PostgreSQL Source Code git master
All Data Structures Namespaces Files Functions Variables Typedefs Enumerations Enumerator Macros Pages
analyze.c
Go to the documentation of this file.
1/*-------------------------------------------------------------------------
2 *
3 * analyze.c
4 * the Postgres statistics generator
5 *
6 * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
7 * Portions Copyright (c) 1994, Regents of the University of California
8 *
9 *
10 * IDENTIFICATION
11 * src/backend/commands/analyze.c
12 *
13 *-------------------------------------------------------------------------
14 */
15#include "postgres.h"
16
17#include <math.h>
18
19#include "access/detoast.h"
20#include "access/genam.h"
21#include "access/multixact.h"
22#include "access/relation.h"
23#include "access/table.h"
24#include "access/tableam.h"
25#include "access/transam.h"
26#include "access/tupconvert.h"
28#include "access/xact.h"
29#include "catalog/index.h"
30#include "catalog/indexing.h"
31#include "catalog/pg_inherits.h"
32#include "commands/dbcommands.h"
33#include "commands/progress.h"
34#include "commands/tablecmds.h"
35#include "commands/vacuum.h"
36#include "common/pg_prng.h"
37#include "executor/executor.h"
38#include "foreign/fdwapi.h"
39#include "miscadmin.h"
40#include "nodes/nodeFuncs.h"
41#include "parser/parse_oper.h"
43#include "pgstat.h"
46#include "storage/bufmgr.h"
47#include "storage/procarray.h"
48#include "utils/attoptcache.h"
49#include "utils/datum.h"
50#include "utils/guc.h"
51#include "utils/lsyscache.h"
52#include "utils/memutils.h"
53#include "utils/pg_rusage.h"
54#include "utils/sampling.h"
55#include "utils/sortsupport.h"
56#include "utils/syscache.h"
57#include "utils/timestamp.h"
58
59
60/* Per-index data for ANALYZE */
61typedef struct AnlIndexData
62{
63 IndexInfo *indexInfo; /* BuildIndexInfo result */
64 double tupleFract; /* fraction of rows for partial index */
65 VacAttrStats **vacattrstats; /* index attrs to analyze */
68
69
70/* Default statistics target (GUC parameter) */
72
73/* A few variables that don't seem worth passing around as parameters */
76
77
78static void do_analyze_rel(Relation onerel,
79 VacuumParams *params, List *va_cols,
80 AcquireSampleRowsFunc acquirefunc, BlockNumber relpages,
81 bool inh, bool in_outer_xact, int elevel);
82static void compute_index_stats(Relation onerel, double totalrows,
83 AnlIndexData *indexdata, int nindexes,
84 HeapTuple *rows, int numrows,
85 MemoryContext col_context);
87 Node *index_expr);
88static int acquire_sample_rows(Relation onerel, int elevel,
89 HeapTuple *rows, int targrows,
90 double *totalrows, double *totaldeadrows);
91static int compare_rows(const void *a, const void *b, void *arg);
92static int acquire_inherited_sample_rows(Relation onerel, int elevel,
93 HeapTuple *rows, int targrows,
94 double *totalrows, double *totaldeadrows);
95static void update_attstats(Oid relid, bool inh,
96 int natts, VacAttrStats **vacattrstats);
97static Datum std_fetch_func(VacAttrStatsP stats, int rownum, bool *isNull);
98static Datum ind_fetch_func(VacAttrStatsP stats, int rownum, bool *isNull);
99
100
101/*
102 * analyze_rel() -- analyze one relation
103 *
104 * relid identifies the relation to analyze. If relation is supplied, use
105 * the name therein for reporting any failure to open/lock the rel; do not
106 * use it once we've successfully opened the rel, since it might be stale.
107 */
108void
109analyze_rel(Oid relid, RangeVar *relation,
110 VacuumParams *params, List *va_cols, bool in_outer_xact,
111 BufferAccessStrategy bstrategy)
112{
113 Relation onerel;
114 int elevel;
115 AcquireSampleRowsFunc acquirefunc = NULL;
116 BlockNumber relpages = 0;
117
118 /* Select logging level */
119 if (params->options & VACOPT_VERBOSE)
120 elevel = INFO;
121 else
122 elevel = DEBUG2;
123
124 /* Set up static variables */
125 vac_strategy = bstrategy;
126
127 /*
128 * Check for user-requested abort.
129 */
131
132 /*
133 * Open the relation, getting ShareUpdateExclusiveLock to ensure that two
134 * ANALYZEs don't run on it concurrently. (This also locks out a
135 * concurrent VACUUM, which doesn't matter much at the moment but might
136 * matter if we ever try to accumulate stats on dead tuples.) If the rel
137 * has been dropped since we last saw it, we don't need to process it.
138 *
139 * Make sure to generate only logs for ANALYZE in this case.
140 */
141 onerel = vacuum_open_relation(relid, relation, params->options & ~(VACOPT_VACUUM),
142 params->log_min_duration >= 0,
144
145 /* leave if relation could not be opened or locked */
146 if (!onerel)
147 return;
148
149 /*
150 * Check if relation needs to be skipped based on privileges. This check
151 * happens also when building the relation list to analyze for a manual
152 * operation, and needs to be done additionally here as ANALYZE could
153 * happen across multiple transactions where privileges could have changed
154 * in-between. Make sure to generate only logs for ANALYZE in this case.
155 */
157 onerel->rd_rel,
158 params->options & ~VACOPT_VACUUM))
159 {
161 return;
162 }
163
164 /*
165 * Silently ignore tables that are temp tables of other backends ---
166 * trying to analyze these is rather pointless, since their contents are
167 * probably not up-to-date on disk. (We don't throw a warning here; it
168 * would just lead to chatter during a database-wide ANALYZE.)
169 */
170 if (RELATION_IS_OTHER_TEMP(onerel))
171 {
173 return;
174 }
175
176 /*
177 * We can ANALYZE any table except pg_statistic. See update_attstats
178 */
179 if (RelationGetRelid(onerel) == StatisticRelationId)
180 {
182 return;
183 }
184
185 /*
186 * Check that it's of an analyzable relkind, and set up appropriately.
187 */
188 if (onerel->rd_rel->relkind == RELKIND_RELATION ||
189 onerel->rd_rel->relkind == RELKIND_MATVIEW)
190 {
191 /* Regular table, so we'll use the regular row acquisition function */
192 acquirefunc = acquire_sample_rows;
193 /* Also get regular table's size */
194 relpages = RelationGetNumberOfBlocks(onerel);
195 }
196 else if (onerel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
197 {
198 /*
199 * For a foreign table, call the FDW's hook function to see whether it
200 * supports analysis.
201 */
202 FdwRoutine *fdwroutine;
203 bool ok = false;
204
205 fdwroutine = GetFdwRoutineForRelation(onerel, false);
206
207 if (fdwroutine->AnalyzeForeignTable != NULL)
208 ok = fdwroutine->AnalyzeForeignTable(onerel,
209 &acquirefunc,
210 &relpages);
211
212 if (!ok)
213 {
215 (errmsg("skipping \"%s\" --- cannot analyze this foreign table",
216 RelationGetRelationName(onerel))));
218 return;
219 }
220 }
221 else if (onerel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE)
222 {
223 /*
224 * For partitioned tables, we want to do the recursive ANALYZE below.
225 */
226 }
227 else
228 {
229 /* No need for a WARNING if we already complained during VACUUM */
230 if (!(params->options & VACOPT_VACUUM))
232 (errmsg("skipping \"%s\" --- cannot analyze non-tables or special system tables",
233 RelationGetRelationName(onerel))));
235 return;
236 }
237
238 /*
239 * OK, let's do it. First, initialize progress reporting.
240 */
242 RelationGetRelid(onerel));
243
244 /*
245 * Do the normal non-recursive ANALYZE. We can skip this for partitioned
246 * tables, which don't contain any rows.
247 */
248 if (onerel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
249 do_analyze_rel(onerel, params, va_cols, acquirefunc,
250 relpages, false, in_outer_xact, elevel);
251
252 /*
253 * If there are child tables, do recursive ANALYZE.
254 */
255 if (onerel->rd_rel->relhassubclass)
256 do_analyze_rel(onerel, params, va_cols, acquirefunc, relpages,
257 true, in_outer_xact, elevel);
258
259 /*
260 * Close source relation now, but keep lock so that no one deletes it
261 * before we commit. (If someone did, they'd fail to clean up the entries
262 * we made in pg_statistic. Also, releasing the lock before commit would
263 * expose us to concurrent-update failures in update_attstats.)
264 */
265 relation_close(onerel, NoLock);
266
268}
269
270/*
271 * do_analyze_rel() -- analyze one relation, recursively or not
272 *
273 * Note that "acquirefunc" is only relevant for the non-inherited case.
274 * For the inherited case, acquire_inherited_sample_rows() determines the
275 * appropriate acquirefunc for each child table.
276 */
277static void
279 List *va_cols, AcquireSampleRowsFunc acquirefunc,
280 BlockNumber relpages, bool inh, bool in_outer_xact,
281 int elevel)
282{
283 int attr_cnt,
284 tcnt,
285 i,
286 ind;
287 Relation *Irel;
288 int nindexes;
289 bool verbose,
290 instrument,
291 hasindex;
292 VacAttrStats **vacattrstats;
293 AnlIndexData *indexdata;
294 int targrows,
295 numrows,
296 minrows;
297 double totalrows,
298 totaldeadrows;
299 HeapTuple *rows;
300 PGRUsage ru0;
301 TimestampTz starttime = 0;
302 MemoryContext caller_context;
303 Oid save_userid;
304 int save_sec_context;
305 int save_nestlevel;
306 WalUsage startwalusage = pgWalUsage;
307 BufferUsage startbufferusage = pgBufferUsage;
308 BufferUsage bufferusage;
309 PgStat_Counter startreadtime = 0;
310 PgStat_Counter startwritetime = 0;
311
312 verbose = (params->options & VACOPT_VERBOSE) != 0;
313 instrument = (verbose || (AmAutoVacuumWorkerProcess() &&
314 params->log_min_duration >= 0));
315 if (inh)
316 ereport(elevel,
317 (errmsg("analyzing \"%s.%s\" inheritance tree",
319 RelationGetRelationName(onerel))));
320 else
321 ereport(elevel,
322 (errmsg("analyzing \"%s.%s\"",
324 RelationGetRelationName(onerel))));
325
326 /*
327 * Set up a working context so that we can easily free whatever junk gets
328 * created.
329 */
331 "Analyze",
333 caller_context = MemoryContextSwitchTo(anl_context);
334
335 /*
336 * Switch to the table owner's userid, so that any index functions are run
337 * as that user. Also lock down security-restricted operations and
338 * arrange to make GUC variable changes local to this command.
339 */
340 GetUserIdAndSecContext(&save_userid, &save_sec_context);
341 SetUserIdAndSecContext(onerel->rd_rel->relowner,
342 save_sec_context | SECURITY_RESTRICTED_OPERATION);
343 save_nestlevel = NewGUCNestLevel();
345
346 /*
347 * When verbose or autovacuum logging is used, initialize a resource usage
348 * snapshot and optionally track I/O timing.
349 */
350 if (instrument)
351 {
352 if (track_io_timing)
353 {
354 startreadtime = pgStatBlockReadTime;
355 startwritetime = pgStatBlockWriteTime;
356 }
357
358 pg_rusage_init(&ru0);
359 }
360
361 /* Used for instrumentation and stats report */
362 starttime = GetCurrentTimestamp();
363
364 /*
365 * Determine which columns to analyze
366 *
367 * Note that system attributes are never analyzed, so we just reject them
368 * at the lookup stage. We also reject duplicate column mentions. (We
369 * could alternatively ignore duplicates, but analyzing a column twice
370 * won't work; we'd end up making a conflicting update in pg_statistic.)
371 */
372 if (va_cols != NIL)
373 {
374 Bitmapset *unique_cols = NULL;
375 ListCell *le;
376
377 vacattrstats = (VacAttrStats **) palloc(list_length(va_cols) *
378 sizeof(VacAttrStats *));
379 tcnt = 0;
380 foreach(le, va_cols)
381 {
382 char *col = strVal(lfirst(le));
383
384 i = attnameAttNum(onerel, col, false);
385 if (i == InvalidAttrNumber)
387 (errcode(ERRCODE_UNDEFINED_COLUMN),
388 errmsg("column \"%s\" of relation \"%s\" does not exist",
389 col, RelationGetRelationName(onerel))));
390 if (bms_is_member(i, unique_cols))
392 (errcode(ERRCODE_DUPLICATE_COLUMN),
393 errmsg("column \"%s\" of relation \"%s\" appears more than once",
394 col, RelationGetRelationName(onerel))));
395 unique_cols = bms_add_member(unique_cols, i);
396
397 vacattrstats[tcnt] = examine_attribute(onerel, i, NULL);
398 if (vacattrstats[tcnt] != NULL)
399 tcnt++;
400 }
401 attr_cnt = tcnt;
402 }
403 else
404 {
405 attr_cnt = onerel->rd_att->natts;
406 vacattrstats = (VacAttrStats **)
407 palloc(attr_cnt * sizeof(VacAttrStats *));
408 tcnt = 0;
409 for (i = 1; i <= attr_cnt; i++)
410 {
411 vacattrstats[tcnt] = examine_attribute(onerel, i, NULL);
412 if (vacattrstats[tcnt] != NULL)
413 tcnt++;
414 }
415 attr_cnt = tcnt;
416 }
417
418 /*
419 * Open all indexes of the relation, and see if there are any analyzable
420 * columns in the indexes. We do not analyze index columns if there was
421 * an explicit column list in the ANALYZE command, however.
422 *
423 * If we are doing a recursive scan, we don't want to touch the parent's
424 * indexes at all. If we're processing a partitioned table, we need to
425 * know if there are any indexes, but we don't want to process them.
426 */
427 if (onerel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE)
428 {
429 List *idxs = RelationGetIndexList(onerel);
430
431 Irel = NULL;
432 nindexes = 0;
433 hasindex = idxs != NIL;
434 list_free(idxs);
435 }
436 else if (!inh)
437 {
438 vac_open_indexes(onerel, AccessShareLock, &nindexes, &Irel);
439 hasindex = nindexes > 0;
440 }
441 else
442 {
443 Irel = NULL;
444 nindexes = 0;
445 hasindex = false;
446 }
447 indexdata = NULL;
448 if (nindexes > 0)
449 {
450 indexdata = (AnlIndexData *) palloc0(nindexes * sizeof(AnlIndexData));
451 for (ind = 0; ind < nindexes; ind++)
452 {
453 AnlIndexData *thisdata = &indexdata[ind];
454 IndexInfo *indexInfo;
455
456 thisdata->indexInfo = indexInfo = BuildIndexInfo(Irel[ind]);
457 thisdata->tupleFract = 1.0; /* fix later if partial */
458 if (indexInfo->ii_Expressions != NIL && va_cols == NIL)
459 {
460 ListCell *indexpr_item = list_head(indexInfo->ii_Expressions);
461
462 thisdata->vacattrstats = (VacAttrStats **)
463 palloc(indexInfo->ii_NumIndexAttrs * sizeof(VacAttrStats *));
464 tcnt = 0;
465 for (i = 0; i < indexInfo->ii_NumIndexAttrs; i++)
466 {
467 int keycol = indexInfo->ii_IndexAttrNumbers[i];
468
469 if (keycol == 0)
470 {
471 /* Found an index expression */
472 Node *indexkey;
473
474 if (indexpr_item == NULL) /* shouldn't happen */
475 elog(ERROR, "too few entries in indexprs list");
476 indexkey = (Node *) lfirst(indexpr_item);
477 indexpr_item = lnext(indexInfo->ii_Expressions,
478 indexpr_item);
479 thisdata->vacattrstats[tcnt] =
480 examine_attribute(Irel[ind], i + 1, indexkey);
481 if (thisdata->vacattrstats[tcnt] != NULL)
482 tcnt++;
483 }
484 }
485 thisdata->attr_cnt = tcnt;
486 }
487 }
488 }
489
490 /*
491 * Determine how many rows we need to sample, using the worst case from
492 * all analyzable columns. We use a lower bound of 100 rows to avoid
493 * possible overflow in Vitter's algorithm. (Note: that will also be the
494 * target in the corner case where there are no analyzable columns.)
495 */
496 targrows = 100;
497 for (i = 0; i < attr_cnt; i++)
498 {
499 if (targrows < vacattrstats[i]->minrows)
500 targrows = vacattrstats[i]->minrows;
501 }
502 for (ind = 0; ind < nindexes; ind++)
503 {
504 AnlIndexData *thisdata = &indexdata[ind];
505
506 for (i = 0; i < thisdata->attr_cnt; i++)
507 {
508 if (targrows < thisdata->vacattrstats[i]->minrows)
509 targrows = thisdata->vacattrstats[i]->minrows;
510 }
511 }
512
513 /*
514 * Look at extended statistics objects too, as those may define custom
515 * statistics target. So we may need to sample more rows and then build
516 * the statistics with enough detail.
517 */
518 minrows = ComputeExtStatisticsRows(onerel, attr_cnt, vacattrstats);
519
520 if (targrows < minrows)
521 targrows = minrows;
522
523 /*
524 * Acquire the sample rows
525 */
526 rows = (HeapTuple *) palloc(targrows * sizeof(HeapTuple));
530 if (inh)
531 numrows = acquire_inherited_sample_rows(onerel, elevel,
532 rows, targrows,
533 &totalrows, &totaldeadrows);
534 else
535 numrows = (*acquirefunc) (onerel, elevel,
536 rows, targrows,
537 &totalrows, &totaldeadrows);
538
539 /*
540 * Compute the statistics. Temporary results during the calculations for
541 * each column are stored in a child context. The calc routines are
542 * responsible to make sure that whatever they store into the VacAttrStats
543 * structure is allocated in anl_context.
544 */
545 if (numrows > 0)
546 {
547 MemoryContext col_context,
548 old_context;
549
552
554 "Analyze Column",
556 old_context = MemoryContextSwitchTo(col_context);
557
558 for (i = 0; i < attr_cnt; i++)
559 {
560 VacAttrStats *stats = vacattrstats[i];
561 AttributeOpts *aopt;
562
563 stats->rows = rows;
564 stats->tupDesc = onerel->rd_att;
565 stats->compute_stats(stats,
567 numrows,
568 totalrows);
569
570 /*
571 * If the appropriate flavor of the n_distinct option is
572 * specified, override with the corresponding value.
573 */
574 aopt = get_attribute_options(onerel->rd_id, stats->tupattnum);
575 if (aopt != NULL)
576 {
577 float8 n_distinct;
578
579 n_distinct = inh ? aopt->n_distinct_inherited : aopt->n_distinct;
580 if (n_distinct != 0.0)
581 stats->stadistinct = n_distinct;
582 }
583
584 MemoryContextReset(col_context);
585 }
586
587 if (nindexes > 0)
588 compute_index_stats(onerel, totalrows,
589 indexdata, nindexes,
590 rows, numrows,
591 col_context);
592
593 MemoryContextSwitchTo(old_context);
594 MemoryContextDelete(col_context);
595
596 /*
597 * Emit the completed stats rows into pg_statistic, replacing any
598 * previous statistics for the target columns. (If there are stats in
599 * pg_statistic for columns we didn't process, we leave them alone.)
600 */
602 attr_cnt, vacattrstats);
603
604 for (ind = 0; ind < nindexes; ind++)
605 {
606 AnlIndexData *thisdata = &indexdata[ind];
607
609 thisdata->attr_cnt, thisdata->vacattrstats);
610 }
611
612 /* Build extended statistics (if there are any). */
613 BuildRelationExtStatistics(onerel, inh, totalrows, numrows, rows,
614 attr_cnt, vacattrstats);
615 }
616
619
620 /*
621 * Update pages/tuples stats in pg_class ... but not if we're doing
622 * inherited stats.
623 *
624 * We assume that VACUUM hasn't set pg_class.reltuples already, even
625 * during a VACUUM ANALYZE. Although VACUUM often updates pg_class,
626 * exceptions exist. A "VACUUM (ANALYZE, INDEX_CLEANUP OFF)" command will
627 * never update pg_class entries for index relations. It's also possible
628 * that an individual index's pg_class entry won't be updated during
629 * VACUUM if the index AM returns NULL from its amvacuumcleanup() routine.
630 */
631 if (!inh)
632 {
633 BlockNumber relallvisible = 0;
634 BlockNumber relallfrozen = 0;
635
636 if (RELKIND_HAS_STORAGE(onerel->rd_rel->relkind))
637 visibilitymap_count(onerel, &relallvisible, &relallfrozen);
638
639 /*
640 * Update pg_class for table relation. CCI first, in case acquirefunc
641 * updated pg_class.
642 */
644 vac_update_relstats(onerel,
645 relpages,
646 totalrows,
647 relallvisible,
648 relallfrozen,
649 hasindex,
652 NULL, NULL,
653 in_outer_xact);
654
655 /* Same for indexes */
656 for (ind = 0; ind < nindexes; ind++)
657 {
658 AnlIndexData *thisdata = &indexdata[ind];
659 double totalindexrows;
660
661 totalindexrows = ceil(thisdata->tupleFract * totalrows);
664 totalindexrows,
665 0, 0,
666 false,
669 NULL, NULL,
670 in_outer_xact);
671 }
672 }
673 else if (onerel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE)
674 {
675 /*
676 * Partitioned tables don't have storage, so we don't set any fields
677 * in their pg_class entries except for reltuples and relhasindex.
678 */
680 vac_update_relstats(onerel, -1, totalrows,
681 0, 0, hasindex, InvalidTransactionId,
683 NULL, NULL,
684 in_outer_xact);
685 }
686
687 /*
688 * Now report ANALYZE to the cumulative stats system. For regular tables,
689 * we do it only if not doing inherited stats. For partitioned tables, we
690 * only do it for inherited stats. (We're never called for not-inherited
691 * stats on partitioned tables anyway.)
692 *
693 * Reset the changes_since_analyze counter only if we analyzed all
694 * columns; otherwise, there is still work for auto-analyze to do.
695 */
696 if (!inh)
697 pgstat_report_analyze(onerel, totalrows, totaldeadrows,
698 (va_cols == NIL), starttime);
699 else if (onerel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE)
700 pgstat_report_analyze(onerel, 0, 0, (va_cols == NIL), starttime);
701
702 /*
703 * If this isn't part of VACUUM ANALYZE, let index AMs do cleanup.
704 *
705 * Note that most index AMs perform a no-op as a matter of policy for
706 * amvacuumcleanup() when called in ANALYZE-only mode. The only exception
707 * among core index AMs is GIN/ginvacuumcleanup().
708 */
709 if (!(params->options & VACOPT_VACUUM))
710 {
711 for (ind = 0; ind < nindexes; ind++)
712 {
714 IndexVacuumInfo ivinfo;
715
716 ivinfo.index = Irel[ind];
717 ivinfo.heaprel = onerel;
718 ivinfo.analyze_only = true;
719 ivinfo.estimated_count = true;
720 ivinfo.message_level = elevel;
721 ivinfo.num_heap_tuples = onerel->rd_rel->reltuples;
722 ivinfo.strategy = vac_strategy;
723
724 stats = index_vacuum_cleanup(&ivinfo, NULL);
725
726 if (stats)
727 pfree(stats);
728 }
729 }
730
731 /* Done with indexes */
732 vac_close_indexes(nindexes, Irel, NoLock);
733
734 /* Log the action if appropriate */
735 if (instrument)
736 {
738
739 if (verbose || params->log_min_duration == 0 ||
740 TimestampDifferenceExceeds(starttime, endtime,
741 params->log_min_duration))
742 {
743 long delay_in_ms;
744 WalUsage walusage;
745 double read_rate = 0;
746 double write_rate = 0;
747 char *msgfmt;
749 int64 total_blks_hit;
750 int64 total_blks_read;
751 int64 total_blks_dirtied;
752
753 memset(&bufferusage, 0, sizeof(BufferUsage));
754 BufferUsageAccumDiff(&bufferusage, &pgBufferUsage, &startbufferusage);
755 memset(&walusage, 0, sizeof(WalUsage));
756 WalUsageAccumDiff(&walusage, &pgWalUsage, &startwalusage);
757
758 total_blks_hit = bufferusage.shared_blks_hit +
759 bufferusage.local_blks_hit;
760 total_blks_read = bufferusage.shared_blks_read +
761 bufferusage.local_blks_read;
762 total_blks_dirtied = bufferusage.shared_blks_dirtied +
763 bufferusage.local_blks_dirtied;
764
765 /*
766 * We do not expect an analyze to take > 25 days and it simplifies
767 * things a bit to use TimestampDifferenceMilliseconds.
768 */
769 delay_in_ms = TimestampDifferenceMilliseconds(starttime, endtime);
770
771 /*
772 * Note that we are reporting these read/write rates in the same
773 * manner as VACUUM does, which means that while the 'average read
774 * rate' here actually corresponds to page misses and resulting
775 * reads which are also picked up by track_io_timing, if enabled,
776 * the 'average write rate' is actually talking about the rate of
777 * pages being dirtied, not being written out, so it's typical to
778 * have a non-zero 'avg write rate' while I/O timings only reports
779 * reads.
780 *
781 * It's not clear that an ANALYZE will ever result in
782 * FlushBuffer() being called, but we track and support reporting
783 * on I/O write time in case that changes as it's practically free
784 * to do so anyway.
785 */
786
787 if (delay_in_ms > 0)
788 {
789 read_rate = (double) BLCKSZ * total_blks_read /
790 (1024 * 1024) / (delay_in_ms / 1000.0);
791 write_rate = (double) BLCKSZ * total_blks_dirtied /
792 (1024 * 1024) / (delay_in_ms / 1000.0);
793 }
794
795 /*
796 * We split this up so we don't emit empty I/O timing values when
797 * track_io_timing isn't enabled.
798 */
799
801
803 msgfmt = _("automatic analyze of table \"%s.%s.%s\"\n");
804 else
805 msgfmt = _("finished analyzing table \"%s.%s.%s\"\n");
806
807 appendStringInfo(&buf, msgfmt,
812 {
813 /*
814 * We bypass the changecount mechanism because this value is
815 * only updated by the calling process.
816 */
817 appendStringInfo(&buf, _("delay time: %.3f ms\n"),
819 }
820 if (track_io_timing)
821 {
822 double read_ms = (double) (pgStatBlockReadTime - startreadtime) / 1000;
823 double write_ms = (double) (pgStatBlockWriteTime - startwritetime) / 1000;
824
825 appendStringInfo(&buf, _("I/O timings: read: %.3f ms, write: %.3f ms\n"),
826 read_ms, write_ms);
827 }
828 appendStringInfo(&buf, _("avg read rate: %.3f MB/s, avg write rate: %.3f MB/s\n"),
829 read_rate, write_rate);
830 appendStringInfo(&buf, _("buffer usage: %" PRId64 " hits, %" PRId64 " reads, %" PRId64 " dirtied\n"),
831 total_blks_hit,
832 total_blks_read,
833 total_blks_dirtied);
835 _("WAL usage: %" PRId64 " records, %" PRId64 " full page images, %" PRIu64 " bytes, %" PRId64 " buffers full\n"),
836 walusage.wal_records,
837 walusage.wal_fpi,
838 walusage.wal_bytes,
839 walusage.wal_buffers_full);
840 appendStringInfo(&buf, _("system usage: %s"), pg_rusage_show(&ru0));
841
843 (errmsg_internal("%s", buf.data)));
844
845 pfree(buf.data);
846 }
847 }
848
849 /* Roll back any GUC changes executed by index functions */
850 AtEOXact_GUC(false, save_nestlevel);
851
852 /* Restore userid and security context */
853 SetUserIdAndSecContext(save_userid, save_sec_context);
854
855 /* Restore current context and release memory */
856 MemoryContextSwitchTo(caller_context);
858 anl_context = NULL;
859}
860
861/*
862 * Compute statistics about indexes of a relation
863 */
864static void
865compute_index_stats(Relation onerel, double totalrows,
866 AnlIndexData *indexdata, int nindexes,
867 HeapTuple *rows, int numrows,
868 MemoryContext col_context)
869{
870 MemoryContext ind_context,
871 old_context;
873 bool isnull[INDEX_MAX_KEYS];
874 int ind,
875 i;
876
878 "Analyze Index",
880 old_context = MemoryContextSwitchTo(ind_context);
881
882 for (ind = 0; ind < nindexes; ind++)
883 {
884 AnlIndexData *thisdata = &indexdata[ind];
885 IndexInfo *indexInfo = thisdata->indexInfo;
886 int attr_cnt = thisdata->attr_cnt;
887 TupleTableSlot *slot;
888 EState *estate;
889 ExprContext *econtext;
890 ExprState *predicate;
891 Datum *exprvals;
892 bool *exprnulls;
893 int numindexrows,
894 tcnt,
895 rowno;
896 double totalindexrows;
897
898 /* Ignore index if no columns to analyze and not partial */
899 if (attr_cnt == 0 && indexInfo->ii_Predicate == NIL)
900 continue;
901
902 /*
903 * Need an EState for evaluation of index expressions and
904 * partial-index predicates. Create it in the per-index context to be
905 * sure it gets cleaned up at the bottom of the loop.
906 */
907 estate = CreateExecutorState();
908 econtext = GetPerTupleExprContext(estate);
909 /* Need a slot to hold the current heap tuple, too */
912
913 /* Arrange for econtext's scan tuple to be the tuple under test */
914 econtext->ecxt_scantuple = slot;
915
916 /* Set up execution state for predicate. */
917 predicate = ExecPrepareQual(indexInfo->ii_Predicate, estate);
918
919 /* Compute and save index expression values */
920 exprvals = (Datum *) palloc(numrows * attr_cnt * sizeof(Datum));
921 exprnulls = (bool *) palloc(numrows * attr_cnt * sizeof(bool));
922 numindexrows = 0;
923 tcnt = 0;
924 for (rowno = 0; rowno < numrows; rowno++)
925 {
926 HeapTuple heapTuple = rows[rowno];
927
928 vacuum_delay_point(true);
929
930 /*
931 * Reset the per-tuple context each time, to reclaim any cruft
932 * left behind by evaluating the predicate or index expressions.
933 */
934 ResetExprContext(econtext);
935
936 /* Set up for predicate or expression evaluation */
937 ExecStoreHeapTuple(heapTuple, slot, false);
938
939 /* If index is partial, check predicate */
940 if (predicate != NULL)
941 {
942 if (!ExecQual(predicate, econtext))
943 continue;
944 }
945 numindexrows++;
946
947 if (attr_cnt > 0)
948 {
949 /*
950 * Evaluate the index row to compute expression values. We
951 * could do this by hand, but FormIndexDatum is convenient.
952 */
953 FormIndexDatum(indexInfo,
954 slot,
955 estate,
956 values,
957 isnull);
958
959 /*
960 * Save just the columns we care about. We copy the values
961 * into ind_context from the estate's per-tuple context.
962 */
963 for (i = 0; i < attr_cnt; i++)
964 {
965 VacAttrStats *stats = thisdata->vacattrstats[i];
966 int attnum = stats->tupattnum;
967
968 if (isnull[attnum - 1])
969 {
970 exprvals[tcnt] = (Datum) 0;
971 exprnulls[tcnt] = true;
972 }
973 else
974 {
975 exprvals[tcnt] = datumCopy(values[attnum - 1],
976 stats->attrtype->typbyval,
977 stats->attrtype->typlen);
978 exprnulls[tcnt] = false;
979 }
980 tcnt++;
981 }
982 }
983 }
984
985 /*
986 * Having counted the number of rows that pass the predicate in the
987 * sample, we can estimate the total number of rows in the index.
988 */
989 thisdata->tupleFract = (double) numindexrows / (double) numrows;
990 totalindexrows = ceil(thisdata->tupleFract * totalrows);
991
992 /*
993 * Now we can compute the statistics for the expression columns.
994 */
995 if (numindexrows > 0)
996 {
997 MemoryContextSwitchTo(col_context);
998 for (i = 0; i < attr_cnt; i++)
999 {
1000 VacAttrStats *stats = thisdata->vacattrstats[i];
1001
1002 stats->exprvals = exprvals + i;
1003 stats->exprnulls = exprnulls + i;
1004 stats->rowstride = attr_cnt;
1005 stats->compute_stats(stats,
1007 numindexrows,
1008 totalindexrows);
1009
1010 MemoryContextReset(col_context);
1011 }
1012 }
1013
1014 /* And clean up */
1015 MemoryContextSwitchTo(ind_context);
1016
1018 FreeExecutorState(estate);
1019 MemoryContextReset(ind_context);
1020 }
1021
1022 MemoryContextSwitchTo(old_context);
1023 MemoryContextDelete(ind_context);
1024}
1025
1026/*
1027 * examine_attribute -- pre-analysis of a single column
1028 *
1029 * Determine whether the column is analyzable; if so, create and initialize
1030 * a VacAttrStats struct for it. If not, return NULL.
1031 *
1032 * If index_expr isn't NULL, then we're trying to analyze an expression index,
1033 * and index_expr is the expression tree representing the column's data.
1034 */
1035static VacAttrStats *
1036examine_attribute(Relation onerel, int attnum, Node *index_expr)
1037{
1038 Form_pg_attribute attr = TupleDescAttr(onerel->rd_att, attnum - 1);
1039 int attstattarget;
1040 HeapTuple atttuple;
1041 Datum dat;
1042 bool isnull;
1043 HeapTuple typtuple;
1044 VacAttrStats *stats;
1045 int i;
1046 bool ok;
1047
1048 /* Never analyze dropped columns */
1049 if (attr->attisdropped)
1050 return NULL;
1051
1052 /* Don't analyze virtual generated columns */
1053 if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL)
1054 return NULL;
1055
1056 /*
1057 * Get attstattarget value. Set to -1 if null. (Analyze functions expect
1058 * -1 to mean use default_statistics_target; see for example
1059 * std_typanalyze.)
1060 */
1062 if (!HeapTupleIsValid(atttuple))
1063 elog(ERROR, "cache lookup failed for attribute %d of relation %u",
1064 attnum, RelationGetRelid(onerel));
1065 dat = SysCacheGetAttr(ATTNUM, atttuple, Anum_pg_attribute_attstattarget, &isnull);
1066 attstattarget = isnull ? -1 : DatumGetInt16(dat);
1067 ReleaseSysCache(atttuple);
1068
1069 /* Don't analyze column if user has specified not to */
1070 if (attstattarget == 0)
1071 return NULL;
1072
1073 /*
1074 * Create the VacAttrStats struct.
1075 */
1076 stats = (VacAttrStats *) palloc0(sizeof(VacAttrStats));
1077 stats->attstattarget = attstattarget;
1078
1079 /*
1080 * When analyzing an expression index, believe the expression tree's type
1081 * not the column datatype --- the latter might be the opckeytype storage
1082 * type of the opclass, which is not interesting for our purposes. (Note:
1083 * if we did anything with non-expression index columns, we'd need to
1084 * figure out where to get the correct type info from, but for now that's
1085 * not a problem.) It's not clear whether anyone will care about the
1086 * typmod, but we store that too just in case.
1087 */
1088 if (index_expr)
1089 {
1090 stats->attrtypid = exprType(index_expr);
1091 stats->attrtypmod = exprTypmod(index_expr);
1092
1093 /*
1094 * If a collation has been specified for the index column, use that in
1095 * preference to anything else; but if not, fall back to whatever we
1096 * can get from the expression.
1097 */
1098 if (OidIsValid(onerel->rd_indcollation[attnum - 1]))
1099 stats->attrcollid = onerel->rd_indcollation[attnum - 1];
1100 else
1101 stats->attrcollid = exprCollation(index_expr);
1102 }
1103 else
1104 {
1105 stats->attrtypid = attr->atttypid;
1106 stats->attrtypmod = attr->atttypmod;
1107 stats->attrcollid = attr->attcollation;
1108 }
1109
1110 typtuple = SearchSysCacheCopy1(TYPEOID,
1111 ObjectIdGetDatum(stats->attrtypid));
1112 if (!HeapTupleIsValid(typtuple))
1113 elog(ERROR, "cache lookup failed for type %u", stats->attrtypid);
1114 stats->attrtype = (Form_pg_type) GETSTRUCT(typtuple);
1115 stats->anl_context = anl_context;
1116 stats->tupattnum = attnum;
1117
1118 /*
1119 * The fields describing the stats->stavalues[n] element types default to
1120 * the type of the data being analyzed, but the type-specific typanalyze
1121 * function can change them if it wants to store something else.
1122 */
1123 for (i = 0; i < STATISTIC_NUM_SLOTS; i++)
1124 {
1125 stats->statypid[i] = stats->attrtypid;
1126 stats->statyplen[i] = stats->attrtype->typlen;
1127 stats->statypbyval[i] = stats->attrtype->typbyval;
1128 stats->statypalign[i] = stats->attrtype->typalign;
1129 }
1130
1131 /*
1132 * Call the type-specific typanalyze function. If none is specified, use
1133 * std_typanalyze().
1134 */
1135 if (OidIsValid(stats->attrtype->typanalyze))
1136 ok = DatumGetBool(OidFunctionCall1(stats->attrtype->typanalyze,
1137 PointerGetDatum(stats)));
1138 else
1139 ok = std_typanalyze(stats);
1140
1141 if (!ok || stats->compute_stats == NULL || stats->minrows <= 0)
1142 {
1143 heap_freetuple(typtuple);
1144 pfree(stats);
1145 return NULL;
1146 }
1147
1148 return stats;
1149}
1150
1151/*
1152 * Read stream callback returning the next BlockNumber as chosen by the
1153 * BlockSampling algorithm.
1154 */
1155static BlockNumber
1157 void *callback_private_data,
1158 void *per_buffer_data)
1159{
1160 BlockSamplerData *bs = callback_private_data;
1161
1163}
1164
1165/*
1166 * acquire_sample_rows -- acquire a random sample of rows from the table
1167 *
1168 * Selected rows are returned in the caller-allocated array rows[], which
1169 * must have at least targrows entries.
1170 * The actual number of rows selected is returned as the function result.
1171 * We also estimate the total numbers of live and dead rows in the table,
1172 * and return them into *totalrows and *totaldeadrows, respectively.
1173 *
1174 * The returned list of tuples is in order by physical position in the table.
1175 * (We will rely on this later to derive correlation estimates.)
1176 *
1177 * As of May 2004 we use a new two-stage method: Stage one selects up
1178 * to targrows random blocks (or all blocks, if there aren't so many).
1179 * Stage two scans these blocks and uses the Vitter algorithm to create
1180 * a random sample of targrows rows (or less, if there are less in the
1181 * sample of blocks). The two stages are executed simultaneously: each
1182 * block is processed as soon as stage one returns its number and while
1183 * the rows are read stage two controls which ones are to be inserted
1184 * into the sample.
1185 *
1186 * Although every row has an equal chance of ending up in the final
1187 * sample, this sampling method is not perfect: not every possible
1188 * sample has an equal chance of being selected. For large relations
1189 * the number of different blocks represented by the sample tends to be
1190 * too small. We can live with that for now. Improvements are welcome.
1191 *
1192 * An important property of this sampling method is that because we do
1193 * look at a statistically unbiased set of blocks, we should get
1194 * unbiased estimates of the average numbers of live and dead rows per
1195 * block. The previous sampling method put too much credence in the row
1196 * density near the start of the table.
1197 */
1198static int
1200 HeapTuple *rows, int targrows,
1201 double *totalrows, double *totaldeadrows)
1202{
1203 int numrows = 0; /* # rows now in reservoir */
1204 double samplerows = 0; /* total # rows collected */
1205 double liverows = 0; /* # live rows seen */
1206 double deadrows = 0; /* # dead rows seen */
1207 double rowstoskip = -1; /* -1 means not set yet */
1208 uint32 randseed; /* Seed for block sampler(s) */
1209 BlockNumber totalblocks;
1210 TransactionId OldestXmin;
1212 ReservoirStateData rstate;
1213 TupleTableSlot *slot;
1214 TableScanDesc scan;
1215 BlockNumber nblocks;
1216 BlockNumber blksdone = 0;
1217 ReadStream *stream;
1218
1219 Assert(targrows > 0);
1220
1221 totalblocks = RelationGetNumberOfBlocks(onerel);
1222
1223 /* Need a cutoff xmin for HeapTupleSatisfiesVacuum */
1224 OldestXmin = GetOldestNonRemovableTransactionId(onerel);
1225
1226 /* Prepare for sampling block numbers */
1228 nblocks = BlockSampler_Init(&bs, totalblocks, targrows, randseed);
1229
1230 /* Report sampling block numbers */
1232 nblocks);
1233
1234 /* Prepare for sampling rows */
1235 reservoir_init_selection_state(&rstate, targrows);
1236
1237 scan = table_beginscan_analyze(onerel);
1238 slot = table_slot_create(onerel, NULL);
1239
1240 /*
1241 * It is safe to use batching, as block_sampling_read_stream_next never
1242 * blocks.
1243 */
1247 scan->rs_rd,
1250 &bs,
1251 0);
1252
1253 /* Outer loop over blocks to sample */
1254 while (table_scan_analyze_next_block(scan, stream))
1255 {
1256 vacuum_delay_point(true);
1257
1258 while (table_scan_analyze_next_tuple(scan, OldestXmin, &liverows, &deadrows, slot))
1259 {
1260 /*
1261 * The first targrows sample rows are simply copied into the
1262 * reservoir. Then we start replacing tuples in the sample until
1263 * we reach the end of the relation. This algorithm is from Jeff
1264 * Vitter's paper (see full citation in utils/misc/sampling.c). It
1265 * works by repeatedly computing the number of tuples to skip
1266 * before selecting a tuple, which replaces a randomly chosen
1267 * element of the reservoir (current set of tuples). At all times
1268 * the reservoir is a true random sample of the tuples we've
1269 * passed over so far, so when we fall off the end of the relation
1270 * we're done.
1271 */
1272 if (numrows < targrows)
1273 rows[numrows++] = ExecCopySlotHeapTuple(slot);
1274 else
1275 {
1276 /*
1277 * t in Vitter's paper is the number of records already
1278 * processed. If we need to compute a new S value, we must
1279 * use the not-yet-incremented value of samplerows as t.
1280 */
1281 if (rowstoskip < 0)
1282 rowstoskip = reservoir_get_next_S(&rstate, samplerows, targrows);
1283
1284 if (rowstoskip <= 0)
1285 {
1286 /*
1287 * Found a suitable tuple, so save it, replacing one old
1288 * tuple at random
1289 */
1290 int k = (int) (targrows * sampler_random_fract(&rstate.randstate));
1291
1292 Assert(k >= 0 && k < targrows);
1293 heap_freetuple(rows[k]);
1294 rows[k] = ExecCopySlotHeapTuple(slot);
1295 }
1296
1297 rowstoskip -= 1;
1298 }
1299
1300 samplerows += 1;
1301 }
1302
1304 ++blksdone);
1305 }
1306
1307 read_stream_end(stream);
1308
1310 table_endscan(scan);
1311
1312 /*
1313 * If we didn't find as many tuples as we wanted then we're done. No sort
1314 * is needed, since they're already in order.
1315 *
1316 * Otherwise we need to sort the collected tuples by position
1317 * (itempointer). It's not worth worrying about corner cases where the
1318 * tuples are already sorted.
1319 */
1320 if (numrows == targrows)
1321 qsort_interruptible(rows, numrows, sizeof(HeapTuple),
1322 compare_rows, NULL);
1323
1324 /*
1325 * Estimate total numbers of live and dead rows in relation, extrapolating
1326 * on the assumption that the average tuple density in pages we didn't
1327 * scan is the same as in the pages we did scan. Since what we scanned is
1328 * a random sample of the pages in the relation, this should be a good
1329 * assumption.
1330 */
1331 if (bs.m > 0)
1332 {
1333 *totalrows = floor((liverows / bs.m) * totalblocks + 0.5);
1334 *totaldeadrows = floor((deadrows / bs.m) * totalblocks + 0.5);
1335 }
1336 else
1337 {
1338 *totalrows = 0.0;
1339 *totaldeadrows = 0.0;
1340 }
1341
1342 /*
1343 * Emit some interesting relation info
1344 */
1345 ereport(elevel,
1346 (errmsg("\"%s\": scanned %d of %u pages, "
1347 "containing %.0f live rows and %.0f dead rows; "
1348 "%d rows in sample, %.0f estimated total rows",
1350 bs.m, totalblocks,
1351 liverows, deadrows,
1352 numrows, *totalrows)));
1353
1354 return numrows;
1355}
1356
1357/*
1358 * Comparator for sorting rows[] array
1359 */
1360static int
1361compare_rows(const void *a, const void *b, void *arg)
1362{
1363 HeapTuple ha = *(const HeapTuple *) a;
1364 HeapTuple hb = *(const HeapTuple *) b;
1369
1370 if (ba < bb)
1371 return -1;
1372 if (ba > bb)
1373 return 1;
1374 if (oa < ob)
1375 return -1;
1376 if (oa > ob)
1377 return 1;
1378 return 0;
1379}
1380
1381
1382/*
1383 * acquire_inherited_sample_rows -- acquire sample rows from inheritance tree
1384 *
1385 * This has the same API as acquire_sample_rows, except that rows are
1386 * collected from all inheritance children as well as the specified table.
1387 * We fail and return zero if there are no inheritance children, or if all
1388 * children are foreign tables that don't support ANALYZE.
1389 */
1390static int
1392 HeapTuple *rows, int targrows,
1393 double *totalrows, double *totaldeadrows)
1394{
1395 List *tableOIDs;
1396 Relation *rels;
1397 AcquireSampleRowsFunc *acquirefuncs;
1398 double *relblocks;
1399 double totalblocks;
1400 int numrows,
1401 nrels,
1402 i;
1403 ListCell *lc;
1404 bool has_child;
1405
1406 /* Initialize output parameters to zero now, in case we exit early */
1407 *totalrows = 0;
1408 *totaldeadrows = 0;
1409
1410 /*
1411 * Find all members of inheritance set. We only need AccessShareLock on
1412 * the children.
1413 */
1414 tableOIDs =
1416
1417 /*
1418 * Check that there's at least one descendant, else fail. This could
1419 * happen despite analyze_rel's relhassubclass check, if table once had a
1420 * child but no longer does. In that case, we can clear the
1421 * relhassubclass field so as not to make the same mistake again later.
1422 * (This is safe because we hold ShareUpdateExclusiveLock.)
1423 */
1424 if (list_length(tableOIDs) < 2)
1425 {
1426 /* CCI because we already updated the pg_class row in this command */
1429 ereport(elevel,
1430 (errmsg("skipping analyze of \"%s.%s\" inheritance tree --- this inheritance tree contains no child tables",
1432 RelationGetRelationName(onerel))));
1433 return 0;
1434 }
1435
1436 /*
1437 * Identify acquirefuncs to use, and count blocks in all the relations.
1438 * The result could overflow BlockNumber, so we use double arithmetic.
1439 */
1440 rels = (Relation *) palloc(list_length(tableOIDs) * sizeof(Relation));
1441 acquirefuncs = (AcquireSampleRowsFunc *)
1442 palloc(list_length(tableOIDs) * sizeof(AcquireSampleRowsFunc));
1443 relblocks = (double *) palloc(list_length(tableOIDs) * sizeof(double));
1444 totalblocks = 0;
1445 nrels = 0;
1446 has_child = false;
1447 foreach(lc, tableOIDs)
1448 {
1449 Oid childOID = lfirst_oid(lc);
1450 Relation childrel;
1451 AcquireSampleRowsFunc acquirefunc = NULL;
1452 BlockNumber relpages = 0;
1453
1454 /* We already got the needed lock */
1455 childrel = table_open(childOID, NoLock);
1456
1457 /* Ignore if temp table of another backend */
1458 if (RELATION_IS_OTHER_TEMP(childrel))
1459 {
1460 /* ... but release the lock on it */
1461 Assert(childrel != onerel);
1462 table_close(childrel, AccessShareLock);
1463 continue;
1464 }
1465
1466 /* Check table type (MATVIEW can't happen, but might as well allow) */
1467 if (childrel->rd_rel->relkind == RELKIND_RELATION ||
1468 childrel->rd_rel->relkind == RELKIND_MATVIEW)
1469 {
1470 /* Regular table, so use the regular row acquisition function */
1471 acquirefunc = acquire_sample_rows;
1472 relpages = RelationGetNumberOfBlocks(childrel);
1473 }
1474 else if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
1475 {
1476 /*
1477 * For a foreign table, call the FDW's hook function to see
1478 * whether it supports analysis.
1479 */
1480 FdwRoutine *fdwroutine;
1481 bool ok = false;
1482
1483 fdwroutine = GetFdwRoutineForRelation(childrel, false);
1484
1485 if (fdwroutine->AnalyzeForeignTable != NULL)
1486 ok = fdwroutine->AnalyzeForeignTable(childrel,
1487 &acquirefunc,
1488 &relpages);
1489
1490 if (!ok)
1491 {
1492 /* ignore, but release the lock on it */
1493 Assert(childrel != onerel);
1494 table_close(childrel, AccessShareLock);
1495 continue;
1496 }
1497 }
1498 else
1499 {
1500 /*
1501 * ignore, but release the lock on it. don't try to unlock the
1502 * passed-in relation
1503 */
1504 Assert(childrel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE);
1505 if (childrel != onerel)
1506 table_close(childrel, AccessShareLock);
1507 else
1508 table_close(childrel, NoLock);
1509 continue;
1510 }
1511
1512 /* OK, we'll process this child */
1513 has_child = true;
1514 rels[nrels] = childrel;
1515 acquirefuncs[nrels] = acquirefunc;
1516 relblocks[nrels] = (double) relpages;
1517 totalblocks += (double) relpages;
1518 nrels++;
1519 }
1520
1521 /*
1522 * If we don't have at least one child table to consider, fail. If the
1523 * relation is a partitioned table, it's not counted as a child table.
1524 */
1525 if (!has_child)
1526 {
1527 ereport(elevel,
1528 (errmsg("skipping analyze of \"%s.%s\" inheritance tree --- this inheritance tree contains no analyzable child tables",
1530 RelationGetRelationName(onerel))));
1531 return 0;
1532 }
1533
1534 /*
1535 * Now sample rows from each relation, proportionally to its fraction of
1536 * the total block count. (This might be less than desirable if the child
1537 * rels have radically different free-space percentages, but it's not
1538 * clear that it's worth working harder.)
1539 */
1541 nrels);
1542 numrows = 0;
1543 for (i = 0; i < nrels; i++)
1544 {
1545 Relation childrel = rels[i];
1546 AcquireSampleRowsFunc acquirefunc = acquirefuncs[i];
1547 double childblocks = relblocks[i];
1548
1549 /*
1550 * Report progress. The sampling function will normally report blocks
1551 * done/total, but we need to reset them to 0 here, so that they don't
1552 * show an old value until that.
1553 */
1554 {
1555 const int progress_index[] = {
1559 };
1560 const int64 progress_vals[] = {
1561 RelationGetRelid(childrel),
1562 0,
1563 0,
1564 };
1565
1566 pgstat_progress_update_multi_param(3, progress_index, progress_vals);
1567 }
1568
1569 if (childblocks > 0)
1570 {
1571 int childtargrows;
1572
1573 childtargrows = (int) rint(targrows * childblocks / totalblocks);
1574 /* Make sure we don't overrun due to roundoff error */
1575 childtargrows = Min(childtargrows, targrows - numrows);
1576 if (childtargrows > 0)
1577 {
1578 int childrows;
1579 double trows,
1580 tdrows;
1581
1582 /* Fetch a random sample of the child's rows */
1583 childrows = (*acquirefunc) (childrel, elevel,
1584 rows + numrows, childtargrows,
1585 &trows, &tdrows);
1586
1587 /* We may need to convert from child's rowtype to parent's */
1588 if (childrows > 0 &&
1590 RelationGetDescr(onerel)))
1591 {
1592 TupleConversionMap *map;
1593
1595 RelationGetDescr(onerel));
1596 if (map != NULL)
1597 {
1598 int j;
1599
1600 for (j = 0; j < childrows; j++)
1601 {
1602 HeapTuple newtup;
1603
1604 newtup = execute_attr_map_tuple(rows[numrows + j], map);
1605 heap_freetuple(rows[numrows + j]);
1606 rows[numrows + j] = newtup;
1607 }
1609 }
1610 }
1611
1612 /* And add to counts */
1613 numrows += childrows;
1614 *totalrows += trows;
1615 *totaldeadrows += tdrows;
1616 }
1617 }
1618
1619 /*
1620 * Note: we cannot release the child-table locks, since we may have
1621 * pointers to their TOAST tables in the sampled rows.
1622 */
1623 table_close(childrel, NoLock);
1625 i + 1);
1626 }
1627
1628 return numrows;
1629}
1630
1631
1632/*
1633 * update_attstats() -- update attribute statistics for one relation
1634 *
1635 * Statistics are stored in several places: the pg_class row for the
1636 * relation has stats about the whole relation, and there is a
1637 * pg_statistic row for each (non-system) attribute that has ever
1638 * been analyzed. The pg_class values are updated by VACUUM, not here.
1639 *
1640 * pg_statistic rows are just added or updated normally. This means
1641 * that pg_statistic will probably contain some deleted rows at the
1642 * completion of a vacuum cycle, unless it happens to get vacuumed last.
1643 *
1644 * To keep things simple, we punt for pg_statistic, and don't try
1645 * to compute or store rows for pg_statistic itself in pg_statistic.
1646 * This could possibly be made to work, but it's not worth the trouble.
1647 * Note analyze_rel() has seen to it that we won't come here when
1648 * vacuuming pg_statistic itself.
1649 *
1650 * Note: there would be a race condition here if two backends could
1651 * ANALYZE the same table concurrently. Presently, we lock that out
1652 * by taking a self-exclusive lock on the relation in analyze_rel().
1653 */
1654static void
1655update_attstats(Oid relid, bool inh, int natts, VacAttrStats **vacattrstats)
1656{
1657 Relation sd;
1658 int attno;
1659 CatalogIndexState indstate = NULL;
1660
1661 if (natts <= 0)
1662 return; /* nothing to do */
1663
1664 sd = table_open(StatisticRelationId, RowExclusiveLock);
1665
1666 for (attno = 0; attno < natts; attno++)
1667 {
1668 VacAttrStats *stats = vacattrstats[attno];
1669 HeapTuple stup,
1670 oldtup;
1671 int i,
1672 k,
1673 n;
1674 Datum values[Natts_pg_statistic];
1675 bool nulls[Natts_pg_statistic];
1676 bool replaces[Natts_pg_statistic];
1677
1678 /* Ignore attr if we weren't able to collect stats */
1679 if (!stats->stats_valid)
1680 continue;
1681
1682 /*
1683 * Construct a new pg_statistic tuple
1684 */
1685 for (i = 0; i < Natts_pg_statistic; ++i)
1686 {
1687 nulls[i] = false;
1688 replaces[i] = true;
1689 }
1690
1691 values[Anum_pg_statistic_starelid - 1] = ObjectIdGetDatum(relid);
1692 values[Anum_pg_statistic_staattnum - 1] = Int16GetDatum(stats->tupattnum);
1693 values[Anum_pg_statistic_stainherit - 1] = BoolGetDatum(inh);
1694 values[Anum_pg_statistic_stanullfrac - 1] = Float4GetDatum(stats->stanullfrac);
1695 values[Anum_pg_statistic_stawidth - 1] = Int32GetDatum(stats->stawidth);
1696 values[Anum_pg_statistic_stadistinct - 1] = Float4GetDatum(stats->stadistinct);
1697 i = Anum_pg_statistic_stakind1 - 1;
1698 for (k = 0; k < STATISTIC_NUM_SLOTS; k++)
1699 {
1700 values[i++] = Int16GetDatum(stats->stakind[k]); /* stakindN */
1701 }
1702 i = Anum_pg_statistic_staop1 - 1;
1703 for (k = 0; k < STATISTIC_NUM_SLOTS; k++)
1704 {
1705 values[i++] = ObjectIdGetDatum(stats->staop[k]); /* staopN */
1706 }
1707 i = Anum_pg_statistic_stacoll1 - 1;
1708 for (k = 0; k < STATISTIC_NUM_SLOTS; k++)
1709 {
1710 values[i++] = ObjectIdGetDatum(stats->stacoll[k]); /* stacollN */
1711 }
1712 i = Anum_pg_statistic_stanumbers1 - 1;
1713 for (k = 0; k < STATISTIC_NUM_SLOTS; k++)
1714 {
1715 int nnum = stats->numnumbers[k];
1716
1717 if (nnum > 0)
1718 {
1719 Datum *numdatums = (Datum *) palloc(nnum * sizeof(Datum));
1720 ArrayType *arry;
1721
1722 for (n = 0; n < nnum; n++)
1723 numdatums[n] = Float4GetDatum(stats->stanumbers[k][n]);
1724 arry = construct_array_builtin(numdatums, nnum, FLOAT4OID);
1725 values[i++] = PointerGetDatum(arry); /* stanumbersN */
1726 }
1727 else
1728 {
1729 nulls[i] = true;
1730 values[i++] = (Datum) 0;
1731 }
1732 }
1733 i = Anum_pg_statistic_stavalues1 - 1;
1734 for (k = 0; k < STATISTIC_NUM_SLOTS; k++)
1735 {
1736 if (stats->numvalues[k] > 0)
1737 {
1738 ArrayType *arry;
1739
1740 arry = construct_array(stats->stavalues[k],
1741 stats->numvalues[k],
1742 stats->statypid[k],
1743 stats->statyplen[k],
1744 stats->statypbyval[k],
1745 stats->statypalign[k]);
1746 values[i++] = PointerGetDatum(arry); /* stavaluesN */
1747 }
1748 else
1749 {
1750 nulls[i] = true;
1751 values[i++] = (Datum) 0;
1752 }
1753 }
1754
1755 /* Is there already a pg_statistic tuple for this attribute? */
1756 oldtup = SearchSysCache3(STATRELATTINH,
1757 ObjectIdGetDatum(relid),
1758 Int16GetDatum(stats->tupattnum),
1759 BoolGetDatum(inh));
1760
1761 /* Open index information when we know we need it */
1762 if (indstate == NULL)
1763 indstate = CatalogOpenIndexes(sd);
1764
1765 if (HeapTupleIsValid(oldtup))
1766 {
1767 /* Yes, replace it */
1768 stup = heap_modify_tuple(oldtup,
1769 RelationGetDescr(sd),
1770 values,
1771 nulls,
1772 replaces);
1773 ReleaseSysCache(oldtup);
1774 CatalogTupleUpdateWithInfo(sd, &stup->t_self, stup, indstate);
1775 }
1776 else
1777 {
1778 /* No, insert new tuple */
1779 stup = heap_form_tuple(RelationGetDescr(sd), values, nulls);
1780 CatalogTupleInsertWithInfo(sd, stup, indstate);
1781 }
1782
1783 heap_freetuple(stup);
1784 }
1785
1786 if (indstate != NULL)
1787 CatalogCloseIndexes(indstate);
1789}
1790
1791/*
1792 * Standard fetch function for use by compute_stats subroutines.
1793 *
1794 * This exists to provide some insulation between compute_stats routines
1795 * and the actual storage of the sample data.
1796 */
1797static Datum
1798std_fetch_func(VacAttrStatsP stats, int rownum, bool *isNull)
1799{
1800 int attnum = stats->tupattnum;
1801 HeapTuple tuple = stats->rows[rownum];
1802 TupleDesc tupDesc = stats->tupDesc;
1803
1804 return heap_getattr(tuple, attnum, tupDesc, isNull);
1805}
1806
1807/*
1808 * Fetch function for analyzing index expressions.
1809 *
1810 * We have not bothered to construct index tuples, instead the data is
1811 * just in Datum arrays.
1812 */
1813static Datum
1814ind_fetch_func(VacAttrStatsP stats, int rownum, bool *isNull)
1815{
1816 int i;
1817
1818 /* exprvals and exprnulls are already offset for proper column */
1819 i = rownum * stats->rowstride;
1820 *isNull = stats->exprnulls[i];
1821 return stats->exprvals[i];
1822}
1823
1824
1825/*==========================================================================
1826 *
1827 * Code below this point represents the "standard" type-specific statistics
1828 * analysis algorithms. This code can be replaced on a per-data-type basis
1829 * by setting a nonzero value in pg_type.typanalyze.
1830 *
1831 *==========================================================================
1832 */
1833
1834
1835/*
1836 * To avoid consuming too much memory during analysis and/or too much space
1837 * in the resulting pg_statistic rows, we ignore varlena datums that are wider
1838 * than WIDTH_THRESHOLD (after detoasting!). This is legitimate for MCV
1839 * and distinct-value calculations since a wide value is unlikely to be
1840 * duplicated at all, much less be a most-common value. For the same reason,
1841 * ignoring wide values will not affect our estimates of histogram bin
1842 * boundaries very much.
1843 */
1844#define WIDTH_THRESHOLD 1024
1845
1846#define swapInt(a,b) do {int _tmp; _tmp=a; a=b; b=_tmp;} while(0)
1847#define swapDatum(a,b) do {Datum _tmp; _tmp=a; a=b; b=_tmp;} while(0)
1848
1849/*
1850 * Extra information used by the default analysis routines
1851 */
1852typedef struct
1853{
1854 int count; /* # of duplicates */
1855 int first; /* values[] index of first occurrence */
1857
1858typedef struct
1859{
1863
1864
1865static void compute_trivial_stats(VacAttrStatsP stats,
1866 AnalyzeAttrFetchFunc fetchfunc,
1867 int samplerows,
1868 double totalrows);
1869static void compute_distinct_stats(VacAttrStatsP stats,
1870 AnalyzeAttrFetchFunc fetchfunc,
1871 int samplerows,
1872 double totalrows);
1873static void compute_scalar_stats(VacAttrStatsP stats,
1874 AnalyzeAttrFetchFunc fetchfunc,
1875 int samplerows,
1876 double totalrows);
1877static int compare_scalars(const void *a, const void *b, void *arg);
1878static int compare_mcvs(const void *a, const void *b, void *arg);
1879static int analyze_mcv_list(int *mcv_counts,
1880 int num_mcv,
1881 double stadistinct,
1882 double stanullfrac,
1883 int samplerows,
1884 double totalrows);
1885
1886
1887/*
1888 * std_typanalyze -- the default type-specific typanalyze function
1889 */
1890bool
1892{
1893 Oid ltopr;
1894 Oid eqopr;
1895 StdAnalyzeData *mystats;
1896
1897 /* If the attstattarget column is negative, use the default value */
1898 if (stats->attstattarget < 0)
1900
1901 /* Look for default "<" and "=" operators for column's type */
1903 false, false, false,
1904 &ltopr, &eqopr, NULL,
1905 NULL);
1906
1907 /* Save the operator info for compute_stats routines */
1908 mystats = (StdAnalyzeData *) palloc(sizeof(StdAnalyzeData));
1909 mystats->eqopr = eqopr;
1910 mystats->eqfunc = OidIsValid(eqopr) ? get_opcode(eqopr) : InvalidOid;
1911 mystats->ltopr = ltopr;
1912 stats->extra_data = mystats;
1913
1914 /*
1915 * Determine which standard statistics algorithm to use
1916 */
1917 if (OidIsValid(eqopr) && OidIsValid(ltopr))
1918 {
1919 /* Seems to be a scalar datatype */
1921 /*--------------------
1922 * The following choice of minrows is based on the paper
1923 * "Random sampling for histogram construction: how much is enough?"
1924 * by Surajit Chaudhuri, Rajeev Motwani and Vivek Narasayya, in
1925 * Proceedings of ACM SIGMOD International Conference on Management
1926 * of Data, 1998, Pages 436-447. Their Corollary 1 to Theorem 5
1927 * says that for table size n, histogram size k, maximum relative
1928 * error in bin size f, and error probability gamma, the minimum
1929 * random sample size is
1930 * r = 4 * k * ln(2*n/gamma) / f^2
1931 * Taking f = 0.5, gamma = 0.01, n = 10^6 rows, we obtain
1932 * r = 305.82 * k
1933 * Note that because of the log function, the dependence on n is
1934 * quite weak; even at n = 10^12, a 300*k sample gives <= 0.66
1935 * bin size error with probability 0.99. So there's no real need to
1936 * scale for n, which is a good thing because we don't necessarily
1937 * know it at this point.
1938 *--------------------
1939 */
1940 stats->minrows = 300 * stats->attstattarget;
1941 }
1942 else if (OidIsValid(eqopr))
1943 {
1944 /* We can still recognize distinct values */
1946 /* Might as well use the same minrows as above */
1947 stats->minrows = 300 * stats->attstattarget;
1948 }
1949 else
1950 {
1951 /* Can't do much but the trivial stuff */
1953 /* Might as well use the same minrows as above */
1954 stats->minrows = 300 * stats->attstattarget;
1955 }
1956
1957 return true;
1958}
1959
1960
1961/*
1962 * compute_trivial_stats() -- compute very basic column statistics
1963 *
1964 * We use this when we cannot find a hash "=" operator for the datatype.
1965 *
1966 * We determine the fraction of non-null rows and the average datum width.
1967 */
1968static void
1970 AnalyzeAttrFetchFunc fetchfunc,
1971 int samplerows,
1972 double totalrows)
1973{
1974 int i;
1975 int null_cnt = 0;
1976 int nonnull_cnt = 0;
1977 double total_width = 0;
1978 bool is_varlena = (!stats->attrtype->typbyval &&
1979 stats->attrtype->typlen == -1);
1980 bool is_varwidth = (!stats->attrtype->typbyval &&
1981 stats->attrtype->typlen < 0);
1982
1983 for (i = 0; i < samplerows; i++)
1984 {
1985 Datum value;
1986 bool isnull;
1987
1988 vacuum_delay_point(true);
1989
1990 value = fetchfunc(stats, i, &isnull);
1991
1992 /* Check for null/nonnull */
1993 if (isnull)
1994 {
1995 null_cnt++;
1996 continue;
1997 }
1998 nonnull_cnt++;
1999
2000 /*
2001 * If it's a variable-width field, add up widths for average width
2002 * calculation. Note that if the value is toasted, we use the toasted
2003 * width. We don't bother with this calculation if it's a fixed-width
2004 * type.
2005 */
2006 if (is_varlena)
2007 {
2008 total_width += VARSIZE_ANY(DatumGetPointer(value));
2009 }
2010 else if (is_varwidth)
2011 {
2012 /* must be cstring */
2013 total_width += strlen(DatumGetCString(value)) + 1;
2014 }
2015 }
2016
2017 /* We can only compute average width if we found some non-null values. */
2018 if (nonnull_cnt > 0)
2019 {
2020 stats->stats_valid = true;
2021 /* Do the simple null-frac and width stats */
2022 stats->stanullfrac = (double) null_cnt / (double) samplerows;
2023 if (is_varwidth)
2024 stats->stawidth = total_width / (double) nonnull_cnt;
2025 else
2026 stats->stawidth = stats->attrtype->typlen;
2027 stats->stadistinct = 0.0; /* "unknown" */
2028 }
2029 else if (null_cnt > 0)
2030 {
2031 /* We found only nulls; assume the column is entirely null */
2032 stats->stats_valid = true;
2033 stats->stanullfrac = 1.0;
2034 if (is_varwidth)
2035 stats->stawidth = 0; /* "unknown" */
2036 else
2037 stats->stawidth = stats->attrtype->typlen;
2038 stats->stadistinct = 0.0; /* "unknown" */
2039 }
2040}
2041
2042
2043/*
2044 * compute_distinct_stats() -- compute column statistics including ndistinct
2045 *
2046 * We use this when we can find only an "=" operator for the datatype.
2047 *
2048 * We determine the fraction of non-null rows, the average width, the
2049 * most common values, and the (estimated) number of distinct values.
2050 *
2051 * The most common values are determined by brute force: we keep a list
2052 * of previously seen values, ordered by number of times seen, as we scan
2053 * the samples. A newly seen value is inserted just after the last
2054 * multiply-seen value, causing the bottommost (oldest) singly-seen value
2055 * to drop off the list. The accuracy of this method, and also its cost,
2056 * depend mainly on the length of the list we are willing to keep.
2057 */
2058static void
2060 AnalyzeAttrFetchFunc fetchfunc,
2061 int samplerows,
2062 double totalrows)
2063{
2064 int i;
2065 int null_cnt = 0;
2066 int nonnull_cnt = 0;
2067 int toowide_cnt = 0;
2068 double total_width = 0;
2069 bool is_varlena = (!stats->attrtype->typbyval &&
2070 stats->attrtype->typlen == -1);
2071 bool is_varwidth = (!stats->attrtype->typbyval &&
2072 stats->attrtype->typlen < 0);
2073 FmgrInfo f_cmpeq;
2074 typedef struct
2075 {
2076 Datum value;
2077 int count;
2078 } TrackItem;
2079 TrackItem *track;
2080 int track_cnt,
2081 track_max;
2082 int num_mcv = stats->attstattarget;
2083 StdAnalyzeData *mystats = (StdAnalyzeData *) stats->extra_data;
2084
2085 /*
2086 * We track up to 2*n values for an n-element MCV list; but at least 10
2087 */
2088 track_max = 2 * num_mcv;
2089 if (track_max < 10)
2090 track_max = 10;
2091 track = (TrackItem *) palloc(track_max * sizeof(TrackItem));
2092 track_cnt = 0;
2093
2094 fmgr_info(mystats->eqfunc, &f_cmpeq);
2095
2096 for (i = 0; i < samplerows; i++)
2097 {
2098 Datum value;
2099 bool isnull;
2100 bool match;
2101 int firstcount1,
2102 j;
2103
2104 vacuum_delay_point(true);
2105
2106 value = fetchfunc(stats, i, &isnull);
2107
2108 /* Check for null/nonnull */
2109 if (isnull)
2110 {
2111 null_cnt++;
2112 continue;
2113 }
2114 nonnull_cnt++;
2115
2116 /*
2117 * If it's a variable-width field, add up widths for average width
2118 * calculation. Note that if the value is toasted, we use the toasted
2119 * width. We don't bother with this calculation if it's a fixed-width
2120 * type.
2121 */
2122 if (is_varlena)
2123 {
2124 total_width += VARSIZE_ANY(DatumGetPointer(value));
2125
2126 /*
2127 * If the value is toasted, we want to detoast it just once to
2128 * avoid repeated detoastings and resultant excess memory usage
2129 * during the comparisons. Also, check to see if the value is
2130 * excessively wide, and if so don't detoast at all --- just
2131 * ignore the value.
2132 */
2134 {
2135 toowide_cnt++;
2136 continue;
2137 }
2139 }
2140 else if (is_varwidth)
2141 {
2142 /* must be cstring */
2143 total_width += strlen(DatumGetCString(value)) + 1;
2144 }
2145
2146 /*
2147 * See if the value matches anything we're already tracking.
2148 */
2149 match = false;
2150 firstcount1 = track_cnt;
2151 for (j = 0; j < track_cnt; j++)
2152 {
2153 if (DatumGetBool(FunctionCall2Coll(&f_cmpeq,
2154 stats->attrcollid,
2155 value, track[j].value)))
2156 {
2157 match = true;
2158 break;
2159 }
2160 if (j < firstcount1 && track[j].count == 1)
2161 firstcount1 = j;
2162 }
2163
2164 if (match)
2165 {
2166 /* Found a match */
2167 track[j].count++;
2168 /* This value may now need to "bubble up" in the track list */
2169 while (j > 0 && track[j].count > track[j - 1].count)
2170 {
2171 swapDatum(track[j].value, track[j - 1].value);
2172 swapInt(track[j].count, track[j - 1].count);
2173 j--;
2174 }
2175 }
2176 else
2177 {
2178 /* No match. Insert at head of count-1 list */
2179 if (track_cnt < track_max)
2180 track_cnt++;
2181 for (j = track_cnt - 1; j > firstcount1; j--)
2182 {
2183 track[j].value = track[j - 1].value;
2184 track[j].count = track[j - 1].count;
2185 }
2186 if (firstcount1 < track_cnt)
2187 {
2188 track[firstcount1].value = value;
2189 track[firstcount1].count = 1;
2190 }
2191 }
2192 }
2193
2194 /* We can only compute real stats if we found some non-null values. */
2195 if (nonnull_cnt > 0)
2196 {
2197 int nmultiple,
2198 summultiple;
2199
2200 stats->stats_valid = true;
2201 /* Do the simple null-frac and width stats */
2202 stats->stanullfrac = (double) null_cnt / (double) samplerows;
2203 if (is_varwidth)
2204 stats->stawidth = total_width / (double) nonnull_cnt;
2205 else
2206 stats->stawidth = stats->attrtype->typlen;
2207
2208 /* Count the number of values we found multiple times */
2209 summultiple = 0;
2210 for (nmultiple = 0; nmultiple < track_cnt; nmultiple++)
2211 {
2212 if (track[nmultiple].count == 1)
2213 break;
2214 summultiple += track[nmultiple].count;
2215 }
2216
2217 if (nmultiple == 0)
2218 {
2219 /*
2220 * If we found no repeated non-null values, assume it's a unique
2221 * column; but be sure to discount for any nulls we found.
2222 */
2223 stats->stadistinct = -1.0 * (1.0 - stats->stanullfrac);
2224 }
2225 else if (track_cnt < track_max && toowide_cnt == 0 &&
2226 nmultiple == track_cnt)
2227 {
2228 /*
2229 * Our track list includes every value in the sample, and every
2230 * value appeared more than once. Assume the column has just
2231 * these values. (This case is meant to address columns with
2232 * small, fixed sets of possible values, such as boolean or enum
2233 * columns. If there are any values that appear just once in the
2234 * sample, including too-wide values, we should assume that that's
2235 * not what we're dealing with.)
2236 */
2237 stats->stadistinct = track_cnt;
2238 }
2239 else
2240 {
2241 /*----------
2242 * Estimate the number of distinct values using the estimator
2243 * proposed by Haas and Stokes in IBM Research Report RJ 10025:
2244 * n*d / (n - f1 + f1*n/N)
2245 * where f1 is the number of distinct values that occurred
2246 * exactly once in our sample of n rows (from a total of N),
2247 * and d is the total number of distinct values in the sample.
2248 * This is their Duj1 estimator; the other estimators they
2249 * recommend are considerably more complex, and are numerically
2250 * very unstable when n is much smaller than N.
2251 *
2252 * In this calculation, we consider only non-nulls. We used to
2253 * include rows with null values in the n and N counts, but that
2254 * leads to inaccurate answers in columns with many nulls, and
2255 * it's intuitively bogus anyway considering the desired result is
2256 * the number of distinct non-null values.
2257 *
2258 * We assume (not very reliably!) that all the multiply-occurring
2259 * values are reflected in the final track[] list, and the other
2260 * nonnull values all appeared but once. (XXX this usually
2261 * results in a drastic overestimate of ndistinct. Can we do
2262 * any better?)
2263 *----------
2264 */
2265 int f1 = nonnull_cnt - summultiple;
2266 int d = f1 + nmultiple;
2267 double n = samplerows - null_cnt;
2268 double N = totalrows * (1.0 - stats->stanullfrac);
2269 double stadistinct;
2270
2271 /* N == 0 shouldn't happen, but just in case ... */
2272 if (N > 0)
2273 stadistinct = (n * d) / ((n - f1) + f1 * n / N);
2274 else
2275 stadistinct = 0;
2276
2277 /* Clamp to sane range in case of roundoff error */
2278 if (stadistinct < d)
2279 stadistinct = d;
2280 if (stadistinct > N)
2281 stadistinct = N;
2282 /* And round to integer */
2283 stats->stadistinct = floor(stadistinct + 0.5);
2284 }
2285
2286 /*
2287 * If we estimated the number of distinct values at more than 10% of
2288 * the total row count (a very arbitrary limit), then assume that
2289 * stadistinct should scale with the row count rather than be a fixed
2290 * value.
2291 */
2292 if (stats->stadistinct > 0.1 * totalrows)
2293 stats->stadistinct = -(stats->stadistinct / totalrows);
2294
2295 /*
2296 * Decide how many values are worth storing as most-common values. If
2297 * we are able to generate a complete MCV list (all the values in the
2298 * sample will fit, and we think these are all the ones in the table),
2299 * then do so. Otherwise, store only those values that are
2300 * significantly more common than the values not in the list.
2301 *
2302 * Note: the first of these cases is meant to address columns with
2303 * small, fixed sets of possible values, such as boolean or enum
2304 * columns. If we can *completely* represent the column population by
2305 * an MCV list that will fit into the stats target, then we should do
2306 * so and thus provide the planner with complete information. But if
2307 * the MCV list is not complete, it's generally worth being more
2308 * selective, and not just filling it all the way up to the stats
2309 * target.
2310 */
2311 if (track_cnt < track_max && toowide_cnt == 0 &&
2312 stats->stadistinct > 0 &&
2313 track_cnt <= num_mcv)
2314 {
2315 /* Track list includes all values seen, and all will fit */
2316 num_mcv = track_cnt;
2317 }
2318 else
2319 {
2320 int *mcv_counts;
2321
2322 /* Incomplete list; decide how many values are worth keeping */
2323 if (num_mcv > track_cnt)
2324 num_mcv = track_cnt;
2325
2326 if (num_mcv > 0)
2327 {
2328 mcv_counts = (int *) palloc(num_mcv * sizeof(int));
2329 for (i = 0; i < num_mcv; i++)
2330 mcv_counts[i] = track[i].count;
2331
2332 num_mcv = analyze_mcv_list(mcv_counts, num_mcv,
2333 stats->stadistinct,
2334 stats->stanullfrac,
2335 samplerows, totalrows);
2336 }
2337 }
2338
2339 /* Generate MCV slot entry */
2340 if (num_mcv > 0)
2341 {
2342 MemoryContext old_context;
2343 Datum *mcv_values;
2344 float4 *mcv_freqs;
2345
2346 /* Must copy the target values into anl_context */
2347 old_context = MemoryContextSwitchTo(stats->anl_context);
2348 mcv_values = (Datum *) palloc(num_mcv * sizeof(Datum));
2349 mcv_freqs = (float4 *) palloc(num_mcv * sizeof(float4));
2350 for (i = 0; i < num_mcv; i++)
2351 {
2352 mcv_values[i] = datumCopy(track[i].value,
2353 stats->attrtype->typbyval,
2354 stats->attrtype->typlen);
2355 mcv_freqs[i] = (double) track[i].count / (double) samplerows;
2356 }
2357 MemoryContextSwitchTo(old_context);
2358
2359 stats->stakind[0] = STATISTIC_KIND_MCV;
2360 stats->staop[0] = mystats->eqopr;
2361 stats->stacoll[0] = stats->attrcollid;
2362 stats->stanumbers[0] = mcv_freqs;
2363 stats->numnumbers[0] = num_mcv;
2364 stats->stavalues[0] = mcv_values;
2365 stats->numvalues[0] = num_mcv;
2366
2367 /*
2368 * Accept the defaults for stats->statypid and others. They have
2369 * been set before we were called (see vacuum.h)
2370 */
2371 }
2372 }
2373 else if (null_cnt > 0)
2374 {
2375 /* We found only nulls; assume the column is entirely null */
2376 stats->stats_valid = true;
2377 stats->stanullfrac = 1.0;
2378 if (is_varwidth)
2379 stats->stawidth = 0; /* "unknown" */
2380 else
2381 stats->stawidth = stats->attrtype->typlen;
2382 stats->stadistinct = 0.0; /* "unknown" */
2383 }
2384
2385 /* We don't need to bother cleaning up any of our temporary palloc's */
2386}
2387
2388
2389/*
2390 * compute_scalar_stats() -- compute column statistics
2391 *
2392 * We use this when we can find "=" and "<" operators for the datatype.
2393 *
2394 * We determine the fraction of non-null rows, the average width, the
2395 * most common values, the (estimated) number of distinct values, the
2396 * distribution histogram, and the correlation of physical to logical order.
2397 *
2398 * The desired stats can be determined fairly easily after sorting the
2399 * data values into order.
2400 */
2401static void
2403 AnalyzeAttrFetchFunc fetchfunc,
2404 int samplerows,
2405 double totalrows)
2406{
2407 int i;
2408 int null_cnt = 0;
2409 int nonnull_cnt = 0;
2410 int toowide_cnt = 0;
2411 double total_width = 0;
2412 bool is_varlena = (!stats->attrtype->typbyval &&
2413 stats->attrtype->typlen == -1);
2414 bool is_varwidth = (!stats->attrtype->typbyval &&
2415 stats->attrtype->typlen < 0);
2416 double corr_xysum;
2417 SortSupportData ssup;
2419 int values_cnt = 0;
2420 int *tupnoLink;
2421 ScalarMCVItem *track;
2422 int track_cnt = 0;
2423 int num_mcv = stats->attstattarget;
2424 int num_bins = stats->attstattarget;
2425 StdAnalyzeData *mystats = (StdAnalyzeData *) stats->extra_data;
2426
2427 values = (ScalarItem *) palloc(samplerows * sizeof(ScalarItem));
2428 tupnoLink = (int *) palloc(samplerows * sizeof(int));
2429 track = (ScalarMCVItem *) palloc(num_mcv * sizeof(ScalarMCVItem));
2430
2431 memset(&ssup, 0, sizeof(ssup));
2433 ssup.ssup_collation = stats->attrcollid;
2434 ssup.ssup_nulls_first = false;
2435
2436 /*
2437 * For now, don't perform abbreviated key conversion, because full values
2438 * are required for MCV slot generation. Supporting that optimization
2439 * would necessitate teaching compare_scalars() to call a tie-breaker.
2440 */
2441 ssup.abbreviate = false;
2442
2443 PrepareSortSupportFromOrderingOp(mystats->ltopr, &ssup);
2444
2445 /* Initial scan to find sortable values */
2446 for (i = 0; i < samplerows; i++)
2447 {
2448 Datum value;
2449 bool isnull;
2450
2451 vacuum_delay_point(true);
2452
2453 value = fetchfunc(stats, i, &isnull);
2454
2455 /* Check for null/nonnull */
2456 if (isnull)
2457 {
2458 null_cnt++;
2459 continue;
2460 }
2461 nonnull_cnt++;
2462
2463 /*
2464 * If it's a variable-width field, add up widths for average width
2465 * calculation. Note that if the value is toasted, we use the toasted
2466 * width. We don't bother with this calculation if it's a fixed-width
2467 * type.
2468 */
2469 if (is_varlena)
2470 {
2471 total_width += VARSIZE_ANY(DatumGetPointer(value));
2472
2473 /*
2474 * If the value is toasted, we want to detoast it just once to
2475 * avoid repeated detoastings and resultant excess memory usage
2476 * during the comparisons. Also, check to see if the value is
2477 * excessively wide, and if so don't detoast at all --- just
2478 * ignore the value.
2479 */
2481 {
2482 toowide_cnt++;
2483 continue;
2484 }
2486 }
2487 else if (is_varwidth)
2488 {
2489 /* must be cstring */
2490 total_width += strlen(DatumGetCString(value)) + 1;
2491 }
2492
2493 /* Add it to the list to be sorted */
2494 values[values_cnt].value = value;
2495 values[values_cnt].tupno = values_cnt;
2496 tupnoLink[values_cnt] = values_cnt;
2497 values_cnt++;
2498 }
2499
2500 /* We can only compute real stats if we found some sortable values. */
2501 if (values_cnt > 0)
2502 {
2503 int ndistinct, /* # distinct values in sample */
2504 nmultiple, /* # that appear multiple times */
2505 num_hist,
2506 dups_cnt;
2507 int slot_idx = 0;
2509
2510 /* Sort the collected values */
2511 cxt.ssup = &ssup;
2512 cxt.tupnoLink = tupnoLink;
2513 qsort_interruptible(values, values_cnt, sizeof(ScalarItem),
2514 compare_scalars, &cxt);
2515
2516 /*
2517 * Now scan the values in order, find the most common ones, and also
2518 * accumulate ordering-correlation statistics.
2519 *
2520 * To determine which are most common, we first have to count the
2521 * number of duplicates of each value. The duplicates are adjacent in
2522 * the sorted list, so a brute-force approach is to compare successive
2523 * datum values until we find two that are not equal. However, that
2524 * requires N-1 invocations of the datum comparison routine, which are
2525 * completely redundant with work that was done during the sort. (The
2526 * sort algorithm must at some point have compared each pair of items
2527 * that are adjacent in the sorted order; otherwise it could not know
2528 * that it's ordered the pair correctly.) We exploit this by having
2529 * compare_scalars remember the highest tupno index that each
2530 * ScalarItem has been found equal to. At the end of the sort, a
2531 * ScalarItem's tupnoLink will still point to itself if and only if it
2532 * is the last item of its group of duplicates (since the group will
2533 * be ordered by tupno).
2534 */
2535 corr_xysum = 0;
2536 ndistinct = 0;
2537 nmultiple = 0;
2538 dups_cnt = 0;
2539 for (i = 0; i < values_cnt; i++)
2540 {
2541 int tupno = values[i].tupno;
2542
2543 corr_xysum += ((double) i) * ((double) tupno);
2544 dups_cnt++;
2545 if (tupnoLink[tupno] == tupno)
2546 {
2547 /* Reached end of duplicates of this value */
2548 ndistinct++;
2549 if (dups_cnt > 1)
2550 {
2551 nmultiple++;
2552 if (track_cnt < num_mcv ||
2553 dups_cnt > track[track_cnt - 1].count)
2554 {
2555 /*
2556 * Found a new item for the mcv list; find its
2557 * position, bubbling down old items if needed. Loop
2558 * invariant is that j points at an empty/ replaceable
2559 * slot.
2560 */
2561 int j;
2562
2563 if (track_cnt < num_mcv)
2564 track_cnt++;
2565 for (j = track_cnt - 1; j > 0; j--)
2566 {
2567 if (dups_cnt <= track[j - 1].count)
2568 break;
2569 track[j].count = track[j - 1].count;
2570 track[j].first = track[j - 1].first;
2571 }
2572 track[j].count = dups_cnt;
2573 track[j].first = i + 1 - dups_cnt;
2574 }
2575 }
2576 dups_cnt = 0;
2577 }
2578 }
2579
2580 stats->stats_valid = true;
2581 /* Do the simple null-frac and width stats */
2582 stats->stanullfrac = (double) null_cnt / (double) samplerows;
2583 if (is_varwidth)
2584 stats->stawidth = total_width / (double) nonnull_cnt;
2585 else
2586 stats->stawidth = stats->attrtype->typlen;
2587
2588 if (nmultiple == 0)
2589 {
2590 /*
2591 * If we found no repeated non-null values, assume it's a unique
2592 * column; but be sure to discount for any nulls we found.
2593 */
2594 stats->stadistinct = -1.0 * (1.0 - stats->stanullfrac);
2595 }
2596 else if (toowide_cnt == 0 && nmultiple == ndistinct)
2597 {
2598 /*
2599 * Every value in the sample appeared more than once. Assume the
2600 * column has just these values. (This case is meant to address
2601 * columns with small, fixed sets of possible values, such as
2602 * boolean or enum columns. If there are any values that appear
2603 * just once in the sample, including too-wide values, we should
2604 * assume that that's not what we're dealing with.)
2605 */
2606 stats->stadistinct = ndistinct;
2607 }
2608 else
2609 {
2610 /*----------
2611 * Estimate the number of distinct values using the estimator
2612 * proposed by Haas and Stokes in IBM Research Report RJ 10025:
2613 * n*d / (n - f1 + f1*n/N)
2614 * where f1 is the number of distinct values that occurred
2615 * exactly once in our sample of n rows (from a total of N),
2616 * and d is the total number of distinct values in the sample.
2617 * This is their Duj1 estimator; the other estimators they
2618 * recommend are considerably more complex, and are numerically
2619 * very unstable when n is much smaller than N.
2620 *
2621 * In this calculation, we consider only non-nulls. We used to
2622 * include rows with null values in the n and N counts, but that
2623 * leads to inaccurate answers in columns with many nulls, and
2624 * it's intuitively bogus anyway considering the desired result is
2625 * the number of distinct non-null values.
2626 *
2627 * Overwidth values are assumed to have been distinct.
2628 *----------
2629 */
2630 int f1 = ndistinct - nmultiple + toowide_cnt;
2631 int d = f1 + nmultiple;
2632 double n = samplerows - null_cnt;
2633 double N = totalrows * (1.0 - stats->stanullfrac);
2634 double stadistinct;
2635
2636 /* N == 0 shouldn't happen, but just in case ... */
2637 if (N > 0)
2638 stadistinct = (n * d) / ((n - f1) + f1 * n / N);
2639 else
2640 stadistinct = 0;
2641
2642 /* Clamp to sane range in case of roundoff error */
2643 if (stadistinct < d)
2644 stadistinct = d;
2645 if (stadistinct > N)
2646 stadistinct = N;
2647 /* And round to integer */
2648 stats->stadistinct = floor(stadistinct + 0.5);
2649 }
2650
2651 /*
2652 * If we estimated the number of distinct values at more than 10% of
2653 * the total row count (a very arbitrary limit), then assume that
2654 * stadistinct should scale with the row count rather than be a fixed
2655 * value.
2656 */
2657 if (stats->stadistinct > 0.1 * totalrows)
2658 stats->stadistinct = -(stats->stadistinct / totalrows);
2659
2660 /*
2661 * Decide how many values are worth storing as most-common values. If
2662 * we are able to generate a complete MCV list (all the values in the
2663 * sample will fit, and we think these are all the ones in the table),
2664 * then do so. Otherwise, store only those values that are
2665 * significantly more common than the values not in the list.
2666 *
2667 * Note: the first of these cases is meant to address columns with
2668 * small, fixed sets of possible values, such as boolean or enum
2669 * columns. If we can *completely* represent the column population by
2670 * an MCV list that will fit into the stats target, then we should do
2671 * so and thus provide the planner with complete information. But if
2672 * the MCV list is not complete, it's generally worth being more
2673 * selective, and not just filling it all the way up to the stats
2674 * target.
2675 */
2676 if (track_cnt == ndistinct && toowide_cnt == 0 &&
2677 stats->stadistinct > 0 &&
2678 track_cnt <= num_mcv)
2679 {
2680 /* Track list includes all values seen, and all will fit */
2681 num_mcv = track_cnt;
2682 }
2683 else
2684 {
2685 int *mcv_counts;
2686
2687 /* Incomplete list; decide how many values are worth keeping */
2688 if (num_mcv > track_cnt)
2689 num_mcv = track_cnt;
2690
2691 if (num_mcv > 0)
2692 {
2693 mcv_counts = (int *) palloc(num_mcv * sizeof(int));
2694 for (i = 0; i < num_mcv; i++)
2695 mcv_counts[i] = track[i].count;
2696
2697 num_mcv = analyze_mcv_list(mcv_counts, num_mcv,
2698 stats->stadistinct,
2699 stats->stanullfrac,
2700 samplerows, totalrows);
2701 }
2702 }
2703
2704 /* Generate MCV slot entry */
2705 if (num_mcv > 0)
2706 {
2707 MemoryContext old_context;
2708 Datum *mcv_values;
2709 float4 *mcv_freqs;
2710
2711 /* Must copy the target values into anl_context */
2712 old_context = MemoryContextSwitchTo(stats->anl_context);
2713 mcv_values = (Datum *) palloc(num_mcv * sizeof(Datum));
2714 mcv_freqs = (float4 *) palloc(num_mcv * sizeof(float4));
2715 for (i = 0; i < num_mcv; i++)
2716 {
2717 mcv_values[i] = datumCopy(values[track[i].first].value,
2718 stats->attrtype->typbyval,
2719 stats->attrtype->typlen);
2720 mcv_freqs[i] = (double) track[i].count / (double) samplerows;
2721 }
2722 MemoryContextSwitchTo(old_context);
2723
2724 stats->stakind[slot_idx] = STATISTIC_KIND_MCV;
2725 stats->staop[slot_idx] = mystats->eqopr;
2726 stats->stacoll[slot_idx] = stats->attrcollid;
2727 stats->stanumbers[slot_idx] = mcv_freqs;
2728 stats->numnumbers[slot_idx] = num_mcv;
2729 stats->stavalues[slot_idx] = mcv_values;
2730 stats->numvalues[slot_idx] = num_mcv;
2731
2732 /*
2733 * Accept the defaults for stats->statypid and others. They have
2734 * been set before we were called (see vacuum.h)
2735 */
2736 slot_idx++;
2737 }
2738
2739 /*
2740 * Generate a histogram slot entry if there are at least two distinct
2741 * values not accounted for in the MCV list. (This ensures the
2742 * histogram won't collapse to empty or a singleton.)
2743 */
2744 num_hist = ndistinct - num_mcv;
2745 if (num_hist > num_bins)
2746 num_hist = num_bins + 1;
2747 if (num_hist >= 2)
2748 {
2749 MemoryContext old_context;
2750 Datum *hist_values;
2751 int nvals;
2752 int pos,
2753 posfrac,
2754 delta,
2755 deltafrac;
2756
2757 /* Sort the MCV items into position order to speed next loop */
2758 qsort_interruptible(track, num_mcv, sizeof(ScalarMCVItem),
2759 compare_mcvs, NULL);
2760
2761 /*
2762 * Collapse out the MCV items from the values[] array.
2763 *
2764 * Note we destroy the values[] array here... but we don't need it
2765 * for anything more. We do, however, still need values_cnt.
2766 * nvals will be the number of remaining entries in values[].
2767 */
2768 if (num_mcv > 0)
2769 {
2770 int src,
2771 dest;
2772 int j;
2773
2774 src = dest = 0;
2775 j = 0; /* index of next interesting MCV item */
2776 while (src < values_cnt)
2777 {
2778 int ncopy;
2779
2780 if (j < num_mcv)
2781 {
2782 int first = track[j].first;
2783
2784 if (src >= first)
2785 {
2786 /* advance past this MCV item */
2787 src = first + track[j].count;
2788 j++;
2789 continue;
2790 }
2791 ncopy = first - src;
2792 }
2793 else
2794 ncopy = values_cnt - src;
2795 memmove(&values[dest], &values[src],
2796 ncopy * sizeof(ScalarItem));
2797 src += ncopy;
2798 dest += ncopy;
2799 }
2800 nvals = dest;
2801 }
2802 else
2803 nvals = values_cnt;
2804 Assert(nvals >= num_hist);
2805
2806 /* Must copy the target values into anl_context */
2807 old_context = MemoryContextSwitchTo(stats->anl_context);
2808 hist_values = (Datum *) palloc(num_hist * sizeof(Datum));
2809
2810 /*
2811 * The object of this loop is to copy the first and last values[]
2812 * entries along with evenly-spaced values in between. So the
2813 * i'th value is values[(i * (nvals - 1)) / (num_hist - 1)]. But
2814 * computing that subscript directly risks integer overflow when
2815 * the stats target is more than a couple thousand. Instead we
2816 * add (nvals - 1) / (num_hist - 1) to pos at each step, tracking
2817 * the integral and fractional parts of the sum separately.
2818 */
2819 delta = (nvals - 1) / (num_hist - 1);
2820 deltafrac = (nvals - 1) % (num_hist - 1);
2821 pos = posfrac = 0;
2822
2823 for (i = 0; i < num_hist; i++)
2824 {
2825 hist_values[i] = datumCopy(values[pos].value,
2826 stats->attrtype->typbyval,
2827 stats->attrtype->typlen);
2828 pos += delta;
2829 posfrac += deltafrac;
2830 if (posfrac >= (num_hist - 1))
2831 {
2832 /* fractional part exceeds 1, carry to integer part */
2833 pos++;
2834 posfrac -= (num_hist - 1);
2835 }
2836 }
2837
2838 MemoryContextSwitchTo(old_context);
2839
2840 stats->stakind[slot_idx] = STATISTIC_KIND_HISTOGRAM;
2841 stats->staop[slot_idx] = mystats->ltopr;
2842 stats->stacoll[slot_idx] = stats->attrcollid;
2843 stats->stavalues[slot_idx] = hist_values;
2844 stats->numvalues[slot_idx] = num_hist;
2845
2846 /*
2847 * Accept the defaults for stats->statypid and others. They have
2848 * been set before we were called (see vacuum.h)
2849 */
2850 slot_idx++;
2851 }
2852
2853 /* Generate a correlation entry if there are multiple values */
2854 if (values_cnt > 1)
2855 {
2856 MemoryContext old_context;
2857 float4 *corrs;
2858 double corr_xsum,
2859 corr_x2sum;
2860
2861 /* Must copy the target values into anl_context */
2862 old_context = MemoryContextSwitchTo(stats->anl_context);
2863 corrs = (float4 *) palloc(sizeof(float4));
2864 MemoryContextSwitchTo(old_context);
2865
2866 /*----------
2867 * Since we know the x and y value sets are both
2868 * 0, 1, ..., values_cnt-1
2869 * we have sum(x) = sum(y) =
2870 * (values_cnt-1)*values_cnt / 2
2871 * and sum(x^2) = sum(y^2) =
2872 * (values_cnt-1)*values_cnt*(2*values_cnt-1) / 6.
2873 *----------
2874 */
2875 corr_xsum = ((double) (values_cnt - 1)) *
2876 ((double) values_cnt) / 2.0;
2877 corr_x2sum = ((double) (values_cnt - 1)) *
2878 ((double) values_cnt) * (double) (2 * values_cnt - 1) / 6.0;
2879
2880 /* And the correlation coefficient reduces to */
2881 corrs[0] = (values_cnt * corr_xysum - corr_xsum * corr_xsum) /
2882 (values_cnt * corr_x2sum - corr_xsum * corr_xsum);
2883
2884 stats->stakind[slot_idx] = STATISTIC_KIND_CORRELATION;
2885 stats->staop[slot_idx] = mystats->ltopr;
2886 stats->stacoll[slot_idx] = stats->attrcollid;
2887 stats->stanumbers[slot_idx] = corrs;
2888 stats->numnumbers[slot_idx] = 1;
2889 slot_idx++;
2890 }
2891 }
2892 else if (nonnull_cnt > 0)
2893 {
2894 /* We found some non-null values, but they were all too wide */
2895 Assert(nonnull_cnt == toowide_cnt);
2896 stats->stats_valid = true;
2897 /* Do the simple null-frac and width stats */
2898 stats->stanullfrac = (double) null_cnt / (double) samplerows;
2899 if (is_varwidth)
2900 stats->stawidth = total_width / (double) nonnull_cnt;
2901 else
2902 stats->stawidth = stats->attrtype->typlen;
2903 /* Assume all too-wide values are distinct, so it's a unique column */
2904 stats->stadistinct = -1.0 * (1.0 - stats->stanullfrac);
2905 }
2906 else if (null_cnt > 0)
2907 {
2908 /* We found only nulls; assume the column is entirely null */
2909 stats->stats_valid = true;
2910 stats->stanullfrac = 1.0;
2911 if (is_varwidth)
2912 stats->stawidth = 0; /* "unknown" */
2913 else
2914 stats->stawidth = stats->attrtype->typlen;
2915 stats->stadistinct = 0.0; /* "unknown" */
2916 }
2917
2918 /* We don't need to bother cleaning up any of our temporary palloc's */
2919}
2920
2921/*
2922 * Comparator for sorting ScalarItems
2923 *
2924 * Aside from sorting the items, we update the tupnoLink[] array
2925 * whenever two ScalarItems are found to contain equal datums. The array
2926 * is indexed by tupno; for each ScalarItem, it contains the highest
2927 * tupno that that item's datum has been found to be equal to. This allows
2928 * us to avoid additional comparisons in compute_scalar_stats().
2929 */
2930static int
2931compare_scalars(const void *a, const void *b, void *arg)
2932{
2933 Datum da = ((const ScalarItem *) a)->value;
2934 int ta = ((const ScalarItem *) a)->tupno;
2935 Datum db = ((const ScalarItem *) b)->value;
2936 int tb = ((const ScalarItem *) b)->tupno;
2938 int compare;
2939
2940 compare = ApplySortComparator(da, false, db, false, cxt->ssup);
2941 if (compare != 0)
2942 return compare;
2943
2944 /*
2945 * The two datums are equal, so update cxt->tupnoLink[].
2946 */
2947 if (cxt->tupnoLink[ta] < tb)
2948 cxt->tupnoLink[ta] = tb;
2949 if (cxt->tupnoLink[tb] < ta)
2950 cxt->tupnoLink[tb] = ta;
2951
2952 /*
2953 * For equal datums, sort by tupno
2954 */
2955 return ta - tb;
2956}
2957
2958/*
2959 * Comparator for sorting ScalarMCVItems by position
2960 */
2961static int
2962compare_mcvs(const void *a, const void *b, void *arg)
2963{
2964 int da = ((const ScalarMCVItem *) a)->first;
2965 int db = ((const ScalarMCVItem *) b)->first;
2966
2967 return da - db;
2968}
2969
2970/*
2971 * Analyze the list of common values in the sample and decide how many are
2972 * worth storing in the table's MCV list.
2973 *
2974 * mcv_counts is assumed to be a list of the counts of the most common values
2975 * seen in the sample, starting with the most common. The return value is the
2976 * number that are significantly more common than the values not in the list,
2977 * and which are therefore deemed worth storing in the table's MCV list.
2978 */
2979static int
2980analyze_mcv_list(int *mcv_counts,
2981 int num_mcv,
2982 double stadistinct,
2983 double stanullfrac,
2984 int samplerows,
2985 double totalrows)
2986{
2987 double ndistinct_table;
2988 double sumcount;
2989 int i;
2990
2991 /*
2992 * If the entire table was sampled, keep the whole list. This also
2993 * protects us against division by zero in the code below.
2994 */
2995 if (samplerows == totalrows || totalrows <= 1.0)
2996 return num_mcv;
2997
2998 /* Re-extract the estimated number of distinct nonnull values in table */
2999 ndistinct_table = stadistinct;
3000 if (ndistinct_table < 0)
3001 ndistinct_table = -ndistinct_table * totalrows;
3002
3003 /*
3004 * Exclude the least common values from the MCV list, if they are not
3005 * significantly more common than the estimated selectivity they would
3006 * have if they weren't in the list. All non-MCV values are assumed to be
3007 * equally common, after taking into account the frequencies of all the
3008 * values in the MCV list and the number of nulls (c.f. eqsel()).
3009 *
3010 * Here sumcount tracks the total count of all but the last (least common)
3011 * value in the MCV list, allowing us to determine the effect of excluding
3012 * that value from the list.
3013 *
3014 * Note that we deliberately do this by removing values from the full
3015 * list, rather than starting with an empty list and adding values,
3016 * because the latter approach can fail to add any values if all the most
3017 * common values have around the same frequency and make up the majority
3018 * of the table, so that the overall average frequency of all values is
3019 * roughly the same as that of the common values. This would lead to any
3020 * uncommon values being significantly overestimated.
3021 */
3022 sumcount = 0.0;
3023 for (i = 0; i < num_mcv - 1; i++)
3024 sumcount += mcv_counts[i];
3025
3026 while (num_mcv > 0)
3027 {
3028 double selec,
3029 otherdistinct,
3030 N,
3031 n,
3032 K,
3033 variance,
3034 stddev;
3035
3036 /*
3037 * Estimated selectivity the least common value would have if it
3038 * wasn't in the MCV list (c.f. eqsel()).
3039 */
3040 selec = 1.0 - sumcount / samplerows - stanullfrac;
3041 if (selec < 0.0)
3042 selec = 0.0;
3043 if (selec > 1.0)
3044 selec = 1.0;
3045 otherdistinct = ndistinct_table - (num_mcv - 1);
3046 if (otherdistinct > 1)
3047 selec /= otherdistinct;
3048
3049 /*
3050 * If the value is kept in the MCV list, its population frequency is
3051 * assumed to equal its sample frequency. We use the lower end of a
3052 * textbook continuity-corrected Wald-type confidence interval to
3053 * determine if that is significantly more common than the non-MCV
3054 * frequency --- specifically we assume the population frequency is
3055 * highly likely to be within around 2 standard errors of the sample
3056 * frequency, which equates to an interval of 2 standard deviations
3057 * either side of the sample count, plus an additional 0.5 for the
3058 * continuity correction. Since we are sampling without replacement,
3059 * this is a hypergeometric distribution.
3060 *
3061 * XXX: Empirically, this approach seems to work quite well, but it
3062 * may be worth considering more advanced techniques for estimating
3063 * the confidence interval of the hypergeometric distribution.
3064 */
3065 N = totalrows;
3066 n = samplerows;
3067 K = N * mcv_counts[num_mcv - 1] / n;
3068 variance = n * K * (N - K) * (N - n) / (N * N * (N - 1));
3069 stddev = sqrt(variance);
3070
3071 if (mcv_counts[num_mcv - 1] > selec * samplerows + 2 * stddev + 0.5)
3072 {
3073 /*
3074 * The value is significantly more common than the non-MCV
3075 * selectivity would suggest. Keep it, and all the other more
3076 * common values in the list.
3077 */
3078 break;
3079 }
3080 else
3081 {
3082 /* Discard this value and consider the next least common value */
3083 num_mcv--;
3084 if (num_mcv == 0)
3085 break;
3086 sumcount -= mcv_counts[num_mcv - 1];
3087 }
3088 }
3089 return num_mcv;
3090}
ArrayType * construct_array(Datum *elems, int nelems, Oid elmtype, int elmlen, bool elmbyval, char elmalign)
Definition: arrayfuncs.c:3361
ArrayType * construct_array_builtin(Datum *elems, int nelems, Oid elmtype)
Definition: arrayfuncs.c:3381
#define InvalidAttrNumber
Definition: attnum.h:23
AttributeOpts * get_attribute_options(Oid attrelid, int attnum)
Definition: attoptcache.c:131
long TimestampDifferenceMilliseconds(TimestampTz start_time, TimestampTz stop_time)
Definition: timestamp.c:1757
bool TimestampDifferenceExceeds(TimestampTz start_time, TimestampTz stop_time, int msec)
Definition: timestamp.c:1781
TimestampTz GetCurrentTimestamp(void)
Definition: timestamp.c:1645
void pgstat_progress_start_command(ProgressCommandType cmdtype, Oid relid)
void pgstat_progress_update_param(int index, int64 val)
void pgstat_progress_update_multi_param(int nparam, const int *index, const int64 *val)
void pgstat_progress_end_command(void)
@ PROGRESS_COMMAND_ANALYZE
PgBackendStatus * MyBEEntry
bool bms_is_member(int x, const Bitmapset *a)
Definition: bitmapset.c:510
Bitmapset * bms_add_member(Bitmapset *a, int x)
Definition: bitmapset.c:815
uint32 BlockNumber
Definition: block.h:31
#define InvalidBlockNumber
Definition: block.h:33
static Datum values[MAXATTR]
Definition: bootstrap.c:151
bool track_io_timing
Definition: bufmgr.c:144
#define RelationGetNumberOfBlocks(reln)
Definition: bufmgr.h:280
#define Min(x, y)
Definition: c.h:975
int64_t int64
Definition: c.h:499
double float8
Definition: c.h:601
uint32_t uint32
Definition: c.h:502
float float4
Definition: c.h:600
uint32 TransactionId
Definition: c.h:623
#define OidIsValid(objectId)
Definition: c.h:746
static Datum std_fetch_func(VacAttrStatsP stats, int rownum, bool *isNull)
Definition: analyze.c:1798
#define swapInt(a, b)
Definition: analyze.c:1846
static void compute_scalar_stats(VacAttrStatsP stats, AnalyzeAttrFetchFunc fetchfunc, int samplerows, double totalrows)
Definition: analyze.c:2402
#define swapDatum(a, b)
Definition: analyze.c:1847
#define WIDTH_THRESHOLD
Definition: analyze.c:1844
static void update_attstats(Oid relid, bool inh, int natts, VacAttrStats **vacattrstats)
Definition: analyze.c:1655
int default_statistics_target
Definition: analyze.c:71
static void compute_distinct_stats(VacAttrStatsP stats, AnalyzeAttrFetchFunc fetchfunc, int samplerows, double totalrows)
Definition: analyze.c:2059
static MemoryContext anl_context
Definition: analyze.c:74
bool std_typanalyze(VacAttrStats *stats)
Definition: analyze.c:1891
static int analyze_mcv_list(int *mcv_counts, int num_mcv, double stadistinct, double stanullfrac, int samplerows, double totalrows)
Definition: analyze.c:2980
static int acquire_inherited_sample_rows(Relation onerel, int elevel, HeapTuple *rows, int targrows, double *totalrows, double *totaldeadrows)
Definition: analyze.c:1391
static BufferAccessStrategy vac_strategy
Definition: analyze.c:75
static BlockNumber block_sampling_read_stream_next(ReadStream *stream, void *callback_private_data, void *per_buffer_data)
Definition: analyze.c:1156
static int compare_mcvs(const void *a, const void *b, void *arg)
Definition: analyze.c:2962
struct AnlIndexData AnlIndexData
static int acquire_sample_rows(Relation onerel, int elevel, HeapTuple *rows, int targrows, double *totalrows, double *totaldeadrows)
Definition: analyze.c:1199
static void compute_trivial_stats(VacAttrStatsP stats, AnalyzeAttrFetchFunc fetchfunc, int samplerows, double totalrows)
Definition: analyze.c:1969
static int compare_scalars(const void *a, const void *b, void *arg)
Definition: analyze.c:2931
static Datum ind_fetch_func(VacAttrStatsP stats, int rownum, bool *isNull)
Definition: analyze.c:1814
void analyze_rel(Oid relid, RangeVar *relation, VacuumParams *params, List *va_cols, bool in_outer_xact, BufferAccessStrategy bstrategy)
Definition: analyze.c:109
static void do_analyze_rel(Relation onerel, VacuumParams *params, List *va_cols, AcquireSampleRowsFunc acquirefunc, BlockNumber relpages, bool inh, bool in_outer_xact, int elevel)
Definition: analyze.c:278
static VacAttrStats * examine_attribute(Relation onerel, int attnum, Node *index_expr)
Definition: analyze.c:1036
static int compare_rows(const void *a, const void *b, void *arg)
Definition: analyze.c:1361
static void compute_index_stats(Relation onerel, double totalrows, AnlIndexData *indexdata, int nindexes, HeapTuple *rows, int numrows, MemoryContext col_context)
Definition: analyze.c:865
int64 TimestampTz
Definition: timestamp.h:39
Datum datumCopy(Datum value, bool typByVal, int typLen)
Definition: datum.c:132
char * get_database_name(Oid dbid)
Definition: dbcommands.c:3188
Size toast_raw_datum_size(Datum value)
Definition: detoast.c:545
int errmsg_internal(const char *fmt,...)
Definition: elog.c:1158
int errcode(int sqlerrcode)
Definition: elog.c:854
int errmsg(const char *fmt,...)
Definition: elog.c:1071
#define _(x)
Definition: elog.c:91
#define LOG
Definition: elog.h:31
#define WARNING
Definition: elog.h:36
#define DEBUG2
Definition: elog.h:29
#define ERROR
Definition: elog.h:39
#define elog(elevel,...)
Definition: elog.h:226
#define INFO
Definition: elog.h:34
#define ereport(elevel,...)
Definition: elog.h:149
ExprState * ExecPrepareQual(List *qual, EState *estate)
Definition: execExpr.c:793
TupleTableSlot * MakeSingleTupleTableSlot(TupleDesc tupdesc, const TupleTableSlotOps *tts_ops)
Definition: execTuples.c:1427
void ExecDropSingleTupleTableSlot(TupleTableSlot *slot)
Definition: execTuples.c:1443
const TupleTableSlotOps TTSOpsHeapTuple
Definition: execTuples.c:85
TupleTableSlot * ExecStoreHeapTuple(HeapTuple tuple, TupleTableSlot *slot, bool shouldFree)
Definition: execTuples.c:1541
void FreeExecutorState(EState *estate)
Definition: execUtils.c:193
EState * CreateExecutorState(void)
Definition: execUtils.c:88
#define GetPerTupleExprContext(estate)
Definition: executor.h:678
#define ResetExprContext(econtext)
Definition: executor.h:672
static bool ExecQual(ExprState *state, ExprContext *econtext)
Definition: executor.h:541
int ComputeExtStatisticsRows(Relation onerel, int natts, VacAttrStats **vacattrstats)
void BuildRelationExtStatistics(Relation onerel, bool inh, double totalrows, int numrows, HeapTuple *rows, int natts, VacAttrStats **vacattrstats)
int(* AcquireSampleRowsFunc)(Relation relation, int elevel, HeapTuple *rows, int targrows, double *totalrows, double *totaldeadrows)
Definition: fdwapi.h:151
Datum FunctionCall2Coll(FmgrInfo *flinfo, Oid collation, Datum arg1, Datum arg2)
Definition: fmgr.c:1149
void fmgr_info(Oid functionId, FmgrInfo *finfo)
Definition: fmgr.c:127
#define OidFunctionCall1(functionId, arg1)
Definition: fmgr.h:720
#define PG_DETOAST_DATUM(datum)
Definition: fmgr.h:240
FdwRoutine * GetFdwRoutineForRelation(Relation relation, bool makecopy)
Definition: foreign.c:442
static int compare(const void *arg1, const void *arg2)
Definition: geqo_pool.c:145
Oid MyDatabaseId
Definition: globals.c:95
int NewGUCNestLevel(void)
Definition: guc.c:2235
void RestrictSearchPath(void)
Definition: guc.c:2246
void AtEOXact_GUC(bool isCommit, int nestLevel)
Definition: guc.c:2262
Assert(PointerIsAligned(start, uint64))
HeapTuple heap_modify_tuple(HeapTuple tuple, TupleDesc tupleDesc, const Datum *replValues, const bool *replIsnull, const bool *doReplace)
Definition: heaptuple.c:1210
HeapTuple heap_form_tuple(TupleDesc tupleDescriptor, const Datum *values, const bool *isnull)
Definition: heaptuple.c:1117
void heap_freetuple(HeapTuple htup)
Definition: heaptuple.c:1435
#define HeapTupleIsValid(tuple)
Definition: htup.h:78
static Datum heap_getattr(HeapTuple tup, int attnum, TupleDesc tupleDesc, bool *isnull)
Definition: htup_details.h:904
static void * GETSTRUCT(const HeapTupleData *tuple)
Definition: htup_details.h:728
int verbose
IndexInfo * BuildIndexInfo(Relation index)
Definition: index.c:2428
void FormIndexDatum(IndexInfo *indexInfo, TupleTableSlot *slot, EState *estate, Datum *values, bool *isnull)
Definition: index.c:2730
IndexBulkDeleteResult * index_vacuum_cleanup(IndexVacuumInfo *info, IndexBulkDeleteResult *istat)
Definition: indexam.c:816
void CatalogTupleInsertWithInfo(Relation heapRel, HeapTuple tup, CatalogIndexState indstate)
Definition: indexing.c:256
void CatalogCloseIndexes(CatalogIndexState indstate)
Definition: indexing.c:61
CatalogIndexState CatalogOpenIndexes(Relation heapRel)
Definition: indexing.c:43
void CatalogTupleUpdateWithInfo(Relation heapRel, ItemPointer otid, HeapTuple tup, CatalogIndexState indstate)
Definition: indexing.c:337
static struct @165 value
WalUsage pgWalUsage
Definition: instrument.c:22
void WalUsageAccumDiff(WalUsage *dst, const WalUsage *add, const WalUsage *sub)
Definition: instrument.c:287
BufferUsage pgBufferUsage
Definition: instrument.c:20
void BufferUsageAccumDiff(BufferUsage *dst, const BufferUsage *add, const BufferUsage *sub)
Definition: instrument.c:248
int b
Definition: isn.c:74
int a
Definition: isn.c:73
int j
Definition: isn.c:78
int i
Definition: isn.c:77
if(TABLE==NULL||TABLE_index==NULL)
Definition: isn.c:81
static OffsetNumber ItemPointerGetOffsetNumber(const ItemPointerData *pointer)
Definition: itemptr.h:124
static BlockNumber ItemPointerGetBlockNumber(const ItemPointerData *pointer)
Definition: itemptr.h:103
void list_free(List *list)
Definition: list.c:1546
#define NoLock
Definition: lockdefs.h:34
#define AccessShareLock
Definition: lockdefs.h:36
#define ShareUpdateExclusiveLock
Definition: lockdefs.h:39
#define RowExclusiveLock
Definition: lockdefs.h:38
RegProcedure get_opcode(Oid opno)
Definition: lsyscache.c:1425
char * get_namespace_name(Oid nspid)
Definition: lsyscache.c:3506
void MemoryContextReset(MemoryContext context)
Definition: mcxt.c:414
void pfree(void *pointer)
Definition: mcxt.c:2147
void * palloc0(Size size)
Definition: mcxt.c:1970
void * palloc(Size size)
Definition: mcxt.c:1940
MemoryContext CurrentMemoryContext
Definition: mcxt.c:159
void MemoryContextDelete(MemoryContext context)
Definition: mcxt.c:485
#define AllocSetContextCreate
Definition: memutils.h:149
#define ALLOCSET_DEFAULT_SIZES
Definition: memutils.h:180
#define AmAutoVacuumWorkerProcess()
Definition: miscadmin.h:383
#define SECURITY_RESTRICTED_OPERATION
Definition: miscadmin.h:319
#define CHECK_FOR_INTERRUPTS()
Definition: miscadmin.h:123
void GetUserIdAndSecContext(Oid *userid, int *sec_context)
Definition: miscinit.c:663
void SetUserIdAndSecContext(Oid userid, int sec_context)
Definition: miscinit.c:670
#define InvalidMultiXactId
Definition: multixact.h:24
Oid exprType(const Node *expr)
Definition: nodeFuncs.c:42
int32 exprTypmod(const Node *expr)
Definition: nodeFuncs.c:301
Oid exprCollation(const Node *expr)
Definition: nodeFuncs.c:821
uint16 OffsetNumber
Definition: off.h:24
static MemoryContext MemoryContextSwitchTo(MemoryContext context)
Definition: palloc.h:124
void get_sort_group_operators(Oid argtype, bool needLT, bool needEQ, bool needGT, Oid *ltOpr, Oid *eqOpr, Oid *gtOpr, bool *isHashable)
Definition: parse_oper.c:180
int attnameAttNum(Relation rd, const char *attname, bool sysColOK)
int16 attnum
Definition: pg_attribute.h:74
FormData_pg_attribute * Form_pg_attribute
Definition: pg_attribute.h:202
void * arg
#define INDEX_MAX_KEYS
List * find_all_inheritors(Oid parentrelId, LOCKMODE lockmode, List **numparents)
Definition: pg_inherits.c:255
#define lfirst(lc)
Definition: pg_list.h:172
static int list_length(const List *l)
Definition: pg_list.h:152
#define NIL
Definition: pg_list.h:68
static ListCell * list_head(const List *l)
Definition: pg_list.h:128
static ListCell * lnext(const List *l, const ListCell *c)
Definition: pg_list.h:343
#define lfirst_oid(lc)
Definition: pg_list.h:174
uint32 pg_prng_uint32(pg_prng_state *state)
Definition: pg_prng.c:227
pg_prng_state pg_global_prng_state
Definition: pg_prng.c:34
const char * pg_rusage_show(const PGRUsage *ru0)
Definition: pg_rusage.c:40
void pg_rusage_init(PGRUsage *ru0)
Definition: pg_rusage.c:27
#define STATISTIC_NUM_SLOTS
Definition: pg_statistic.h:127
static char * buf
Definition: pg_test_fsync.c:72
FormData_pg_type * Form_pg_type
Definition: pg_type.h:261
int64 PgStat_Counter
Definition: pgstat.h:65
PgStat_Counter pgStatBlockReadTime
PgStat_Counter pgStatBlockWriteTime
void pgstat_report_analyze(Relation rel, PgStat_Counter livetuples, PgStat_Counter deadtuples, bool resetcounter, TimestampTz starttime)
void qsort_interruptible(void *base, size_t nel, size_t elsize, qsort_arg_comparator cmp, void *arg)
static bool DatumGetBool(Datum X)
Definition: postgres.h:95
static Datum PointerGetDatum(const void *X)
Definition: postgres.h:327
static Datum Float4GetDatum(float4 X)
Definition: postgres.h:480
uintptr_t Datum
Definition: postgres.h:69
static Datum Int16GetDatum(int16 X)
Definition: postgres.h:177
static Datum BoolGetDatum(bool X)
Definition: postgres.h:107
static Datum ObjectIdGetDatum(Oid X)
Definition: postgres.h:257
static char * DatumGetCString(Datum X)
Definition: postgres.h:340
static Pointer DatumGetPointer(Datum X)
Definition: postgres.h:317
static Datum Int32GetDatum(int32 X)
Definition: postgres.h:217
static int16 DatumGetInt16(Datum X)
Definition: postgres.h:167
#define InvalidOid
Definition: postgres_ext.h:35
unsigned int Oid
Definition: postgres_ext.h:30
TransactionId GetOldestNonRemovableTransactionId(Relation rel)
Definition: procarray.c:2005
#define PROGRESS_ANALYZE_PHASE_FINALIZE_ANALYZE
Definition: progress.h:57
#define PROGRESS_ANALYZE_PHASE_ACQUIRE_SAMPLE_ROWS_INH
Definition: progress.h:54
#define PROGRESS_ANALYZE_BLOCKS_DONE
Definition: progress.h:44
#define PROGRESS_ANALYZE_PHASE
Definition: progress.h:42
#define PROGRESS_ANALYZE_CHILD_TABLES_TOTAL
Definition: progress.h:47
#define PROGRESS_ANALYZE_BLOCKS_TOTAL
Definition: progress.h:43
#define PROGRESS_ANALYZE_PHASE_COMPUTE_STATS
Definition: progress.h:55
#define PROGRESS_ANALYZE_DELAY_TIME
Definition: progress.h:50
#define PROGRESS_ANALYZE_PHASE_ACQUIRE_SAMPLE_ROWS
Definition: progress.h:53
#define PROGRESS_ANALYZE_CHILD_TABLES_DONE
Definition: progress.h:48
#define PROGRESS_ANALYZE_CURRENT_CHILD_TABLE_RELID
Definition: progress.h:49
ReadStream * read_stream_begin_relation(int flags, BufferAccessStrategy strategy, Relation rel, ForkNumber forknum, ReadStreamBlockNumberCB callback, void *callback_private_data, size_t per_buffer_data_size)
Definition: read_stream.c:716
void read_stream_end(ReadStream *stream)
Definition: read_stream.c:1055
#define READ_STREAM_MAINTENANCE
Definition: read_stream.h:28
#define READ_STREAM_USE_BATCHING
Definition: read_stream.h:64
#define RelationGetRelid(relation)
Definition: rel.h:516
#define RelationGetDescr(relation)
Definition: rel.h:542
#define RelationGetRelationName(relation)
Definition: rel.h:550
#define RELATION_IS_OTHER_TEMP(relation)
Definition: rel.h:669
#define RelationGetNamespace(relation)
Definition: rel.h:557
List * RelationGetIndexList(Relation relation)
Definition: relcache.c:4819
struct RelationData * Relation
Definition: relcache.h:27
@ MAIN_FORKNUM
Definition: relpath.h:58
BlockNumber BlockSampler_Init(BlockSampler bs, BlockNumber nblocks, int samplesize, uint32 randseed)
Definition: sampling.c:39
void reservoir_init_selection_state(ReservoirState rs, int n)
Definition: sampling.c:133
double sampler_random_fract(pg_prng_state *randstate)
Definition: sampling.c:241
bool BlockSampler_HasMore(BlockSampler bs)
Definition: sampling.c:58
BlockNumber BlockSampler_Next(BlockSampler bs)
Definition: sampling.c:64
double reservoir_get_next_S(ReservoirState rs, double t, int n)
Definition: sampling.c:147
#define K(t)
Definition: sha1.c:66
void PrepareSortSupportFromOrderingOp(Oid orderingOp, SortSupport ssup)
Definition: sortsupport.c:134
static int ApplySortComparator(Datum datum1, bool isNull1, Datum datum2, bool isNull2, SortSupport ssup)
Definition: sortsupport.h:200
int f1[ARRAY_SIZE]
Definition: sql-declare.c:113
void relation_close(Relation relation, LOCKMODE lockmode)
Definition: relation.c:205
void appendStringInfo(StringInfo str, const char *fmt,...)
Definition: stringinfo.c:145
void initStringInfo(StringInfo str)
Definition: stringinfo.c:97
double tupleFract
Definition: analyze.c:64
int attr_cnt
Definition: analyze.c:66
IndexInfo * indexInfo
Definition: analyze.c:63
VacAttrStats ** vacattrstats
Definition: analyze.c:65
float8 n_distinct
Definition: attoptcache.h:22
float8 n_distinct_inherited
Definition: attoptcache.h:23
int64 shared_blks_dirtied
Definition: instrument.h:28
int64 local_blks_hit
Definition: instrument.h:30
int64 shared_blks_read
Definition: instrument.h:27
int64 local_blks_read
Definition: instrument.h:31
int64 local_blks_dirtied
Definition: instrument.h:32
int64 shared_blks_hit
Definition: instrument.h:26
SortSupport ssup
Definition: analyze.c:1860
TupleTableSlot * ecxt_scantuple
Definition: execnodes.h:268
AnalyzeForeignTable_function AnalyzeForeignTable
Definition: fdwapi.h:257
Definition: fmgr.h:57
ItemPointerData t_self
Definition: htup.h:65
int ii_NumIndexAttrs
Definition: execnodes.h:196
List * ii_Expressions
Definition: execnodes.h:199
AttrNumber ii_IndexAttrNumbers[INDEX_MAX_KEYS]
Definition: execnodes.h:198
List * ii_Predicate
Definition: execnodes.h:201
Relation index
Definition: genam.h:69
double num_heap_tuples
Definition: genam.h:75
bool analyze_only
Definition: genam.h:71
BufferAccessStrategy strategy
Definition: genam.h:76
Relation heaprel
Definition: genam.h:70
int message_level
Definition: genam.h:74
bool estimated_count
Definition: genam.h:73
Definition: pg_list.h:54
Definition: nodes.h:135
int64 st_progress_param[PGSTAT_NUM_PROGRESS_PARAM]
TupleDesc rd_att
Definition: rel.h:112
Oid rd_id
Definition: rel.h:113
Oid * rd_indcollation
Definition: rel.h:217
Form_pg_class rd_rel
Definition: rel.h:111
pg_prng_state randstate
Definition: sampling.h:49
bool ssup_nulls_first
Definition: sortsupport.h:75
MemoryContext ssup_cxt
Definition: sortsupport.h:66
Relation rs_rd
Definition: relscan.h:36
int32 attrtypmod
Definition: vacuum.h:127
bool stats_valid
Definition: vacuum.h:144
float4 stanullfrac
Definition: vacuum.h:145
Form_pg_type attrtype
Definition: vacuum.h:128
int16 stakind[STATISTIC_NUM_SLOTS]
Definition: vacuum.h:148
int tupattnum
Definition: vacuum.h:171
MemoryContext anl_context
Definition: vacuum.h:130
Oid statypid[STATISTIC_NUM_SLOTS]
Definition: vacuum.h:162
Oid staop[STATISTIC_NUM_SLOTS]
Definition: vacuum.h:149
Oid stacoll[STATISTIC_NUM_SLOTS]
Definition: vacuum.h:150
char statypalign[STATISTIC_NUM_SLOTS]
Definition: vacuum.h:165
float4 * stanumbers[STATISTIC_NUM_SLOTS]
Definition: vacuum.h:152
int rowstride
Definition: vacuum.h:176
Oid attrtypid
Definition: vacuum.h:126
HeapTuple * rows
Definition: vacuum.h:172
int minrows
Definition: vacuum.h:137
int attstattarget
Definition: vacuum.h:125
int32 stawidth
Definition: vacuum.h:146
void * extra_data
Definition: vacuum.h:138
bool statypbyval[STATISTIC_NUM_SLOTS]
Definition: vacuum.h:164
int16 statyplen[STATISTIC_NUM_SLOTS]
Definition: vacuum.h:163
bool * exprnulls
Definition: vacuum.h:175
TupleDesc tupDesc
Definition: vacuum.h:173
Datum * exprvals
Definition: vacuum.h:174
int numvalues[STATISTIC_NUM_SLOTS]
Definition: vacuum.h:153
Datum * stavalues[STATISTIC_NUM_SLOTS]
Definition: vacuum.h:154
float4 stadistinct
Definition: vacuum.h:147
int numnumbers[STATISTIC_NUM_SLOTS]
Definition: vacuum.h:151
AnalyzeAttrComputeStatsFunc compute_stats
Definition: vacuum.h:136
Oid attrcollid
Definition: vacuum.h:129
bits32 options
Definition: vacuum.h:219
int log_min_duration
Definition: vacuum.h:227
int64 wal_buffers_full
Definition: instrument.h:56
uint64 wal_bytes
Definition: instrument.h:55
int64 wal_fpi
Definition: instrument.h:54
int64 wal_records
Definition: instrument.h:53
void ReleaseSysCache(HeapTuple tuple)
Definition: syscache.c:269
HeapTuple SearchSysCache3(int cacheId, Datum key1, Datum key2, Datum key3)
Definition: syscache.c:243
Datum SysCacheGetAttr(int cacheId, HeapTuple tup, AttrNumber attributeNumber, bool *isNull)
Definition: syscache.c:600
HeapTuple SearchSysCache2(int cacheId, Datum key1, Datum key2)
Definition: syscache.c:232
#define SearchSysCacheCopy1(cacheId, key1)
Definition: syscache.h:91
void table_close(Relation relation, LOCKMODE lockmode)
Definition: table.c:126
Relation table_open(Oid relationId, LOCKMODE lockmode)
Definition: table.c:40
TupleTableSlot * table_slot_create(Relation relation, List **reglist)
Definition: tableam.c:92
static void table_endscan(TableScanDesc scan)
Definition: tableam.h:979
static bool table_scan_analyze_next_tuple(TableScanDesc scan, TransactionId OldestXmin, double *liverows, double *deadrows, TupleTableSlot *slot)
Definition: tableam.h:1698
static bool table_scan_analyze_next_block(TableScanDesc scan, ReadStream *stream)
Definition: tableam.h:1682
static TableScanDesc table_beginscan_analyze(Relation rel)
Definition: tableam.h:968
void SetRelationHasSubclass(Oid relationId, bool relhassubclass)
Definition: tablecmds.c:3636
#define InvalidTransactionId
Definition: transam.h:31
TupleConversionMap * convert_tuples_by_name(TupleDesc indesc, TupleDesc outdesc)
Definition: tupconvert.c:102
void free_conversion_map(TupleConversionMap *map)
Definition: tupconvert.c:299
HeapTuple execute_attr_map_tuple(HeapTuple tuple, TupleConversionMap *map)
Definition: tupconvert.c:154
bool equalRowTypes(TupleDesc tupdesc1, TupleDesc tupdesc2)
Definition: tupdesc.c:770
static FormData_pg_attribute * TupleDescAttr(TupleDesc tupdesc, int i)
Definition: tupdesc.h:160
static HeapTuple ExecCopySlotHeapTuple(TupleTableSlot *slot)
Definition: tuptable.h:485
bool track_cost_delay_timing
Definition: vacuum.c:80
void vac_open_indexes(Relation relation, LOCKMODE lockmode, int *nindexes, Relation **Irel)
Definition: vacuum.c:2338
Relation vacuum_open_relation(Oid relid, RangeVar *relation, bits32 options, bool verbose, LOCKMODE lmode)
Definition: vacuum.c:773
void vac_close_indexes(int nindexes, Relation *Irel, LOCKMODE lockmode)
Definition: vacuum.c:2381
void vacuum_delay_point(bool is_analyze)
Definition: vacuum.c:2402
bool vacuum_is_permitted_for_relation(Oid relid, Form_pg_class reltuple, bits32 options)
Definition: vacuum.c:721
void vac_update_relstats(Relation relation, BlockNumber num_pages, double num_tuples, BlockNumber num_all_visible_pages, BlockNumber num_all_frozen_pages, bool hasindex, TransactionId frozenxid, MultiXactId minmulti, bool *frozenxid_updated, bool *minmulti_updated, bool in_outer_xact)
Definition: vacuum.c:1428
#define VACOPT_VACUUM
Definition: vacuum.h:180
#define VACOPT_VERBOSE
Definition: vacuum.h:182
Datum(* AnalyzeAttrFetchFunc)(VacAttrStatsP stats, int rownum, bool *isNull)
Definition: vacuum.h:108
#define strVal(v)
Definition: value.h:82
#define VARSIZE_ANY(PTR)
Definition: varatt.h:311
void visibilitymap_count(Relation rel, BlockNumber *all_visible, BlockNumber *all_frozen)
void CommandCounterIncrement(void)
Definition: xact.c:1100