On 3/11/26 11:01, Zsolt Parragi wrote:
+ /*
+ * For ALL semantics, if the array contains NULL, assume
+ * operator is strict. The ScalarArrayOpExpr cannot
+ * evaluate to TRUE, so return zero.
+ */
+ nonconst_sel = var_eq_non_const(&vardata, operator,
+ clause->inputcollid,
+ other_op, var_on_left,
+ isInequality);
+ if (isInequality)
+ individual_s = 1.0 - individual_s - nullfrac;
Isn't this the double negation issue again, which was once
mentioned/fixed earlier?
Right. I fixed it by using 'invert' for non-constant case. If there is a
more elegant way to structure this, suggestions are very welcome.
+ int count; /* number of occurrences of current value in */
That's a truncated comment
Fixed.
After the commit c95cd29 I have rebased this patch. During the rebase, I
also add the NUL-handling path. In particular, I added an Assert(useOr)
in the relevant branch to document and enforce the expected execution flow.
Additionally after the 374a639 I prepared a set of regression-style
tests to verify that the selectivity estimates remain unchanged before
and after applying the patch. However, these tests rely on stable row
estimates from EXPLAIN, which are not guaranteed to be consistent across
platforms. For that reason, they are not suitable for inclusion in the
upstream test suite. I will keep these tests locally to validate
correctness before and after the patch.
--
Best regards,
Ilia Evdokimov,
Tantor Labs LLC,
https://tantorlabs.com/
From 5d93f945a022d38b3dd39c940ba620a3640bb236 Mon Sep 17 00:00:00 2001
From: Evdokimov Ilia <[email protected]>
Date: Fri, 20 Mar 2026 18:18:24 +0300
Subject: [PATCH v9] Use hash-based MCV matching for ScalarArrayOpExpr
selectivity
When estimating selectivity for ScalarArrayOpExpr (IN / ANY / ALL) with
available MCV statistics, the planner currently matches IN-list elements
against the MCV array using nested loops. For large IN-lists and/or large
MCV lists this leads to O(N*M) planning-time behavior.
This patch adds a hash-based matching strategy, similar to the one used
in join selectivity estimation. When MCV statistics are available and the
operator supports hashing, the smaller of the two inputs (MCV list or
IN-list constant elements) is chosen as the hash table build side, and
the other side is scanned once, reducing complexity to O(N+M).
The hash-based path is restricted to equality and inequality operators
that use eqsel()/neqsel(), and is applied only when suitable hash
functions and MCV statistics are available.
---
src/backend/utils/adt/selfuncs.c | 520 ++++++++++++++++++++++++++++++-
1 file changed, 515 insertions(+), 5 deletions(-)
diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
index 86b55c9bb8b..1d812162980 100644
--- a/src/backend/utils/adt/selfuncs.c
+++ b/src/backend/utils/adt/selfuncs.c
@@ -146,23 +146,27 @@
/*
* In production builds, switch to hash-based MCV matching when the lists are
* large enough to amortize hash setup cost. (This threshold is compared to
- * the sum of the lengths of the two MCV lists. This is simplistic but seems
+ * the sum of the lengths of the two lists. This is simplistic but seems
* to work well enough.) In debug builds, we use a smaller threshold so that
* the regression tests cover both paths well.
*/
#ifndef USE_ASSERT_CHECKING
-#define EQJOINSEL_MCV_HASH_THRESHOLD 200
+#define MCV_HASH_THRESHOLD 200
#else
-#define EQJOINSEL_MCV_HASH_THRESHOLD 20
+#define MCV_HASH_THRESHOLD 20
#endif
-/* Entries in the simplehash hash table used by eqjoinsel_find_matches */
+/*
+ * Entries in the simplehash hash table used by
+ * eqjoinsel_find_matches and scalararray_mcv_hash_match
+ */
typedef struct MCVHashEntry
{
Datum value; /* the value represented by this entry */
int index; /* its index in the relevant AttStatsSlot */
uint32 hash; /* hash code for the Datum */
char status; /* status code used by simplehash.h */
+ int count; /* number of occurrences of current value */
} MCVHashEntry;
/* private_data for the simplehash hash table */
@@ -184,6 +188,16 @@ get_relation_stats_hook_type get_relation_stats_hook = NULL;
get_index_stats_hook_type get_index_stats_hook = NULL;
static double eqsel_internal(PG_FUNCTION_ARGS, bool negate);
+static double scalararray_mcv_hash_match(VariableStatData *vardata, Oid operator,
+ Oid collation, Selectivity nonconst_sel,
+ Datum *elem_values, bool *elem_nulls,
+ int num_elems, bool *elem_const,
+ Oid nominal_element_type, bool useOr,
+ bool isEquality, bool isInequality);
+static void accum_scalararray_prob(double s1, int count, bool useOr,
+ bool isEquality, bool isInequality,
+ double nullfrac, bool invert,
+ double *selec, double *s1disjoint);
static double eqjoinsel_inner(FmgrInfo *eqproc, Oid collation,
Oid hashLeft, Oid hashRight,
VariableStatData *vardata1, VariableStatData *vardata2,
@@ -1893,6 +1907,37 @@ strip_array_coercion(Node *node)
return node;
}
+/*
+ * Accumulate the selectivity contribution of a single array element
+ * into the running ScalarArrayOpExpr selectivity estimate.
+ */
+static void
+accum_scalararray_prob(double s1, int count, bool useOr, bool isEquality,
+ bool isInequality, double nullfrac, bool invert,
+ double *selec, double *s1disjoint)
+{
+ if (count <= 0)
+ return;
+
+ if (invert && isInequality)
+ s1 = 1.0 - s1 - nullfrac;
+
+ CLAMP_PROBABILITY(s1);
+
+ if (useOr)
+ {
+ *selec = 1.0 - (1.0 - *selec) * pow(1.0 - s1, count);
+ if (isEquality)
+ *s1disjoint += s1 * count;
+ }
+ else
+ {
+ *selec = (*selec) * pow(s1, count);
+ if (isInequality)
+ *s1disjoint += count * (s1 - 1.0);
+ }
+}
+
/*
* scalararraysel - Selectivity of ScalarArrayOpExpr Node.
*/
@@ -2034,6 +2079,36 @@ scalararraysel(PlannerInfo *root,
elmlen, elmbyval, elmalign,
&elem_values, &elem_nulls, &num_elems);
+ /* Try to avoid O(N^2) selectivity calculation for ScalarArrayOpExpr */
+ if ((isEquality || isInequality) && !is_join_clause)
+ {
+ VariableStatData vardata;
+ Node *other_op = NULL;
+ bool var_on_left;
+ bool *elem_const = NULL;
+
+ /*
+ * If the clause is of the form "var OP something" or "something
+ * OP var", extract statistics for the variable. Otherwise, fall
+ * back to a default per-element estimate.
+ */
+ if (get_restriction_variable(root, clause->args, varRelid,
+ &vardata, &other_op, &var_on_left))
+ {
+ s1 = scalararray_mcv_hash_match(&vardata, operator,
+ clause->inputcollid, -1.0,
+ elem_values, elem_nulls,
+ num_elems, elem_const,
+ nominal_element_type, useOr,
+ isEquality, isInequality);
+
+ ReleaseVariableStats(vardata);
+
+ if (s1 >= 0.0)
+ return s1;
+ }
+ }
+
/*
* For generic operators, we assume the probability of success is
* independent for each array element. But for "= ANY" or "<> ALL",
@@ -2109,6 +2184,100 @@ scalararraysel(PlannerInfo *root,
get_typlenbyval(arrayexpr->element_typeid,
&elmlen, &elmbyval);
+ /* Try to avoid O(N^2) selectivity calculation for ScalarArrayOpExpr */
+ if ((isEquality || isInequality) && !is_join_clause)
+ {
+ VariableStatData vardata;
+ Node *other_op = NULL;
+ bool var_on_left;
+ int num_elems = list_length(arrayexpr->elements);
+
+ /*
+ * If expression is not variable = something or something =
+ * variable, then fall back to default code path to compute
+ * default selectivity.
+ */
+ if (get_restriction_variable(root, clause->args, varRelid,
+ &vardata, &other_op, &var_on_left))
+ {
+ Selectivity nonconst_sel;
+ Datum *elem_values;
+ bool *elem_nulls;
+ bool *elem_const;
+ ListCell *lc;
+
+ /*
+ * Build arrays describing ARRAY[] elements: - elem_values:
+ * Datum value for Const elements - elem_nulls: whether
+ * element is NULL - elem_const: whether element is a Const
+ * node
+ */
+ elem_values = palloc_array(Datum, num_elems);
+ elem_nulls = palloc0_array(bool, num_elems);
+ elem_const = palloc0_array(bool, num_elems);
+
+ foreach(lc, arrayexpr->elements)
+ {
+ Node *elem_value = (Node *) lfirst(lc);
+ int i = foreach_current_index(lc);
+
+ if (IsA(elem_value, Const))
+ {
+ elem_values[i] = ((Const *) elem_value)->constvalue;
+ elem_nulls[i] = ((Const *) elem_value)->constisnull;
+ elem_const[i] = true;
+ }
+ else
+ {
+ elem_nulls[i] = false;
+ elem_const[i] = false;
+ }
+
+ /*
+ * When the array contains a NULL constant, same as var_eq_const,
+ * we assume the operator is strict and nothing will match, thus
+ * return 0.0.
+ */
+ if (!useOr && elem_nulls[i])
+ {
+ pfree(elem_values);
+ pfree(elem_nulls);
+ pfree(elem_const);
+
+ ReleaseVariableStats(vardata);
+
+ return (Selectivity) 0.0;
+ }
+ }
+
+ /*
+ * Compute per-element selectivity via eqsel()/neqsel
+ * semantics.
+ */
+ nonconst_sel = var_eq_non_const(&vardata, operator,
+ clause->inputcollid,
+ other_op, var_on_left,
+ isInequality);
+
+ s1 = scalararray_mcv_hash_match(&vardata, operator,
+ clause->inputcollid,
+ nonconst_sel, elem_values,
+ elem_nulls, num_elems,
+ elem_const,
+ nominal_element_type, useOr,
+ isEquality, isInequality);
+
+ pfree(elem_values);
+ pfree(elem_nulls);
+ pfree(elem_const);
+
+ ReleaseVariableStats(vardata);
+
+ if (s1 >= 0.0)
+ return s1;
+ }
+ }
+
/*
* We use the assumption of disjoint probabilities here too, although
* the odds of equal array elements are rather higher if the elements
@@ -2227,6 +2396,347 @@ scalararraysel(PlannerInfo *root,
return s1;
}
+/*
+ * Estimate selectivity of a ScalarArrayOpExpr (ANY/ALL) using MCV statistics
+ * with hash-based matching.
+ *
+ * This function follows the same probability model as the generic
+ * ScalarArrayOpExpr selectivity code (independent or disjoint probabilities
+ * for OR/AND combinations), but attempts to speed up matching between
+ * IN-list elements and the column's most-common-values (MCV) statistics by
+ * using hashing instead of nested loops.
+ *
+ * MCV statistics are used only to obtain per-value selectivities for
+ * constants that match MCV entries. All probabilities are combined using
+ * the standard ANY/ALL formulas, exactly as in the generic estimator.
+ *
+ * The function may return -1.0 to indicate that hash-based MCV estimation
+ * is not applicable (for example, missing statistics, unsupported operator,
+ * or unavailable hash functions), in which case the caller should fall back
+ * to the generic ScalarArrayOpExpr selectivity estimation.
+ *
+ * Inputs:
+ * vardata: statistics and metadata for the variable being estimated
+ * operator: equality or inequality operator to apply
+ * collation: OID of collation to use
+ * nonconst_sel: selectivity of non-const element
+ * elem_values: array of IN-list element values
+ * elem_nulls: array indicating which IN-list elements are NULL
+ * elem_const: array indicating which IN-list elements are Const nodes.
+ * array is NULL if all elemnets are const.
+ * num_elems: number of IN-list elements
+ * nominal_element_type: type of IN-list elements
+ * useOr: true if elements are combined using OR semantics, false for AND
+ * isEquality: true if the operator behaves like equality
+ * isInequality: true if the operator behaves like inequality
+ *
+ * Result:
+ * Selectivity estimate in the range [0.0, 1.0], or -1.0 if no estimate
+ * could be produced by this function.
+ *
+ * Note:
+ * This function assumes that the operator’s selectivity behavior matches
+ * eqsel()/neqsel semantics. It must not be used for operators with custom
+ * or non-standard selectivity behavior.
+ */
+static double
+scalararray_mcv_hash_match(VariableStatData *vardata, Oid operator,
+ Oid collation, Selectivity nonconst_sel,
+ Datum *elem_values, bool *elem_nulls, int num_elems,
+ bool *elem_const, Oid nominal_element_type,
+ bool useOr, bool isEquality, bool isInequality)
+{
+ Form_pg_statistic stats;
+ AttStatsSlot sslot;
+ FmgrInfo eqproc;
+ double selec = -1.0,
+ s1disjoint,
+ nullfrac = 0.0;
+ Oid hashLeft = InvalidOid,
+ hashRight = InvalidOid,
+ opfuncoid;
+ bool have_mcvs = false;
+
+ /*
+ * If the variable is known to be unique, MCV statistics do not represent
+ * a meaningful frequency distribution, so skip MCV-based estimation.
+ */
+ if (vardata->isunique && vardata->rel && vardata->rel->tuples >= 1.0)
+ return -1.0;
+
+ /*
+ * For inequality (<>, ALL), we compute probabilities using the negated
+ * equality operator and later transform them as
+ *
+ * p(x <> c) = 1 - p(x = c) - nullfrac
+ */
+ if (isInequality)
+ {
+ operator = get_negator(operator);
+ if (!OidIsValid(operator))
+ return -1.0;
+ }
+
+ opfuncoid = get_opcode(operator);
+ memset(&sslot, 0, sizeof(sslot));
+
+ if (HeapTupleIsValid(vardata->statsTuple))
+ {
+ if (statistic_proc_security_check(vardata, opfuncoid))
+ have_mcvs = get_attstatsslot(&sslot, vardata->statsTuple,
+ STATISTIC_KIND_MCV, InvalidOid,
+ ATTSTATSSLOT_VALUES | ATTSTATSSLOT_NUMBERS);
+ }
+
+ if (have_mcvs)
+ {
+ /*
+ * If the MCV list and IN-list are large enough, and the operator
+ * supports hashing, attempt to use hash functions so that MCV–IN
+ * matching can be done in O(N+M) instead of O(N×M).
+ */
+ if (sslot.nvalues + num_elems >= MCV_HASH_THRESHOLD)
+ {
+ fmgr_info(opfuncoid, &eqproc);
+ (void) get_op_hash_functions(operator, &hashLeft, &hashRight);
+ }
+ }
+
+ if (have_mcvs && OidIsValid(hashLeft) && OidIsValid(hashRight))
+ {
+ /* Use a hash table to speed up the matching */
+ LOCAL_FCINFO(fcinfo, 2);
+ LOCAL_FCINFO(hash_fcinfo, 1);
+ MCVHashTable_hash *hashTable;
+ FmgrInfo hash_proc;
+ MCVHashContext hashContext;
+ double sumallcommon = 0.0,
+ nonmcv_selec = 0.0;
+ bool isdefault;
+ bool hash_mcv;
+ double otherdistinct;
+ Datum *arrayHash;
+ Datum *arrayProbe;
+ int nvaluesHash;
+ int nvaluesProbe;
+ int nonmcv_cnt = num_elems;
+ int nonconst_cnt = 0;
+
+ /* Grab the nullfrac for use below. */
+ stats = (Form_pg_statistic) GETSTRUCT(vardata->statsTuple);
+ nullfrac = stats->stanullfrac;
+
+ selec = s1disjoint = (useOr ? 0.0 : 1.0);
+
+ InitFunctionCallInfoData(*fcinfo, &eqproc, 2, collation,
+ NULL, NULL);
+ fcinfo->args[0].isnull = false;
+ fcinfo->args[1].isnull = false;
+
+ for (int i = 0; i < sslot.nvalues; i++)
+ sumallcommon += sslot.numbers[i];
+
+ /*
+ * Compute the total probability mass of all non-MCV values. This is
+ * the part of the column distribution not covered by MCVs.
+ */
+ nonmcv_selec = 1.0 - sumallcommon - nullfrac;
+ CLAMP_PROBABILITY(nonmcv_selec);
+
+ /*
+ * Approximate the per-value probability of a non-MCV constant by
+ * dividing the remaining probability mass by the number of other
+ * distinct values.
+ */
+ otherdistinct = get_variable_numdistinct(vardata, &isdefault) - sslot.nnumbers;
+ if (otherdistinct > 1)
+ nonmcv_selec /= otherdistinct;
+
+ if (sslot.nnumbers > 0 && nonmcv_selec > sslot.numbers[sslot.nnumbers - 1])
+ nonmcv_selec = sslot.numbers[sslot.nnumbers - 1];
+
+ /* Make sure we build the hash table on the smaller array. */
+ if (sslot.nvalues <= num_elems)
+ {
+ hash_mcv = true;
+ nvaluesHash = sslot.nvalues;
+ nvaluesProbe = num_elems;
+ arrayHash = sslot.values;
+ arrayProbe = elem_values;
+ }
+ else
+ {
+ hash_mcv = false;
+ nvaluesHash = num_elems;
+ nvaluesProbe = sslot.nvalues;
+ arrayHash = elem_values;
+ arrayProbe = sslot.values;
+ }
+
+ fmgr_info(hash_mcv ? hashLeft : hashRight, &hash_proc);
+ InitFunctionCallInfoData(*hash_fcinfo, &hash_proc, 1, collation,
+ NULL, NULL);
+ hash_fcinfo->args[0].isnull = false;
+
+ hashContext.equal_fcinfo = fcinfo;
+ hashContext.hash_fcinfo = hash_fcinfo;
+ hashContext.op_is_reversed = hash_mcv;
+ hashContext.insert_mode = true;
+
+ get_typlenbyval(hash_mcv ? sslot.valuetype : nominal_element_type,
+ &hashContext.hash_typlen,
+ &hashContext.hash_typbyval);
+
+ hashTable = MCVHashTable_create(CurrentMemoryContext,
+ nvaluesHash,
+ &hashContext);
+
+ /* Build a hash table over the smaller input side. */
+ for (int i = 0; i < nvaluesHash; i++)
+ {
+ bool found = false;
+ MCVHashEntry *entry;
+
+ /*
+ * When hashing IN-list values (hash_mcv == false), we only insert
+ * constant, non-NULL elements. NULL and non-Const elements are
+ * counted separately, because they cannot participate in MCV
+ * matching and must be handled later using generic selectivity
+ * estimation.
+ */
+ if (!hash_mcv)
+ {
+ if (elem_nulls[i])
+ {
+ Assert(useOr);
+ nonmcv_cnt--;
+ continue;
+ }
+
+ if (elem_const != NULL && !elem_const[i])
+ {
+ nonmcv_cnt--;
+ nonconst_cnt++;
+ continue;
+ }
+ }
+
+ entry = MCVHashTable_insert(hashTable, arrayHash[i], &found);
+
+ /*
+ * entry->count tracks how many times the same value appears, so
+ * that duplicate IN-list elements can be folded into the
+ * probability calculation.
+ */
+ if (likely(!found))
+ {
+ entry->index = i;
+ entry->count = 1;
+ }
+ else
+ entry->count++;
+ }
+
+ hashContext.insert_mode = false;
+ if (hashLeft != hashRight)
+ {
+ fmgr_info(hash_mcv ? hashRight : hashLeft, &hash_proc);
+ /* Resetting hash_fcinfo is probably unnecessary, but be safe */
+ InitFunctionCallInfoData(*hash_fcinfo, &hash_proc, 1, collation,
+ NULL, NULL);
+ hash_fcinfo->args[0].isnull = false;
+ }
+
+ for (int i = 0; i < nvaluesProbe; i++)
+ {
+ MCVHashEntry *entry;
+ Selectivity s1;
+ int nvaluesmcv;
+
+ /*
+ * When probing with IN-list elements, ignore NULLs and non-Const
+ * expressions: they cannot be matched against MCVs and will be
+ * accounted for later by generic estimation.
+ */
+ if (hash_mcv)
+ {
+ if (elem_nulls[i])
+ {
+ Assert(useOr);
+ nonmcv_cnt--;
+ continue;
+ }
+
+ if (elem_const != NULL && !elem_const[i])
+ {
+ nonmcv_cnt--;
+ nonconst_cnt++;
+ continue;
+ }
+ }
+
+ entry = MCVHashTable_lookup(hashTable, arrayProbe[i]);
+
+ /*
+ * If found, obtain its MCV frequency and remember how many values
+ * on the hashed side map to this entry.
+ */
+ if (entry != NULL)
+ {
+ s1 = hash_mcv ? sslot.numbers[entry->index]
+ : sslot.numbers[i];
+
+ nvaluesmcv = entry->count;
+
+ accum_scalararray_prob(s1, nvaluesmcv, useOr, isEquality,
+ isInequality, nullfrac, true, &selec,
+ &s1disjoint);
+
+ /* Matched values are no longer considered non-MCV */
+ nonmcv_cnt -= nvaluesmcv;
+ }
+ }
+
+ /*
+ * Account for constant IN-list values that did not match any MCV.
+ *
+ * Each such value is assumed to have probability = nonmcv_selec,
+ * derived from the remaining (non-MCV) probability mass.
+ */
+ accum_scalararray_prob(nonmcv_selec, nonmcv_cnt, useOr, isEquality,
+ isInequality, nullfrac, true,
+ &selec, &s1disjoint);
+
+ /*
+ * Account for non-Const IN-list elements.
+ *
+ * These values cannot be matched against MCVs, so we rely on the
+ * operator's generic selectivity estimator for each of them.
+ */
+ accum_scalararray_prob(nonconst_sel, nonconst_cnt, useOr, isEquality,
+ isInequality, nullfrac, false,
+ &selec, &s1disjoint);
+
+ /*
+ * For = ANY or <> ALL, if the IN-list elements are assumed distinct,
+ * the events are disjoint and the total probability is the sum of
+ * individual probabilities. Use that estimate if it lies in [0,1].
+ */
+ if ((useOr ? isEquality : isInequality) &&
+ s1disjoint >= 0.0 && s1disjoint <= 1.0)
+ selec = s1disjoint;
+
+ CLAMP_PROBABILITY(selec);
+
+ MCVHashTable_destroy(hashTable);
+ }
+
+ if (have_mcvs)
+ free_attstatsslot(&sslot);
+
+ return selec;
+}
+
/*
* Estimate number of elements in the array yielded by an expression.
*
@@ -2463,7 +2973,7 @@ eqjoinsel(PG_FUNCTION_ARGS)
* If the MCV lists are long enough to justify hashing, try to look up
* hash functions for the join operator.
*/
- if ((sslot1.nvalues + sslot2.nvalues) >= EQJOINSEL_MCV_HASH_THRESHOLD)
+ if ((sslot1.nvalues + sslot2.nvalues) >= MCV_HASH_THRESHOLD)
(void) get_op_hash_functions(operator, &hashLeft, &hashRight);
}
else
--
2.34.1
diff --git a/src/test/regress/expected/planner_est.out b/src/test/regress/expected/planner_est.out
index b62a47552fa..3ef720908f5 100644
--- a/src/test/regress/expected/planner_est.out
+++ b/src/test/regress/expected/planner_est.out
@@ -210,4 +210,213 @@ false, true, false, true);
-> Result (cost=N..N rows=1 width=N)
(4 rows)
+-- Ensure stable and rich MCV statistics
+SET default_statistics_target = 1000;
+CREATE TABLE t_mcv (a int);
+-- Build ~100 MCV values with uniform distribution
+INSERT INTO t_mcv
+SELECT (i % 100)
+FROM generate_series(1, 20000) s(i);
+ANALYZE t_mcv;
+-- =========================================================
+-- CASE 1: Large ANY list (MCV < ANY) → hash on MCV
+-- =========================================================
+-- 1. Single element
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY(SELECT 1));$$,
+false, true, false, true);
+ explain_mask_costs
+--------------------------------------------------
+ Seq Scan on t_mcv (cost=N..N rows=1912 width=N)
+ Filter: (a = ANY ((InitPlan array_1).col1))
+ InitPlan array_1
+ -> Result (cost=N..N rows=1 width=N)
+(4 rows)
+
+-- 2. Multiple elements (all in MCV)
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY(SELECT i FROM generate_series(1,3) s(i)));$$,
+false, true, false, true);
+ explain_mask_costs
+------------------------------------------------------------------------
+ Seq Scan on t_mcv (cost=N..N rows=1912 width=N)
+ Filter: (a = ANY ((InitPlan array_1).col1))
+ InitPlan array_1
+ -> Function Scan on generate_series s (cost=N..N rows=3 width=N)
+(4 rows)
+
+-- 3. Includes non-MCV values
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[1, 2, 1000]);$$,
+false, true, false, true);
+ explain_mask_costs
+-------------------------------------------------
+ Seq Scan on t_mcv (cost=N..N rows=400 width=N)
+ Filter: (a = ANY ('{1,2,1000}'::integer[]))
+(2 rows)
+
+-- 4. Duplicates
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY(SELECT (i % 3) + 1 FROM generate_series(1,30) s(i)));$$,
+false, true, false, true);
+ explain_mask_costs
+-------------------------------------------------------------------------
+ Seq Scan on t_mcv (cost=N..N rows=1912 width=N)
+ Filter: (a = ANY ((InitPlan array_1).col1))
+ InitPlan array_1
+ -> Function Scan on generate_series s (cost=N..N rows=30 width=N)
+(4 rows)
+
+-- =========================================================
+-- CASE 2: Small ANY list (ANY < MCV) → hash on ANY
+-- =========================================================
+-- 1. Single element
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[10]);$$,
+false, true, false, true);
+ explain_mask_costs
+-------------------------------------------------
+ Seq Scan on t_mcv (cost=N..N rows=200 width=N)
+ Filter: (a = ANY ('{10}'::integer[]))
+(2 rows)
+
+-- 2. Multiple elements (all in MCV)
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[10,20,30]);$$,
+false, true, false, true);
+ explain_mask_costs
+-------------------------------------------------
+ Seq Scan on t_mcv (cost=N..N rows=600 width=N)
+ Filter: (a = ANY ('{10,20,30}'::integer[]))
+(2 rows)
+
+-- 3. Includes non-MCV values
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[10,20,10000]);$$,
+false, true, false, true);
+ explain_mask_costs
+--------------------------------------------------
+ Seq Scan on t_mcv (cost=N..N rows=400 width=N)
+ Filter: (a = ANY ('{10,20,10000}'::integer[]))
+(2 rows)
+
+-- 4. Duplicates
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[10,10,10,20,20]);$$,
+false, true, false, true);
+ explain_mask_costs
+-----------------------------------------------------
+ Seq Scan on t_mcv (cost=N..N rows=1000 width=N)
+ Filter: (a = ANY ('{10,10,10,20,20}'::integer[]))
+(2 rows)
+
+-- =========================================================
+-- CASE 3: Guaranteed large case → stress hash path
+-- =========================================================
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY(SELECT i % 100 FROM generate_series(1,500) s(i)));$$,
+false, true, false, true);
+ explain_mask_costs
+--------------------------------------------------------------------------
+ Seq Scan on t_mcv (cost=N..N rows=1912 width=N)
+ Filter: (a = ANY ((InitPlan array_1).col1))
+ InitPlan array_1
+ -> Function Scan on generate_series s (cost=N..N rows=500 width=N)
+(4 rows)
+
+-- =========================================================
+-- CASE 4: inequality (<> ALL)
+-- =========================================================
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a <> ALL (ARRAY[1,2,3]);$$,
+false, true, false, true);
+ explain_mask_costs
+---------------------------------------------------
+ Seq Scan on t_mcv (cost=N..N rows=19400 width=N)
+ Filter: (a <> ALL ('{1,2,3}'::integer[]))
+(2 rows)
+
+-- =========================================================
+-- CASE 5: mix const + non-const
+-- =========================================================
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[1,2] || ARRAY(SELECT i FROM generate_series(3,5) s(i)));$$,
+false, true, false, true);
+ explain_mask_costs
+------------------------------------------------------------------------
+ Seq Scan on t_mcv (cost=N..N rows=1912 width=N)
+ Filter: (a = ANY (('{1,2}'::integer[] || (InitPlan array_1).col1)))
+ InitPlan array_1
+ -> Function Scan on generate_series s (cost=N..N rows=3 width=N)
+(4 rows)
+
+-- =========================================================
+-- CASE 6: NULL handling
+-- =========================================================
+-- ANY with NULL
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[NULL,1]);$$,
+false, true, false, true);
+ explain_mask_costs
+-------------------------------------------------
+ Seq Scan on t_mcv (cost=N..N rows=200 width=N)
+ Filter: (a = ANY ('{NULL,1}'::integer[]))
+(2 rows)
+
+-- ALL with NULL (should be 0 selectivity)
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ALL (ARRAY[1,NULL]);$$,
+false, true, false, true);
+ explain_mask_costs
+-----------------------------------------------
+ Seq Scan on t_mcv (cost=N..N rows=1 width=N)
+ Filter: (a = ALL ('{1,NULL}'::integer[]))
+(2 rows)
+
+-- =========================================================
+-- CASE 7: Combined all of them
+-- =========================================================
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[1, 2, 3, 1000, 2000, NULL, 1, 1, 2, (SELECT 4), (SELECT 5), (SELECT 10000), (SELECT 4), (SELECT 4)] || ARRAY( SELECT i % 120 FROM generate_series(1, 500) s(i)));$$,
+false, true, false, true);
+ explain_mask_costs
+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ Seq Scan on t_mcv (cost=N..N rows=1912 width=N)
+ Filter: (a = ANY ((ARRAY[1, 2, 3, 1000, 2000, NULL::integer, 1, 1, 2, (InitPlan expr_1).col1, (InitPlan expr_2).col1, (InitPlan expr_3).col1, (InitPlan expr_4).col1, (InitPlan expr_5).col1] || (InitPlan array_1).col1)))
+ InitPlan expr_1
+ -> Result (cost=N..N rows=1 width=N)
+ InitPlan expr_2
+ -> Result (cost=N..N rows=1 width=N)
+ InitPlan expr_3
+ -> Result (cost=N..N rows=1 width=N)
+ InitPlan expr_4
+ -> Result (cost=N..N rows=1 width=N)
+ InitPlan expr_5
+ -> Result (cost=N..N rows=1 width=N)
+ InitPlan array_1
+ -> Function Scan on generate_series s (cost=N..N rows=500 width=N)
+(14 rows)
+
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a <> ALL (ARRAY[1, 2, 3, 1000, 2000, NULL, 1, 1, 2, (SELECT 4), (SELECT 5), (SELECT 10000), (SELECT 4), (SELECT 4)] || ARRAY( SELECT i % 120 FROM generate_series(1, 500) s(i)));$$,
+false, true, false, true);
+ explain_mask_costs
+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ Seq Scan on t_mcv (cost=N..N rows=18088 width=N)
+ Filter: (a <> ALL ((ARRAY[1, 2, 3, 1000, 2000, NULL::integer, 1, 1, 2, (InitPlan expr_1).col1, (InitPlan expr_2).col1, (InitPlan expr_3).col1, (InitPlan expr_4).col1, (InitPlan expr_5).col1] || (InitPlan array_1).col1)))
+ InitPlan expr_1
+ -> Result (cost=N..N rows=1 width=N)
+ InitPlan expr_2
+ -> Result (cost=N..N rows=1 width=N)
+ InitPlan expr_3
+ -> Result (cost=N..N rows=1 width=N)
+ InitPlan expr_4
+ -> Result (cost=N..N rows=1 width=N)
+ InitPlan expr_5
+ -> Result (cost=N..N rows=1 width=N)
+ InitPlan array_1
+ -> Function Scan on generate_series s (cost=N..N rows=500 width=N)
+(14 rows)
+
+DROP TABLE t_mcv;
DROP FUNCTION explain_mask_costs(text, bool, bool, bool, bool);
diff --git a/src/test/regress/sql/planner_est.sql b/src/test/regress/sql/planner_est.sql
index 53210d5baad..ba8f8bd8fb6 100644
--- a/src/test/regress/sql/planner_est.sql
+++ b/src/test/regress/sql/planner_est.sql
@@ -147,4 +147,116 @@ SELECT explain_mask_costs($$
SELECT * FROM tenk1 WHERE unique1 <> ALL (ARRAY[1, 2, 98, (SELECT 99), NULL]);$$,
false, true, false, true);
+-- Ensure stable and rich MCV statistics
+SET default_statistics_target = 1000;
+
+CREATE TABLE t_mcv (a int);
+
+-- Build ~100 MCV values with uniform distribution
+INSERT INTO t_mcv
+SELECT (i % 100)
+FROM generate_series(1, 20000) s(i);
+
+ANALYZE t_mcv;
+
+-- =========================================================
+-- CASE 1: Large ANY list (MCV < ANY) → hash on MCV
+-- =========================================================
+
+-- 1. Single element
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY(SELECT 1));$$,
+false, true, false, true);
+
+-- 2. Multiple elements (all in MCV)
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY(SELECT i FROM generate_series(1,3) s(i)));$$,
+false, true, false, true);
+
+-- 3. Includes non-MCV values
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[1, 2, 1000]);$$,
+false, true, false, true);
+
+-- 4. Duplicates
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY(SELECT (i % 3) + 1 FROM generate_series(1,30) s(i)));$$,
+false, true, false, true);
+
+-- =========================================================
+-- CASE 2: Small ANY list (ANY < MCV) → hash on ANY
+-- =========================================================
+
+-- 1. Single element
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[10]);$$,
+false, true, false, true);
+
+-- 2. Multiple elements (all in MCV)
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[10,20,30]);$$,
+false, true, false, true);
+
+-- 3. Includes non-MCV values
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[10,20,10000]);$$,
+false, true, false, true);
+
+-- 4. Duplicates
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[10,10,10,20,20]);$$,
+false, true, false, true);
+
+-- =========================================================
+-- CASE 3: Guaranteed large case → stress hash path
+-- =========================================================
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY(SELECT i % 100 FROM generate_series(1,500) s(i)));$$,
+false, true, false, true);
+
+-- =========================================================
+-- CASE 4: inequality (<> ALL)
+-- =========================================================
+
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a <> ALL (ARRAY[1,2,3]);$$,
+false, true, false, true);
+
+-- =========================================================
+-- CASE 5: mix const + non-const
+-- =========================================================
+
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[1,2] || ARRAY(SELECT i FROM generate_series(3,5) s(i)));$$,
+false, true, false, true);
+
+-- =========================================================
+-- CASE 6: NULL handling
+-- =========================================================
+
+-- ANY with NULL
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[NULL,1]);$$,
+false, true, false, true);
+
+-- ALL with NULL (should be 0 selectivity)
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ALL (ARRAY[1,NULL]);$$,
+false, true, false, true);
+
+-- =========================================================
+-- CASE 7: Combined all of them
+-- =========================================================
+
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a = ANY (ARRAY[1, 2, 3, 1000, 2000, NULL, 1, 1, 2, (SELECT 4), (SELECT 5), (SELECT 10000), (SELECT 4), (SELECT 4)] || ARRAY( SELECT i % 120 FROM generate_series(1, 500) s(i)));$$,
+false, true, false, true);
+
+SELECT explain_mask_costs($$
+SELECT * FROM t_mcv WHERE a <> ALL (ARRAY[1, 2, 3, 1000, 2000, NULL, 1, 1, 2, (SELECT 4), (SELECT 5), (SELECT 10000), (SELECT 4), (SELECT 4)] || ARRAY( SELECT i % 120 FROM generate_series(1, 500) s(i)));$$,
+false, true, false, true);
+
+DROP TABLE t_mcv;
+
+
DROP FUNCTION explain_mask_costs(text, bool, bool, bool, bool);
