Thank you for looking at it.
> In inet_his_inclusion_selec function,
> When the constant matches only the right side of the bucket, and if it’s a
> last bucket then it's never considered as partial match candidate.
> In my opinion, if it's not a last bucket then for next bucket it will become
> left boundary and this will be treated as partial match so no problem, but
> in-case of last bucket it can give wrong selectivity.
>
> Can't we consider it as partial bucket match if it is last bucket ?
Actually, in that case, the ratio for one value in the column is used.
I clarified the comment about it. I do not think it is common enough
case to make the function more complicated.
> Apart from that there is one spell check you can correct
> -- in inet_his_inclusion_selec comments
> histogram boundies -> histogram boundaries :)
I fixed it. New version attached. The debug log statements are also
removed.
diff --git a/src/backend/utils/adt/network_selfuncs.c
b/src/backend/utils/adt/network_selfuncs.c
index d0d806f..d8aeae9 100644
--- a/src/backend/utils/adt/network_selfuncs.c
+++ b/src/backend/utils/adt/network_selfuncs.c
@@ -1,32 +1,677 @@
/*-------------------------------------------------------------------------
*
* network_selfuncs.c
* Functions for selectivity estimation of inet/cidr operators
*
- * Currently these are just stubs, but we hope to do better soon.
+ * Estimates are based on null fraction, distinct value count, most common
+ * values, and histogram of inet/cidr datatypes.
*
* Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
* src/backend/utils/adt/network_selfuncs.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
+#include <math.h>
+
+#include "access/htup_details.h"
+#include "catalog/pg_collation.h"
+#include "catalog/pg_operator.h"
+#include "catalog/pg_statistic.h"
+#include "utils/lsyscache.h"
#include "utils/inet.h"
+#include "utils/selfuncs.h"
+/* Default selectivity constant for the inet overlap operator */
+#define DEFAULT_OVERLAP_SEL 0.01
+
+/* Default selectivity constant for the other operators */
+#define DEFAULT_INCLUSION_SEL 0.005
+
+/* Default selectivity for given operator */
+#define DEFAULT_SEL(operator) \
+ ((operator) == OID_INET_OVERLAP_OP ? \
+ DEFAULT_OVERLAP_SEL : DEFAULT_INCLUSION_SEL)
+
+static short int inet_opr_order(Oid operator, bool reversed);
+static Selectivity inet_his_inclusion_selec(Datum *values, int nvalues,
+ int red_nvalues, Datum *constvalue,
double ndistinct,
+ short int opr_order);
+static Selectivity inet_mcv_join_selec(Datum *values1, float4 *numbers1,
+ int nvalues1, Datum *values2, float4
*numbers2,
+ int nvalues2, Oid operator, bool
reversed);
+static Selectivity inet_mcv_his_selec(Datum *mcv_values, float4 *mcv_numbers,
+ int mcv_nvalues, Datum *his_values, int
his_nvalues,
+ int red_nvalues, short int opr_order);
+static Selectivity inet_his_inclusion_join_selec(Datum *his1_values,
+ int his1_nvalues, int red1_nvalues,
Datum *his2_values,
+ int his2_nvalues, int red2_nvalues,
short int opr_order);
+static short int inet_inclusion_cmp(inet *left, inet *right,
+ short
int opr_order);
+static short int inet_masklen_inclusion_cmp(inet *left, inet *right,
+
short int opr_order);
+static short int inet_his_match_divider(inet *boundary, inet *query,
+
short int opr_order);
+
+/*
+ * Selectivity estimation for the subnet inclusion operators
+ */
Datum
networksel(PG_FUNCTION_ARGS)
{
- PG_RETURN_FLOAT8(0.001);
+ 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),
+ his_nvalues;
+ VariableStatData vardata;
+ Node *other;
+ bool varonleft;
+ Selectivity selec,
+ max_mcv_selec,
+ max_his_selec;
+ Datum constvalue,
+ *his_values;
+ Form_pg_statistic stats;
+ 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 subnet inclusion operators are strict. */
+ if (((Const *) other)->constisnull)
+ {
+ ReleaseVariableStats(vardata);
+ PG_RETURN_FLOAT8(0.0);
+ }
+
+ if (!HeapTupleIsValid(vardata.statsTuple))
+ {
+ ReleaseVariableStats(vardata);
+ PG_RETURN_FLOAT8(DEFAULT_SEL(operator));
+ }
+
+ constvalue = ((Const *) other)->constvalue;
+ stats = (Form_pg_statistic) GETSTRUCT(vardata.statsTuple);
+
+ fmgr_info(get_opcode(operator), &proc);
+ selec = mcv_selectivity(&vardata, &proc, constvalue, varonleft,
+ &max_mcv_selec);
+ max_his_selec = 1.0 - stats->stanullfrac - max_mcv_selec;
+
+ if (get_attstatsslot(vardata.statsTuple,
+ vardata.atttype,
vardata.atttypmod,
+ STATISTIC_KIND_HISTOGRAM,
InvalidOid,
+ NULL,
+ &his_values, &his_nvalues,
+ NULL, NULL))
+ {
+ selec += max_his_selec *
+ inet_his_inclusion_selec(his_values,
his_nvalues, his_nvalues,
+
&constvalue, stats->stadistinct,
+
inet_opr_order(operator, !varonleft));
+
+ free_attstatsslot(vardata.atttype, his_values, his_nvalues,
NULL, 0);
+ }
+ else
+ if (max_mcv_selec > 0)
+ selec = selec / (1.0 - max_his_selec); /* Correct the
value. */
+ else
+ selec = DEFAULT_SEL(operator);
+
+ /* Result should be in range, but make sure... */
+ CLAMP_PROBABILITY(selec);
+
+ ReleaseVariableStats(vardata);
+ PG_RETURN_FLOAT8(selec);
}
+/*
+ * Join selectivity estimation for the subnet inclusion operators
+ *
+ * Calculates MCV vs MCV, MCV vs histogram and histogram vs histogram
+ * selectivity for join using the subnet inclusion operators. Unlike the
+ * join selectivity function for the equality operator, eqjoinsel(), 1 to 1
+ * matching of the values is not enough. Network inclusion operators are
+ * likely to match many to many. It requires to loop the MVC and histogram
+ * lists to the end. Also, MCV vs histogram selectiviy is not neglected
+ * as in eqjoinsel().
+ *
+ * More processing on this function can become a problem with large
+ * statistics. To avoid it only some of the values in the lists are used.
+ * The reduced amount of the list is calculated by the square root of
+ * the original amount. It fits the situation because the lists will be
+ * matched to each other (sqrt(x) * sqrt(x) == x). MCV's will be reduced
+ * by choosing the first N values. Histogram boundaries will be reduced
+ * by skipping some of them.
+ */
Datum
networkjoinsel(PG_FUNCTION_ARGS)
{
- PG_RETURN_FLOAT8(0.001);
+ PlannerInfo *root = (PlannerInfo *) PG_GETARG_POINTER(0);
+ Oid operator = PG_GETARG_OID(1);
+ List *args = (List *) PG_GETARG_POINTER(2);
+ SpecialJoinInfo *sjinfo = (SpecialJoinInfo *) PG_GETARG_POINTER(4);
+ VariableStatData vardata1,
+ vardata2;
+ Form_pg_statistic stats1,
+ stats2;
+ Selectivity selec,
+ mcv1_max_selec,
+ mcv1_red_selec,
+ mcv2_max_selec,
+ mcv2_red_selec;
+ bool reversed,
+ mcv1_exists,
+ mcv2_exists,
+ his1_exists,
+ his2_exists;
+ short int opr_order;
+ int mcv1_nvalues,
+ mcv2_nvalues,
+ mcv1_nnumbers,
+ mcv2_nnumbers,
+ his1_nvalues,
+ his2_nvalues,
+ red1_nvalues,
+ red2_nvalues,
+ i;
+ Datum *mcv1_values,
+ *mcv2_values,
+ *his1_values,
+ *his2_values;
+ float4 *mcv1_numbers,
+ *mcv2_numbers;
+
+ get_join_variables(root, args, sjinfo, &vardata1, &vardata2, &reversed);
+
+ switch (sjinfo->jointype)
+ {
+ case JOIN_INNER:
+ case JOIN_LEFT:
+ case JOIN_FULL:
+ break;
+ default:
+ ReleaseVariableStats(vardata1);
+ ReleaseVariableStats(vardata2);
+ PG_RETURN_FLOAT8(DEFAULT_SEL(operator));
+ }
+
+ if (!HeapTupleIsValid(vardata1.statsTuple) ||
+ !HeapTupleIsValid(vardata2.statsTuple))
+ {
+ ReleaseVariableStats(vardata1);
+ ReleaseVariableStats(vardata2);
+ PG_RETURN_FLOAT8(DEFAULT_SEL(operator));
+ }
+
+ opr_order = inet_opr_order(operator, reversed);
+ stats1 = (Form_pg_statistic) GETSTRUCT(vardata1.statsTuple);
+ stats2 = (Form_pg_statistic) GETSTRUCT(vardata2.statsTuple);
+ mcv1_exists = get_attstatsslot(vardata1.statsTuple,
+
vardata1.atttype, vardata1.atttypmod,
+
STATISTIC_KIND_MCV, InvalidOid,
+ NULL,
+
&mcv1_values, &mcv1_nvalues,
+
&mcv1_numbers, &mcv1_nnumbers);
+ mcv2_exists = get_attstatsslot(vardata2.statsTuple,
+
vardata2.atttype, vardata2.atttypmod,
+
STATISTIC_KIND_MCV, InvalidOid,
+ NULL,
+
&mcv2_values, &mcv2_nvalues,
+
&mcv2_numbers, &mcv2_nnumbers);
+ his1_exists = get_attstatsslot(vardata1.statsTuple,
+
vardata1.atttype, vardata1.atttypmod,
+
STATISTIC_KIND_HISTOGRAM, InvalidOid,
+ NULL,
+
&his1_values, &his1_nvalues,
+ NULL, NULL);
+ his2_exists = get_attstatsslot(vardata2.statsTuple,
+
vardata2.atttype, vardata2.atttypmod,
+
STATISTIC_KIND_HISTOGRAM, InvalidOid,
+ NULL,
+
&his2_values, &his2_nvalues,
+ NULL, NULL);
+
+ red1_nvalues = ((int) sqrt(Max(mcv1_nvalues, his1_nvalues))) + 1;
+ red2_nvalues = ((int) sqrt(Max(mcv2_nvalues, his2_nvalues))) + 1;
+
+ selec = 0.0;
+ mcv1_max_selec = 0.0;
+ mcv1_red_selec = 0.0;
+ mcv2_max_selec = 0.0;
+ mcv2_red_selec = 0.0;
+ if (mcv1_exists)
+ for (i = 0; i < mcv1_nvalues; i++)
+ {
+ mcv1_max_selec += mcv1_numbers[i];
+ if (i < red1_nvalues)
+ mcv1_red_selec += mcv1_numbers[i];
+ }
+ if (mcv2_exists)
+ for (i = 0; i < mcv2_nvalues; i++)
+ {
+ mcv2_max_selec += mcv2_numbers[i];
+ if (i < red2_nvalues)
+ mcv2_red_selec += mcv2_numbers[i];
+ }
+
+ if (mcv1_exists && mcv2_exists)
+ selec += (mcv1_max_selec / mcv1_red_selec) *
+ (mcv2_max_selec / mcv2_red_selec) *
+ inet_mcv_join_selec(mcv1_values, mcv1_numbers,
+
Min(mcv1_nvalues, red1_nvalues),
+
mcv2_values, mcv2_numbers,
+
Min(mcv2_nvalues, red2_nvalues),
+
operator, reversed);
+ if (mcv1_exists && his2_exists)
+ selec += (mcv1_max_selec / mcv1_red_selec) *
+ inet_mcv_his_selec(mcv1_values, mcv1_numbers,
+
Min(mcv1_nvalues, red1_nvalues),
+
his2_values, his2_nvalues, red2_nvalues,
+
opr_order);
+ if (mcv2_exists && his1_exists)
+ selec += (mcv2_max_selec / mcv2_red_selec) *
+ inet_mcv_his_selec(mcv2_values, mcv2_numbers,
+
Min(mcv2_nvalues, red2_nvalues),
+
his1_values, his1_nvalues, red1_nvalues,
+
opr_order);
+ if (his1_exists && his2_exists)
+ selec += (1.0 - stats1->stanullfrac - mcv1_max_selec) *
+ (1.0 - stats2->stanullfrac - mcv2_max_selec) *
+ inet_his_inclusion_join_selec(his1_values,
his1_nvalues,
+
red1_nvalues, his2_values,
+
his2_nvalues, red2_nvalues,
+
opr_order);
+
+ /* Correct the value. */
+ if (!his1_exists)
+ selec /= stats1->stanullfrac + mcv1_max_selec;
+ if (!his2_exists)
+ selec /= stats2->stanullfrac + mcv2_max_selec;
+
+ if (!mcv1_exists && !mcv2_exists && !his1_exists && his2_exists)
+ selec = DEFAULT_SEL(operator);
+
+ if (mcv1_exists)
+ free_attstatsslot(vardata1.atttype, mcv1_values, mcv1_nvalues,
+ mcv1_numbers, mcv1_nnumbers);
+ if (mcv2_exists)
+ free_attstatsslot(vardata2.atttype, mcv2_values, mcv2_nvalues,
+ mcv2_numbers, mcv2_nnumbers);
+ if (his1_exists)
+ free_attstatsslot(vardata1.atttype, his1_values, his1_nvalues,
NULL, 0);
+ if (his2_exists)
+ free_attstatsslot(vardata2.atttype, his2_values, his2_nvalues,
NULL, 0);
+ ReleaseVariableStats(vardata1);
+ ReleaseVariableStats(vardata2);
+
+ /* Result should be in range, but make sure... */
+ CLAMP_PROBABILITY(selec);
+
+ PG_RETURN_FLOAT8(selec);
+}
+
+/*
+ * Practical comparable numbers for the subnet inclusion operators
+ */
+static short int
+inet_opr_order(Oid operator, bool reversed)
+{
+ short int order;
+
+ switch (operator)
+ {
+ case OID_INET_SUP_OP:
+ order = -2;
+ break;
+ case OID_INET_SUPEQ_OP:
+ order = -1;
+ break;
+ case OID_INET_OVERLAP_OP:
+ order = 0;
+ break;
+ case OID_INET_SUBEQ_OP:
+ order = 1;
+ break;
+ case OID_INET_SUB_OP:
+ order = 2;
+ break;
+ default:
+ elog(ERROR, "unknown operator for inet inclusion
selectivity");
+ }
+
+ return (reversed ? order * -1 : order);
+}
+
+/*
+ * Inet histogram inclusion selectivity estimation
+ *
+ * Calculates histogram selectivity for the subnet inclusion operators of
+ * the inet type. The return value is between 0 and 1. It should be
+ * corrected with the MVC selectivity and null fraction. If the constant
+ * is less than the first element or greater than the last element of
+ * the histogram the return value will be 0.
+ *
+ * This function is capable of checking only some of the histogram boundaries.
+ * Reduced number of values, red_nvalues, argument is added for that purpose.
+ * Nvalues can also be given to it to avoid this behavior. This functionality
+ * is used to make join selectivity estimation faster. It is explained on
+ * inet_mcv_join_selec(), below.
+ *
+ * The histogram is originally for the basic comparison operators. Only
+ * the common bits of the network part and the lenght of the network part
+ * (masklen) are appropriate for the subnet inclusion opeators. Fortunately,
+ * basic comparison fits in this situation. Even so, the lenght of the
+ * network part would not really be significant in the histogram. This would
+ * lead to big mistakes for data sets with uneven masklen distribution.
+ * To avoid this problem, comparison with the left and the right side of the
+ * buckets used together.
+ *
+ * Histogram bucket matches are calculated in 3 forms. If the constant
+ * matches both sides the bucket is considered as fully matched. If the
+ * constant matches only the right side the bucket, it is considered as
+ * only matched with a single value. In that case the ratio for only one
+ * value in the column is added to the selectivity.
+ *
+ * The ratio for only one value is calculated with the ndistinct variable
+ * if greater than 0. 0 can be given, if this behavior is not desired.
+ * This ratio can be big enough to not disregard for addresses with small
+ * masklens. See pg_statistic for more information about it.
+ *
+ * When the constant matches only the right side of the bucket, it will match
+ * the next bucket, unless the bucket is the last one. If these buckets would
+ * be considered as matched it would lead to unfair multiple matches for some
+ * constants.
+ *
+ * The third form is to match the bucket partially. We try to calculate
+ * dividers for both of the boundaries. If the address family of the boundary
+ * does not match the constant or comparison of the lenght of the network
+ * parts is not true by the operator, the divider for the boundary would not
+ * taken into account. If both of the dividers can be calculated the greater
+ * one will be used to mimimize the mistake in the buckets which have
+ * disperate masklens.
+ *
+ * The divider on the partial bucket match is imagined as the distance
+ * between the decisive bits and the common bits of the addresses. It will
+ * be* used as power of two as it is the natural scale for the IP network
+ * inclusion. The partial bucket match divider calculation is an empirical
+ * formula and subject to change with more experiment.
+ *
+ * For partial match with buckets which have different address families
+ * on the left and right sides only the boundary with the same address
+ * family is taken into consideration. This can cause more mistakes for these
+ * buckets if the masklens of their boundaries are also disparate. It can
+ * only be the case for one bucket, if there are addresses with different
+ * families on the column. It seems as a better option than not considering
+ * these buckets.
+ */
+static Selectivity
+inet_his_inclusion_selec(Datum *values, int nvalues, int red_nvalues,
+ Datum *constvalue, double
ndistinct,
+ short int opr_order)
+{
+ inet *query,
+ *left,
+ *right;
+ float gap,
+ match;
+ int i;
+ short int left_order,
+ right_order,
+ left_divider,
+ right_divider;
+
+ Assert(nvalues >= red_nvalues);
+
+ gap = ((float) (nvalues - 1)) / ((float) red_nvalues);
+ match = 0.0;
+ query = DatumGetInetP(*constvalue);
+ left = DatumGetInetP(values[0]);
+ left_order = inet_inclusion_cmp(left, query, opr_order);
+
+ for (i = 1; i <= red_nvalues; i++)
+ {
+ right = DatumGetInetP(values[(int) (i * gap)]);
+ right_order = inet_inclusion_cmp(right, query, opr_order);
+
+ if (left_order == 0 && right_order == 0)
+ {
+ /* Full bucket match. */
+
+ match += 1.0;
+ }
+ else if ((left_order <= 0 && right_order > 0) ||
+ (left_order >= 0 && right_order < 0))
+ {
+ /* Partial bucket match. */
+
+ left_divider = inet_his_match_divider(left, query,
opr_order);
+ right_divider = inet_his_match_divider(right, query,
opr_order);
+
+ if (left_divider >= 0 || right_divider >= 0)
+ match += 1.0 / pow(2, Max(left_divider,
right_divider));
+ }
+ else if (right_order == 0)
+ {
+ /* Only right boundary match. */
+
+ if (ndistinct > 0)
+ match += 1.0 / ndistinct;
+ }
+
+ /* Shift the variables. */
+ left = right;
+ left_order = right_order;
+ }
+
+ return match / (red_nvalues - 1);
+}
+
+/*
+ * Inet MCV join selectivity estimation
+ *
+ * The original function of the operator used in this function, like the
+ * mcv_selectivity() on selfuncs.c. Actually this function has nothing
+ * to do with the network data types except its name and location.
+ */
+static Selectivity
+inet_mcv_join_selec(Datum *values1, float4 *numbers1, int nvalues1,
+ Datum *values2, float4 *numbers2, int
nvalues2,
+ Oid operator, bool reversed)
+{
+ Selectivity selec;
+ FmgrInfo proc;
+ int i,
+ j;
+
+ fmgr_info(get_opcode(operator), &proc);
+ selec = 0.0;
+
+ for (i = 0; i < nvalues1; i++)
+ for (j = 0; j < nvalues2; j++)
+ if (reversed ?
+ DatumGetBool(FunctionCall2Coll(&proc,
+
DEFAULT_COLLATION_OID,
+
values1[i],
+
values2[j])) :
+ DatumGetBool(FunctionCall2Coll(&proc,
+
DEFAULT_COLLATION_OID,
+
values2[j],
+
values1[i])))
+ selec += numbers1[i] * numbers2[j];
+
+ return selec;
+}
+
+/*
+ * Inet MCV vs histogram inclusion join selectivity estimation
+ */
+static Selectivity
+inet_mcv_his_selec(Datum *mcv_values, float4 *mcv_numbers, int mcv_nvalues,
+ Datum *his_values, int his_nvalues, int
red_nvalues,
+ short int opr_order)
+{
+ Selectivity selec;
+ int i;
+
+ selec = 0.0;
+ for (i = 0; i < mcv_nvalues; i++)
+ selec += mcv_numbers[i] *
+ inet_his_inclusion_selec(his_values,
his_nvalues, red_nvalues,
+
&mcv_values[i], 0, opr_order);
+ return selec;
+}
+
+/*
+ * Inet histogram inclusion join selectivity estimation
+ *
+ * It is required to choose red1_nvalues from his1_values. The first and
+ * the last values will not be used for better sampling. A gap will be
+ * calculated and used to skip some of the histogram boundaries. It is
+ * important to check exactly given amount of the values.
+ */
+static Selectivity
+inet_his_inclusion_join_selec(Datum *his1_values, int his1_nvalues,
+ int red1_nvalues,
Datum *his2_values,
+ int his2_nvalues, int
red2_nvalues,
+ short int opr_order)
+{
+ float match,
+ gap;
+ int i;
+
+ Assert(his1_nvalues >= red1_nvalues);
+
+ gap = ((float) (his1_nvalues - 2)) / ((float) red1_nvalues);
+ match = 0.0;
+ for (i = 1; i <= red1_nvalues; i++)
+ match += inet_his_inclusion_selec(his2_values, his2_nvalues,
+
red2_nvalues,
+
&his1_values[(int) (i * gap)],
+
0, opr_order);
+
+ return match / red1_nvalues;
+}
+
+/*
+ * Comparison function for the subnet inclusion operators
+ *
+ * Comparison is compatible with the basic comparison function for the inet
+ * type. See network_cmp_internal on network.c for the original. Basic
+ * comparison operators are implemented with the network_cmp_internal
+ * function. It is possible to implement the subnet inclusion operators with
+ * this function.
+ *
+ * Comparison is first on the common bits of the network part, then on
+ * the length of the network part (masklen) as the network_cmp_internal
+ * function. Only the first part is on this function. The second part is
+ * seperated to another function for reusability. The difference between
+ * the second part and the original network_cmp_internal is that the operator
+ * is used while comparing the lengths of the network parts. See the second
+ * part on the inet_masklen_inclusion_cmp function below.
+ */
+static short int
+inet_inclusion_cmp(inet *left, inet *right, short int opr_order)
+{
+ if (ip_family(left) == ip_family(right))
+ {
+ short int order;
+
+ order = bitncmp(ip_addr(left), ip_addr(right),
+ Min(ip_bits(left),
ip_bits(right)));
+
+ if (order != 0)
+ return order;
+
+ return inet_masklen_inclusion_cmp(left, right, opr_order);
+ }
+
+ return ip_family(left) - ip_family(right);
+}
+
+/*
+ * Masklen comparison function for the subnet inclusion operators
+ *
+ * Compares the lengths of network parts of the inputs using the operator.
+ * If the comparision is okay for the operator the return value will be 0.
+ * Otherwise the return value will be less than or greater than 0 with
+ * respect to the operator.
+ */
+static short int
+inet_masklen_inclusion_cmp(inet *left, inet *right, short int opr_order)
+{
+ if (ip_family(left) == ip_family(right))
+ {
+ short int order;
+
+ order = ip_bits(left) - ip_bits(right);
+
+ if ((order > 0 && opr_order >= 0) ||
+ (order == 0 && opr_order >= -1 && opr_order <= 1) ||
+ (order < 0 && opr_order <= 0))
+ return 0;
+
+ return opr_order;
+ }
+
+ return ip_family(left) - ip_family(right);
+}
+
+/*
+ * Inet histogram partial match divider calculation
+ *
+ * First the families and the lenghts of the network parts are compared
+ * using the subnet inclusion operator. The divider will be calculated
+ * using the masklens and the common bits of the addresses. -1 will be
+ * returned if it cannot be calculated.
+ */
+static short int
+inet_his_match_divider(inet *boundary, inet *query, short int opr_order)
+{
+ if (inet_masklen_inclusion_cmp(boundary, query, opr_order) == 0)
+ {
+ short int min_bits,
+ decisive_bits;
+
+ min_bits = Min(ip_bits(boundary), ip_bits(query));
+
+ /*
+ * Set the decisive bits from the one which should contain the
other
+ * according to the operator.
+ */
+ if (opr_order < 0)
+ decisive_bits = ip_bits(boundary);
+ else if (opr_order > 0)
+ decisive_bits = ip_bits(query);
+ else
+ decisive_bits = min_bits;
+
+ if (min_bits > 0)
+ return decisive_bits - bitncommon(ip_addr(boundary),
ip_addr(query),
+
min_bits);
+ return decisive_bits;
+ }
+
+ return -1;
}
diff --git a/src/include/catalog/pg_operator.h
b/src/include/catalog/pg_operator.h
index f8b4a65..fb37337 100644
--- a/src/include/catalog/pg_operator.h
+++ b/src/include/catalog/pg_operator.h
@@ -1135,32 +1135,33 @@ DESCR("not equal");
DATA(insert OID = 1203 ( "<" PGNSP PGUID b f f 869 869 16 1205 1206
network_lt scalarltsel scalarltjoinsel ));
DESCR("less than");
DATA(insert OID = 1204 ( "<=" PGNSP PGUID b f f 869 869 16 1206 1205
network_le scalarltsel scalarltjoinsel ));
DESCR("less than or equal");
DATA(insert OID = 1205 ( ">" PGNSP PGUID b f f 869 869 16 1203 1204
network_gt scalargtsel scalargtjoinsel ));
DESCR("greater than");
DATA(insert OID = 1206 ( ">=" PGNSP PGUID b f f 869 869 16 1204 1203
network_ge scalargtsel scalargtjoinsel ));
DESCR("greater than or equal");
DATA(insert OID = 931 ( "<<" PGNSP PGUID b f f 869 869 16 933
0 network_sub networksel networkjoinsel ));
DESCR("is subnet");
-#define OID_INET_SUB_OP 931
+#define OID_INET_SUB_OP 931
DATA(insert OID = 932 ( "<<=" PGNSP PGUID b f f 869 869 16 934
0 network_subeq networksel networkjoinsel ));
DESCR("is subnet or equal");
-#define OID_INET_SUBEQ_OP 932
+#define OID_INET_SUBEQ_OP 932
DATA(insert OID = 933 ( ">>" PGNSP PGUID b f f 869 869 16 931
0 network_sup networksel networkjoinsel ));
DESCR("is supernet");
-#define OID_INET_SUP_OP 933
+#define OID_INET_SUP_OP 933
DATA(insert OID = 934 ( ">>=" PGNSP PGUID b f f 869 869 16 932
0 network_supeq networksel networkjoinsel ));
DESCR("is supernet or equal");
-#define OID_INET_SUPEQ_OP 934
+#define OID_INET_SUPEQ_OP 934
DATA(insert OID = 3552 ( "&&" PGNSP PGUID b f f 869 869 16 3552
0 network_overlap networksel networkjoinsel ));
DESCR("overlaps (is subnet or supernet)");
+#define OID_INET_OVERLAP_OP 3552
DATA(insert OID = 2634 ( "~" PGNSP PGUID l f f 0 869 869 0 0 inetnot
- - ));
DESCR("bitwise not");
DATA(insert OID = 2635 ( "&" PGNSP PGUID b f f 869 869 869 0 0 inetand
- - ));
DESCR("bitwise and");
DATA(insert OID = 2636 ( "|" PGNSP PGUID b f f 869 869 869 0 0 inetor
- - ));
DESCR("bitwise or");
DATA(insert OID = 2637 ( "+" PGNSP PGUID b f f 869 20 869 2638 0
inetpl - - ));
DESCR("add");
DATA(insert OID = 2638 ( "+" PGNSP PGUID b f f 20 869 869 2637 0
int8pl_inet - - ));
--
Sent via pgsql-hackers mailing list (pgsql-hackers@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-hackers
