/* * Join selectivity estimation for the subnet inclusion/overlap operators * * This function has the same structure as eqjoinsel() in selfuncs.c. * * Throughout networkjoinsel and its subroutines, we have a performance issue * in that the amount of work to be done is O(N^2) in the length of the MCV * and histogram arrays. To keep the runtime from getting out of hand when * large statistics targets have been set, we arbitrarily limit the number of * values considered to 1024 (MAX_CONSIDERED_ELEMS). For the MCV arrays, this * is easy: just consider at most the first N elements. (Since the MCVs are * sorted by decreasing frequency, this correctly gets us the first N MCVs.) * For the histogram arrays, we decimate; that is consider only every k'th * element, where k is chosen so that no more than MAX_CONSIDERED_ELEMS * elements are considered. This should still give us a good random sample of * the non-MCV population. Decimation is done on-the-fly in the loops that * iterate over the histogram arrays. */ Datum networkjoinsel(PG_FUNCTION_ARGS) { PlannerInfo *root = (PlannerInfo *) PG_GETARG_POINTER(0); Oid operator = PG_GETARG_OID(1); List *args = (List *) PG_GETARG_POINTER(2); #ifdef NOT_USED JoinType jointype = (JoinType) PG_GETARG_INT16(3); #endif SpecialJoinInfo *sjinfo = (SpecialJoinInfo *) PG_GETARG_POINTER(4); double selec; VariableStatData vardata1; VariableStatData vardata2; bool join_is_reversed; get_join_variables(root, args, sjinfo, &vardata1, &vardata2, &join_is_reversed); switch (sjinfo->jointype) { case JOIN_INNER: case JOIN_LEFT: case JOIN_FULL: /* * Selectivity for left/full join is not exactly the same as inner * join, but we neglect the difference, as eqjoinsel does. */ selec = networkjoinsel_inner(operator, &vardata1, &vardata2); break; case JOIN_SEMI: case JOIN_ANTI: /* Here, it's important that we pass the outer var on the left. */ if (!join_is_reversed) selec = networkjoinsel_semi(operator, &vardata1, &vardata2); else selec = networkjoinsel_semi(get_commutator(operator), &vardata2, &vardata1); break; default: /* other values not expected here */ elog(ERROR, "unrecognized join type: %d", (int) sjinfo->jointype); selec = 0; /* keep compiler quiet */ break; } ReleaseVariableStats(vardata1); ReleaseVariableStats(vardata2); CLAMP_PROBABILITY(selec); PG_RETURN_FLOAT8((float8) selec); }
/* * scalararraysel_containment * Estimate selectivity of ScalarArrayOpExpr via array containment. * * If we have const =/<> ANY/ALL (array_var) then we can estimate the * selectivity as though this were an array containment operator, * array_var op ARRAY[const]. * * scalararraysel() has already verified that the ScalarArrayOpExpr's operator * is the array element type's default equality or inequality operator, and * has aggressively simplified both inputs to constants. * * Returns selectivity (0..1), or -1 if we fail to estimate selectivity. */ Selectivity scalararraysel_containment(PlannerInfo *root, Node *leftop, Node *rightop, Oid elemtype, bool isEquality, bool useOr, int varRelid) { Selectivity selec; VariableStatData vardata; Datum constval; TypeCacheEntry *typentry; FmgrInfo *cmpfunc; /* * rightop must be a variable, else punt. */ examine_variable(root, rightop, varRelid, &vardata); if (!vardata.rel) { ReleaseVariableStats(vardata); return -1.0; } /* * leftop must be a constant, else punt. */ if (!IsA(leftop, Const)) { ReleaseVariableStats(vardata); return -1.0; } if (((Const *) leftop)->constisnull) { /* qual can't succeed if null on left */ ReleaseVariableStats(vardata); return (Selectivity) 0.0; } constval = ((Const *) leftop)->constvalue; /* Get element type's default comparison function */ typentry = lookup_type_cache(elemtype, TYPECACHE_CMP_PROC_FINFO); if (!OidIsValid(typentry->cmp_proc_finfo.fn_oid)) { ReleaseVariableStats(vardata); return -1.0; } cmpfunc = &typentry->cmp_proc_finfo; /* * If the operator is <>, swap ANY/ALL, then invert the result later. */ if (!isEquality) useOr = !useOr; /* Get array element stats for var, if available */ if (HeapTupleIsValid(vardata.statsTuple) && statistic_proc_security_check(&vardata, cmpfunc->fn_oid)) { Form_pg_statistic stats; AttStatsSlot sslot; AttStatsSlot hslot; stats = (Form_pg_statistic) GETSTRUCT(vardata.statsTuple); /* MCELEM will be an array of same type as element */ if (get_attstatsslot(&sslot, vardata.statsTuple, STATISTIC_KIND_MCELEM, InvalidOid, ATTSTATSSLOT_VALUES | ATTSTATSSLOT_NUMBERS)) { /* For ALL case, also get histogram of distinct-element counts */ if (useOr || !get_attstatsslot(&hslot, vardata.statsTuple, STATISTIC_KIND_DECHIST, InvalidOid, ATTSTATSSLOT_NUMBERS)) memset(&hslot, 0, sizeof(hslot)); /* * For = ANY, estimate as var @> ARRAY[const]. * * For = ALL, estimate as var <@ ARRAY[const]. */ if (useOr) selec = mcelem_array_contain_overlap_selec(sslot.values, sslot.nvalues, sslot.numbers, sslot.nnumbers, &constval, 1, OID_ARRAY_CONTAINS_OP, cmpfunc); else selec = mcelem_array_contained_selec(sslot.values, sslot.nvalues, sslot.numbers, sslot.nnumbers, &constval, 1, hslot.numbers, hslot.nnumbers, OID_ARRAY_CONTAINED_OP, cmpfunc); free_attstatsslot(&hslot); free_attstatsslot(&sslot); } else { /* No most-common-elements info, so do without */ if (useOr) selec = mcelem_array_contain_overlap_selec(NULL, 0, NULL, 0, &constval, 1, OID_ARRAY_CONTAINS_OP, cmpfunc); else selec = mcelem_array_contained_selec(NULL, 0, NULL, 0, &constval, 1, NULL, 0, OID_ARRAY_CONTAINED_OP, cmpfunc); } /* * MCE stats count only non-null rows, so adjust for null rows. */ selec *= (1.0 - stats->stanullfrac); } else { /* No stats at all, so do without */ if (useOr) selec = mcelem_array_contain_overlap_selec(NULL, 0, NULL, 0, &constval, 1, OID_ARRAY_CONTAINS_OP, cmpfunc); else selec = mcelem_array_contained_selec(NULL, 0, NULL, 0, &constval, 1, NULL, 0, OID_ARRAY_CONTAINED_OP, cmpfunc); /* we assume no nulls here, so no stanullfrac correction */ } ReleaseVariableStats(vardata); /* * If the operator is <>, invert the results. */ if (!isEquality) selec = 1.0 - selec; CLAMP_PROBABILITY(selec); return selec; }
/* * arraycontsel -- restriction selectivity for array @>, &&, <@ operators */ Datum arraycontsel(PG_FUNCTION_ARGS) { PlannerInfo *root = (PlannerInfo *) PG_GETARG_POINTER(0); Oid operator = PG_GETARG_OID(1); List *args = (List *) PG_GETARG_POINTER(2); int varRelid = PG_GETARG_INT32(3); VariableStatData vardata; Node *other; bool varonleft; Selectivity selec; Oid element_typeid; /* * If expression is not (variable op something) or (something op * variable), then punt and return a default estimate. */ if (!get_restriction_variable(root, args, varRelid, &vardata, &other, &varonleft)) PG_RETURN_FLOAT8(DEFAULT_SEL(operator)); /* * Can't do anything useful if the something is not a constant, either. */ if (!IsA(other, Const)) { ReleaseVariableStats(vardata); PG_RETURN_FLOAT8(DEFAULT_SEL(operator)); } /* * The "&&", "@>" and "<@" operators are strict, so we can cope with a * NULL constant right away. */ if (((Const *) other)->constisnull) { ReleaseVariableStats(vardata); PG_RETURN_FLOAT8(0.0); } /* * If var is on the right, commute the operator, so that we can assume the * var is on the left in what follows. */ if (!varonleft) { if (operator == OID_ARRAY_CONTAINS_OP) operator = OID_ARRAY_CONTAINED_OP; else if (operator == OID_ARRAY_CONTAINED_OP) operator = OID_ARRAY_CONTAINS_OP; } /* * OK, there's a Var and a Const we're dealing with here. We need the * Const to be an array with same element type as column, else we can't do * anything useful. (Such cases will likely fail at runtime, but here * we'd rather just return a default estimate.) */ element_typeid = get_base_element_type(((Const *) other)->consttype); if (element_typeid != InvalidOid && element_typeid == get_base_element_type(vardata.vartype)) { selec = calc_arraycontsel(&vardata, ((Const *) other)->constvalue, element_typeid, operator); } else { selec = DEFAULT_SEL(operator); } ReleaseVariableStats(vardata); CLAMP_PROBABILITY(selec); PG_RETURN_FLOAT8((float8) selec); }
/* * ltreeparentsel - Selectivity of parent relationship for ltree data types. */ Datum ltreeparentsel(PG_FUNCTION_ARGS) { PlannerInfo *root = (PlannerInfo *) PG_GETARG_POINTER(0); Oid operator = PG_GETARG_OID(1); List *args = (List *) PG_GETARG_POINTER(2); int varRelid = PG_GETARG_INT32(3); VariableStatData vardata; Node *other; bool varonleft; double selec; /* * If expression is not variable <@ something or something <@ variable, * then punt and return a default estimate. */ if (!get_restriction_variable(root, args, varRelid, &vardata, &other, &varonleft)) PG_RETURN_FLOAT8(DEFAULT_PARENT_SEL); /* * If the something is a NULL constant, assume operator is strict and * return zero, ie, operator will never return TRUE. */ if (IsA(other, Const) && ((Const *) other)->constisnull) { ReleaseVariableStats(vardata); PG_RETURN_FLOAT8(0.0); } if (IsA(other, Const)) { /* Variable is being compared to a known non-null constant */ Datum constval = ((Const *) other)->constvalue; FmgrInfo contproc; double mcvsum; double mcvsel; double nullfrac; int hist_size; fmgr_info(get_opcode(operator), &contproc); /* * Is the constant "<@" to any of the column's most common values? */ mcvsel = mcv_selectivity(&vardata, &contproc, constval, varonleft, &mcvsum); /* * If the histogram is large enough, see what fraction of it the * constant is "<@" to, and assume that's representative of the * non-MCV population. Otherwise use the default selectivity for the * non-MCV population. */ selec = histogram_selectivity(&vardata, &contproc, constval, varonleft, 10, 1, &hist_size); if (selec < 0) { /* Nope, fall back on default */ selec = DEFAULT_PARENT_SEL; } else if (hist_size < 100) { /* * For histogram sizes from 10 to 100, we combine the histogram * and default selectivities, putting increasingly more trust in * the histogram for larger sizes. */ double hist_weight = hist_size / 100.0; selec = selec * hist_weight + DEFAULT_PARENT_SEL * (1.0 - hist_weight); } /* In any case, don't believe extremely small or large estimates. */ if (selec < 0.0001) selec = 0.0001; else if (selec > 0.9999) selec = 0.9999; if (HeapTupleIsValid(vardata.statsTuple)) nullfrac = ((Form_pg_statistic) GETSTRUCT(vardata.statsTuple))->stanullfrac; else nullfrac = 0.0; /* * Now merge the results from the MCV and histogram calculations, * realizing that the histogram covers only the non-null values that * are not listed in MCV. */ selec *= 1.0 - nullfrac - mcvsum; selec += mcvsel; } else selec = DEFAULT_PARENT_SEL; ReleaseVariableStats(vardata); /* result should be in range, but make sure... */ CLAMP_PROBABILITY(selec); PG_RETURN_FLOAT8((float8) selec); }
/* * rangesel -- restriction selectivity for range operators */ Datum rangesel(PG_FUNCTION_ARGS) { PlannerInfo *root = (PlannerInfo *) PG_GETARG_POINTER(0); Oid operator = PG_GETARG_OID(1); List *args = (List *) PG_GETARG_POINTER(2); int varRelid = PG_GETARG_INT32(3); VariableStatData vardata; Node *other; bool varonleft; Selectivity selec; TypeCacheEntry *typcache = NULL; RangeType *constrange = NULL; /* * If expression is not (variable op something) or (something op * variable), then punt and return a default estimate. */ if (!get_restriction_variable(root, args, varRelid, &vardata, &other, &varonleft)) PG_RETURN_FLOAT8(default_range_selectivity(operator)); /* * Can't do anything useful if the something is not a constant, either. */ if (!IsA(other, Const)) { ReleaseVariableStats(vardata); PG_RETURN_FLOAT8(default_range_selectivity(operator)); } /* * All the range operators are strict, so we can cope with a NULL constant * right away. */ if (((Const *) other)->constisnull) { ReleaseVariableStats(vardata); PG_RETURN_FLOAT8(0.0); } /* * If var is on the right, commute the operator, so that we can assume the * var is on the left in what follows. */ if (!varonleft) { /* we have other Op var, commute to make var Op other */ operator = get_commutator(operator); if (!operator) { /* Use default selectivity (should we raise an error instead?) */ ReleaseVariableStats(vardata); PG_RETURN_FLOAT8(default_range_selectivity(operator)); } } /* * OK, there's a Var and a Const we're dealing with here. We need the * Const to be of same range type as the column, else we can't do anything * useful. (Such cases will likely fail at runtime, but here we'd rather * just return a default estimate.) * * If the operator is "range @> element", the constant should be of the * element type of the range column. Convert it to a range that includes * only that single point, so that we don't need special handling for that * in what follows. */ if (operator == OID_RANGE_CONTAINS_ELEM_OP) { typcache = range_get_typcache(fcinfo, vardata.vartype); if (((Const *) other)->consttype == typcache->rngelemtype->type_id) { RangeBound lower, upper; lower.inclusive = true; lower.val = ((Const *) other)->constvalue; lower.infinite = false; lower.lower = true; upper.inclusive = true; upper.val = ((Const *) other)->constvalue; upper.infinite = false; upper.lower = false; constrange = range_serialize(typcache, &lower, &upper, false); } } else if (operator == OID_RANGE_ELEM_CONTAINED_OP) { /* * Here, the Var is the elem, not the range. For now we just punt and * return the default estimate. In future we could disassemble the * range constant and apply scalarineqsel ... */ } else if (((Const *) other)->consttype == vardata.vartype) { /* Both sides are the same range type */ typcache = range_get_typcache(fcinfo, vardata.vartype); constrange = DatumGetRangeType(((Const *) other)->constvalue); } /* * If we got a valid constant on one side of the operator, proceed to * estimate using statistics. Otherwise punt and return a default constant * estimate. Note that calc_rangesel need not handle * OID_RANGE_ELEM_CONTAINED_OP. */ if (constrange) selec = calc_rangesel(typcache, &vardata, constrange, operator); else selec = default_range_selectivity(operator); ReleaseVariableStats(vardata); CLAMP_PROBABILITY(selec); PG_RETURN_FLOAT8((float8) selec); }
/* * _int_matchsel -- restriction selectivity function for intarray @@ query_int */ Datum _int_matchsel(PG_FUNCTION_ARGS) { PlannerInfo *root = (PlannerInfo *) PG_GETARG_POINTER(0); List *args = (List *) PG_GETARG_POINTER(2); int varRelid = PG_GETARG_INT32(3); VariableStatData vardata; Node *other; bool varonleft; Selectivity selec; QUERYTYPE *query; Datum *mcelems = NULL; float4 *mcefreqs = NULL; int nmcelems = 0; float4 minfreq = 0.0; float4 nullfrac = 0.0; Form_pg_statistic stats; Datum *values = NULL; int nvalues = 0; float4 *numbers = NULL; int nnumbers = 0; /* * If expression is not "variable @@ something" or "something @@ variable" * then punt and return a default estimate. */ if (!get_restriction_variable(root, args, varRelid, &vardata, &other, &varonleft)) PG_RETURN_FLOAT8(DEFAULT_EQ_SEL); /* * Variable should be int[]. We don't support cases where variable is * query_int. */ if (vardata.vartype != INT4ARRAYOID) PG_RETURN_FLOAT8(DEFAULT_EQ_SEL); /* * Can't do anything useful if the something is not a constant, either. */ if (!IsA(other, Const)) { ReleaseVariableStats(vardata); PG_RETURN_FLOAT8(DEFAULT_EQ_SEL); } /* * The "@@" operator is strict, so we can cope with NULL right away. */ if (((Const *) other)->constisnull) { ReleaseVariableStats(vardata); PG_RETURN_FLOAT8(0.0); } /* The caller made sure the const is a query, so get it now */ query = DatumGetQueryTypeP(((Const *) other)->constvalue); /* Empty query matches nothing */ if (query->size == 0) { ReleaseVariableStats(vardata); return (Selectivity) 0.0; } /* * Get the statistics for the intarray column. * * We're interested in the Most-Common-Elements list, and the NULL * fraction. */ if (HeapTupleIsValid(vardata.statsTuple)) { stats = (Form_pg_statistic) GETSTRUCT(vardata.statsTuple); nullfrac = stats->stanullfrac; /* * For an int4 array, the default array type analyze function will * collect a Most Common Elements list, which is an array of int4s. */ if (get_attstatsslot(vardata.statsTuple, INT4OID, -1, STATISTIC_KIND_MCELEM, InvalidOid, NULL, &values, &nvalues, &numbers, &nnumbers)) { /* * There should be three more Numbers than Values, because the * last three (for intarray) cells are taken for minimal, maximal * and nulls frequency. Punt if not. */ if (nnumbers == nvalues + 3) { /* Grab the lowest frequency. */ minfreq = numbers[nnumbers - (nnumbers - nvalues)]; mcelems = values; mcefreqs = numbers; nmcelems = nvalues; } } } /* Process the logical expression in the query, using the stats */ selec = int_query_opr_selec(GETQUERY(query) + query->size - 1, mcelems, mcefreqs, nmcelems, minfreq); /* MCE stats count only non-null rows, so adjust for null rows. */ selec *= (1.0 - nullfrac); free_attstatsslot(INT4OID, values, nvalues, numbers, nnumbers); ReleaseVariableStats(vardata); CLAMP_PROBABILITY(selec); PG_RETURN_FLOAT8((float8) selec); }
/* * tsmatchsel -- Selectivity of "@@" * * restriction selectivity function for tsvector @@ tsquery and * tsquery @@ tsvector */ Datum tsmatchsel(PG_FUNCTION_ARGS) { PlannerInfo *root = (PlannerInfo *) PG_GETARG_POINTER(0); #ifdef NOT_USED Oid operator = PG_GETARG_OID(1); #endif List *args = (List *) PG_GETARG_POINTER(2); int varRelid = PG_GETARG_INT32(3); VariableStatData vardata; Node *other; bool varonleft; Selectivity selec; /* * If expression is not variable = something or something = variable, then * punt and return a default estimate. */ if (!get_restriction_variable(root, args, varRelid, &vardata, &other, &varonleft)) PG_RETURN_FLOAT8(DEFAULT_TS_MATCH_SEL); /* * Can't do anything useful if the something is not a constant, either. */ if (!IsA(other, Const)) { ReleaseVariableStats(vardata); PG_RETURN_FLOAT8(DEFAULT_TS_MATCH_SEL); } /* * The "@@" operator is strict, so we can cope with NULL right away */ if (((Const *) other)->constisnull) { ReleaseVariableStats(vardata); PG_RETURN_FLOAT8(0.0); } /* * OK, there's a Var and a Const we're dealing with here. We need the * Const to be a TSQuery, else we can't do anything useful. We have to * check this because the Var might be the TSQuery not the TSVector. */ if (((Const *) other)->consttype == TSQUERYOID) { /* tsvector @@ tsquery or the other way around */ Assert(vardata.vartype == TSVECTOROID); selec = tsquerysel(&vardata, ((Const *) other)->constvalue); } else { /* If we can't see the query structure, must punt */ selec = DEFAULT_TS_MATCH_SEL; } ReleaseVariableStats(vardata); CLAMP_PROBABILITY(selec); PG_RETURN_FLOAT8((float8) selec); }
/* * Selectivity estimation for the subnet inclusion/overlap operators */ Datum networksel(PG_FUNCTION_ARGS) { PlannerInfo *root = (PlannerInfo *) PG_GETARG_POINTER(0); Oid operator = PG_GETARG_OID(1); List *args = (List *) PG_GETARG_POINTER(2); int varRelid = PG_GETARG_INT32(3); VariableStatData vardata; Node *other; bool varonleft; Selectivity selec, mcv_selec, non_mcv_selec; Datum constvalue, *hist_values; int hist_nvalues; Form_pg_statistic stats; double sumcommon, nullfrac; FmgrInfo proc; /* * If expression is not (variable op something) or (something op * variable), then punt and return a default estimate. */ if (!get_restriction_variable(root, args, varRelid, &vardata, &other, &varonleft)) PG_RETURN_FLOAT8(DEFAULT_SEL(operator)); /* * Can't do anything useful if the something is not a constant, either. */ if (!IsA(other, Const)) { ReleaseVariableStats(vardata); PG_RETURN_FLOAT8(DEFAULT_SEL(operator)); } /* All of the operators handled here are strict. */ if (((Const *) other)->constisnull) { ReleaseVariableStats(vardata); PG_RETURN_FLOAT8(0.0); } constvalue = ((Const *) other)->constvalue; /* Otherwise, we need stats in order to produce a non-default estimate. */ if (!HeapTupleIsValid(vardata.statsTuple)) { ReleaseVariableStats(vardata); PG_RETURN_FLOAT8(DEFAULT_SEL(operator)); } stats = (Form_pg_statistic) GETSTRUCT(vardata.statsTuple); nullfrac = stats->stanullfrac; /* * If we have most-common-values info, add up the fractions of the MCV * entries that satisfy MCV OP CONST. These fractions contribute directly * to the result selectivity. Also add up the total fraction represented * by MCV entries. */ fmgr_info(get_opcode(operator), &proc); mcv_selec = mcv_selectivity(&vardata, &proc, constvalue, varonleft, &sumcommon); /* * If we have a histogram, use it to estimate the proportion of the * non-MCV population that satisfies the clause. If we don't, apply the * default selectivity to that population. */ if (get_attstatsslot(vardata.statsTuple, vardata.atttype, vardata.atttypmod, STATISTIC_KIND_HISTOGRAM, InvalidOid, NULL, &hist_values, &hist_nvalues, NULL, NULL)) { int opr_codenum = inet_opr_codenum(operator); /* Commute if needed, so we can consider histogram to be on the left */ if (!varonleft) opr_codenum = -opr_codenum; non_mcv_selec = inet_hist_value_sel(hist_values, hist_nvalues, constvalue, opr_codenum); free_attstatsslot(vardata.atttype, hist_values, hist_nvalues, NULL, 0); } else non_mcv_selec = DEFAULT_SEL(operator); /* Combine selectivities for MCV and non-MCV populations */ selec = mcv_selec + (1.0 - nullfrac - sumcommon) * non_mcv_selec; /* Result should be in range, but make sure... */ CLAMP_PROBABILITY(selec); ReleaseVariableStats(vardata); PG_RETURN_FLOAT8(selec); }