Loading...
Searching...
No Matches
gserialized_estimate.c File Reference
#include "postgres.h"#include "access/genam.h"#include "access/gin.h"#include "access/gist.h"#include "access/gist_private.h"#include "access/gistscan.h"#include "access/detoast.h"#include "utils/datum.h"#include "access/heapam.h"#include "catalog/index.h"#include "catalog/pg_am.h"#include "miscadmin.h"#include "storage/lmgr.h"#include "catalog/namespace.h"#include "catalog/indexing.h"#include "utils/regproc.h"#include "utils/varlena.h"#include "utils/builtins.h"#include "utils/snapmgr.h"#include "utils/fmgroids.h"#include "funcapi.h"#include "catalog/pg_type.h"#include "access/relscan.h"#include "executor/spi.h"#include "fmgr.h"#include "commands/vacuum.h"#include "nodes/pathnodes.h"#include "parser/parsetree.h"#include "utils/array.h"#include "utils/lsyscache.h"#include "utils/syscache.h"#include "utils/rel.h"#include "utils/selfuncs.h"#include "../postgis_config.h"#include "access/htup_details.h"#include "stringbuffer.h"#include "liblwgeom.h"#include "lwgeodetic.h"#include "lwgeom_pg.h"#include "gserialized_gist.h"#include "gserialized_estimate_support.h"#include <math.h>#include <limits.h>#include <float.h>#include <string.h>#include <stdio.h>#include <ctype.h>
Include dependency graph for gserialized_estimate.c:
Go to the source code of this file.
Data Structures | |
| struct | GserializedAnalyzeExtraData |
Macros | |
| #define | STATISTIC_KIND_ND 102 |
| #define | STATISTIC_KIND_2D 103 |
| #define | STATISTIC_SLOT_ND 3 |
| #define | STATISTIC_SLOT_2D 4 |
| #define | SDFACTOR 3.25 |
| #define | MIN_DIMENSION_WIDTH 0.000000001 |
| Minimum width of a dimension that we'll bother trying to compute statistics on. | |
| #define | MAX_DIMENSION_WIDTH 1.0E+20 |
| Maximum width of a dimension that we'll bother trying to compute statistics on. | |
| #define | DEFAULT_ND_SEL 0.0001 |
| Default geometry selectivity factor. | |
| #define | DEFAULT_ND_JOINSEL 0.001 |
| #define | FALLBACK_ND_SEL 0.2 |
| More modest fallback selectivity factor. | |
| #define | FALLBACK_ND_JOINSEL 0.3 |
| #define | MAX_NUM_BINS 50 |
| #define | BIN_MIN_SIZE 10 |
Functions | |
| Datum | gserialized_gist_joinsel (PG_FUNCTION_ARGS) |
| Datum | gserialized_gist_joinsel_2d (PG_FUNCTION_ARGS) |
| Datum | gserialized_gist_joinsel_nd (PG_FUNCTION_ARGS) |
| Datum | gserialized_gist_sel (PG_FUNCTION_ARGS) |
| Datum | gserialized_gist_sel_2d (PG_FUNCTION_ARGS) |
| Datum | gserialized_gist_sel_nd (PG_FUNCTION_ARGS) |
| Datum | gserialized_analyze_nd (PG_FUNCTION_ARGS) |
| Datum | gserialized_estimated_extent (PG_FUNCTION_ARGS) |
| Datum | _postgis_gserialized_index_extent (PG_FUNCTION_ARGS) |
| Datum | _postgis_gserialized_sel (PG_FUNCTION_ARGS) |
| Datum | _postgis_gserialized_joinsel (PG_FUNCTION_ARGS) |
| Datum | _postgis_gserialized_stats (PG_FUNCTION_ARGS) |
| static Oid | table_get_spatial_index (Oid tbl_oid, int16 attnum, int *key_type, int16 *idx_attnum) |
| static GBOX * | spatial_index_read_extent (Oid idx_oid, int idx_att_num, int key_type) |
| float8 | gserialized_joinsel_internal (PlannerInfo *root, List *args, JoinType jointype, int mode) |
| float8 | gserialized_sel_internal (PlannerInfo *root, List *args, int varRelid, int mode) |
| This function should return an estimation of the number of rows returned by a query involving an overlap check ( it's the restrict function for the && operator ) | |
| Datum | geometry_estimated_extent (PG_FUNCTION_ARGS) |
| static int | gbox_ndims (const GBOX *gbox) |
| Given that geodetic boxes are X/Y/Z regardless of the underlying geometry dimensionality and other boxes are guided by HAS_Z/HAS_M in their dimensionality, we have a little utility function to make it easy. | |
| static int | text_p_get_mode (const text *txt) |
| Utility function to see if the first letter of the mode argument is 'N'. | |
| static int | cmp_int (const void *a, const void *b) |
| Integer comparison function for qsort. | |
| static int | range_full (int *vals, int nvals) |
| The difference between the fourth and first quintile values, the "inter-quintile range". | |
| static double | total_double (const double *vals, int nvals) |
| Given double array, return sum of values. | |
| static char * | nd_box_to_json (const ND_BOX *nd_box, int ndims) |
| Convert an ND_BOX to a JSON string for printing. | |
| static char * | nd_stats_to_json (const ND_STATS *nd_stats) |
| Convert an ND_STATS to a JSON representation for external use. | |
| static char * | nd_stats_to_grid (const ND_STATS *stats) |
| Create a printable view of the ND_STATS histogram. | |
| static int | nd_box_merge (const ND_BOX *source, ND_BOX *target) |
| Expand the bounds of target to include source. | |
| static int | nd_box_init (ND_BOX *a) |
| Zero out an ND_BOX. | |
| static int | nd_box_init_bounds (ND_BOX *a) |
| Prepare an ND_BOX for bounds calculation: set the maxes to the smallest thing possible and the mins to the largest. | |
| static void | nd_box_from_gbox (const GBOX *gbox, ND_BOX *nd_box) |
| Set the values of an ND_BOX from a GBOX. | |
| static int | nd_box_intersects (const ND_BOX *a, const ND_BOX *b, int ndims) |
| Return true if ND_BOX a overlaps b, false otherwise. | |
| static int | nd_box_contains (const ND_BOX *a, const ND_BOX *b, int ndims) |
| Return true if ND_BOX a contains b, false otherwise. | |
| static int | nd_box_expand (ND_BOX *nd_box, double expansion_factor) |
| Expand an ND_BOX ever so slightly. | |
| static int | nd_box_overlap (const ND_STATS *nd_stats, const ND_BOX *nd_box, ND_IBOX *nd_ibox) |
| What stats cells overlap with this ND_BOX? Put the lowest cell addresses in ND_IBOX->min and the highest in ND_IBOX->max. | |
| static int | nd_box_array_distribution (const ND_BOX **nd_boxes, int num_boxes, const ND_BOX *extent, int ndims, double *distribution) |
| Calculate how much a set of boxes is homogeneously distributed or contentrated within one dimension, returning the range_quintile of of the overlap counts per cell in a uniform partition of the extent of the dimension. | |
| static int | nd_increment (ND_IBOX *ibox, int ndims, int *counter) |
| Given an n-d index array (counter), and a domain to increment it in (ibox) increment it by one, unless it's already at the max of the domain, in which case return false. | |
| static ND_STATS * | pg_nd_stats_from_tuple (HeapTuple stats_tuple, int mode) |
| static ND_STATS * | pg_get_nd_stats (const Oid table_oid, AttrNumber att_num, int mode, bool only_parent) |
| Pull the stats object from the PgSQL system catalogs. | |
| static ND_STATS * | pg_get_nd_stats_by_name (const Oid table_oid, const text *att_text, int mode, bool only_parent) |
| Pull the stats object from the PgSQL system catalogs. | |
| static float8 | estimate_join_selectivity (const ND_STATS *s1, const ND_STATS *s2) |
| Given two statistics histograms, what is the selectivity of a join driven by the && or &&& operator? | |
| PG_FUNCTION_INFO_V1 (gserialized_gist_joinsel_nd) | |
| For (geometry &&& geometry) and (geography && geography) we call into the N-D mode. | |
| PG_FUNCTION_INFO_V1 (gserialized_gist_joinsel_2d) | |
| For (geometry && geometry) we call into the 2-D mode. | |
| PG_FUNCTION_INFO_V1 (gserialized_gist_joinsel) | |
| Join selectivity of the && operator. | |
| static void | compute_gserialized_stats_mode (VacAttrStats *stats, AnalyzeAttrFetchFunc fetchfunc, int sample_rows, double total_rows, int mode) |
| The gserialized_analyze_nd sets this function as a callback on the stats object when called by the ANALYZE command. | |
| static void | compute_gserialized_stats (VacAttrStats *stats, AnalyzeAttrFetchFunc fetchfunc, int sample_rows, double total_rows) |
| In order to do useful selectivity calculations in both 2-D and N-D modes, we actually have to generate two stats objects, one for 2-D and one for N-D. | |
| PG_FUNCTION_INFO_V1 (gserialized_analyze_nd) | |
| This function will be called when the ANALYZE command is run on a column of the "geometry" or "geography" type. | |
| static float8 | estimate_selectivity (const GBOX *box, const ND_STATS *nd_stats, int mode) |
| This function returns an estimate of the selectivity of a search GBOX by looking at data in the ND_STATS structure. | |
| PG_FUNCTION_INFO_V1 (_postgis_gserialized_stats) | |
| Utility function to print the statistics information for a given table/column in JSON. | |
| PG_FUNCTION_INFO_V1 (_postgis_gserialized_sel) | |
| Utility function to read the calculated selectivity for a given search box and table/column. | |
| PG_FUNCTION_INFO_V1 (_postgis_gserialized_joinsel) | |
| Utility function to read the calculated join selectivity for a pair of tables. | |
| PG_FUNCTION_INFO_V1 (gserialized_gist_sel_2d) | |
| For (geometry && geometry) we call into the 2-D mode. | |
| PG_FUNCTION_INFO_V1 (gserialized_gist_sel_nd) | |
| For (geometry &&& geometry) and (geography && geography) we call into the N-D mode. | |
| PG_FUNCTION_INFO_V1 (gserialized_gist_sel) | |
| static int16 | index_has_attr (Oid index_oid, Oid table_oid, int16 table_attnum) |
| static int | index_get_am (Oid index_oid) |
| static int | index_get_keytype (Oid index_oid, int16 index_attnum) |
| PG_FUNCTION_INFO_V1 (_postgis_gserialized_index_extent) | |
| static bool | get_attnum_attypid (Oid table_oid, const char *col, int16 *attnum, Oid *atttypid) |
| PG_FUNCTION_INFO_V1 (gserialized_estimated_extent) | |
| Return the estimated extent of the table looking at gathered statistics (or NULL if no statistics have been gathered). | |
| PG_FUNCTION_INFO_V1 (geometry_estimated_extent) | |
