postgresql/src/backend/statistics/extended_stats.c

517 lines
13 KiB
C
Raw Normal View History

Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
/*-------------------------------------------------------------------------
*
* extended_stats.c
* POSTGRES extended statistics
*
* Generic code supporting statistics objects created via CREATE STATISTICS.
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
*
*
* Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
* src/backend/statistics/extended_stats.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "access/genam.h"
#include "access/heapam.h"
#include "access/htup_details.h"
#include "catalog/indexing.h"
#include "catalog/pg_collation.h"
#include "catalog/pg_statistic_ext.h"
#include "nodes/relation.h"
#include "postmaster/autovacuum.h"
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
#include "statistics/extended_stats_internal.h"
#include "statistics/statistics.h"
#include "utils/builtins.h"
#include "utils/fmgroids.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
#include "utils/rel.h"
#include "utils/syscache.h"
/*
* Used internally to refer to an individual statistics object, i.e.,
* a pg_statistic_ext entry.
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
*/
typedef struct StatExtEntry
{
Oid statOid; /* OID of pg_statistic_ext entry */
char *schema; /* statistics object's schema */
char *name; /* statistics object's name */
Bitmapset *columns; /* attribute numbers covered by the object */
List *types; /* 'char' list of enabled statistic kinds */
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
} StatExtEntry;
static List *fetch_statentries_for_relation(Relation pg_statext, Oid relid);
static VacAttrStats **lookup_var_attr_stats(Relation rel, Bitmapset *attrs,
int nvacatts, VacAttrStats **vacatts);
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
static void statext_store(Relation pg_stext, Oid relid,
MVNDistinct *ndistinct, MVDependencies *dependencies,
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
VacAttrStats **stats);
/*
* Compute requested extended stats, using the rows sampled for the plain
* (single-column) stats.
*
* This fetches a list of stats types from pg_statistic_ext, computes the
* requested stats, and serializes them back into the catalog.
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
*/
void
BuildRelationExtStatistics(Relation onerel, double totalrows,
int numrows, HeapTuple *rows,
int natts, VacAttrStats **vacattrstats)
{
Relation pg_stext;
ListCell *lc;
List *stats;
MemoryContext cxt;
MemoryContext oldcxt;
Allow memory contexts to have both fixed and variable ident strings. Originally, we treated memory context names as potentially variable in all cases, and therefore always copied them into the context header. Commit 9fa6f00b1 rethought this a little bit and invented a distinction between fixed and variable names, skipping the copy step for the former. But we can make things both simpler and more useful by instead allowing there to be two parts to a context's identification, a fixed "name" and an optional, variable "ident". The name supplied in the context create call is now required to be a compile-time-constant string in all cases, as it is never copied but just pointed to. The "ident" string, if wanted, is supplied later. This is needed because typically we want the ident to be stored inside the context so that it's cleaned up automatically on context deletion; that means it has to be copied into the context before we can set the pointer. The cost of this approach is basically just an additional pointer field in struct MemoryContextData, which isn't much overhead, and is bought back entirely in the AllocSet case by not needing a headerSize field anymore, since we no longer have to cope with variable header length. In addition, we can simplify the internal interfaces for memory context creation still further, saving a few cycles there. And it's no longer true that a custom identifier disqualifies a context from participating in aset.c's freelist scheme, so possibly there's some win on that end. All the places that were using non-compile-time-constant context names are adjusted to put the variable info into the "ident" instead. This allows more effective identification of those contexts in many cases; for example, subsidary contexts of relcache entries are now identified by both type (e.g. "index info") and relname, where before you got only one or the other. Contexts associated with PL function cache entries are now identified more fully and uniformly, too. I also arranged for plancache contexts to use the query source string as their identifier. This is basically free for CachedPlanSources, as they contained a copy of that string already. We pay an extra pstrdup to do it for CachedPlans. That could perhaps be avoided, but it would make things more fragile (since the CachedPlanSource is sometimes destroyed first). I suspect future improvements in error reporting will require CachedPlans to have a copy of that string anyway, so it's not clear that it's worth moving mountains to avoid it now. This also changes the APIs for context statistics routines so that the context-specific routines no longer assume that output goes straight to stderr, nor do they know all details of the output format. This is useful immediately to reduce code duplication, and it also allows for external code to do something with stats output that's different from printing to stderr. The reason for pushing this now rather than waiting for v12 is that it rethinks some of the API changes made by commit 9fa6f00b1. Seems better for extension authors to endure just one round of API changes not two. Discussion: https://postgr.es/m/CAB=Je-FdtmFZ9y9REHD7VsSrnCkiBhsA4mdsLKSPauwXtQBeNA@mail.gmail.com
2018-03-27 22:46:47 +02:00
cxt = AllocSetContextCreate(CurrentMemoryContext,
"BuildRelationExtStatistics",
ALLOCSET_DEFAULT_SIZES);
oldcxt = MemoryContextSwitchTo(cxt);
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
pg_stext = heap_open(StatisticExtRelationId, RowExclusiveLock);
stats = fetch_statentries_for_relation(pg_stext, RelationGetRelid(onerel));
foreach(lc, stats)
{
StatExtEntry *stat = (StatExtEntry *) lfirst(lc);
MVNDistinct *ndistinct = NULL;
MVDependencies *dependencies = NULL;
VacAttrStats **stats;
ListCell *lc2;
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
/*
* Check if we can build these stats based on the column analyzed. If
* not, report this fact (except in autovacuum) and move on.
*/
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
stats = lookup_var_attr_stats(onerel, stat->columns,
natts, vacattrstats);
if (!stats)
{
if (!IsAutoVacuumWorkerProcess())
ereport(WARNING,
(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
errmsg("statistics object \"%s.%s\" could not be computed for relation \"%s.%s\"",
stat->schema, stat->name,
get_namespace_name(onerel->rd_rel->relnamespace),
RelationGetRelationName(onerel)),
errtable(onerel)));
continue;
}
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
/* check allowed number of dimensions */
Assert(bms_num_members(stat->columns) >= 2 &&
bms_num_members(stat->columns) <= STATS_MAX_DIMENSIONS);
/* compute statistic of each requested type */
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
foreach(lc2, stat->types)
{
char t = (char) lfirst_int(lc2);
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
if (t == STATS_EXT_NDISTINCT)
ndistinct = statext_ndistinct_build(totalrows, numrows, rows,
stat->columns, stats);
else if (t == STATS_EXT_DEPENDENCIES)
dependencies = statext_dependencies_build(numrows, rows,
stat->columns, stats);
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
}
/* store the statistics in the catalog */
statext_store(pg_stext, stat->statOid, ndistinct, dependencies, stats);
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
}
heap_close(pg_stext, RowExclusiveLock);
MemoryContextSwitchTo(oldcxt);
MemoryContextDelete(cxt);
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
}
/*
* statext_is_kind_built
* Is this stat kind built in the given pg_statistic_ext tuple?
*/
bool
statext_is_kind_built(HeapTuple htup, char type)
{
AttrNumber attnum;
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
switch (type)
{
case STATS_EXT_NDISTINCT:
attnum = Anum_pg_statistic_ext_stxndistinct;
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
break;
case STATS_EXT_DEPENDENCIES:
attnum = Anum_pg_statistic_ext_stxdependencies;
break;
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
default:
elog(ERROR, "unexpected statistics type requested: %d", type);
}
return !heap_attisnull(htup, attnum, NULL);
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
}
/*
* Return a list (of StatExtEntry) of statistics objects for the given relation.
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
*/
static List *
fetch_statentries_for_relation(Relation pg_statext, Oid relid)
{
SysScanDesc scan;
ScanKeyData skey;
HeapTuple htup;
List *result = NIL;
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
/*
* Prepare to scan pg_statistic_ext for entries having stxrelid = this
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
* rel.
*/
ScanKeyInit(&skey,
Anum_pg_statistic_ext_stxrelid,
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
BTEqualStrategyNumber, F_OIDEQ,
ObjectIdGetDatum(relid));
scan = systable_beginscan(pg_statext, StatisticExtRelidIndexId, true,
NULL, 1, &skey);
while (HeapTupleIsValid(htup = systable_getnext(scan)))
{
StatExtEntry *entry;
Datum datum;
bool isnull;
int i;
ArrayType *arr;
char *enabled;
Form_pg_statistic_ext staForm;
entry = palloc0(sizeof(StatExtEntry));
staForm = (Form_pg_statistic_ext) GETSTRUCT(htup);
Remove WITH OIDS support, change oid catalog column visibility. Previously tables declared WITH OIDS, including a significant fraction of the catalog tables, stored the oid column not as a normal column, but as part of the tuple header. This special column was not shown by default, which was somewhat odd, as it's often (consider e.g. pg_class.oid) one of the more important parts of a row. Neither pg_dump nor COPY included the contents of the oid column by default. The fact that the oid column was not an ordinary column necessitated a significant amount of special case code to support oid columns. That already was painful for the existing, but upcoming work aiming to make table storage pluggable, would have required expanding and duplicating that "specialness" significantly. WITH OIDS has been deprecated since 2005 (commit ff02d0a05280e0). Remove it. Removing includes: - CREATE TABLE and ALTER TABLE syntax for declaring the table to be WITH OIDS has been removed (WITH (oids[ = true]) will error out) - pg_dump does not support dumping tables declared WITH OIDS and will issue a warning when dumping one (and ignore the oid column). - restoring an pg_dump archive with pg_restore will warn when restoring a table with oid contents (and ignore the oid column) - COPY will refuse to load binary dump that includes oids. - pg_upgrade will error out when encountering tables declared WITH OIDS, they have to be altered to remove the oid column first. - Functionality to access the oid of the last inserted row (like plpgsql's RESULT_OID, spi's SPI_lastoid, ...) has been removed. The syntax for declaring a table WITHOUT OIDS (or WITH (oids = false) for CREATE TABLE) is still supported. While that requires a bit of support code, it seems unnecessary to break applications / dumps that do not use oids, and are explicit about not using them. The biggest user of WITH OID columns was postgres' catalog. This commit changes all 'magic' oid columns to be columns that are normally declared and stored. To reduce unnecessary query breakage all the newly added columns are still named 'oid', even if a table's column naming scheme would indicate 'reloid' or such. This obviously requires adapting a lot code, mostly replacing oid access via HeapTupleGetOid() with access to the underlying Form_pg_*->oid column. The bootstrap process now assigns oids for all oid columns in genbki.pl that do not have an explicit value (starting at the largest oid previously used), only oids assigned later by oids will be above FirstBootstrapObjectId. As the oid column now is a normal column the special bootstrap syntax for oids has been removed. Oids are not automatically assigned during insertion anymore, all backend code explicitly assigns oids with GetNewOidWithIndex(). For the rare case that insertions into the catalog via SQL are called for the new pg_nextoid() function can be used (which only works on catalog tables). The fact that oid columns on system tables are now normal columns means that they will be included in the set of columns expanded by * (i.e. SELECT * FROM pg_class will now include the table's oid, previously it did not). It'd not technically be hard to hide oid column by default, but that'd mean confusing behavior would either have to be carried forward forever, or it'd cause breakage down the line. While it's not unlikely that further adjustments are needed, the scope/invasiveness of the patch makes it worthwhile to get merge this now. It's painful to maintain externally, too complicated to commit after the code code freeze, and a dependency of a number of other patches. Catversion bump, for obvious reasons. Author: Andres Freund, with contributions by John Naylor Discussion: https://postgr.es/m/20180930034810.ywp2c7awz7opzcfr@alap3.anarazel.de
2018-11-21 00:36:57 +01:00
entry->statOid = staForm->oid;
entry->schema = get_namespace_name(staForm->stxnamespace);
entry->name = pstrdup(NameStr(staForm->stxname));
for (i = 0; i < staForm->stxkeys.dim1; i++)
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
{
entry->columns = bms_add_member(entry->columns,
staForm->stxkeys.values[i]);
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
}
/* decode the stxkind char array into a list of chars */
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
datum = SysCacheGetAttr(STATEXTOID, htup,
Anum_pg_statistic_ext_stxkind, &isnull);
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
Assert(!isnull);
arr = DatumGetArrayTypeP(datum);
if (ARR_NDIM(arr) != 1 ||
ARR_HASNULL(arr) ||
ARR_ELEMTYPE(arr) != CHAROID)
elog(ERROR, "stxkind is not a 1-D char array");
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
enabled = (char *) ARR_DATA_PTR(arr);
for (i = 0; i < ARR_DIMS(arr)[0]; i++)
{
Assert((enabled[i] == STATS_EXT_NDISTINCT) ||
(enabled[i] == STATS_EXT_DEPENDENCIES));
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
entry->types = lappend_int(entry->types, (int) enabled[i]);
}
result = lappend(result, entry);
}
systable_endscan(scan);
return result;
}
/*
* Using 'vacatts' of size 'nvacatts' as input data, return a newly built
* VacAttrStats array which includes only the items corresponding to
* attributes indicated by 'stxkeys'. If we don't have all of the per column
* stats available to compute the extended stats, then we return NULL to indicate
* to the caller that the stats should not be built.
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
*/
static VacAttrStats **
lookup_var_attr_stats(Relation rel, Bitmapset *attrs,
int nvacatts, VacAttrStats **vacatts)
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
{
int i = 0;
int x = -1;
VacAttrStats **stats;
stats = (VacAttrStats **)
palloc(bms_num_members(attrs) * sizeof(VacAttrStats *));
/* lookup VacAttrStats info for the requested columns (same attnum) */
while ((x = bms_next_member(attrs, x)) >= 0)
{
int j;
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
stats[i] = NULL;
for (j = 0; j < nvacatts; j++)
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
{
if (x == vacatts[j]->tupattnum)
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
{
stats[i] = vacatts[j];
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
break;
}
}
if (!stats[i])
{
/*
* Looks like stats were not gathered for one of the columns
* required. We'll be unable to build the extended stats without
* this column.
*/
pfree(stats);
return NULL;
}
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
/*
* Sanity check that the column is not dropped - stats should have
* been removed in this case.
*/
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
Assert(!stats[i]->attr->attisdropped);
i++;
}
return stats;
}
/*
* statext_store
* Serializes the statistics and stores them into the pg_statistic_ext tuple.
*/
static void
statext_store(Relation pg_stext, Oid statOid,
MVNDistinct *ndistinct, MVDependencies *dependencies,
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
VacAttrStats **stats)
{
HeapTuple stup,
oldtup;
Datum values[Natts_pg_statistic_ext];
bool nulls[Natts_pg_statistic_ext];
bool replaces[Natts_pg_statistic_ext];
memset(nulls, true, sizeof(nulls));
memset(replaces, false, sizeof(replaces));
memset(values, 0, sizeof(values));
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
/*
* Construct a new pg_statistic_ext tuple, replacing the calculated stats.
*/
if (ndistinct != NULL)
{
bytea *data = statext_ndistinct_serialize(ndistinct);
nulls[Anum_pg_statistic_ext_stxndistinct - 1] = (data == NULL);
values[Anum_pg_statistic_ext_stxndistinct - 1] = PointerGetDatum(data);
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
}
if (dependencies != NULL)
{
bytea *data = statext_dependencies_serialize(dependencies);
nulls[Anum_pg_statistic_ext_stxdependencies - 1] = (data == NULL);
values[Anum_pg_statistic_ext_stxdependencies - 1] = PointerGetDatum(data);
}
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
/* always replace the value (either by bytea or NULL) */
replaces[Anum_pg_statistic_ext_stxndistinct - 1] = true;
replaces[Anum_pg_statistic_ext_stxdependencies - 1] = true;
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
/* there should already be a pg_statistic_ext tuple */
oldtup = SearchSysCache1(STATEXTOID, ObjectIdGetDatum(statOid));
if (!HeapTupleIsValid(oldtup))
elog(ERROR, "cache lookup failed for statistics object %u", statOid);
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
/* replace it */
stup = heap_modify_tuple(oldtup,
RelationGetDescr(pg_stext),
values,
nulls,
replaces);
ReleaseSysCache(oldtup);
CatalogTupleUpdate(pg_stext, &stup->t_self, stup);
heap_freetuple(stup);
}
/* initialize multi-dimensional sort */
MultiSortSupport
multi_sort_init(int ndims)
{
MultiSortSupport mss;
Assert(ndims >= 2);
mss = (MultiSortSupport) palloc0(offsetof(MultiSortSupportData, ssup)
2017-06-21 20:39:04 +02:00
+ sizeof(SortSupportData) * ndims);
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
mss->ndims = ndims;
return mss;
}
/*
* Prepare sort support info using the given sort operator
* at the position 'sortdim'
*/
void
multi_sort_add_dimension(MultiSortSupport mss, int sortdim, Oid oper)
{
SortSupport ssup = &mss->ssup[sortdim];
Implement multivariate n-distinct coefficients Add support for explicitly declared statistic objects (CREATE STATISTICS), allowing collection of statistics on more complex combinations that individual table columns. Companion commands DROP STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are added too. All this DDL has been designed so that more statistic types can be added later on, such as multivariate most-common-values and multivariate histograms between columns of a single table, leaving room for permitting columns on multiple tables, too, as well as expressions. This commit only adds support for collection of n-distinct coefficient on user-specified sets of columns in a single table. This is useful to estimate number of distinct groups in GROUP BY and DISTINCT clauses; estimation errors there can cause over-allocation of memory in hashed aggregates, for instance, so it's a worthwhile problem to solve. A new special pseudo-type pg_ndistinct is used. (num-distinct estimation was deemed sufficiently useful by itself that this is worthwhile even if no further statistic types are added immediately; so much so that another version of essentially the same functionality was submitted by Kyotaro Horiguchi: https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp though this commit does not use that code.) Author: Tomas Vondra. Some code rework by Álvaro. Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes, Ideriha Takeshi Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
2017-03-24 18:06:10 +01:00
ssup->ssup_cxt = CurrentMemoryContext;
ssup->ssup_collation = DEFAULT_COLLATION_OID;
ssup->ssup_nulls_first = false;
ssup->ssup_cxt = CurrentMemoryContext;
PrepareSortSupportFromOrderingOp(oper, ssup);
}
/* compare all the dimensions in the selected order */
int
multi_sort_compare(const void *a, const void *b, void *arg)
{
MultiSortSupport mss = (MultiSortSupport) arg;
SortItem *ia = (SortItem *) a;
SortItem *ib = (SortItem *) b;
int i;
for (i = 0; i < mss->ndims; i++)
{
int compare;
compare = ApplySortComparator(ia->values[i], ia->isnull[i],
ib->values[i], ib->isnull[i],
&mss->ssup[i]);
if (compare != 0)
return compare;
}
/* equal by default */
return 0;
}
/* compare selected dimension */
int
multi_sort_compare_dim(int dim, const SortItem *a, const SortItem *b,
MultiSortSupport mss)
{
return ApplySortComparator(a->values[dim], a->isnull[dim],
b->values[dim], b->isnull[dim],
&mss->ssup[dim]);
}
int
multi_sort_compare_dims(int start, int end,
const SortItem *a, const SortItem *b,
MultiSortSupport mss)
{
int dim;
for (dim = start; dim <= end; dim++)
{
int r = ApplySortComparator(a->values[dim], a->isnull[dim],
b->values[dim], b->isnull[dim],
&mss->ssup[dim]);
if (r != 0)
return r;
}
return 0;
}
/*
* has_stats_of_kind
* Check whether the list contains statistic of a given kind
*/
bool
has_stats_of_kind(List *stats, char requiredkind)
{
ListCell *l;
foreach(l, stats)
{
StatisticExtInfo *stat = (StatisticExtInfo *) lfirst(l);
if (stat->kind == requiredkind)
return true;
}
return false;
}
/*
* choose_best_statistics
* Look for and return statistics with the specified 'requiredkind' which
* have keys that match at least two of the given attnums. Return NULL if
* there's no match.
*
* The current selection criteria is very simple - we choose the statistics
* object referencing the most of the requested attributes, breaking ties
* in favor of objects with fewer keys overall.
*
* XXX if multiple statistics objects tie on both criteria, then which object
* is chosen depends on the order that they appear in the stats list. Perhaps
* further tiebreakers are needed.
*/
StatisticExtInfo *
choose_best_statistics(List *stats, Bitmapset *attnums, char requiredkind)
{
ListCell *lc;
StatisticExtInfo *best_match = NULL;
int best_num_matched = 2; /* goal #1: maximize */
int best_match_keys = (STATS_MAX_DIMENSIONS + 1); /* goal #2: minimize */
foreach(lc, stats)
{
StatisticExtInfo *info = (StatisticExtInfo *) lfirst(lc);
int num_matched;
int numkeys;
Bitmapset *matched;
/* skip statistics that are not of the correct type */
if (info->kind != requiredkind)
continue;
/* determine how many attributes of these stats can be matched to */
matched = bms_intersect(attnums, info->keys);
num_matched = bms_num_members(matched);
bms_free(matched);
/*
* save the actual number of keys in the stats so that we can choose
* the narrowest stats with the most matching keys.
*/
numkeys = bms_num_members(info->keys);
/*
* Use this object when it increases the number of matched clauses or
* when it matches the same number of attributes but these stats have
* fewer keys than any previous match.
*/
if (num_matched > best_num_matched ||
(num_matched == best_num_matched && numkeys < best_match_keys))
{
best_match = info;
best_num_matched = num_matched;
best_match_keys = numkeys;
}
}
return best_match;
}