oid eq_opr; /* default equality operator's OID */
41 : Oid coll_id; /* collation to use */
42 : bool typbyval; /* physical properties of element type */
43 : int16 typlen;
44 : char typalign;
45 :
46 : /*
47 : * Lookup data for element type's comparison and hash functions (these are
48 : * in the type's typcache entry, which we expect to remain valid over the
49 : * lifespan of the ANALYZE run)
50 : */
51 : FmgrInfo *cmp;
52 : FmgrInfo *hash;
53 :
54 : /* Saved state from std_typanalyze() */
55 : AnalyzeAttrComputeStatsFunc std_compute_stats;
56 : void *std_extra_data;
57 : } ArrayAnalyzeExtraData;
58 :
59 : /*
60 : * While compute_array_stats is running, we keep a pointer to the extra data
61 : * here for use by assorted subroutines. compute_array_stats doesn't
62 : * currently need to be re-entrant, so avoiding this is not worth the extra
63 : * notational cruft that would be needed.
64 : */
65 : static ArrayAnalyzeExtraData *array_extra_data;
66 :
67 : /* A hash table entry for the Lossy Counting algorithm */
68 : typedef struct
69 : {
70 : Datum key; /* This is 'e' from the LC algorithm. */
71 : int frequency; /* This is 'f'. */
72 : int delta; /* And this is 'delta'. */
73 : int last_container; /* For de-duplication of array elements. */
74 : } TrackItem;
75 :
76 : /* A hash table entry for distinct-elements counts */
77 : typedef struct
78 : {
79 : int count; /* Count of distinct elements in an array */
80 : int frequency; /* Number of arrays seen with this count */
81 : } DECountItem;
82 :
83 : static void compute_array_stats(VacAttrStats *stats,
84 : AnalyzeAttrFetchFunc fetchfunc, int samplerows, double totalrows);
85 : static void prune_element_hashtable(HTAB *elements_tab, int b_current);
86 : static uint32 element_hash(const void *key, Size keysize);
87 : static int element_match(const void *key1, const void *key2, Size keysize);
88 : static int element_compare(const void *key1, const void *key2);
89 : static int trackitem_compare_frequencies_desc(const void *e1, const void *e2, void *arg);
90 : static int trackitem_compare_element(const void *e1, const void *e2, void *arg);
91 : static int countitem_compare_count(const void *e1, const void *e2, void *arg);
92 :
93 :
94 : /*
95 : * array_typanalyze -- typanalyze function for array columns
96 : */
97 : Datum
98 CBC 14084 : array_typanalyze(PG_FUNCTION_ARGS)
99 : {
100 14084 : VacAttrStats *stats = (VacAttrStats *) PG_GETARG_POINTER(0);
101 : Oid element_typeid;
102 : TypeCacheEntry *typentry;
103 : ArrayAnalyzeExtraData *extra_data;
104 :
105 : /*
106 : * Call the standard typanalyze function. It may fail to find needed
107 : * operators, in which case we also can't do anything, so just fail.
108 : */
109 14084 : if (!std_typanalyze(stats))
110 UBC 0 : PG_RETURN_BOOL(false);
111 :
112 : /*
113 : * Check attribute data type is a varlena array (or a domain over one).
114 : */
115 CBC 14084 : element_typeid = get_base_element_type(stats->attrtypid);
116 14084 : if (!OidIsValid(element_typeid))
117 UBC 0 : elog(ERROR, "array_typanalyze was invoked for non-array type %u",
118 : stats->attrtypid);
119 :
120 : /*
121 : * Gather information about the element type. If we fail to find
122 : * something, return leaving the state from std_typanalyze() in place.
123 : */
124 CBC 14084 : typentry = lookup_type_cache(element_typeid,
125 : TYPECACHE_EQ_OPR |
126 : TYPECACHE_CMP_PROC_FINFO |
127 : TYPECACHE_HASH_PROC_FINFO);
128 :
129 14084 : if (!OidIsValid(typentry->eq_opr) ||
130 13760 : !OidIsValid(typentry->cmp_proc_finfo.fn_oid) ||
131 9208 : !OidIsValid(typentry->hash_proc_finfo.fn_oid))
132 4876 : PG_RETURN_BOOL(true);
133 :
134 : /* Store our findings for use by compute_array_stats() */
135 9208 : extra_data = (ArrayAnalyzeExtraData *) palloc(sizeof(ArrayAnalyzeExtraData));
136 9208 : extra_data->type_id = typentry->type_id;
137 9208 : extra_data->eq_opr = typentry->eq_opr;
138 9208 : extra_data->coll_id = stats->attrcollid; /* collation we should use */
139 9208 : extra_data->typbyval = typentry->typbyval;
140 9208 : extra_data->typlen = typentry->typlen;
141 9208 : extra_data->typalign = typentry->typalign;
142 9208 : extra_data->cmp = &typentry->cmp_proc_finfo;
143 9208 : extra_data->hash = &typentry->hash_proc_finfo;
144 :
145 : /* Save old compute_stats and extra_data for scalar statistics ... */
146 9208 : extra_data->std_compute_stats = stats->compute_stats;
147 9208 : extra_data->std_extra_data = stats->extra_data;
148 :
149 : /* ... and replace with our info */
150 9208 : stats->compute_stats = compute_array_stats;
151 9208 : stats->extra_data = extra_data;
152 :
153 : /*
154 : * Note we leave stats->minrows set as std_typanalyze set it. Should it
155 : * be increased for array analysis purposes?
156 : */
157 :
158 9208 : PG_RETURN_BOOL(true);
159 : }
160 :
161 : /*
162 : * compute_array_stats() -- compute statistics for an array column
163 : *
164 : * This function computes statistics useful for determining selectivity of
165 : * the array operators <@, &&, and @>. It is invoked by ANALYZE via the
166 : * compute_stats hook after sample rows have been collected.
167 : *
168 : * We also invoke the standard compute_stats function, which will compute
169 : * "scalar" statistics relevant to the btree-style array comparison operators.
170 : * However, exact duplicates of an entire array may be rare despite many
171 : * arrays sharing individual elements. This especially afflicts long arrays,
172 : * which are also liable to lack all scalar statistics due to the low
173 : * WIDTH_THRESHOLD used in analyze.c. So, in addition to the standard stats,
174 : * we find the most common array elements and compute a histogram of distinct
175 : * element counts.
176 : *
177 : * The algorithm used is Lossy Counting, as proposed in the paper "Approximate
178 : * frequency counts over data streams" by G. S. Manku and R. Motwani, in
179 : * Proceedings of the 28th International Conference on Very Large Data Bases,
180 : * Hong Kong, China, August 2002, section 4.2. The paper is available at
181 : * http://www.vldb.org/conf/2002/S10P03.pdf
182 : *
183 : * The Lossy Counting (aka LC) algorithm goes like this:
184 : * Let s be the threshold frequency for an item (the minimum frequency we
185 : * are interested in) and epsilon the error margin for the frequency. Let D
186 : * be a set of triples (e, f, delta), where e is an element value, f is that
187 : * element's frequency (actually, its current occurrence count) and delta is
188 : * the maximum error in f. We start with D empty and process the elements in
189 : * batches of size w. (The batch size is also known as "bucket size" and is
190 : * equal to 1/epsilon.) Let the current batch number be b_current, starting
191 : * with 1. For each element e we either increment its f count, if it's
192 : * already in D, or insert a new triple into D with values (e, 1, b_current
193 : * - 1). After processing each batch we prune D, by removing from it all
194 : * elements with f + delta <= b_current. After the algorithm finishes we
195 : * suppress all elements from D that do not satisfy f >= (s - epsilon) * N,
196 : * where N is the total number of elements in the input. We emit the
197 : * remaining elements with estimated frequency f/N. The LC paper proves
198 : * that this algorithm finds all elements with true frequency at least s,
199 : * and that no frequency is overestimated or is underestimated by more than
200 : * epsilon. Furthermore, given reasonable assumptions about the input
201 : * distribution, the required table size is no more than about 7 times w.
202 : *
203 : * In the absence of a principled basis for other particular values, we
204 : * follow ts_typanalyze() and use parameters s = 0.07/K, epsilon = s/10.
205 : * But we leave out the correction for stopwords, which do not apply to
206 : * arrays. These parameters give bucket width w = K/0.007 and maximum
207 : * expected hashtable size of about 1000 * K.
208 : *
209 : * Elements may repeat within an array. Since duplicates do not change the
210 : * behavior of <@, && or @>, we want to count each element only once per
211 : * array. Therefore, we store in the finished pg_statistic entry each
212 : * element's frequency as the fraction of all non-null rows that contain it.
213 : * We divide the raw counts by nonnull_cnt to get those figures.
214 : */
215 : static void
216 5965 : compute_array_stats(VacAttrStats *stats, AnalyzeAttrFetchFunc fetchfunc,
217 : int samplerows, double totalrows)
218 : {
219 : ArrayAnalyzeExtraData *extra_data;
220 : int num_mcelem;
221 5965 : int null_elem_cnt = 0;
222 5965 : int analyzed_rows = 0;
223 :
224 : /* This is D from the LC algorithm. */
225 : HTAB *elements_tab;
226 : HASHCTL elem_hash_ctl;
227 : HASH_SEQ_STATUS scan_status;
228 :
229 : /* This is the current bucket number from the LC algorithm */
230 : int b_current;
231 :
232 : /* This is 'w' from the LC algorithm */
233 : int bucket_width;
234 : int array_no;
235 : int64 element_no;
236 : TrackItem *item;
237 : int slot_idx;
238 : HTAB *count_tab;
239 : HASHCTL count_hash_ctl;
240 : DECountItem *count_item;
241 :
242 5965 : extra_data = (ArrayAnalyzeExtraData *) stats->extra_data;
243 :
244 : /*
245 : * Invoke analyze.c's standard analysis function to create scalar-style
246 : * stats for the column. It will expect its own extra_data pointer, so
247 : * temporarily install that.
248 : */
249 5965 : stats->extra_data = extra_data->std_extra_data;
250 5965 : extra_data->std_compute_stats(stats, fetchfunc, samplerows, totalrows);
251 5965 : stats->extra_data = extra_data;
252 :
253 : /*
254 : * Set up static pointer for use by subroutines. We wait till here in
255 : * case std_compute_stats somehow recursively invokes us (probably not
256 : * possible, but ...)
257 : */
258 5965 : array_extra_data = extra_data;
259 :
260 : /*
261 : * We want statistics_target * 10 elements in the MCELEM array. This
262 : * multiplier is pretty arbitrary, but is meant to reflect the fact that
263 : * the number of individual elements tracked in pg_statistic ought to be
264 : * more than the number of values for a simple scalar column.
265 : */
266 5965 : num_mcelem = stats->attr->attstattarget * 10;
267 :
268 : /*
269 : * We set bucket width equal to num_mcelem / 0.007 as per the comment
270 : * above.
271 : */
272 5965 : bucket_width = num_mcelem * 1000 / 7;
273 :
274 : /*
275 : * Create the hashtable. It will be in local memory, so we don't need to
276 : * worry about overflowing the initial size. Also we don't need to pay any
277 : * attention to locking and memory management.
278 : */
279 5965 : elem_hash_ctl.keysize = sizeof(Datum);
280 5965 : elem_hash_ctl.entrysize = sizeof(TrackItem);
281 5965 : elem_hash_ctl.hash = element_hash;
282 5965 : elem_hash_ctl.match = element_match;
283 5965 : elem_hash_ctl.hcxt = CurrentMemoryContext;
284 5965 : elements_tab = hash_create("Analyzed elements table",
285 : num_mcelem,
286 : &elem_hash_ctl,
287 : HASH_ELEM | HASH_FUNCTION | HASH_COMPARE | HASH_CONTEXT);
288 :
289 : /* hashtable for array distinct elements counts */
290 5965 : count_hash_ctl.keysize = sizeof(int);
291 5965 : count_hash_ctl.entrysize = sizeof(DECountItem);
292 5965 : count_hash_ctl.hcxt = CurrentMemoryContext;
293 5965 : count_tab = hash_create("Array distinct element count table",
294 : 64,
295 : &count_hash_ctl,
296 : HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
297 :
298 : /* Initialize counters. */
299 5965 : b_current = 1;
300 5965 : element_no = 0;
301 :
302 : /* Loop over the arrays. */
303 8107412 : for (array_no = 0; array_no < samplerows; array_no++)
304 : {
305 : Datum value;
306 : bool isnull;
307 : ArrayType *array;
308 : int num_elems;
309 : Datum *elem_values;
310 : bool *elem_nulls;
311 : bool null_present;
312 : int j;
313 8101447 : int64 prev_element_no = element_no;
314 : int distinct_count;
315 : bool count_item_found;
316 :
317 8101447 : vacuum_delay_point();
318 :
319 8101447 : value = fetchfunc(stats, array_no, &isnull);
320 8101447 : if (isnull)
321 : {
322 : /* ignore arrays that are null overall */
323 7711706 : continue;
324 : }
325 :
326 : /* Skip too-large values. */
327 389741 : if (toast_raw_datum_size(value) > ARRAY_WIDTH_THRESHOLD)
328 UBC 0 : continue;
329 : else
330 CBC 389741 : analyzed_rows++;
331 :
332 : /*
333 : * Now detoast the array if needed, and deconstruct into datums.
334 : */
335 389741 : array = DatumGetArrayTypeP(value);
336 :
337 389741 : Assert(ARR_ELEMTYPE(array) == extra_data->type_id);
338 389741 : deconstruct_array(array,
339 : extra_data->type_id,
340 389741 : extra_data->typlen,
341 389741 : extra_data->typbyval,
342 389741 : extra_data->typalign,
343 : &elem_values, &elem_nulls, &num_elems);
344 :
345 : /*
346 : * We loop through the elements in the array and add them to our
347 : * tracking hashtable.
348 : */
349 389741 : null_present = false;
350 1722526 : for (j = 0; j < num_elems; j++)
351 : {
352 : Datum elem_value;
353 : bool found;
354 :
355 : /* No null element processing other than flag setting here */
356 1332785 : if (elem_nulls[j])
357 : {
358 20 : null_present = true;
359 250450 : continue;
360 : }
361 :
362 : /* Lookup current element in hashtable, adding it if new */
363 1332765 : elem_value = elem_values[j];
364 1332765 : item = (TrackItem *) hash_search(elements_tab,
365 : &elem_value,
366 : HASH_ENTER, &found);
367 :
368 1332765 : if (found)
369 : {
370 : /* The element value is already on the tracking list */
371 :
372 : /*
373 : * The operators we assist ignore duplicate array elements, so
374 : * count a given distinct element only once per array.
375 : */
376 1048677 : if (item->last_container == array_no)
377 250430 : continue;
378 :
379 798247 : item->frequency++;
380 798247 : item->last_container = array_no;
381 : }
382 : else
383 : {
384 : /* Initialize new tracking list element */
385 :
386 : /*
387 : * If element type is pass-by-reference, we must copy it into
388 : * palloc'd space, so that we can release the array below. (We
389 : * do this so that the space needed for element values is
390 : * limited by the size of the hashtable; if we kept all the
391 : * array values around, it could be much more.)
392 : */
393 568176 : item->key = datumCopy(elem_value,
394 284088 : extra_data->typbyval,
395 284088 : extra_data->typlen);
396 :
397 284088 : item->frequency = 1;
398 284088 : item->delta = b_current - 1;
399 284088 : item->last_container = array_no;
400 : }
401 :
402 : /* element_no is the number of elements processed (ie N) */
403 1082335 : element_no++;
404 :
405 : /* We prune the D structure after processing each bucket */
406 1082335 : if (element_no % bucket_width == 0)
407 : {
408 UBC 0 : prune_element_hashtable(elements_tab, b_current);
409 0 : b_current++;
410 : }
411 : }
412 :
413 : /* Count null element presence once per array. */
414 CBC 389741 : if (null_present)
415 20 : null_elem_cnt++;
416 :
417 : /* Update frequency of the particular array distinct element count. */
418 389741 : distinct_count = (int) (element_no - prev_element_no);
419 389741 : count_item = (DECountItem *) hash_search(count_tab, &distinct_count,
420 : HASH_ENTER,
421 : &count_item_found);
422 :
423 389741 : if (count_item_found)
424 378076 : count_item->frequency++;
425 : else
426 11665 : count_item->frequency = 1;
427 :
428 : /* Free memory allocated while detoasting. */
429 389741 : if (PointerGetDatum(array) != value)
430 366017 : pfree(array);
431 389741 : pfree(elem_values);
432 389741 : pfree(elem_nulls);
433 : }
434 :
435 : /* Skip pg_statistic slots occupied by standard statistics */
436 5965 : slot_idx = 0;
437 10657 : while (slot_idx < STATISTIC_NUM_SLOTS && stats->stakind[slot_idx] != 0)
438 4692 : slot_idx++;
439 5965 : if (slot_idx > STATISTIC_NUM_SLOTS - 2)
440 UBC 0 : elog(ERROR, "insufficient pg_statistic slots for array stats");
441 :
442 : /* We can only compute real stats if we found some non-null values. */
443 CBC 5965 : if (analyzed_rows > 0)
444 : {
445 1703 : int nonnull_cnt = analyzed_rows;
446 : int count_items_count;
447 : int i;
448 : TrackItem **sort_table;
449 : int track_len;
450 : int64 cutoff_freq;
451 : int64 minfreq,
452 : maxfreq;
453 :
454 : /*
455 : * We assume the standard stats code already took care of setting
456 : * stats_valid, stanullfrac, stawidth, stadistinct. We'd have to
457 : * re-compute those values if we wanted to not store the standard
458 : * stats.
459 : */
460 :
461 : /*
462 : * Construct an array of the interesting hashtable items, that is,
463 : * those meeting the cutoff frequency (s - epsilon)*N. Also identify
464 : * the minimum and maximum frequencies among these items.
465 : *
466 : * Since epsilon = s/10 and bucket_width = 1/epsilon, the cutoff
467 : * frequency is 9*N / bucket_width.
468 : */
469 1703 : cutoff_freq = 9 * element_no / bucket_width;
470 :
471 1703 : i = hash_get_num_entries(elements_tab); /* surely enough space */
472 1703 : sort_table = (TrackItem **) palloc(sizeof(TrackItem *) * i);
473 :
474 1703 : hash_seq_init(&scan_status, elements_tab);
475 1703 : track_len = 0;
476 1703 : minfreq = element_no;
477 1703 : maxfreq = 0;
478 287494 : while ((item = (TrackItem *) hash_seq_search(&scan_status)) != NULL)
479 : {
480 284088 : if (item->frequency > cutoff_freq)
481 : {
482 176079 : sort_table[track_len++] = item;
483 176079 : minfreq = Min(minfreq, item->frequency);
484 176079 : maxfreq = Max(maxfreq, item->frequency);
485 : }
486 : }
487 1703 : Assert(track_len <= i);
488 :
489 : /* emit some statistics for debug purposes */
490 1703 : elog(DEBUG3, "compute_array_stats: target # mces = %d, "
491 : "bucket width = %d, "
492 : "# elements = " INT64_FORMAT ", hashtable size = %d, "
493 : "usable entries = %d",
494 : num_mcelem, bucket_width, element_no, i, track_len);
495 :
496 : /*
497 : * If we obtained more elements than we really want, get rid of those
498 : * with least frequencies. The easiest way is to qsort the array into
499 : * descending frequency order and truncate the array.
500 : */
501 1703 : if (num_mcelem < track_len)
502 : {
503 15 : qsort_interruptible(sort_table, track_len, sizeof(TrackItem *),
504 : trackitem_compare_frequencies_desc, NULL);
505 : /* reset minfreq to the smallest frequency we're keeping */
506 15 : minfreq = sort_table[num_mcelem - 1]->frequency;
507 : }
508 : else
509 1688 : num_mcelem = track_len;
510 :
511 : /* Generate MCELEM slot entry */
512 1703 : if (num_mcelem > 0)
513 : {
514 : MemoryContext old_context;
515 : Datum *mcelem_values;
516 : float4 *mcelem_freqs;
517 :
518 : /*
519 : * We want to store statistics sorted on the element value using
520 : * the element type's default comparison function. This permits
521 : * fast binary searches in selectivity estimation functions.
522 : */
523 1703 : qsort_interruptible(sort_table, num_mcelem, sizeof(TrackItem *),
524 : trackitem_compare_element, NULL);
525 :
526 : /* Must copy the target values into anl_context */
527 1703 : old_context = MemoryContextSwitchTo(stats->anl_context);
528 :
529 : /*
530 : * We sorted statistics on the element value, but we want to be
531 : * able to find the minimal and maximal frequencies without going
532 : * through all the values. We also want the frequency of null
533 : * elements. Store these three values at the end of mcelem_freqs.
534 : */
535 1703 : mcelem_values = (Datum *) palloc(num_mcelem * sizeof(Datum));
536 1703 : mcelem_freqs = (float4 *) palloc((num_mcelem + 3) * sizeof(float4));
537 :
538 : /*
539 : * See comments above about use of nonnull_cnt as the divisor for
540 : * the final frequency estimates.
541 : */
542 170684 : for (i = 0; i < num_mcelem; i++)
543 : {
544 GNC 168981 : TrackItem *titem = sort_table[i];
545 :
546 337962 : mcelem_values[i] = datumCopy(titem->key,
547 CBC 168981 : extra_data->typbyval,
548 168981 : extra_data->typlen);
549 GNC 168981 : mcelem_freqs[i] = (double) titem->frequency /
550 CBC 168981 : (double) nonnull_cnt;
551 : }
552 1703 : mcelem_freqs[i++] = (double) minfreq / (double) nonnull_cnt;
553 1703 : mcelem_freqs[i++] = (double) maxfreq / (double) nonnull_cnt;
554 1703 : mcelem_freqs[i++] = (double) null_elem_cnt / (double) nonnull_cnt;
555 :
556 1703 : MemoryContextSwitchTo(old_context);
557 :
558 1703 : stats->stakind[slot_idx] = STATISTIC_KIND_MCELEM;
559 1703 : stats->staop[slot_idx] = extra_data->eq_opr;
560 1703 : stats->stacoll[slot_idx] = extra_data->coll_id;
561 1703 : stats->stanumbers[slot_idx] = mcelem_freqs;
562 : /* See above comment about extra stanumber entries */
563 1703 : stats->numnumbers[slot_idx] = num_mcelem + 3;
564 1703 : stats->stavalues[slot_idx] = mcelem_values;
565 1703 : stats->numvalues[slot_idx] = num_mcelem;
566 : /* We are storing values of element type */
567 1703 : stats->statypid[slot_idx] = extra_data->type_id;
568 1703 : stats->statyplen[slot_idx] = extra_data->typlen;
569 1703 : stats->statypbyval[slot_idx] = extra_data->typbyval;
570 1703 : stats->statypalign[slot_idx] = extra_data->typalign;
571 1703 : slot_idx++;
572 : }
573 :
574 : /* Generate DECHIST slot entry */
575 1703 : count_items_count = hash_get_num_entries(count_tab);
576 1703 : if (count_items_count > 0)
577 : {
578 1703 : int num_hist = stats->attr->attstattarget;
579 : DECountItem **sorted_count_items;
580 : int j;
581 : int delta;
582 : int64 frac;
583 : float4 *hist;
584 :
585 : /* num_hist must be at least 2 for the loop below to work */
586 1703 : num_hist = Max(num_hist, 2);
587 :
588 : /*
589 : * Create an array of DECountItem pointers, and sort them into
590 : * increasing count order.
591 : */
592 : sorted_count_items = (DECountItem **)
593 1703 : palloc(sizeof(DECountItem *) * count_items_count);
594 1703 : hash_seq_init(&scan_status, count_tab);
595 1703 : j = 0;
596 13368 : while ((count_item = (DECountItem *) hash_seq_search(&scan_status)) != NULL)
597 : {
598 11665 : sorted_count_items[j++] = count_item;
599 : }
600 1703 : qsort_interruptible(sorted_count_items, count_items_count,
601 : sizeof(DECountItem *),
602 : countitem_compare_count, NULL);
603 :
604 : /*
605 : * Prepare to fill stanumbers with the histogram, followed by the
606 : * average count. This array must be stored in anl_context.
607 : */
608 : hist = (float4 *)
609 1703 : MemoryContextAlloc(stats->anl_context,
610 1703 : sizeof(float4) * (num_hist + 1));
611 1703 : hist[num_hist] = (double) element_no / (double) nonnull_cnt;
612 :
613 : /*----------
614 : * Construct the histogram of distinct-element counts (DECs).
615 : *
616 : * The object of this loop is to copy the min and max DECs to
617 : * hist[0] and hist[num_hist - 1], along with evenly-spaced DECs
618 : * in between (where "evenly-spaced" is with reference to the
619 : * whole input population of arrays). If we had a complete sorted
620 : * array of DECs, one per analyzed row, the i'th hist value would
621 : * come from DECs[i * (analyzed_rows - 1) / (num_hist - 1)]
622 : * (compare the histogram-making loop in compute_scalar_stats()).
623 : * But instead of that we have the sorted_count_items[] array,
624 : * which holds unique DEC values with their frequencies (that is,
625 : * a run-length-compressed version of the full array). So we
626 : * control advancing through sorted_count_items[] with the
627 : * variable "frac", which is defined as (x - y) * (num_hist - 1),
628 : * where x is the index in the notional DECs array corresponding
629 : * to the start of the next sorted_count_items[] element's run,
630 : * and y is the index in DECs from which we should take the next
631 : * histogram value. We have to advance whenever x <= y, that is
632 : * frac <= 0. The x component is the sum of the frequencies seen
633 : * so far (up through the current sorted_count_items[] element),
634 : * and of course y * (num_hist - 1) = i * (analyzed_rows - 1),
635 : * per the subscript calculation above. (The subscript calculation
636 : * implies dropping any fractional part of y; in this formulation
637 : * that's handled by not advancing until frac reaches 1.)
638 : *
639 : * Even though frac has a bounded range, it could overflow int32
640 : * when working with very large statistics targets, so we do that
641 : * math in int64.
642 : *----------
643 : */
644 1703 : delta = analyzed_rows - 1;
645 1703 : j = 0; /* current index in sorted_count_items */
646 : /* Initialize frac for sorted_count_items[0]; y is initially 0 */
647 1703 : frac = (int64) sorted_count_items[0]->frequency * (num_hist - 1);
648 169183 : for (i = 0; i < num_hist; i++)
649 : {
650 177442 : while (frac <= 0)
651 : {
652 : /* Advance, and update x component of frac */
653 9962 : j++;
654 9962 : frac += (int64) sorted_count_items[j]->frequency * (num_hist - 1);
655 : }
656 167480 : hist[i] = sorted_count_items[j]->count;
657 167480 : frac -= delta; /* update y for upcoming i increment */
658 : }
659 1703 : Assert(j == count_items_count - 1);
660 :
661 1703 : stats->stakind[slot_idx] = STATISTIC_KIND_DECHIST;
662 1703 : stats->staop[slot_idx] = extra_data->eq_opr;
663 1703 : stats->stacoll[slot_idx] = extra_data->coll_id;
664 1703 : stats->stanumbers[slot_idx] = hist;
665 1703 : stats->numnumbers[slot_idx] = num_hist + 1;
666 1703 : slot_idx++;
667 : }
668 : }
669 :
670 : /*
671 : * We don't need to bother cleaning up any of our temporary palloc's. The
672 : * hashtable should also go away, as it used a child memory context.
673 : */
674 5965 : }
675 :
676 : /*
677 : * A function to prune the D structure from the Lossy Counting algorithm.
678 : * Consult compute_tsvector_stats() for wider explanation.
679 : */
680 : static void
681 UBC 0 : prune_element_hashtable(HTAB *elements_tab, int b_current)
682 : {
683 : HASH_SEQ_STATUS scan_status;
684 : TrackItem *item;
685 :
686 0 : hash_seq_init(&scan_status, elements_tab);
687 0 : while ((item = (TrackItem *) hash_seq_search(&scan_status)) != NULL)
688 : {
689 0 : if (item->frequency + item->delta <= b_current)
690 : {
691 0 : Datum value = item->key;
692 :
693 UNC 0 : if (hash_search(elements_tab, &item->key,
694 : HASH_REMOVE, NULL) == NULL)
695 UBC 0 : elog(ERROR, "hash table corrupted");
696 : /* We should free memory if element is not passed by value */
697 0 : if (!array_extra_data->typbyval)
698 0 : pfree(DatumGetPointer(value));
699 : }
700 : }
701 0 : }
702 :
703 : /*
704 : * Hash function for elements.
705 : *
706 : * We use the element type's default hash opclass, and the column collation
707 : * if the type is collation-sensitive.
708 : */
709 : static uint32
710 CBC 1332765 : element_hash(const void *key, Size keysize)
711 : {
712 1332765 : Datum d = *((const Datum *) key);
713 : Datum h;
714 :
715 1332765 : h = FunctionCall1Coll(array_extra_data->hash,
716 1332765 : array_extra_data->coll_id,
717 : d);
718 1332765 : return DatumGetUInt32(h);
719 : }
720 :
721 : /*
722 : * Matching function for elements, to be used in hashtable lookups.
723 : */
724 : static int
725 1049574 : element_match(const void *key1, const void *key2, Size keysize)
726 : {
727 : /* The keysize parameter is superfluous here */
728 1049574 : return element_compare(key1, key2);
729 : }
730 :
731 : /*
732 : * Comparison function for elements.
733 : *
734 : * We use the element type's default btree opclass, and the column collation
735 : * if the type is collation-sensitive.
736 : *
737 : * XXX consider using SortSupport infrastructure
738 : */
739 : static int
740 2458703 : element_compare(const void *key1, const void *key2)
741 : {
742 2458703 : Datum d1 = *((const Datum *) key1);
743 2458703 : Datum d2 = *((const Datum *) key2);
744 : Datum c;
745 :
746 2458703 : c = FunctionCall2Coll(array_extra_data->cmp,
747 2458703 : array_extra_data->coll_id,
748 : d1, d2);
749 2458703 : return DatumGetInt32(c);
750 : }
751 :
752 : /*
753 : * Comparator for sorting TrackItems by frequencies (descending sort)
754 : */
755 : static int
756 17346 : trackitem_compare_frequencies_desc(const void *e1, const void *e2, void *arg)
757 : {
758 17346 : const TrackItem *const *t1 = (const TrackItem *const *) e1;
759 17346 : const TrackItem *const *t2 = (const TrackItem *const *) e2;
760 :
761 17346 : return (*t2)->frequency - (*t1)->frequency;
762 : }
763 :
764 : /*
765 : * Comparator for sorting TrackItems by element values
766 : */
767 : static int
768 1409129 : trackitem_compare_element(const void *e1, const void *e2, void *arg)
769 : {
770 1409129 : const TrackItem *const *t1 = (const TrackItem *const *) e1;
771 1409129 : const TrackItem *const *t2 = (const TrackItem *const *) e2;
772 :
773 1409129 : return element_compare(&(*t1)->key, &(*t2)->key);
774 : }
775 :
776 : /*
777 : * Comparator for sorting DECountItems by count
778 : */
779 : static int
780 31098 : countitem_compare_count(const void *e1, const void *e2, void *arg)
781 : {
782 31098 : const DECountItem *const *t1 = (const DECountItem *const *) e1;
783 31098 : const DECountItem *const *t2 = (const DECountItem *const *) e2;
784 :
785 31098 : if ((*t1)->count < (*t2)->count)
786 14217 : return -1;
787 16881 : else if ((*t1)->count == (*t2)->count)
788 UBC 0 : return 0;
789 : else
790 CBC 16881 : return 1;
791 : }
|
