LCOV - code coverage report
Current view: top level - src/backend/utils/adt - array_typanalyze.c (source / functions) Hit Total Coverage
Test: PostgreSQL 15beta1 Lines: 200 217 92.2 %
Date: 2022-05-18 03:10:05 Functions: 8 9 88.9 %
Legend: Lines: hit not hit

          Line data    Source code
       1             : /*-------------------------------------------------------------------------
       2             :  *
       3             :  * array_typanalyze.c
       4             :  *    Functions for gathering statistics from array columns
       5             :  *
       6             :  * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
       7             :  * Portions Copyright (c) 1994, Regents of the University of California
       8             :  *
       9             :  *
      10             :  * IDENTIFICATION
      11             :  *    src/backend/utils/adt/array_typanalyze.c
      12             :  *
      13             :  *-------------------------------------------------------------------------
      14             :  */
      15             : #include "postgres.h"
      16             : 
      17             : #include "access/detoast.h"
      18             : #include "commands/vacuum.h"
      19             : #include "utils/array.h"
      20             : #include "utils/builtins.h"
      21             : #include "utils/datum.h"
      22             : #include "utils/lsyscache.h"
      23             : #include "utils/typcache.h"
      24             : 
      25             : 
      26             : /*
      27             :  * To avoid consuming too much memory, IO and CPU load during analysis, and/or
      28             :  * too much space in the resulting pg_statistic rows, we ignore arrays that
      29             :  * are wider than ARRAY_WIDTH_THRESHOLD (after detoasting!).  Note that this
      30             :  * number is considerably more than the similar WIDTH_THRESHOLD limit used
      31             :  * in analyze.c's standard typanalyze code.
      32             :  */
      33             : #define ARRAY_WIDTH_THRESHOLD 0x10000
      34             : 
      35             : /* Extra data for compute_array_stats function */
      36             : typedef struct
      37             : {
      38             :     /* Information about array element type */
      39             :     Oid         type_id;        /* element type's OID */
      40             :     Oid         eq_opr;         /* default equality operator's OID */
      41             :     Oid         coll_id;        /* collation to use */
      42             :     bool        typbyval;       /* physical properties of element type */
      43             :     int16       typlen;
      44             :     char        typalign;
      45             : 
      46             :     /*
      47             :      * Lookup data for element type's comparison and hash functions (these are
      48             :      * in the type's typcache entry, which we expect to remain valid over the
      49             :      * lifespan of the ANALYZE run)
      50             :      */
      51             :     FmgrInfo   *cmp;
      52             :     FmgrInfo   *hash;
      53             : 
      54             :     /* Saved state from std_typanalyze() */
      55             :     AnalyzeAttrComputeStatsFunc std_compute_stats;
      56             :     void       *std_extra_data;
      57             : } ArrayAnalyzeExtraData;
      58             : 
      59             : /*
      60             :  * While compute_array_stats is running, we keep a pointer to the extra data
      61             :  * here for use by assorted subroutines.  compute_array_stats doesn't
      62             :  * currently need to be re-entrant, so avoiding this is not worth the extra
      63             :  * notational cruft that would be needed.
      64             :  */
      65             : static ArrayAnalyzeExtraData *array_extra_data;
      66             : 
      67             : /* A hash table entry for the Lossy Counting algorithm */
      68             : typedef struct
      69             : {
      70             :     Datum       key;            /* This is 'e' from the LC algorithm. */
      71             :     int         frequency;      /* This is 'f'. */
      72             :     int         delta;          /* And this is 'delta'. */
      73             :     int         last_container; /* For de-duplication of array elements. */
      74             : } TrackItem;
      75             : 
      76             : /* A hash table entry for distinct-elements counts */
      77             : typedef struct
      78             : {
      79             :     int         count;          /* Count of distinct elements in an array */
      80             :     int         frequency;      /* Number of arrays seen with this count */
      81             : } DECountItem;
      82             : 
      83             : static void compute_array_stats(VacAttrStats *stats,
      84             :                                 AnalyzeAttrFetchFunc fetchfunc, int samplerows, double totalrows);
      85             : static void prune_element_hashtable(HTAB *elements_tab, int b_current);
      86             : static uint32 element_hash(const void *key, Size keysize);
      87             : static int  element_match(const void *key1, const void *key2, Size keysize);
      88             : static int  element_compare(const void *key1, const void *key2);
      89             : static int  trackitem_compare_frequencies_desc(const void *e1, const void *e2);
      90             : static int  trackitem_compare_element(const void *e1, const void *e2);
      91             : static int  countitem_compare_count(const void *e1, const void *e2);
      92             : 
      93             : 
      94             : /*
      95             :  * array_typanalyze -- typanalyze function for array columns
      96             :  */
      97             : Datum
      98       24234 : array_typanalyze(PG_FUNCTION_ARGS)
      99             : {
     100       24234 :     VacAttrStats *stats = (VacAttrStats *) PG_GETARG_POINTER(0);
     101             :     Oid         element_typeid;
     102             :     TypeCacheEntry *typentry;
     103             :     ArrayAnalyzeExtraData *extra_data;
     104             : 
     105             :     /*
     106             :      * Call the standard typanalyze function.  It may fail to find needed
     107             :      * operators, in which case we also can't do anything, so just fail.
     108             :      */
     109       24234 :     if (!std_typanalyze(stats))
     110           0 :         PG_RETURN_BOOL(false);
     111             : 
     112             :     /*
     113             :      * Check attribute data type is a varlena array (or a domain over one).
     114             :      */
     115       24234 :     element_typeid = get_base_element_type(stats->attrtypid);
     116       24234 :     if (!OidIsValid(element_typeid))
     117           0 :         elog(ERROR, "array_typanalyze was invoked for non-array type %u",
     118             :              stats->attrtypid);
     119             : 
     120             :     /*
     121             :      * Gather information about the element type.  If we fail to find
     122             :      * something, return leaving the state from std_typanalyze() in place.
     123             :      */
     124       24234 :     typentry = lookup_type_cache(element_typeid,
     125             :                                  TYPECACHE_EQ_OPR |
     126             :                                  TYPECACHE_CMP_PROC_FINFO |
     127             :                                  TYPECACHE_HASH_PROC_FINFO);
     128             : 
     129       24234 :     if (!OidIsValid(typentry->eq_opr) ||
     130       23658 :         !OidIsValid(typentry->cmp_proc_finfo.fn_oid) ||
     131       15610 :         !OidIsValid(typentry->hash_proc_finfo.fn_oid))
     132        8624 :         PG_RETURN_BOOL(true);
     133             : 
     134             :     /* Store our findings for use by compute_array_stats() */
     135       15610 :     extra_data = (ArrayAnalyzeExtraData *) palloc(sizeof(ArrayAnalyzeExtraData));
     136       15610 :     extra_data->type_id = typentry->type_id;
     137       15610 :     extra_data->eq_opr = typentry->eq_opr;
     138       15610 :     extra_data->coll_id = stats->attrcollid;  /* collation we should use */
     139       15610 :     extra_data->typbyval = typentry->typbyval;
     140       15610 :     extra_data->typlen = typentry->typlen;
     141       15610 :     extra_data->typalign = typentry->typalign;
     142       15610 :     extra_data->cmp = &typentry->cmp_proc_finfo;
     143       15610 :     extra_data->hash = &typentry->hash_proc_finfo;
     144             : 
     145             :     /* Save old compute_stats and extra_data for scalar statistics ... */
     146       15610 :     extra_data->std_compute_stats = stats->compute_stats;
     147       15610 :     extra_data->std_extra_data = stats->extra_data;
     148             : 
     149             :     /* ... and replace with our info */
     150       15610 :     stats->compute_stats = compute_array_stats;
     151       15610 :     stats->extra_data = extra_data;
     152             : 
     153             :     /*
     154             :      * Note we leave stats->minrows set as std_typanalyze set it.  Should it
     155             :      * be increased for array analysis purposes?
     156             :      */
     157             : 
     158       15610 :     PG_RETURN_BOOL(true);
     159             : }
     160             : 
     161             : /*
     162             :  * compute_array_stats() -- compute statistics for an array column
     163             :  *
     164             :  * This function computes statistics useful for determining selectivity of
     165             :  * the array operators <@, &&, and @>.  It is invoked by ANALYZE via the
     166             :  * compute_stats hook after sample rows have been collected.
     167             :  *
     168             :  * We also invoke the standard compute_stats function, which will compute
     169             :  * "scalar" statistics relevant to the btree-style array comparison operators.
     170             :  * However, exact duplicates of an entire array may be rare despite many
     171             :  * arrays sharing individual elements.  This especially afflicts long arrays,
     172             :  * which are also liable to lack all scalar statistics due to the low
     173             :  * WIDTH_THRESHOLD used in analyze.c.  So, in addition to the standard stats,
     174             :  * we find the most common array elements and compute a histogram of distinct
     175             :  * element counts.
     176             :  *
     177             :  * The algorithm used is Lossy Counting, as proposed in the paper "Approximate
     178             :  * frequency counts over data streams" by G. S. Manku and R. Motwani, in
     179             :  * Proceedings of the 28th International Conference on Very Large Data Bases,
     180             :  * Hong Kong, China, August 2002, section 4.2. The paper is available at
     181             :  * http://www.vldb.org/conf/2002/S10P03.pdf
     182             :  *
     183             :  * The Lossy Counting (aka LC) algorithm goes like this:
     184             :  * Let s be the threshold frequency for an item (the minimum frequency we
     185             :  * are interested in) and epsilon the error margin for the frequency. Let D
     186             :  * be a set of triples (e, f, delta), where e is an element value, f is that
     187             :  * element's frequency (actually, its current occurrence count) and delta is
     188             :  * the maximum error in f. We start with D empty and process the elements in
     189             :  * batches of size w. (The batch size is also known as "bucket size" and is
     190             :  * equal to 1/epsilon.) Let the current batch number be b_current, starting
     191             :  * with 1. For each element e we either increment its f count, if it's
     192             :  * already in D, or insert a new triple into D with values (e, 1, b_current
     193             :  * - 1). After processing each batch we prune D, by removing from it all
     194             :  * elements with f + delta <= b_current.  After the algorithm finishes we
     195             :  * suppress all elements from D that do not satisfy f >= (s - epsilon) * N,
     196             :  * where N is the total number of elements in the input.  We emit the
     197             :  * remaining elements with estimated frequency f/N.  The LC paper proves
     198             :  * that this algorithm finds all elements with true frequency at least s,
     199             :  * and that no frequency is overestimated or is underestimated by more than
     200             :  * epsilon.  Furthermore, given reasonable assumptions about the input
     201             :  * distribution, the required table size is no more than about 7 times w.
     202             :  *
     203             :  * In the absence of a principled basis for other particular values, we
     204             :  * follow ts_typanalyze() and use parameters s = 0.07/K, epsilon = s/10.
     205             :  * But we leave out the correction for stopwords, which do not apply to
     206             :  * arrays.  These parameters give bucket width w = K/0.007 and maximum
     207             :  * expected hashtable size of about 1000 * K.
     208             :  *
     209             :  * Elements may repeat within an array.  Since duplicates do not change the
     210             :  * behavior of <@, && or @>, we want to count each element only once per
     211             :  * array.  Therefore, we store in the finished pg_statistic entry each
     212             :  * element's frequency as the fraction of all non-null rows that contain it.
     213             :  * We divide the raw counts by nonnull_cnt to get those figures.
     214             :  */
     215             : static void
     216       10442 : compute_array_stats(VacAttrStats *stats, AnalyzeAttrFetchFunc fetchfunc,
     217             :                     int samplerows, double totalrows)
     218             : {
     219             :     ArrayAnalyzeExtraData *extra_data;
     220             :     int         num_mcelem;
     221       10442 :     int         null_cnt = 0;
     222       10442 :     int         null_elem_cnt = 0;
     223       10442 :     int         analyzed_rows = 0;
     224             : 
     225             :     /* This is D from the LC algorithm. */
     226             :     HTAB       *elements_tab;
     227             :     HASHCTL     elem_hash_ctl;
     228             :     HASH_SEQ_STATUS scan_status;
     229             : 
     230             :     /* This is the current bucket number from the LC algorithm */
     231             :     int         b_current;
     232             : 
     233             :     /* This is 'w' from the LC algorithm */
     234             :     int         bucket_width;
     235             :     int         array_no;
     236             :     int64       element_no;
     237             :     TrackItem  *item;
     238             :     int         slot_idx;
     239             :     HTAB       *count_tab;
     240             :     HASHCTL     count_hash_ctl;
     241             :     DECountItem *count_item;
     242             : 
     243       10442 :     extra_data = (ArrayAnalyzeExtraData *) stats->extra_data;
     244             : 
     245             :     /*
     246             :      * Invoke analyze.c's standard analysis function to create scalar-style
     247             :      * stats for the column.  It will expect its own extra_data pointer, so
     248             :      * temporarily install that.
     249             :      */
     250       10442 :     stats->extra_data = extra_data->std_extra_data;
     251       10442 :     extra_data->std_compute_stats(stats, fetchfunc, samplerows, totalrows);
     252       10442 :     stats->extra_data = extra_data;
     253             : 
     254             :     /*
     255             :      * Set up static pointer for use by subroutines.  We wait till here in
     256             :      * case std_compute_stats somehow recursively invokes us (probably not
     257             :      * possible, but ...)
     258             :      */
     259       10442 :     array_extra_data = extra_data;
     260             : 
     261             :     /*
     262             :      * We want statistics_target * 10 elements in the MCELEM array. This
     263             :      * multiplier is pretty arbitrary, but is meant to reflect the fact that
     264             :      * the number of individual elements tracked in pg_statistic ought to be
     265             :      * more than the number of values for a simple scalar column.
     266             :      */
     267       10442 :     num_mcelem = stats->attr->attstattarget * 10;
     268             : 
     269             :     /*
     270             :      * We set bucket width equal to num_mcelem / 0.007 as per the comment
     271             :      * above.
     272             :      */
     273       10442 :     bucket_width = num_mcelem * 1000 / 7;
     274             : 
     275             :     /*
     276             :      * Create the hashtable. It will be in local memory, so we don't need to
     277             :      * worry about overflowing the initial size. Also we don't need to pay any
     278             :      * attention to locking and memory management.
     279             :      */
     280       10442 :     elem_hash_ctl.keysize = sizeof(Datum);
     281       10442 :     elem_hash_ctl.entrysize = sizeof(TrackItem);
     282       10442 :     elem_hash_ctl.hash = element_hash;
     283       10442 :     elem_hash_ctl.match = element_match;
     284       10442 :     elem_hash_ctl.hcxt = CurrentMemoryContext;
     285       10442 :     elements_tab = hash_create("Analyzed elements table",
     286             :                                num_mcelem,
     287             :                                &elem_hash_ctl,
     288             :                                HASH_ELEM | HASH_FUNCTION | HASH_COMPARE | HASH_CONTEXT);
     289             : 
     290             :     /* hashtable for array distinct elements counts */
     291       10442 :     count_hash_ctl.keysize = sizeof(int);
     292       10442 :     count_hash_ctl.entrysize = sizeof(DECountItem);
     293       10442 :     count_hash_ctl.hcxt = CurrentMemoryContext;
     294       10442 :     count_tab = hash_create("Array distinct element count table",
     295             :                             64,
     296             :                             &count_hash_ctl,
     297             :                             HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
     298             : 
     299             :     /* Initialize counters. */
     300       10442 :     b_current = 1;
     301       10442 :     element_no = 0;
     302             : 
     303             :     /* Loop over the arrays. */
     304    13853392 :     for (array_no = 0; array_no < samplerows; array_no++)
     305             :     {
     306             :         Datum       value;
     307             :         bool        isnull;
     308             :         ArrayType  *array;
     309             :         int         num_elems;
     310             :         Datum      *elem_values;
     311             :         bool       *elem_nulls;
     312             :         bool        null_present;
     313             :         int         j;
     314    13842950 :         int64       prev_element_no = element_no;
     315             :         int         distinct_count;
     316             :         bool        count_item_found;
     317             : 
     318    13842950 :         vacuum_delay_point();
     319             : 
     320    13842950 :         value = fetchfunc(stats, array_no, &isnull);
     321    13842950 :         if (isnull)
     322             :         {
     323             :             /* array is null, just count that */
     324    13202224 :             null_cnt++;
     325    13202224 :             continue;
     326             :         }
     327             : 
     328             :         /* Skip too-large values. */
     329      640726 :         if (toast_raw_datum_size(value) > ARRAY_WIDTH_THRESHOLD)
     330           0 :             continue;
     331             :         else
     332      640726 :             analyzed_rows++;
     333             : 
     334             :         /*
     335             :          * Now detoast the array if needed, and deconstruct into datums.
     336             :          */
     337      640726 :         array = DatumGetArrayTypeP(value);
     338             : 
     339             :         Assert(ARR_ELEMTYPE(array) == extra_data->type_id);
     340      640726 :         deconstruct_array(array,
     341             :                           extra_data->type_id,
     342      640726 :                           extra_data->typlen,
     343      640726 :                           extra_data->typbyval,
     344      640726 :                           extra_data->typalign,
     345             :                           &elem_values, &elem_nulls, &num_elems);
     346             : 
     347             :         /*
     348             :          * We loop through the elements in the array and add them to our
     349             :          * tracking hashtable.
     350             :          */
     351      640726 :         null_present = false;
     352     2967006 :         for (j = 0; j < num_elems; j++)
     353             :         {
     354             :             Datum       elem_value;
     355             :             bool        found;
     356             : 
     357             :             /* No null element processing other than flag setting here */
     358     2326280 :             if (elem_nulls[j])
     359             :             {
     360          32 :                 null_present = true;
     361      409754 :                 continue;
     362             :             }
     363             : 
     364             :             /* Lookup current element in hashtable, adding it if new */
     365     2326248 :             elem_value = elem_values[j];
     366     2326248 :             item = (TrackItem *) hash_search(elements_tab,
     367             :                                              (const void *) &elem_value,
     368             :                                              HASH_ENTER, &found);
     369             : 
     370     2326248 :             if (found)
     371             :             {
     372             :                 /* The element value is already on the tracking list */
     373             : 
     374             :                 /*
     375             :                  * The operators we assist ignore duplicate array elements, so
     376             :                  * count a given distinct element only once per array.
     377             :                  */
     378     1816702 :                 if (item->last_container == array_no)
     379      409722 :                     continue;
     380             : 
     381     1406980 :                 item->frequency++;
     382     1406980 :                 item->last_container = array_no;
     383             :             }
     384             :             else
     385             :             {
     386             :                 /* Initialize new tracking list element */
     387             : 
     388             :                 /*
     389             :                  * If element type is pass-by-reference, we must copy it into
     390             :                  * palloc'd space, so that we can release the array below. (We
     391             :                  * do this so that the space needed for element values is
     392             :                  * limited by the size of the hashtable; if we kept all the
     393             :                  * array values around, it could be much more.)
     394             :                  */
     395     1019092 :                 item->key = datumCopy(elem_value,
     396      509546 :                                       extra_data->typbyval,
     397      509546 :                                       extra_data->typlen);
     398             : 
     399      509546 :                 item->frequency = 1;
     400      509546 :                 item->delta = b_current - 1;
     401      509546 :                 item->last_container = array_no;
     402             :             }
     403             : 
     404             :             /* element_no is the number of elements processed (ie N) */
     405     1916526 :             element_no++;
     406             : 
     407             :             /* We prune the D structure after processing each bucket */
     408     1916526 :             if (element_no % bucket_width == 0)
     409             :             {
     410           0 :                 prune_element_hashtable(elements_tab, b_current);
     411           0 :                 b_current++;
     412             :             }
     413             :         }
     414             : 
     415             :         /* Count null element presence once per array. */
     416      640726 :         if (null_present)
     417          32 :             null_elem_cnt++;
     418             : 
     419             :         /* Update frequency of the particular array distinct element count. */
     420      640726 :         distinct_count = (int) (element_no - prev_element_no);
     421      640726 :         count_item = (DECountItem *) hash_search(count_tab, &distinct_count,
     422             :                                                  HASH_ENTER,
     423             :                                                  &count_item_found);
     424             : 
     425      640726 :         if (count_item_found)
     426      619624 :             count_item->frequency++;
     427             :         else
     428       21102 :             count_item->frequency = 1;
     429             : 
     430             :         /* Free memory allocated while detoasting. */
     431      640726 :         if (PointerGetDatum(array) != value)
     432      596006 :             pfree(array);
     433      640726 :         pfree(elem_values);
     434      640726 :         pfree(elem_nulls);
     435             :     }
     436             : 
     437             :     /* Skip pg_statistic slots occupied by standard statistics */
     438       10442 :     slot_idx = 0;
     439       18688 :     while (slot_idx < STATISTIC_NUM_SLOTS && stats->stakind[slot_idx] != 0)
     440        8246 :         slot_idx++;
     441       10442 :     if (slot_idx > STATISTIC_NUM_SLOTS - 2)
     442           0 :         elog(ERROR, "insufficient pg_statistic slots for array stats");
     443             : 
     444             :     /* We can only compute real stats if we found some non-null values. */
     445       10442 :     if (analyzed_rows > 0)
     446             :     {
     447        2972 :         int         nonnull_cnt = analyzed_rows;
     448             :         int         count_items_count;
     449             :         int         i;
     450             :         TrackItem **sort_table;
     451             :         int         track_len;
     452             :         int64       cutoff_freq;
     453             :         int64       minfreq,
     454             :                     maxfreq;
     455             : 
     456             :         /*
     457             :          * We assume the standard stats code already took care of setting
     458             :          * stats_valid, stanullfrac, stawidth, stadistinct.  We'd have to
     459             :          * re-compute those values if we wanted to not store the standard
     460             :          * stats.
     461             :          */
     462             : 
     463             :         /*
     464             :          * Construct an array of the interesting hashtable items, that is,
     465             :          * those meeting the cutoff frequency (s - epsilon)*N.  Also identify
     466             :          * the minimum and maximum frequencies among these items.
     467             :          *
     468             :          * Since epsilon = s/10 and bucket_width = 1/epsilon, the cutoff
     469             :          * frequency is 9*N / bucket_width.
     470             :          */
     471        2972 :         cutoff_freq = 9 * element_no / bucket_width;
     472             : 
     473        2972 :         i = hash_get_num_entries(elements_tab); /* surely enough space */
     474        2972 :         sort_table = (TrackItem **) palloc(sizeof(TrackItem *) * i);
     475             : 
     476        2972 :         hash_seq_init(&scan_status, elements_tab);
     477        2972 :         track_len = 0;
     478        2972 :         minfreq = element_no;
     479        2972 :         maxfreq = 0;
     480      512518 :         while ((item = (TrackItem *) hash_seq_search(&scan_status)) != NULL)
     481             :         {
     482      509546 :             if (item->frequency > cutoff_freq)
     483             :             {
     484      293528 :                 sort_table[track_len++] = item;
     485      293528 :                 minfreq = Min(minfreq, item->frequency);
     486      293528 :                 maxfreq = Max(maxfreq, item->frequency);
     487             :             }
     488             :         }
     489             :         Assert(track_len <= i);
     490             : 
     491             :         /* emit some statistics for debug purposes */
     492        2972 :         elog(DEBUG3, "compute_array_stats: target # mces = %d, "
     493             :              "bucket width = %d, "
     494             :              "# elements = " INT64_FORMAT ", hashtable size = %d, "
     495             :              "usable entries = %d",
     496             :              num_mcelem, bucket_width, element_no, i, track_len);
     497             : 
     498             :         /*
     499             :          * If we obtained more elements than we really want, get rid of those
     500             :          * with least frequencies.  The easiest way is to qsort the array into
     501             :          * descending frequency order and truncate the array.
     502             :          */
     503        2972 :         if (num_mcelem < track_len)
     504             :         {
     505          30 :             qsort(sort_table, track_len, sizeof(TrackItem *),
     506             :                   trackitem_compare_frequencies_desc);
     507             :             /* reset minfreq to the smallest frequency we're keeping */
     508          30 :             minfreq = sort_table[num_mcelem - 1]->frequency;
     509             :         }
     510             :         else
     511        2942 :             num_mcelem = track_len;
     512             : 
     513             :         /* Generate MCELEM slot entry */
     514        2972 :         if (num_mcelem > 0)
     515             :         {
     516             :             MemoryContext old_context;
     517             :             Datum      *mcelem_values;
     518             :             float4     *mcelem_freqs;
     519             : 
     520             :             /*
     521             :              * We want to store statistics sorted on the element value using
     522             :              * the element type's default comparison function.  This permits
     523             :              * fast binary searches in selectivity estimation functions.
     524             :              */
     525        2972 :             qsort(sort_table, num_mcelem, sizeof(TrackItem *),
     526             :                   trackitem_compare_element);
     527             : 
     528             :             /* Must copy the target values into anl_context */
     529        2972 :             old_context = MemoryContextSwitchTo(stats->anl_context);
     530             : 
     531             :             /*
     532             :              * We sorted statistics on the element value, but we want to be
     533             :              * able to find the minimal and maximal frequencies without going
     534             :              * through all the values.  We also want the frequency of null
     535             :              * elements.  Store these three values at the end of mcelem_freqs.
     536             :              */
     537        2972 :             mcelem_values = (Datum *) palloc(num_mcelem * sizeof(Datum));
     538        2972 :             mcelem_freqs = (float4 *) palloc((num_mcelem + 3) * sizeof(float4));
     539             : 
     540             :             /*
     541             :              * See comments above about use of nonnull_cnt as the divisor for
     542             :              * the final frequency estimates.
     543             :              */
     544      282452 :             for (i = 0; i < num_mcelem; i++)
     545             :             {
     546      279480 :                 TrackItem  *item = sort_table[i];
     547             : 
     548      558960 :                 mcelem_values[i] = datumCopy(item->key,
     549      279480 :                                              extra_data->typbyval,
     550      279480 :                                              extra_data->typlen);
     551      279480 :                 mcelem_freqs[i] = (double) item->frequency /
     552      279480 :                     (double) nonnull_cnt;
     553             :             }
     554        2972 :             mcelem_freqs[i++] = (double) minfreq / (double) nonnull_cnt;
     555        2972 :             mcelem_freqs[i++] = (double) maxfreq / (double) nonnull_cnt;
     556        2972 :             mcelem_freqs[i++] = (double) null_elem_cnt / (double) nonnull_cnt;
     557             : 
     558        2972 :             MemoryContextSwitchTo(old_context);
     559             : 
     560        2972 :             stats->stakind[slot_idx] = STATISTIC_KIND_MCELEM;
     561        2972 :             stats->staop[slot_idx] = extra_data->eq_opr;
     562        2972 :             stats->stacoll[slot_idx] = extra_data->coll_id;
     563        2972 :             stats->stanumbers[slot_idx] = mcelem_freqs;
     564             :             /* See above comment about extra stanumber entries */
     565        2972 :             stats->numnumbers[slot_idx] = num_mcelem + 3;
     566        2972 :             stats->stavalues[slot_idx] = mcelem_values;
     567        2972 :             stats->numvalues[slot_idx] = num_mcelem;
     568             :             /* We are storing values of element type */
     569        2972 :             stats->statypid[slot_idx] = extra_data->type_id;
     570        2972 :             stats->statyplen[slot_idx] = extra_data->typlen;
     571        2972 :             stats->statypbyval[slot_idx] = extra_data->typbyval;
     572        2972 :             stats->statypalign[slot_idx] = extra_data->typalign;
     573        2972 :             slot_idx++;
     574             :         }
     575             : 
     576             :         /* Generate DECHIST slot entry */
     577        2972 :         count_items_count = hash_get_num_entries(count_tab);
     578        2972 :         if (count_items_count > 0)
     579             :         {
     580        2972 :             int         num_hist = stats->attr->attstattarget;
     581             :             DECountItem **sorted_count_items;
     582             :             int         j;
     583             :             int         delta;
     584             :             int64       frac;
     585             :             float4     *hist;
     586             : 
     587             :             /* num_hist must be at least 2 for the loop below to work */
     588        2972 :             num_hist = Max(num_hist, 2);
     589             : 
     590             :             /*
     591             :              * Create an array of DECountItem pointers, and sort them into
     592             :              * increasing count order.
     593             :              */
     594             :             sorted_count_items = (DECountItem **)
     595        2972 :                 palloc(sizeof(DECountItem *) * count_items_count);
     596        2972 :             hash_seq_init(&scan_status, count_tab);
     597        2972 :             j = 0;
     598       24074 :             while ((count_item = (DECountItem *) hash_seq_search(&scan_status)) != NULL)
     599             :             {
     600       21102 :                 sorted_count_items[j++] = count_item;
     601             :             }
     602        2972 :             qsort(sorted_count_items, count_items_count,
     603             :                   sizeof(DECountItem *), countitem_compare_count);
     604             : 
     605             :             /*
     606             :              * Prepare to fill stanumbers with the histogram, followed by the
     607             :              * average count.  This array must be stored in anl_context.
     608             :              */
     609             :             hist = (float4 *)
     610        2972 :                 MemoryContextAlloc(stats->anl_context,
     611        2972 :                                    sizeof(float4) * (num_hist + 1));
     612        2972 :             hist[num_hist] = (double) element_no / (double) nonnull_cnt;
     613             : 
     614             :             /*----------
     615             :              * Construct the histogram of distinct-element counts (DECs).
     616             :              *
     617             :              * The object of this loop is to copy the min and max DECs to
     618             :              * hist[0] and hist[num_hist - 1], along with evenly-spaced DECs
     619             :              * in between (where "evenly-spaced" is with reference to the
     620             :              * whole input population of arrays).  If we had a complete sorted
     621             :              * array of DECs, one per analyzed row, the i'th hist value would
     622             :              * come from DECs[i * (analyzed_rows - 1) / (num_hist - 1)]
     623             :              * (compare the histogram-making loop in compute_scalar_stats()).
     624             :              * But instead of that we have the sorted_count_items[] array,
     625             :              * which holds unique DEC values with their frequencies (that is,
     626             :              * a run-length-compressed version of the full array).  So we
     627             :              * control advancing through sorted_count_items[] with the
     628             :              * variable "frac", which is defined as (x - y) * (num_hist - 1),
     629             :              * where x is the index in the notional DECs array corresponding
     630             :              * to the start of the next sorted_count_items[] element's run,
     631             :              * and y is the index in DECs from which we should take the next
     632             :              * histogram value.  We have to advance whenever x <= y, that is
     633             :              * frac <= 0.  The x component is the sum of the frequencies seen
     634             :              * so far (up through the current sorted_count_items[] element),
     635             :              * and of course y * (num_hist - 1) = i * (analyzed_rows - 1),
     636             :              * per the subscript calculation above.  (The subscript calculation
     637             :              * implies dropping any fractional part of y; in this formulation
     638             :              * that's handled by not advancing until frac reaches 1.)
     639             :              *
     640             :              * Even though frac has a bounded range, it could overflow int32
     641             :              * when working with very large statistics targets, so we do that
     642             :              * math in int64.
     643             :              *----------
     644             :              */
     645        2972 :             delta = analyzed_rows - 1;
     646        2972 :             j = 0;              /* current index in sorted_count_items */
     647             :             /* Initialize frac for sorted_count_items[0]; y is initially 0 */
     648        2972 :             frac = (int64) sorted_count_items[0]->frequency * (num_hist - 1);
     649      294532 :             for (i = 0; i < num_hist; i++)
     650             :             {
     651      309690 :                 while (frac <= 0)
     652             :                 {
     653             :                     /* Advance, and update x component of frac */
     654       18130 :                     j++;
     655       18130 :                     frac += (int64) sorted_count_items[j]->frequency * (num_hist - 1);
     656             :                 }
     657      291560 :                 hist[i] = sorted_count_items[j]->count;
     658      291560 :                 frac -= delta;  /* update y for upcoming i increment */
     659             :             }
     660             :             Assert(j == count_items_count - 1);
     661             : 
     662        2972 :             stats->stakind[slot_idx] = STATISTIC_KIND_DECHIST;
     663        2972 :             stats->staop[slot_idx] = extra_data->eq_opr;
     664        2972 :             stats->stacoll[slot_idx] = extra_data->coll_id;
     665        2972 :             stats->stanumbers[slot_idx] = hist;
     666        2972 :             stats->numnumbers[slot_idx] = num_hist + 1;
     667        2972 :             slot_idx++;
     668             :         }
     669             :     }
     670             : 
     671             :     /*
     672             :      * We don't need to bother cleaning up any of our temporary palloc's. The
     673             :      * hashtable should also go away, as it used a child memory context.
     674             :      */
     675       10442 : }
     676             : 
     677             : /*
     678             :  * A function to prune the D structure from the Lossy Counting algorithm.
     679             :  * Consult compute_tsvector_stats() for wider explanation.
     680             :  */
     681             : static void
     682           0 : prune_element_hashtable(HTAB *elements_tab, int b_current)
     683             : {
     684             :     HASH_SEQ_STATUS scan_status;
     685             :     TrackItem  *item;
     686             : 
     687           0 :     hash_seq_init(&scan_status, elements_tab);
     688           0 :     while ((item = (TrackItem *) hash_seq_search(&scan_status)) != NULL)
     689             :     {
     690           0 :         if (item->frequency + item->delta <= b_current)
     691             :         {
     692           0 :             Datum       value = item->key;
     693             : 
     694           0 :             if (hash_search(elements_tab, (const void *) &item->key,
     695             :                             HASH_REMOVE, NULL) == NULL)
     696           0 :                 elog(ERROR, "hash table corrupted");
     697             :             /* We should free memory if element is not passed by value */
     698           0 :             if (!array_extra_data->typbyval)
     699           0 :                 pfree(DatumGetPointer(value));
     700             :         }
     701             :     }
     702           0 : }
     703             : 
     704             : /*
     705             :  * Hash function for elements.
     706             :  *
     707             :  * We use the element type's default hash opclass, and the column collation
     708             :  * if the type is collation-sensitive.
     709             :  */
     710             : static uint32
     711     2326248 : element_hash(const void *key, Size keysize)
     712             : {
     713     2326248 :     Datum       d = *((const Datum *) key);
     714             :     Datum       h;
     715             : 
     716     2326248 :     h = FunctionCall1Coll(array_extra_data->hash,
     717     2326248 :                           array_extra_data->coll_id,
     718             :                           d);
     719     2326248 :     return DatumGetUInt32(h);
     720             : }
     721             : 
     722             : /*
     723             :  * Matching function for elements, to be used in hashtable lookups.
     724             :  */
     725             : static int
     726     1818496 : element_match(const void *key1, const void *key2, Size keysize)
     727             : {
     728             :     /* The keysize parameter is superfluous here */
     729     1818496 :     return element_compare(key1, key2);
     730             : }
     731             : 
     732             : /*
     733             :  * Comparison function for elements.
     734             :  *
     735             :  * We use the element type's default btree opclass, and the column collation
     736             :  * if the type is collation-sensitive.
     737             :  *
     738             :  * XXX consider using SortSupport infrastructure
     739             :  */
     740             : static int
     741     4180266 : element_compare(const void *key1, const void *key2)
     742             : {
     743     4180266 :     Datum       d1 = *((const Datum *) key1);
     744     4180266 :     Datum       d2 = *((const Datum *) key2);
     745             :     Datum       c;
     746             : 
     747     4180266 :     c = FunctionCall2Coll(array_extra_data->cmp,
     748     4180266 :                           array_extra_data->coll_id,
     749             :                           d1, d2);
     750     4180266 :     return DatumGetInt32(c);
     751             : }
     752             : 
     753             : /*
     754             :  * qsort() comparator for sorting TrackItems by frequencies (descending sort)
     755             :  */
     756             : static int
     757       34586 : trackitem_compare_frequencies_desc(const void *e1, const void *e2)
     758             : {
     759       34586 :     const TrackItem *const *t1 = (const TrackItem *const *) e1;
     760       34586 :     const TrackItem *const *t2 = (const TrackItem *const *) e2;
     761             : 
     762       34586 :     return (*t2)->frequency - (*t1)->frequency;
     763             : }
     764             : 
     765             : /*
     766             :  * qsort() comparator for sorting TrackItems by element values
     767             :  */
     768             : static int
     769     2361770 : trackitem_compare_element(const void *e1, const void *e2)
     770             : {
     771     2361770 :     const TrackItem *const *t1 = (const TrackItem *const *) e1;
     772     2361770 :     const TrackItem *const *t2 = (const TrackItem *const *) e2;
     773             : 
     774     2361770 :     return element_compare(&(*t1)->key, &(*t2)->key);
     775             : }
     776             : 
     777             : /*
     778             :  * qsort() comparator for sorting DECountItems by count
     779             :  */
     780             : static int
     781       58212 : countitem_compare_count(const void *e1, const void *e2)
     782             : {
     783       58212 :     const DECountItem *const *t1 = (const DECountItem *const *) e1;
     784       58212 :     const DECountItem *const *t2 = (const DECountItem *const *) e2;
     785             : 
     786       58212 :     if ((*t1)->count < (*t2)->count)
     787       27324 :         return -1;
     788       30888 :     else if ((*t1)->count == (*t2)->count)
     789           0 :         return 0;
     790             :     else
     791       30888 :         return 1;
     792             : }

Generated by: LCOV version 1.14